diff options
Diffstat (limited to 'tools/perf/util')
72 files changed, 5348 insertions, 1956 deletions
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e01af2b1a469..011ed2676604 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -16,6 +16,8 @@ #include "annotate.h" #include <pthread.h> +const char *disassembler_style; + int symbol__annotate_init(struct map *map __used, struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); @@ -23,17 +25,17 @@ int symbol__annotate_init(struct map *map __used, struct symbol *sym) return 0; } -int symbol__alloc_hist(struct symbol *sym, int nevents) +int symbol__alloc_hist(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); size_t sizeof_sym_hist = (sizeof(struct sym_hist) + (sym->end - sym->start) * sizeof(u64)); - notes->src = zalloc(sizeof(*notes->src) + nevents * sizeof_sym_hist); + notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist); if (notes->src == NULL) return -1; notes->src->sizeof_sym_hist = sizeof_sym_hist; - notes->src->nr_histograms = nevents; + notes->src->nr_histograms = symbol_conf.nr_events; INIT_LIST_HEAD(¬es->src->source); return 0; } @@ -308,9 +310,12 @@ fallback: } err = -ENOENT; dso->annotate_warned = 1; - pr_err("Can't annotate %s: No vmlinux file%s was found in the " - "path.\nPlease use 'perf buildid-cache -av vmlinux' or " - "--vmlinux vmlinux.\n", + pr_err("Can't annotate %s:\n\n" + "No vmlinux file%s\nwas found in the path.\n\n" + "Please use:\n\n" + " perf buildid-cache -av vmlinux\n\n" + "or:\n\n" + " --vmlinux vmlinux", sym->name, build_id_msg ?: ""); goto out_free_filename; } @@ -323,10 +328,15 @@ fallback: dso, dso->long_name, sym, sym->name); snprintf(command, sizeof(command), - "objdump --start-address=0x%016" PRIx64 - " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand", + "objdump %s%s --start-address=0x%016" PRIx64 + " --stop-address=0x%016" PRIx64 + " -d %s %s -C %s|grep -v %s|expand", + disassembler_style ? "-M " : "", + disassembler_style ? disassembler_style : "", map__rip_2objdump(map, sym->start), - map__rip_2objdump(map, sym->end), + map__rip_2objdump(map, sym->end+1), + symbol_conf.annotate_asm_raw ? "" : "--no-show-raw", + symbol_conf.annotate_src ? "-S" : "", symfs_filename, filename); pr_debug("Executing: %s\n", command); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index c2c286896801..efa5dc82bfae 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -72,7 +72,7 @@ static inline struct annotation *symbol__annotation(struct symbol *sym) int symbol__inc_addr_samples(struct symbol *sym, struct map *map, int evidx, u64 addr); -int symbol__alloc_hist(struct symbol *sym, int nevents); +int symbol__alloc_hist(struct symbol *sym); void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize); @@ -91,13 +91,17 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, #ifdef NO_NEWT_SUPPORT static inline int symbol__tui_annotate(struct symbol *sym __used, struct map *map __used, - int evidx __used, int refresh __used) + int evidx __used, + void(*timer)(void *arg) __used, + void *arg __used, int delay_secs __used) { return 0; } #else int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, - int refresh); + void(*timer)(void *arg), void *arg, int delay_secs); #endif +extern const char *disassembler_style; + #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index a91cd99f26ea..dff9c7a725f4 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -13,15 +13,18 @@ #include "symbol.h" #include <linux/kernel.h> #include "debug.h" +#include "session.h" +#include "tool.h" -static int build_id__mark_dso_hit(union perf_event *event, +static int build_id__mark_dso_hit(struct perf_tool *tool __used, + union perf_event *event, struct perf_sample *sample __used, struct perf_evsel *evsel __used, - struct perf_session *session) + struct machine *machine) { struct addr_location al; u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = perf_session__findnew(session, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, event->ip.pid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", @@ -29,8 +32,8 @@ static int build_id__mark_dso_hit(union perf_event *event, return -1; } - thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION, - event->ip.pid, event->ip.ip, &al); + thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, + event->ip.ip, &al); if (al.map != NULL) al.map->dso->hit = 1; @@ -38,25 +41,26 @@ static int build_id__mark_dso_hit(union perf_event *event, return 0; } -static int perf_event__exit_del_thread(union perf_event *event, +static int perf_event__exit_del_thread(struct perf_tool *tool __used, + union perf_event *event, struct perf_sample *sample __used, - struct perf_session *session) + struct machine *machine) { - struct thread *thread = perf_session__findnew(session, event->fork.tid); + struct thread *thread = machine__findnew_thread(machine, event->fork.tid); dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid, event->fork.ppid, event->fork.ptid); if (thread) { - rb_erase(&thread->rb_node, &session->threads); - session->last_match = NULL; + rb_erase(&thread->rb_node, &machine->threads); + machine->last_match = NULL; thread__delete(thread); } return 0; } -struct perf_event_ops build_id__mark_dso_hit_ops = { +struct perf_tool build_id__mark_dso_hit_ops = { .sample = build_id__mark_dso_hit, .mmap = perf_event__process_mmap, .fork = perf_event__process_task, diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 5dafb00eaa06..a993ba87d996 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -3,7 +3,7 @@ #include "session.h" -extern struct perf_event_ops build_id__mark_dso_hit_ops; +extern struct perf_tool build_id__mark_dso_hit_ops; char *dso__build_id_filename(struct dso *self, char *bf, size_t size); diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 9b4ff16cac96..7f9c0f1ae3a9 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -101,6 +101,9 @@ int callchain_append(struct callchain_root *root, int callchain_merge(struct callchain_cursor *cursor, struct callchain_root *dst, struct callchain_root *src); +struct ip_callchain; +union perf_event; + bool ip_callchain__valid(struct ip_callchain *chain, const union perf_event *event); /* diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 96bee5c46008..dbe2f16b1a1a 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -3,7 +3,6 @@ #include "parse-options.h" #include "evsel.h" #include "cgroup.h" -#include "debugfs.h" /* MAX_PATH, STR() */ #include "evlist.h" int nr_cgroups; @@ -12,7 +11,7 @@ static int cgroupfs_find_mountpoint(char *buf, size_t maxlen) { FILE *fp; - char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1]; + char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1]; char *token, *saved_ptr = NULL; int found = 0; @@ -25,8 +24,8 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) * and inspect every cgroupfs mount point to find one that has * perf_event subsystem */ - while (fscanf(fp, "%*s %"STR(MAX_PATH)"s %"STR(MAX_PATH)"s %" - STR(MAX_PATH)"s %*d %*d\n", + while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %" + STR(PATH_MAX)"s %*d %*d\n", mountpoint, type, tokens) == 3) { if (!strcmp(type, "cgroup")) { @@ -57,15 +56,15 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) static int open_cgroup(char *name) { - char path[MAX_PATH+1]; - char mnt[MAX_PATH+1]; + char path[PATH_MAX + 1]; + char mnt[PATH_MAX + 1]; int fd; - if (cgroupfs_find_mountpoint(mnt, MAX_PATH+1)) + if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1)) return -1; - snprintf(path, MAX_PATH, "%s/%s", mnt, name); + snprintf(path, PATH_MAX, "%s/%s", mnt, name); fd = open(path, O_RDONLY); if (fd == -1) diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index e191eb9a667f..521c38a79190 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -200,7 +200,7 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, * Auto-detect: */ if (perf_use_color_default < 0) { - if (isatty(1) || pager_in_use()) + if (isatty(fileno(fp)) || pager_in_use()) perf_use_color_default = 1; else perf_use_color_default = 0; diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index e02d78cae70f..0deac6a14b65 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -1,5 +1,8 @@ /* - * GIT - The information manager from hell + * config.c + * + * Helper functions for parsing config items. + * Originally copied from GIT source. * * Copyright (C) Linus Torvalds, 2005 * Copyright (C) Johannes Schindelin, 2005 @@ -341,7 +344,7 @@ const char *perf_config_dirname(const char *name, const char *value) static int perf_default_core_config(const char *var __used, const char *value __used) { - /* Add other config variables here and to Documentation/config.txt. */ + /* Add other config variables here. */ return 0; } @@ -350,7 +353,7 @@ int perf_default_config(const char *var, const char *value, void *dummy __used) if (!prefixcmp(var, "core.")) return perf_default_core_config(var, value); - /* Add other config variables here and to Documentation/config.txt. */ + /* Add other config variables here. */ return 0; } @@ -399,7 +402,6 @@ static int perf_config_global(void) int perf_config(config_fn_t fn, void *data) { int ret = 0, found = 0; - char *repo_config = NULL; const char *home = NULL; /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */ @@ -414,19 +416,32 @@ int perf_config(config_fn_t fn, void *data) home = getenv("HOME"); if (perf_config_global() && home) { char *user_config = strdup(mkpath("%s/.perfconfig", home)); - if (!access(user_config, R_OK)) { - ret += perf_config_from_file(fn, user_config, data); - found += 1; + struct stat st; + + if (user_config == NULL) { + warning("Not enough memory to process %s/.perfconfig, " + "ignoring it.", home); + goto out; } - free(user_config); - } - repo_config = perf_pathdup("config"); - if (!access(repo_config, R_OK)) { - ret += perf_config_from_file(fn, repo_config, data); + if (stat(user_config, &st) < 0) + goto out_free; + + if (st.st_uid && (st.st_uid != geteuid())) { + warning("File %s not owned by current user or root, " + "ignoring it.", user_config); + goto out_free; + } + + if (!st.st_size) + goto out_free; + + ret += perf_config_from_file(fn, user_config, data); found += 1; +out_free: + free(user_config); } - free(repo_config); +out: if (found == 0) return -1; return ret; diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 155749d74350..26817daa2961 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -47,19 +47,20 @@ int dump_printf(const char *fmt, ...) } #ifdef NO_NEWT_SUPPORT -void ui__warning(const char *format, ...) +int ui__warning(const char *format, ...) { va_list args; va_start(args, format); vfprintf(stderr, format, args); va_end(args); + return 0; } #endif -void ui__warning_paranoid(void) +int ui__error_paranoid(void) { - ui__warning("Permission error - are you root?\n" + return ui__error("Permission error - are you root?\n" "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n" " -1 - Not paranoid at all\n" " 0 - Disallow raw tracepoint access for unpriv\n" diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index fd53db47e3de..f2ce88d04f54 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -19,23 +19,18 @@ static inline int ui_helpline__show_help(const char *format __used, va_list ap _ return 0; } -static inline struct ui_progress *ui_progress__new(const char *title __used, - u64 total __used) -{ - return (struct ui_progress *)1; -} - -static inline void ui_progress__update(struct ui_progress *self __used, - u64 curr __used) {} +static inline void ui_progress__update(u64 curr __used, u64 total __used, + const char *title __used) {} -static inline void ui_progress__delete(struct ui_progress *self __used) {} +#define ui__error(format, arg...) ui__warning(format, ##arg) #else extern char ui_helpline__last_msg[]; int ui_helpline__show_help(const char *format, va_list ap); #include "ui/progress.h" +int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); #endif -void ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); -void ui__warning_paranoid(void); +int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); +int ui__error_paranoid(void); #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/debugfs.c b/tools/perf/util/debugfs.c index a88fefc0cc0a..ffc35e748e89 100644 --- a/tools/perf/util/debugfs.c +++ b/tools/perf/util/debugfs.c @@ -2,8 +2,12 @@ #include "debugfs.h" #include "cache.h" +#include <linux/kernel.h> +#include <sys/mount.h> + static int debugfs_premounted; -static char debugfs_mountpoint[MAX_PATH+1]; +char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug"; +char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events"; static const char *debugfs_known_mountpoints[] = { "/sys/kernel/debug/", @@ -62,11 +66,9 @@ const char *debugfs_find_mountpoint(void) /* give up and parse /proc/mounts */ fp = fopen("/proc/mounts", "r"); if (fp == NULL) - die("Can't open /proc/mounts for read"); + return NULL; - while (fscanf(fp, "%*s %" - STR(MAX_PATH) - "s %99s %*s %*d %*d\n", + while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n", debugfs_mountpoint, type) == 2) { if (strcmp(type, "debugfs") == 0) break; @@ -106,6 +108,12 @@ int debugfs_valid_entry(const char *path) return 0; } +static void debugfs_set_tracing_events_path(const char *mountpoint) +{ + snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s", + mountpoint, "tracing/events"); +} + /* mount the debugfs somewhere if it's not mounted */ char *debugfs_mount(const char *mountpoint) @@ -113,7 +121,7 @@ char *debugfs_mount(const char *mountpoint) /* see if it's already mounted */ if (debugfs_find_mountpoint()) { debugfs_premounted = 1; - return debugfs_mountpoint; + goto out; } /* if not mounted and no argument */ @@ -129,12 +137,19 @@ char *debugfs_mount(const char *mountpoint) return NULL; /* save the mountpoint */ - strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint)); debugfs_found = 1; - + strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint)); +out: + debugfs_set_tracing_events_path(debugfs_mountpoint); return debugfs_mountpoint; } +void debugfs_set_path(const char *mountpoint) +{ + snprintf(debugfs_mountpoint, sizeof(debugfs_mountpoint), "%s", mountpoint); + debugfs_set_tracing_events_path(mountpoint); +} + /* umount the debugfs */ int debugfs_umount(void) @@ -158,7 +173,7 @@ int debugfs_umount(void) int debugfs_write(const char *entry, const char *value) { - char path[MAX_PATH+1]; + char path[PATH_MAX + 1]; int ret, count; int fd; @@ -203,7 +218,7 @@ int debugfs_write(const char *entry, const char *value) */ int debugfs_read(const char *entry, char *buffer, size_t size) { - char path[MAX_PATH+1]; + char path[PATH_MAX + 1]; int ret; int fd; diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h index 83a02879745f..4a878f735eb0 100644 --- a/tools/perf/util/debugfs.h +++ b/tools/perf/util/debugfs.h @@ -1,25 +1,18 @@ #ifndef __DEBUGFS_H__ #define __DEBUGFS_H__ -#include <sys/mount.h> +const char *debugfs_find_mountpoint(void); +int debugfs_valid_mountpoint(const char *debugfs); +int debugfs_valid_entry(const char *path); +char *debugfs_mount(const char *mountpoint); +int debugfs_umount(void); +void debugfs_set_path(const char *mountpoint); +int debugfs_write(const char *entry, const char *value); +int debugfs_read(const char *entry, char *buffer, size_t size); +void debugfs_force_cleanup(void); +int debugfs_make_path(const char *element, char *buffer, int size); -#ifndef MAX_PATH -# define MAX_PATH 256 -#endif - -#ifndef STR -# define _STR(x) #x -# define STR(x) _STR(x) -#endif - -extern const char *debugfs_find_mountpoint(void); -extern int debugfs_valid_mountpoint(const char *debugfs); -extern int debugfs_valid_entry(const char *path); -extern char *debugfs_mount(const char *mountpoint); -extern int debugfs_umount(void); -extern int debugfs_write(const char *entry, const char *value); -extern int debugfs_read(const char *entry, char *buffer, size_t size); -extern void debugfs_force_cleanup(void); -extern int debugfs_make_path(const char *element, char *buffer, int size); +extern char debugfs_mountpoint[]; +extern char tracing_events_path[]; #endif /* __DEBUGFS_H__ */ diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index fddf40f30d3e..ee51e9b4dc09 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -96,6 +96,39 @@ int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr, return *lineno ?: -ENOENT; } +static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data); + +/** + * cu_walk_functions_at - Walk on function DIEs at given address + * @cu_die: A CU DIE + * @addr: An address + * @callback: A callback which called with found DIEs + * @data: A user data + * + * Walk on function DIEs at given @addr in @cu_die. Passed DIEs + * should be subprogram or inlined-subroutines. + */ +int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, + int (*callback)(Dwarf_Die *, void *), void *data) +{ + Dwarf_Die die_mem; + Dwarf_Die *sc_die; + int ret = -ENOENT; + + /* Inlined function could be recursive. Trace it until fail */ + for (sc_die = die_find_realfunc(cu_die, addr, &die_mem); + sc_die != NULL; + sc_die = die_find_child(sc_die, __die_find_inline_cb, &addr, + &die_mem)) { + ret = callback(sc_die, data); + if (ret) + break; + } + + return ret; + +} + /** * die_compare_name - Compare diename and tname * @dw_die: a DIE @@ -198,6 +231,19 @@ static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name, return 0; } +/* Get attribute and translate it as a sdata */ +static int die_get_attr_sdata(Dwarf_Die *tp_die, unsigned int attr_name, + Dwarf_Sword *result) +{ + Dwarf_Attribute attr; + + if (dwarf_attr(tp_die, attr_name, &attr) == NULL || + dwarf_formsdata(&attr, result) != 0) + return -ENOENT; + + return 0; +} + /** * die_is_signed_type - Check whether a type DIE is signed or not * @tp_die: a DIE of a type @@ -250,6 +296,50 @@ int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs) return 0; } +/* Get the call file index number in CU DIE */ +static int die_get_call_fileno(Dwarf_Die *in_die) +{ + Dwarf_Sword idx; + + if (die_get_attr_sdata(in_die, DW_AT_call_file, &idx) == 0) + return (int)idx; + else + return -ENOENT; +} + +/* Get the declared file index number in CU DIE */ +static int die_get_decl_fileno(Dwarf_Die *pdie) +{ + Dwarf_Sword idx; + + if (die_get_attr_sdata(pdie, DW_AT_decl_file, &idx) == 0) + return (int)idx; + else + return -ENOENT; +} + +/** + * die_get_call_file - Get callsite file name of inlined function instance + * @in_die: a DIE of an inlined function instance + * + * Get call-site file name of @in_die. This means from which file the inline + * function is called. + */ +const char *die_get_call_file(Dwarf_Die *in_die) +{ + Dwarf_Die cu_die; + Dwarf_Files *files; + int idx; + + idx = die_get_call_fileno(in_die); + if (idx < 0 || !dwarf_diecu(in_die, &cu_die, NULL, NULL) || + dwarf_getsrcfiles(&cu_die, &files, NULL) != 0) + return NULL; + + return dwarf_filesrc(files, idx, NULL, NULL); +} + + /** * die_find_child - Generic DIE search function in DIE tree * @rt_die: a root DIE @@ -374,9 +464,78 @@ Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, return die_mem; } +struct __instance_walk_param { + void *addr; + int (*callback)(Dwarf_Die *, void *); + void *data; + int retval; +}; + +static int __die_walk_instances_cb(Dwarf_Die *inst, void *data) +{ + struct __instance_walk_param *iwp = data; + Dwarf_Attribute attr_mem; + Dwarf_Die origin_mem; + Dwarf_Attribute *attr; + Dwarf_Die *origin; + int tmp; + + attr = dwarf_attr(inst, DW_AT_abstract_origin, &attr_mem); + if (attr == NULL) + return DIE_FIND_CB_CONTINUE; + + origin = dwarf_formref_die(attr, &origin_mem); + if (origin == NULL || origin->addr != iwp->addr) + return DIE_FIND_CB_CONTINUE; + + /* Ignore redundant instances */ + if (dwarf_tag(inst) == DW_TAG_inlined_subroutine) { + dwarf_decl_line(origin, &tmp); + if (die_get_call_lineno(inst) == tmp) { + tmp = die_get_decl_fileno(origin); + if (die_get_call_fileno(inst) == tmp) + return DIE_FIND_CB_CONTINUE; + } + } + + iwp->retval = iwp->callback(inst, iwp->data); + + return (iwp->retval) ? DIE_FIND_CB_END : DIE_FIND_CB_CONTINUE; +} + +/** + * die_walk_instances - Walk on instances of given DIE + * @or_die: an abstract original DIE + * @callback: a callback function which is called with instance DIE + * @data: user data + * + * Walk on the instances of give @in_die. @in_die must be an inlined function + * declartion. This returns the return value of @callback if it returns + * non-zero value, or -ENOENT if there is no instance. + */ +int die_walk_instances(Dwarf_Die *or_die, int (*callback)(Dwarf_Die *, void *), + void *data) +{ + Dwarf_Die cu_die; + Dwarf_Die die_mem; + struct __instance_walk_param iwp = { + .addr = or_die->addr, + .callback = callback, + .data = data, + .retval = -ENOENT, + }; + + if (dwarf_diecu(or_die, &cu_die, NULL, NULL) == NULL) + return -ENOENT; + + die_find_child(&cu_die, __die_walk_instances_cb, &iwp, &die_mem); + + return iwp.retval; +} + /* Line walker internal parameters */ struct __line_walk_param { - const char *fname; + bool recursive; line_walk_callback_t callback; void *data; int retval; @@ -385,39 +544,56 @@ struct __line_walk_param { static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data) { struct __line_walk_param *lw = data; - Dwarf_Addr addr; + Dwarf_Addr addr = 0; + const char *fname; int lineno; if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) { + fname = die_get_call_file(in_die); lineno = die_get_call_lineno(in_die); - if (lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) { - lw->retval = lw->callback(lw->fname, lineno, addr, - lw->data); + if (fname && lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) { + lw->retval = lw->callback(fname, lineno, addr, lw->data); if (lw->retval != 0) return DIE_FIND_CB_END; } } - return DIE_FIND_CB_SIBLING; + if (!lw->recursive) + /* Don't need to search recursively */ + return DIE_FIND_CB_SIBLING; + + if (addr) { + fname = dwarf_decl_file(in_die); + if (fname && dwarf_decl_line(in_die, &lineno) == 0) { + lw->retval = lw->callback(fname, lineno, addr, lw->data); + if (lw->retval != 0) + return DIE_FIND_CB_END; + } + } + + /* Continue to search nested inlined function call-sites */ + return DIE_FIND_CB_CONTINUE; } /* Walk on lines of blocks included in given DIE */ -static int __die_walk_funclines(Dwarf_Die *sp_die, +static int __die_walk_funclines(Dwarf_Die *sp_die, bool recursive, line_walk_callback_t callback, void *data) { struct __line_walk_param lw = { + .recursive = recursive, .callback = callback, .data = data, .retval = 0, }; Dwarf_Die die_mem; Dwarf_Addr addr; + const char *fname; int lineno; /* Handle function declaration line */ - lw.fname = dwarf_decl_file(sp_die); - if (lw.fname && dwarf_decl_line(sp_die, &lineno) == 0 && + fname = dwarf_decl_file(sp_die); + if (fname && dwarf_decl_line(sp_die, &lineno) == 0 && dwarf_entrypc(sp_die, &addr) == 0) { - lw.retval = callback(lw.fname, lineno, addr, data); + lw.retval = callback(fname, lineno, addr, data); if (lw.retval != 0) goto done; } @@ -430,7 +606,7 @@ static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data) { struct __line_walk_param *lw = data; - lw->retval = __die_walk_funclines(sp_die, lw->callback, lw->data); + lw->retval = __die_walk_funclines(sp_die, true, lw->callback, lw->data); if (lw->retval != 0) return DWARF_CB_ABORT; @@ -439,7 +615,7 @@ static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data) /** * die_walk_lines - Walk on lines inside given DIE - * @rt_die: a root DIE (CU or subprogram) + * @rt_die: a root DIE (CU, subprogram or inlined_subroutine) * @callback: callback routine * @data: user data * @@ -460,12 +636,12 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) size_t nlines, i; /* Get the CU die */ - if (dwarf_tag(rt_die) == DW_TAG_subprogram) + if (dwarf_tag(rt_die) != DW_TAG_compile_unit) cu_die = dwarf_diecu(rt_die, &die_mem, NULL, NULL); else cu_die = rt_die; if (!cu_die) { - pr_debug2("Failed to get CU from subprogram\n"); + pr_debug2("Failed to get CU from given DIE.\n"); return -EINVAL; } @@ -509,7 +685,11 @@ int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) * subroutines. We have to check functions list or given function. */ if (rt_die != cu_die) - ret = __die_walk_funclines(rt_die, callback, data); + /* + * Don't need walk functions recursively, because nested + * inlined functions don't have lines of the specified DIE. + */ + ret = __die_walk_funclines(rt_die, false, callback, data); else { struct __line_walk_param param = { .callback = callback, diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index bc3b21167e70..6ce1717784b7 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -34,12 +34,19 @@ extern const char *cu_get_comp_dir(Dwarf_Die *cu_die); extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, const char **fname, int *lineno); +/* Walk on funcitons at given address */ +extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, + int (*callback)(Dwarf_Die *, void *), void *data); + /* Compare diename and tname */ extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname); /* Get callsite line number of inline-function instance */ extern int die_get_call_lineno(Dwarf_Die *in_die); +/* Get callsite file name of inlined function instance */ +extern const char *die_get_call_file(Dwarf_Die *in_die); + /* Get type die */ extern Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem); @@ -73,6 +80,10 @@ extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr, extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, Dwarf_Die *die_mem); +/* Walk on the instances of given DIE */ +extern int die_walk_instances(Dwarf_Die *in_die, + int (*callback)(Dwarf_Die *, void *), void *data); + /* Walker on lines (Note: line number will not be sorted) */ typedef int (* line_walk_callback_t) (const char *fname, int lineno, Dwarf_Addr addr, void *data); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 3c1b8a632101..73ddaf06b8e7 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,7 +1,6 @@ #include <linux/types.h> #include "event.h" #include "debug.h" -#include "session.h" #include "sort.h" #include "string.h" #include "strlist.h" @@ -44,36 +43,27 @@ static struct perf_sample synth_sample = { .period = 1, }; -static pid_t perf_event__synthesize_comm(union perf_event *event, pid_t pid, - int full, perf_event__handler_t process, - struct perf_session *session) +static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) { char filename[PATH_MAX]; char bf[BUFSIZ]; FILE *fp; size_t size = 0; - DIR *tasks; - struct dirent dirent, *next; - pid_t tgid = 0; + pid_t tgid = -1; snprintf(filename, sizeof(filename), "/proc/%d/status", pid); fp = fopen(filename, "r"); if (fp == NULL) { -out_race: - /* - * We raced with a task exiting - just return: - */ pr_debug("couldn't open %s\n", filename); return 0; } - memset(&event->comm, 0, sizeof(event->comm)); - - while (!event->comm.comm[0] || !event->comm.pid) { + while (!comm[0] || (tgid < 0)) { if (fgets(bf, sizeof(bf), fp) == NULL) { - pr_warning("couldn't get COMM and pgid, malformed %s\n", filename); - goto out; + pr_warning("couldn't get COMM and pgid, malformed %s\n", + filename); + break; } if (memcmp(bf, "Name:", 5) == 0) { @@ -81,33 +71,65 @@ out_race: while (*name && isspace(*name)) ++name; size = strlen(name) - 1; - memcpy(event->comm.comm, name, size++); + if (size >= len) + size = len - 1; + memcpy(comm, name, size); + } else if (memcmp(bf, "Tgid:", 5) == 0) { char *tgids = bf + 5; while (*tgids && isspace(*tgids)) ++tgids; - tgid = event->comm.pid = atoi(tgids); + tgid = atoi(tgids); } } + fclose(fp); + + return tgid; +} + +static pid_t perf_event__synthesize_comm(struct perf_tool *tool, + union perf_event *event, pid_t pid, + int full, + perf_event__handler_t process, + struct machine *machine) +{ + char filename[PATH_MAX]; + size_t size; + DIR *tasks; + struct dirent dirent, *next; + pid_t tgid; + + memset(&event->comm, 0, sizeof(event->comm)); + + tgid = perf_event__get_comm_tgid(pid, event->comm.comm, + sizeof(event->comm.comm)); + if (tgid < 0) + goto out; + + event->comm.pid = tgid; event->comm.header.type = PERF_RECORD_COMM; + + size = strlen(event->comm.comm) + 1; size = ALIGN(size, sizeof(u64)); - memset(event->comm.comm + size, 0, session->id_hdr_size); + memset(event->comm.comm + size, 0, machine->id_hdr_size); event->comm.header.size = (sizeof(event->comm) - (sizeof(event->comm.comm) - size) + - session->id_hdr_size); + machine->id_hdr_size); if (!full) { event->comm.tid = pid; - process(event, &synth_sample, session); + process(tool, event, &synth_sample, machine); goto out; } snprintf(filename, sizeof(filename), "/proc/%d/task", pid); tasks = opendir(filename); - if (tasks == NULL) - goto out_race; + if (tasks == NULL) { + pr_debug("couldn't open %s\n", filename); + return 0; + } while (!readdir_r(tasks, &dirent, &next) && next) { char *end; @@ -115,22 +137,32 @@ out_race: if (*end) continue; + /* already have tgid; jut want to update the comm */ + (void) perf_event__get_comm_tgid(pid, event->comm.comm, + sizeof(event->comm.comm)); + + size = strlen(event->comm.comm) + 1; + size = ALIGN(size, sizeof(u64)); + memset(event->comm.comm + size, 0, machine->id_hdr_size); + event->comm.header.size = (sizeof(event->comm) - + (sizeof(event->comm.comm) - size) + + machine->id_hdr_size); + event->comm.tid = pid; - process(event, &synth_sample, session); + process(tool, event, &synth_sample, machine); } closedir(tasks); out: - fclose(fp); - return tgid; } -static int perf_event__synthesize_mmap_events(union perf_event *event, +static int perf_event__synthesize_mmap_events(struct perf_tool *tool, + union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, - struct perf_session *session) + struct machine *machine) { char filename[PATH_MAX]; FILE *fp; @@ -169,12 +201,17 @@ static int perf_event__synthesize_mmap_events(union perf_event *event, continue; pbf += n + 3; if (*pbf == 'x') { /* vm_exec */ + char anonstr[] = "//anon\n"; char *execname = strchr(bf, '/'); /* Catch VDSO */ if (execname == NULL) execname = strstr(bf, "[vdso]"); + /* Catch anonymous mmaps */ + if ((execname == NULL) && !strstr(bf, "[")) + execname = anonstr; + if (execname == NULL) continue; @@ -188,12 +225,12 @@ static int perf_event__synthesize_mmap_events(union perf_event *event, event->mmap.len -= event->mmap.start; event->mmap.header.size = (sizeof(event->mmap) - (sizeof(event->mmap.filename) - size)); - memset(event->mmap.filename + size, 0, session->id_hdr_size); - event->mmap.header.size += session->id_hdr_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; - process(event, &synth_sample, session); + process(tool, event, &synth_sample, machine); } } @@ -201,14 +238,14 @@ static int perf_event__synthesize_mmap_events(union perf_event *event, return 0; } -int perf_event__synthesize_modules(perf_event__handler_t process, - struct perf_session *session, +int perf_event__synthesize_modules(struct perf_tool *tool, + perf_event__handler_t process, struct machine *machine) { struct rb_node *nd; struct map_groups *kmaps = &machine->kmaps; union perf_event *event = zalloc((sizeof(event->mmap) + - session->id_hdr_size)); + machine->id_hdr_size)); if (event == NULL) { pr_debug("Not enough memory synthesizing mmap event " "for kernel modules\n"); @@ -238,15 +275,15 @@ int perf_event__synthesize_modules(perf_event__handler_t process, event->mmap.header.type = PERF_RECORD_MMAP; event->mmap.header.size = (sizeof(event->mmap) - (sizeof(event->mmap.filename) - size)); - memset(event->mmap.filename + size, 0, session->id_hdr_size); - event->mmap.header.size += session->id_hdr_size; + memset(event->mmap.filename + size, 0, machine->id_hdr_size); + event->mmap.header.size += machine->id_hdr_size; event->mmap.start = pos->start; event->mmap.len = pos->end - pos->start; event->mmap.pid = machine->pid; memcpy(event->mmap.filename, pos->dso->long_name, pos->dso->long_name_len + 1); - process(event, &synth_sample, session); + process(tool, event, &synth_sample, machine); } free(event); @@ -255,40 +292,69 @@ int perf_event__synthesize_modules(perf_event__handler_t process, static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *mmap_event, - pid_t pid, perf_event__handler_t process, - struct perf_session *session) + pid_t pid, int full, + perf_event__handler_t process, + struct perf_tool *tool, + struct machine *machine) { - pid_t tgid = perf_event__synthesize_comm(comm_event, pid, 1, process, - session); + pid_t tgid = perf_event__synthesize_comm(tool, comm_event, pid, full, + process, machine); if (tgid == -1) return -1; - return perf_event__synthesize_mmap_events(mmap_event, pid, tgid, - process, session); + return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine); } -int perf_event__synthesize_thread_map(struct thread_map *threads, +int perf_event__synthesize_thread_map(struct perf_tool *tool, + struct thread_map *threads, perf_event__handler_t process, - struct perf_session *session) + struct machine *machine) { union perf_event *comm_event, *mmap_event; - int err = -1, thread; + int err = -1, thread, j; - comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size); + comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); if (comm_event == NULL) goto out; - mmap_event = malloc(sizeof(mmap_event->mmap) + session->id_hdr_size); + mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size); if (mmap_event == NULL) goto out_free_comm; err = 0; for (thread = 0; thread < threads->nr; ++thread) { if (__event__synthesize_thread(comm_event, mmap_event, - threads->map[thread], - process, session)) { + threads->map[thread], 0, + process, tool, machine)) { err = -1; break; } + + /* + * comm.pid is set to thread group id by + * perf_event__synthesize_comm + */ + if ((int) comm_event->comm.pid != threads->map[thread]) { + bool need_leader = true; + + /* is thread group leader in thread_map? */ + for (j = 0; j < threads->nr; ++j) { + if ((int) comm_event->comm.pid == threads->map[j]) { + need_leader = false; + break; + } + } + + /* if not, generate events for it */ + if (need_leader && + __event__synthesize_thread(comm_event, + mmap_event, + comm_event->comm.pid, 0, + process, tool, machine)) { + err = -1; + break; + } + } } free(mmap_event); out_free_comm: @@ -297,19 +363,20 @@ out: return err; } -int perf_event__synthesize_threads(perf_event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) { DIR *proc; struct dirent dirent, *next; union perf_event *comm_event, *mmap_event; int err = -1; - comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size); + comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); if (comm_event == NULL) goto out; - mmap_event = malloc(sizeof(mmap_event->mmap) + session->id_hdr_size); + mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size); if (mmap_event == NULL) goto out_free_comm; @@ -324,8 +391,8 @@ int perf_event__synthesize_threads(perf_event__handler_t process, if (*end) /* only interested in proper numerical dirents */ continue; - __event__synthesize_thread(comm_event, mmap_event, pid, - process, session); + __event__synthesize_thread(comm_event, mmap_event, pid, 1, + process, tool, machine); } closedir(proc); @@ -360,8 +427,8 @@ static int find_symbol_cb(void *arg, const char *name, char type, return 1; } -int perf_event__synthesize_kernel_mmap(perf_event__handler_t process, - struct perf_session *session, +int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, struct machine *machine, const char *symbol_name) { @@ -378,7 +445,7 @@ int perf_event__synthesize_kernel_mmap(perf_event__handler_t process, */ struct process_symbol_args args = { .name = symbol_name, }; union perf_event *event = zalloc((sizeof(event->mmap) + - session->id_hdr_size)); + machine->id_hdr_size)); if (event == NULL) { pr_debug("Not enough memory synthesizing mmap event " "for kernel modules\n"); @@ -412,25 +479,32 @@ int perf_event__synthesize_kernel_mmap(perf_event__handler_t process, size = ALIGN(size, sizeof(u64)); event->mmap.header.type = PERF_RECORD_MMAP; event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size) + session->id_hdr_size); + (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); event->mmap.pgoff = args.start; event->mmap.start = map->start; event->mmap.len = map->end - event->mmap.start; event->mmap.pid = machine->pid; - err = process(event, &synth_sample, session); + err = process(tool, event, &synth_sample, machine); free(event); return err; } -int perf_event__process_comm(union perf_event *event, +size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) +{ + return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid); +} + +int perf_event__process_comm(struct perf_tool *tool __used, + union perf_event *event, struct perf_sample *sample __used, - struct perf_session *session) + struct machine *machine) { - struct thread *thread = perf_session__findnew(session, event->comm.tid); + struct thread *thread = machine__findnew_thread(machine, event->comm.tid); - dump_printf(": %s:%d\n", event->comm.comm, event->comm.tid); + if (dump_trace) + perf_event__fprintf_comm(event, stdout); if (thread == NULL || thread__set_comm(thread, event->comm.comm)) { dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); @@ -440,13 +514,13 @@ int perf_event__process_comm(union perf_event *event, return 0; } -int perf_event__process_lost(union perf_event *event, +int perf_event__process_lost(struct perf_tool *tool __used, + union perf_event *event, struct perf_sample *sample __used, - struct perf_session *session) + struct machine *machine __used) { dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", event->lost.id, event->lost.lost); - session->hists.stats.total_lost += event->lost.lost; return 0; } @@ -463,21 +537,15 @@ static void perf_event__set_kernel_mmap_len(union perf_event *event, maps[MAP__FUNCTION]->end = ~0ULL; } -static int perf_event__process_kernel_mmap(union perf_event *event, - struct perf_session *session) +static int perf_event__process_kernel_mmap(struct perf_tool *tool __used, + union perf_event *event, + struct machine *machine) { struct map *map; char kmmap_prefix[PATH_MAX]; - struct machine *machine; enum dso_kernel_type kernel_type; bool is_kernel_mmap; - machine = perf_session__findnew_machine(session, event->mmap.pid); - if (!machine) { - pr_err("Can't find id %d's machine\n", event->mmap.pid); - goto out_problem; - } - machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix)); if (machine__is_host(machine)) kernel_type = DSO_TYPE_KERNEL; @@ -544,9 +612,9 @@ static int perf_event__process_kernel_mmap(union perf_event *event, * time /proc/sys/kernel/kptr_restrict was non zero. */ if (event->mmap.pgoff != 0) { - perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, - symbol_name, - event->mmap.pgoff); + maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, + symbol_name, + event->mmap.pgoff); } if (machine__is_default_guest(machine)) { @@ -562,32 +630,35 @@ out_problem: return -1; } -int perf_event__process_mmap(union perf_event *event, +size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) +{ + return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n", + event->mmap.pid, event->mmap.tid, event->mmap.start, + event->mmap.len, event->mmap.pgoff, event->mmap.filename); +} + +int perf_event__process_mmap(struct perf_tool *tool, + union perf_event *event, struct perf_sample *sample __used, - struct perf_session *session) + struct machine *machine) { - struct machine *machine; struct thread *thread; struct map *map; u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; int ret = 0; - dump_printf(" %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n", - event->mmap.pid, event->mmap.tid, event->mmap.start, - event->mmap.len, event->mmap.pgoff, event->mmap.filename); + if (dump_trace) + perf_event__fprintf_mmap(event, stdout); if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || cpumode == PERF_RECORD_MISC_KERNEL) { - ret = perf_event__process_kernel_mmap(event, session); + ret = perf_event__process_kernel_mmap(tool, event, machine); if (ret < 0) goto out_problem; return 0; } - machine = perf_session__find_host_machine(session); - if (machine == NULL) - goto out_problem; - thread = perf_session__findnew(session, event->mmap.pid); + thread = machine__findnew_thread(machine, event->mmap.pid); if (thread == NULL) goto out_problem; map = map__new(&machine->user_dsos, event->mmap.start, @@ -605,18 +676,26 @@ out_problem: return 0; } -int perf_event__process_task(union perf_event *event, +size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) +{ + return fprintf(fp, "(%d:%d):(%d:%d)\n", + event->fork.pid, event->fork.tid, + event->fork.ppid, event->fork.ptid); +} + +int perf_event__process_task(struct perf_tool *tool __used, + union perf_event *event, struct perf_sample *sample __used, - struct perf_session *session) + struct machine *machine) { - struct thread *thread = perf_session__findnew(session, event->fork.tid); - struct thread *parent = perf_session__findnew(session, event->fork.ptid); + struct thread *thread = machine__findnew_thread(machine, event->fork.tid); + struct thread *parent = machine__findnew_thread(machine, event->fork.ptid); - dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid, - event->fork.ppid, event->fork.ptid); + if (dump_trace) + perf_event__fprintf_task(event, stdout); if (event->header.type == PERF_RECORD_EXIT) { - perf_session__remove_thread(session, thread); + machine__remove_thread(machine, thread); return 0; } @@ -629,22 +708,45 @@ int perf_event__process_task(union perf_event *event, return 0; } -int perf_event__process(union perf_event *event, struct perf_sample *sample, - struct perf_session *session) +size_t perf_event__fprintf(union perf_event *event, FILE *fp) +{ + size_t ret = fprintf(fp, "PERF_RECORD_%s", + perf_event__name(event->header.type)); + + switch (event->header.type) { + case PERF_RECORD_COMM: + ret += perf_event__fprintf_comm(event, fp); + break; + case PERF_RECORD_FORK: + case PERF_RECORD_EXIT: + ret += perf_event__fprintf_task(event, fp); + break; + case PERF_RECORD_MMAP: + ret += perf_event__fprintf_mmap(event, fp); + break; + default: + ret += fprintf(fp, "\n"); + } + + return ret; +} + +int perf_event__process(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, struct machine *machine) { switch (event->header.type) { case PERF_RECORD_COMM: - perf_event__process_comm(event, sample, session); + perf_event__process_comm(tool, event, sample, machine); break; case PERF_RECORD_MMAP: - perf_event__process_mmap(event, sample, session); + perf_event__process_mmap(tool, event, sample, machine); break; case PERF_RECORD_FORK: case PERF_RECORD_EXIT: - perf_event__process_task(event, sample, session); + perf_event__process_task(tool, event, sample, machine); break; case PERF_RECORD_LOST: - perf_event__process_lost(event, sample, session); + perf_event__process_lost(tool, event, sample, machine); default: break; } @@ -653,36 +755,29 @@ int perf_event__process(union perf_event *event, struct perf_sample *sample, } void thread__find_addr_map(struct thread *self, - struct perf_session *session, u8 cpumode, - enum map_type type, pid_t pid, u64 addr, + struct machine *machine, u8 cpumode, + enum map_type type, u64 addr, struct addr_location *al) { struct map_groups *mg = &self->mg; - struct machine *machine = NULL; al->thread = self; al->addr = addr; al->cpumode = cpumode; al->filtered = false; + if (machine == NULL) { + al->map = NULL; + return; + } + if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; - machine = perf_session__find_host_machine(session); - if (machine == NULL) { - al->map = NULL; - return; - } mg = &machine->kmaps; } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; - machine = perf_session__find_host_machine(session); } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { al->level = 'g'; - machine = perf_session__find_machine(session, pid); - if (machine == NULL) { - al->map = NULL; - return; - } mg = &machine->kmaps; } else { /* @@ -728,13 +823,12 @@ try_again: al->addr = al->map->map_ip(al->map, al->addr); } -void thread__find_addr_location(struct thread *self, - struct perf_session *session, u8 cpumode, - enum map_type type, pid_t pid, u64 addr, +void thread__find_addr_location(struct thread *thread, struct machine *machine, + u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) { - thread__find_addr_map(self, session, cpumode, type, pid, addr, al); + thread__find_addr_map(thread, machine, cpumode, type, addr, al); if (al->map != NULL) al->sym = map__find_symbol(al->map, al->addr, filter); else @@ -742,13 +836,13 @@ void thread__find_addr_location(struct thread *self, } int perf_event__preprocess_sample(const union perf_event *event, - struct perf_session *session, + struct machine *machine, struct addr_location *al, struct perf_sample *sample, symbol_filter_t filter) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = perf_session__findnew(session, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, event->ip.pid); if (thread == NULL) return -1; @@ -759,18 +853,18 @@ int perf_event__preprocess_sample(const union perf_event *event, dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); /* - * Have we already created the kernel maps for the host machine? + * Have we already created the kernel maps for this machine? * * This should have happened earlier, when we processed the kernel MMAP * events, but for older perf.data files there was no such thing, so do * it now. */ if (cpumode == PERF_RECORD_MISC_KERNEL && - session->host_machine.vmlinux_maps[MAP__FUNCTION] == NULL) - machine__create_kernel_maps(&session->host_machine); + machine->vmlinux_maps[MAP__FUNCTION] == NULL) + machine__create_kernel_maps(machine); - thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION, - event->ip.pid, event->ip.ip, al); + thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, + event->ip.ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); @@ -778,13 +872,14 @@ int perf_event__preprocess_sample(const union perf_event *event, al->cpu = sample->cpu; if (al->map) { + struct dso *dso = al->map->dso; + if (symbol_conf.dso_list && - (!al->map || !al->map->dso || - !(strlist__has_entry(symbol_conf.dso_list, - al->map->dso->short_name) || - (al->map->dso->short_name != al->map->dso->long_name && - strlist__has_entry(symbol_conf.dso_list, - al->map->dso->long_name))))) + (!dso || !(strlist__has_entry(symbol_conf.dso_list, + dso->short_name) || + (dso->short_name != dso->long_name && + strlist__has_entry(symbol_conf.dso_list, + dso->long_name))))) goto out_filtered; al->sym = map__find_symbol(al->map, al->addr, filter); diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 1d7f66488a88..cbdeaad9c5e5 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -2,6 +2,7 @@ #define __PERF_RECORD_H #include <limits.h> +#include <stdio.h> #include "../perf.h" #include "map.h" @@ -141,43 +142,54 @@ union perf_event { void perf_event__print_totals(void); -struct perf_session; +struct perf_tool; struct thread_map; -typedef int (*perf_event__handler_synth_t)(union perf_event *event, - struct perf_session *session); -typedef int (*perf_event__handler_t)(union perf_event *event, +typedef int (*perf_event__handler_t)(struct perf_tool *tool, + union perf_event *event, struct perf_sample *sample, - struct perf_session *session); + struct machine *machine); -int perf_event__synthesize_thread_map(struct thread_map *threads, +int perf_event__synthesize_thread_map(struct perf_tool *tool, + struct thread_map *threads, perf_event__handler_t process, - struct perf_session *session); -int perf_event__synthesize_threads(perf_event__handler_t process, - struct perf_session *session); -int perf_event__synthesize_kernel_mmap(perf_event__handler_t process, - struct perf_session *session, + struct machine *machine); +int perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine); +int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, struct machine *machine, const char *symbol_name); -int perf_event__synthesize_modules(perf_event__handler_t process, - struct perf_session *session, +int perf_event__synthesize_modules(struct perf_tool *tool, + perf_event__handler_t process, struct machine *machine); -int perf_event__process_comm(union perf_event *event, struct perf_sample *sample, - struct perf_session *session); -int perf_event__process_lost(union perf_event *event, struct perf_sample *sample, - struct perf_session *session); -int perf_event__process_mmap(union perf_event *event, struct perf_sample *sample, - struct perf_session *session); -int perf_event__process_task(union perf_event *event, struct perf_sample *sample, - struct perf_session *session); -int perf_event__process(union perf_event *event, struct perf_sample *sample, - struct perf_session *session); +int perf_event__process_comm(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process_lost(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process_mmap(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process_task(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); struct addr_location; int perf_event__preprocess_sample(const union perf_event *self, - struct perf_session *session, + struct machine *machine, struct addr_location *al, struct perf_sample *sample, symbol_filter_t filter); @@ -186,6 +198,14 @@ const char *perf_event__name(unsigned int id); int perf_event__parse_sample(const union perf_event *event, u64 type, int sample_size, bool sample_id_all, - struct perf_sample *sample); + struct perf_sample *sample, bool swapped); +int perf_event__synthesize_sample(union perf_event *event, u64 type, + const struct perf_sample *sample, + bool swapped); + +size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_task(union perf_event *event, FILE *fp); +size_t perf_event__fprintf(union perf_event *event, FILE *fp); #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index b021ea9265c3..3f16e08a5c8d 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -6,12 +6,16 @@ * * Released under the GPL v2. (and only v2, not any later version) */ +#include "util.h" +#include "debugfs.h" #include <poll.h> #include "cpumap.h" #include "thread_map.h" #include "evlist.h" #include "evsel.h" -#include "util.h" +#include <unistd.h> + +#include "parse-events.h" #include <sys/mman.h> @@ -30,6 +34,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, INIT_HLIST_HEAD(&evlist->heads[i]); INIT_LIST_HEAD(&evlist->entries); perf_evlist__set_maps(evlist, cpus, threads); + evlist->workload.pid = -1; } struct perf_evlist *perf_evlist__new(struct cpu_map *cpus, @@ -43,6 +48,22 @@ struct perf_evlist *perf_evlist__new(struct cpu_map *cpus, return evlist; } +void perf_evlist__config_attrs(struct perf_evlist *evlist, + struct perf_record_opts *opts) +{ + struct perf_evsel *evsel; + + if (evlist->cpus->map[0] < 0) + opts->no_inherit = true; + + list_for_each_entry(evsel, &evlist->entries, node) { + perf_evsel__config(evsel, opts); + + if (evlist->nr_entries > 1) + evsel->attr.sample_type |= PERF_SAMPLE_ID; + } +} + static void perf_evlist__purge(struct perf_evlist *evlist) { struct perf_evsel *pos, *n; @@ -76,22 +97,188 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) ++evlist->nr_entries; } +static void perf_evlist__splice_list_tail(struct perf_evlist *evlist, + struct list_head *list, + int nr_entries) +{ + list_splice_tail(list, &evlist->entries); + evlist->nr_entries += nr_entries; +} + int perf_evlist__add_default(struct perf_evlist *evlist) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, }; - struct perf_evsel *evsel = perf_evsel__new(&attr, 0); + struct perf_evsel *evsel; + + event_attr_init(&attr); + evsel = perf_evsel__new(&attr, 0); if (evsel == NULL) - return -ENOMEM; + goto error; + + /* use strdup() because free(evsel) assumes name is allocated */ + evsel->name = strdup("cycles"); + if (!evsel->name) + goto error_free; perf_evlist__add(evlist, evsel); return 0; +error_free: + perf_evsel__delete(evsel); +error: + return -ENOMEM; +} + +int perf_evlist__add_attrs(struct perf_evlist *evlist, + struct perf_event_attr *attrs, size_t nr_attrs) +{ + struct perf_evsel *evsel, *n; + LIST_HEAD(head); + size_t i; + + for (i = 0; i < nr_attrs; i++) { + evsel = perf_evsel__new(attrs + i, evlist->nr_entries + i); + if (evsel == NULL) + goto out_delete_partial_list; + list_add_tail(&evsel->node, &head); + } + + perf_evlist__splice_list_tail(evlist, &head, nr_attrs); + + return 0; + +out_delete_partial_list: + list_for_each_entry_safe(evsel, n, &head, node) + perf_evsel__delete(evsel); + return -1; +} + +static int trace_event__id(const char *evname) +{ + char *filename, *colon; + int err = -1, fd; + + if (asprintf(&filename, "%s/%s/id", tracing_events_path, evname) < 0) + return -1; + + colon = strrchr(filename, ':'); + if (colon != NULL) + *colon = '/'; + + fd = open(filename, O_RDONLY); + if (fd >= 0) { + char id[16]; + if (read(fd, id, sizeof(id)) > 0) + err = atoi(id); + close(fd); + } + + free(filename); + return err; +} + +int perf_evlist__add_tracepoints(struct perf_evlist *evlist, + const char *tracepoints[], + size_t nr_tracepoints) +{ + int err; + size_t i; + struct perf_event_attr *attrs = zalloc(nr_tracepoints * sizeof(*attrs)); + + if (attrs == NULL) + return -1; + + for (i = 0; i < nr_tracepoints; i++) { + err = trace_event__id(tracepoints[i]); + + if (err < 0) + goto out_free_attrs; + + attrs[i].type = PERF_TYPE_TRACEPOINT; + attrs[i].config = err; + attrs[i].sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | + PERF_SAMPLE_CPU); + attrs[i].sample_period = 1; + } + + err = perf_evlist__add_attrs(evlist, attrs, nr_tracepoints); +out_free_attrs: + free(attrs); + return err; +} + +static struct perf_evsel * + perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + if (evsel->attr.type == PERF_TYPE_TRACEPOINT && + (int)evsel->attr.config == id) + return evsel; + } + + return NULL; } -int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) +int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist, + const struct perf_evsel_str_handler *assocs, + size_t nr_assocs) +{ + struct perf_evsel *evsel; + int err; + size_t i; + + for (i = 0; i < nr_assocs; i++) { + err = trace_event__id(assocs[i].name); + if (err < 0) + goto out; + + evsel = perf_evlist__find_tracepoint_by_id(evlist, err); + if (evsel == NULL) + continue; + + err = -EEXIST; + if (evsel->handler.func != NULL) + goto out; + evsel->handler.func = assocs[i].handler; + } + + err = 0; +out: + return err; +} + +void perf_evlist__disable(struct perf_evlist *evlist) +{ + int cpu, thread; + struct perf_evsel *pos; + + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + list_for_each_entry(pos, &evlist->entries, node) { + for (thread = 0; thread < evlist->threads->nr; thread++) + ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE); + } + } +} + +void perf_evlist__enable(struct perf_evlist *evlist) +{ + int cpu, thread; + struct perf_evsel *pos; + + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + list_for_each_entry(pos, &evlist->entries, node) { + for (thread = 0; thread < evlist->threads->nr; thread++) + ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE); + } + } +} + +static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries; evlist->pollfd = malloc(sizeof(struct pollfd) * nfds); @@ -247,7 +434,7 @@ void perf_evlist__munmap(struct perf_evlist *evlist) evlist->mmap = NULL; } -int perf_evlist__alloc_mmap(struct perf_evlist *evlist) +static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) { evlist->nr_mmaps = evlist->cpus->nr; if (evlist->cpus->map[0] == -1) @@ -263,8 +450,10 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, evlist->mmap[idx].mask = mask; evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot, MAP_SHARED, fd, 0); - if (evlist->mmap[idx].base == MAP_FAILED) + if (evlist->mmap[idx].base == MAP_FAILED) { + evlist->mmap[idx].base = NULL; return -1; + } perf_evlist__add_pollfd(evlist, fd); return 0; @@ -365,14 +554,22 @@ out_unmap: * * Using perf_evlist__read_on_cpu does this automatically. */ -int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite) +int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, + bool overwrite) { unsigned int page_size = sysconf(_SC_PAGE_SIZE); - int mask = pages * page_size - 1; 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); + int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask; + + /* 512 kiB: default amount of unprivileged mlocked memory */ + if (pages == UINT_MAX) + pages = (512 * 1024) / page_size; + else if (!is_power_of_2(pages)) + return -EINVAL; + + mask = pages * page_size - 1; if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) return -ENOMEM; @@ -477,6 +674,38 @@ u64 perf_evlist__sample_type(const struct perf_evlist *evlist) return first->attr.sample_type; } +u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist) +{ + struct perf_evsel *first; + struct perf_sample *data; + u64 sample_type; + u16 size = 0; + + first = list_entry(evlist->entries.next, struct perf_evsel, node); + + if (!first->attr.sample_id_all) + goto out; + + sample_type = first->attr.sample_type; + + if (sample_type & PERF_SAMPLE_TID) + size += sizeof(data->tid) * 2; + + if (sample_type & PERF_SAMPLE_TIME) + size += sizeof(data->time); + + if (sample_type & PERF_SAMPLE_ID) + size += sizeof(data->id); + + if (sample_type & PERF_SAMPLE_STREAM_ID) + size += sizeof(data->stream_id); + + if (sample_type & PERF_SAMPLE_CPU) + size += sizeof(data->cpu) * 2; +out: + return size; +} + bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist) { struct perf_evsel *pos, *first; @@ -498,3 +727,133 @@ bool perf_evlist__sample_id_all(const struct perf_evlist *evlist) first = list_entry(evlist->entries.next, struct perf_evsel, node); return first->attr.sample_id_all; } + +void perf_evlist__set_selected(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + evlist->selected = evsel; +} + +int perf_evlist__open(struct perf_evlist *evlist, bool group) +{ + struct perf_evsel *evsel, *first; + int err, ncpus, nthreads; + + first = list_entry(evlist->entries.next, struct perf_evsel, node); + + list_for_each_entry(evsel, &evlist->entries, node) { + struct xyarray *group_fd = NULL; + + if (group && evsel != first) + group_fd = first->fd; + + err = perf_evsel__open(evsel, evlist->cpus, evlist->threads, + group, group_fd); + if (err < 0) + goto out_err; + } + + return 0; +out_err: + ncpus = evlist->cpus ? evlist->cpus->nr : 1; + nthreads = evlist->threads ? evlist->threads->nr : 1; + + list_for_each_entry_reverse(evsel, &evlist->entries, node) + perf_evsel__close(evsel, ncpus, nthreads); + + return err; +} + +int perf_evlist__prepare_workload(struct perf_evlist *evlist, + struct perf_record_opts *opts, + const char *argv[]) +{ + int child_ready_pipe[2], go_pipe[2]; + char bf; + + if (pipe(child_ready_pipe) < 0) { + perror("failed to create 'ready' pipe"); + return -1; + } + + if (pipe(go_pipe) < 0) { + perror("failed to create 'go' pipe"); + goto out_close_ready_pipe; + } + + evlist->workload.pid = fork(); + if (evlist->workload.pid < 0) { + perror("failed to fork"); + goto out_close_pipes; + } + + if (!evlist->workload.pid) { + if (opts->pipe_output) + dup2(2, 1); + + close(child_ready_pipe[0]); + close(go_pipe[1]); + fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); + + /* + * Do a dummy execvp to get the PLT entry resolved, + * so we avoid the resolver overhead on the real + * execvp call. + */ + execvp("", (char **)argv); + + /* + * Tell the parent we're ready to go + */ + close(child_ready_pipe[1]); + + /* + * Wait until the parent tells us to go. + */ + if (read(go_pipe[0], &bf, 1) == -1) + perror("unable to read pipe"); + + execvp(argv[0], (char **)argv); + + perror(argv[0]); + kill(getppid(), SIGUSR1); + exit(-1); + } + + if (!opts->system_wide && opts->target_tid == -1 && opts->target_pid == -1) + evlist->threads->map[0] = evlist->workload.pid; + + close(child_ready_pipe[1]); + close(go_pipe[0]); + /* + * wait for child to settle + */ + if (read(child_ready_pipe[0], &bf, 1) == -1) { + perror("unable to read pipe"); + goto out_close_pipes; + } + + evlist->workload.cork_fd = go_pipe[1]; + close(child_ready_pipe[0]); + return 0; + +out_close_pipes: + close(go_pipe[0]); + close(go_pipe[1]); +out_close_ready_pipe: + close(child_ready_pipe[0]); + close(child_ready_pipe[1]); + return -1; +} + +int perf_evlist__start_workload(struct perf_evlist *evlist) +{ + if (evlist->workload.cork_fd > 0) { + /* + * Remove the cork, let it rip! + */ + return close(evlist->workload.cork_fd); + } + + return 0; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index b2b862374f37..8922aeed0467 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -2,12 +2,16 @@ #define __PERF_EVLIST_H 1 #include <linux/list.h> +#include <stdio.h> #include "../perf.h" #include "event.h" +#include "util.h" +#include <unistd.h> struct pollfd; struct thread_map; struct cpu_map; +struct perf_record_opts; #define PERF_EVLIST__HLIST_BITS 8 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) @@ -19,12 +23,22 @@ struct perf_evlist { int nr_fds; int nr_mmaps; int mmap_len; + struct { + int cork_fd; + pid_t pid; + } workload; bool overwrite; union perf_event event_copy; struct perf_mmap *mmap; struct pollfd *pollfd; struct thread_map *threads; struct cpu_map *cpus; + struct perf_evsel *selected; +}; + +struct perf_evsel_str_handler { + const char *name; + void *handler; }; struct perf_evsel; @@ -38,21 +52,52 @@ void perf_evlist__delete(struct perf_evlist *evlist); void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry); int perf_evlist__add_default(struct perf_evlist *evlist); +int perf_evlist__add_attrs(struct perf_evlist *evlist, + struct perf_event_attr *attrs, size_t nr_attrs); +int perf_evlist__add_tracepoints(struct perf_evlist *evlist, + const char *tracepoints[], size_t nr_tracepoints); +int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist, + const struct perf_evsel_str_handler *assocs, + size_t nr_assocs); + +#define perf_evlist__add_attrs_array(evlist, array) \ + perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array)) + +#define perf_evlist__add_tracepoints_array(evlist, array) \ + perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array)) + +#define perf_evlist__set_tracepoints_handlers_array(evlist, array) \ + perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array)) void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu, int thread, u64 id); -int perf_evlist__alloc_pollfd(struct perf_evlist *evlist); void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); -int perf_evlist__alloc_mmap(struct perf_evlist *evlist); -int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite); +int perf_evlist__open(struct perf_evlist *evlist, bool group); + +void perf_evlist__config_attrs(struct perf_evlist *evlist, + struct perf_record_opts *opts); + +int perf_evlist__prepare_workload(struct perf_evlist *evlist, + struct perf_record_opts *opts, + const char *argv[]); +int perf_evlist__start_workload(struct perf_evlist *evlist); + +int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, + bool overwrite); void perf_evlist__munmap(struct perf_evlist *evlist); +void perf_evlist__disable(struct perf_evlist *evlist); +void perf_evlist__enable(struct perf_evlist *evlist); + +void perf_evlist__set_selected(struct perf_evlist *evlist, + struct perf_evsel *evsel); + static inline void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, struct thread_map *threads) @@ -68,6 +113,7 @@ int perf_evlist__set_filters(struct perf_evlist *evlist); u64 perf_evlist__sample_type(const struct perf_evlist *evlist); bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist); +u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist); bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist); bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a03a36b7908a..667f3b78bb2c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -7,6 +7,8 @@ * Released under the GPL v2. (and only v2, not any later version) */ +#include <byteswap.h> +#include "asm/bug.h" #include "evsel.h" #include "evlist.h" #include "util.h" @@ -14,6 +16,7 @@ #include "thread_map.h" #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) +#define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0)) int __perf_evsel__sample_size(u64 sample_type) { @@ -31,12 +34,23 @@ int __perf_evsel__sample_size(u64 sample_type) return size; } +static void hists__init(struct hists *hists) +{ + memset(hists, 0, sizeof(*hists)); + hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; + hists->entries_in = &hists->entries_in_array[0]; + hists->entries_collapsed = RB_ROOT; + hists->entries = RB_ROOT; + pthread_mutex_init(&hists->lock, NULL); +} + void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx) { evsel->idx = idx; evsel->attr = *attr; INIT_LIST_HEAD(&evsel->node); + hists__init(&evsel->hists); } struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx) @@ -49,6 +63,79 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx) return evsel; } +void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts) +{ + struct perf_event_attr *attr = &evsel->attr; + int track = !evsel->idx; /* only the first counter needs these */ + + attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0; + attr->inherit = !opts->no_inherit; + attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING | + PERF_FORMAT_ID; + + attr->sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID; + + /* + * We default some events to a 1 default interval. But keep + * it a weak assumption overridable by the user. + */ + if (!attr->sample_period || (opts->user_freq != UINT_MAX && + opts->user_interval != ULLONG_MAX)) { + if (opts->freq) { + attr->sample_type |= PERF_SAMPLE_PERIOD; + attr->freq = 1; + attr->sample_freq = opts->freq; + } else { + attr->sample_period = opts->default_interval; + } + } + + if (opts->no_samples) + attr->sample_freq = 0; + + if (opts->inherit_stat) + attr->inherit_stat = 1; + + if (opts->sample_address) { + attr->sample_type |= PERF_SAMPLE_ADDR; + attr->mmap_data = track; + } + + if (opts->call_graph) + attr->sample_type |= PERF_SAMPLE_CALLCHAIN; + + if (opts->system_wide) + attr->sample_type |= PERF_SAMPLE_CPU; + + if (opts->period) + attr->sample_type |= PERF_SAMPLE_PERIOD; + + if (opts->sample_id_all_avail && + (opts->sample_time || opts->system_wide || + !opts->no_inherit || opts->cpu_list)) + attr->sample_type |= PERF_SAMPLE_TIME; + + if (opts->raw_samples) { + attr->sample_type |= PERF_SAMPLE_TIME; + attr->sample_type |= PERF_SAMPLE_RAW; + attr->sample_type |= PERF_SAMPLE_CPU; + } + + if (opts->no_delay) { + attr->watermark = 0; + attr->wakeup_events = 1; + } + + attr->mmap = track; + attr->comm = track; + + if (opts->target_pid == -1 && opts->target_tid == -1 && !opts->system_wide) { + attr->disabled = 1; + attr->enable_on_exec = 1; + } +} + int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { int cpu, thread; @@ -201,15 +288,16 @@ int __perf_evsel__read(struct perf_evsel *evsel, } static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads, bool group) + struct thread_map *threads, bool group, + struct xyarray *group_fds) { int cpu, thread; unsigned long flags = 0; - int pid = -1; + int pid = -1, err; if (evsel->fd == NULL && perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) - return -1; + return -ENOMEM; if (evsel->cgrp) { flags = PERF_FLAG_PID_CGROUP; @@ -217,7 +305,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, } for (cpu = 0; cpu < cpus->nr; cpu++) { - int group_fd = -1; + int group_fd = group_fds ? GROUP_FD(group_fds, cpu) : -1; for (thread = 0; thread < threads->nr; thread++) { @@ -228,8 +316,10 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, pid, cpus->map[cpu], group_fd, flags); - if (FD(evsel, cpu, thread) < 0) + if (FD(evsel, cpu, thread) < 0) { + err = -errno; goto out_close; + } if (group && group_fd == -1) group_fd = FD(evsel, cpu, thread); @@ -246,7 +336,17 @@ out_close: } thread = threads->nr; } while (--cpu >= 0); - return -1; + return err; +} + +void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + if (evsel->fd == NULL) + return; + + perf_evsel__close_fd(evsel, ncpus, nthreads); + perf_evsel__free_fd(evsel); + evsel->fd = NULL; } static struct { @@ -266,7 +366,8 @@ static struct { }; int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads, bool group) + struct thread_map *threads, bool group, + struct xyarray *group_fd) { if (cpus == NULL) { /* Work around old compiler warnings about strict aliasing */ @@ -276,19 +377,23 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, if (threads == NULL) threads = &empty_thread_map.map; - return __perf_evsel__open(evsel, cpus, threads, group); + return __perf_evsel__open(evsel, cpus, threads, group, group_fd); } int perf_evsel__open_per_cpu(struct perf_evsel *evsel, - struct cpu_map *cpus, bool group) + struct cpu_map *cpus, bool group, + struct xyarray *group_fd) { - return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group); + return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, + group_fd); } int perf_evsel__open_per_thread(struct perf_evsel *evsel, - struct thread_map *threads, bool group) + struct thread_map *threads, bool group, + struct xyarray *group_fd) { - return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group); + return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, + group_fd); } static int perf_event__parse_id_sample(const union perf_event *event, u64 type, @@ -342,10 +447,20 @@ static bool sample_overlap(const union perf_event *event, int perf_event__parse_sample(const union perf_event *event, u64 type, int sample_size, bool sample_id_all, - struct perf_sample *data) + struct perf_sample *data, bool swapped) { const u64 *array; + /* + * used for cross-endian analysis. See git commit 65014ab3 + * for why this goofiness is needed. + */ + union { + u64 val64; + u32 val32[2]; + } u; + + memset(data, 0, sizeof(*data)); data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; @@ -366,9 +481,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type, } if (type & PERF_SAMPLE_TID) { - u32 *p = (u32 *)array; - data->pid = p[0]; - data->tid = p[1]; + u.val64 = *array; + if (swapped) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + u.val32[1] = bswap_32(u.val32[1]); + } + + data->pid = u.val32[0]; + data->tid = u.val32[1]; array++; } @@ -395,8 +517,15 @@ int perf_event__parse_sample(const union perf_event *event, u64 type, } if (type & PERF_SAMPLE_CPU) { - u32 *p = (u32 *)array; - data->cpu = *p; + + u.val64 = *array; + if (swapped) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + } + + data->cpu = u.val32[0]; array++; } @@ -423,18 +552,106 @@ int perf_event__parse_sample(const union perf_event *event, u64 type, } if (type & PERF_SAMPLE_RAW) { - u32 *p = (u32 *)array; + const u64 *pdata; + + u.val64 = *array; + if (WARN_ONCE(swapped, + "Endianness of raw data not corrected!\n")) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + u.val32[1] = bswap_32(u.val32[1]); + } if (sample_overlap(event, array, sizeof(u32))) return -EFAULT; - data->raw_size = *p; - p++; + data->raw_size = u.val32[0]; + pdata = (void *) array + sizeof(u32); - if (sample_overlap(event, p, data->raw_size)) + if (sample_overlap(event, pdata, data->raw_size)) return -EFAULT; - data->raw_data = p; + data->raw_data = (void *) pdata; + } + + return 0; +} + +int perf_event__synthesize_sample(union perf_event *event, u64 type, + const struct perf_sample *sample, + bool swapped) +{ + u64 *array; + + /* + * used for cross-endian analysis. See git commit 65014ab3 + * for why this goofiness is needed. + */ + union { + u64 val64; + u32 val32[2]; + } u; + + array = event->sample.array; + + if (type & PERF_SAMPLE_IP) { + event->ip.ip = sample->ip; + array++; + } + + if (type & PERF_SAMPLE_TID) { + u.val32[0] = sample->pid; + u.val32[1] = sample->tid; + if (swapped) { + /* + * Inverse of what is done in perf_event__parse_sample + */ + u.val32[0] = bswap_32(u.val32[0]); + u.val32[1] = bswap_32(u.val32[1]); + u.val64 = bswap_64(u.val64); + } + + *array = u.val64; + array++; + } + + if (type & PERF_SAMPLE_TIME) { + *array = sample->time; + array++; + } + + if (type & PERF_SAMPLE_ADDR) { + *array = sample->addr; + array++; + } + + if (type & PERF_SAMPLE_ID) { + *array = sample->id; + array++; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + *array = sample->stream_id; + array++; + } + + if (type & PERF_SAMPLE_CPU) { + u.val32[0] = sample->cpu; + if (swapped) { + /* + * Inverse of what is done in perf_event__parse_sample + */ + u.val32[0] = bswap_32(u.val32[0]); + u.val64 = bswap_64(u.val64); + } + *array = u.val64; + array++; + } + + if (type & PERF_SAMPLE_PERIOD) { + *array = sample->period; + array++; } return 0; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index e9a31554e265..326b8e4d5035 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -61,12 +61,17 @@ struct perf_evsel { off_t id_offset; }; struct cgroup_sel *cgrp; + struct { + void *func; + void *data; + } handler; bool supported; }; struct cpu_map; struct thread_map; struct perf_evlist; +struct perf_record_opts; struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx); void perf_evsel__init(struct perf_evsel *evsel, @@ -74,6 +79,9 @@ void perf_evsel__init(struct perf_evsel *evsel, void perf_evsel__exit(struct perf_evsel *evsel); void perf_evsel__delete(struct perf_evsel *evsel); +void perf_evsel__config(struct perf_evsel *evsel, + struct perf_record_opts *opts); + int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); @@ -82,11 +90,15 @@ void perf_evsel__free_id(struct perf_evsel *evsel); void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__open_per_cpu(struct perf_evsel *evsel, - struct cpu_map *cpus, bool group); + struct cpu_map *cpus, bool group, + struct xyarray *group_fds); int perf_evsel__open_per_thread(struct perf_evsel *evsel, - struct thread_map *threads, bool group); + struct thread_map *threads, bool group, + struct xyarray *group_fds); int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads, bool group); + struct thread_map *threads, bool group, + struct xyarray *group_fds); +void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads); #define perf_evsel__match(evsel, t, c) \ (evsel->attr.type == PERF_TYPE_##t && \ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index cb2959a3fb43..3e7e0b09c12c 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1,5 +1,6 @@ #define _FILE_OFFSET_BITS 64 +#include "util.h" #include <sys/types.h> #include <byteswap.h> #include <unistd.h> @@ -7,22 +8,27 @@ #include <stdlib.h> #include <linux/list.h> #include <linux/kernel.h> +#include <linux/bitops.h> +#include <sys/utsname.h> #include "evlist.h" #include "evsel.h" -#include "util.h" #include "header.h" #include "../perf.h" #include "trace-event.h" #include "session.h" #include "symbol.h" #include "debug.h" +#include "cpumap.h" static bool no_buildid_cache = false; static int event_count; static struct perf_trace_event_type *events; +static u32 header_argc; +static const char **header_argv; + int perf_header__push_event(u64 id, const char *name) { if (strlen(name) > MAX_EVENT_NAME) @@ -110,6 +116,75 @@ static int write_padded(int fd, const void *bf, size_t count, return err; } +static int do_write_string(int fd, const char *str) +{ + u32 len, olen; + int ret; + + olen = strlen(str) + 1; + len = ALIGN(olen, NAME_ALIGN); + + /* write len, incl. \0 */ + ret = do_write(fd, &len, sizeof(len)); + if (ret < 0) + return ret; + + return write_padded(fd, str, olen, len); +} + +static char *do_read_string(int fd, struct perf_header *ph) +{ + ssize_t sz, ret; + u32 len; + char *buf; + + sz = read(fd, &len, sizeof(len)); + if (sz < (ssize_t)sizeof(len)) + return NULL; + + if (ph->needs_swap) + len = bswap_32(len); + + buf = malloc(len); + if (!buf) + return NULL; + + ret = read(fd, buf, len); + if (ret == (ssize_t)len) { + /* + * strings are padded by zeroes + * thus the actual strlen of buf + * may be less than len + */ + return buf; + } + + free(buf); + return NULL; +} + +int +perf_header__set_cmdline(int argc, const char **argv) +{ + int i; + + header_argc = (u32)argc; + + /* do not include NULL termination */ + header_argv = calloc(argc, sizeof(char *)); + if (!header_argv) + return -ENOMEM; + + /* + * must copy argv contents because it gets moved + * around during option parsing + */ + for (i = 0; i < argc ; i++) + header_argv[i] = argv[i]; + + return 0; +} + #define dsos__for_each_with_build_id(pos, head) \ list_for_each_entry(pos, head, node) \ if (!pos->has_build_id) \ @@ -189,8 +264,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, const char *name, bool is_kallsyms) { const size_t size = PATH_MAX; - char *realname, *filename = malloc(size), - *linkname = malloc(size), *targetname; + char *realname, *filename = zalloc(size), + *linkname = zalloc(size), *targetname; int len, err = -1; if (is_kallsyms) { @@ -254,8 +329,8 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) { const size_t size = PATH_MAX; - char *filename = malloc(size), - *linkname = malloc(size); + char *filename = zalloc(size), + *linkname = zalloc(size); int err = -1; if (filename == NULL || linkname == NULL) @@ -267,7 +342,7 @@ int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) if (access(linkname, F_OK)) goto out_free; - if (readlink(linkname, filename, size) < 0) + if (readlink(linkname, filename, size - 1) < 0) goto out_free; if (unlink(linkname)) @@ -356,27 +431,1001 @@ static bool perf_session__read_build_ids(struct perf_session *session, bool with return ret; } +static int write_trace_info(int fd, struct perf_header *h __used, + struct perf_evlist *evlist) +{ + return read_tracing_data(fd, &evlist->entries); +} + + +static int write_build_id(int fd, struct perf_header *h, + struct perf_evlist *evlist __used) +{ + struct perf_session *session; + int err; + + session = container_of(h, struct perf_session, header); + + if (!perf_session__read_build_ids(session, true)) + return -1; + + err = dsos__write_buildid_table(h, fd); + if (err < 0) { + pr_debug("failed to write buildid table\n"); + return err; + } + if (!no_buildid_cache) + perf_session__cache_build_ids(session); + + return 0; +} + +static int write_hostname(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + struct utsname uts; + int ret; + + ret = uname(&uts); + if (ret < 0) + return -1; + + return do_write_string(fd, uts.nodename); +} + +static int write_osrelease(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + struct utsname uts; + int ret; + + ret = uname(&uts); + if (ret < 0) + return -1; + + return do_write_string(fd, uts.release); +} + +static int write_arch(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + struct utsname uts; + int ret; + + ret = uname(&uts); + if (ret < 0) + return -1; + + return do_write_string(fd, uts.machine); +} + +static int write_version(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + return do_write_string(fd, perf_version_string); +} + +static int write_cpudesc(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ +#ifndef CPUINFO_PROC +#define CPUINFO_PROC NULL +#endif + FILE *file; + char *buf = NULL; + char *s, *p; + const char *search = CPUINFO_PROC; + size_t len = 0; + int ret = -1; + + if (!search) + return -1; + + file = fopen("/proc/cpuinfo", "r"); + if (!file) + return -1; + + while (getline(&buf, &len, file) > 0) { + ret = strncmp(buf, search, strlen(search)); + if (!ret) + break; + } + + if (ret) + goto done; + + s = buf; + + p = strchr(buf, ':'); + if (p && *(p+1) == ' ' && *(p+2)) + s = p + 2; + p = strchr(s, '\n'); + if (p) + *p = '\0'; + + /* squash extra space characters (branding string) */ + p = s; + while (*p) { + if (isspace(*p)) { + char *r = p + 1; + char *q = r; + *p = ' '; + while (*q && isspace(*q)) + q++; + if (q != (p+1)) + while ((*r++ = *q++)); + } + p++; + } + ret = do_write_string(fd, s); +done: + free(buf); + fclose(file); + return ret; +} + +static int write_nrcpus(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + long nr; + u32 nrc, nra; + int ret; + + nr = sysconf(_SC_NPROCESSORS_CONF); + if (nr < 0) + return -1; + + nrc = (u32)(nr & UINT_MAX); + + nr = sysconf(_SC_NPROCESSORS_ONLN); + if (nr < 0) + return -1; + + nra = (u32)(nr & UINT_MAX); + + ret = do_write(fd, &nrc, sizeof(nrc)); + if (ret < 0) + return ret; + + return do_write(fd, &nra, sizeof(nra)); +} + +static int write_event_desc(int fd, struct perf_header *h __used, + struct perf_evlist *evlist) +{ + struct perf_evsel *attr; + u32 nre = 0, nri, sz; + int ret; + + list_for_each_entry(attr, &evlist->entries, node) + nre++; + + /* + * write number of events + */ + ret = do_write(fd, &nre, sizeof(nre)); + if (ret < 0) + return ret; + + /* + * size of perf_event_attr struct + */ + sz = (u32)sizeof(attr->attr); + ret = do_write(fd, &sz, sizeof(sz)); + if (ret < 0) + return ret; + + list_for_each_entry(attr, &evlist->entries, node) { + + ret = do_write(fd, &attr->attr, sz); + if (ret < 0) + return ret; + /* + * write number of unique id per event + * there is one id per instance of an event + * + * copy into an nri to be independent of the + * type of ids, + */ + nri = attr->ids; + ret = do_write(fd, &nri, sizeof(nri)); + if (ret < 0) + return ret; + + /* + * write event string as passed on cmdline + */ + ret = do_write_string(fd, event_name(attr)); + if (ret < 0) + return ret; + /* + * write unique ids for this event + */ + ret = do_write(fd, attr->id, attr->ids * sizeof(u64)); + if (ret < 0) + return ret; + } + return 0; +} + +static int write_cmdline(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + char buf[MAXPATHLEN]; + char proc[32]; + u32 i, n; + int ret; + + /* + * actual atual path to perf binary + */ + sprintf(proc, "/proc/%d/exe", getpid()); + ret = readlink(proc, buf, sizeof(buf)); + if (ret <= 0) + return -1; + + /* readlink() does not add null termination */ + buf[ret] = '\0'; + + /* account for binary path */ + n = header_argc + 1; + + ret = do_write(fd, &n, sizeof(n)); + if (ret < 0) + return ret; + + ret = do_write_string(fd, buf); + if (ret < 0) + return ret; + + for (i = 0 ; i < header_argc; i++) { + ret = do_write_string(fd, header_argv[i]); + if (ret < 0) + return ret; + } + return 0; +} + +#define CORE_SIB_FMT \ + "/sys/devices/system/cpu/cpu%d/topology/core_siblings_list" +#define THRD_SIB_FMT \ + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list" + +struct cpu_topo { + u32 core_sib; + u32 thread_sib; + char **core_siblings; + char **thread_siblings; +}; + +static int build_cpu_topo(struct cpu_topo *tp, int cpu) +{ + FILE *fp; + char filename[MAXPATHLEN]; + char *buf = NULL, *p; + size_t len = 0; + u32 i = 0; + int ret = -1; + + sprintf(filename, CORE_SIB_FMT, cpu); + fp = fopen(filename, "r"); + if (!fp) + return -1; + + if (getline(&buf, &len, fp) <= 0) + goto done; + + fclose(fp); + + p = strchr(buf, '\n'); + if (p) + *p = '\0'; + + for (i = 0; i < tp->core_sib; i++) { + if (!strcmp(buf, tp->core_siblings[i])) + break; + } + if (i == tp->core_sib) { + tp->core_siblings[i] = buf; + tp->core_sib++; + buf = NULL; + len = 0; + } + + sprintf(filename, THRD_SIB_FMT, cpu); + fp = fopen(filename, "r"); + if (!fp) + goto done; + + if (getline(&buf, &len, fp) <= 0) + goto done; + + p = strchr(buf, '\n'); + if (p) + *p = '\0'; + + for (i = 0; i < tp->thread_sib; i++) { + if (!strcmp(buf, tp->thread_siblings[i])) + break; + } + if (i == tp->thread_sib) { + tp->thread_siblings[i] = buf; + tp->thread_sib++; + buf = NULL; + } + ret = 0; +done: + if(fp) + fclose(fp); + free(buf); + return ret; +} + +static void free_cpu_topo(struct cpu_topo *tp) +{ + u32 i; + + if (!tp) + return; + + for (i = 0 ; i < tp->core_sib; i++) + free(tp->core_siblings[i]); + + for (i = 0 ; i < tp->thread_sib; i++) + free(tp->thread_siblings[i]); + + free(tp); +} + +static struct cpu_topo *build_cpu_topology(void) +{ + struct cpu_topo *tp; + void *addr; + u32 nr, i; + size_t sz; + long ncpus; + int ret = -1; + + ncpus = sysconf(_SC_NPROCESSORS_CONF); + if (ncpus < 0) + return NULL; + + nr = (u32)(ncpus & UINT_MAX); + + sz = nr * sizeof(char *); + + addr = calloc(1, sizeof(*tp) + 2 * sz); + if (!addr) + return NULL; + + tp = addr; + + addr += sizeof(*tp); + tp->core_siblings = addr; + addr += sz; + tp->thread_siblings = addr; + + for (i = 0; i < nr; i++) { + ret = build_cpu_topo(tp, i); + if (ret < 0) + break; + } + if (ret) { + free_cpu_topo(tp); + tp = NULL; + } + return tp; +} + +static int write_cpu_topology(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + struct cpu_topo *tp; + u32 i; + int ret; + + tp = build_cpu_topology(); + if (!tp) + return -1; + + ret = do_write(fd, &tp->core_sib, sizeof(tp->core_sib)); + if (ret < 0) + goto done; + + for (i = 0; i < tp->core_sib; i++) { + ret = do_write_string(fd, tp->core_siblings[i]); + if (ret < 0) + goto done; + } + ret = do_write(fd, &tp->thread_sib, sizeof(tp->thread_sib)); + if (ret < 0) + goto done; + + for (i = 0; i < tp->thread_sib; i++) { + ret = do_write_string(fd, tp->thread_siblings[i]); + if (ret < 0) + break; + } +done: + free_cpu_topo(tp); + return ret; +} + + + +static int write_total_mem(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + char *buf = NULL; + FILE *fp; + size_t len = 0; + int ret = -1, n; + uint64_t mem; + + fp = fopen("/proc/meminfo", "r"); + if (!fp) + return -1; + + while (getline(&buf, &len, fp) > 0) { + ret = strncmp(buf, "MemTotal:", 9); + if (!ret) + break; + } + if (!ret) { + n = sscanf(buf, "%*s %"PRIu64, &mem); + if (n == 1) + ret = do_write(fd, &mem, sizeof(mem)); + } + free(buf); + fclose(fp); + return ret; +} + +static int write_topo_node(int fd, int node) +{ + char str[MAXPATHLEN]; + char field[32]; + char *buf = NULL, *p; + size_t len = 0; + FILE *fp; + u64 mem_total, mem_free, mem; + int ret = -1; + + sprintf(str, "/sys/devices/system/node/node%d/meminfo", node); + fp = fopen(str, "r"); + if (!fp) + return -1; + + while (getline(&buf, &len, fp) > 0) { + /* skip over invalid lines */ + if (!strchr(buf, ':')) + continue; + if (sscanf(buf, "%*s %*d %s %"PRIu64, field, &mem) != 2) + goto done; + if (!strcmp(field, "MemTotal:")) + mem_total = mem; + if (!strcmp(field, "MemFree:")) + mem_free = mem; + } + + fclose(fp); + + ret = do_write(fd, &mem_total, sizeof(u64)); + if (ret) + goto done; + + ret = do_write(fd, &mem_free, sizeof(u64)); + if (ret) + goto done; + + ret = -1; + sprintf(str, "/sys/devices/system/node/node%d/cpulist", node); + + fp = fopen(str, "r"); + if (!fp) + goto done; + + if (getline(&buf, &len, fp) <= 0) + goto done; + + p = strchr(buf, '\n'); + if (p) + *p = '\0'; + + ret = do_write_string(fd, buf); +done: + free(buf); + fclose(fp); + return ret; +} + +static int write_numa_topology(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + char *buf = NULL; + size_t len = 0; + FILE *fp; + struct cpu_map *node_map = NULL; + char *c; + u32 nr, i, j; + int ret = -1; + + fp = fopen("/sys/devices/system/node/online", "r"); + if (!fp) + return -1; + + if (getline(&buf, &len, fp) <= 0) + goto done; + + c = strchr(buf, '\n'); + if (c) + *c = '\0'; + + node_map = cpu_map__new(buf); + if (!node_map) + goto done; + + nr = (u32)node_map->nr; + + ret = do_write(fd, &nr, sizeof(nr)); + if (ret < 0) + goto done; + + for (i = 0; i < nr; i++) { + j = (u32)node_map->map[i]; + ret = do_write(fd, &j, sizeof(j)); + if (ret < 0) + break; + + ret = write_topo_node(fd, i); + if (ret < 0) + break; + } +done: + free(buf); + fclose(fp); + free(node_map); + return ret; +} + +/* + * default get_cpuid(): nothing gets recorded + * actual implementation must be in arch/$(ARCH)/util/header.c + */ +int __attribute__((weak)) get_cpuid(char *buffer __used, size_t sz __used) +{ + return -1; +} + +static int write_cpuid(int fd, struct perf_header *h __used, + struct perf_evlist *evlist __used) +{ + char buffer[64]; + int ret; + + ret = get_cpuid(buffer, sizeof(buffer)); + if (!ret) + goto write_it; + + return -1; +write_it: + return do_write_string(fd, buffer); +} + +static void print_hostname(struct perf_header *ph, int fd, FILE *fp) +{ + char *str = do_read_string(fd, ph); + fprintf(fp, "# hostname : %s\n", str); + free(str); +} + +static void print_osrelease(struct perf_header *ph, int fd, FILE *fp) +{ + char *str = do_read_string(fd, ph); + fprintf(fp, "# os release : %s\n", str); + free(str); +} + +static void print_arch(struct perf_header *ph, int fd, FILE *fp) +{ + char *str = do_read_string(fd, ph); + fprintf(fp, "# arch : %s\n", str); + free(str); +} + +static void print_cpudesc(struct perf_header *ph, int fd, FILE *fp) +{ + char *str = do_read_string(fd, ph); + fprintf(fp, "# cpudesc : %s\n", str); + free(str); +} + +static void print_nrcpus(struct perf_header *ph, int fd, FILE *fp) +{ + ssize_t ret; + u32 nr; + + ret = read(fd, &nr, sizeof(nr)); + if (ret != (ssize_t)sizeof(nr)) + nr = -1; /* interpreted as error */ + + if (ph->needs_swap) + nr = bswap_32(nr); + + fprintf(fp, "# nrcpus online : %u\n", nr); + + ret = read(fd, &nr, sizeof(nr)); + if (ret != (ssize_t)sizeof(nr)) + nr = -1; /* interpreted as error */ + + if (ph->needs_swap) + nr = bswap_32(nr); + + fprintf(fp, "# nrcpus avail : %u\n", nr); +} + +static void print_version(struct perf_header *ph, int fd, FILE *fp) +{ + char *str = do_read_string(fd, ph); + fprintf(fp, "# perf version : %s\n", str); + free(str); +} + +static void print_cmdline(struct perf_header *ph, int fd, FILE *fp) +{ + ssize_t ret; + char *str; + u32 nr, i; + + ret = read(fd, &nr, sizeof(nr)); + if (ret != (ssize_t)sizeof(nr)) + return; + + if (ph->needs_swap) + nr = bswap_32(nr); + + fprintf(fp, "# cmdline : "); + + for (i = 0; i < nr; i++) { + str = do_read_string(fd, ph); + fprintf(fp, "%s ", str); + free(str); + } + fputc('\n', fp); +} + +static void print_cpu_topology(struct perf_header *ph, int fd, FILE *fp) +{ + ssize_t ret; + u32 nr, i; + char *str; + + ret = read(fd, &nr, sizeof(nr)); + if (ret != (ssize_t)sizeof(nr)) + return; + + if (ph->needs_swap) + nr = bswap_32(nr); + + for (i = 0; i < nr; i++) { + str = do_read_string(fd, ph); + fprintf(fp, "# sibling cores : %s\n", str); + free(str); + } + + ret = read(fd, &nr, sizeof(nr)); + if (ret != (ssize_t)sizeof(nr)) + return; + + if (ph->needs_swap) + nr = bswap_32(nr); + + for (i = 0; i < nr; i++) { + str = do_read_string(fd, ph); + fprintf(fp, "# sibling threads : %s\n", str); + free(str); + } +} + +static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) +{ + struct perf_event_attr attr; + uint64_t id; + void *buf = NULL; + char *str; + u32 nre, sz, nr, i, j, msz; + int ret; + + /* number of events */ + ret = read(fd, &nre, sizeof(nre)); + if (ret != (ssize_t)sizeof(nre)) + goto error; + + if (ph->needs_swap) + nre = bswap_32(nre); + + ret = read(fd, &sz, sizeof(sz)); + if (ret != (ssize_t)sizeof(sz)) + goto error; + + if (ph->needs_swap) + sz = bswap_32(sz); + + /* + * ensure it is at least to our ABI rev + */ + if (sz < (u32)sizeof(attr)) + goto error; + + memset(&attr, 0, sizeof(attr)); + + /* read entire region to sync up to next field */ + buf = malloc(sz); + if (!buf) + goto error; + + msz = sizeof(attr); + if (sz < msz) + msz = sz; + + for (i = 0 ; i < nre; i++) { + + ret = read(fd, buf, sz); + if (ret != (ssize_t)sz) + goto error; + + if (ph->needs_swap) + perf_event__attr_swap(buf); + + memcpy(&attr, buf, msz); + + ret = read(fd, &nr, sizeof(nr)); + if (ret != (ssize_t)sizeof(nr)) + goto error; + + if (ph->needs_swap) + nr = bswap_32(nr); + + str = do_read_string(fd, ph); + fprintf(fp, "# event : name = %s, ", str); + free(str); + + fprintf(fp, "type = %d, config = 0x%"PRIx64 + ", config1 = 0x%"PRIx64", config2 = 0x%"PRIx64, + attr.type, + (u64)attr.config, + (u64)attr.config1, + (u64)attr.config2); + + fprintf(fp, ", excl_usr = %d, excl_kern = %d", + attr.exclude_user, + attr.exclude_kernel); + + if (nr) + fprintf(fp, ", id = {"); + + for (j = 0 ; j < nr; j++) { + ret = read(fd, &id, sizeof(id)); + if (ret != (ssize_t)sizeof(id)) + goto error; + + if (ph->needs_swap) + id = bswap_64(id); + + if (j) + fputc(',', fp); + + fprintf(fp, " %"PRIu64, id); + } + if (nr && j == nr) + fprintf(fp, " }"); + fputc('\n', fp); + } + free(buf); + return; +error: + fprintf(fp, "# event desc: not available or unable to read\n"); +} + +static void print_total_mem(struct perf_header *h __used, int fd, FILE *fp) +{ + uint64_t mem; + ssize_t ret; + + ret = read(fd, &mem, sizeof(mem)); + if (ret != sizeof(mem)) + goto error; + + if (h->needs_swap) + mem = bswap_64(mem); + + fprintf(fp, "# total memory : %"PRIu64" kB\n", mem); + return; +error: + fprintf(fp, "# total memory : unknown\n"); +} + +static void print_numa_topology(struct perf_header *h __used, int fd, FILE *fp) +{ + ssize_t ret; + u32 nr, c, i; + char *str; + uint64_t mem_total, mem_free; + + /* nr nodes */ + ret = read(fd, &nr, sizeof(nr)); + if (ret != (ssize_t)sizeof(nr)) + goto error; + + if (h->needs_swap) + nr = bswap_32(nr); + + for (i = 0; i < nr; i++) { + + /* node number */ + ret = read(fd, &c, sizeof(c)); + if (ret != (ssize_t)sizeof(c)) + goto error; + + if (h->needs_swap) + c = bswap_32(c); + + ret = read(fd, &mem_total, sizeof(u64)); + if (ret != sizeof(u64)) + goto error; + + ret = read(fd, &mem_free, sizeof(u64)); + if (ret != sizeof(u64)) + goto error; + + if (h->needs_swap) { + mem_total = bswap_64(mem_total); + mem_free = bswap_64(mem_free); + } + + fprintf(fp, "# node%u meminfo : total = %"PRIu64" kB," + " free = %"PRIu64" kB\n", + c, + mem_total, + mem_free); + + str = do_read_string(fd, h); + fprintf(fp, "# node%u cpu list : %s\n", c, str); + free(str); + } + return; +error: + fprintf(fp, "# numa topology : not available\n"); +} + +static void print_cpuid(struct perf_header *ph, int fd, FILE *fp) +{ + char *str = do_read_string(fd, ph); + fprintf(fp, "# cpuid : %s\n", str); + free(str); +} + +struct feature_ops { + int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); + void (*print)(struct perf_header *h, int fd, FILE *fp); + const char *name; + bool full_only; +}; + +#define FEAT_OPA(n, func) \ + [n] = { .name = #n, .write = write_##func, .print = print_##func } +#define FEAT_OPF(n, func) \ + [n] = { .name = #n, .write = write_##func, .print = print_##func, .full_only = true } + +/* feature_ops not implemented: */ +#define print_trace_info NULL +#define print_build_id NULL + +static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { + FEAT_OPA(HEADER_TRACE_INFO, trace_info), + FEAT_OPA(HEADER_BUILD_ID, build_id), + FEAT_OPA(HEADER_HOSTNAME, hostname), + FEAT_OPA(HEADER_OSRELEASE, osrelease), + FEAT_OPA(HEADER_VERSION, version), + FEAT_OPA(HEADER_ARCH, arch), + FEAT_OPA(HEADER_NRCPUS, nrcpus), + FEAT_OPA(HEADER_CPUDESC, cpudesc), + FEAT_OPA(HEADER_CPUID, cpuid), + FEAT_OPA(HEADER_TOTAL_MEM, total_mem), + FEAT_OPA(HEADER_EVENT_DESC, event_desc), + FEAT_OPA(HEADER_CMDLINE, cmdline), + FEAT_OPF(HEADER_CPU_TOPOLOGY, cpu_topology), + FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology), +}; + +struct header_print_data { + FILE *fp; + bool full; /* extended list of headers */ +}; + +static int perf_file_section__fprintf_info(struct perf_file_section *section, + struct perf_header *ph, + int feat, int fd, void *data) +{ + struct header_print_data *hd = data; + + if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { + pr_debug("Failed to lseek to %" PRIu64 " offset for feature " + "%d, continuing...\n", section->offset, feat); + return 0; + } + if (feat >= HEADER_LAST_FEATURE) { + pr_warning("unknown feature %d\n", feat); + return 0; + } + if (!feat_ops[feat].print) + return 0; + + if (!feat_ops[feat].full_only || hd->full) + feat_ops[feat].print(ph, fd, hd->fp); + else + fprintf(hd->fp, "# %s info available, use -I to display\n", + feat_ops[feat].name); + + return 0; +} + +int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) +{ + struct header_print_data hd; + struct perf_header *header = &session->header; + int fd = session->fd; + hd.fp = fp; + hd.full = full; + + perf_header__process_sections(header, fd, &hd, + perf_file_section__fprintf_info); + return 0; +} + +static int do_write_feat(int fd, struct perf_header *h, int type, + struct perf_file_section **p, + struct perf_evlist *evlist) +{ + int err; + int ret = 0; + + if (perf_header__has_feat(h, type)) { + if (!feat_ops[type].write) + return -1; + + (*p)->offset = lseek(fd, 0, SEEK_CUR); + + err = feat_ops[type].write(fd, h, evlist); + if (err < 0) { + pr_debug("failed to write feature %d\n", type); + + /* undo anything written */ + lseek(fd, (*p)->offset, SEEK_SET); + + return -1; + } + (*p)->size = lseek(fd, 0, SEEK_CUR) - (*p)->offset; + (*p)++; + } + return ret; +} + static int perf_header__adds_write(struct perf_header *header, struct perf_evlist *evlist, int fd) { int nr_sections; - struct perf_session *session; - struct perf_file_section *feat_sec; + struct perf_file_section *feat_sec, *p; int sec_size; u64 sec_start; - int idx = 0, err; - - session = container_of(header, struct perf_session, header); - - if (perf_header__has_feat(header, HEADER_BUILD_ID && - !perf_session__read_build_ids(session, true))) - perf_header__clear_feat(header, HEADER_BUILD_ID); + int feat; + int err; nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); if (!nr_sections) return 0; - feat_sec = calloc(sizeof(*feat_sec), nr_sections); + feat_sec = p = calloc(sizeof(*feat_sec), nr_sections); if (feat_sec == NULL) return -ENOMEM; @@ -385,40 +1434,19 @@ static int perf_header__adds_write(struct perf_header *header, sec_start = header->data_offset + header->data_size; lseek(fd, sec_start + sec_size, SEEK_SET); - if (perf_header__has_feat(header, HEADER_TRACE_INFO)) { - struct perf_file_section *trace_sec; - - trace_sec = &feat_sec[idx++]; - - /* Write trace info */ - trace_sec->offset = lseek(fd, 0, SEEK_CUR); - read_tracing_data(fd, &evlist->entries); - trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset; - } - - if (perf_header__has_feat(header, HEADER_BUILD_ID)) { - struct perf_file_section *buildid_sec; - - buildid_sec = &feat_sec[idx++]; - - /* Write build-ids */ - buildid_sec->offset = lseek(fd, 0, SEEK_CUR); - err = dsos__write_buildid_table(header, fd); - if (err < 0) { - pr_debug("failed to write buildid table\n"); - goto out_free; - } - buildid_sec->size = lseek(fd, 0, SEEK_CUR) - - buildid_sec->offset; - if (!no_buildid_cache) - perf_session__cache_build_ids(session); + for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { + if (do_write_feat(fd, header, feat, &p, evlist)) + perf_header__clear_feat(header, feat); } lseek(fd, sec_start, SEEK_SET); + /* + * may write more than needed due to dropped feature, but + * this is okay, reader will skip the mising entries + */ err = do_write(fd, feat_sec, sec_size); if (err < 0) pr_debug("failed to write feature section\n"); -out_free: free(feat_sec); return err; } @@ -554,21 +1582,22 @@ static int perf_header__getbuffer64(struct perf_header *header, } int perf_header__process_sections(struct perf_header *header, int fd, + void *data, int (*process)(struct perf_file_section *section, struct perf_header *ph, - int feat, int fd)) + int feat, int fd, void *data)) { - struct perf_file_section *feat_sec; + struct perf_file_section *feat_sec, *sec; int nr_sections; int sec_size; - int idx = 0; - int err = -1, feat = 1; + int feat; + int err; nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); if (!nr_sections) return 0; - feat_sec = calloc(sizeof(*feat_sec), nr_sections); + feat_sec = sec = calloc(sizeof(*feat_sec), nr_sections); if (!feat_sec) return -1; @@ -576,20 +1605,16 @@ int perf_header__process_sections(struct perf_header *header, int fd, lseek(fd, header->data_offset + header->data_size, SEEK_SET); - if (perf_header__getbuffer64(header, fd, feat_sec, sec_size)) + err = perf_header__getbuffer64(header, fd, feat_sec, sec_size); + if (err < 0) goto out_free; - err = 0; - while (idx < nr_sections && feat < HEADER_LAST_FEATURE) { - if (perf_header__has_feat(header, feat)) { - struct perf_file_section *sec = &feat_sec[idx++]; - - err = process(sec, header, feat, fd); - if (err < 0) - break; - } - ++feat; + for_each_set_bit(feat, header->adds_features, HEADER_LAST_FEATURE) { + err = process(sec++, header, feat, fd, data); + if (err < 0) + goto out_free; } + err = 0; out_free: free(feat_sec); return err; @@ -621,21 +1646,41 @@ int perf_file_header__read(struct perf_file_header *header, bitmap_zero(header->adds_features, HEADER_FEAT_BITS); else return -1; + } else if (ph->needs_swap) { + unsigned int i; + /* + * feature bitmap is declared as an array of unsigned longs -- + * not good since its size can differ between the host that + * generated the data file and the host analyzing the file. + * + * We need to handle endianness, but we don't know the size of + * the unsigned long where the file was generated. Take a best + * guess at determining it: try 64-bit swap first (ie., file + * created on a 64-bit host), and check if the hostname feature + * bit is set (this feature bit is forced on as of fbe96f2). + * If the bit is not, undo the 64-bit swap and try a 32-bit + * swap. If the hostname bit is still not set (e.g., older data + * file), punt and fallback to the original behavior -- + * clearing all feature bits and setting buildid. + */ + for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i) + header->adds_features[i] = bswap_64(header->adds_features[i]); + + if (!test_bit(HEADER_HOSTNAME, header->adds_features)) { + for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i) { + header->adds_features[i] = bswap_64(header->adds_features[i]); + header->adds_features[i] = bswap_32(header->adds_features[i]); + } + } + + if (!test_bit(HEADER_HOSTNAME, header->adds_features)) { + bitmap_zero(header->adds_features, HEADER_FEAT_BITS); + set_bit(HEADER_BUILD_ID, header->adds_features); + } } memcpy(&ph->adds_features, &header->adds_features, sizeof(ph->adds_features)); - /* - * FIXME: hack that assumes that if we need swap the perf.data file - * may be coming from an arch with a different word-size, ergo different - * DEFINE_BITMAP format, investigate more later, but for now its mostly - * safe to assume that we have a build-id section. Trace files probably - * have several other issues in this realm anyway... - */ - if (ph->needs_swap) { - memset(&ph->adds_features, 0, sizeof(ph->adds_features)); - perf_header__set_feat(ph, HEADER_BUILD_ID); - } ph->event_offset = header->event_types.offset; ph->event_size = header->event_types.size; @@ -726,7 +1771,16 @@ static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, return -1; bev.header = old_bev.header; - bev.pid = 0; + + /* + * As the pid is the missing value, we need to fill + * it properly. The header.misc value give us nice hint. + */ + bev.pid = HOST_KERNEL_ID; + if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER || + bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL) + bev.pid = DEFAULT_GUEST_KERNEL_ID; + memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id)); __event_process_build_id(&bev, filename, session); @@ -787,7 +1841,7 @@ out: static int perf_file_section__process(struct perf_file_section *section, struct perf_header *ph, - int feat, int fd) + int feat, int fd, void *data __used) { if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { pr_debug("Failed to lseek to %" PRIu64 " offset for feature " @@ -795,17 +1849,21 @@ static int perf_file_section__process(struct perf_file_section *section, return 0; } + if (feat >= HEADER_LAST_FEATURE) { + pr_debug("unknown feature %d, continuing...\n", feat); + return 0; + } + switch (feat) { case HEADER_TRACE_INFO: trace_report(fd, false); break; - case HEADER_BUILD_ID: if (perf_header__read_build_ids(ph, fd, section->offset, section->size)) pr_debug("Failed to read buildids, continuing...\n"); break; default: - pr_debug("unknown feature %d, continuing...\n", feat); + break; } return 0; @@ -915,6 +1973,8 @@ int perf_session__read_header(struct perf_session *session, int fd) lseek(fd, tmp, SEEK_SET); } + symbol_conf.nr_events = nr_attrs; + if (f_header.event_types.size) { lseek(fd, f_header.event_types.offset, SEEK_SET); events = malloc(f_header.event_types.size); @@ -926,7 +1986,8 @@ int perf_session__read_header(struct perf_session *session, int fd) event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); } - perf_header__process_sections(header, fd, perf_file_section__process); + perf_header__process_sections(header, fd, NULL, + perf_file_section__process); lseek(fd, header->data_offset, SEEK_SET); @@ -941,9 +2002,9 @@ out_delete_evlist: return -ENOMEM; } -int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, - perf_event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_attr(struct perf_tool *tool, + struct perf_event_attr *attr, u16 ids, u64 *id, + perf_event__handler_t process) { union perf_event *ev; size_t size; @@ -965,22 +2026,23 @@ int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, ev->attr.header.type = PERF_RECORD_HEADER_ATTR; ev->attr.header.size = size; - err = process(ev, NULL, session); + err = process(tool, ev, NULL, NULL); free(ev); return err; } -int perf_session__synthesize_attrs(struct perf_session *session, +int perf_event__synthesize_attrs(struct perf_tool *tool, + struct perf_session *session, perf_event__handler_t process) { struct perf_evsel *attr; int err = 0; list_for_each_entry(attr, &session->evlist->entries, node) { - err = perf_event__synthesize_attr(&attr->attr, attr->ids, - attr->id, process, session); + err = perf_event__synthesize_attr(tool, &attr->attr, attr->ids, + attr->id, process); if (err) { pr_debug("failed to create perf header attribute\n"); return err; @@ -991,23 +2053,23 @@ int perf_session__synthesize_attrs(struct perf_session *session, } int perf_event__process_attr(union perf_event *event, - struct perf_session *session) + struct perf_evlist **pevlist) { unsigned int i, ids, n_ids; struct perf_evsel *evsel; + struct perf_evlist *evlist = *pevlist; - if (session->evlist == NULL) { - session->evlist = perf_evlist__new(NULL, NULL); - if (session->evlist == NULL) + if (evlist == NULL) { + *pevlist = evlist = perf_evlist__new(NULL, NULL); + if (evlist == NULL) return -ENOMEM; } - evsel = perf_evsel__new(&event->attr.attr, - session->evlist->nr_entries); + evsel = perf_evsel__new(&event->attr.attr, evlist->nr_entries); if (evsel == NULL) return -ENOMEM; - perf_evlist__add(session->evlist, evsel); + perf_evlist__add(evlist, evsel); ids = event->header.size; ids -= (void *)&event->attr.id - (void *)event; @@ -1021,18 +2083,16 @@ int perf_event__process_attr(union perf_event *event, return -ENOMEM; for (i = 0; i < n_ids; i++) { - perf_evlist__id_add(session->evlist, evsel, 0, i, - event->attr.id[i]); + perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]); } - perf_session__update_sample_type(session); - return 0; } -int perf_event__synthesize_event_type(u64 event_id, char *name, +int perf_event__synthesize_event_type(struct perf_tool *tool, + u64 event_id, char *name, perf_event__handler_t process, - struct perf_session *session) + struct machine *machine) { union perf_event ev; size_t size = 0; @@ -1050,13 +2110,14 @@ int perf_event__synthesize_event_type(u64 event_id, char *name, ev.event_type.header.size = sizeof(ev.event_type) - (sizeof(ev.event_type.event_type.name) - size); - err = process(&ev, NULL, session); + err = process(tool, &ev, NULL, machine); return err; } -int perf_event__synthesize_event_types(perf_event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_event_types(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) { struct perf_trace_event_type *type; int i, err = 0; @@ -1064,9 +2125,9 @@ int perf_event__synthesize_event_types(perf_event__handler_t process, for (i = 0; i < event_count; i++) { type = &events[i]; - err = perf_event__synthesize_event_type(type->event_id, + err = perf_event__synthesize_event_type(tool, type->event_id, type->name, process, - session); + machine); if (err) { pr_debug("failed to create perf header event type\n"); return err; @@ -1076,8 +2137,8 @@ int perf_event__synthesize_event_types(perf_event__handler_t process, return err; } -int perf_event__process_event_type(union perf_event *event, - struct perf_session *session __unused) +int perf_event__process_event_type(struct perf_tool *tool __unused, + union perf_event *event) { if (perf_header__push_event(event->event_type.event_type.event_id, event->event_type.event_type.name) < 0) @@ -1086,28 +2147,47 @@ int perf_event__process_event_type(union perf_event *event, return 0; } -int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist, - perf_event__handler_t process, - struct perf_session *session __unused) +int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, + struct perf_evlist *evlist, + perf_event__handler_t process) { union perf_event ev; + struct tracing_data *tdata; ssize_t size = 0, aligned_size = 0, padding; int err __used = 0; + /* + * We are going to store the size of the data followed + * by the data contents. Since the fd descriptor is a pipe, + * we cannot seek back to store the size of the data once + * we know it. Instead we: + * + * - write the tracing data to the temp file + * - get/write the data size to pipe + * - write the tracing data from the temp file + * to the pipe + */ + tdata = tracing_data_get(&evlist->entries, fd, true); + if (!tdata) + return -1; + memset(&ev, 0, sizeof(ev)); ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA; - size = read_tracing_data_size(fd, &evlist->entries); - if (size <= 0) - return size; + size = tdata->size; aligned_size = ALIGN(size, sizeof(u64)); padding = aligned_size - size; ev.tracing_data.header.size = sizeof(ev.tracing_data); ev.tracing_data.size = aligned_size; - process(&ev, NULL, session); + process(tool, &ev, NULL, NULL); + + /* + * The put function will copy all the tracing data + * stored in temp file to the pipe. + */ + tracing_data_put(tdata); - err = read_tracing_data(fd, &evlist->entries); write_padded(fd, NULL, 0, padding); return aligned_size; @@ -1142,10 +2222,10 @@ int perf_event__process_tracing_data(union perf_event *event, return size_read + padding; } -int perf_event__synthesize_build_id(struct dso *pos, u16 misc, +int perf_event__synthesize_build_id(struct perf_tool *tool, + struct dso *pos, u16 misc, perf_event__handler_t process, - struct machine *machine, - struct perf_session *session) + struct machine *machine) { union perf_event ev; size_t len; @@ -1165,12 +2245,13 @@ int perf_event__synthesize_build_id(struct dso *pos, u16 misc, ev.build_id.header.size = sizeof(ev.build_id) + len; memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len); - err = process(&ev, NULL, session); + err = process(tool, &ev, NULL, machine); return err; } -int perf_event__process_build_id(union perf_event *event, +int perf_event__process_build_id(struct perf_tool *tool __used, + union perf_event *event, struct perf_session *session) { __event_process_build_id(&event->build_id, diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 1886256768a1..ac4ec956024e 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -10,13 +10,27 @@ #include <linux/bitmap.h> enum { - HEADER_TRACE_INFO = 1, + HEADER_RESERVED = 0, /* always cleared */ + HEADER_TRACE_INFO = 1, HEADER_BUILD_ID, + + HEADER_HOSTNAME, + HEADER_OSRELEASE, + HEADER_VERSION, + HEADER_ARCH, + HEADER_NRCPUS, + HEADER_CPUDESC, + HEADER_CPUID, + HEADER_TOTAL_MEM, + HEADER_CMDLINE, + HEADER_EVENT_DESC, + HEADER_CPU_TOPOLOGY, + HEADER_NUMA_TOPOLOGY, + HEADER_LAST_FEATURE, + HEADER_FEAT_BITS = 256, }; -#define HEADER_FEAT_BITS 256 - struct perf_file_section { u64 offset; u64 size; @@ -54,6 +68,7 @@ struct perf_header { }; struct perf_evlist; +struct perf_session; int perf_session__read_header(struct perf_session *session, int fd); int perf_session__write_header(struct perf_session *session, @@ -68,40 +83,55 @@ void perf_header__set_feat(struct perf_header *header, int feat); void perf_header__clear_feat(struct perf_header *header, int feat); bool perf_header__has_feat(const struct perf_header *header, int feat); +int perf_header__set_cmdline(int argc, const char **argv); + int perf_header__process_sections(struct perf_header *header, int fd, + void *data, int (*process)(struct perf_file_section *section, - struct perf_header *ph, - int feat, int fd)); + struct perf_header *ph, + int feat, int fd, void *data)); + +int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full); int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, const char *name, bool is_kallsyms); int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir); -int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, - perf_event__handler_t process, - struct perf_session *session); -int perf_session__synthesize_attrs(struct perf_session *session, - perf_event__handler_t process); -int perf_event__process_attr(union perf_event *event, struct perf_session *session); +int perf_event__synthesize_attr(struct perf_tool *tool, + struct perf_event_attr *attr, u16 ids, u64 *id, + perf_event__handler_t process); +int perf_event__synthesize_attrs(struct perf_tool *tool, + struct perf_session *session, + perf_event__handler_t process); +int perf_event__process_attr(union perf_event *event, struct perf_evlist **pevlist); -int perf_event__synthesize_event_type(u64 event_id, char *name, +int perf_event__synthesize_event_type(struct perf_tool *tool, + u64 event_id, char *name, perf_event__handler_t process, - struct perf_session *session); -int perf_event__synthesize_event_types(perf_event__handler_t process, - struct perf_session *session); -int perf_event__process_event_type(union perf_event *event, - struct perf_session *session); - -int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist, - perf_event__handler_t process, - struct perf_session *session); + struct machine *machine); +int perf_event__synthesize_event_types(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine); +int perf_event__process_event_type(struct perf_tool *tool, + union perf_event *event); + +int perf_event__synthesize_tracing_data(struct perf_tool *tool, + int fd, struct perf_evlist *evlist, + perf_event__handler_t process); int perf_event__process_tracing_data(union perf_event *event, struct perf_session *session); -int perf_event__synthesize_build_id(struct dso *pos, u16 misc, +int perf_event__synthesize_build_id(struct perf_tool *tool, + struct dso *pos, u16 misc, perf_event__handler_t process, - struct machine *machine, - struct perf_session *session); -int perf_event__process_build_id(union perf_event *event, + struct machine *machine); +int perf_event__process_build_id(struct perf_tool *tool, + union perf_event *event, struct perf_session *session); + +/* + * arch specific callback + */ +int get_cpuid(char *buffer, size_t sz); + #endif /* __PERF_HEADER_H */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 677e1da6bb3e..6f505d1abac7 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -6,6 +6,11 @@ #include "sort.h" #include <math.h> +static bool hists__filter_entry_by_dso(struct hists *hists, + struct hist_entry *he); +static bool hists__filter_entry_by_thread(struct hists *hists, + struct hist_entry *he); + enum hist_filter { HIST_FILTER__DSO, HIST_FILTER__THREAD, @@ -18,80 +23,141 @@ struct callchain_param callchain_param = { .order = ORDER_CALLEE }; -u16 hists__col_len(struct hists *self, enum hist_column col) +u16 hists__col_len(struct hists *hists, enum hist_column col) { - return self->col_len[col]; + return hists->col_len[col]; } -void hists__set_col_len(struct hists *self, enum hist_column col, u16 len) +void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len) { - self->col_len[col] = len; + hists->col_len[col] = len; } -bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len) +bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len) { - if (len > hists__col_len(self, col)) { - hists__set_col_len(self, col, len); + if (len > hists__col_len(hists, col)) { + hists__set_col_len(hists, col, len); return true; } return false; } -static void hists__reset_col_len(struct hists *self) +static void hists__reset_col_len(struct hists *hists) { enum hist_column col; for (col = 0; col < HISTC_NR_COLS; ++col) - hists__set_col_len(self, col, 0); + hists__set_col_len(hists, col, 0); } -static void hists__calc_col_len(struct hists *self, struct hist_entry *h) +static void hists__calc_col_len(struct hists *hists, struct hist_entry *h) { u16 len; if (h->ms.sym) - hists__new_col_len(self, HISTC_SYMBOL, h->ms.sym->namelen); + hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen); else { const unsigned int unresolved_col_width = BITS_PER_LONG / 4; - if (hists__col_len(self, HISTC_DSO) < unresolved_col_width && + if (hists__col_len(hists, HISTC_DSO) < unresolved_col_width && !symbol_conf.col_width_list_str && !symbol_conf.field_sep && !symbol_conf.dso_list) - hists__set_col_len(self, HISTC_DSO, + hists__set_col_len(hists, HISTC_DSO, unresolved_col_width); } len = thread__comm_len(h->thread); - if (hists__new_col_len(self, HISTC_COMM, len)) - hists__set_col_len(self, HISTC_THREAD, len + 6); + if (hists__new_col_len(hists, HISTC_COMM, len)) + hists__set_col_len(hists, HISTC_THREAD, len + 6); if (h->ms.map) { len = dso__name_len(h->ms.map->dso); - hists__new_col_len(self, HISTC_DSO, len); + hists__new_col_len(hists, HISTC_DSO, len); } } -static void hist_entry__add_cpumode_period(struct hist_entry *self, +static void hist_entry__add_cpumode_period(struct hist_entry *he, unsigned int cpumode, u64 period) { switch (cpumode) { case PERF_RECORD_MISC_KERNEL: - self->period_sys += period; + he->period_sys += period; break; case PERF_RECORD_MISC_USER: - self->period_us += period; + he->period_us += period; break; case PERF_RECORD_MISC_GUEST_KERNEL: - self->period_guest_sys += period; + he->period_guest_sys += period; break; case PERF_RECORD_MISC_GUEST_USER: - self->period_guest_us += period; + he->period_guest_us += period; break; default: break; } } +static void hist_entry__decay(struct hist_entry *he) +{ + he->period = (he->period * 7) / 8; + he->nr_events = (he->nr_events * 7) / 8; +} + +static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) +{ + u64 prev_period = he->period; + + if (prev_period == 0) + return true; + + hist_entry__decay(he); + + if (!he->filtered) + hists->stats.total_period -= prev_period - he->period; + + return he->period == 0; +} + +static void __hists__decay_entries(struct hists *hists, bool zap_user, + bool zap_kernel, bool threaded) +{ + struct rb_node *next = rb_first(&hists->entries); + struct hist_entry *n; + + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + /* + * We may be annotating this, for instance, so keep it here in + * case some it gets new samples, we'll eventually free it when + * the user stops browsing and it agains gets fully decayed. + */ + if (((zap_user && n->level == '.') || + (zap_kernel && n->level != '.') || + hists__decay_entry(hists, n)) && + !n->used) { + rb_erase(&n->rb_node, &hists->entries); + + if (sort__need_collapse || threaded) + rb_erase(&n->rb_node_in, &hists->entries_collapsed); + + hist_entry__free(n); + --hists->nr_entries; + } + } +} + +void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) +{ + return __hists__decay_entries(hists, zap_user, zap_kernel, false); +} + +void hists__decay_entries_threaded(struct hists *hists, + bool zap_user, bool zap_kernel) +{ + return __hists__decay_entries(hists, zap_user, zap_kernel, true); +} + /* * histogram, sorted on item, collects periods */ @@ -99,25 +165,26 @@ static void hist_entry__add_cpumode_period(struct hist_entry *self, static struct hist_entry *hist_entry__new(struct hist_entry *template) { size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0; - struct hist_entry *self = malloc(sizeof(*self) + callchain_size); + struct hist_entry *he = malloc(sizeof(*he) + callchain_size); - if (self != NULL) { - *self = *template; - self->nr_events = 1; - if (self->ms.map) - self->ms.map->referenced = true; + if (he != NULL) { + *he = *template; + he->nr_events = 1; + if (he->ms.map) + he->ms.map->referenced = true; if (symbol_conf.use_callchain) - callchain_init(self->callchain); + callchain_init(he->callchain); } - return self; + return he; } -static void hists__inc_nr_entries(struct hists *self, struct hist_entry *h) +static void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h) { if (!h->filtered) { - hists__calc_col_len(self, h); - ++self->nr_entries; + hists__calc_col_len(hists, h); + ++hists->nr_entries; + hists->stats.total_period += h->period; } } @@ -128,11 +195,11 @@ static u8 symbol__parent_filter(const struct symbol *parent) return 0; } -struct hist_entry *__hists__add_entry(struct hists *self, +struct hist_entry *__hists__add_entry(struct hists *hists, struct addr_location *al, struct symbol *sym_parent, u64 period) { - struct rb_node **p = &self->entries.rb_node; + struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; struct hist_entry entry = { @@ -150,9 +217,13 @@ struct hist_entry *__hists__add_entry(struct hists *self, }; int cmp; + pthread_mutex_lock(&hists->lock); + + p = &hists->entries_in->rb_node; + while (*p != NULL) { parent = *p; - he = rb_entry(parent, struct hist_entry, rb_node); + he = rb_entry(parent, struct hist_entry, rb_node_in); cmp = hist_entry__cmp(&entry, he); @@ -170,12 +241,14 @@ struct hist_entry *__hists__add_entry(struct hists *self, he = hist_entry__new(&entry); if (!he) - return NULL; - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, &self->entries); - hists__inc_nr_entries(self, he); + goto out_unlock; + + rb_link_node(&he->rb_node_in, parent, p); + rb_insert_color(&he->rb_node_in, hists->entries_in); out: hist_entry__add_cpumode_period(he, al->cpumode, period); +out_unlock: + pthread_mutex_unlock(&hists->lock); return he; } @@ -222,7 +295,7 @@ void hist_entry__free(struct hist_entry *he) * collapse the histogram */ -static bool hists__collapse_insert_entry(struct hists *self, +static bool hists__collapse_insert_entry(struct hists *hists, struct rb_root *root, struct hist_entry *he) { @@ -233,15 +306,16 @@ static bool hists__collapse_insert_entry(struct hists *self, while (*p != NULL) { parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); + iter = rb_entry(parent, struct hist_entry, rb_node_in); cmp = hist_entry__collapse(iter, he); if (!cmp) { iter->period += he->period; + iter->nr_events += he->nr_events; if (symbol_conf.use_callchain) { - callchain_cursor_reset(&self->callchain_cursor); - callchain_merge(&self->callchain_cursor, iter->callchain, + callchain_cursor_reset(&hists->callchain_cursor); + callchain_merge(&hists->callchain_cursor, iter->callchain, he->callchain); } hist_entry__free(he); @@ -254,35 +328,68 @@ static bool hists__collapse_insert_entry(struct hists *self, p = &(*p)->rb_right; } - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, root); + rb_link_node(&he->rb_node_in, parent, p); + rb_insert_color(&he->rb_node_in, root); return true; } -void hists__collapse_resort(struct hists *self) +static struct rb_root *hists__get_rotate_entries_in(struct hists *hists) { - struct rb_root tmp; + struct rb_root *root; + + pthread_mutex_lock(&hists->lock); + + root = hists->entries_in; + if (++hists->entries_in > &hists->entries_in_array[1]) + hists->entries_in = &hists->entries_in_array[0]; + + pthread_mutex_unlock(&hists->lock); + + return root; +} + +static void hists__apply_filters(struct hists *hists, struct hist_entry *he) +{ + hists__filter_entry_by_dso(hists, he); + hists__filter_entry_by_thread(hists, he); +} + +static void __hists__collapse_resort(struct hists *hists, bool threaded) +{ + struct rb_root *root; struct rb_node *next; struct hist_entry *n; - if (!sort__need_collapse) + if (!sort__need_collapse && !threaded) return; - tmp = RB_ROOT; - next = rb_first(&self->entries); - self->nr_entries = 0; - hists__reset_col_len(self); + root = hists__get_rotate_entries_in(hists); + next = rb_first(root); while (next) { - n = rb_entry(next, struct hist_entry, rb_node); - next = rb_next(&n->rb_node); - - rb_erase(&n->rb_node, &self->entries); - if (hists__collapse_insert_entry(self, &tmp, n)) - hists__inc_nr_entries(self, n); + n = rb_entry(next, struct hist_entry, rb_node_in); + next = rb_next(&n->rb_node_in); + + rb_erase(&n->rb_node_in, root); + if (hists__collapse_insert_entry(hists, &hists->entries_collapsed, n)) { + /* + * If it wasn't combined with one of the entries already + * collapsed, we need to apply the filters that may have + * been set by, say, the hist_browser. + */ + hists__apply_filters(hists, n); + } } +} - self->entries = tmp; +void hists__collapse_resort(struct hists *hists) +{ + return __hists__collapse_resort(hists, false); +} + +void hists__collapse_resort_threaded(struct hists *hists) +{ + return __hists__collapse_resort(hists, true); } /* @@ -315,31 +422,44 @@ static void __hists__insert_output_entry(struct rb_root *entries, rb_insert_color(&he->rb_node, entries); } -void hists__output_resort(struct hists *self) +static void __hists__output_resort(struct hists *hists, bool threaded) { - struct rb_root tmp; + struct rb_root *root; struct rb_node *next; struct hist_entry *n; u64 min_callchain_hits; - min_callchain_hits = self->stats.total_period * (callchain_param.min_percent / 100); + min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100); + + if (sort__need_collapse || threaded) + root = &hists->entries_collapsed; + else + root = hists->entries_in; - tmp = RB_ROOT; - next = rb_first(&self->entries); + next = rb_first(root); + hists->entries = RB_ROOT; - self->nr_entries = 0; - hists__reset_col_len(self); + hists->nr_entries = 0; + hists->stats.total_period = 0; + hists__reset_col_len(hists); while (next) { - n = rb_entry(next, struct hist_entry, rb_node); - next = rb_next(&n->rb_node); + n = rb_entry(next, struct hist_entry, rb_node_in); + next = rb_next(&n->rb_node_in); - rb_erase(&n->rb_node, &self->entries); - __hists__insert_output_entry(&tmp, n, min_callchain_hits); - hists__inc_nr_entries(self, n); + __hists__insert_output_entry(&hists->entries, n, min_callchain_hits); + hists__inc_nr_entries(hists, n); } +} + +void hists__output_resort(struct hists *hists) +{ + return __hists__output_resort(hists, false); +} - self->entries = tmp; +void hists__output_resort_threaded(struct hists *hists) +{ + return __hists__output_resort(hists, true); } static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) @@ -557,15 +677,16 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self, return ret; } -static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, - u64 total_samples, int left_margin) +static size_t hist_entry_callchain__fprintf(struct hist_entry *he, + u64 total_samples, int left_margin, + FILE *fp) { struct rb_node *rb_node; struct callchain_node *chain; size_t ret = 0; u32 entries_printed = 0; - rb_node = rb_first(&self->sorted_chain); + rb_node = rb_first(&he->sorted_chain); while (rb_node) { double percent; @@ -594,36 +715,51 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, return ret; } -int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, - struct hists *hists, struct hists *pair_hists, - bool show_displacement, long displacement, - bool color, u64 session_total) +void hists__output_recalc_col_len(struct hists *hists, int max_rows) +{ + struct rb_node *next = rb_first(&hists->entries); + struct hist_entry *n; + int row = 0; + + hists__reset_col_len(hists); + + while (next && row++ < max_rows) { + n = rb_entry(next, struct hist_entry, rb_node); + if (!n->filtered) + hists__calc_col_len(hists, n); + next = rb_next(&n->rb_node); + } +} + +static int hist_entry__pcnt_snprintf(struct hist_entry *he, char *s, + size_t size, struct hists *pair_hists, + bool show_displacement, long displacement, + bool color, u64 total_period) { - struct sort_entry *se; u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us; u64 nr_events; const char *sep = symbol_conf.field_sep; int ret; - if (symbol_conf.exclude_other && !self->parent) + if (symbol_conf.exclude_other && !he->parent) return 0; if (pair_hists) { - period = self->pair ? self->pair->period : 0; - nr_events = self->pair ? self->pair->nr_events : 0; + period = he->pair ? he->pair->period : 0; + nr_events = he->pair ? he->pair->nr_events : 0; total = pair_hists->stats.total_period; - period_sys = self->pair ? self->pair->period_sys : 0; - period_us = self->pair ? self->pair->period_us : 0; - period_guest_sys = self->pair ? self->pair->period_guest_sys : 0; - period_guest_us = self->pair ? self->pair->period_guest_us : 0; + period_sys = he->pair ? he->pair->period_sys : 0; + period_us = he->pair ? he->pair->period_us : 0; + period_guest_sys = he->pair ? he->pair->period_guest_sys : 0; + period_guest_us = he->pair ? he->pair->period_guest_us : 0; } else { - period = self->period; - nr_events = self->nr_events; - total = session_total; - period_sys = self->period_sys; - period_us = self->period_us; - period_guest_sys = self->period_guest_sys; - period_guest_us = self->period_guest_us; + period = he->period; + nr_events = he->nr_events; + total = total_period; + period_sys = he->period_sys; + period_us = he->period_us; + period_guest_sys = he->period_guest_sys; + period_guest_us = he->period_guest_us; } if (total) { @@ -664,14 +800,21 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, ret += snprintf(s + ret, size - ret, "%11" PRIu64, nr_events); } + if (symbol_conf.show_total_period) { + if (sep) + ret += snprintf(s + ret, size - ret, "%c%" PRIu64, *sep, period); + else + ret += snprintf(s + ret, size - ret, " %12" PRIu64, period); + } + if (pair_hists) { char bf[32]; double old_percent = 0, new_percent = 0, diff; if (total > 0) old_percent = (period * 100.0) / total; - if (session_total > 0) - new_percent = (self->period * 100.0) / session_total; + if (total_period > 0) + new_percent = (he->period * 100.0) / total_period; diff = new_percent - old_percent; @@ -698,32 +841,49 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, } } + return ret; +} + +int hist_entry__snprintf(struct hist_entry *he, char *s, size_t size, + struct hists *hists) +{ + const char *sep = symbol_conf.field_sep; + struct sort_entry *se; + int ret = 0; + list_for_each_entry(se, &hist_entry__sort_list, list) { if (se->elide) continue; ret += snprintf(s + ret, size - ret, "%s", sep ?: " "); - ret += se->se_snprintf(self, s + ret, size - ret, + ret += se->se_snprintf(he, s + ret, size - ret, hists__col_len(hists, se->se_width_idx)); } return ret; } -int hist_entry__fprintf(struct hist_entry *self, struct hists *hists, - struct hists *pair_hists, bool show_displacement, - long displacement, FILE *fp, u64 session_total) +static int hist_entry__fprintf(struct hist_entry *he, size_t size, + struct hists *hists, struct hists *pair_hists, + bool show_displacement, long displacement, + u64 total_period, FILE *fp) { char bf[512]; - hist_entry__snprintf(self, bf, sizeof(bf), hists, pair_hists, - show_displacement, displacement, - true, session_total); + int ret; + + if (size == 0 || size > sizeof(bf)) + size = sizeof(bf); + + ret = hist_entry__pcnt_snprintf(he, bf, size, pair_hists, + show_displacement, displacement, + true, total_period); + hist_entry__snprintf(he, bf + ret, size - ret, hists); return fprintf(fp, "%s\n", bf); } -static size_t hist_entry__fprintf_callchain(struct hist_entry *self, - struct hists *hists, FILE *fp, - u64 session_total) +static size_t hist_entry__fprintf_callchain(struct hist_entry *he, + struct hists *hists, + u64 total_period, FILE *fp) { int left_margin = 0; @@ -731,35 +891,33 @@ static size_t hist_entry__fprintf_callchain(struct hist_entry *self, struct sort_entry *se = list_first_entry(&hist_entry__sort_list, typeof(*se), list); left_margin = hists__col_len(hists, se->se_width_idx); - left_margin -= thread__comm_len(self->thread); + left_margin -= thread__comm_len(he->thread); } - return hist_entry_callchain__fprintf(fp, self, session_total, - left_margin); + return hist_entry_callchain__fprintf(he, total_period, left_margin, fp); } -size_t hists__fprintf(struct hists *self, struct hists *pair, - bool show_displacement, FILE *fp) +size_t hists__fprintf(struct hists *hists, struct hists *pair, + bool show_displacement, bool show_header, int max_rows, + int max_cols, FILE *fp) { struct sort_entry *se; struct rb_node *nd; size_t ret = 0; + u64 total_period; unsigned long position = 1; long displacement = 0; unsigned int width; const char *sep = symbol_conf.field_sep; const char *col_width = symbol_conf.col_width_list_str; + int nr_rows = 0; init_rem_hits(); - fprintf(fp, "# %s", pair ? "Baseline" : "Overhead"); + if (!show_header) + goto print_entries; - if (symbol_conf.show_nr_samples) { - if (sep) - fprintf(fp, "%cSamples", *sep); - else - fputs(" Samples ", fp); - } + fprintf(fp, "# %s", pair ? "Baseline" : "Overhead"); if (symbol_conf.show_cpu_utilization) { if (sep) { @@ -770,8 +928,8 @@ size_t hists__fprintf(struct hists *self, struct hists *pair, ret += fprintf(fp, "%cguest us", *sep); } } else { - ret += fprintf(fp, " sys "); - ret += fprintf(fp, " us "); + ret += fprintf(fp, " sys "); + ret += fprintf(fp, " us "); if (perf_guest) { ret += fprintf(fp, " guest sys "); ret += fprintf(fp, " guest us "); @@ -779,6 +937,20 @@ size_t hists__fprintf(struct hists *self, struct hists *pair, } } + if (symbol_conf.show_nr_samples) { + if (sep) + fprintf(fp, "%cSamples", *sep); + else + fputs(" Samples ", fp); + } + + if (symbol_conf.show_total_period) { + if (sep) + ret += fprintf(fp, "%cPeriod", *sep); + else + ret += fprintf(fp, " Period "); + } + if (pair) { if (sep) ret += fprintf(fp, "%cDelta", *sep); @@ -803,25 +975,32 @@ size_t hists__fprintf(struct hists *self, struct hists *pair, width = strlen(se->se_header); if (symbol_conf.col_width_list_str) { if (col_width) { - hists__set_col_len(self, se->se_width_idx, + hists__set_col_len(hists, se->se_width_idx, atoi(col_width)); col_width = strchr(col_width, ','); if (col_width) ++col_width; } } - if (!hists__new_col_len(self, se->se_width_idx, width)) - width = hists__col_len(self, se->se_width_idx); + if (!hists__new_col_len(hists, se->se_width_idx, width)) + width = hists__col_len(hists, se->se_width_idx); fprintf(fp, " %*s", width, se->se_header); } + fprintf(fp, "\n"); + if (max_rows && ++nr_rows >= max_rows) + goto out; if (sep) goto print_entries; fprintf(fp, "# ........"); + if (symbol_conf.show_cpu_utilization) + fprintf(fp, " ....... ......."); if (symbol_conf.show_nr_samples) fprintf(fp, " .........."); + if (symbol_conf.show_total_period) + fprintf(fp, " ............"); if (pair) { fprintf(fp, " .........."); if (show_displacement) @@ -834,17 +1013,25 @@ size_t hists__fprintf(struct hists *self, struct hists *pair, continue; fprintf(fp, " "); - width = hists__col_len(self, se->se_width_idx); + width = hists__col_len(hists, se->se_width_idx); if (width == 0) width = strlen(se->se_header); for (i = 0; i < width; i++) fprintf(fp, "."); } - fprintf(fp, "\n#\n"); + fprintf(fp, "\n"); + if (max_rows && ++nr_rows >= max_rows) + goto out; + + fprintf(fp, "#\n"); + if (max_rows && ++nr_rows >= max_rows) + goto out; print_entries: - for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { + total_period = hists->stats.total_period; + + for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); if (h->filtered) @@ -858,19 +1045,21 @@ print_entries: displacement = 0; ++position; } - ret += hist_entry__fprintf(h, self, pair, show_displacement, - displacement, fp, self->stats.total_period); + ret += hist_entry__fprintf(h, max_cols, hists, pair, show_displacement, + displacement, total_period, fp); if (symbol_conf.use_callchain) - ret += hist_entry__fprintf_callchain(h, self, fp, - self->stats.total_period); + ret += hist_entry__fprintf_callchain(h, hists, total_period, fp); + if (max_rows && ++nr_rows >= max_rows) + goto out; + if (h->ms.map == NULL && verbose > 1) { __map_groups__fprintf_maps(&h->thread->mg, MAP__FUNCTION, verbose, fp); fprintf(fp, "%.10s end\n", graph_dotted_line); } } - +out: free(rem_sq_bracket); return ret; @@ -879,7 +1068,7 @@ print_entries: /* * See hists__fprintf to match the column widths */ -unsigned int hists__sort_list_width(struct hists *self) +unsigned int hists__sort_list_width(struct hists *hists) { struct sort_entry *se; int ret = 9; /* total % */ @@ -896,9 +1085,12 @@ unsigned int hists__sort_list_width(struct hists *self) if (symbol_conf.show_nr_samples) ret += 11; + if (symbol_conf.show_total_period) + ret += 13; + list_for_each_entry(se, &hist_entry__sort_list, list) if (!se->elide) - ret += 2 + hists__col_len(self, se->se_width_idx); + ret += 2 + hists__col_len(hists, se->se_width_idx); if (verbose) /* Addr + origin */ ret += 3 + BITS_PER_LONG / 4; @@ -906,63 +1098,84 @@ unsigned int hists__sort_list_width(struct hists *self) return ret; } -static void hists__remove_entry_filter(struct hists *self, struct hist_entry *h, +static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h, enum hist_filter filter) { h->filtered &= ~(1 << filter); if (h->filtered) return; - ++self->nr_entries; + ++hists->nr_entries; if (h->ms.unfolded) - self->nr_entries += h->nr_rows; + hists->nr_entries += h->nr_rows; h->row_offset = 0; - self->stats.total_period += h->period; - self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events; + hists->stats.total_period += h->period; + hists->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events; - hists__calc_col_len(self, h); + hists__calc_col_len(hists, h); } -void hists__filter_by_dso(struct hists *self, const struct dso *dso) + +static bool hists__filter_entry_by_dso(struct hists *hists, + struct hist_entry *he) +{ + if (hists->dso_filter != NULL && + (he->ms.map == NULL || he->ms.map->dso != hists->dso_filter)) { + he->filtered |= (1 << HIST_FILTER__DSO); + return true; + } + + return false; +} + +void hists__filter_by_dso(struct hists *hists) { struct rb_node *nd; - self->nr_entries = self->stats.total_period = 0; - self->stats.nr_events[PERF_RECORD_SAMPLE] = 0; - hists__reset_col_len(self); + hists->nr_entries = hists->stats.total_period = 0; + hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0; + hists__reset_col_len(hists); - for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { + for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); if (symbol_conf.exclude_other && !h->parent) continue; - if (dso != NULL && (h->ms.map == NULL || h->ms.map->dso != dso)) { - h->filtered |= (1 << HIST_FILTER__DSO); + if (hists__filter_entry_by_dso(hists, h)) continue; - } - hists__remove_entry_filter(self, h, HIST_FILTER__DSO); + hists__remove_entry_filter(hists, h, HIST_FILTER__DSO); } } -void hists__filter_by_thread(struct hists *self, const struct thread *thread) +static bool hists__filter_entry_by_thread(struct hists *hists, + struct hist_entry *he) +{ + if (hists->thread_filter != NULL && + he->thread != hists->thread_filter) { + he->filtered |= (1 << HIST_FILTER__THREAD); + return true; + } + + return false; +} + +void hists__filter_by_thread(struct hists *hists) { struct rb_node *nd; - self->nr_entries = self->stats.total_period = 0; - self->stats.nr_events[PERF_RECORD_SAMPLE] = 0; - hists__reset_col_len(self); + hists->nr_entries = hists->stats.total_period = 0; + hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0; + hists__reset_col_len(hists); - for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { + for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - if (thread != NULL && h->thread != thread) { - h->filtered |= (1 << HIST_FILTER__THREAD); + if (hists__filter_entry_by_thread(hists, h)) continue; - } - hists__remove_entry_filter(self, h, HIST_FILTER__THREAD); + hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD); } } @@ -976,13 +1189,13 @@ int hist_entry__annotate(struct hist_entry *he, size_t privsize) return symbol__annotate(he->ms.sym, he->ms.map, privsize); } -void hists__inc_nr_events(struct hists *self, u32 type) +void hists__inc_nr_events(struct hists *hists, u32 type) { - ++self->stats.nr_events[0]; - ++self->stats.nr_events[type]; + ++hists->stats.nr_events[0]; + ++hists->stats.nr_events[type]; } -size_t hists__fprintf_nr_events(struct hists *self, FILE *fp) +size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp) { int i; size_t ret = 0; @@ -990,7 +1203,7 @@ size_t hists__fprintf_nr_events(struct hists *self, FILE *fp) for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) { const char *name; - if (self->stats.nr_events[i] == 0) + if (hists->stats.nr_events[i] == 0) continue; name = perf_event__name(i); @@ -998,7 +1211,7 @@ size_t hists__fprintf_nr_events(struct hists *self, FILE *fp) continue; ret += fprintf(fp, "%16s events: %10d\n", name, - self->stats.nr_events[i]); + hists->stats.nr_events[i]); } return ret; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 3beb97c4d822..f55f0a8d1f81 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -2,6 +2,7 @@ #define __PERF_HIST_H #include <linux/types.h> +#include <pthread.h> #include "callchain.h" extern struct callchain_param callchain_param; @@ -27,6 +28,7 @@ struct events_stats { u64 total_lost; u64 total_invalid_chains; u32 nr_events[PERF_RECORD_HEADER_MAX]; + u32 nr_lost_warned; u32 nr_unknown_events; u32 nr_invalid_chains; u32 nr_unknown_id; @@ -42,9 +44,18 @@ enum hist_column { HISTC_NR_COLS, /* Last entry */ }; +struct thread; +struct dso; + struct hists { + struct rb_root entries_in_array[2]; + struct rb_root *entries_in; struct rb_root entries; + struct rb_root entries_collapsed; u64 nr_entries; + const struct thread *thread_filter; + const struct dso *dso_filter; + pthread_mutex_t lock; struct events_stats stats; u64 event_stream; u16 col_len[HISTC_NR_COLS]; @@ -55,31 +66,34 @@ struct hists { struct hist_entry *__hists__add_entry(struct hists *self, struct addr_location *al, struct symbol *parent, u64 period); -extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *); -extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *); -int hist_entry__fprintf(struct hist_entry *self, struct hists *hists, - struct hists *pair_hists, bool show_displacement, - long displacement, FILE *fp, u64 total); +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__snprintf(struct hist_entry *self, char *bf, size_t size, - struct hists *hists, struct hists *pair_hists, - bool show_displacement, long displacement, - bool color, u64 total); + struct hists *hists); void hist_entry__free(struct hist_entry *); void hists__output_resort(struct hists *self); +void hists__output_resort_threaded(struct hists *hists); void hists__collapse_resort(struct hists *self); +void hists__collapse_resort_threaded(struct hists *hists); + +void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); +void hists__decay_entries_threaded(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_events(struct hists *self, u32 type); size_t hists__fprintf_nr_events(struct hists *self, FILE *fp); size_t hists__fprintf(struct hists *self, struct hists *pair, - bool show_displacement, FILE *fp); + bool show_displacement, bool show_header, + int max_rows, int max_cols, FILE *fp); int hist_entry__inc_addr_samples(struct hist_entry *self, int evidx, u64 addr); int hist_entry__annotate(struct hist_entry *self, size_t privsize); -void hists__filter_by_dso(struct hists *self, const struct dso *dso); -void hists__filter_by_thread(struct hists *self, const struct thread *thread); +void hists__filter_by_dso(struct hists *hists); +void hists__filter_by_thread(struct hists *hists); u16 hists__col_len(struct hists *self, enum hist_column col); void hists__set_col_len(struct hists *self, enum hist_column col, u16 len); @@ -90,26 +104,32 @@ struct perf_evlist; #ifdef NO_NEWT_SUPPORT static inline int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __used, - const char *help __used) + const char *help __used, + void(*timer)(void *arg) __used, + void *arg __used, + int refresh __used) { return 0; } static inline int hist_entry__tui_annotate(struct hist_entry *self __used, - int evidx __used) + int evidx __used, + void(*timer)(void *arg) __used, + void *arg __used, + int delay_secs __used) { return 0; } -#define KEY_LEFT -1 -#define KEY_RIGHT -2 +#define K_LEFT -1 +#define K_RIGHT -2 #else -#include <newt.h> -int hist_entry__tui_annotate(struct hist_entry *self, int evidx); - -#define KEY_LEFT NEWT_KEY_LEFT -#define KEY_RIGHT NEWT_KEY_RIGHT +#include "ui/keysyms.h" +int hist_entry__tui_annotate(struct hist_entry *he, int evidx, + void(*timer)(void *arg), void *arg, int delay_secs); -int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help); +int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, + void(*timer)(void *arg), void *arg, + int refresh); #endif unsigned int hists__sort_list_width(struct hists *self); diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h index 305c8484f200..62cdee78db7b 100644 --- a/tools/perf/util/include/linux/bitops.h +++ b/tools/perf/util/include/linux/bitops.h @@ -9,6 +9,17 @@ #define BITS_PER_BYTE 8 #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) +#define for_each_set_bit(bit, addr, size) \ + for ((bit) = find_first_bit((addr), (size)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + +/* same as for_each_set_bit() but use bit as value to start with */ +#define for_each_set_bit_cont(bit, addr, size) \ + for ((bit) = find_next_bit((addr), (size), (bit)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + static inline void set_bit(int nr, unsigned long *addr) { addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG); @@ -30,4 +41,111 @@ static inline unsigned long hweight_long(unsigned long w) return sizeof(w) == 4 ? hweight32(w) : hweight64(w); } +#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) + +/** + * __ffs - find first bit in word. + * @word: The word to search + * + * Undefined if no bit exists, so code should check against 0 first. + */ +static __always_inline unsigned long __ffs(unsigned long word) +{ + int num = 0; + +#if BITS_PER_LONG == 64 + if ((word & 0xffffffff) == 0) { + num += 32; + word >>= 32; + } +#endif + if ((word & 0xffff) == 0) { + num += 16; + word >>= 16; + } + if ((word & 0xff) == 0) { + num += 8; + word >>= 8; + } + if ((word & 0xf) == 0) { + num += 4; + word >>= 4; + } + if ((word & 0x3) == 0) { + num += 2; + word >>= 2; + } + if ((word & 0x1) == 0) + num += 1; + return num; +} + +/* + * Find the first set bit in a memory region. + */ +static inline unsigned long +find_first_bit(const unsigned long *addr, unsigned long size) +{ + const unsigned long *p = addr; + unsigned long result = 0; + unsigned long tmp; + + while (size & ~(BITS_PER_LONG-1)) { + if ((tmp = *(p++))) + goto found; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + + tmp = (*p) & (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found: + return result + __ffs(tmp); +} + +/* + * Find the next set bit in a memory region. + */ +static inline unsigned long +find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) +{ + const unsigned long *p = addr + BITOP_WORD(offset); + unsigned long result = offset & ~(BITS_PER_LONG-1); + unsigned long tmp; + + if (offset >= size) + return size; + size -= result; + offset %= BITS_PER_LONG; + if (offset) { + tmp = *(p++); + tmp &= (~0UL << offset); + if (size < BITS_PER_LONG) + goto found_first; + if (tmp) + goto found_middle; + size -= BITS_PER_LONG; + result += BITS_PER_LONG; + } + while (size & ~(BITS_PER_LONG-1)) { + if ((tmp = *(p++))) + goto found_middle; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = *p; + +found_first: + tmp &= (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found_middle: + return result + __ffs(tmp); +} + #endif diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h index 791f9dd27ebf..547628e97f3d 100644 --- a/tools/perf/util/include/linux/compiler.h +++ b/tools/perf/util/include/linux/compiler.h @@ -5,7 +5,9 @@ #define __always_inline inline #endif #define __user +#ifndef __attribute_const__ #define __attribute_const__ +#endif #define __used __attribute__((__unused__)) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index a16ecab5229d..316aa0ab7122 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -18,6 +18,13 @@ static inline int is_anon_memory(const char *filename) return strcmp(filename, "//anon") == 0; } +static inline int is_no_dso_memory(const char *filename) +{ + return !strcmp(filename, "[stack]") || + !strcmp(filename, "[vdso]") || + !strcmp(filename, "[heap]"); +} + void map__init(struct map *self, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso) { @@ -42,9 +49,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, if (self != NULL) { char newfilename[PATH_MAX]; struct dso *dso; - int anon; + int anon, no_dso; anon = is_anon_memory(filename); + no_dso = is_no_dso_memory(filename); if (anon) { snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid); @@ -57,12 +65,16 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, map__init(self, type, start, start + len, pgoff, dso); - if (anon) { -set_identity: + if (anon || no_dso) { self->map_ip = self->unmap_ip = identity__map_ip; - } else if (strcmp(filename, "[vdso]") == 0) { - dso__set_loaded(dso, self->type); - goto set_identity; + + /* + * Set memory without DSO as loaded. All map__find_* + * functions still return NULL, and we avoid the + * unnecessary map__load warning. + */ + if (no_dso) + dso__set_loaded(dso, self->type); } } return self; @@ -127,8 +139,8 @@ int map__load(struct map *self, symbol_filter_t filter) if (len > sizeof(DSO__DELETED) && strcmp(name + real_len + 1, DSO__DELETED) == 0) { - pr_warning("%.*s was updated, restart the long " - "running apps that use it!\n", + pr_warning("%.*s was updated (is prelink enabled?). " + "Restart the long running apps that use it!\n", (int)real_len, name); } else { pr_warning("no symbols found in %s, maybe install " @@ -220,55 +232,55 @@ u64 map__objdump_2ip(struct map *map, u64 addr) return ip; } -void map_groups__init(struct map_groups *self) +void map_groups__init(struct map_groups *mg) { int i; for (i = 0; i < MAP__NR_TYPES; ++i) { - self->maps[i] = RB_ROOT; - INIT_LIST_HEAD(&self->removed_maps[i]); + mg->maps[i] = RB_ROOT; + INIT_LIST_HEAD(&mg->removed_maps[i]); } - self->machine = NULL; + mg->machine = NULL; } -static void maps__delete(struct rb_root *self) +static void maps__delete(struct rb_root *maps) { - struct rb_node *next = rb_first(self); + struct rb_node *next = rb_first(maps); while (next) { struct map *pos = rb_entry(next, struct map, rb_node); next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, self); + rb_erase(&pos->rb_node, maps); map__delete(pos); } } -static void maps__delete_removed(struct list_head *self) +static void maps__delete_removed(struct list_head *maps) { struct map *pos, *n; - list_for_each_entry_safe(pos, n, self, node) { + list_for_each_entry_safe(pos, n, maps, node) { list_del(&pos->node); map__delete(pos); } } -void map_groups__exit(struct map_groups *self) +void map_groups__exit(struct map_groups *mg) { int i; for (i = 0; i < MAP__NR_TYPES; ++i) { - maps__delete(&self->maps[i]); - maps__delete_removed(&self->removed_maps[i]); + maps__delete(&mg->maps[i]); + maps__delete_removed(&mg->removed_maps[i]); } } -void map_groups__flush(struct map_groups *self) +void map_groups__flush(struct map_groups *mg) { int type; for (type = 0; type < MAP__NR_TYPES; type++) { - struct rb_root *root = &self->maps[type]; + struct rb_root *root = &mg->maps[type]; struct rb_node *next = rb_first(root); while (next) { @@ -280,17 +292,17 @@ void map_groups__flush(struct map_groups *self) * instance in some hist_entry instances, so * just move them to a separate list. */ - list_add_tail(&pos->node, &self->removed_maps[pos->type]); + list_add_tail(&pos->node, &mg->removed_maps[pos->type]); } } } -struct symbol *map_groups__find_symbol(struct map_groups *self, +struct symbol *map_groups__find_symbol(struct map_groups *mg, enum map_type type, u64 addr, struct map **mapp, symbol_filter_t filter) { - struct map *map = map_groups__find(self, type, addr); + struct map *map = map_groups__find(mg, type, addr); if (map != NULL) { if (mapp != NULL) @@ -301,7 +313,7 @@ struct symbol *map_groups__find_symbol(struct map_groups *self, return NULL; } -struct symbol *map_groups__find_symbol_by_name(struct map_groups *self, +struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, enum map_type type, const char *name, struct map **mapp, @@ -309,7 +321,7 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *self, { struct rb_node *nd; - for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) { struct map *pos = rb_entry(nd, struct map, rb_node); struct symbol *sym = map__find_symbol_by_name(pos, name, filter); @@ -323,13 +335,13 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *self, return NULL; } -size_t __map_groups__fprintf_maps(struct map_groups *self, +size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, int verbose, FILE *fp) { size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); struct rb_node *nd; - for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) { struct map *pos = rb_entry(nd, struct map, rb_node); printed += fprintf(fp, "Map:"); printed += map__fprintf(pos, fp); @@ -342,22 +354,22 @@ size_t __map_groups__fprintf_maps(struct map_groups *self, return printed; } -size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp) +size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_maps(self, i, verbose, fp); + printed += __map_groups__fprintf_maps(mg, i, verbose, fp); return printed; } -static size_t __map_groups__fprintf_removed_maps(struct map_groups *self, +static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg, enum map_type type, int verbose, FILE *fp) { struct map *pos; size_t printed = 0; - list_for_each_entry(pos, &self->removed_maps[type], node) { + list_for_each_entry(pos, &mg->removed_maps[type], node) { printed += fprintf(fp, "Map:"); printed += map__fprintf(pos, fp); if (verbose > 1) { @@ -368,26 +380,26 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *self, return printed; } -static size_t map_groups__fprintf_removed_maps(struct map_groups *self, +static size_t map_groups__fprintf_removed_maps(struct map_groups *mg, int verbose, FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_removed_maps(self, i, verbose, fp); + printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp); return printed; } -size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp) +size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp) { - size_t printed = map_groups__fprintf_maps(self, verbose, fp); + size_t printed = map_groups__fprintf_maps(mg, verbose, fp); printed += fprintf(fp, "Removed maps:\n"); - return printed + map_groups__fprintf_removed_maps(self, verbose, fp); + return printed + map_groups__fprintf_removed_maps(mg, verbose, fp); } -int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, +int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, int verbose, FILE *fp) { - struct rb_root *root = &self->maps[map->type]; + struct rb_root *root = &mg->maps[map->type]; struct rb_node *next = rb_first(root); int err = 0; @@ -418,7 +430,7 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, } before->end = map->start - 1; - map_groups__insert(self, before); + map_groups__insert(mg, before); if (verbose >= 2) map__fprintf(before, fp); } @@ -432,7 +444,7 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, } after->start = map->end + 1; - map_groups__insert(self, after); + map_groups__insert(mg, after); if (verbose >= 2) map__fprintf(after, fp); } @@ -441,7 +453,7 @@ move_map: * If we have references, just move them to a separate list. */ if (pos->referenced) - list_add_tail(&pos->node, &self->removed_maps[map->type]); + list_add_tail(&pos->node, &mg->removed_maps[map->type]); else map__delete(pos); @@ -455,7 +467,7 @@ move_map: /* * XXX This should not really _copy_ te maps, but refcount them. */ -int map_groups__clone(struct map_groups *self, +int map_groups__clone(struct map_groups *mg, struct map_groups *parent, enum map_type type) { struct rb_node *nd; @@ -464,7 +476,7 @@ int map_groups__clone(struct map_groups *self, struct map *new = map__clone(map); if (new == NULL) return -ENOMEM; - map_groups__insert(self, new); + map_groups__insert(mg, new); } return 0; } @@ -550,6 +562,10 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid) INIT_LIST_HEAD(&self->user_dsos); INIT_LIST_HEAD(&self->kernel_dsos); + self->threads = RB_ROOT; + INIT_LIST_HEAD(&self->dead_threads); + self->last_match = NULL; + self->kmaps.machine = self; self->pid = pid; self->root_dir = strdup(root_dir); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index b397c0383728..2b8017f8a930 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -18,9 +18,11 @@ enum map_type { extern const char *map_type__name[MAP__NR_TYPES]; struct dso; +struct ip_callchain; struct ref_reloc_sym; struct map_groups; struct machine; +struct perf_evsel; struct map { union { @@ -61,7 +63,11 @@ struct map_groups { struct machine { struct rb_node rb_node; pid_t pid; + u16 id_hdr_size; char *root_dir; + struct rb_root threads; + struct list_head dead_threads; + struct thread *last_match; struct list_head user_dsos; struct list_head kernel_dsos; struct map_groups kmaps; @@ -123,17 +129,17 @@ void map__fixup_end(struct map *self); void map__reloc_vmlinux(struct map *self); -size_t __map_groups__fprintf_maps(struct map_groups *self, +size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, int verbose, FILE *fp); void maps__insert(struct rb_root *maps, struct map *map); -void maps__remove(struct rb_root *self, struct map *map); +void maps__remove(struct rb_root *maps, struct map *map); struct map *maps__find(struct rb_root *maps, u64 addr); -void map_groups__init(struct map_groups *self); -void map_groups__exit(struct map_groups *self); -int map_groups__clone(struct map_groups *self, +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 *self, int verbose, FILE *fp); -size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp); +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); typedef void (*machine__process_t)(struct machine *self, void *data); @@ -148,6 +154,13 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid); void machine__exit(struct machine *self); void machine__delete(struct machine *self); +int machine__resolve_callchain(struct machine *machine, + struct perf_evsel *evsel, struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent); +int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, + u64 addr); + /* * Default guest kernel is defined by parameter --guestkallsyms * and --guestmodules @@ -162,34 +175,40 @@ static inline bool machine__is_host(struct machine *self) return self ? self->pid == HOST_KERNEL_ID : false; } -static inline void map_groups__insert(struct map_groups *self, struct map *map) +static inline void map_groups__insert(struct map_groups *mg, struct map *map) { - maps__insert(&self->maps[map->type], map); - map->groups = self; + maps__insert(&mg->maps[map->type], map); + map->groups = mg; } -static inline void map_groups__remove(struct map_groups *self, struct map *map) +static inline void map_groups__remove(struct map_groups *mg, struct map *map) { - maps__remove(&self->maps[map->type], map); + maps__remove(&mg->maps[map->type], map); } -static inline struct map *map_groups__find(struct map_groups *self, +static inline struct map *map_groups__find(struct map_groups *mg, enum map_type type, u64 addr) { - return maps__find(&self->maps[type], addr); + return maps__find(&mg->maps[type], addr); } -struct symbol *map_groups__find_symbol(struct map_groups *self, +struct symbol *map_groups__find_symbol(struct map_groups *mg, enum map_type type, u64 addr, struct map **mapp, symbol_filter_t filter); -struct symbol *map_groups__find_symbol_by_name(struct map_groups *self, +struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, enum map_type type, const char *name, struct map **mapp, symbol_filter_t filter); + +struct thread *machine__findnew_thread(struct machine *machine, pid_t pid); +void machine__remove_thread(struct machine *machine, struct thread *th); + +size_t machine__fprintf(struct machine *machine, FILE *fp); + static inline struct symbol *machine__find_kernel_symbol(struct machine *self, enum map_type type, u64 addr, @@ -208,11 +227,11 @@ struct symbol *machine__find_kernel_function(struct machine *self, u64 addr, } static inline -struct symbol *map_groups__find_function_by_name(struct map_groups *self, +struct symbol *map_groups__find_function_by_name(struct map_groups *mg, const char *name, struct map **mapp, symbol_filter_t filter) { - return map_groups__find_symbol_by_name(self, MAP__FUNCTION, name, mapp, filter); + return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter); } static inline @@ -225,13 +244,13 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *self, filter); } -int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, +int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, int verbose, FILE *fp); -struct map *map_groups__find_by_name(struct map_groups *self, +struct map *map_groups__find_by_name(struct map_groups *mg, enum map_type type, const char *name); struct map *machine__new_module(struct machine *self, u64 start, const char *filename); -void map_groups__flush(struct map_groups *self); +void map_groups__flush(struct map_groups *mg); #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4ea7e19f5251..b029296d20d9 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -25,8 +25,6 @@ enum event_result { EVT_HANDLED_ALL }; -char debugfs_path[MAXPATHLEN]; - #define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x #define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x @@ -40,6 +38,7 @@ static struct event_symbol event_symbols[] = { { CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" }, { CHW(BRANCH_MISSES), "branch-misses", "" }, { CHW(BUS_CYCLES), "bus-cycles", "" }, + { CHW(REF_CPU_CYCLES), "ref-cycles", "" }, { CSW(CPU_CLOCK), "cpu-clock", "" }, { CSW(TASK_CLOCK), "task-clock", "" }, @@ -70,6 +69,7 @@ static const char *hw_event_names[PERF_COUNT_HW_MAX] = { "bus-cycles", "stalled-cycles-frontend", "stalled-cycles-backend", + "ref-cycles", }; static const char *sw_event_names[PERF_COUNT_SW_MAX] = { @@ -140,7 +140,7 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) char evt_path[MAXPATHLEN]; int fd; - snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path, + snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path, sys_dir->d_name, evt_dir->d_name); fd = open(evt_path, O_RDONLY); if (fd < 0) @@ -171,16 +171,16 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(debugfs_path)) + if (debugfs_valid_mountpoint(tracing_events_path)) return NULL; - sys_dir = opendir(debugfs_path); + sys_dir = opendir(tracing_events_path); if (!sys_dir) return NULL; for_each_subsystem(sys_dir, sys_dirent, sys_next) { - snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path, + snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_dirent.d_name); evt_dir = opendir(dir_path); if (!evt_dir) @@ -447,7 +447,7 @@ parse_single_tracepoint_event(char *sys_name, u64 id; int fd; - snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path, + snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path, sys_name, evt_name); fd = open(evt_path, O_RDONLY); @@ -485,7 +485,7 @@ parse_multiple_tracepoint_event(struct perf_evlist *evlist, char *sys_name, struct dirent *evt_ent; DIR *evt_dir; - snprintf(evt_path, MAXPATHLEN, "%s/%s", debugfs_path, sys_name); + snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name); evt_dir = opendir(evt_path); if (!evt_dir) { @@ -528,7 +528,7 @@ parse_tracepoint_event(struct perf_evlist *evlist, const char **strp, char sys_name[MAX_EVENT_LENGTH]; unsigned int sys_length, evt_length; - if (debugfs_valid_mountpoint(debugfs_path)) + if (debugfs_valid_mountpoint(tracing_events_path)) return 0; evt_name = strchr(*strp, ':'); @@ -697,7 +697,11 @@ parse_raw_event(const char **strp, struct perf_event_attr *attr) return EVT_FAILED; n = hex2u64(str + 1, &config); if (n > 0) { - *strp = str + n + 1; + const char *end = str + n + 1; + if (*end != '\0' && *end != ',' && *end != ':') + return EVT_FAILED; + + *strp = end; attr->type = PERF_TYPE_RAW; attr->config = config; return EVT_HANDLED; @@ -731,8 +735,8 @@ static int parse_event_modifier(const char **strp, struct perf_event_attr *attr) { const char *str = *strp; - int exclude = 0; - int eu = 0, ek = 0, eh = 0, precise = 0; + int exclude = 0, exclude_GH = 0; + int eu = 0, ek = 0, eh = 0, eH = 0, eG = 0, precise = 0; if (!*str) return 0; @@ -756,6 +760,14 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr) if (!exclude) exclude = eu = ek = eh = 1; eh = 0; + } else if (*str == 'G') { + if (!exclude_GH) + exclude_GH = eG = eH = 1; + eG = 0; + } else if (*str == 'H') { + if (!exclude_GH) + exclude_GH = eG = eH = 1; + eH = 0; } else if (*str == 'p') { precise++; } else @@ -772,6 +784,8 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr) attr->exclude_kernel = ek; attr->exclude_hv = eh; attr->precise_ip = precise; + attr->exclude_host = eH; + attr->exclude_guest = eG; return 0; } @@ -834,6 +848,7 @@ int parse_events(struct perf_evlist *evlist , const char *str, int unset __used) for (;;) { ostr = str; memset(&attr, 0, sizeof(attr)); + event_attr_init(&attr); ret = parse_event_symbols(evlist, &str, &attr); if (ret == EVT_FAILED) return -1; @@ -916,10 +931,10 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob) char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(debugfs_path)) + if (debugfs_valid_mountpoint(tracing_events_path)) return; - sys_dir = opendir(debugfs_path); + sys_dir = opendir(tracing_events_path); if (!sys_dir) return; @@ -928,7 +943,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob) !strglobmatch(sys_dirent.d_name, subsys_glob)) continue; - snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path, + snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_dirent.d_name); evt_dir = opendir(dir_path); if (!evt_dir) @@ -960,16 +975,16 @@ int is_valid_tracepoint(const char *event_string) char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(debugfs_path)) + if (debugfs_valid_mountpoint(tracing_events_path)) return 0; - sys_dir = opendir(debugfs_path); + sys_dir = opendir(tracing_events_path); if (!sys_dir) return 0; for_each_subsystem(sys_dir, sys_dirent, sys_next) { - snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path, + snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_dirent.d_name); evt_dir = opendir(dir_path); if (!evt_dir) @@ -1097,6 +1112,4 @@ void print_events(const char *event_glob) printf("\n"); print_tracepoint_events(NULL, NULL); - - exit(129); } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 2f8e375e038d..7e0cbe75d5f1 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -39,7 +39,6 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob); int print_hwcache_events(const char *event_glob); extern int is_valid_tracepoint(const char *event_string); -extern char debugfs_path[]; extern int valid_debugfs_mount(const char *debugfs); #endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index b82d54fa2c56..eb25900e2211 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1820,11 +1820,15 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev, ret = -ENOMEM; goto error; } - tev->point.module = strdup(module); - if (tev->point.module == NULL) { - ret = -ENOMEM; - goto error; + + if (module) { + tev->point.module = strdup(module); + if (tev->point.module == NULL) { + ret = -ENOMEM; + goto error; + } } + tev->point.offset = pev->point.offset; tev->point.retprobe = pev->point.retprobe; tev->nargs = pev->nargs; @@ -1952,8 +1956,10 @@ static int __del_trace_probe_event(int fd, struct str_node *ent) pr_debug("Writing event: %s\n", buf); ret = write(fd, buf, strlen(buf)); - if (ret < 0) + if (ret < 0) { + ret = -errno; goto error; + } printf("Remove event: %s\n", ent->s); return 0; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 3e44a3e36519..5d732621a462 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -612,12 +612,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) return ret; } -/* Find a variable in a subprogram die */ -static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) +/* Find a variable in a scope DIE */ +static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) { - Dwarf_Die vr_die, *scopes; + Dwarf_Die vr_die; char buf[32], *ptr; - int ret, nscopes; + int ret = 0; if (!is_c_varname(pf->pvar->var)) { /* Copy raw parameters */ @@ -652,30 +652,16 @@ static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) if (pf->tvar->name == NULL) return -ENOMEM; - pr_debug("Searching '%s' variable in context.\n", - pf->pvar->var); + pr_debug("Searching '%s' variable in context.\n", pf->pvar->var); /* Search child die for local variables and parameters. */ - if (die_find_variable_at(sp_die, pf->pvar->var, pf->addr, &vr_die)) - ret = convert_variable(&vr_die, pf); - else { - /* Search upper class */ - nscopes = dwarf_getscopes_die(sp_die, &scopes); - while (nscopes-- > 1) { - pr_debug("Searching variables in %s\n", - dwarf_diename(&scopes[nscopes])); - /* We should check this scope, so give dummy address */ - if (die_find_variable_at(&scopes[nscopes], - pf->pvar->var, 0, - &vr_die)) { - ret = convert_variable(&vr_die, pf); - goto found; - } - } - if (scopes) - free(scopes); - ret = -ENOENT; + 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)) + ret = -ENOENT; } -found: + 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); @@ -718,26 +704,30 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr, return 0; } -/* Call probe_finder callback with real subprogram DIE */ -static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf) +/* Call probe_finder callback with scope DIE */ +static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) { - Dwarf_Die die_mem; Dwarf_Attribute fb_attr; size_t nops; int ret; - /* If no real subprogram, find a real one */ - if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) { - sp_die = die_find_realfunc(&pf->cu_die, pf->addr, &die_mem); - if (!sp_die) { + if (!sc_die) { + pr_err("Caller must pass a scope DIE. Program error.\n"); + return -EINVAL; + } + + /* If not a real subprogram, find a real one */ + if (dwarf_tag(sc_die) != DW_TAG_subprogram) { + if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) { pr_warning("Failed to find probe point in any " "functions.\n"); return -ENOENT; } - } + } else + memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die)); - /* Get the frame base attribute/ops */ - dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr); + /* Get the frame base attribute/ops from subprogram */ + dwarf_attr(&pf->sp_die, DW_AT_frame_base, &fb_attr); ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1); if (ret <= 0 || nops == 0) { pf->fb_ops = NULL; @@ -755,7 +745,7 @@ static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf) } /* Call finder's callback handler */ - ret = pf->callback(sp_die, pf); + ret = pf->callback(sc_die, pf); /* *pf->fb_ops will be cached in libdw. Don't free it. */ pf->fb_ops = NULL; @@ -763,17 +753,82 @@ static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf) return ret; } +struct find_scope_param { + const char *function; + const char *file; + int line; + int diff; + Dwarf_Die *die_mem; + bool found; +}; + +static int find_best_scope_cb(Dwarf_Die *fn_die, void *data) +{ + struct find_scope_param *fsp = data; + const char *file; + int lno; + + /* Skip if declared file name does not match */ + if (fsp->file) { + file = dwarf_decl_file(fn_die); + if (!file || strcmp(fsp->file, file) != 0) + return 0; + } + /* If the function name is given, that's what user expects */ + if (fsp->function) { + if (die_compare_name(fn_die, fsp->function)) { + memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die)); + fsp->found = true; + return 1; + } + } else { + /* With the line number, find the nearest declared DIE */ + dwarf_decl_line(fn_die, &lno); + if (lno < fsp->line && fsp->diff > fsp->line - lno) { + /* Keep a candidate and continue */ + fsp->diff = fsp->line - lno; + memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die)); + fsp->found = true; + } + } + return 0; +} + +/* Find an appropriate scope fits to given conditions */ +static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem) +{ + struct find_scope_param fsp = { + .function = pf->pev->point.function, + .file = pf->fname, + .line = pf->lno, + .diff = INT_MAX, + .die_mem = die_mem, + .found = false, + }; + + cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, &fsp); + + return fsp.found ? die_mem : NULL; +} + static int probe_point_line_walker(const char *fname, int lineno, Dwarf_Addr addr, void *data) { struct probe_finder *pf = data; + Dwarf_Die *sc_die, die_mem; int ret; if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0) return 0; pf->addr = addr; - ret = call_probe_finder(NULL, pf); + sc_die = find_best_scope(pf, &die_mem); + if (!sc_die) { + pr_warning("Failed to find scope of probe point.\n"); + return -ENOENT; + } + + ret = call_probe_finder(sc_die, pf); /* Continue if no error, because the line will be in inline function */ return ret < 0 ? ret : 0; @@ -827,6 +882,7 @@ static int probe_point_lazy_walker(const char *fname, int lineno, Dwarf_Addr addr, void *data) { struct probe_finder *pf = data; + Dwarf_Die *sc_die, die_mem; int ret; if (!line_list__has_line(&pf->lcache, lineno) || @@ -836,7 +892,14 @@ static int probe_point_lazy_walker(const char *fname, int lineno, pr_debug("Probe line found: line:%d addr:0x%llx\n", lineno, (unsigned long long)addr); pf->addr = addr; - ret = call_probe_finder(NULL, pf); + pf->lno = lineno; + sc_die = find_best_scope(pf, &die_mem); + if (!sc_die) { + pr_warning("Failed to find scope of probe point.\n"); + return -ENOENT; + } + + ret = call_probe_finder(sc_die, pf); /* * Continue if no error, because the lazy pattern will match @@ -861,42 +924,39 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) return die_walk_lines(sp_die, probe_point_lazy_walker, pf); } -/* Callback parameter with return value */ -struct dwarf_callback_param { - void *data; - int retval; -}; - static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) { - struct dwarf_callback_param *param = data; - struct probe_finder *pf = param->data; + struct probe_finder *pf = data; struct perf_probe_point *pp = &pf->pev->point; Dwarf_Addr addr; + int ret; if (pp->lazy_line) - param->retval = find_probe_point_lazy(in_die, pf); + ret = find_probe_point_lazy(in_die, pf); else { /* Get probe address */ if (dwarf_entrypc(in_die, &addr) != 0) { pr_warning("Failed to get entry address of %s.\n", dwarf_diename(in_die)); - param->retval = -ENOENT; - return DWARF_CB_ABORT; + return -ENOENT; } pf->addr = addr; pf->addr += pp->offset; pr_debug("found inline addr: 0x%jx\n", (uintmax_t)pf->addr); - param->retval = call_probe_finder(in_die, pf); - if (param->retval < 0) - return DWARF_CB_ABORT; + ret = call_probe_finder(in_die, pf); } - return DWARF_CB_OK; + return ret; } +/* Callback parameter with return value for libdw */ +struct dwarf_callback_param { + void *data; + int retval; +}; + /* Search function from function name */ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) { @@ -933,14 +993,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) /* TODO: Check the address in this function */ param->retval = call_probe_finder(sp_die, pf); } - } else { - struct dwarf_callback_param _param = {.data = (void *)pf, - .retval = 0}; + } else /* Inlined function: search instances */ - dwarf_func_inline_instances(sp_die, probe_point_inline_cb, - &_param); - param->retval = _param.retval; - } + param->retval = die_walk_instances(sp_die, + probe_point_inline_cb, (void *)pf); return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */ } @@ -1060,7 +1116,7 @@ found: } /* Add a found probe point into trace event list */ -static int add_probe_trace_event(Dwarf_Die *sp_die, struct probe_finder *pf) +static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) { struct trace_event_finder *tf = container_of(pf, struct trace_event_finder, pf); @@ -1075,8 +1131,9 @@ static int add_probe_trace_event(Dwarf_Die *sp_die, struct probe_finder *pf) } tev = &tf->tevs[tf->ntevs++]; - ret = convert_to_trace_point(sp_die, pf->addr, pf->pev->point.retprobe, - &tev->point); + /* Trace point should be converted from subprogram DIE */ + ret = convert_to_trace_point(&pf->sp_die, pf->addr, + pf->pev->point.retprobe, &tev->point); if (ret < 0) return ret; @@ -1091,7 +1148,8 @@ static int add_probe_trace_event(Dwarf_Die *sp_die, struct probe_finder *pf) for (i = 0; i < pf->pev->nargs; i++) { pf->pvar = &pf->pev->args[i]; pf->tvar = &tev->args[i]; - ret = find_variable(sp_die, pf); + /* Variable should be found from scope DIE */ + ret = find_variable(sc_die, pf); if (ret != 0) return ret; } @@ -1159,13 +1217,13 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data) } /* Add a found vars into available variables list */ -static int add_available_vars(Dwarf_Die *sp_die, struct probe_finder *pf) +static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) { struct available_var_finder *af = container_of(pf, struct available_var_finder, pf); struct variable_list *vl; - Dwarf_Die die_mem, *scopes = NULL; - int ret, nscopes; + Dwarf_Die die_mem; + int ret; /* Check number of tevs */ if (af->nvls == af->max_vls) { @@ -1174,8 +1232,9 @@ static int add_available_vars(Dwarf_Die *sp_die, struct probe_finder *pf) } vl = &af->vls[af->nvls++]; - ret = convert_to_trace_point(sp_die, pf->addr, pf->pev->point.retprobe, - &vl->point); + /* Trace point should be converted from subprogram DIE */ + ret = convert_to_trace_point(&pf->sp_die, pf->addr, + pf->pev->point.retprobe, &vl->point); if (ret < 0) return ret; @@ -1187,19 +1246,14 @@ static int add_available_vars(Dwarf_Die *sp_die, struct probe_finder *pf) if (vl->vars == NULL) return -ENOMEM; af->child = true; - die_find_child(sp_die, collect_variables_cb, (void *)af, &die_mem); + die_find_child(sc_die, collect_variables_cb, (void *)af, &die_mem); /* Find external variables */ if (!af->externs) goto out; /* Don't need to search child DIE for externs. */ af->child = false; - nscopes = dwarf_getscopes_die(sp_die, &scopes); - while (nscopes-- > 1) - die_find_child(&scopes[nscopes], collect_variables_cb, - (void *)af, &die_mem); - if (scopes) - free(scopes); + die_find_child(&pf->cu_die, collect_variables_cb, (void *)af, &die_mem); out: if (strlist__empty(vl->vars)) { @@ -1391,10 +1445,14 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) static int line_range_inline_cb(Dwarf_Die *in_die, void *data) { - struct dwarf_callback_param *param = data; + find_line_range_by_line(in_die, data); - param->retval = find_line_range_by_line(in_die, param->data); - return DWARF_CB_ABORT; /* No need to find other instances */ + /* + * We have to check all instances of inlined function, because + * some execution paths can be optimized out depends on the + * function argument of instances + */ + return 0; } /* Search function from function name */ @@ -1422,15 +1480,10 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) pr_debug("New line range: %d to %d\n", lf->lno_s, lf->lno_e); lr->start = lf->lno_s; lr->end = lf->lno_e; - if (dwarf_func_inline(sp_die)) { - struct dwarf_callback_param _param; - _param.data = (void *)lf; - _param.retval = 0; - dwarf_func_inline_instances(sp_die, - line_range_inline_cb, - &_param); - param->retval = _param.retval; - } else + if (dwarf_func_inline(sp_die)) + param->retval = die_walk_instances(sp_die, + line_range_inline_cb, lf); + else param->retval = find_line_range_by_line(sp_die, lf); return DWARF_CB_ABORT; } diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index c478b42a2473..17e94d0c36f9 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -5,7 +5,6 @@ #include "util.h" #include "probe-event.h" -#define MAX_PATH_LEN 256 #define MAX_PROBE_BUFFER 1024 #define MAX_PROBES 128 @@ -57,7 +56,7 @@ struct probe_finder { struct perf_probe_event *pev; /* Target probe event */ /* Callback when a probe point is found */ - int (*callback)(Dwarf_Die *sp_die, struct probe_finder *pf); + int (*callback)(Dwarf_Die *sc_die, struct probe_finder *pf); /* For function searching */ int lno; /* Line number */ diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 8e0b5a39d8a7..9dd47a4f2596 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -187,16 +187,119 @@ static PyTypeObject pyrf_throttle_event__type = { .tp_repr = (reprfunc)pyrf_throttle_event__repr, }; +static char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object."); + +static PyMemberDef pyrf_lost_event__members[] = { + sample_members + member_def(lost_event, id, T_ULONGLONG, "event id"), + member_def(lost_event, lost, T_ULONGLONG, "number of lost events"), + { .name = NULL, }, +}; + +static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent) +{ + PyObject *ret; + char *s; + + if (asprintf(&s, "{ type: lost, id: %#" PRIx64 ", " + "lost: %#" PRIx64 " }", + pevent->event.lost.id, pevent->event.lost.lost) < 0) { + ret = PyErr_NoMemory(); + } else { + ret = PyString_FromString(s); + free(s); + } + return ret; +} + +static PyTypeObject pyrf_lost_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.lost_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_lost_event__doc, + .tp_members = pyrf_lost_event__members, + .tp_repr = (reprfunc)pyrf_lost_event__repr, +}; + +static char pyrf_read_event__doc[] = PyDoc_STR("perf read event object."); + +static PyMemberDef pyrf_read_event__members[] = { + sample_members + member_def(read_event, pid, T_UINT, "event pid"), + member_def(read_event, tid, T_UINT, "event tid"), + { .name = NULL, }, +}; + +static PyObject *pyrf_read_event__repr(struct pyrf_event *pevent) +{ + return PyString_FromFormat("{ type: read, pid: %u, tid: %u }", + pevent->event.read.pid, + pevent->event.read.tid); + /* + * FIXME: return the array of read values, + * making this method useful ;-) + */ +} + +static PyTypeObject pyrf_read_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.read_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_read_event__doc, + .tp_members = pyrf_read_event__members, + .tp_repr = (reprfunc)pyrf_read_event__repr, +}; + +static char pyrf_sample_event__doc[] = PyDoc_STR("perf sample event object."); + +static PyMemberDef pyrf_sample_event__members[] = { + sample_members + member_def(perf_event_header, type, T_UINT, "event type"), + { .name = NULL, }, +}; + +static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent) +{ + PyObject *ret; + char *s; + + if (asprintf(&s, "{ type: sample }") < 0) { + ret = PyErr_NoMemory(); + } else { + ret = PyString_FromString(s); + free(s); + } + return ret; +} + +static PyTypeObject pyrf_sample_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.sample_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_sample_event__doc, + .tp_members = pyrf_sample_event__members, + .tp_repr = (reprfunc)pyrf_sample_event__repr, +}; + static int pyrf_event__setup_types(void) { int err; pyrf_mmap_event__type.tp_new = pyrf_task_event__type.tp_new = pyrf_comm_event__type.tp_new = + pyrf_lost_event__type.tp_new = + pyrf_read_event__type.tp_new = + pyrf_sample_event__type.tp_new = pyrf_throttle_event__type.tp_new = PyType_GenericNew; err = PyType_Ready(&pyrf_mmap_event__type); if (err < 0) goto out; + err = PyType_Ready(&pyrf_lost_event__type); + if (err < 0) + goto out; err = PyType_Ready(&pyrf_task_event__type); if (err < 0) goto out; @@ -206,20 +309,26 @@ static int pyrf_event__setup_types(void) err = PyType_Ready(&pyrf_throttle_event__type); if (err < 0) goto out; + err = PyType_Ready(&pyrf_read_event__type); + if (err < 0) + goto out; + err = PyType_Ready(&pyrf_sample_event__type); + if (err < 0) + goto out; out: return err; } static PyTypeObject *pyrf_event__type[] = { [PERF_RECORD_MMAP] = &pyrf_mmap_event__type, - [PERF_RECORD_LOST] = &pyrf_mmap_event__type, + [PERF_RECORD_LOST] = &pyrf_lost_event__type, [PERF_RECORD_COMM] = &pyrf_comm_event__type, [PERF_RECORD_EXIT] = &pyrf_task_event__type, [PERF_RECORD_THROTTLE] = &pyrf_throttle_event__type, [PERF_RECORD_UNTHROTTLE] = &pyrf_throttle_event__type, [PERF_RECORD_FORK] = &pyrf_task_event__type, - [PERF_RECORD_READ] = &pyrf_mmap_event__type, - [PERF_RECORD_SAMPLE] = &pyrf_mmap_event__type, + [PERF_RECORD_READ] = &pyrf_read_event__type, + [PERF_RECORD_SAMPLE] = &pyrf_sample_event__type, }; static PyObject *pyrf_event__new(union perf_event *event) @@ -514,7 +623,11 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, cpus = ((struct pyrf_cpu_map *)pcpus)->cpus; evsel->attr.inherit = inherit; - if (perf_evsel__open(evsel, cpus, threads, group) < 0) { + /* + * This will group just the fds for this single evsel, to group + * multiple events, use evlist.open(). + */ + if (perf_evsel__open(evsel, cpus, threads, group, NULL) < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } @@ -694,7 +807,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, first = list_entry(evlist->entries.next, struct perf_evsel, node); err = perf_event__parse_sample(event, first->attr.sample_type, perf_evsel__sample_size(first), - sample_id_all, &pevent->sample); + sample_id_all, &pevent->sample, false); if (err) return PyErr_Format(PyExc_OSError, "perf: can't parse sample, err=%d", err); @@ -705,6 +818,25 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, return Py_None; } +static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs) +{ + struct perf_evlist *evlist = &pevlist->evlist; + int group = 0; + static char *kwlist[] = { "group", NULL }; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, &group)) + return NULL; + + if (perf_evlist__open(evlist, group) < 0) { + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + + Py_INCREF(Py_None); + return Py_None; +} + static PyMethodDef pyrf_evlist__methods[] = { { .ml_name = "mmap", @@ -713,6 +845,12 @@ static PyMethodDef pyrf_evlist__methods[] = { .ml_doc = PyDoc_STR("mmap the file descriptor table.") }, { + .ml_name = "open", + .ml_meth = (PyCFunction)pyrf_evlist__open, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("open the file descriptors.") + }, + { .ml_name = "poll", .ml_meth = (PyCFunction)pyrf_evlist__poll, .ml_flags = METH_VARARGS | METH_KEYWORDS, diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 74350ffb57fe..e30749e38a9b 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -27,7 +27,10 @@ #include "../../perf.h" #include "../util.h" +#include "../thread.h" +#include "../event.h" #include "../trace-event.h" +#include "../evsel.h" #include <EXTERN.h> #include <perl.h> @@ -245,11 +248,11 @@ static inline struct event *find_cache_event(int type) return event; } -static void perl_process_event(union perf_event *pevent __unused, - struct perf_sample *sample, - struct perf_evsel *evsel, - struct perf_session *session __unused, - struct thread *thread) +static void perl_process_tracepoint(union perf_event *pevent __unused, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine __unused, + struct thread *thread) { struct format_field *field; static char handler[256]; @@ -265,6 +268,9 @@ static void perl_process_event(union perf_event *pevent __unused, dSP; + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + return; + type = trace_parse_common_type(data); event = find_cache_event(type); @@ -332,6 +338,42 @@ static void perl_process_event(union perf_event *pevent __unused, LEAVE; } +static void perl_process_event_generic(union perf_event *pevent __unused, + struct perf_sample *sample, + struct perf_evsel *evsel __unused, + struct machine *machine __unused, + struct thread *thread __unused) +{ + dSP; + + if (!get_cv("process_event", 0)) + return; + + ENTER; + SAVETMPS; + PUSHMARK(SP); + XPUSHs(sv_2mortal(newSVpvn((const char *)pevent, pevent->header.size))); + XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->attr, sizeof(evsel->attr)))); + XPUSHs(sv_2mortal(newSVpvn((const char *)sample, sizeof(*sample)))); + XPUSHs(sv_2mortal(newSVpvn((const char *)sample->raw_data, sample->raw_size))); + PUTBACK; + call_pv("process_event", G_SCALAR); + SPAGAIN; + PUTBACK; + FREETMPS; + LEAVE; +} + +static void perl_process_event(union perf_event *pevent, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine, + struct thread *thread) +{ + perl_process_tracepoint(pevent, sample, evsel, machine, thread); + perl_process_event_generic(pevent, sample, evsel, machine, thread); +} + static void run_start_sub(void) { dSP; /* access to Perl stack */ @@ -553,7 +595,28 @@ static int perl_generate_script(const char *outfile) fprintf(ofp, "sub print_header\n{\n" "\tmy ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_;\n\n" "\tprintf(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \",\n\t " - "$event_name, $cpu, $secs, $nsecs, $pid, $comm);\n}"); + "$event_name, $cpu, $secs, $nsecs, $pid, $comm);\n}\n"); + + fprintf(ofp, + "\n# Packed byte string args of process_event():\n" + "#\n" + "# $event:\tunion perf_event\tutil/event.h\n" + "# $attr:\tstruct perf_event_attr\tlinux/perf_event.h\n" + "# $sample:\tstruct perf_sample\tutil/event.h\n" + "# $raw_data:\tperf_sample->raw_data\tutil/event.h\n" + "\n" + "sub process_event\n" + "{\n" + "\tmy ($event, $attr, $sample, $raw_data) = @_;\n" + "\n" + "\tmy @event\t= unpack(\"LSS\", $event);\n" + "\tmy @attr\t= unpack(\"LLQQQQQLLQQ\", $attr);\n" + "\tmy @sample\t= unpack(\"QLLQQQQQLL\", $sample);\n" + "\tmy @raw_data\t= unpack(\"C*\", $raw_data);\n" + "\n" + "\tuse Data::Dumper;\n" + "\tprint Dumper \\@event, \\@attr, \\@sample, \\@raw_data;\n" + "}\n"); fclose(ofp); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 6ccf70e8d8f2..0b2a48783172 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -29,6 +29,8 @@ #include "../../perf.h" #include "../util.h" +#include "../event.h" +#include "../thread.h" #include "../trace-event.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -207,7 +209,7 @@ static inline struct event *find_cache_event(int type) static void python_process_event(union perf_event *pevent __unused, struct perf_sample *sample, struct perf_evsel *evsel __unused, - struct perf_session *session __unused, + struct machine *machine __unused, struct thread *thread) { PyObject *handler, *retval, *context, *t, *obj, *dict = NULL; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 72458d9da5b1..b5ca2558c7bb 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -10,6 +10,7 @@ #include "evlist.h" #include "evsel.h" #include "session.h" +#include "tool.h" #include "sort.h" #include "util.h" #include "cpumap.h" @@ -78,39 +79,13 @@ out_close: return -1; } -static void perf_session__id_header_size(struct perf_session *session) -{ - struct perf_sample *data; - u64 sample_type = session->sample_type; - u16 size = 0; - - if (!session->sample_id_all) - goto out; - - if (sample_type & PERF_SAMPLE_TID) - size += sizeof(data->tid) * 2; - - if (sample_type & PERF_SAMPLE_TIME) - size += sizeof(data->time); - - if (sample_type & PERF_SAMPLE_ID) - size += sizeof(data->id); - - if (sample_type & PERF_SAMPLE_STREAM_ID) - size += sizeof(data->stream_id); - - if (sample_type & PERF_SAMPLE_CPU) - size += sizeof(data->cpu) * 2; -out: - session->id_hdr_size = size; -} - void perf_session__update_sample_type(struct perf_session *self) { self->sample_type = perf_evlist__sample_type(self->evlist); self->sample_size = __perf_evsel__sample_size(self->sample_type); self->sample_id_all = perf_evlist__sample_id_all(self->evlist); - perf_session__id_header_size(self); + self->id_hdr_size = perf_evlist__id_hdr_size(self->evlist); + self->host_machine.id_hdr_size = self->id_hdr_size; } int perf_session__create_kernel_maps(struct perf_session *self) @@ -130,18 +105,26 @@ static void perf_session__destroy_kernel_maps(struct perf_session *self) struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe, - struct perf_event_ops *ops) + struct perf_tool *tool) { - size_t len = filename ? strlen(filename) + 1 : 0; - struct perf_session *self = zalloc(sizeof(*self) + len); + struct perf_session *self; + struct stat st; + size_t len; + + if (!filename || !strlen(filename)) { + if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode)) + filename = "-"; + else + filename = "perf.data"; + } + + len = strlen(filename); + self = zalloc(sizeof(*self) + len); if (self == NULL) goto out; memcpy(self->filename, filename, len); - self->threads = RB_ROOT; - INIT_LIST_HEAD(&self->dead_threads); - self->last_match = NULL; /* * On 64bit we can mmap the data file in one go. No need for tiny mmap * slices. On 32bit we use 32MB. @@ -171,10 +154,10 @@ struct perf_session *perf_session__new(const char *filename, int mode, goto out_delete; } - if (ops && ops->ordering_requires_timestamps && - ops->ordered_samples && !self->sample_id_all) { + if (tool && tool->ordering_requires_timestamps && + tool->ordered_samples && !self->sample_id_all) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); - ops->ordered_samples = false; + tool->ordered_samples = false; } out: @@ -184,17 +167,22 @@ out_delete: return NULL; } -static void perf_session__delete_dead_threads(struct perf_session *self) +static void machine__delete_dead_threads(struct machine *machine) { struct thread *n, *t; - list_for_each_entry_safe(t, n, &self->dead_threads, node) { + list_for_each_entry_safe(t, n, &machine->dead_threads, node) { list_del(&t->node); thread__delete(t); } } -static void perf_session__delete_threads(struct perf_session *self) +static void perf_session__delete_dead_threads(struct perf_session *session) +{ + machine__delete_dead_threads(&session->host_machine); +} + +static void machine__delete_threads(struct machine *self) { struct rb_node *nd = rb_first(&self->threads); @@ -207,6 +195,11 @@ static void perf_session__delete_threads(struct perf_session *self) } } +static void perf_session__delete_threads(struct perf_session *session) +{ + machine__delete_threads(&session->host_machine); +} + void perf_session__delete(struct perf_session *self) { perf_session__destroy_kernel_maps(self); @@ -217,7 +210,7 @@ void perf_session__delete(struct perf_session *self) free(self); } -void perf_session__remove_thread(struct perf_session *self, struct thread *th) +void machine__remove_thread(struct machine *self, struct thread *th) { self->last_match = NULL; rb_erase(&th->rb_node, &self->threads); @@ -236,16 +229,16 @@ static bool symbol__match_parent_regex(struct symbol *sym) return 0; } -int perf_session__resolve_callchain(struct perf_session *self, - struct thread *thread, - struct ip_callchain *chain, - struct symbol **parent) +int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel, + struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent) { u8 cpumode = PERF_RECORD_MISC_USER; unsigned int i; int err; - callchain_cursor_reset(&self->callchain_cursor); + callchain_cursor_reset(&evsel->hists.callchain_cursor); for (i = 0; i < chain->nr; i++) { u64 ip; @@ -272,7 +265,7 @@ int perf_session__resolve_callchain(struct perf_session *self, al.filtered = false; thread__find_addr_location(thread, self, cpumode, - MAP__FUNCTION, thread->pid, ip, &al, NULL); + MAP__FUNCTION, ip, &al, NULL); if (al.sym != NULL) { if (sort__has_parent && !*parent && symbol__match_parent_regex(al.sym)) @@ -281,7 +274,7 @@ int perf_session__resolve_callchain(struct perf_session *self, break; } - err = callchain_cursor_append(&self->callchain_cursor, + err = callchain_cursor_append(&evsel->hists.callchain_cursor, ip, al.map, al.sym); if (err) return err; @@ -290,75 +283,91 @@ int perf_session__resolve_callchain(struct perf_session *self, return 0; } -static int process_event_synth_stub(union perf_event *event __used, - struct perf_session *session __used) +static int process_event_synth_tracing_data_stub(union perf_event *event __used, + struct perf_session *session __used) { dump_printf(": unhandled!\n"); return 0; } -static int process_event_sample_stub(union perf_event *event __used, +static int process_event_synth_attr_stub(union perf_event *event __used, + struct perf_evlist **pevlist __used) +{ + dump_printf(": unhandled!\n"); + return 0; +} + +static int process_event_sample_stub(struct perf_tool *tool __used, + union perf_event *event __used, struct perf_sample *sample __used, struct perf_evsel *evsel __used, - struct perf_session *session __used) + struct machine *machine __used) { dump_printf(": unhandled!\n"); return 0; } -static int process_event_stub(union perf_event *event __used, +static int process_event_stub(struct perf_tool *tool __used, + union perf_event *event __used, struct perf_sample *sample __used, - struct perf_session *session __used) + struct machine *machine __used) +{ + dump_printf(": unhandled!\n"); + return 0; +} + +static int process_finished_round_stub(struct perf_tool *tool __used, + union perf_event *event __used, + struct perf_session *perf_session __used) { dump_printf(": unhandled!\n"); return 0; } -static int process_finished_round_stub(union perf_event *event __used, - struct perf_session *session __used, - struct perf_event_ops *ops __used) +static int process_event_type_stub(struct perf_tool *tool __used, + union perf_event *event __used) { dump_printf(": unhandled!\n"); return 0; } -static int process_finished_round(union perf_event *event, - struct perf_session *session, - struct perf_event_ops *ops); +static int process_finished_round(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session); -static void perf_event_ops__fill_defaults(struct perf_event_ops *handler) +static void perf_tool__fill_defaults(struct perf_tool *tool) { - if (handler->sample == NULL) - handler->sample = process_event_sample_stub; - if (handler->mmap == NULL) - handler->mmap = process_event_stub; - if (handler->comm == NULL) - handler->comm = process_event_stub; - if (handler->fork == NULL) - handler->fork = process_event_stub; - if (handler->exit == NULL) - handler->exit = process_event_stub; - if (handler->lost == NULL) - handler->lost = perf_event__process_lost; - if (handler->read == NULL) - handler->read = process_event_stub; - if (handler->throttle == NULL) - handler->throttle = process_event_stub; - if (handler->unthrottle == NULL) - handler->unthrottle = process_event_stub; - if (handler->attr == NULL) - handler->attr = process_event_synth_stub; - if (handler->event_type == NULL) - handler->event_type = process_event_synth_stub; - if (handler->tracing_data == NULL) - handler->tracing_data = process_event_synth_stub; - if (handler->build_id == NULL) - handler->build_id = process_event_synth_stub; - if (handler->finished_round == NULL) { - if (handler->ordered_samples) - handler->finished_round = process_finished_round; + if (tool->sample == NULL) + tool->sample = process_event_sample_stub; + if (tool->mmap == NULL) + tool->mmap = process_event_stub; + if (tool->comm == NULL) + tool->comm = process_event_stub; + if (tool->fork == NULL) + tool->fork = process_event_stub; + if (tool->exit == NULL) + tool->exit = process_event_stub; + if (tool->lost == NULL) + tool->lost = perf_event__process_lost; + if (tool->read == NULL) + tool->read = process_event_sample_stub; + if (tool->throttle == NULL) + tool->throttle = process_event_stub; + if (tool->unthrottle == NULL) + tool->unthrottle = process_event_stub; + if (tool->attr == NULL) + tool->attr = process_event_synth_attr_stub; + if (tool->event_type == NULL) + tool->event_type = process_event_type_stub; + if (tool->tracing_data == NULL) + tool->tracing_data = process_event_synth_tracing_data_stub; + if (tool->build_id == NULL) + tool->build_id = process_finished_round_stub; + if (tool->finished_round == NULL) { + if (tool->ordered_samples) + tool->finished_round = process_finished_round; else - handler->finished_round = process_finished_round_stub; + tool->finished_round = process_finished_round_stub; } } @@ -490,11 +499,11 @@ static void perf_session_free_sample_buffers(struct perf_session *session) static int perf_session_deliver_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, - struct perf_event_ops *ops, + struct perf_tool *tool, u64 file_offset); static void flush_sample_queue(struct perf_session *s, - struct perf_event_ops *ops) + struct perf_tool *tool) { struct ordered_samples *os = &s->ordered_samples; struct list_head *head = &os->samples; @@ -502,9 +511,10 @@ static void flush_sample_queue(struct perf_session *s, struct perf_sample sample; u64 limit = os->next_flush; u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL; + unsigned idx = 0, progress_next = os->nr_samples / 16; int ret; - if (!ops->ordered_samples || !limit) + if (!tool->ordered_samples || !limit) return; list_for_each_entry_safe(iter, tmp, head, list) { @@ -515,12 +525,17 @@ static void flush_sample_queue(struct perf_session *s, if (ret) pr_err("Can't parse sample, err = %d\n", ret); else - perf_session_deliver_event(s, iter->event, &sample, ops, + perf_session_deliver_event(s, iter->event, &sample, tool, iter->file_offset); os->last_flush = iter->timestamp; list_del(&iter->list); list_add(&iter->list, &os->sample_cache); + if (++idx >= progress_next) { + progress_next += os->nr_samples / 16; + ui_progress__update(idx, os->nr_samples, + "Processing time ordered events..."); + } } if (list_empty(head)) { @@ -529,6 +544,8 @@ static void flush_sample_queue(struct perf_session *s, os->last_sample = list_entry(head->prev, struct sample_queue, list); } + + os->nr_samples = 0; } /* @@ -570,11 +587,11 @@ static void flush_sample_queue(struct perf_session *s, * Flush every events below timestamp 7 * etc... */ -static int process_finished_round(union perf_event *event __used, - struct perf_session *session, - struct perf_event_ops *ops) +static int process_finished_round(struct perf_tool *tool, + union perf_event *event __used, + struct perf_session *session) { - flush_sample_queue(session, ops); + flush_sample_queue(session, tool); session->ordered_samples.next_flush = session->ordered_samples.max_timestamp; return 0; @@ -588,6 +605,7 @@ static void __queue_event(struct sample_queue *new, struct perf_session *s) u64 timestamp = new->timestamp; struct list_head *p; + ++os->nr_samples; os->last_sample = new; if (!sample) { @@ -728,41 +746,75 @@ static void dump_sample(struct perf_session *session, union perf_event *event, callchain__printf(sample); } +static struct machine * + perf_session__find_machine_for_cpumode(struct perf_session *session, + union perf_event *event) +{ + const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) + return perf_session__find_machine(session, event->ip.pid); + + return perf_session__find_host_machine(session); +} + static int perf_session_deliver_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, - struct perf_event_ops *ops, + struct perf_tool *tool, u64 file_offset) { struct perf_evsel *evsel; + struct machine *machine; dump_event(session, event, file_offset, sample); + evsel = perf_evlist__id2evsel(session->evlist, sample->id); + if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) { + /* + * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here + * because the tools right now may apply filters, discarding + * some of the samples. For consistency, in the future we + * should have something like nr_filtered_samples and remove + * the sample->period from total_sample_period, etc, KISS for + * now tho. + * + * Also testing against NULL allows us to handle files without + * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the + * future probably it'll be a good idea to restrict event + * processing via perf_session to files with both set. + */ + hists__inc_nr_events(&evsel->hists, event->header.type); + } + + machine = perf_session__find_machine_for_cpumode(session, event); + switch (event->header.type) { case PERF_RECORD_SAMPLE: dump_sample(session, event, sample); - evsel = perf_evlist__id2evsel(session->evlist, sample->id); if (evsel == NULL) { ++session->hists.stats.nr_unknown_id; return -1; } - return ops->sample(event, sample, evsel, session); + return tool->sample(tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: - return ops->mmap(event, sample, session); + return tool->mmap(tool, event, sample, machine); case PERF_RECORD_COMM: - return ops->comm(event, sample, session); + return tool->comm(tool, event, sample, machine); case PERF_RECORD_FORK: - return ops->fork(event, sample, session); + return tool->fork(tool, event, sample, machine); case PERF_RECORD_EXIT: - return ops->exit(event, sample, session); + return tool->exit(tool, event, sample, machine); case PERF_RECORD_LOST: - return ops->lost(event, sample, session); + if (tool->lost == perf_event__process_lost) + session->hists.stats.total_lost += event->lost.lost; + return tool->lost(tool, event, sample, machine); case PERF_RECORD_READ: - return ops->read(event, sample, session); + return tool->read(tool, event, sample, evsel, machine); case PERF_RECORD_THROTTLE: - return ops->throttle(event, sample, session); + return tool->throttle(tool, event, sample, machine); case PERF_RECORD_UNTHROTTLE: - return ops->unthrottle(event, sample, session); + return tool->unthrottle(tool, event, sample, machine); default: ++session->hists.stats.nr_unknown_events; return -1; @@ -786,24 +838,29 @@ static int perf_session__preprocess_sample(struct perf_session *session, } static int perf_session__process_user_event(struct perf_session *session, union perf_event *event, - struct perf_event_ops *ops, u64 file_offset) + struct perf_tool *tool, u64 file_offset) { + int err; + dump_event(session, event, file_offset, NULL); /* These events are processed right away */ switch (event->header.type) { case PERF_RECORD_HEADER_ATTR: - return ops->attr(event, session); + err = tool->attr(event, &session->evlist); + if (err == 0) + perf_session__update_sample_type(session); + return err; case PERF_RECORD_HEADER_EVENT_TYPE: - return ops->event_type(event, session); + return tool->event_type(tool, event); case PERF_RECORD_HEADER_TRACING_DATA: /* setup for reading amidst mmap */ lseek(session->fd, file_offset, SEEK_SET); - return ops->tracing_data(event, session); + return tool->tracing_data(event, session); case PERF_RECORD_HEADER_BUILD_ID: - return ops->build_id(event, session); + return tool->build_id(tool, event, session); case PERF_RECORD_FINISHED_ROUND: - return ops->finished_round(event, session, ops); + return tool->finished_round(tool, event, session); default: return -EINVAL; } @@ -811,7 +868,7 @@ static int perf_session__process_user_event(struct perf_session *session, union static int perf_session__process_event(struct perf_session *session, union perf_event *event, - struct perf_event_ops *ops, + struct perf_tool *tool, u64 file_offset) { struct perf_sample sample; @@ -827,7 +884,7 @@ static int perf_session__process_event(struct perf_session *session, hists__inc_nr_events(&session->hists, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) - return perf_session__process_user_event(session, event, ops, file_offset); + return perf_session__process_user_event(session, event, tool, file_offset); /* * For all kernel events we get the sample data @@ -840,14 +897,14 @@ static int perf_session__process_event(struct perf_session *session, if (perf_session__preprocess_sample(session, event, &sample)) return 0; - if (ops->ordered_samples) { + if (tool->ordered_samples) { ret = perf_session_queue_event(session, event, &sample, file_offset); if (ret != -ETIME) return ret; } - return perf_session_deliver_event(session, event, &sample, ops, + return perf_session_deliver_event(session, event, &sample, tool, file_offset); } @@ -858,6 +915,11 @@ void perf_event_header__bswap(struct perf_event_header *self) self->size = bswap_16(self->size); } +struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) +{ + return machine__findnew_thread(&session->host_machine, pid); +} + static struct thread *perf_session__register_idle_thread(struct perf_session *self) { struct thread *thread = perf_session__findnew(self, 0); @@ -871,14 +933,14 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se } static void perf_session__warn_about_errors(const struct perf_session *session, - const struct perf_event_ops *ops) + const struct perf_tool *tool) { - if (ops->lost == perf_event__process_lost && - session->hists.stats.total_lost != 0) { - ui__warning("Processed %" PRIu64 " events and LOST %" PRIu64 - "!\n\nCheck IO/CPU overload!\n\n", - session->hists.stats.total_period, - session->hists.stats.total_lost); + if (tool->lost == perf_event__process_lost && + session->hists.stats.nr_events[PERF_RECORD_LOST] != 0) { + ui__warning("Processed %d events and lost %d chunks!\n\n" + "Check IO/CPU overload!\n\n", + session->hists.stats.nr_events[0], + session->hists.stats.nr_events[PERF_RECORD_LOST]); } if (session->hists.stats.nr_unknown_events != 0) { @@ -908,7 +970,7 @@ static void perf_session__warn_about_errors(const struct perf_session *session, volatile int session_done; static int __perf_session__process_pipe_events(struct perf_session *self, - struct perf_event_ops *ops) + struct perf_tool *tool) { union perf_event event; uint32_t size; @@ -917,7 +979,7 @@ static int __perf_session__process_pipe_events(struct perf_session *self, int err; void *p; - perf_event_ops__fill_defaults(ops); + perf_tool__fill_defaults(tool); head = 0; more: @@ -953,8 +1015,7 @@ more: } } - if (size == 0 || - (skip = perf_session__process_event(self, &event, ops, head)) < 0) { + if ((skip = perf_session__process_event(self, &event, tool, head)) < 0) { dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n", head, event.header.size, event.header.type); /* @@ -977,7 +1038,7 @@ more: done: err = 0; out_err: - perf_session__warn_about_errors(self, ops); + perf_session__warn_about_errors(self, tool); perf_session_free_sample_buffers(self); return err; } @@ -1008,17 +1069,16 @@ fetch_mmaped_event(struct perf_session *session, int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, - u64 file_size, struct perf_event_ops *ops) + u64 file_size, struct perf_tool *tool) { u64 head, page_offset, file_offset, file_pos, progress_next; int err, mmap_prot, mmap_flags, map_idx = 0; - struct ui_progress *progress; size_t page_size, mmap_size; char *buf, *mmaps[8]; union perf_event *event; uint32_t size; - perf_event_ops__fill_defaults(ops); + perf_tool__fill_defaults(tool); page_size = sysconf(_SC_PAGESIZE); @@ -1030,9 +1090,6 @@ int __perf_session__process_events(struct perf_session *session, file_size = data_offset + data_size; progress_next = file_size / 16; - progress = ui_progress__new("Processing events...", file_size); - if (progress == NULL) - return -1; mmap_size = session->mmap_window; if (mmap_size > file_size) @@ -1076,7 +1133,7 @@ more: size = event->header.size; if (size == 0 || - perf_session__process_event(session, event, ops, file_pos) < 0) { + perf_session__process_event(session, event, tool, file_pos) < 0) { dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n", file_offset + head, event->header.size, event->header.type); @@ -1095,7 +1152,8 @@ more: if (file_pos >= progress_next) { progress_next += file_size / 16; - ui_progress__update(progress, file_pos); + ui_progress__update(file_pos, file_size, + "Processing events..."); } if (file_pos < file_size) @@ -1104,16 +1162,15 @@ more: err = 0; /* do the final flush for ordered samples */ session->ordered_samples.next_flush = ULLONG_MAX; - flush_sample_queue(session, ops); + flush_sample_queue(session, tool); out_err: - ui_progress__delete(progress); - perf_session__warn_about_errors(session, ops); + perf_session__warn_about_errors(session, tool); perf_session_free_sample_buffers(session); return err; } int perf_session__process_events(struct perf_session *self, - struct perf_event_ops *ops) + struct perf_tool *tool) { int err; @@ -1124,9 +1181,9 @@ int perf_session__process_events(struct perf_session *self, err = __perf_session__process_events(self, self->header.data_offset, self->header.data_size, - self->size, ops); + self->size, tool); else - err = __perf_session__process_pipe_events(self, ops); + err = __perf_session__process_pipe_events(self, tool); return err; } @@ -1141,9 +1198,8 @@ bool perf_session__has_traces(struct perf_session *self, const char *msg) return true; } -int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps, - const char *symbol_name, - u64 addr) +int maps__set_kallsyms_ref_reloc_sym(struct map **maps, + const char *symbol_name, u64 addr) { char *bracket; enum map_type i; @@ -1202,6 +1258,27 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) return ret; } +size_t perf_session__fprintf(struct perf_session *session, FILE *fp) +{ + /* + * FIXME: Here we have to actually print all the machines in this + * session, not just the host... + */ + return machine__fprintf(&session->host_machine, fp); +} + +void perf_session__remove_thread(struct perf_session *session, + struct thread *th) +{ + /* + * FIXME: This one makes no sense, we need to remove the thread from + * the machine it belongs to, perf_session can have many machines, so + * doing it always on ->host_machine is wrong. Fix when auditing all + * the 'perf kvm' code. + */ + machine__remove_thread(&session->host_machine, th); +} + struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type) { @@ -1214,17 +1291,16 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, return NULL; } -void perf_session__print_ip(union perf_event *event, - struct perf_sample *sample, - struct perf_session *session, - int print_sym, int print_dso) +void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, + struct machine *machine, struct perf_evsel *evsel, + int print_sym, int print_dso) { struct addr_location al; const char *symname, *dsoname; - struct callchain_cursor *cursor = &session->callchain_cursor; + struct callchain_cursor *cursor = &evsel->hists.callchain_cursor; struct callchain_cursor_node *node; - if (perf_event__preprocess_sample(event, session, &al, sample, + if (perf_event__preprocess_sample(event, machine, &al, sample, NULL) < 0) { error("problem processing %d event, skipping it.\n", event->header.type); @@ -1233,7 +1309,7 @@ void perf_session__print_ip(union perf_event *event, if (symbol_conf.use_callchain && sample->callchain) { - if (perf_session__resolve_callchain(session, al.thread, + if (machine__resolve_callchain(machine, evsel, al.thread, sample->callchain, NULL) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); @@ -1311,6 +1387,10 @@ int perf_session__cpu_bitmap(struct perf_session *session, } map = cpu_map__new(cpu_list); + if (map == NULL) { + pr_err("Invalid cpu_list\n"); + return -1; + } for (i = 0; i < map->nr; i++) { int cpu = map->map[i]; @@ -1326,3 +1406,22 @@ int perf_session__cpu_bitmap(struct perf_session *session, return 0; } + +void perf_session__fprintf_info(struct perf_session *session, FILE *fp, + bool full) +{ + struct stat st; + int ret; + + if (session == NULL || fp == NULL) + return; + + ret = fstat(session->fd, &st); + if (ret == -1) + return; + + fprintf(fp, "# ========\n"); + fprintf(fp, "# captured on: %s", ctime(&st.st_ctime)); + perf_header__fprintf_info(session, fp, full); + fprintf(fp, "# ========\n#\n"); +} diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 170601e67d6b..37bc38381fb6 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -23,15 +23,13 @@ struct ordered_samples { struct sample_queue *sample_buffer; struct sample_queue *last_sample; int sample_buffer_idx; + unsigned int nr_samples; }; struct perf_session { struct perf_header header; unsigned long size; unsigned long mmap_window; - struct rb_root threads; - struct list_head dead_threads; - struct thread *last_match; struct machine host_machine; struct rb_root machines; struct perf_evlist *evlist; @@ -52,65 +50,31 @@ struct perf_session { int cwdlen; char *cwd; struct ordered_samples ordered_samples; - struct callchain_cursor callchain_cursor; - char filename[0]; + char filename[1]; }; -struct perf_evsel; -struct perf_event_ops; - -typedef int (*event_sample)(union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, struct perf_session *session); -typedef int (*event_op)(union perf_event *self, struct perf_sample *sample, - struct perf_session *session); -typedef int (*event_synth_op)(union perf_event *self, - struct perf_session *session); -typedef int (*event_op2)(union perf_event *self, struct perf_session *session, - struct perf_event_ops *ops); - -struct perf_event_ops { - event_sample sample; - event_op mmap, - comm, - fork, - exit, - lost, - read, - throttle, - unthrottle; - event_synth_op attr, - event_type, - tracing_data, - build_id; - event_op2 finished_round; - bool ordered_samples; - bool ordering_requires_timestamps; -}; +struct perf_tool; struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe, - struct perf_event_ops *ops); + struct perf_tool *tool); void perf_session__delete(struct perf_session *self); void perf_event_header__bswap(struct perf_event_header *self); int __perf_session__process_events(struct perf_session *self, u64 data_offset, u64 data_size, u64 size, - struct perf_event_ops *ops); + struct perf_tool *tool); int perf_session__process_events(struct perf_session *self, - struct perf_event_ops *event_ops); + struct perf_tool *tool); -int perf_session__resolve_callchain(struct perf_session *self, +int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel *evsel, struct thread *thread, struct ip_callchain *chain, struct symbol **parent); bool perf_session__has_traces(struct perf_session *self, const char *msg); -int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps, - const char *symbol_name, - u64 addr); - void mem_bswap_64(void *src, int byte_size); void perf_event__attr_swap(struct perf_event_attr *attr); @@ -143,12 +107,16 @@ struct machine *perf_session__findnew_machine(struct perf_session *self, pid_t p static inline void perf_session__process_machines(struct perf_session *self, + struct perf_tool *tool, machine__process_t process) { - process(&self->host_machine, self); - return machines__process(&self->machines, process, self); + process(&self->host_machine, tool); + return machines__process(&self->machines, process, tool); } +struct thread *perf_session__findnew(struct perf_session *self, pid_t pid); +size_t perf_session__fprintf(struct perf_session *self, FILE *fp); + size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp); size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, @@ -162,18 +130,27 @@ static inline int perf_session__parse_sample(struct perf_session *session, { return perf_event__parse_sample(event, session->sample_type, session->sample_size, - session->sample_id_all, sample); + session->sample_id_all, sample, + session->header.needs_swap); +} + +static inline int perf_session__synthesize_sample(struct perf_session *session, + union perf_event *event, + const struct perf_sample *sample) +{ + return perf_event__synthesize_sample(event, session->sample_type, + sample, session->header.needs_swap); } struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type); -void perf_session__print_ip(union perf_event *event, - struct perf_sample *sample, - struct perf_session *session, - int print_sym, int print_dso); +void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, + struct machine *machine, struct perf_evsel *evsel, + int print_sym, int print_dso); int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); +void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full); #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index bbc982f5dd8b..36d4c5619575 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -3,13 +3,32 @@ from distutils.core import setup, Extension from os import getenv +from distutils.command.build_ext import build_ext as _build_ext +from distutils.command.install_lib import install_lib as _install_lib + +class build_ext(_build_ext): + def finalize_options(self): + _build_ext.finalize_options(self) + self.build_lib = build_lib + self.build_temp = build_tmp + +class install_lib(_install_lib): + def finalize_options(self): + _install_lib.finalize_options(self) + self.build_dir = build_lib + + cflags = ['-fno-strict-aliasing', '-Wno-write-strings'] cflags += getenv('CFLAGS', '').split() +build_lib = getenv('PYTHON_EXTBUILD_LIB') +build_tmp = getenv('PYTHON_EXTBUILD_TMP') + perf = Extension('perf', sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c', 'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c', - 'util/util.c', 'util/xyarray.c', 'util/cgroup.c'], + 'util/util.c', 'util/xyarray.c', 'util/cgroup.c', + 'util/debugfs.c'], include_dirs = ['util/include'], extra_compile_args = cflags, ) @@ -21,4 +40,5 @@ setup(name='perf', author_email='acme@redhat.com', license='GPLv2', url='http://perf.wiki.kernel.org', - ext_modules=[perf]) + ext_modules=[perf], + cmdclass={'build_ext': build_ext, 'install_lib': install_lib}) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 401e220566fd..16da30d8d765 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -151,11 +151,17 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) { u64 ip_l, ip_r; + if (!left->ms.sym && !right->ms.sym) + return right->level - left->level; + + if (!left->ms.sym || !right->ms.sym) + return cmp_null(left->ms.sym, right->ms.sym); + if (left->ms.sym == right->ms.sym) return 0; - ip_l = left->ms.sym ? left->ms.sym->start : left->ip; - ip_r = right->ms.sym ? right->ms.sym->start : right->ip; + ip_l = left->ms.sym->start; + ip_r = right->ms.sym->start; return (int64_t)(ip_r - ip_l); } @@ -171,7 +177,9 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, BITS_PER_LONG / 4, self->ip, o); } - ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level); + if (!sort_dso.elide) + ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level); + if (self->ms.sym) ret += repsep_snprintf(bf + ret, size - ret, "%s", self->ms.sym->name); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 77d0388ad415..3f67ae395752 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -45,6 +45,7 @@ extern enum sort_type sort__first_dimension; * @nr_rows - rows expanded in callchain, recalculated on folding/unfolding */ struct hist_entry { + struct rb_node rb_node_in; struct rb_node rb_node; u64 period; u64 period_sys; @@ -63,6 +64,7 @@ struct hist_entry { bool init_have_children; char level; + bool used; u8 filtered; struct symbol *parent; union { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index eec196329fd9..215d50f2042e 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -24,7 +24,7 @@ #include <sys/utsname.h> #ifndef KSYM_NAME_LEN -#define KSYM_NAME_LEN 128 +#define KSYM_NAME_LEN 256 #endif #ifndef NT_GNU_BUILD_ID @@ -46,6 +46,7 @@ struct symbol_conf symbol_conf = { .exclude_other = true, .use_modules = true, .try_vmlinux_path = true, + .annotate_src = true, .symfs = "", }; @@ -74,16 +75,104 @@ static void dso__set_sorted_by_name(struct dso *dso, enum map_type type) bool symbol_type__is_a(char symbol_type, enum map_type map_type) { + symbol_type = toupper(symbol_type); + switch (map_type) { case MAP__FUNCTION: return symbol_type == 'T' || symbol_type == 'W'; case MAP__VARIABLE: - return symbol_type == 'D' || symbol_type == 'd'; + return symbol_type == 'D'; default: return false; } } +static int prefix_underscores_count(const char *str) +{ + const char *tail = str; + + while (*tail == '_') + tail++; + + return tail - str; +} + +#define SYMBOL_A 0 +#define SYMBOL_B 1 + +static int choose_best_symbol(struct symbol *syma, struct symbol *symb) +{ + s64 a; + s64 b; + + /* Prefer a symbol with non zero length */ + a = syma->end - syma->start; + b = symb->end - symb->start; + if ((b == 0) && (a > 0)) + return SYMBOL_A; + else if ((a == 0) && (b > 0)) + return SYMBOL_B; + + /* Prefer a non weak symbol over a weak one */ + a = syma->binding == STB_WEAK; + b = symb->binding == STB_WEAK; + if (b && !a) + return SYMBOL_A; + if (a && !b) + return SYMBOL_B; + + /* Prefer a global symbol over a non global one */ + a = syma->binding == STB_GLOBAL; + b = symb->binding == STB_GLOBAL; + if (a && !b) + return SYMBOL_A; + if (b && !a) + return SYMBOL_B; + + /* Prefer a symbol with less underscores */ + a = prefix_underscores_count(syma->name); + b = prefix_underscores_count(symb->name); + if (b > a) + return SYMBOL_A; + else if (a > b) + return SYMBOL_B; + + /* If all else fails, choose the symbol with the longest name */ + if (strlen(syma->name) >= strlen(symb->name)) + return SYMBOL_A; + else + return SYMBOL_B; +} + +static void symbols__fixup_duplicate(struct rb_root *symbols) +{ + struct rb_node *nd; + struct symbol *curr, *next; + + nd = rb_first(symbols); + + while (nd) { + curr = rb_entry(nd, struct symbol, rb_node); +again: + nd = rb_next(&curr->rb_node); + next = rb_entry(nd, struct symbol, rb_node); + + if (!nd) + break; + + if (curr->start != next->start) + continue; + + if (choose_best_symbol(curr, next) == SYMBOL_A) { + rb_erase(&next->rb_node, symbols); + goto again; + } else { + nd = rb_next(&curr->rb_node); + rb_erase(&curr->rb_node, symbols); + } + } +} + static void symbols__fixup_end(struct rb_root *symbols) { struct rb_node *nd, *prevnd = rb_first(symbols); @@ -438,18 +527,11 @@ int kallsyms__parse(const char *filename, void *arg, char *line = NULL; size_t n; int err = -1; - u64 prev_start = 0; - char prev_symbol_type = 0; - char *prev_symbol_name; FILE *file = fopen(filename, "r"); if (file == NULL) goto out_failure; - prev_symbol_name = malloc(KSYM_NAME_LEN); - if (prev_symbol_name == NULL) - goto out_close; - err = 0; while (!feof(file)) { @@ -470,7 +552,7 @@ int kallsyms__parse(const char *filename, void *arg, if (len + 2 >= line_len) continue; - symbol_type = toupper(line[len]); + symbol_type = line[len]; len += 2; symbol_name = line + len; len = line_len - len; @@ -480,24 +562,18 @@ int kallsyms__parse(const char *filename, void *arg, break; } - if (prev_symbol_type) { - u64 end = start; - if (end != prev_start) - --end; - err = process_symbol(arg, prev_symbol_name, - prev_symbol_type, prev_start, end); - if (err) - break; - } - - memcpy(prev_symbol_name, symbol_name, len + 1); - prev_symbol_type = symbol_type; - prev_start = start; + /* + * module symbols are not sorted so we add all + * symbols with zero length and rely on + * symbols__fixup_end() to fix it up. + */ + err = process_symbol(arg, symbol_name, + symbol_type, start, start); + if (err) + break; } - free(prev_symbol_name); free(line); -out_close: fclose(file); return err; @@ -703,6 +779,9 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, if (dso__load_all_kallsyms(dso, filename, map) < 0) return -1; + symbols__fixup_duplicate(&dso->symbols[map->type]); + symbols__fixup_end(&dso->symbols[map->type]); + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) dso->symtab_type = SYMTAB__GUEST_KALLSYMS; else @@ -1092,8 +1171,7 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name, if (dso->has_build_id) { u8 build_id[BUILD_ID_SIZE]; - if (elf_read_build_id(elf, build_id, - BUILD_ID_SIZE) != BUILD_ID_SIZE) + if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) goto out_elf_end; if (!dso__build_id_equal(dso, build_id)) @@ -1111,6 +1189,8 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name, } opdsec = elf_section_by_name(elf, &ehdr, &opdshdr, ".opd", &opdidx); + if (opdshdr.sh_type != SHT_PROGBITS) + opdsec = NULL; if (opdsec) opddata = elf_rawdata(opdsec, NULL); @@ -1276,6 +1356,7 @@ new_symbol: * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { + symbols__fixup_duplicate(&dso->symbols[map->type]); symbols__fixup_end(&dso->symbols[map->type]); if (kmap) { /* @@ -1362,8 +1443,8 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size) ptr = data->d_buf; while (ptr < (data->d_buf + data->d_size)) { GElf_Nhdr *nhdr = ptr; - int namesz = NOTE_ALIGN(nhdr->n_namesz), - descsz = NOTE_ALIGN(nhdr->n_descsz); + size_t namesz = NOTE_ALIGN(nhdr->n_namesz), + descsz = NOTE_ALIGN(nhdr->n_descsz); const char *name; ptr += sizeof(*nhdr); @@ -1372,8 +1453,10 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size) if (nhdr->n_type == NT_GNU_BUILD_ID && nhdr->n_namesz == sizeof("GNU")) { if (memcmp(name, "GNU", sizeof("GNU")) == 0) { - memcpy(bf, ptr, BUILD_ID_SIZE); - err = BUILD_ID_SIZE; + size_t sz = min(size, descsz); + memcpy(bf, ptr, sz); + memset(bf + sz, 0, size - sz); + err = descsz; break; } } @@ -1425,7 +1508,7 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size) while (1) { char bf[BUFSIZ]; GElf_Nhdr nhdr; - int namesz, descsz; + size_t namesz, descsz; if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr)) break; @@ -1434,15 +1517,16 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size) descsz = NOTE_ALIGN(nhdr.n_descsz); if (nhdr.n_type == NT_GNU_BUILD_ID && nhdr.n_namesz == sizeof("GNU")) { - if (read(fd, bf, namesz) != namesz) + if (read(fd, bf, namesz) != (ssize_t)namesz) break; if (memcmp(bf, "GNU", sizeof("GNU")) == 0) { - if (read(fd, build_id, - BUILD_ID_SIZE) == BUILD_ID_SIZE) { + size_t sz = min(descsz, size); + if (read(fd, build_id, sz) == (ssize_t)sz) { + memset(build_id + sz, 0, size - sz); err = 0; break; } - } else if (read(fd, bf, descsz) != descsz) + } else if (read(fd, bf, descsz) != (ssize_t)descsz) break; } else { int n = namesz + descsz; @@ -1504,6 +1588,17 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) dso->adjust_symbols = 0; if (strncmp(dso->name, "/tmp/perf-", 10) == 0) { + struct stat st; + + if (lstat(dso->name, &st) < 0) + return -1; + + if (st.st_uid && (st.st_uid != geteuid())) { + pr_warning("File %s not owned by current user or root, " + "ignoring it.\n", dso->name); + return -1; + } + ret = dso__load_perf_map(dso, map, filter); dso->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT : SYMTAB__NOT_FOUND; @@ -1662,7 +1757,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, struct stat st; /*sshfs might return bad dent->d_type, so we have to stat*/ - sprintf(path, "%s/%s", dir_name, dent->d_name); + snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name); if (stat(path, &st)) continue; @@ -1671,8 +1766,6 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, !strcmp(dent->d_name, "..")) continue; - snprintf(path, sizeof(path), "%s/%s", - dir_name, dent->d_name); ret = map_groups__set_modules_path_dir(mg, path); if (ret < 0) goto out; @@ -1693,9 +1786,6 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, if (map == NULL) continue; - snprintf(path, sizeof(path), "%s/%s", - dir_name, dent->d_name); - long_name = strdup(path); if (long_name == NULL) { ret = -1; @@ -2170,27 +2260,22 @@ size_t machines__fprintf_dsos_buildid(struct rb_root *machines, return ret; } -struct dso *dso__new_kernel(const char *name) +static struct dso* +dso__kernel_findnew(struct machine *machine, const char *name, + const char *short_name, int dso_type) { - struct dso *dso = dso__new(name ?: "[kernel.kallsyms]"); - - if (dso != NULL) { - dso__set_short_name(dso, "[kernel]"); - dso->kernel = DSO_TYPE_KERNEL; - } - - return dso; -} + /* + * The kernel dso could be created by build_id processing. + */ + struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name); -static struct dso *dso__new_guest_kernel(struct machine *machine, - const char *name) -{ - char bf[PATH_MAX]; - struct dso *dso = dso__new(name ?: machine__mmap_name(machine, bf, - sizeof(bf))); + /* + * We need to run this in all cases, since during the build_id + * processing we had no idea this was the kernel dso. + */ if (dso != NULL) { - dso__set_short_name(dso, "[guest.kernel]"); - dso->kernel = DSO_TYPE_GUEST_KERNEL; + dso__set_short_name(dso, short_name); + dso->kernel = dso_type; } return dso; @@ -2208,24 +2293,36 @@ void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine) dso->has_build_id = true; } -static struct dso *machine__create_kernel(struct machine *machine) +static struct dso *machine__get_kernel(struct machine *machine) { const char *vmlinux_name = NULL; struct dso *kernel; if (machine__is_host(machine)) { vmlinux_name = symbol_conf.vmlinux_name; - kernel = dso__new_kernel(vmlinux_name); + if (!vmlinux_name) + vmlinux_name = "[kernel.kallsyms]"; + + kernel = dso__kernel_findnew(machine, vmlinux_name, + "[kernel]", + DSO_TYPE_KERNEL); } else { + char bf[PATH_MAX]; + if (machine__is_default_guest(machine)) vmlinux_name = symbol_conf.default_guest_vmlinux_name; - kernel = dso__new_guest_kernel(machine, vmlinux_name); + if (!vmlinux_name) + vmlinux_name = machine__mmap_name(machine, bf, + sizeof(bf)); + + kernel = dso__kernel_findnew(machine, vmlinux_name, + "[guest.kernel]", + DSO_TYPE_GUEST_KERNEL); } - if (kernel != NULL) { + if (kernel != NULL && (!kernel->has_build_id)) dso__read_running_kernel_build_id(kernel, machine); - dsos__add(&machine->kernel_dsos, kernel); - } + return kernel; } @@ -2329,7 +2426,7 @@ void machine__destroy_kernel_maps(struct machine *machine) int machine__create_kernel_maps(struct machine *machine) { - struct dso *kernel = machine__create_kernel(machine); + struct dso *kernel = machine__get_kernel(machine); if (kernel == NULL || __machine__create_kernel_maps(machine, kernel) < 0) @@ -2507,10 +2604,10 @@ int symbol__init(void) symbol_conf.initialized = true; return 0; -out_free_dso_list: - strlist__delete(symbol_conf.dso_list); out_free_comm_list: strlist__delete(symbol_conf.comm_list); +out_free_dso_list: + strlist__delete(symbol_conf.dso_list); return -1; } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 325ee36a9d29..123c2e14353e 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -68,15 +68,19 @@ struct strlist; struct symbol_conf { unsigned short priv_size; + unsigned short nr_events; bool try_vmlinux_path, use_modules, sort_by_name, show_nr_samples, + show_total_period, use_callchain, exclude_other, show_cpu_utilization, initialized, - kptr_restrict; + kptr_restrict, + annotate_asm_raw, + annotate_src; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -155,7 +159,6 @@ struct dso { }; struct dso *dso__new(const char *name); -struct dso *dso__new_kernel(const char *name); void dso__delete(struct dso *dso); int dso__name_len(const struct dso *dso); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index d5d3b22250f3..fb4b7ea6752f 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -61,7 +61,7 @@ static size_t thread__fprintf(struct thread *self, FILE *fp) map_groups__fprintf(&self->mg, verbose, fp); } -struct thread *perf_session__findnew(struct perf_session *self, pid_t pid) +struct thread *machine__findnew_thread(struct machine *self, pid_t pid) { struct rb_node **p = &self->threads.rb_node; struct rb_node *parent = NULL; @@ -125,12 +125,12 @@ int thread__fork(struct thread *self, struct thread *parent) return 0; } -size_t perf_session__fprintf(struct perf_session *self, FILE *fp) +size_t machine__fprintf(struct machine *machine, FILE *fp) { size_t ret = 0; struct rb_node *nd; - for (nd = rb_first(&self->threads); nd; nd = rb_next(nd)) { + for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { struct thread *pos = rb_entry(nd, struct thread, rb_node); ret += thread__fprintf(pos, fp); diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index e5f2401c1b5e..70c2c13ff679 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -18,16 +18,14 @@ struct thread { int comm_len; }; -struct perf_session; +struct machine; void thread__delete(struct thread *self); int thread__set_comm(struct thread *self, const char *comm); int thread__comm_len(struct thread *self); -struct thread *perf_session__findnew(struct perf_session *self, pid_t pid); void thread__insert_map(struct thread *self, struct map *map); int thread__fork(struct thread *self, struct thread *parent); -size_t perf_session__fprintf(struct perf_session *self, FILE *fp); static inline struct map *thread__find_map(struct thread *self, enum map_type type, u64 addr) @@ -35,14 +33,12 @@ static inline struct map *thread__find_map(struct thread *self, return self ? map_groups__find(&self->mg, type, addr) : NULL; } -void thread__find_addr_map(struct thread *self, - struct perf_session *session, u8 cpumode, - enum map_type type, pid_t pid, u64 addr, +void thread__find_addr_map(struct thread *thread, struct machine *machine, + u8 cpumode, enum map_type type, u64 addr, struct addr_location *al); -void thread__find_addr_location(struct thread *self, - struct perf_session *session, u8 cpumode, - enum map_type type, pid_t pid, u64 addr, +void thread__find_addr_location(struct thread *thread, struct machine *machine, + u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter); #endif /* __PERF_THREAD_H */ diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h new file mode 100644 index 000000000000..b0e1aadba8d5 --- /dev/null +++ b/tools/perf/util/tool.h @@ -0,0 +1,50 @@ +#ifndef __PERF_TOOL_H +#define __PERF_TOOL_H + +#include <stdbool.h> + +struct perf_session; +union perf_event; +struct perf_evlist; +struct perf_evsel; +struct perf_sample; +struct perf_tool; +struct machine; + +typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, struct machine *machine); + +typedef int (*event_op)(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, struct machine *machine); + +typedef int (*event_attr_op)(union perf_event *event, + struct perf_evlist **pevlist); +typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event); + +typedef int (*event_synth_op)(union perf_event *event, + struct perf_session *session); + +typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event, + struct perf_session *session); + +struct perf_tool { + event_sample sample, + read; + event_op mmap, + comm, + fork, + exit, + lost, + throttle, + unthrottle; + event_attr_op attr; + event_synth_op tracing_data; + event_simple_op event_type; + event_op2 finished_round, + build_id; + bool ordered_samples; + bool ordering_requires_timestamps; +}; + +#endif /* __PERF_TOOL_H */ diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index a11f60735a18..500471dffa4f 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -15,52 +15,6 @@ #include "top.h" #include <inttypes.h> -/* - * Ordering weight: count-1 * count-2 * ... / count-n - */ -static double sym_weight(const struct sym_entry *sym, struct perf_top *top) -{ - double weight = sym->snap_count; - int counter; - - if (!top->display_weighted) - return weight; - - for (counter = 1; counter < top->evlist->nr_entries - 1; counter++) - weight *= sym->count[counter]; - - weight /= (sym->count[counter] + 1); - - return weight; -} - -static void perf_top__remove_active_sym(struct perf_top *top, struct sym_entry *syme) -{ - pthread_mutex_lock(&top->active_symbols_lock); - list_del_init(&syme->node); - pthread_mutex_unlock(&top->active_symbols_lock); -} - -static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se) -{ - struct rb_node **p = &tree->rb_node; - struct rb_node *parent = NULL; - struct sym_entry *iter; - - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct sym_entry, rb_node); - - if (se->weight > iter->weight) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&se->rb_node, parent, p); - rb_insert_color(&se->rb_node, tree); -} - #define SNPRINTF(buf, size, fmt, args...) \ ({ \ size_t r = snprintf(buf, size, fmt, ## args); \ @@ -69,7 +23,6 @@ static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se) size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) { - struct perf_evsel *counter; float samples_per_sec = top->samples / top->delay_secs; float ksamples_per_sec = top->kernel_samples / top->delay_secs; float esamples_percent = (100.0 * top->exact_samples) / top->samples; @@ -104,7 +57,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) esamples_percent); } - if (top->evlist->nr_entries == 1 || !top->display_weighted) { + if (top->evlist->nr_entries == 1) { struct perf_evsel *first; first = list_entry(top->evlist->entries.next, struct perf_evsel, node); ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ", @@ -112,27 +65,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) top->freq ? "Hz" : ""); } - if (!top->display_weighted) { - ret += SNPRINTF(bf + ret, size - ret, "%s", - event_name(top->sym_evsel)); - } else { - /* - * Don't let events eat all the space. Leaving 30 bytes - * for the rest should be enough. - */ - size_t last_pos = size - 30; - - list_for_each_entry(counter, &top->evlist->entries, node) { - ret += SNPRINTF(bf + ret, size - ret, "%s%s", - counter->idx ? "/" : "", - event_name(counter)); - if (ret > last_pos) { - sprintf(bf + last_pos - 3, ".."); - ret = last_pos - 1; - break; - } - } - } + ret += SNPRINTF(bf + ret, size - ret, "%s", event_name(top->sym_evsel)); ret += SNPRINTF(bf + ret, size - ret, "], "); @@ -166,73 +99,3 @@ void perf_top__reset_sample_counters(struct perf_top *top) top->exact_samples = top->guest_kernel_samples = top->guest_us_samples = 0; } - -float perf_top__decay_samples(struct perf_top *top, struct rb_root *root) -{ - struct sym_entry *syme, *n; - float sum_ksamples = 0.0; - int snap = !top->display_weighted ? top->sym_evsel->idx : 0, j; - - /* Sort the active symbols */ - pthread_mutex_lock(&top->active_symbols_lock); - syme = list_entry(top->active_symbols.next, struct sym_entry, node); - pthread_mutex_unlock(&top->active_symbols_lock); - - top->rb_entries = 0; - list_for_each_entry_safe_from(syme, n, &top->active_symbols, node) { - syme->snap_count = syme->count[snap]; - if (syme->snap_count != 0) { - - if ((top->hide_user_symbols && - syme->map->dso->kernel == DSO_TYPE_USER) || - (top->hide_kernel_symbols && - syme->map->dso->kernel == DSO_TYPE_KERNEL)) { - perf_top__remove_active_sym(top, syme); - continue; - } - syme->weight = sym_weight(syme, top); - - if ((int)syme->snap_count >= top->count_filter) { - rb_insert_active_sym(root, syme); - ++top->rb_entries; - } - sum_ksamples += syme->snap_count; - - for (j = 0; j < top->evlist->nr_entries; j++) - syme->count[j] = top->zero ? 0 : syme->count[j] * 7 / 8; - } else - perf_top__remove_active_sym(top, syme); - } - - return sum_ksamples; -} - -/* - * Find the longest symbol name that will be displayed - */ -void perf_top__find_widths(struct perf_top *top, struct rb_root *root, - int *dso_width, int *dso_short_width, int *sym_width) -{ - struct rb_node *nd; - int printed = 0; - - *sym_width = *dso_width = *dso_short_width = 0; - - for (nd = rb_first(root); nd; nd = rb_next(nd)) { - struct sym_entry *syme = rb_entry(nd, struct sym_entry, rb_node); - struct symbol *sym = sym_entry__symbol(syme); - - if (++printed > top->print_entries || - (int)syme->snap_count < top->count_filter) - continue; - - if (syme->map->dso->long_name_len > *dso_width) - *dso_width = syme->map->dso->long_name_len; - - if (syme->map->dso->short_name_len > *dso_short_width) - *dso_short_width = syme->map->dso->short_name_len; - - if (sym->namelen > *sym_width) - *sym_width = sym->namelen; - } -} diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index bfbf95bcc603..a248f3c2c60d 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -1,64 +1,52 @@ #ifndef __PERF_TOP_H #define __PERF_TOP_H 1 +#include "tool.h" #include "types.h" -#include "../perf.h" #include <stddef.h> -#include <pthread.h> -#include <linux/list.h> -#include <linux/rbtree.h> +#include <stdbool.h> struct perf_evlist; struct perf_evsel; - -struct sym_entry { - struct rb_node rb_node; - struct list_head node; - unsigned long snap_count; - double weight; - struct map *map; - unsigned long count[0]; -}; - -static inline struct symbol *sym_entry__symbol(struct sym_entry *self) -{ - return ((void *)self) + symbol_conf.priv_size; -} +struct perf_session; struct perf_top { + struct perf_tool tool; struct perf_evlist *evlist; /* * Symbols will be added here in perf_event__process_sample and will * get out after decayed. */ - struct list_head active_symbols; - pthread_mutex_t active_symbols_lock; - pthread_cond_t active_symbols_cond; u64 samples; u64 kernel_samples, us_samples; u64 exact_samples; u64 guest_us_samples, guest_kernel_samples; int print_entries, count_filter, delay_secs; - int display_weighted, freq, rb_entries; + int freq; pid_t target_pid, target_tid; bool hide_kernel_symbols, hide_user_symbols, zero; + bool system_wide; + bool use_tui, use_stdio; + bool sort_has_symbols; + bool dont_use_callchains; + bool kptr_restrict_warned; + bool vmlinux_warned; + bool inherit; + bool group; + bool sample_id_all_avail; + bool dump_symtab; const char *cpu_list; - struct sym_entry *sym_filter_entry; + struct hist_entry *sym_filter_entry; struct perf_evsel *sym_evsel; + struct perf_session *session; + struct winsize winsize; + unsigned int mmap_pages; + int default_interval; + int realtime_prio; + int sym_pcnt_filter; + const char *sym_filter; }; size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size); void perf_top__reset_sample_counters(struct perf_top *top); -float perf_top__decay_samples(struct perf_top *top, struct rb_root *root); -void perf_top__find_widths(struct perf_top *top, struct rb_root *root, - int *dso_width, int *dso_short_width, int *sym_width); - -#ifdef NO_NEWT_SUPPORT -static inline int perf_top__tui_browser(struct perf_top *top __used) -{ - return 0; -} -#else -int perf_top__tui_browser(struct perf_top *top); -#endif #endif /* __PERF_TOP_H */ diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 3403f814ad72..fc22cf5c605f 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -18,7 +18,7 @@ * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -#define _GNU_SOURCE +#include "util.h" #include <dirent.h> #include <mntent.h> #include <stdio.h> @@ -31,7 +31,6 @@ #include <pthread.h> #include <fcntl.h> #include <unistd.h> -#include <ctype.h> #include <errno.h> #include <stdbool.h> #include <linux/list.h> @@ -44,10 +43,6 @@ #define VERSION "0.5" -#define _STR(x) #x -#define STR(x) _STR(x) -#define MAX_PATH 256 - #define TRACE_CTRL "tracing_on" #define TRACE "trace" #define AVAILABLE "available_tracers" @@ -73,26 +68,6 @@ struct events { }; - -static void die(const char *fmt, ...) -{ - va_list ap; - int ret = errno; - - if (errno) - perror("trace-cmd"); - else - ret = -1; - - va_start(ap, fmt); - fprintf(stderr, " "); - vfprintf(stderr, fmt, ap); - va_end(ap); - - fprintf(stderr, "\n"); - exit(ret); -} - void *malloc_or_die(unsigned int size) { void *data; @@ -196,7 +171,8 @@ static void record_file(const char *file, size_t hdr_sz) die("Can't read '%s'", file); /* put in zeros for file size, then fill true size later */ - write_or_die(&size, hdr_sz); + if (hdr_sz) + write_or_die(&size, hdr_sz); do { r = read(fd, buf, BUFSIZ); @@ -212,7 +188,7 @@ static void record_file(const char *file, size_t hdr_sz) if (bigendian()) sizep += sizeof(u64) - hdr_sz; - if (pwrite(output_fd, sizep, hdr_sz, hdr_pos) < 0) + if (hdr_sz && pwrite(output_fd, sizep, hdr_sz, hdr_pos) < 0) die("writing to %s", output_file); } @@ -428,6 +404,19 @@ get_tracepoints_path(struct list_head *pattrs) return nr_tracepoints > 0 ? path.next : NULL; } +static void +put_tracepoints_path(struct tracepoint_path *tps) +{ + while (tps) { + struct tracepoint_path *t = tps; + + tps = tps->next; + free(t->name); + free(t->system); + free(t); + } +} + bool have_tracepoints(struct list_head *pattrs) { struct perf_evsel *pos; @@ -439,19 +428,11 @@ bool have_tracepoints(struct list_head *pattrs) return false; } -int read_tracing_data(int fd, struct list_head *pattrs) +static void tracing_data_header(void) { - char buf[BUFSIZ]; - struct tracepoint_path *tps = get_tracepoints_path(pattrs); - - /* - * What? No tracepoints? No sense writing anything here, bail out. - */ - if (tps == NULL) - return -1; - - output_fd = fd; + char buf[20]; + /* just guessing this is someone's birthday.. ;) */ buf[0] = 23; buf[1] = 8; buf[2] = 68; @@ -476,28 +457,86 @@ int read_tracing_data(int fd, struct list_head *pattrs) /* save page_size */ page_size = sysconf(_SC_PAGESIZE); write_or_die(&page_size, 4); +} + +struct tracing_data *tracing_data_get(struct list_head *pattrs, + int fd, bool temp) +{ + struct tracepoint_path *tps; + struct tracing_data *tdata; + + output_fd = fd; + + tps = get_tracepoints_path(pattrs); + if (!tps) + return NULL; + + tdata = malloc_or_die(sizeof(*tdata)); + tdata->temp = temp; + tdata->size = 0; + if (temp) { + int temp_fd; + + snprintf(tdata->temp_file, sizeof(tdata->temp_file), + "/tmp/perf-XXXXXX"); + if (!mkstemp(tdata->temp_file)) + die("Can't make temp file"); + + temp_fd = open(tdata->temp_file, O_RDWR); + if (temp_fd < 0) + die("Can't read '%s'", tdata->temp_file); + + /* + * Set the temp file the default output, so all the + * tracing data are stored into it. + */ + output_fd = temp_fd; + } + + tracing_data_header(); read_header_files(); read_ftrace_files(tps); read_event_files(tps); read_proc_kallsyms(); read_ftrace_printk(); - return 0; + /* + * All tracing data are stored by now, we can restore + * the default output file in case we used temp file. + */ + if (temp) { + tdata->size = lseek(output_fd, 0, SEEK_CUR); + close(output_fd); + output_fd = fd; + } + + put_tracepoints_path(tps); + return tdata; } -ssize_t read_tracing_data_size(int fd, struct list_head *pattrs) +void tracing_data_put(struct tracing_data *tdata) { - ssize_t size; - int err = 0; + if (tdata->temp) { + record_file(tdata->temp_file, 0); + unlink(tdata->temp_file); + } + + free(tdata); +} - calc_data_size = 1; - err = read_tracing_data(fd, pattrs); - size = calc_data_size - 1; - calc_data_size = 0; +int read_tracing_data(int fd, struct list_head *pattrs) +{ + struct tracing_data *tdata; - if (err < 0) - return err; + /* + * We work over the real file, so we can write data + * directly, no temp file is needed. + */ + tdata = tracing_data_get(pattrs, fd, false); + if (!tdata) + return -ENOMEM; - return size; + tracing_data_put(tdata); + return 0; } diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 0a7ed5b5e281..6c164dc9ee95 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -1537,6 +1537,8 @@ process_flags(struct event *event, struct print_arg *arg, char **tok) field = malloc_or_die(sizeof(*field)); type = process_arg(event, field, &token); + while (type == EVENT_OP) + type = process_op(event, field, &token); if (test_type_token(type, token, EVENT_DELIM, ",")) goto out_free; diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index c9dcbec7d800..a3fdf55f317b 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -39,7 +39,7 @@ static int stop_script_unsupported(void) static void process_event_unsupported(union perf_event *event __unused, struct perf_sample *sample __unused, struct perf_evsel *evsel __unused, - struct perf_session *session __unused, + struct machine *machine __unused, struct thread *thread __unused) { } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index f674dda3363b..58ae14c5baac 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -3,7 +3,11 @@ #include <stdbool.h> #include "parse-events.h" -#include "session.h" + +struct machine; +struct perf_sample; +union perf_event; +struct thread; #define __unused __attribute__((unused)) @@ -263,7 +267,18 @@ void *raw_field_ptr(struct event *event, const char *name, void *data); unsigned long long eval_flag(const char *flag); int read_tracing_data(int fd, struct list_head *pattrs); -ssize_t read_tracing_data_size(int fd, struct list_head *pattrs); + +struct tracing_data { + /* size is only valid if temp is 'true' */ + ssize_t size; + bool temp; + char temp_file[50]; +}; + +struct tracing_data *tracing_data_get(struct list_head *pattrs, + int fd, bool temp); +void tracing_data_put(struct tracing_data *tdata); + /* taken from kernel/trace/trace.h */ enum trace_flag_type { @@ -281,7 +296,7 @@ struct scripting_ops { void (*process_event) (union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, - struct perf_session *session, + struct machine *machine, struct thread *thread); int (*generate_script) (const char *outfile); }; diff --git a/tools/perf/util/ui/browser.c b/tools/perf/util/ui/browser.c index 611219f80680..556829124b02 100644 --- a/tools/perf/util/ui/browser.c +++ b/tools/perf/util/ui/browser.c @@ -1,5 +1,10 @@ +#include "../util.h" +#include "../cache.h" +#include "../../perf.h" #include "libslang.h" +#include <newt.h> #include "ui.h" +#include "util.h" #include <linux/compiler.h> #include <linux/list.h> #include <linux/rbtree.h> @@ -7,13 +12,13 @@ #include <sys/ttydefaults.h> #include "browser.h" #include "helpline.h" +#include "keysyms.h" #include "../color.h" -#include "../util.h" -#include <stdio.h> -static int ui_browser__percent_color(double percent, bool current) +static int ui_browser__percent_color(struct ui_browser *browser, + double percent, bool current) { - if (current) + if (current && (!browser->use_navkeypressed || browser->navkeypressed)) return HE_COLORSET_SELECTED; if (percent >= MIN_RED) return HE_COLORSET_TOP; @@ -30,7 +35,7 @@ void ui_browser__set_color(struct ui_browser *self __used, int color) void ui_browser__set_percent_color(struct ui_browser *self, double percent, bool current) { - int color = ui_browser__percent_color(percent, current); + int color = ui_browser__percent_color(self, percent, current); ui_browser__set_color(self, color); } @@ -39,31 +44,62 @@ void ui_browser__gotorc(struct ui_browser *self, int y, int x) SLsmg_gotorc(self->y + y, self->x + x); } +static struct list_head * +ui_browser__list_head_filter_entries(struct ui_browser *browser, + struct list_head *pos) +{ + do { + if (!browser->filter || !browser->filter(browser, pos)) + return pos; + pos = pos->next; + } while (pos != browser->entries); + + return NULL; +} + +static struct list_head * +ui_browser__list_head_filter_prev_entries(struct ui_browser *browser, + struct list_head *pos) +{ + do { + if (!browser->filter || !browser->filter(browser, pos)) + return pos; + pos = pos->prev; + } while (pos != browser->entries); + + return NULL; +} + void ui_browser__list_head_seek(struct ui_browser *self, off_t offset, int whence) { struct list_head *head = self->entries; struct list_head *pos; + if (self->nr_entries == 0) + return; + switch (whence) { case SEEK_SET: - pos = head->next; + pos = ui_browser__list_head_filter_entries(self, head->next); break; case SEEK_CUR: pos = self->top; break; case SEEK_END: - pos = head->prev; + pos = ui_browser__list_head_filter_prev_entries(self, head->prev); break; default: return; } + assert(pos != NULL); + if (offset > 0) { while (offset-- != 0) - pos = pos->next; + pos = ui_browser__list_head_filter_entries(self, pos->next); } else { while (offset++ != 0) - pos = pos->prev; + pos = ui_browser__list_head_filter_prev_entries(self, pos->prev); } self->top = pos; @@ -127,41 +163,76 @@ bool ui_browser__is_current_entry(struct ui_browser *self, unsigned row) void ui_browser__refresh_dimensions(struct ui_browser *self) { - int cols, rows; - newtGetScreenSize(&cols, &rows); - - self->width = cols - 1; - self->height = rows - 2; + self->width = SLtt_Screen_Cols - 1; + self->height = SLtt_Screen_Rows - 2; self->y = 1; self->x = 0; } -void ui_browser__reset_index(struct ui_browser *self) +void ui_browser__handle_resize(struct ui_browser *browser) { - self->index = self->top_idx = 0; - self->seek(self, 0, SEEK_SET); + ui__refresh_dimensions(false); + ui_browser__show(browser, browser->title, ui_helpline__current); + ui_browser__refresh(browser); } -void ui_browser__add_exit_key(struct ui_browser *self, int key) +int ui_browser__warning(struct ui_browser *browser, int timeout, + const char *format, ...) { - newtFormAddHotKey(self->form, key); + va_list args; + char *text; + int key = 0, err; + + va_start(args, format); + err = vasprintf(&text, format, args); + va_end(args); + + if (err < 0) { + va_start(args, format); + ui_helpline__vpush(format, args); + va_end(args); + } else { + while ((key == ui__question_window("Warning!", text, + "Press any key...", + timeout)) == K_RESIZE) + ui_browser__handle_resize(browser); + free(text); + } + + return key; } -void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]) +int ui_browser__help_window(struct ui_browser *browser, const char *text) { - int i = 0; + int key; - while (keys[i] && i < 64) { - ui_browser__add_exit_key(self, keys[i]); - ++i; - } + while ((key = ui__help_window(text)) == K_RESIZE) + ui_browser__handle_resize(browser); + + return key; +} + +bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text) +{ + int key; + + while ((key = ui__dialog_yesno(text)) == K_RESIZE) + ui_browser__handle_resize(browser); + + return key == K_ENTER || toupper(key) == 'Y'; +} + +void ui_browser__reset_index(struct ui_browser *self) +{ + self->index = self->top_idx = 0; + self->seek(self, 0, SEEK_SET); } void __ui_browser__show_title(struct ui_browser *browser, const char *title) { SLsmg_gotorc(0, 0); ui_browser__set_color(browser, NEWT_COLORSET_ROOT); - slsmg_write_nstring(title, browser->width); + slsmg_write_nstring(title, browser->width + 1); } void ui_browser__show_title(struct ui_browser *browser, const char *title) @@ -174,78 +245,145 @@ void ui_browser__show_title(struct ui_browser *browser, const char *title) int ui_browser__show(struct ui_browser *self, const char *title, const char *helpline, ...) { + int err; va_list ap; - int keys[] = { NEWT_KEY_UP, NEWT_KEY_DOWN, NEWT_KEY_PGUP, - NEWT_KEY_PGDN, NEWT_KEY_HOME, NEWT_KEY_END, ' ', - NEWT_KEY_LEFT, NEWT_KEY_ESCAPE, 'q', CTRL('c'), 0 }; - - if (self->form != NULL) - newtFormDestroy(self->form); ui_browser__refresh_dimensions(self); - self->form = newtForm(NULL, NULL, 0); - if (self->form == NULL) - return -1; - - self->sb = newtVerticalScrollbar(self->width, 1, self->height, - HE_COLORSET_NORMAL, - HE_COLORSET_SELECTED); - if (self->sb == NULL) - return -1; pthread_mutex_lock(&ui__lock); __ui_browser__show_title(self, title); - ui_browser__add_exit_keys(self, keys); - newtFormAddComponent(self->form, self->sb); + self->title = title; + free(self->helpline); + self->helpline = NULL; va_start(ap, helpline); - ui_helpline__vpush(helpline, ap); + err = vasprintf(&self->helpline, helpline, ap); va_end(ap); + if (err > 0) + ui_helpline__push(self->helpline); pthread_mutex_unlock(&ui__lock); - return 0; + return err ? 0 : -1; } -void ui_browser__hide(struct ui_browser *self) +void ui_browser__hide(struct ui_browser *browser __used) { pthread_mutex_lock(&ui__lock); - newtFormDestroy(self->form); - self->form = NULL; ui_helpline__pop(); pthread_mutex_unlock(&ui__lock); } -int ui_browser__refresh(struct ui_browser *self) +static void ui_browser__scrollbar_set(struct ui_browser *browser) +{ + int height = browser->height, h = 0, pct = 0, + col = browser->width, + row = browser->y - 1; + + if (browser->nr_entries > 1) { + pct = ((browser->index * (browser->height - 1)) / + (browser->nr_entries - 1)); + } + + SLsmg_set_char_set(1); + + while (h < height) { + ui_browser__gotorc(browser, row++, col); + SLsmg_write_char(h == pct ? SLSMG_DIAMOND_CHAR : SLSMG_CKBRD_CHAR); + ++h; + } + + SLsmg_set_char_set(0); +} + +static int __ui_browser__refresh(struct ui_browser *browser) { int row; + int width = browser->width; + + row = browser->refresh(browser); + ui_browser__set_color(browser, HE_COLORSET_NORMAL); + + if (!browser->use_navkeypressed || browser->navkeypressed) + ui_browser__scrollbar_set(browser); + else + width += 1; + + SLsmg_fill_region(browser->y + row, browser->x, + browser->height - row, width, ' '); + + return 0; +} +int ui_browser__refresh(struct ui_browser *browser) +{ pthread_mutex_lock(&ui__lock); - newtScrollbarSet(self->sb, self->index, self->nr_entries - 1); - row = self->refresh(self); - ui_browser__set_color(self, HE_COLORSET_NORMAL); - SLsmg_fill_region(self->y + row, self->x, - self->height - row, self->width, ' '); + __ui_browser__refresh(browser); pthread_mutex_unlock(&ui__lock); return 0; } -int ui_browser__run(struct ui_browser *self) +/* + * Here we're updating nr_entries _after_ we started browsing, i.e. we have to + * forget about any reference to any entry in the underlying data structure, + * that is why we do a SEEK_SET. Think about 'perf top' in the hists browser + * after an output_resort and hist decay. + */ +void ui_browser__update_nr_entries(struct ui_browser *browser, u32 nr_entries) { - struct newtExitStruct es; + off_t offset = nr_entries - browser->nr_entries; + + browser->nr_entries = nr_entries; - if (ui_browser__refresh(self) < 0) - return -1; + if (offset < 0) { + if (browser->top_idx < (u64)-offset) + offset = -browser->top_idx; + + browser->index += offset; + browser->top_idx += offset; + } + + browser->top = NULL; + browser->seek(browser, browser->top_idx, SEEK_SET); +} + +int ui_browser__run(struct ui_browser *self, int delay_secs) +{ + int err, key; while (1) { off_t offset; - newtFormRun(self->form, &es); - - if (es.reason != NEWT_EXIT_HOTKEY) + pthread_mutex_lock(&ui__lock); + err = __ui_browser__refresh(self); + SLsmg_refresh(); + pthread_mutex_unlock(&ui__lock); + if (err < 0) break; - switch (es.u.key) { - case NEWT_KEY_DOWN: + + key = ui__getch(delay_secs); + + if (key == K_RESIZE) { + ui__refresh_dimensions(false); + ui_browser__refresh_dimensions(self); + __ui_browser__show_title(self, self->title); + ui_helpline__puts(self->helpline); + continue; + } + + if (self->use_navkeypressed && !self->navkeypressed) { + if (key == K_DOWN || key == K_UP || + key == K_PGDN || key == K_PGUP || + key == K_HOME || key == K_END || + key == ' ') { + self->navkeypressed = true; + continue; + } else + return key; + } + + switch (key) { + case K_DOWN: if (self->index == self->nr_entries - 1) break; ++self->index; @@ -254,7 +392,7 @@ int ui_browser__run(struct ui_browser *self) self->seek(self, +1, SEEK_CUR); } break; - case NEWT_KEY_UP: + case K_UP: if (self->index == 0) break; --self->index; @@ -263,7 +401,7 @@ int ui_browser__run(struct ui_browser *self) self->seek(self, -1, SEEK_CUR); } break; - case NEWT_KEY_PGDN: + case K_PGDN: case ' ': if (self->top_idx + self->height > self->nr_entries - 1) break; @@ -275,7 +413,7 @@ int ui_browser__run(struct ui_browser *self) self->top_idx += offset; self->seek(self, +offset, SEEK_CUR); break; - case NEWT_KEY_PGUP: + case K_PGUP: if (self->top_idx == 0) break; @@ -288,10 +426,10 @@ int ui_browser__run(struct ui_browser *self) self->top_idx -= offset; self->seek(self, -offset, SEEK_CUR); break; - case NEWT_KEY_HOME: + case K_HOME: ui_browser__reset_index(self); break; - case NEWT_KEY_END: + case K_END: offset = self->height - 1; if (offset >= self->nr_entries) offset = self->nr_entries - 1; @@ -301,10 +439,8 @@ int ui_browser__run(struct ui_browser *self) self->seek(self, -offset, SEEK_END); break; default: - return es.u.key; + return key; } - if (ui_browser__refresh(self) < 0) - return -1; } return -1; } @@ -316,41 +452,146 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *self) int row = 0; if (self->top == NULL || self->top == self->entries) - self->top = head->next; + self->top = ui_browser__list_head_filter_entries(self, head->next); pos = self->top; list_for_each_from(pos, head) { - ui_browser__gotorc(self, row, 0); - self->write(self, pos, row); - if (++row == self->height) - break; + if (!self->filter || !self->filter(self, pos)) { + ui_browser__gotorc(self, row, 0); + self->write(self, pos, row); + if (++row == self->height) + break; + } } return row; } -static struct newtPercentTreeColors { - const char *topColorFg, *topColorBg; - const char *mediumColorFg, *mediumColorBg; - const char *normalColorFg, *normalColorBg; - const char *selColorFg, *selColorBg; - const char *codeColorFg, *codeColorBg; -} defaultPercentTreeColors = { - "red", "lightgray", - "green", "lightgray", - "black", "lightgray", - "lightgray", "magenta", - "blue", "lightgray", +static struct ui_browser__colorset { + const char *name, *fg, *bg; + int colorset; +} ui_browser__colorsets[] = { + { + .colorset = HE_COLORSET_TOP, + .name = "top", + .fg = "red", + .bg = "default", + }, + { + .colorset = HE_COLORSET_MEDIUM, + .name = "medium", + .fg = "green", + .bg = "default", + }, + { + .colorset = HE_COLORSET_NORMAL, + .name = "normal", + .fg = "default", + .bg = "default", + }, + { + .colorset = HE_COLORSET_SELECTED, + .name = "selected", + .fg = "black", + .bg = "lightgray", + }, + { + .colorset = HE_COLORSET_CODE, + .name = "code", + .fg = "blue", + .bg = "default", + }, + { + .name = NULL, + } }; + +static int ui_browser__color_config(const char *var, const char *value, + void *data __used) +{ + char *fg = NULL, *bg; + int i; + + /* same dir for all commands */ + if (prefixcmp(var, "colors.") != 0) + return 0; + + for (i = 0; ui_browser__colorsets[i].name != NULL; ++i) { + const char *name = var + 7; + + if (strcmp(ui_browser__colorsets[i].name, name) != 0) + continue; + + fg = strdup(value); + if (fg == NULL) + break; + + bg = strchr(fg, ','); + if (bg == NULL) + break; + + *bg = '\0'; + while (isspace(*++bg)); + ui_browser__colorsets[i].bg = bg; + ui_browser__colorsets[i].fg = fg; + return 0; + } + + free(fg); + return -1; +} + +void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence) +{ + switch (whence) { + case SEEK_SET: + browser->top = browser->entries; + break; + case SEEK_CUR: + browser->top = browser->top + browser->top_idx + offset; + break; + case SEEK_END: + browser->top = browser->top + browser->nr_entries + offset; + break; + default: + return; + } +} + +unsigned int ui_browser__argv_refresh(struct ui_browser *browser) +{ + unsigned int row = 0, idx = browser->top_idx; + char **pos; + + if (browser->top == NULL) + browser->top = browser->entries; + + pos = (char **)browser->top; + while (idx < browser->nr_entries) { + if (!browser->filter || !browser->filter(browser, *pos)) { + ui_browser__gotorc(browser, row, 0); + browser->write(browser, pos, row); + if (++row == browser->height) + break; + } + + ++idx; + ++pos; + } + + return row; +} + void ui_browser__init(void) { - struct newtPercentTreeColors *c = &defaultPercentTreeColors; + int i = 0; + + perf_config(ui_browser__color_config, NULL); - sltt_set_color(HE_COLORSET_TOP, NULL, c->topColorFg, c->topColorBg); - sltt_set_color(HE_COLORSET_MEDIUM, NULL, c->mediumColorFg, c->mediumColorBg); - sltt_set_color(HE_COLORSET_NORMAL, NULL, c->normalColorFg, c->normalColorBg); - sltt_set_color(HE_COLORSET_SELECTED, NULL, c->selColorFg, c->selColorBg); - sltt_set_color(HE_COLORSET_CODE, NULL, c->codeColorFg, c->codeColorBg); + while (ui_browser__colorsets[i].name) { + struct ui_browser__colorset *c = &ui_browser__colorsets[i++]; + sltt_set_color(c->colorset, c->name, c->fg, c->bg); + } } diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h index fc63dda10910..84d761b730c1 100644 --- a/tools/perf/util/ui/browser.h +++ b/tools/perf/util/ui/browser.h @@ -2,7 +2,6 @@ #define _PERF_UI_BROWSER_H_ 1 #include <stdbool.h> -#include <newt.h> #include <sys/types.h> #include "../types.h" @@ -13,15 +12,19 @@ #define HE_COLORSET_CODE 54 struct ui_browser { - newtComponent form, sb; u64 index, top_idx; void *top, *entries; u16 y, x, width, height; void *priv; + const char *title; + char *helpline; unsigned int (*refresh)(struct ui_browser *self); void (*write)(struct ui_browser *self, void *entry, int row); void (*seek)(struct ui_browser *self, off_t offset, int whence); + bool (*filter)(struct ui_browser *self, void *entry); u32 nr_entries; + bool navkeypressed; + bool use_navkeypressed; }; void ui_browser__set_color(struct ui_browser *self, int color); @@ -32,15 +35,23 @@ void ui_browser__refresh_dimensions(struct ui_browser *self); void ui_browser__reset_index(struct ui_browser *self); void ui_browser__gotorc(struct ui_browser *self, int y, int x); -void ui_browser__add_exit_key(struct ui_browser *self, int key); -void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]); void __ui_browser__show_title(struct ui_browser *browser, const char *title); void ui_browser__show_title(struct ui_browser *browser, const char *title); int ui_browser__show(struct ui_browser *self, const char *title, const char *helpline, ...); void ui_browser__hide(struct ui_browser *self); int ui_browser__refresh(struct ui_browser *self); -int ui_browser__run(struct ui_browser *self); +int ui_browser__run(struct ui_browser *browser, int delay_secs); +void ui_browser__update_nr_entries(struct ui_browser *browser, u32 nr_entries); +void ui_browser__handle_resize(struct ui_browser *browser); + +int ui_browser__warning(struct ui_browser *browser, int timeout, + const char *format, ...); +int ui_browser__help_window(struct ui_browser *browser, const char *text); +bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text); + +void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence); +unsigned int ui_browser__argv_refresh(struct ui_browser *browser); void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence); unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self); diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c index 0229723aceb3..295a9c93f945 100644 --- a/tools/perf/util/ui/browsers/annotate.c +++ b/tools/perf/util/ui/browsers/annotate.c @@ -1,31 +1,31 @@ +#include "../../util.h" #include "../browser.h" #include "../helpline.h" #include "../libslang.h" +#include "../ui.h" +#include "../util.h" #include "../../annotate.h" #include "../../hist.h" #include "../../sort.h" #include "../../symbol.h" #include <pthread.h> - -static void ui__error_window(const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - newtWinMessagev((char *)"Error", (char *)"Ok", (char *)fmt, ap); - va_end(ap); -} +#include <newt.h> struct annotate_browser { struct ui_browser b; struct rb_root entries; struct rb_node *curr_hot; + struct objdump_line *selection; + int nr_asm_entries; + int nr_entries; + bool hide_src_code; }; struct objdump_line_rb_node { struct rb_node rb_node; double percent; u32 idx; + int idx_asm; }; static inline @@ -34,9 +34,22 @@ struct objdump_line_rb_node *objdump_line__rb(struct objdump_line *self) return (struct objdump_line_rb_node *)(self + 1); } +static bool objdump_line__filter(struct ui_browser *browser, void *entry) +{ + struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); + + if (ab->hide_src_code) { + struct objdump_line *ol = list_entry(entry, struct objdump_line, node); + return ol->offset == -1; + } + + return false; +} + static void annotate_browser__write(struct ui_browser *self, void *entry, int row) { - struct objdump_line *ol = rb_entry(entry, struct objdump_line, node); + struct annotate_browser *ab = container_of(self, struct annotate_browser, b); + struct objdump_line *ol = list_entry(entry, struct objdump_line, node); bool current_entry = ui_browser__is_current_entry(self, row); int width = self->width; @@ -51,6 +64,11 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro SLsmg_write_char(':'); slsmg_write_nstring(" ", 8); + + /* The scroll bar isn't being used */ + if (!self->navkeypressed) + width += 1; + if (!*ol->line) slsmg_write_nstring(" ", width - 18); else @@ -58,6 +76,8 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro if (!current_entry) ui_browser__set_color(self, HE_COLORSET_CODE); + else + ab->selection = ol; } static double objdump_line__calc_percent(struct objdump_line *self, @@ -141,7 +161,8 @@ static void annotate_browser__set_top(struct annotate_browser *self, static void annotate_browser__calc_percent(struct annotate_browser *browser, int evidx) { - struct symbol *sym = browser->b.priv; + struct map_symbol *ms = browser->b.priv; + struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); struct objdump_line *pos; @@ -163,25 +184,60 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, browser->curr_hot = rb_last(&browser->entries); } +static bool annotate_browser__toggle_source(struct annotate_browser *browser) +{ + struct objdump_line *ol; + struct objdump_line_rb_node *olrb; + off_t offset = browser->b.index - browser->b.top_idx; + + browser->b.seek(&browser->b, offset, SEEK_CUR); + ol = list_entry(browser->b.top, struct objdump_line, node); + olrb = objdump_line__rb(ol); + + if (browser->hide_src_code) { + if (olrb->idx_asm < offset) + offset = olrb->idx; + + browser->b.nr_entries = browser->nr_entries; + browser->hide_src_code = false; + browser->b.seek(&browser->b, -offset, SEEK_CUR); + browser->b.top_idx = olrb->idx - offset; + browser->b.index = olrb->idx; + } else { + if (olrb->idx_asm < 0) { + ui_helpline__puts("Only available for assembly lines."); + browser->b.seek(&browser->b, -offset, SEEK_CUR); + return false; + } + + if (olrb->idx_asm < offset) + offset = olrb->idx_asm; + + browser->b.nr_entries = browser->nr_asm_entries; + browser->hide_src_code = true; + browser->b.seek(&browser->b, -offset, SEEK_CUR); + browser->b.top_idx = olrb->idx_asm - offset; + browser->b.index = olrb->idx_asm; + } + + return true; +} + static int annotate_browser__run(struct annotate_browser *self, int evidx, - int refresh) + void(*timer)(void *arg), + void *arg, int delay_secs) { struct rb_node *nd = NULL; - struct symbol *sym = self->b.priv; - /* - * RIGHT To allow builtin-annotate to cycle thru multiple symbols by - * examining the exit key for this function. - */ - int exit_keys[] = { 'H', NEWT_KEY_TAB, NEWT_KEY_UNTAB, - NEWT_KEY_RIGHT, 0 }; + struct map_symbol *ms = self->b.priv; + struct symbol *sym = ms->sym; + const char *help = "<-, ESC: exit, TAB/shift+TAB: cycle hottest lines, " + "H: Hottest, -> Line action, S -> Toggle source " + "code view"; int key; - if (ui_browser__show(&self->b, sym->name, - "<-, -> or ESC: exit, TAB/shift+TAB: " - "cycle hottest lines, H: Hottest") < 0) + if (ui_browser__show(&self->b, sym->name, help) < 0) return -1; - ui_browser__add_exit_keys(&self->b, exit_keys); annotate_browser__calc_percent(self, evidx); if (self->curr_hot) @@ -189,13 +245,10 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx, nd = self->curr_hot; - if (refresh != 0) - newtFormSetTimer(self->b.form, refresh); - while (1) { - key = ui_browser__run(&self->b); + key = ui_browser__run(&self->b, delay_secs); - if (refresh != 0) { + if (delay_secs != 0) { annotate_browser__calc_percent(self, evidx); /* * Current line focus got out of the list of most active @@ -207,15 +260,14 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx, } switch (key) { - case -1: - /* - * FIXME we need to check if it was - * es.reason == NEWT_EXIT_TIMER - */ - if (refresh != 0) + case K_TIMER: + if (timer != NULL) + timer(arg); + + if (delay_secs != 0) symbol__annotate_decay_histogram(sym, evidx); continue; - case NEWT_KEY_TAB: + case K_TAB: if (nd != NULL) { nd = rb_prev(nd); if (nd == NULL) @@ -223,7 +275,7 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx, } else nd = self->curr_hot; break; - case NEWT_KEY_UNTAB: + case K_UNTAB: if (nd != NULL) nd = rb_next(nd); if (nd == NULL) @@ -234,8 +286,67 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx, case 'H': nd = self->curr_hot; break; - default: + case 'S': + if (annotate_browser__toggle_source(self)) + ui_helpline__puts(help); + continue; + case K_ENTER: + case K_RIGHT: + if (self->selection == NULL) { + ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org"); + continue; + } + + if (self->selection->offset == -1) { + ui_helpline__puts("Actions are only available for assembly lines."); + continue; + } else { + char *s = strstr(self->selection->line, "callq "); + struct annotation *notes; + struct symbol *target; + u64 ip; + + if (s == NULL) { + ui_helpline__puts("Actions are only available for the 'callq' instruction."); + continue; + } + + s = strchr(s, ' '); + if (s++ == NULL) { + ui_helpline__puts("Invallid callq instruction."); + continue; + } + + ip = strtoull(s, NULL, 16); + ip = ms->map->map_ip(ms->map, ip); + target = map__find_symbol(ms->map, ip, NULL); + if (target == NULL) { + ui_helpline__puts("The called function was not found."); + continue; + } + + notes = symbol__annotation(target); + pthread_mutex_lock(¬es->lock); + + if (notes->src == NULL && symbol__alloc_hist(target) < 0) { + pthread_mutex_unlock(¬es->lock); + ui__warning("Not enough memory for annotating '%s' symbol!\n", + target->name); + continue; + } + + pthread_mutex_unlock(¬es->lock); + symbol__tui_annotate(target, ms->map, evidx, + timer, arg, delay_secs); + } + continue; + case K_LEFT: + case K_ESC: + case 'q': + case CTRL('c'): goto out; + default: + continue; } if (nd != NULL) @@ -246,22 +357,31 @@ out: return key; } -int hist_entry__tui_annotate(struct hist_entry *he, int evidx) +int hist_entry__tui_annotate(struct hist_entry *he, int evidx, + void(*timer)(void *arg), void *arg, int delay_secs) { - return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, 0); + return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, + timer, arg, delay_secs); } int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, - int refresh) + void(*timer)(void *arg), void *arg, + int delay_secs) { struct objdump_line *pos, *n; struct annotation *notes; + struct map_symbol ms = { + .map = map, + .sym = sym, + }; struct annotate_browser browser = { .b = { .refresh = ui_browser__list_head_refresh, .seek = ui_browser__list_head_seek, .write = annotate_browser__write, - .priv = sym, + .filter = objdump_line__filter, + .priv = &ms, + .use_navkeypressed = true, }, }; int ret; @@ -273,7 +393,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, return -1; if (symbol__annotate(sym, map, sizeof(struct objdump_line_rb_node)) < 0) { - ui__error_window(ui_helpline__last_msg); + ui__error("%s", ui_helpline__last_msg); return -1; } @@ -288,12 +408,17 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, if (browser.b.width < line_len) browser.b.width = line_len; rbpos = objdump_line__rb(pos); - rbpos->idx = browser.b.nr_entries++; + rbpos->idx = browser.nr_entries++; + if (pos->offset != -1) + rbpos->idx_asm = browser.nr_asm_entries++; + else + rbpos->idx_asm = -1; } + browser.b.nr_entries = browser.nr_entries; browser.b.entries = ¬es->src->source, browser.b.width += 18; /* Percentage */ - ret = annotate_browser__run(&browser, evidx, refresh); + ret = annotate_browser__run(&browser, evidx, timer, arg, delay_secs); list_for_each_entry_safe(pos, n, ¬es->src->source, node) { list_del(&pos->node); objdump_line__free(pos); diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c index 5d767c622dfc..1212a386a033 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/util/ui/browsers/hists.c @@ -17,6 +17,7 @@ #include "../browser.h" #include "../helpline.h" #include "../util.h" +#include "../ui.h" #include "map.h" struct hist_browser { @@ -24,8 +25,12 @@ struct hist_browser { struct hists *hists; struct hist_entry *he_selection; struct map_symbol *selection; + bool has_symbols; }; +static int hists__browser_title(struct hists *self, char *bf, size_t size, + const char *ev_name); + static void hist_browser__refresh_dimensions(struct hist_browser *self) { /* 3 == +/- toggle symbol before actual hist_entry rendering */ @@ -290,28 +295,49 @@ static void hist_browser__set_folding(struct hist_browser *self, bool unfold) ui_browser__reset_index(&self->b); } -static int hist_browser__run(struct hist_browser *self, const char *title) +static void ui_browser__warn_lost_events(struct ui_browser *browser) +{ + ui_browser__warning(browser, 4, + "Events are being lost, check IO/CPU overload!\n\n" + "You may want to run 'perf' using a RT scheduler policy:\n\n" + " perf top -r 80\n\n" + "Or reduce the sampling frequency."); +} + +static int hist_browser__run(struct hist_browser *self, const char *ev_name, + void(*timer)(void *arg), void *arg, int delay_secs) { int key; - int exit_keys[] = { 'a', '?', 'h', 'C', 'd', 'D', 'E', 't', - NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT, - NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0, }; + char title[160]; self->b.entries = &self->hists->entries; self->b.nr_entries = self->hists->nr_entries; hist_browser__refresh_dimensions(self); + hists__browser_title(self->hists, title, sizeof(title), ev_name); if (ui_browser__show(&self->b, title, "Press '?' for help on key bindings") < 0) return -1; - ui_browser__add_exit_keys(&self->b, exit_keys); - while (1) { - key = ui_browser__run(&self->b); + key = ui_browser__run(&self->b, delay_secs); switch (key) { + case K_TIMER: + timer(arg); + ui_browser__update_nr_entries(&self->b, self->hists->nr_entries); + + if (self->hists->stats.nr_lost_warned != + self->hists->stats.nr_events[PERF_RECORD_LOST]) { + self->hists->stats.nr_lost_warned = + self->hists->stats.nr_events[PERF_RECORD_LOST]; + ui_browser__warn_lost_events(&self->b); + } + + hists__browser_title(self->hists, title, sizeof(title), ev_name); + ui_browser__show_title(&self->b, title); + continue; case 'D': { /* Debug */ static int seq; struct hist_entry *h = rb_entry(self->b.top, @@ -334,7 +360,7 @@ static int hist_browser__run(struct hist_browser *self, const char *title) /* Expand the whole world. */ hist_browser__set_folding(self, true); break; - case NEWT_KEY_ENTER: + case K_ENTER: if (hist_browser__toggle_fold(self)) break; /* fall thru */ @@ -532,7 +558,7 @@ static int hist_browser__show_entry(struct hist_browser *self, char s[256]; double percent; int printed = 0; - int color, width = self->b.width; + int width = self->b.width - 6; /* The percentage */ char folded_sign = ' '; bool current_entry = ui_browser__is_current_entry(&self->b, row); off_t row_offset = entry->row_offset; @@ -548,26 +574,35 @@ static int hist_browser__show_entry(struct hist_browser *self, } if (row_offset == 0) { - hist_entry__snprintf(entry, s, sizeof(s), self->hists, NULL, false, - 0, false, self->hists->stats.total_period); + hist_entry__snprintf(entry, s, sizeof(s), self->hists); percent = (entry->period * 100.0) / self->hists->stats.total_period; - color = HE_COLORSET_SELECTED; - if (!current_entry) { - if (percent >= MIN_RED) - color = HE_COLORSET_TOP; - else if (percent >= MIN_GREEN) - color = HE_COLORSET_MEDIUM; - else - color = HE_COLORSET_NORMAL; - } - - ui_browser__set_color(&self->b, color); + ui_browser__set_percent_color(&self->b, percent, current_entry); ui_browser__gotorc(&self->b, row, 0); if (symbol_conf.use_callchain) { slsmg_printf("%c ", folded_sign); width -= 2; } + + slsmg_printf(" %5.2f%%", percent); + + /* The scroll bar isn't being used */ + if (!self->b.navkeypressed) + width += 1; + + if (!current_entry || !self->b.navkeypressed) + ui_browser__set_color(&self->b, HE_COLORSET_NORMAL); + + if (symbol_conf.show_nr_samples) { + slsmg_printf(" %11u", entry->nr_events); + width -= 12; + } + + if (symbol_conf.show_total_period) { + slsmg_printf(" %12" PRIu64, entry->period); + width -= 13; + } + slsmg_write_nstring(s, width); ++row; ++printed; @@ -585,14 +620,23 @@ static int hist_browser__show_entry(struct hist_browser *self, return printed; } +static void ui_browser__hists_init_top(struct ui_browser *browser) +{ + if (browser->top == NULL) { + struct hist_browser *hb; + + hb = container_of(browser, struct hist_browser, b); + browser->top = rb_first(&hb->hists->entries); + } +} + static unsigned int hist_browser__refresh(struct ui_browser *self) { unsigned row = 0; struct rb_node *nd; struct hist_browser *hb = container_of(self, struct hist_browser, b); - if (self->top == NULL) - self->top = rb_first(&hb->hists->entries); + ui_browser__hists_init_top(self); for (nd = self->top; nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); @@ -644,6 +688,8 @@ static void ui_browser__hists_seek(struct ui_browser *self, if (self->nr_entries == 0) return; + ui_browser__hists_init_top(self); + switch (whence) { case SEEK_SET: nd = hists__filter_entries(rb_first(self->entries)); @@ -761,6 +807,8 @@ static struct hist_browser *hist_browser__new(struct hists *hists) self->hists = hists; self->b.refresh = hist_browser__refresh; self->b.seek = ui_browser__hists_seek; + self->b.use_navkeypressed = true, + self->has_symbols = sort_sym.list.next != NULL; } return self; @@ -782,11 +830,12 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *self) } static int hists__browser_title(struct hists *self, char *bf, size_t size, - const char *ev_name, const struct dso *dso, - const struct thread *thread) + const char *ev_name) { char unit; int printed; + const struct dso *dso = self->dso_filter; + const struct thread *thread = self->thread_filter; unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE]; nr_events = convert_unit(nr_events, &unit); @@ -803,16 +852,15 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size, return printed; } -static int perf_evsel__hists_browse(struct perf_evsel *evsel, +static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, const char *helpline, const char *ev_name, - bool left_exits) + bool left_exits, + void(*timer)(void *arg), void *arg, + int delay_secs) { struct hists *self = &evsel->hists; struct hist_browser *browser = hist_browser__new(self); struct pstack *fstack; - const struct thread *thread_filter = NULL; - const struct dso *dso_filter = NULL; - char msg[160]; int key = -1; if (browser == NULL) @@ -824,8 +872,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, ui_helpline__push(helpline); - hists__browser_title(self, msg, sizeof(msg), ev_name, - dso_filter, thread_filter); while (1) { const struct thread *thread = NULL; const struct dso *dso = NULL; @@ -834,7 +880,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, annotate = -2, zoom_dso = -2, zoom_thread = -2, browse_map = -2; - key = hist_browser__run(browser, msg); + key = hist_browser__run(browser, ev_name, timer, arg, delay_secs); if (browser->he_selection != NULL) { thread = hist_browser__selected_thread(browser); @@ -842,14 +888,23 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, } switch (key) { - case NEWT_KEY_TAB: - case NEWT_KEY_UNTAB: + case K_TAB: + case K_UNTAB: + if (nr_events == 1) + continue; /* * Exit the browser, let hists__browser_tree * go to the next or previous */ goto out_free_stack; case 'a': + if (!browser->has_symbols) { + ui_browser__warning(&browser->b, delay_secs * 2, + "Annotation is only available for symbolic views, " + "include \"sym\" in --sort to use it."); + continue; + } + if (browser->selection == NULL || browser->selection->sym == NULL || browser->selection->map->dso->annotate_warned) @@ -859,25 +914,30 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, goto zoom_dso; case 't': goto zoom_thread; - case NEWT_KEY_F1: + case K_F1: case 'h': case '?': - ui__help_window("-> Zoom into DSO/Threads & Annotate current symbol\n" - "<- Zoom out\n" - "a Annotate current symbol\n" - "h/?/F1 Show this window\n" - "C Collapse all callchains\n" - "E Expand all callchains\n" - "d Zoom into current DSO\n" - "t Zoom into current Thread\n" - "TAB/UNTAB Switch events\n" - "q/CTRL+C Exit browser"); + ui_browser__help_window(&browser->b, + "h/?/F1 Show this window\n" + "UP/DOWN/PGUP\n" + "PGDN/SPACE Navigate\n" + "q/ESC/CTRL+C Exit browser\n\n" + "For multiple event sessions:\n\n" + "TAB/UNTAB Switch events\n\n" + "For symbolic views (--sort has sym):\n\n" + "-> Zoom into DSO/Threads & Annotate current symbol\n" + "<- Zoom out\n" + "a Annotate current symbol\n" + "C Collapse all callchains\n" + "E Expand all callchains\n" + "d Zoom into current DSO\n" + "t Zoom into current Thread"); continue; - case NEWT_KEY_ENTER: - case NEWT_KEY_RIGHT: + case K_ENTER: + case K_RIGHT: /* menu */ break; - case NEWT_KEY_LEFT: { + case K_LEFT: { const void *top; if (pstack__empty(fstack)) { @@ -889,21 +949,28 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, continue; } top = pstack__pop(fstack); - if (top == &dso_filter) + if (top == &browser->hists->dso_filter) goto zoom_out_dso; - if (top == &thread_filter) + if (top == &browser->hists->thread_filter) goto zoom_out_thread; continue; } - case NEWT_KEY_ESCAPE: + case K_ESC: if (!left_exits && - !ui__dialog_yesno("Do you really want to exit?")) + !ui_browser__dialog_yesno(&browser->b, + "Do you really want to exit?")) continue; /* Fall thru */ - default: + case 'q': + case CTRL('c'): goto out_free_stack; + default: + continue; } + if (!browser->has_symbols) + goto add_exit_option; + if (browser->selection != NULL && browser->selection->sym != NULL && !browser->selection->map->dso->annotate_warned && @@ -913,14 +980,14 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, if (thread != NULL && asprintf(&options[nr_options], "Zoom %s %s(%d) thread", - (thread_filter ? "out of" : "into"), + (browser->hists->thread_filter ? "out of" : "into"), (thread->comm_set ? thread->comm : ""), thread->pid) > 0) zoom_thread = nr_options++; if (dso != NULL && asprintf(&options[nr_options], "Zoom %s %s DSO", - (dso_filter ? "out of" : "into"), + (browser->hists->dso_filter ? "out of" : "into"), (dso->kernel ? "the Kernel" : dso->short_name)) > 0) zoom_dso = nr_options++; @@ -928,7 +995,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, browser->selection->map != NULL && asprintf(&options[nr_options], "Browse map details") > 0) browse_map = nr_options++; - +add_exit_option: options[nr_options++] = (char *)"Exit"; choice = ui__popup_menu(nr_options, options); @@ -944,50 +1011,59 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, if (choice == annotate) { struct hist_entry *he; + int err; do_annotate: he = hist_browser__selected_entry(browser); if (he == NULL) continue; - - hist_entry__tui_annotate(he, evsel->idx); + /* + * Don't let this be freed, say, by hists__decay_entry. + */ + he->used = true; + err = hist_entry__tui_annotate(he, evsel->idx, + timer, arg, delay_secs); + he->used = false; + ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries); + if (err) + ui_browser__handle_resize(&browser->b); } else if (choice == browse_map) map__browse(browser->selection->map); else if (choice == zoom_dso) { zoom_dso: - if (dso_filter) { - pstack__remove(fstack, &dso_filter); + if (browser->hists->dso_filter) { + pstack__remove(fstack, &browser->hists->dso_filter); zoom_out_dso: ui_helpline__pop(); - dso_filter = NULL; + browser->hists->dso_filter = NULL; + sort_dso.elide = false; } else { if (dso == NULL) continue; ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"", dso->kernel ? "the Kernel" : dso->short_name); - dso_filter = dso; - pstack__push(fstack, &dso_filter); + browser->hists->dso_filter = dso; + sort_dso.elide = true; + pstack__push(fstack, &browser->hists->dso_filter); } - hists__filter_by_dso(self, dso_filter); - hists__browser_title(self, msg, sizeof(msg), ev_name, - dso_filter, thread_filter); + hists__filter_by_dso(self); hist_browser__reset(browser); } else if (choice == zoom_thread) { zoom_thread: - if (thread_filter) { - pstack__remove(fstack, &thread_filter); + if (browser->hists->thread_filter) { + pstack__remove(fstack, &browser->hists->thread_filter); zoom_out_thread: ui_helpline__pop(); - thread_filter = NULL; + browser->hists->thread_filter = NULL; + sort_thread.elide = false; } else { ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"", thread->comm_set ? thread->comm : "", thread->pid); - thread_filter = thread; - pstack__push(fstack, &thread_filter); + browser->hists->thread_filter = thread; + sort_thread.elide = true; + pstack__push(fstack, &browser->hists->thread_filter); } - hists__filter_by_thread(self, thread_filter); - hists__browser_title(self, msg, sizeof(msg), ev_name, - dso_filter, thread_filter); + hists__filter_by_thread(self); hist_browser__reset(browser); } } @@ -1001,6 +1077,7 @@ out: struct perf_evsel_menu { struct ui_browser b; struct perf_evsel *selection; + bool lost_events, lost_events_warned; }; static void perf_evsel_menu__write(struct ui_browser *browser, @@ -1013,22 +1090,38 @@ static void perf_evsel_menu__write(struct ui_browser *browser, unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE]; const char *ev_name = event_name(evsel); char bf[256], unit; + const char *warn = " "; + size_t printed; ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : HE_COLORSET_NORMAL); nr_events = convert_unit(nr_events, &unit); - snprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events, - unit, unit == ' ' ? "" : " ", ev_name); - slsmg_write_nstring(bf, browser->width); + printed = snprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events, + unit, unit == ' ' ? "" : " ", ev_name); + slsmg_printf("%s", bf); + + nr_events = evsel->hists.stats.nr_events[PERF_RECORD_LOST]; + if (nr_events != 0) { + menu->lost_events = true; + if (!current_entry) + ui_browser__set_color(browser, HE_COLORSET_TOP); + nr_events = convert_unit(nr_events, &unit); + snprintf(bf, sizeof(bf), ": %ld%c%schunks LOST!", nr_events, + unit, unit == ' ' ? "" : " "); + warn = bf; + } + + slsmg_write_nstring(warn, browser->width - printed); if (current_entry) menu->selection = evsel; } -static int perf_evsel_menu__run(struct perf_evsel_menu *menu, const char *help) +static int perf_evsel_menu__run(struct perf_evsel_menu *menu, + int nr_events, const char *help, + void(*timer)(void *arg), void *arg, int delay_secs) { - int exit_keys[] = { NEWT_KEY_ENTER, NEWT_KEY_RIGHT, 0, }; struct perf_evlist *evlist = menu->b.priv; struct perf_evsel *pos; const char *ev_name, *title = "Available samples"; @@ -1038,50 +1131,72 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu, const char *help) "ESC: exit, ENTER|->: Browse histograms") < 0) return -1; - ui_browser__add_exit_keys(&menu->b, exit_keys); - while (1) { - key = ui_browser__run(&menu->b); + key = ui_browser__run(&menu->b, delay_secs); switch (key) { - case NEWT_KEY_RIGHT: - case NEWT_KEY_ENTER: + case K_TIMER: + timer(arg); + + if (!menu->lost_events_warned && menu->lost_events) { + ui_browser__warn_lost_events(&menu->b); + menu->lost_events_warned = true; + } + continue; + case K_RIGHT: + case K_ENTER: if (!menu->selection) continue; pos = menu->selection; browse_hists: + perf_evlist__set_selected(evlist, pos); + /* + * Give the calling tool a chance to populate the non + * default evsel resorted hists tree. + */ + if (timer) + timer(arg); ev_name = event_name(pos); - key = perf_evsel__hists_browse(pos, help, ev_name, true); + key = perf_evsel__hists_browse(pos, nr_events, help, + ev_name, true, timer, + arg, delay_secs); ui_browser__show_title(&menu->b, title); - break; - case NEWT_KEY_LEFT: + switch (key) { + case K_TAB: + if (pos->node.next == &evlist->entries) + pos = list_entry(evlist->entries.next, struct perf_evsel, node); + else + pos = list_entry(pos->node.next, struct perf_evsel, node); + goto browse_hists; + case K_UNTAB: + if (pos->node.prev == &evlist->entries) + pos = list_entry(evlist->entries.prev, struct perf_evsel, node); + else + pos = list_entry(pos->node.prev, struct perf_evsel, node); + goto browse_hists; + case K_ESC: + if (!ui_browser__dialog_yesno(&menu->b, + "Do you really want to exit?")) + continue; + /* Fall thru */ + case 'q': + case CTRL('c'): + goto out; + default: + continue; + } + case K_LEFT: continue; - case NEWT_KEY_ESCAPE: - if (!ui__dialog_yesno("Do you really want to exit?")) + case K_ESC: + if (!ui_browser__dialog_yesno(&menu->b, + "Do you really want to exit?")) continue; /* Fall thru */ - default: - goto out; - } - - switch (key) { - case NEWT_KEY_TAB: - if (pos->node.next == &evlist->entries) - pos = list_entry(evlist->entries.next, struct perf_evsel, node); - else - pos = list_entry(pos->node.next, struct perf_evsel, node); - goto browse_hists; - case NEWT_KEY_UNTAB: - if (pos->node.prev == &evlist->entries) - pos = list_entry(evlist->entries.prev, struct perf_evsel, node); - else - pos = list_entry(pos->node.prev, struct perf_evsel, node); - goto browse_hists; case 'q': case CTRL('c'): goto out; default: - break; + continue; } } @@ -1091,7 +1206,9 @@ out: } static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, - const char *help) + const char *help, + void(*timer)(void *arg), void *arg, + int delay_secs) { struct perf_evsel *pos; struct perf_evsel_menu menu = { @@ -1121,18 +1238,24 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, pos->name = strdup(ev_name); } - return perf_evsel_menu__run(&menu, help); + return perf_evsel_menu__run(&menu, evlist->nr_entries, help, timer, + arg, delay_secs); } -int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help) +int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, + void(*timer)(void *arg), void *arg, + int delay_secs) { if (evlist->nr_entries == 1) { struct perf_evsel *first = list_entry(evlist->entries.next, struct perf_evsel, node); const char *ev_name = event_name(first); - return perf_evsel__hists_browse(first, help, ev_name, false); + return perf_evsel__hists_browse(first, evlist->nr_entries, help, + ev_name, false, timer, arg, + delay_secs); } - return __perf_evlist__tui_browse_hists(evlist, help); + return __perf_evlist__tui_browse_hists(evlist, help, + timer, arg, delay_secs); } diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c index 8462bffe20bc..6905bcc8be2d 100644 --- a/tools/perf/util/ui/browsers/map.c +++ b/tools/perf/util/ui/browsers/map.c @@ -1,5 +1,6 @@ #include "../libslang.h" #include <elf.h> +#include <newt.h> #include <inttypes.h> #include <sys/ttydefaults.h> #include <ctype.h> @@ -108,11 +109,8 @@ static int map_browser__run(struct map_browser *self) verbose ? "" : "restart with -v to use") < 0) return -1; - if (verbose) - ui_browser__add_exit_key(&self->b, '/'); - while (1) { - key = ui_browser__run(&self->b); + key = ui_browser__run(&self->b, 0); if (verbose && key == '/') map_browser__search(self); diff --git a/tools/perf/util/ui/browsers/top.c b/tools/perf/util/ui/browsers/top.c deleted file mode 100644 index 5a06538532af..000000000000 --- a/tools/perf/util/ui/browsers/top.c +++ /dev/null @@ -1,213 +0,0 @@ -/* - * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> - * - * Parts came from builtin-{top,stat,record}.c, see those files for further - * copyright notes. - * - * Released under the GPL v2. (and only v2, not any later version) - */ -#include "../browser.h" -#include "../../annotate.h" -#include "../helpline.h" -#include "../libslang.h" -#include "../util.h" -#include "../../evlist.h" -#include "../../hist.h" -#include "../../sort.h" -#include "../../symbol.h" -#include "../../top.h" - -struct perf_top_browser { - struct ui_browser b; - struct rb_root root; - struct sym_entry *selection; - float sum_ksamples; - int dso_width; - int dso_short_width; - int sym_width; -}; - -static void perf_top_browser__write(struct ui_browser *browser, void *entry, int row) -{ - struct perf_top_browser *top_browser = container_of(browser, struct perf_top_browser, b); - struct sym_entry *syme = rb_entry(entry, struct sym_entry, rb_node); - bool current_entry = ui_browser__is_current_entry(browser, row); - struct symbol *symbol = sym_entry__symbol(syme); - struct perf_top *top = browser->priv; - int width = browser->width; - double pcnt; - - pcnt = 100.0 - (100.0 * ((top_browser->sum_ksamples - syme->snap_count) / - top_browser->sum_ksamples)); - ui_browser__set_percent_color(browser, pcnt, current_entry); - - if (top->evlist->nr_entries == 1 || !top->display_weighted) { - slsmg_printf("%20.2f ", syme->weight); - width -= 24; - } else { - slsmg_printf("%9.1f %10ld ", syme->weight, syme->snap_count); - width -= 23; - } - - slsmg_printf("%4.1f%%", pcnt); - width -= 7; - - if (verbose) { - slsmg_printf(" %016" PRIx64, symbol->start); - width -= 17; - } - - slsmg_printf(" %-*.*s ", top_browser->sym_width, top_browser->sym_width, - symbol->name); - width -= top_browser->sym_width; - slsmg_write_nstring(width >= syme->map->dso->long_name_len ? - syme->map->dso->long_name : - syme->map->dso->short_name, width); - - if (current_entry) - top_browser->selection = syme; -} - -static void perf_top_browser__update_rb_tree(struct perf_top_browser *browser) -{ - struct perf_top *top = browser->b.priv; - u64 top_idx = browser->b.top_idx; - - browser->root = RB_ROOT; - browser->b.top = NULL; - browser->sum_ksamples = perf_top__decay_samples(top, &browser->root); - /* - * No active symbols - */ - if (top->rb_entries == 0) - return; - - perf_top__find_widths(top, &browser->root, &browser->dso_width, - &browser->dso_short_width, - &browser->sym_width); - if (browser->sym_width + browser->dso_width > browser->b.width - 29) { - browser->dso_width = browser->dso_short_width; - if (browser->sym_width + browser->dso_width > browser->b.width - 29) - browser->sym_width = browser->b.width - browser->dso_width - 29; - } - - /* - * Adjust the ui_browser indexes since the entries in the browser->root - * rb_tree may have changed, then seek it from start, so that we get a - * possible new top of the screen. - */ - browser->b.nr_entries = top->rb_entries; - - if (top_idx >= browser->b.nr_entries) { - if (browser->b.height >= browser->b.nr_entries) - top_idx = browser->b.nr_entries - browser->b.height; - else - top_idx = 0; - } - - if (browser->b.index >= top_idx + browser->b.height) - browser->b.index = top_idx + browser->b.index - browser->b.top_idx; - - if (browser->b.index >= browser->b.nr_entries) - browser->b.index = browser->b.nr_entries - 1; - - browser->b.top_idx = top_idx; - browser->b.seek(&browser->b, top_idx, SEEK_SET); -} - -static void perf_top_browser__annotate(struct perf_top_browser *browser) -{ - struct sym_entry *syme = browser->selection; - struct symbol *sym = sym_entry__symbol(syme); - struct annotation *notes = symbol__annotation(sym); - struct perf_top *top = browser->b.priv; - - if (notes->src != NULL) - goto do_annotation; - - pthread_mutex_lock(¬es->lock); - - top->sym_filter_entry = NULL; - - if (symbol__alloc_hist(sym, top->evlist->nr_entries) < 0) { - pr_err("Not enough memory for annotating '%s' symbol!\n", - sym->name); - pthread_mutex_unlock(¬es->lock); - return; - } - - top->sym_filter_entry = syme; - - pthread_mutex_unlock(¬es->lock); -do_annotation: - symbol__tui_annotate(sym, syme->map, 0, top->delay_secs * 1000); -} - -static int perf_top_browser__run(struct perf_top_browser *browser) -{ - int key; - char title[160]; - struct perf_top *top = browser->b.priv; - int delay_msecs = top->delay_secs * 1000; - int exit_keys[] = { 'a', NEWT_KEY_ENTER, NEWT_KEY_RIGHT, 0, }; - - perf_top_browser__update_rb_tree(browser); - perf_top__header_snprintf(top, title, sizeof(title)); - perf_top__reset_sample_counters(top); - - if (ui_browser__show(&browser->b, title, - "ESC: exit, ENTER|->|a: Live Annotate") < 0) - return -1; - - newtFormSetTimer(browser->b.form, delay_msecs); - ui_browser__add_exit_keys(&browser->b, exit_keys); - - while (1) { - key = ui_browser__run(&browser->b); - - switch (key) { - case -1: - /* FIXME we need to check if it was es.reason == NEWT_EXIT_TIMER */ - perf_top_browser__update_rb_tree(browser); - perf_top__header_snprintf(top, title, sizeof(title)); - perf_top__reset_sample_counters(top); - ui_browser__set_color(&browser->b, NEWT_COLORSET_ROOT); - SLsmg_gotorc(0, 0); - slsmg_write_nstring(title, browser->b.width); - break; - case 'a': - case NEWT_KEY_RIGHT: - case NEWT_KEY_ENTER: - if (browser->selection) - perf_top_browser__annotate(browser); - break; - case NEWT_KEY_LEFT: - continue; - case NEWT_KEY_ESCAPE: - if (!ui__dialog_yesno("Do you really want to exit?")) - continue; - /* Fall thru */ - default: - goto out; - } - } -out: - ui_browser__hide(&browser->b); - return key; -} - -int perf_top__tui_browser(struct perf_top *top) -{ - struct perf_top_browser browser = { - .b = { - .entries = &browser.root, - .refresh = ui_browser__rb_tree_refresh, - .seek = ui_browser__rb_tree_seek, - .write = perf_top_browser__write, - .priv = top, - }, - }; - - ui_helpline__push("Press <- or ESC to exit"); - return perf_top_browser__run(&browser); -} diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/util/ui/helpline.c index f36d2ff509ed..6ef3c5691762 100644 --- a/tools/perf/util/ui/helpline.c +++ b/tools/perf/util/ui/helpline.c @@ -1,20 +1,28 @@ #define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> -#include <newt.h> +#include <string.h> #include "../debug.h" #include "helpline.h" #include "ui.h" +#include "libslang.h" void ui_helpline__pop(void) { - newtPopHelpLine(); } +char ui_helpline__current[512]; + void ui_helpline__push(const char *msg) { - newtPushHelpLine(msg); + const size_t sz = sizeof(ui_helpline__current); + + SLsmg_gotorc(SLtt_Screen_Rows - 1, 0); + SLsmg_set_color(0); + SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols); + SLsmg_refresh(); + strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0'; } void ui_helpline__vpush(const char *fmt, va_list ap) @@ -63,7 +71,7 @@ int ui_helpline__show_help(const char *format, va_list ap) if (ui_helpline__last_msg[backlog - 1] == '\n') { ui_helpline__puts(ui_helpline__last_msg); - newtRefresh(); + SLsmg_refresh(); backlog = 0; } pthread_mutex_unlock(&ui__lock); diff --git a/tools/perf/util/ui/helpline.h b/tools/perf/util/ui/helpline.h index ab6028d0c401..7bab6b34e35e 100644 --- a/tools/perf/util/ui/helpline.h +++ b/tools/perf/util/ui/helpline.h @@ -1,6 +1,9 @@ #ifndef _PERF_UI_HELPLINE_H_ #define _PERF_UI_HELPLINE_H_ 1 +#include <stdio.h> +#include <stdarg.h> + void ui_helpline__init(void); void ui_helpline__pop(void); void ui_helpline__push(const char *msg); @@ -8,4 +11,6 @@ void ui_helpline__vpush(const char *fmt, va_list ap); void ui_helpline__fpush(const char *fmt, ...); void ui_helpline__puts(const char *msg); +extern char ui_helpline__current[]; + #endif /* _PERF_UI_HELPLINE_H_ */ diff --git a/tools/perf/util/ui/keysyms.h b/tools/perf/util/ui/keysyms.h new file mode 100644 index 000000000000..3458b1985761 --- /dev/null +++ b/tools/perf/util/ui/keysyms.h @@ -0,0 +1,25 @@ +#ifndef _PERF_KEYSYMS_H_ +#define _PERF_KEYSYMS_H_ 1 + +#include "libslang.h" + +#define K_DOWN SL_KEY_DOWN +#define K_END SL_KEY_END +#define K_ENTER '\r' +#define K_ESC 033 +#define K_F1 SL_KEY_F(1) +#define K_HOME SL_KEY_HOME +#define K_LEFT SL_KEY_LEFT +#define K_PGDN SL_KEY_NPAGE +#define K_PGUP SL_KEY_PPAGE +#define K_RIGHT SL_KEY_RIGHT +#define K_TAB '\t' +#define K_UNTAB SL_KEY_UNTAB +#define K_UP SL_KEY_UP + +/* Not really keys */ +#define K_TIMER -1 +#define K_ERROR -2 +#define K_RESIZE -3 + +#endif /* _PERF_KEYSYMS_H_ */ diff --git a/tools/perf/util/ui/libslang.h b/tools/perf/util/ui/libslang.h index 2b63e1c9b181..4d54b6450f5b 100644 --- a/tools/perf/util/ui/libslang.h +++ b/tools/perf/util/ui/libslang.h @@ -24,4 +24,6 @@ #define sltt_set_color SLtt_set_color #endif +#define SL_KEY_UNTAB 0x1000 + #endif /* _PERF_UI_SLANG_H_ */ diff --git a/tools/perf/util/ui/progress.c b/tools/perf/util/ui/progress.c index d7fc399d36b3..13aa64e50e11 100644 --- a/tools/perf/util/ui/progress.c +++ b/tools/perf/util/ui/progress.c @@ -1,60 +1,32 @@ -#include <stdlib.h> -#include <newt.h> #include "../cache.h" #include "progress.h" +#include "libslang.h" +#include "ui.h" +#include "browser.h" -struct ui_progress { - newtComponent form, scale; -}; - -struct ui_progress *ui_progress__new(const char *title, u64 total) -{ - struct ui_progress *self = malloc(sizeof(*self)); - - if (self != NULL) { - int cols; - - if (use_browser <= 0) - return self; - newtGetScreenSize(&cols, NULL); - cols -= 4; - newtCenteredWindow(cols, 1, title); - self->form = newtForm(NULL, NULL, 0); - if (self->form == NULL) - goto out_free_self; - self->scale = newtScale(0, 0, cols, total); - if (self->scale == NULL) - goto out_free_form; - newtFormAddComponent(self->form, self->scale); - newtRefresh(); - } - - return self; - -out_free_form: - newtFormDestroy(self->form); -out_free_self: - free(self); - return NULL; -} - -void ui_progress__update(struct ui_progress *self, u64 curr) +void ui_progress__update(u64 curr, u64 total, const char *title) { + int bar, y; /* * FIXME: We should have a per UI backend way of showing progress, * stdio will just show a percentage as NN%, etc. */ if (use_browser <= 0) return; - newtScaleSet(self->scale, curr); - newtRefresh(); -} -void ui_progress__delete(struct ui_progress *self) -{ - if (use_browser > 0) { - newtFormDestroy(self->form); - newtPopWindow(); - } - free(self); + if (total == 0) + return; + + ui__refresh_dimensions(true); + pthread_mutex_lock(&ui__lock); + y = SLtt_Screen_Rows / 2 - 2; + SLsmg_set_color(0); + SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols); + SLsmg_gotorc(y++, 1); + SLsmg_write_string((char *)title); + SLsmg_set_color(HE_COLORSET_SELECTED); + bar = ((SLtt_Screen_Cols - 2) * curr) / total; + SLsmg_fill_region(y, 1, 1, bar, ' '); + SLsmg_refresh(); + pthread_mutex_unlock(&ui__lock); } diff --git a/tools/perf/util/ui/progress.h b/tools/perf/util/ui/progress.h index a3820a0beb5b..d9c205b59aa1 100644 --- a/tools/perf/util/ui/progress.h +++ b/tools/perf/util/ui/progress.h @@ -1,11 +1,8 @@ #ifndef _PERF_UI_PROGRESS_H_ #define _PERF_UI_PROGRESS_H_ 1 -struct ui_progress; +#include <../types.h> -struct ui_progress *ui_progress__new(const char *title, u64 total); -void ui_progress__delete(struct ui_progress *self); - -void ui_progress__update(struct ui_progress *self, u64 curr); +void ui_progress__update(u64 curr, u64 total, const char *title); #endif diff --git a/tools/perf/util/ui/setup.c b/tools/perf/util/ui/setup.c index ee46d671db59..85a69faa09aa 100644 --- a/tools/perf/util/ui/setup.c +++ b/tools/perf/util/ui/setup.c @@ -7,9 +7,85 @@ #include "browser.h" #include "helpline.h" #include "ui.h" +#include "util.h" +#include "libslang.h" +#include "keysyms.h" pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; +static volatile int ui__need_resize; + +void ui__refresh_dimensions(bool force) +{ + if (force || ui__need_resize) { + ui__need_resize = 0; + pthread_mutex_lock(&ui__lock); + SLtt_get_screen_size(); + SLsmg_reinit_smg(); + pthread_mutex_unlock(&ui__lock); + } +} + +static void ui__sigwinch(int sig __used) +{ + ui__need_resize = 1; +} + +static void ui__setup_sigwinch(void) +{ + static bool done; + + if (done) + return; + + done = true; + pthread__unblock_sigwinch(); + signal(SIGWINCH, ui__sigwinch); +} + +int ui__getch(int delay_secs) +{ + struct timeval timeout, *ptimeout = delay_secs ? &timeout : NULL; + fd_set read_set; + int err, key; + + ui__setup_sigwinch(); + + FD_ZERO(&read_set); + FD_SET(0, &read_set); + + if (delay_secs) { + timeout.tv_sec = delay_secs; + timeout.tv_usec = 0; + } + + err = select(1, &read_set, NULL, NULL, ptimeout); + + if (err == 0) + return K_TIMER; + + if (err == -1) { + if (errno == EINTR) + return K_RESIZE; + return K_ERROR; + } + + key = SLang_getkey(); + if (key != K_ESC) + return key; + + FD_ZERO(&read_set); + FD_SET(0, &read_set); + timeout.tv_sec = 0; + timeout.tv_usec = 20; + err = select(1, &read_set, NULL, NULL, &timeout); + if (err == 0) + return K_ESC; + + SLang_ungetkey(key); + return SLkp_getkey(); +} + static void newt_suspend(void *d __used) { newtSuspend(); @@ -17,6 +93,33 @@ static void newt_suspend(void *d __used) newtResume(); } +static int ui__init(void) +{ + int err = SLkp_init(); + + if (err < 0) + goto out; + + SLkp_define_keysym((char *)"^(kB)", SL_KEY_UNTAB); +out: + return err; +} + +static void ui__exit(void) +{ + SLtt_set_cursor_visibility(1); + SLsmg_refresh(); + SLsmg_reset_smg(); + SLang_reset_tty(); +} + +static void ui__signal(int sig) +{ + ui__exit(); + psignal(sig, "perf"); + exit(0); +} + void setup_browser(bool fallback_to_pager) { if (!isatty(1) || !use_browser || dump_trace) { @@ -28,19 +131,25 @@ void setup_browser(bool fallback_to_pager) use_browser = 1; newtInit(); - newtCls(); + ui__init(); newtSetSuspendCallback(newt_suspend, NULL); ui_helpline__init(); ui_browser__init(); + + signal(SIGSEGV, ui__signal); + signal(SIGFPE, ui__signal); + signal(SIGINT, ui__signal); + signal(SIGQUIT, ui__signal); + signal(SIGTERM, ui__signal); } void exit_browser(bool wait_for_ok) { if (use_browser > 0) { - if (wait_for_ok) { - char title[] = "Fatal Error", ok[] = "Ok"; - newtWinMessage(title, ok, ui_helpline__last_msg); - } - newtFinished(); + if (wait_for_ok) + ui__question_window("Fatal Error", + ui_helpline__last_msg, + "Press any key...", 0); + ui__exit(); } } diff --git a/tools/perf/util/ui/ui.h b/tools/perf/util/ui/ui.h index d264e059c829..7b67045479f6 100644 --- a/tools/perf/util/ui/ui.h +++ b/tools/perf/util/ui/ui.h @@ -2,7 +2,10 @@ #define _PERF_UI_H_ 1 #include <pthread.h> +#include <stdbool.h> extern pthread_mutex_t ui__lock; +void ui__refresh_dimensions(bool force); + #endif /* _PERF_UI_H_ */ diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c index fdf1fc8f08bc..45daa7c41dad 100644 --- a/tools/perf/util/ui/util.c +++ b/tools/perf/util/ui/util.c @@ -1,6 +1,5 @@ -#include <newt.h> +#include "../util.h" #include <signal.h> -#include <stdio.h> #include <stdbool.h> #include <string.h> #include <sys/ttydefaults.h> @@ -8,72 +7,75 @@ #include "../cache.h" #include "../debug.h" #include "browser.h" +#include "keysyms.h" #include "helpline.h" #include "ui.h" #include "util.h" +#include "libslang.h" -static void newt_form__set_exit_keys(newtComponent self) +static void ui_browser__argv_write(struct ui_browser *browser, + void *entry, int row) { - newtFormAddHotKey(self, NEWT_KEY_LEFT); - newtFormAddHotKey(self, NEWT_KEY_ESCAPE); - newtFormAddHotKey(self, 'Q'); - newtFormAddHotKey(self, 'q'); - newtFormAddHotKey(self, CTRL('c')); -} + char **arg = entry; + bool current_entry = ui_browser__is_current_entry(browser, row); -static newtComponent newt_form__new(void) -{ - newtComponent self = newtForm(NULL, NULL, 0); - if (self) - newt_form__set_exit_keys(self); - return self; + ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : + HE_COLORSET_NORMAL); + slsmg_write_nstring(*arg, browser->width); } -int ui__popup_menu(int argc, char * const argv[]) +static int popup_menu__run(struct ui_browser *menu) { - struct newtExitStruct es; - int i, rc = -1, max_len = 5; - newtComponent listbox, form = newt_form__new(); + int key; - if (form == NULL) + if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0) return -1; - listbox = newtListbox(0, 0, argc, NEWT_FLAG_RETURNEXIT); - if (listbox == NULL) - goto out_destroy_form; + while (1) { + key = ui_browser__run(menu, 0); - newtFormAddComponent(form, listbox); + switch (key) { + case K_RIGHT: + case K_ENTER: + key = menu->index; + break; + case K_LEFT: + case K_ESC: + case 'q': + case CTRL('c'): + key = -1; + break; + default: + continue; + } - for (i = 0; i < argc; ++i) { - int len = strlen(argv[i]); - if (len > max_len) - max_len = len; - if (newtListboxAddEntry(listbox, argv[i], (void *)(long)i)) - goto out_destroy_form; + break; } - newtCenteredWindow(max_len, argc, NULL); - newtFormRun(form, &es); - rc = newtListboxGetCurrent(listbox) - NULL; - if (es.reason == NEWT_EXIT_HOTKEY) - rc = -1; - newtPopWindow(); -out_destroy_form: - newtFormDestroy(form); - return rc; + ui_browser__hide(menu); + return key; } -int ui__help_window(const char *text) +int ui__popup_menu(int argc, char * const argv[]) { - struct newtExitStruct es; - newtComponent tb, form = newt_form__new(); - int rc = -1; + struct ui_browser menu = { + .entries = (void *)argv, + .refresh = ui_browser__argv_refresh, + .seek = ui_browser__argv_seek, + .write = ui_browser__argv_write, + .nr_entries = argc, + }; + + return popup_menu__run(&menu); +} + +int ui__question_window(const char *title, const char *text, + const char *exit_msg, int delay_secs) +{ + int x, y; int max_len = 0, nr_lines = 0; const char *t; - if (form == NULL) - return -1; - t = text; while (1) { const char *sep = strchr(t, '\n'); @@ -90,41 +92,77 @@ int ui__help_window(const char *text) t = sep + 1; } - tb = newtTextbox(0, 0, max_len, nr_lines, 0); - if (tb == NULL) - goto out_destroy_form; - - newtTextboxSetText(tb, text); - newtFormAddComponent(form, tb); - newtCenteredWindow(max_len, nr_lines, NULL); - newtFormRun(form, &es); - newtPopWindow(); - rc = 0; -out_destroy_form: - newtFormDestroy(form); - return rc; + max_len += 2; + nr_lines += 4; + y = SLtt_Screen_Rows / 2 - nr_lines / 2, + x = SLtt_Screen_Cols / 2 - max_len / 2; + + SLsmg_set_color(0); + SLsmg_draw_box(y, x++, nr_lines, max_len); + if (title) { + SLsmg_gotorc(y, x + 1); + SLsmg_write_string((char *)title); + } + SLsmg_gotorc(++y, x); + nr_lines -= 2; + max_len -= 2; + SLsmg_write_wrapped_string((unsigned char *)text, y, x, + nr_lines, max_len, 1); + SLsmg_gotorc(y + nr_lines - 2, x); + SLsmg_write_nstring((char *)" ", max_len); + SLsmg_gotorc(y + nr_lines - 1, x); + SLsmg_write_nstring((char *)exit_msg, max_len); + SLsmg_refresh(); + return ui__getch(delay_secs); } -static const char yes[] = "Yes", no[] = "No", - warning_str[] = "Warning!", ok[] = "Ok"; +int ui__help_window(const char *text) +{ + return ui__question_window("Help", text, "Press any key...", 0); +} -bool ui__dialog_yesno(const char *msg) +int ui__dialog_yesno(const char *msg) { - /* newtWinChoice should really be accepting const char pointers... */ - return newtWinChoice(NULL, (char *)yes, (char *)no, (char *)msg) == 1; + return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0); } -void ui__warning(const char *format, ...) +int __ui__warning(const char *title, const char *format, va_list args) { - va_list args; + char *s; + + if (use_browser > 0 && vasprintf(&s, format, args) > 0) { + int key; - va_start(args, format); - if (use_browser > 0) { pthread_mutex_lock(&ui__lock); - newtWinMessagev((char *)warning_str, (char *)ok, - (char *)format, args); + key = ui__question_window(title, s, "Press any key...", 0); pthread_mutex_unlock(&ui__lock); - } else - vfprintf(stderr, format, args); + free(s); + return key; + } + + fprintf(stderr, "%s:\n", title); + vfprintf(stderr, format, args); + return K_ESC; +} + +int ui__warning(const char *format, ...) +{ + int key; + va_list args; + + va_start(args, format); + key = __ui__warning("Warning", format, args); + va_end(args); + return key; +} + +int ui__error(const char *format, ...) +{ + int key; + va_list args; + + va_start(args, format); + key = __ui__warning("Error", format, args); va_end(args); + return key; } diff --git a/tools/perf/util/ui/util.h b/tools/perf/util/ui/util.h index afcbc1d99531..2d1738bd71c8 100644 --- a/tools/perf/util/ui/util.h +++ b/tools/perf/util/ui/util.h @@ -1,10 +1,14 @@ #ifndef _PERF_UI_UTIL_H_ #define _PERF_UI_UTIL_H_ 1 -#include <stdbool.h> +#include <stdarg.h> +int ui__getch(int delay_secs); int ui__popup_menu(int argc, char * const argv[]); int ui__help_window(const char *text); -bool ui__dialog_yesno(const char *msg); +int ui__dialog_yesno(const char *msg); +int ui__question_window(const char *title, const char *text, + const char *exit_msg, int delay_secs); +int __ui__warning(const char *title, const char *format, va_list args); #endif /* _PERF_UI_UTIL_H_ */ diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index e16bf9a707e8..d76d1c0ff98f 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -1,5 +1,8 @@ /* - * GIT - The information manager from hell + * usage.c + * + * Various reporting routines. + * Originally copied from GIT source. * * Copyright (C) Linus Torvalds, 2005 */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 5b3ea49aa63e..813141047fc2 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,6 +1,21 @@ +#include "../perf.h" #include "util.h" #include <sys/mman.h> +/* + * XXX We need to find a better place for these things... + */ +bool perf_host = true; +bool perf_guest = true; + +void event_attr_init(struct perf_event_attr *attr) +{ + if (!perf_host) + attr->exclude_host = 1; + if (!perf_guest) + attr->exclude_guest = 1; +} + int mkdir_p(char *path, mode_t mode) { struct stat st; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 0128906bac88..b9c530cce79a 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -242,7 +242,22 @@ int strtailcmp(const char *s1, const char *s2); unsigned long convert_unit(unsigned long value, char *unit); int readn(int fd, void *buf, size_t size); +struct perf_event_attr; + +void event_attr_init(struct perf_event_attr *attr); + #define _STR(x) #x #define STR(x) _STR(x) +/* + * Determine whether some value is a power of two, where zero is + * *not* considered a power of two. + */ + +static inline __attribute__((const)) +bool is_power_of_2(unsigned long n) +{ + return (n != 0 && ((n & (n - 1)) == 0)); +} + #endif diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index bdd33470b235..697c8b4e59cc 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -32,6 +32,7 @@ void perf_read_values_destroy(struct perf_read_values *values) for (i = 0; i < values->threads; i++) free(values->value[i]); + free(values->value); free(values->pid); free(values->tid); free(values->counterrawid); |