diff options
Diffstat (limited to 'tools/perf/util')
93 files changed, 6373 insertions, 2080 deletions
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN index 15a77b7c0e36..39f17507578d 100755 --- a/tools/perf/util/PERF-VERSION-GEN +++ b/tools/perf/util/PERF-VERSION-GEN @@ -19,6 +19,9 @@ if test -d ../../.git -o -f ../../.git then TAG=$(git describe --abbrev=0 --match "v[0-9].[0-9]*" 2>/dev/null ) CID=$(git log -1 --abbrev=4 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID" +elif test -f ../../PERF-VERSION-FILE +then + TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g') fi if test -z "$TAG" then @@ -40,7 +43,7 @@ else VC=unset fi test "$VN" = "$VC" || { - echo >&2 "PERF_VERSION = $VN" + echo >&2 " PERF_VERSION = $VN" echo "#define PERF_VERSION \"$VN\"" >$GVF } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index d102716c43a1..cf6242c92ee2 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -110,10 +110,10 @@ static int jump__parse(struct ins_operands *ops) { const char *s = strchr(ops->raw, '+'); - ops->target.addr = strtoll(ops->raw, NULL, 16); + ops->target.addr = strtoull(ops->raw, NULL, 16); if (s++ != NULL) - ops->target.offset = strtoll(s, NULL, 16); + ops->target.offset = strtoull(s, NULL, 16); else ops->target.offset = UINT64_MAX; @@ -809,7 +809,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, end = map__rip_2objdump(map, sym->end); offset = line_ip - start; - if (offset < 0 || (u64)line_ip > end) + if ((u64)line_ip < start || (u64)line_ip > end) offset = -1; else parsed_line = tmp2 + 1; @@ -821,11 +821,51 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, if (dl == NULL) return -1; + if (dl->ops.target.offset == UINT64_MAX) + dl->ops.target.offset = dl->ops.target.addr - + map__rip_2objdump(map, sym->start); + + /* kcore has no symbols, so add the call target name */ + if (dl->ins && ins__is_call(dl->ins) && !dl->ops.target.name) { + struct addr_map_symbol target = { + .map = map, + .addr = dl->ops.target.addr, + }; + + if (!map_groups__find_ams(&target, NULL) && + target.sym->start == target.al_addr) + dl->ops.target.name = strdup(target.sym->name); + } + disasm__add(¬es->src->source, dl); return 0; } +static void delete_last_nop(struct symbol *sym) +{ + struct annotation *notes = symbol__annotation(sym); + struct list_head *list = ¬es->src->source; + struct disasm_line *dl; + + while (!list_empty(list)) { + dl = list_entry(list->prev, struct disasm_line, node); + + if (dl->ins && dl->ins->ops) { + if (dl->ins->ops != &nop_ops) + return; + } else { + if (!strstr(dl->line, " nop ") && + !strstr(dl->line, " nopl ") && + !strstr(dl->line, " nopw ")) + return; + } + + list_del(&dl->node); + disasm_line__free(dl); + } +} + int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) { struct dso *dso = map->dso; @@ -835,6 +875,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) FILE *file; int err = 0; char symfs_filename[PATH_MAX]; + struct kcore_extract kce; + bool delete_extract = false; if (filename) { snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", @@ -864,7 +906,8 @@ fallback: free_filename = false; } - if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) { + if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && + !dso__is_kcore(dso)) { char bf[BUILD_ID_SIZE * 2 + 16] = " with build id "; char *build_id_msg = NULL; @@ -895,10 +938,27 @@ fallback: pr_debug("annotating [%p] %30s : [%p] %30s\n", dso, dso->long_name, sym, sym->name); + if (dso__is_kcore(dso)) { + kce.kcore_filename = symfs_filename; + kce.addr = map__rip_2objdump(map, sym->start); + kce.offs = sym->start; + kce.len = sym->end + 1 - sym->start; + if (!kcore_extract__create(&kce)) { + delete_extract = true; + strlcpy(symfs_filename, kce.extract_filename, + sizeof(symfs_filename)); + if (free_filename) { + free(filename); + free_filename = false; + } + filename = symfs_filename; + } + } + snprintf(command, sizeof(command), "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -d %s %s -C %s|grep -v %s|expand", + " -d %s %s -C %s 2>/dev/null|grep -v %s|expand", objdump_path ? objdump_path : "objdump", disassembler_style ? "-M " : "", disassembler_style ? disassembler_style : "", @@ -918,8 +978,17 @@ fallback: if (symbol__parse_objdump_line(sym, map, file, privsize) < 0) break; + /* + * kallsyms does not have symbol sizes so there may a nop at the end. + * Remove it. + */ + if (dso__is_kcore(dso)) + delete_last_nop(sym); + pclose(file); out_free_filename: + if (delete_extract) + kcore_extract__delete(&kce); if (free_filename) free(filename); return err; @@ -1018,7 +1087,7 @@ static void symbol__free_source_line(struct symbol *sym, int len) (sizeof(src_line->p) * (src_line->nr_pcnt - 1)); for (i = 0; i < len; i++) { - free(src_line->path); + free_srcline(src_line->path); src_line = (void *)src_line + sizeof_src_line; } @@ -1029,13 +1098,11 @@ static void symbol__free_source_line(struct symbol *sym, int len) /* Get the filename:line for the colored entries */ static int symbol__get_source_line(struct symbol *sym, struct map *map, struct perf_evsel *evsel, - struct rb_root *root, int len, - const char *filename) + struct rb_root *root, int len) { u64 start; int i, k; int evidx = evsel->idx; - char cmd[PATH_MAX * 2]; struct source_line *src_line; struct annotation *notes = symbol__annotation(sym); struct sym_hist *h = annotation__histogram(notes, evidx); @@ -1063,10 +1130,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, start = map__rip_2objdump(map, sym->start); for (i = 0; i < len; i++) { - char *path = NULL; - size_t line_len; u64 offset; - FILE *fp; double percent_max = 0.0; src_line->nr_pcnt = nr_pcnt; @@ -1083,23 +1147,9 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, goto next; offset = start + i; - sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset); - fp = popen(cmd, "r"); - if (!fp) - goto next; - - if (getline(&path, &line_len, fp) < 0 || !line_len) - goto next_close; - - src_line->path = malloc(sizeof(char) * line_len + 1); - if (!src_line->path) - goto next_close; - - strcpy(src_line->path, path); + src_line->path = get_srcline(map->dso, offset); insert_source_line(&tmp_root, src_line); - next_close: - pclose(fp); next: src_line = (void *)src_line + sizeof_src_line; } @@ -1140,7 +1190,7 @@ static void print_summary(struct rb_root *root, const char *filename) path = src_line->path; color = get_percent_color(percent_max); - color_fprintf(stdout, color, " %s", path); + color_fprintf(stdout, color, " %s\n", path); node = rb_next(node); } @@ -1304,7 +1354,6 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, bool full_paths, int min_pcnt, int max_lines) { struct dso *dso = map->dso; - const char *filename = dso->long_name; struct rb_root source_line = RB_ROOT; u64 len; @@ -1314,9 +1363,8 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, len = symbol__size(sym); if (print_lines) { - symbol__get_source_line(sym, map, evsel, &source_line, - len, filename); - print_summary(&source_line, filename); + symbol__get_source_line(sym, map, evsel, &source_line, len); + print_summary(&source_line, dso->long_name); } symbol__annotate_printf(sym, map, evsel, full_paths, diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index af755156d278..834b7b57b788 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -150,7 +150,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, bool print_lines, bool full_paths, int min_pcnt, int max_lines); -#ifdef SLANG_SUPPORT +#ifdef HAVE_SLANG_SUPPORT int symbol__tui_annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, struct hist_browser_timer *hbt); @@ -165,30 +165,6 @@ static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, } #endif -#ifdef GTK2_SUPPORT -int symbol__gtk_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, - struct hist_browser_timer *hbt); - -static inline int hist_entry__gtk_annotate(struct hist_entry *he, - struct perf_evsel *evsel, - struct hist_browser_timer *hbt) -{ - return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt); -} - -void perf_gtk__show_annotations(void); -#else -static inline int hist_entry__gtk_annotate(struct hist_entry *he __maybe_unused, - struct perf_evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused) -{ - return 0; -} - -static inline void perf_gtk__show_annotations(void) {} -#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 5295625c0c00..a92770c98cc7 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -18,13 +18,14 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct perf_evsel *evsel __maybe_unused, struct machine *machine) { struct addr_location al; u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = machine__findnew_thread(machine, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->pid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", @@ -33,7 +34,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, } thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - event->ip.ip, &al); + sample->ip, &al); if (al.map != NULL) al.map->dso->hit = 1; @@ -47,7 +48,9 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, __maybe_unused, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, event->fork.tid); + struct thread *thread = machine__findnew_thread(machine, + event->fork.pid, + event->fork.tid); dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid, event->fork.ppid, event->fork.ptid); @@ -64,6 +67,7 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, struct perf_tool build_id__mark_dso_hit_ops = { .sample = build_id__mark_dso_hit, .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, .fork = perf_event__process_fork, .exit = perf_event__exit_del_thread, .attr = perf_event__process_attr, @@ -85,14 +89,14 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf) return raw - build_id; } -char *dso__build_id_filename(struct dso *self, char *bf, size_t size) +char *dso__build_id_filename(struct dso *dso, char *bf, size_t size) { char build_id_hex[BUILD_ID_SIZE * 2 + 1]; - if (!self->has_build_id) + if (!dso->has_build_id) return NULL; - build_id__sprintf(self->build_id, sizeof(self->build_id), build_id_hex); + build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex); if (bf == NULL) { if (asprintf(&bf, "%s/.build-id/%.2s/%s", buildid_dir, build_id_hex, build_id_hex + 2) < 0) diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index a811f5c62e18..929f28a7c14d 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -10,10 +10,9 @@ extern struct perf_tool build_id__mark_dso_hit_ops; struct dso; int build_id__sprintf(const u8 *build_id, int len, char *bf); -char *dso__build_id_filename(struct dso *self, char *bf, size_t size); +char *dso__build_id_filename(struct dso *dso, char *bf, size_t size); int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine); - #endif diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 26e367239873..7b176dd02e1a 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -70,8 +70,7 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2 extern char *perf_pathdup(const char *fmt, ...) __attribute__((format (printf, 1, 2))); -#ifndef HAVE_STRLCPY +/* Matches the libc/libbsd function attribute so we declare this unconditionally: */ extern size_t strlcpy(char *dest, const char *src, size_t size); -#endif #endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 42b6a632fe7b..e3970e3eaacf 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -15,25 +15,12 @@ #include <errno.h> #include <math.h> +#include "hist.h" #include "util.h" #include "callchain.h" __thread struct callchain_cursor callchain_cursor; -bool ip_callchain__valid(struct ip_callchain *chain, - const union perf_event *event) -{ - unsigned int chain_size = event->header.size; - chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event; - return chain->nr * sizeof(u64) <= chain_size; -} - -#define chain_for_each_child(child, parent) \ - list_for_each_entry(child, &parent->children, siblings) - -#define chain_for_each_child_safe(child, next, parent) \ - list_for_each_entry_safe(child, next, &parent->children, siblings) - static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, enum chain_mode mode) @@ -78,10 +65,16 @@ static void __sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node, u64 min_hit) { + struct rb_node *n; struct callchain_node *child; - chain_for_each_child(child, node) + n = rb_first(&node->rb_root_in); + while (n) { + child = rb_entry(n, struct callchain_node, rb_node_in); + n = rb_next(n); + __sort_chain_flat(rb_root, child, min_hit); + } if (node->hit && node->hit >= min_hit) rb_insert_callchain(rb_root, node, CHAIN_FLAT); @@ -101,11 +94,16 @@ sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root, static void __sort_chain_graph_abs(struct callchain_node *node, u64 min_hit) { + struct rb_node *n; struct callchain_node *child; node->rb_root = RB_ROOT; + n = rb_first(&node->rb_root_in); + + while (n) { + child = rb_entry(n, struct callchain_node, rb_node_in); + n = rb_next(n); - chain_for_each_child(child, node) { __sort_chain_graph_abs(child, min_hit); if (callchain_cumul_hits(child) >= min_hit) rb_insert_callchain(&node->rb_root, child, @@ -124,13 +122,18 @@ sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_root *chain_root, static void __sort_chain_graph_rel(struct callchain_node *node, double min_percent) { + struct rb_node *n; struct callchain_node *child; u64 min_hit; node->rb_root = RB_ROOT; min_hit = ceil(node->children_hit * min_percent); - chain_for_each_child(child, node) { + n = rb_first(&node->rb_root_in); + while (n) { + child = rb_entry(n, struct callchain_node, rb_node_in); + n = rb_next(n); + __sort_chain_graph_rel(child, min_percent); if (callchain_cumul_hits(child) >= min_hit) rb_insert_callchain(&node->rb_root, child, @@ -180,19 +183,26 @@ create_child(struct callchain_node *parent, bool inherit_children) return NULL; } new->parent = parent; - INIT_LIST_HEAD(&new->children); INIT_LIST_HEAD(&new->val); if (inherit_children) { - struct callchain_node *next; + struct rb_node *n; + struct callchain_node *child; + + new->rb_root_in = parent->rb_root_in; + parent->rb_root_in = RB_ROOT; - list_splice(&parent->children, &new->children); - INIT_LIST_HEAD(&parent->children); + n = rb_first(&new->rb_root_in); + while (n) { + child = rb_entry(n, struct callchain_node, rb_node_in); + child->parent = new; + n = rb_next(n); + } - chain_for_each_child(next, new) - next->parent = new; + /* make it the first child */ + rb_link_node(&new->rb_node_in, NULL, &parent->rb_root_in.rb_node); + rb_insert_color(&new->rb_node_in, &parent->rb_root_in); } - list_add_tail(&new->siblings, &parent->children); return new; } @@ -230,7 +240,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) } } -static void +static struct callchain_node * add_child(struct callchain_node *parent, struct callchain_cursor *cursor, u64 period) @@ -242,6 +252,19 @@ add_child(struct callchain_node *parent, new->children_hit = 0; new->hit = period; + return new; +} + +static s64 match_chain(struct callchain_cursor_node *node, + struct callchain_list *cnode) +{ + struct symbol *sym = node->sym; + + if (cnode->ms.sym && sym && + callchain_param.key == CCKEY_FUNCTION) + return cnode->ms.sym->start - sym->start; + else + return cnode->ip - node->ip; } /* @@ -279,9 +302,33 @@ split_add_child(struct callchain_node *parent, /* create a new child for the new branch if any */ if (idx_total < cursor->nr) { + struct callchain_node *first; + struct callchain_list *cnode; + struct callchain_cursor_node *node; + struct rb_node *p, **pp; + parent->hit = 0; - add_child(parent, cursor, period); parent->children_hit += period; + + node = callchain_cursor_current(cursor); + new = add_child(parent, cursor, period); + + /* + * This is second child since we moved parent's children + * to new (first) child above. + */ + p = parent->rb_root_in.rb_node; + first = rb_entry(p, struct callchain_node, rb_node_in); + cnode = list_first_entry(&first->val, struct callchain_list, + list); + + if (match_chain(node, cnode) < 0) + pp = &p->rb_left; + else + pp = &p->rb_right; + + rb_link_node(&new->rb_node_in, p, pp); + rb_insert_color(&new->rb_node_in, &parent->rb_root_in); } else { parent->hit = period; } @@ -298,16 +345,40 @@ append_chain_children(struct callchain_node *root, u64 period) { struct callchain_node *rnode; + struct callchain_cursor_node *node; + struct rb_node **p = &root->rb_root_in.rb_node; + struct rb_node *parent = NULL; + + node = callchain_cursor_current(cursor); + if (!node) + return; /* lookup in childrens */ - chain_for_each_child(rnode, root) { - unsigned int ret = append_chain(rnode, cursor, period); + while (*p) { + s64 ret; + struct callchain_list *cnode; - if (!ret) + parent = *p; + rnode = rb_entry(parent, struct callchain_node, rb_node_in); + cnode = list_first_entry(&rnode->val, struct callchain_list, + list); + + /* just check first entry */ + ret = match_chain(node, cnode); + if (ret == 0) { + append_chain(rnode, cursor, period); goto inc_children_hit; + } + + if (ret < 0) + p = &parent->rb_left; + else + p = &parent->rb_right; } /* nothing in children, add to the current node */ - add_child(root, cursor, period); + rnode = add_child(root, cursor, period); + rb_link_node(&rnode->rb_node_in, parent, p); + rb_insert_color(&rnode->rb_node_in, &root->rb_root_in); inc_children_hit: root->children_hit += period; @@ -327,31 +398,25 @@ append_chain(struct callchain_node *root, /* * Lookup in the current node * If we have a symbol, then compare the start to match - * anywhere inside a function. + * anywhere inside a function, unless function + * mode is disabled. */ list_for_each_entry(cnode, &root->val, list) { struct callchain_cursor_node *node; - struct symbol *sym; node = callchain_cursor_current(cursor); if (!node) break; - sym = node->sym; - - if (cnode->ms.sym && sym) { - if (cnode->ms.sym->start != sym->start) - break; - } else if (cnode->ip != node->ip) + if (match_chain(node, cnode) != 0) break; - if (!found) - found = true; + found = true; callchain_cursor_advance(cursor); } - /* matches not, relay on the parent */ + /* matches not, relay no the parent */ if (!found) { cursor->curr = curr_snap; cursor->pos = start; @@ -400,8 +465,9 @@ merge_chain_branch(struct callchain_cursor *cursor, struct callchain_node *dst, struct callchain_node *src) { struct callchain_cursor_node **old_last = cursor->last; - struct callchain_node *child, *next_child; + struct callchain_node *child; struct callchain_list *list, *next_list; + struct rb_node *n; int old_pos = cursor->nr; int err = 0; @@ -417,12 +483,16 @@ merge_chain_branch(struct callchain_cursor *cursor, append_chain_children(dst, cursor, src->hit); } - chain_for_each_child_safe(child, next_child, src) { + n = rb_first(&src->rb_root_in); + while (n) { + child = container_of(n, struct callchain_node, rb_node_in); + n = rb_next(n); + rb_erase(&child->rb_node_in, &src->rb_root_in); + err = merge_chain_branch(cursor, dst, child); if (err) break; - list_del(&child->siblings); free(child); } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 3ee9f67d5af0..4f7f989876ec 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -21,11 +21,11 @@ enum chain_order { struct callchain_node { struct callchain_node *parent; - struct list_head siblings; - struct list_head children; struct list_head val; - struct rb_node rb_node; /* to sort nodes in an rbtree */ - struct rb_root rb_root; /* sorted tree of children */ + struct rb_node rb_node_in; /* to insert nodes in an rbtree */ + struct rb_node rb_node; /* to sort nodes in an output tree */ + struct rb_root rb_root_in; /* input tree of children */ + struct rb_root rb_root; /* sorted output tree of children */ unsigned int val_nr; u64 hit; u64 children_hit; @@ -41,12 +41,18 @@ struct callchain_param; typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *, u64, struct callchain_param *); +enum chain_key { + CCKEY_FUNCTION, + CCKEY_ADDRESS +}; + struct callchain_param { enum chain_mode mode; u32 print_limit; double min_percent; sort_chain_func_t sort; enum chain_order order; + enum chain_key key; }; struct callchain_list { @@ -80,13 +86,12 @@ extern __thread struct callchain_cursor callchain_cursor; static inline void callchain_init(struct callchain_root *root) { - INIT_LIST_HEAD(&root->node.siblings); - INIT_LIST_HEAD(&root->node.children); INIT_LIST_HEAD(&root->node.val); root->node.parent = NULL; root->node.hit = 0; root->node.children_hit = 0; + root->node.rb_root_in = RB_ROOT; root->max_depth = 0; } @@ -103,11 +108,6 @@ 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); /* * Initialize a cursor before adding entries inside, but keep * the previously allocated entries as a cache. @@ -146,6 +146,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) struct option; +int record_parse_callchain(const char *arg, struct perf_record_opts *opts); int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); +int record_callchain_opt(const struct option *opt, const char *arg, int unset); + extern const char record_callchain_help[]; #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 11e46da17bbb..66e44a5019d5 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -318,8 +318,15 @@ int percent_color_fprintf(FILE *fp, const char *fmt, double percent) return r; } -int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent) +int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...) { - const char *color = get_percent_color(percent); + va_list args; + double percent; + const char *color; + + va_start(args, fmt); + percent = va_arg(args, double); + va_end(args); + color = get_percent_color(percent); return color_snprintf(bf, size, color, fmt, percent); } diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index dea082b79602..fced3840e99c 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -39,7 +39,7 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...); int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...); int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...); int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf); -int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent); +int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...); int percent_color_fprintf(FILE *fp, const char *fmt, double percent); const char *get_percent_color(double percent); diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c new file mode 100644 index 000000000000..ee0df0e24cdb --- /dev/null +++ b/tools/perf/util/comm.c @@ -0,0 +1,121 @@ +#include "comm.h" +#include "util.h" +#include <stdlib.h> +#include <stdio.h> + +struct comm_str { + char *str; + struct rb_node rb_node; + int ref; +}; + +/* Should perhaps be moved to struct machine */ +static struct rb_root comm_str_root; + +static void comm_str__get(struct comm_str *cs) +{ + cs->ref++; +} + +static void comm_str__put(struct comm_str *cs) +{ + if (!--cs->ref) { + rb_erase(&cs->rb_node, &comm_str_root); + free(cs->str); + free(cs); + } +} + +static struct comm_str *comm_str__alloc(const char *str) +{ + struct comm_str *cs; + + cs = zalloc(sizeof(*cs)); + if (!cs) + return NULL; + + cs->str = strdup(str); + if (!cs->str) { + free(cs); + return NULL; + } + + return cs; +} + +static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct comm_str *iter, *new; + int cmp; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct comm_str, rb_node); + + cmp = strcmp(str, iter->str); + if (!cmp) + return iter; + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + new = comm_str__alloc(str); + if (!new) + return NULL; + + rb_link_node(&new->rb_node, parent, p); + rb_insert_color(&new->rb_node, root); + + return new; +} + +struct comm *comm__new(const char *str, u64 timestamp) +{ + struct comm *comm = zalloc(sizeof(*comm)); + + if (!comm) + return NULL; + + comm->start = timestamp; + + comm->comm_str = comm_str__findnew(str, &comm_str_root); + if (!comm->comm_str) { + free(comm); + return NULL; + } + + comm_str__get(comm->comm_str); + + return comm; +} + +void comm__override(struct comm *comm, const char *str, u64 timestamp) +{ + struct comm_str *old = comm->comm_str; + + comm->comm_str = comm_str__findnew(str, &comm_str_root); + if (!comm->comm_str) { + comm->comm_str = old; + return; + } + + comm->start = timestamp; + comm_str__get(comm->comm_str); + comm_str__put(old); +} + +void comm__free(struct comm *comm) +{ + comm_str__put(comm->comm_str); + free(comm); +} + +const char *comm__str(const struct comm *comm) +{ + return comm->comm_str->str; +} diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h new file mode 100644 index 000000000000..7a86e5656710 --- /dev/null +++ b/tools/perf/util/comm.h @@ -0,0 +1,21 @@ +#ifndef __PERF_COMM_H +#define __PERF_COMM_H + +#include "../perf.h" +#include <linux/rbtree.h> +#include <linux/list.h> + +struct comm_str; + +struct comm { + struct comm_str *comm_str; + u64 start; + struct list_head list; +}; + +void comm__free(struct comm *comm); +struct comm *comm__new(const char *str, u64 timestamp); +const char *comm__str(const struct comm *comm); +void comm__override(struct comm *comm, const char *str, u64 timestamp); + +#endif /* __PERF_COMM_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index beb8cf9f9976..a9b48c42e81e 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -1,5 +1,5 @@ #include "util.h" -#include "sysfs.h" +#include "fs.h" #include "../perf.h" #include "cpumap.h" #include <assert.h> @@ -216,7 +216,7 @@ int cpu_map__get_socket(struct cpu_map *map, int idx) cpu = map->map[idx]; - mnt = sysfs_find_mountpoint(); + mnt = sysfs__mountpoint(); if (!mnt) return -1; @@ -279,7 +279,7 @@ int cpu_map__get_core(struct cpu_map *map, int idx) cpu = map->map[idx]; - mnt = sysfs_find_mountpoint(); + mnt = sysfs__mountpoint(); if (!mnt) return -1; diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 9bed02e5fb3d..b123bb9d6f55 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -41,7 +41,7 @@ static inline int cpu_map__nr(const struct cpu_map *map) return map ? map->nr : 1; } -static inline bool cpu_map__all(const struct cpu_map *map) +static inline bool cpu_map__empty(const struct cpu_map *map) { return map ? map->map[0] == -1 : true; } diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c new file mode 100644 index 000000000000..7d09faf85cf1 --- /dev/null +++ b/tools/perf/util/data.c @@ -0,0 +1,120 @@ +#include <linux/compiler.h> +#include <linux/kernel.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <string.h> + +#include "data.h" +#include "util.h" + +static bool check_pipe(struct perf_data_file *file) +{ + struct stat st; + bool is_pipe = false; + int fd = perf_data_file__is_read(file) ? + STDIN_FILENO : STDOUT_FILENO; + + if (!file->path) { + if (!fstat(fd, &st) && S_ISFIFO(st.st_mode)) + is_pipe = true; + } else { + if (!strcmp(file->path, "-")) + is_pipe = true; + } + + if (is_pipe) + file->fd = fd; + + return file->is_pipe = is_pipe; +} + +static int check_backup(struct perf_data_file *file) +{ + struct stat st; + + if (!stat(file->path, &st) && st.st_size) { + /* TODO check errors properly */ + char oldname[PATH_MAX]; + snprintf(oldname, sizeof(oldname), "%s.old", + file->path); + unlink(oldname); + rename(file->path, oldname); + } + + return 0; +} + +static int open_file_read(struct perf_data_file *file) +{ + struct stat st; + int fd; + + fd = open(file->path, O_RDONLY); + if (fd < 0) { + int err = errno; + + pr_err("failed to open %s: %s", file->path, strerror(err)); + if (err == ENOENT && !strcmp(file->path, "perf.data")) + pr_err(" (try 'perf record' first)"); + pr_err("\n"); + return -err; + } + + if (fstat(fd, &st) < 0) + goto out_close; + + if (!file->force && st.st_uid && (st.st_uid != geteuid())) { + pr_err("file %s not owned by current user or root\n", + file->path); + goto out_close; + } + + if (!st.st_size) { + pr_info("zero-sized file (%s), nothing to do!\n", + file->path); + goto out_close; + } + + file->size = st.st_size; + return fd; + + out_close: + close(fd); + return -1; +} + +static int open_file_write(struct perf_data_file *file) +{ + if (check_backup(file)) + return -1; + + return open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); +} + +static int open_file(struct perf_data_file *file) +{ + int fd; + + fd = perf_data_file__is_read(file) ? + open_file_read(file) : open_file_write(file); + + file->fd = fd; + return fd < 0 ? -1 : 0; +} + +int perf_data_file__open(struct perf_data_file *file) +{ + if (check_pipe(file)) + return 0; + + if (!file->path) + file->path = "perf.data"; + + return open_file(file); +} + +void perf_data_file__close(struct perf_data_file *file) +{ + close(file->fd); +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h new file mode 100644 index 000000000000..8c2df80152a5 --- /dev/null +++ b/tools/perf/util/data.h @@ -0,0 +1,48 @@ +#ifndef __PERF_DATA_H +#define __PERF_DATA_H + +#include <stdbool.h> + +enum perf_data_mode { + PERF_DATA_MODE_WRITE, + PERF_DATA_MODE_READ, +}; + +struct perf_data_file { + const char *path; + int fd; + bool is_pipe; + bool force; + unsigned long size; + enum perf_data_mode mode; +}; + +static inline bool perf_data_file__is_read(struct perf_data_file *file) +{ + return file->mode == PERF_DATA_MODE_READ; +} + +static inline bool perf_data_file__is_write(struct perf_data_file *file) +{ + return file->mode == PERF_DATA_MODE_WRITE; +} + +static inline int perf_data_file__is_pipe(struct perf_data_file *file) +{ + return file->is_pipe; +} + +static inline int perf_data_file__fd(struct perf_data_file *file) +{ + return file->fd; +} + +static inline unsigned long perf_data_file__size(struct perf_data_file *file) +{ + return file->size; +} + +int perf_data_file__open(struct perf_data_file *file); +void perf_data_file__close(struct perf_data_file *file); + +#endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index c4374f07603c..af4c687cc49b 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -7,19 +7,20 @@ char dso__symtab_origin(const struct dso *dso) { static const char origin[] = { - [DSO_BINARY_TYPE__KALLSYMS] = 'k', - [DSO_BINARY_TYPE__VMLINUX] = 'v', - [DSO_BINARY_TYPE__JAVA_JIT] = 'j', - [DSO_BINARY_TYPE__DEBUGLINK] = 'l', - [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B', - [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f', - [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u', - [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b', - [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd', - [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K', - [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g', - [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', - [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', + [DSO_BINARY_TYPE__KALLSYMS] = 'k', + [DSO_BINARY_TYPE__VMLINUX] = 'v', + [DSO_BINARY_TYPE__JAVA_JIT] = 'j', + [DSO_BINARY_TYPE__DEBUGLINK] = 'l', + [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B', + [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f', + [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u', + [DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO] = 'o', + [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b', + [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd', + [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K', + [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g', + [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', + [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', }; if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND) @@ -64,6 +65,28 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, symbol_conf.symfs, dso->long_name); break; + case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + { + char *last_slash; + size_t len; + size_t dir_size; + + last_slash = dso->long_name + dso->long_name_len; + while (last_slash != dso->long_name && *last_slash != '/') + last_slash--; + + len = scnprintf(file, size, "%s", symbol_conf.symfs); + dir_size = last_slash - dso->long_name + 2; + if (dir_size > (size - len)) { + ret = -1; + break; + } + len += scnprintf(file + len, dir_size, "%s", dso->long_name); + len += scnprintf(file + len , size - len, ".debug%s", + last_slash); + break; + } + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: if (!dso->has_build_id) { ret = -1; @@ -78,6 +101,8 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, symbol_conf.symfs, build_id_hex, build_id_hex + 2); break; + case DSO_BINARY_TYPE__VMLINUX: + case DSO_BINARY_TYPE__GUEST_VMLINUX: case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: snprintf(file, size, "%s%s", symbol_conf.symfs, dso->long_name); @@ -93,11 +118,14 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, dso->long_name); break; + case DSO_BINARY_TYPE__KCORE: + case DSO_BINARY_TYPE__GUEST_KCORE: + snprintf(file, size, "%s", dso->long_name); + break; + default: case DSO_BINARY_TYPE__KALLSYMS: - case DSO_BINARY_TYPE__VMLINUX: case DSO_BINARY_TYPE__GUEST_KALLSYMS: - case DSO_BINARY_TYPE__GUEST_VMLINUX: case DSO_BINARY_TYPE__JAVA_JIT: case DSO_BINARY_TYPE__NOT_FOUND: ret = -1; @@ -419,8 +447,10 @@ struct dso *dso__new(const char *name) dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; dso->data_type = DSO_BINARY_TYPE__NOT_FOUND; dso->loaded = 0; + dso->rel = 0; dso->sorted_by_name = 0; dso->has_build_id = 0; + dso->has_srcline = 1; dso->kernel = DSO_TYPE_USER; dso->needs_swap = DSO_SWAP__UNSET; INIT_LIST_HEAD(&dso->node); diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index d51aaf272c68..9ac666abbe7e 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -3,8 +3,10 @@ #include <linux/types.h> #include <linux/rbtree.h> +#include <stdbool.h> #include "types.h" #include "map.h" +#include "build-id.h" enum dso_binary_type { DSO_BINARY_TYPE__KALLSYMS = 0, @@ -20,6 +22,9 @@ enum dso_binary_type { DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__KCORE, + DSO_BINARY_TYPE__GUEST_KCORE, + DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, DSO_BINARY_TYPE__NOT_FOUND, }; @@ -78,12 +83,14 @@ struct dso { enum dso_binary_type data_type; u8 adjust_symbols:1; u8 has_build_id:1; + u8 has_srcline:1; u8 hit:1; u8 annotate_warned:1; u8 sname_alloc:1; u8 lname_alloc:1; u8 sorted_by_name; u8 loaded; + u8 rel; u8 build_id[BUILD_ID_SIZE]; const char *short_name; char *long_name; @@ -146,4 +153,17 @@ size_t dso__fprintf_buildid(struct dso *dso, FILE *fp); size_t dso__fprintf_symbols_by_name(struct dso *dso, enum map_type type, FILE *fp); size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp); + +static inline bool dso__is_vmlinux(struct dso *dso) +{ + return dso->data_type == DSO_BINARY_TYPE__VMLINUX || + dso->data_type == DSO_BINARY_TYPE__GUEST_VMLINUX; +} + +static inline bool dso__is_kcore(struct dso *dso) +{ + return dso->data_type == DSO_BINARY_TYPE__KCORE || + dso->data_type == DSO_BINARY_TYPE__GUEST_KCORE; +} + #endif /* __PERF_DSO */ diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 3e5f5430a28a..7defd77105d0 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -263,6 +263,21 @@ bool die_is_signed_type(Dwarf_Die *tp_die) } /** + * die_is_func_def - Ensure that this DIE is a subprogram and definition + * @dw_die: a DIE + * + * Ensure that this DIE is a subprogram and NOT a declaration. This + * returns true if @dw_die is a function definition. + **/ +bool die_is_func_def(Dwarf_Die *dw_die) +{ + Dwarf_Attribute attr; + + return (dwarf_tag(dw_die) == DW_TAG_subprogram && + dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL); +} + +/** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure * @offs: The offset of the member in the data structure @@ -392,6 +407,10 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) { struct __addr_die_search_param *ad = data; + /* + * Since a declaration entry doesn't has given pc, this always returns + * function definition entry. + */ if (dwarf_tag(fn_die) == DW_TAG_subprogram && dwarf_haspc(fn_die, ad->addr)) { memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die)); @@ -407,7 +426,7 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) * @die_mem: a buffer for result DIE * * Search a non-inlined function DIE which includes @addr. Stores the - * DIE to @die_mem and returns it if found. Returns NULl if failed. + * DIE to @die_mem and returns it if found. Returns NULL if failed. */ Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr, Dwarf_Die *die_mem) @@ -435,15 +454,32 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data) } /** + * die_find_top_inlinefunc - Search the top inlined function at given address + * @sp_die: a subprogram DIE which including @addr + * @addr: target address + * @die_mem: a buffer for result DIE + * + * Search an inlined function DIE which includes @addr. Stores the + * DIE to @die_mem and returns it if found. Returns NULL if failed. + * Even if several inlined functions are expanded recursively, this + * doesn't trace it down, and returns the topmost one. + */ +Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, + Dwarf_Die *die_mem) +{ + return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem); +} + +/** * die_find_inlinefunc - Search an inlined function at given address - * @cu_die: a CU DIE which including @addr + * @sp_die: a subprogram DIE which including @addr * @addr: target address * @die_mem: a buffer for result DIE * * Search an inlined function DIE which includes @addr. Stores the - * DIE to @die_mem and returns it if found. Returns NULl if failed. + * DIE to @die_mem and returns it if found. Returns NULL if failed. * If several inlined functions are expanded recursively, this trace - * it and returns deepest one. + * it down and returns deepest one. */ Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, Dwarf_Die *die_mem) diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 6ce1717784b7..b4fe90c6cb2d 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -38,6 +38,9 @@ extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, int (*callback)(Dwarf_Die *, void *), void *data); +/* Ensure that this DIE is a subprogram and definition (not declaration) */ +extern bool die_is_func_def(Dwarf_Die *dw_die); + /* Compare diename and tname */ extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname); @@ -76,7 +79,11 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die, extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr, Dwarf_Die *die_mem); -/* Search an inlined function including given address */ +/* Search the top inlined function including given address */ +extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, + Dwarf_Die *die_mem); + +/* Search the deepest inlined function including given address */ extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, Dwarf_Die *die_mem); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 5cd13d768cec..ec9ae1114ed4 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -11,6 +11,7 @@ static const char *perf_event__names[] = { [0] = "TOTAL", [PERF_RECORD_MMAP] = "MMAP", + [PERF_RECORD_MMAP2] = "MMAP2", [PERF_RECORD_LOST] = "LOST", [PERF_RECORD_COMM] = "COMM", [PERF_RECORD_EXIT] = "EXIT", @@ -198,6 +199,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, char execname[PATH_MAX]; char anonstr[] = "//anon"; size_t size; + ssize_t n; if (fgets(bf, sizeof(bf), fp) == NULL) break; @@ -206,9 +208,13 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, ""); /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n", + n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n", &event->mmap.start, &event->mmap.len, prot, - &event->mmap.pgoff, execname); + &event->mmap.pgoff, + execname); + + if (n != 5) + continue; if (prot[2] != 'x') continue; @@ -221,7 +227,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, size = PERF_ALIGN(size, sizeof(u64)); event->mmap.len -= event->mmap.start; event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size)); + (sizeof(event->mmap.filename) - size)); memset(event->mmap.filename + size, 0, machine->id_hdr_size); event->mmap.header.size += machine->id_hdr_size; event->mmap.pid = tgid; @@ -506,18 +512,18 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_comm_event(machine, event); + return machine__process_comm_event(machine, event, sample); } int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_lost_event(machine, event); + return machine__process_lost_event(machine, event, sample); } size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) @@ -527,12 +533,31 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) event->mmap.len, event->mmap.pgoff, event->mmap.filename); } +size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) +{ + return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 + " %02x:%02x %"PRIu64" %"PRIu64"]: %s\n", + event->mmap2.pid, event->mmap2.tid, event->mmap2.start, + event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, + event->mmap2.min, event->mmap2.ino, + event->mmap2.ino_generation, + event->mmap2.filename); +} + int perf_event__process_mmap(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_mmap_event(machine, event); + return machine__process_mmap_event(machine, event, sample); +} + +int perf_event__process_mmap2(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_mmap2_event(machine, event, sample); } size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) @@ -544,18 +569,18 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) int perf_event__process_fork(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_fork_event(machine, event); + return machine__process_fork_event(machine, event, sample); } int perf_event__process_exit(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_exit_event(machine, event); + return machine__process_exit_event(machine, event, sample); } size_t perf_event__fprintf(union perf_event *event, FILE *fp) @@ -574,6 +599,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) case PERF_RECORD_MMAP: ret += perf_event__fprintf_mmap(event, fp); break; + case PERF_RECORD_MMAP2: + ret += perf_event__fprintf_mmap2(event, fp); + break; default: ret += fprintf(fp, "\n"); } @@ -583,20 +611,21 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) int perf_event__process(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_event(machine, event); + return machine__process_event(machine, event, sample); } -void thread__find_addr_map(struct thread *self, +void thread__find_addr_map(struct thread *thread, struct machine *machine, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al) { - struct map_groups *mg = &self->mg; + struct map_groups *mg = &thread->mg; + bool load_map = false; - al->thread = self; + al->thread = thread; al->addr = addr; al->cpumode = cpumode; al->filtered = false; @@ -609,11 +638,13 @@ void thread__find_addr_map(struct thread *self, if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; mg = &machine->kmaps; + load_map = true; } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { al->level = 'g'; mg = &machine->kmaps; + load_map = true; } else { /* * 'u' means guest os user space. @@ -654,18 +685,25 @@ try_again: mg = &machine->kmaps; goto try_again; } - } else + } else { + /* + * Kernel maps might be changed when loading symbols so loading + * must be done prior to using kernel maps. + */ + if (load_map) + map__load(al->map, machine->symbol_filter); al->addr = al->map->map_ip(al->map, al->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) + struct addr_location *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); + al->sym = map__find_symbol(al->map, al->addr, + machine->symbol_filter); else al->sym = NULL; } @@ -673,20 +711,20 @@ void thread__find_addr_location(struct thread *thread, struct machine *machine, int perf_event__preprocess_sample(const union perf_event *event, struct machine *machine, struct addr_location *al, - struct perf_sample *sample, - symbol_filter_t filter) + struct perf_sample *sample) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = machine__findnew_thread(machine, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->pid); if (thread == NULL) return -1; if (symbol_conf.comm_list && - !strlist__has_entry(symbol_conf.comm_list, thread->comm)) + !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread))) goto out_filtered; - dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); + dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid); /* * Have we already created the kernel maps for this machine? * @@ -699,7 +737,7 @@ int perf_event__preprocess_sample(const union perf_event *event, machine__create_kernel_maps(machine); thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - event->ip.ip, al); + sample->ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); @@ -717,7 +755,8 @@ int perf_event__preprocess_sample(const union perf_event *event, dso->long_name))))) goto out_filtered; - al->sym = map__find_symbol(al->map, al->addr, filter); + al->sym = map__find_symbol(al->map, al->addr, + machine->symbol_filter); } if (symbol_conf.sym_list && diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 181389535c0c..f8d70f3003ab 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -8,22 +8,25 @@ #include "map.h" #include "build-id.h" -/* - * PERF_SAMPLE_IP | PERF_SAMPLE_TID | * - */ -struct ip_event { +struct mmap_event { struct perf_event_header header; - u64 ip; u32 pid, tid; - unsigned char __more_data[]; + u64 start; + u64 len; + u64 pgoff; + char filename[PATH_MAX]; }; -struct mmap_event { +struct mmap2_event { struct perf_event_header header; u32 pid, tid; u64 start; u64 len; u64 pgoff; + u32 maj; + u32 min; + u64 ino; + u64 ino_generation; char filename[PATH_MAX]; }; @@ -58,12 +61,22 @@ struct read_event { u64 id; }; +struct throttle_event { + struct perf_event_header header; + u64 time; + u64 id; + u64 stream_id; +}; #define PERF_SAMPLE_MASK \ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | \ PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID | \ - PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD) + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD | \ + PERF_SAMPLE_IDENTIFIER) + +/* perf sample has 16 bits size limit */ +#define PERF_SAMPLE_MAX_SIZE (1 << 16) struct sample_event { struct perf_event_header header; @@ -71,6 +84,7 @@ struct sample_event { }; struct regs_dump { + u64 abi; u64 *regs; }; @@ -80,6 +94,23 @@ struct stack_dump { char *data; }; +struct sample_read_value { + u64 value; + u64 id; +}; + +struct sample_read { + u64 time_enabled; + u64 time_running; + union { + struct { + u64 nr; + struct sample_read_value *values; + } group; + struct sample_read_value one; + }; +}; + struct perf_sample { u64 ip; u32 pid, tid; @@ -89,6 +120,7 @@ struct perf_sample { u64 stream_id; u64 period; u64 weight; + u64 transaction; u32 cpu; u32 raw_size; u64 data_src; @@ -97,6 +129,7 @@ struct perf_sample { struct branch_stack *branch_stack; struct regs_dump user_regs; struct stack_dump user_stack; + struct sample_read read; }; #define PERF_MEM_DATA_SRC_NONE \ @@ -116,7 +149,7 @@ struct build_id_event { enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_USER_TYPE_START = 64, PERF_RECORD_HEADER_ATTR = 64, - PERF_RECORD_HEADER_EVENT_TYPE = 65, + PERF_RECORD_HEADER_EVENT_TYPE = 65, /* depreceated */ PERF_RECORD_HEADER_TRACING_DATA = 66, PERF_RECORD_HEADER_BUILD_ID = 67, PERF_RECORD_FINISHED_ROUND = 68, @@ -148,12 +181,13 @@ struct tracing_data_event { union perf_event { struct perf_event_header header; - struct ip_event ip; struct mmap_event mmap; + struct mmap2_event mmap2; struct comm_event comm; struct fork_event fork; struct lost_event lost; struct read_event read; + struct throttle_event throttle; struct sample_event sample; struct attr_event attr; struct event_type_event event_type; @@ -199,6 +233,10 @@ int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_mmap2(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process_fork(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -213,20 +251,24 @@ int perf_event__process(struct perf_tool *tool, struct machine *machine); struct addr_location; -int perf_event__preprocess_sample(const union perf_event *self, + +int perf_event__preprocess_sample(const union perf_event *event, struct machine *machine, struct addr_location *al, - struct perf_sample *sample, - symbol_filter_t filter); + struct perf_sample *sample); const char *perf_event__name(unsigned int id); +size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, + u64 sample_regs_user, u64 read_format); int perf_event__synthesize_sample(union perf_event *event, u64 type, + u64 sample_regs_user, u64 read_format, 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_mmap2(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); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 8065ce8fa9a5..b939221efd8d 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -14,9 +14,11 @@ #include "target.h" #include "evlist.h" #include "evsel.h" +#include "debug.h" #include <unistd.h> #include "parse-events.h" +#include "parse-options.h" #include <sys/mman.h> @@ -48,26 +50,41 @@ struct perf_evlist *perf_evlist__new(void) return evlist; } -void perf_evlist__config(struct perf_evlist *evlist, - struct perf_record_opts *opts) +struct perf_evlist *perf_evlist__new_default(void) { - struct perf_evsel *evsel; - /* - * Set the evsel leader links before we configure attributes, - * since some might depend on this info. - */ - if (opts->group) - perf_evlist__set_leader(evlist); + struct perf_evlist *evlist = perf_evlist__new(); - if (evlist->cpus->map[0] < 0) - opts->no_inherit = true; + if (evlist && perf_evlist__add_default(evlist)) { + perf_evlist__delete(evlist); + evlist = NULL; + } - list_for_each_entry(evsel, &evlist->entries, node) { - perf_evsel__config(evsel, opts); + return evlist; +} - if (evlist->nr_entries > 1) - perf_evsel__set_sample_id(evsel); - } +/** + * perf_evlist__set_id_pos - set the positions of event ids. + * @evlist: selected event list + * + * Events with compatible sample types all have the same id_pos + * and is_pos. For convenience, put a copy on evlist. + */ +void perf_evlist__set_id_pos(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + + evlist->id_pos = first->id_pos; + evlist->is_pos = first->is_pos; +} + +static void perf_evlist__update_id_pos(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) + perf_evsel__calc_id_pos(evsel); + + perf_evlist__set_id_pos(evlist); } static void perf_evlist__purge(struct perf_evlist *evlist) @@ -100,15 +117,20 @@ void perf_evlist__delete(struct perf_evlist *evlist) void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) { list_add_tail(&entry->node, &evlist->entries); - ++evlist->nr_entries; + if (!evlist->nr_entries++) + perf_evlist__set_id_pos(evlist); } void perf_evlist__splice_list_tail(struct perf_evlist *evlist, struct list_head *list, int nr_entries) { + bool set_id_pos = !evlist->nr_entries; + list_splice_tail(list, &evlist->entries); evlist->nr_entries += nr_entries; + if (set_id_pos) + perf_evlist__set_id_pos(evlist); } void __perf_evlist__set_leader(struct list_head *list) @@ -209,6 +231,21 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) return NULL; } +struct perf_evsel * +perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, + const char *name) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) && + (strcmp(evsel->name, name) == 0)) + return evsel; + } + + return NULL; +} + int perf_evlist__add_newtp(struct perf_evlist *evlist, const char *sys, const char *name, void *handler) { @@ -218,7 +255,7 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist, if (evsel == NULL) return -1; - evsel->handler.func = handler; + evsel->handler = handler; perf_evlist__add(evlist, evsel); return 0; } @@ -232,7 +269,7 @@ void perf_evlist__disable(struct perf_evlist *evlist) for (cpu = 0; cpu < nr_cpus; cpu++) { list_for_each_entry(pos, &evlist->entries, node) { - if (!perf_evsel__is_group_leader(pos)) + if (!perf_evsel__is_group_leader(pos) || !pos->fd) continue; for (thread = 0; thread < nr_threads; thread++) ioctl(FD(pos, cpu, thread), @@ -250,7 +287,7 @@ void perf_evlist__enable(struct perf_evlist *evlist) for (cpu = 0; cpu < nr_cpus; cpu++) { list_for_each_entry(pos, &evlist->entries, node) { - if (!perf_evsel__is_group_leader(pos)) + if (!perf_evsel__is_group_leader(pos) || !pos->fd) continue; for (thread = 0; thread < nr_threads; thread++) ioctl(FD(pos, cpu, thread), @@ -259,6 +296,44 @@ void perf_evlist__enable(struct perf_evlist *evlist) } } +int perf_evlist__disable_event(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + int cpu, thread, err; + + if (!evsel->fd) + return 0; + + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + for (thread = 0; thread < evlist->threads->nr; thread++) { + err = ioctl(FD(evsel, cpu, thread), + PERF_EVENT_IOC_DISABLE, 0); + if (err) + return err; + } + } + return 0; +} + +int perf_evlist__enable_event(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + int cpu, thread, err; + + if (!evsel->fd) + return -EINVAL; + + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + for (thread = 0; thread < evlist->threads->nr; thread++) { + err = ioctl(FD(evsel, cpu, thread), + PERF_EVENT_IOC_ENABLE, 0); + if (err) + return err; + } + } + return 0; +} + static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { int nr_cpus = cpu_map__nr(evlist->cpus); @@ -302,6 +377,24 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist, { u64 read_data[4] = { 0, }; int id_idx = 1; /* The first entry is the counter value */ + u64 id; + int ret; + + ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); + if (!ret) + goto add; + + if (errno != ENOTTY) + return -1; + + /* Legacy way to get event id.. All hail to old kernels! */ + + /* + * This way does not work with group format read, so bail + * out in that case. + */ + if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP) + return -1; if (!(evsel->attr.read_format & PERF_FORMAT_ID) || read(fd, &read_data, sizeof(read_data)) == -1) @@ -312,25 +405,39 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist, if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) ++id_idx; - perf_evlist__id_add(evlist, evsel, cpu, thread, read_data[id_idx]); + id = read_data[id_idx]; + + add: + perf_evlist__id_add(evlist, evsel, cpu, thread, id); return 0; } -struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) +struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id) { struct hlist_head *head; struct perf_sample_id *sid; int hash; - if (evlist->nr_entries == 1) - return perf_evlist__first(evlist); - hash = hash_64(id, PERF_EVLIST__HLIST_BITS); head = &evlist->heads[hash]; hlist_for_each_entry(sid, head, node) if (sid->id == id) - return sid->evsel; + return sid; + + return NULL; +} + +struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) +{ + struct perf_sample_id *sid; + + if (evlist->nr_entries == 1) + return perf_evlist__first(evlist); + + sid = perf_evlist__id2sid(evlist, id); + if (sid) + return sid->evsel; if (!perf_evlist__sample_id_all(evlist)) return perf_evlist__first(evlist); @@ -338,6 +445,60 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) return NULL; } +static int perf_evlist__event2id(struct perf_evlist *evlist, + union perf_event *event, u64 *id) +{ + const u64 *array = event->sample.array; + ssize_t n; + + n = (event->header.size - sizeof(event->header)) >> 3; + + if (event->header.type == PERF_RECORD_SAMPLE) { + if (evlist->id_pos >= n) + return -1; + *id = array[evlist->id_pos]; + } else { + if (evlist->is_pos > n) + return -1; + n -= evlist->is_pos; + *id = array[n]; + } + return 0; +} + +static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, + union perf_event *event) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + struct hlist_head *head; + struct perf_sample_id *sid; + int hash; + u64 id; + + if (evlist->nr_entries == 1) + return first; + + if (!first->attr.sample_id_all && + event->header.type != PERF_RECORD_SAMPLE) + return first; + + if (perf_evlist__event2id(evlist, event, &id)) + return NULL; + + /* Synthesized events have an id of zero */ + if (!id) + return first; + + hash = hash_64(id, PERF_EVLIST__HLIST_BITS); + head = &evlist->heads[hash]; + + hlist_for_each_entry(sid, head, node) { + if (sid->id == id) + return sid->evsel; + } + return NULL; +} + union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { struct perf_mmap *md = &evlist->mmap[idx]; @@ -379,7 +540,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) if ((old & md->mask) + size != ((old + size) & md->mask)) { unsigned int offset = old; unsigned int len = min(sizeof(*event), size), cpy; - void *dst = &md->event_copy; + void *dst = md->event_copy; do { cpy = min(md->mask + 1 - (offset & md->mask), len); @@ -389,7 +550,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) len -= cpy; } while (len); - event = &md->event_copy; + event = (union perf_event *) md->event_copy; } old += size; @@ -397,22 +558,33 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) md->prev = old; - if (!evlist->overwrite) + return event; +} + +void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) +{ + if (!evlist->overwrite) { + struct perf_mmap *md = &evlist->mmap[idx]; + unsigned int old = md->prev; + perf_mmap__write_tail(md, old); + } +} - return event; +static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) +{ + if (evlist->mmap[idx].base != NULL) { + munmap(evlist->mmap[idx].base, evlist->mmap_len); + evlist->mmap[idx].base = NULL; + } } void perf_evlist__munmap(struct perf_evlist *evlist) { int i; - for (i = 0; i < evlist->nr_mmaps; i++) { - if (evlist->mmap[i].base != NULL) { - munmap(evlist->mmap[i].base, evlist->mmap_len); - evlist->mmap[i].base = NULL; - } - } + for (i = 0; i < evlist->nr_mmaps; i++) + __perf_evlist__munmap(evlist, i); free(evlist->mmap); evlist->mmap = NULL; @@ -421,7 +593,7 @@ void perf_evlist__munmap(struct perf_evlist *evlist) static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) { evlist->nr_mmaps = cpu_map__nr(evlist->cpus); - if (cpu_map__all(evlist->cpus)) + if (cpu_map__empty(evlist->cpus)) evlist->nr_mmaps = thread_map__nr(evlist->threads); evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); return evlist->mmap != NULL ? 0 : -ENOMEM; @@ -435,6 +607,8 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot, MAP_SHARED, fd, 0); if (evlist->mmap[idx].base == MAP_FAILED) { + pr_debug2("failed to mmap perf event ring buffer, error %d\n", + errno); evlist->mmap[idx].base = NULL; return -1; } @@ -443,103 +617,152 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, return 0; } -static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask) +static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, + int prot, int mask, int cpu, int thread, + int *output) { struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + int fd = FD(evsel, cpu, thread); + + if (*output == -1) { + *output = fd; + if (__perf_evlist__mmap(evlist, idx, prot, mask, + *output) < 0) + return -1; + } else { + if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) + return -1; + } + + if ((evsel->attr.read_format & PERF_FORMAT_ID) && + perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) + return -1; + } + + return 0; +} + +static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, + int mask) +{ int cpu, thread; int nr_cpus = cpu_map__nr(evlist->cpus); int nr_threads = thread_map__nr(evlist->threads); + pr_debug2("perf event ring buffer mmapped per cpu\n"); for (cpu = 0; cpu < nr_cpus; cpu++) { int output = -1; for (thread = 0; thread < nr_threads; thread++) { - list_for_each_entry(evsel, &evlist->entries, node) { - int fd = FD(evsel, cpu, thread); - - if (output == -1) { - output = fd; - if (__perf_evlist__mmap(evlist, cpu, - prot, mask, output) < 0) - goto out_unmap; - } else { - if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0) - goto out_unmap; - } - - if ((evsel->attr.read_format & PERF_FORMAT_ID) && - perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) - goto out_unmap; - } + if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask, + cpu, thread, &output)) + goto out_unmap; } } return 0; out_unmap: - for (cpu = 0; cpu < nr_cpus; cpu++) { - if (evlist->mmap[cpu].base != NULL) { - munmap(evlist->mmap[cpu].base, evlist->mmap_len); - evlist->mmap[cpu].base = NULL; - } - } + for (cpu = 0; cpu < nr_cpus; cpu++) + __perf_evlist__munmap(evlist, cpu); return -1; } -static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask) +static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, + int mask) { - struct perf_evsel *evsel; int thread; int nr_threads = thread_map__nr(evlist->threads); + pr_debug2("perf event ring buffer mmapped per thread\n"); for (thread = 0; thread < nr_threads; thread++) { int output = -1; - list_for_each_entry(evsel, &evlist->entries, node) { - int fd = FD(evsel, 0, thread); - - if (output == -1) { - output = fd; - if (__perf_evlist__mmap(evlist, thread, - prot, mask, output) < 0) - goto out_unmap; - } else { - if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0) - goto out_unmap; - } - - if ((evsel->attr.read_format & PERF_FORMAT_ID) && - perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0) - goto out_unmap; - } + if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0, + thread, &output)) + goto out_unmap; } return 0; out_unmap: - for (thread = 0; thread < nr_threads; thread++) { - if (evlist->mmap[thread].base != NULL) { - munmap(evlist->mmap[thread].base, evlist->mmap_len); - evlist->mmap[thread].base = NULL; + for (thread = 0; thread < nr_threads; thread++) + __perf_evlist__munmap(evlist, thread); + return -1; +} + +static size_t perf_evlist__mmap_size(unsigned long pages) +{ + /* 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 0; + + return (pages + 1) * page_size; +} + +int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + unsigned int *mmap_pages = opt->value; + unsigned long pages, val; + size_t size; + static struct parse_tag tags[] = { + { .tag = 'B', .mult = 1 }, + { .tag = 'K', .mult = 1 << 10 }, + { .tag = 'M', .mult = 1 << 20 }, + { .tag = 'G', .mult = 1 << 30 }, + { .tag = 0 }, + }; + + val = parse_tag_value(str, tags); + if (val != (unsigned long) -1) { + /* we got file size value */ + pages = PERF_ALIGN(val, page_size) / page_size; + if (pages < (1UL << 31) && !is_power_of_2(pages)) { + pages = next_pow2(pages); + pr_info("rounding mmap pages size to %lu (%lu pages)\n", + pages * page_size, pages); + } + } else { + /* we got pages count value */ + char *eptr; + pages = strtoul(str, &eptr, 10); + if (*eptr != '\0') { + pr_err("failed to parse --mmap_pages/-m value\n"); + return -1; } } - return -1; + + if (pages > UINT_MAX || pages > SIZE_MAX / page_size) { + pr_err("--mmap_pages/-m value too big\n"); + return -1; + } + + size = perf_evlist__mmap_size(pages); + if (!size) { + pr_err("--mmap_pages/-m value must be a power of two."); + return -1; + } + + *mmap_pages = pages; + return 0; } -/** perf_evlist__mmap - Create per cpu maps to receive events - * - * @evlist - list of events - * @pages - map length in pages - * @overwrite - overwrite older events? +/** + * perf_evlist__mmap - Create mmaps to receive events. + * @evlist: list of events + * @pages: map length in pages + * @overwrite: overwrite older events? * - * If overwrite is false the user needs to signal event consuption using: + * If @overwrite is %false the user needs to signal event consumption using + * perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this + * automatically. * - * struct perf_mmap *m = &evlist->mmap[cpu]; - * unsigned int head = perf_mmap__read_head(m); - * - * perf_mmap__write_tail(m, head) - * - * Using perf_evlist__read_on_cpu does this automatically. + * Return: %0 on success, negative error code otherwise. */ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, bool overwrite) @@ -549,14 +772,6 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, const struct thread_map *threads = evlist->threads; 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; @@ -564,7 +779,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return -ENOMEM; evlist->overwrite = overwrite; - evlist->mmap_len = (pages + 1) * page_size; + evlist->mmap_len = perf_evlist__mmap_size(pages); + pr_debug("mmap size %zuB\n", evlist->mmap_len); + mask = evlist->mmap_len - page_size - 1; list_for_each_entry(evsel, &evlist->entries, node) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && @@ -573,7 +790,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return -ENOMEM; } - if (cpu_map__all(cpus)) + if (cpu_map__empty(cpus)) return perf_evlist__mmap_per_thread(evlist, prot, mask); return perf_evlist__mmap_per_cpu(evlist, prot, mask); @@ -650,20 +867,66 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) { + struct perf_evsel *pos; + + if (evlist->nr_entries == 1) + return true; + + if (evlist->id_pos < 0 || evlist->is_pos < 0) + return false; + + list_for_each_entry(pos, &evlist->entries, node) { + if (pos->id_pos != evlist->id_pos || + pos->is_pos != evlist->is_pos) + return false; + } + + return true; +} + +u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + if (evlist->combined_sample_type) + return evlist->combined_sample_type; + + list_for_each_entry(evsel, &evlist->entries, node) + evlist->combined_sample_type |= evsel->attr.sample_type; + + return evlist->combined_sample_type; +} + +u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist) +{ + evlist->combined_sample_type = 0; + return __perf_evlist__combined_sample_type(evlist); +} + +bool perf_evlist__valid_read_format(struct perf_evlist *evlist) +{ struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; + u64 read_format = first->attr.read_format; + u64 sample_type = first->attr.sample_type; list_for_each_entry_continue(pos, &evlist->entries, node) { - if (first->attr.sample_type != pos->attr.sample_type) + if (read_format != pos->attr.read_format) return false; } + /* PERF_SAMPLE_READ imples PERF_FORMAT_ID. */ + if ((sample_type & PERF_SAMPLE_READ) && + !(read_format & PERF_FORMAT_ID)) { + return false; + } + return true; } -u64 perf_evlist__sample_type(struct perf_evlist *evlist) +u64 perf_evlist__read_format(struct perf_evlist *evlist) { struct perf_evsel *first = perf_evlist__first(evlist); - return first->attr.sample_type; + return first->attr.read_format; } u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist) @@ -692,6 +955,9 @@ u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist) if (sample_type & PERF_SAMPLE_CPU) size += sizeof(data->cpu) * 2; + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + size += sizeof(data->id); out: return size; } @@ -735,6 +1001,8 @@ int perf_evlist__open(struct perf_evlist *evlist) struct perf_evsel *evsel; int err; + perf_evlist__update_id_pos(evlist); + list_for_each_entry(evsel, &evlist->entries, node) { err = perf_evsel__open(evsel, evlist->cpus, evlist->threads); if (err < 0) @@ -783,13 +1051,6 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, 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]); @@ -838,7 +1099,7 @@ out_close_ready_pipe: int perf_evlist__start_workload(struct perf_evlist *evlist) { if (evlist->workload.cork_fd > 0) { - char bf; + char bf = 0; int ret; /* * Remove the cork, let it rip! @@ -857,7 +1118,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist) int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, struct perf_sample *sample) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + + if (!evsel) + return -EFAULT; return perf_evsel__parse_sample(evsel, event, sample); } @@ -873,3 +1137,66 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) return printed + fprintf(fp, "\n");; } + +int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused, + int err, char *buf, size_t size) +{ + char sbuf[128]; + + switch (err) { + case ENOENT: + scnprintf(buf, size, "%s", + "Error:\tUnable to find debugfs\n" + "Hint:\tWas your kernel was compiled with debugfs support?\n" + "Hint:\tIs the debugfs filesystem mounted?\n" + "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'"); + break; + case EACCES: + scnprintf(buf, size, + "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n" + "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n", + debugfs_mountpoint, debugfs_mountpoint); + break; + default: + scnprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf))); + break; + } + + return 0; +} + +int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, + int err, char *buf, size_t size) +{ + int printed, value; + char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf)); + + switch (err) { + case EACCES: + case EPERM: + printed = scnprintf(buf, size, + "Error:\t%s.\n" + "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg); + + if (filename__read_int("/proc/sys/kernel/perf_event_paranoid", &value)) + break; + + printed += scnprintf(buf + printed, size - printed, "\nHint:\t"); + + if (value >= 2) { + printed += scnprintf(buf + printed, size - printed, + "For your workloads it needs to be <= 1\nHint:\t"); + } + printed += scnprintf(buf + printed, size - printed, + "For system wide tracing it needs to be set to -1"); + + printed += scnprintf(buf + printed, size - printed, + ".\nHint:\tThe current value is %d.", value); + break; + default: + scnprintf(buf, size, "%s", emsg); + break; + } + + return 0; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 0583d36252be..ecaa582f40e2 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -21,7 +21,7 @@ struct perf_mmap { void *base; int mask; unsigned int prev; - union perf_event event_copy; + char event_copy[PERF_SAMPLE_MAX_SIZE]; }; struct perf_evlist { @@ -31,7 +31,10 @@ struct perf_evlist { int nr_groups; int nr_fds; int nr_mmaps; - int mmap_len; + size_t mmap_len; + int id_pos; + int is_pos; + u64 combined_sample_type; struct { int cork_fd; pid_t pid; @@ -50,6 +53,7 @@ struct perf_evsel_str_handler { }; struct perf_evlist *perf_evlist__new(void); +struct perf_evlist *perf_evlist__new_default(void); void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, struct thread_map *threads); void perf_evlist__exit(struct perf_evlist *evlist); @@ -71,6 +75,10 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter); struct perf_evsel * perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); +struct perf_evsel * +perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, + const char *name); + void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu, int thread, u64 id); @@ -78,13 +86,20 @@ 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); +struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); + +union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx); + +void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); int perf_evlist__open(struct perf_evlist *evlist); void perf_evlist__close(struct perf_evlist *evlist); +void perf_evlist__set_id_pos(struct perf_evlist *evlist); +bool perf_can_sample_identifier(void); void perf_evlist__config(struct perf_evlist *evlist, struct perf_record_opts *opts); +int perf_record_opts__config(struct perf_record_opts *opts); int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct perf_target *target, @@ -92,6 +107,10 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, bool want_signal); int perf_evlist__start_workload(struct perf_evlist *evlist); +int perf_evlist__parse_mmap_pages(const struct option *opt, + const char *str, + int unset); + int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, bool overwrite); void perf_evlist__munmap(struct perf_evlist *evlist); @@ -99,6 +118,11 @@ void perf_evlist__munmap(struct perf_evlist *evlist); void perf_evlist__disable(struct perf_evlist *evlist); void perf_evlist__enable(struct perf_evlist *evlist); +int perf_evlist__disable_event(struct perf_evlist *evlist, + struct perf_evsel *evsel); +int perf_evlist__enable_event(struct perf_evlist *evlist, + struct perf_evsel *evsel); + void perf_evlist__set_selected(struct perf_evlist *evlist, struct perf_evsel *evsel); @@ -118,7 +142,9 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist); void __perf_evlist__set_leader(struct list_head *list); void perf_evlist__set_leader(struct perf_evlist *evlist); -u64 perf_evlist__sample_type(struct perf_evlist *evlist); +u64 perf_evlist__read_format(struct perf_evlist *evlist); +u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist); +u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist); bool perf_evlist__sample_id_all(struct perf_evlist *evlist); u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist); @@ -127,6 +153,7 @@ int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *even bool perf_evlist__valid_sample_type(struct perf_evlist *evlist); bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist); +bool perf_evlist__valid_read_format(struct perf_evlist *evlist); void perf_evlist__splice_list_tail(struct perf_evlist *evlist, struct list_head *list, @@ -144,10 +171,13 @@ static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); +int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size); +int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size); + static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) { struct perf_event_mmap_page *pc = mm->base; - int head = pc->data_head; + int head = ACCESS_ONCE(pc->data_head); rmb(); return head; } @@ -160,7 +190,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, /* * ensure all reads are done before we write the tail out. */ - /* mb(); */ + mb(); pc->data_tail = tail; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c9c7494506a1..5280820ed389 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -9,27 +9,30 @@ #include <byteswap.h> #include <linux/bitops.h> -#include "asm/bug.h" #include <lk/debugfs.h> -#include "event-parse.h" +#include <traceevent/event-parse.h> +#include <linux/hw_breakpoint.h> +#include <linux/perf_event.h> +#include <sys/resource.h> +#include "asm/bug.h" #include "evsel.h" #include "evlist.h" #include "util.h" #include "cpumap.h" #include "thread_map.h" #include "target.h" -#include <linux/hw_breakpoint.h> -#include <linux/perf_event.h> #include "perf_regs.h" +#include "debug.h" static struct { bool sample_id_all; bool exclude_guest; + bool mmap2; } perf_missing_features; #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) -static int __perf_evsel__sample_size(u64 sample_type) +int __perf_evsel__sample_size(u64 sample_type) { u64 mask = sample_type & PERF_SAMPLE_MASK; int size = 0; @@ -45,6 +48,72 @@ static int __perf_evsel__sample_size(u64 sample_type) return size; } +/** + * __perf_evsel__calc_id_pos - calculate id_pos. + * @sample_type: sample type + * + * This function returns the position of the event id (PERF_SAMPLE_ID or + * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct + * sample_event. + */ +static int __perf_evsel__calc_id_pos(u64 sample_type) +{ + int idx = 0; + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + return 0; + + if (!(sample_type & PERF_SAMPLE_ID)) + return -1; + + if (sample_type & PERF_SAMPLE_IP) + idx += 1; + + if (sample_type & PERF_SAMPLE_TID) + idx += 1; + + if (sample_type & PERF_SAMPLE_TIME) + idx += 1; + + if (sample_type & PERF_SAMPLE_ADDR) + idx += 1; + + return idx; +} + +/** + * __perf_evsel__calc_is_pos - calculate is_pos. + * @sample_type: sample type + * + * This function returns the position (counting backwards) of the event id + * (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if + * sample_id_all is used there is an id sample appended to non-sample events. + */ +static int __perf_evsel__calc_is_pos(u64 sample_type) +{ + int idx = 1; + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + return 1; + + if (!(sample_type & PERF_SAMPLE_ID)) + return -1; + + if (sample_type & PERF_SAMPLE_CPU) + idx += 1; + + if (sample_type & PERF_SAMPLE_STREAM_ID) + idx += 1; + + return idx; +} + +void perf_evsel__calc_id_pos(struct perf_evsel *evsel) +{ + evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type); + evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type); +} + void hists__init(struct hists *hists) { memset(hists, 0, sizeof(*hists)); @@ -61,6 +130,7 @@ void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, if (!(evsel->attr.sample_type & bit)) { evsel->attr.sample_type |= bit; evsel->sample_size += sizeof(u64); + perf_evsel__calc_id_pos(evsel); } } @@ -70,12 +140,19 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, if (evsel->attr.sample_type & bit) { evsel->attr.sample_type &= ~bit; evsel->sample_size -= sizeof(u64); + perf_evsel__calc_id_pos(evsel); } } -void perf_evsel__set_sample_id(struct perf_evsel *evsel) +void perf_evsel__set_sample_id(struct perf_evsel *evsel, + bool can_sample_identifier) { - perf_evsel__set_sample_bit(evsel, ID); + if (can_sample_identifier) { + perf_evsel__reset_sample_bit(evsel, ID); + perf_evsel__set_sample_bit(evsel, IDENTIFIER); + } else { + perf_evsel__set_sample_bit(evsel, ID); + } evsel->attr.read_format |= PERF_FORMAT_ID; } @@ -88,6 +165,7 @@ void perf_evsel__init(struct perf_evsel *evsel, INIT_LIST_HEAD(&evsel->node); hists__init(&evsel->hists); evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); + perf_evsel__calc_id_pos(evsel); } struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx) @@ -246,6 +324,7 @@ const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = { "major-faults", "alignment-faults", "emulation-faults", + "dummy", }; static const char *__perf_evsel__sw_name(u64 config) @@ -490,6 +569,7 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts) { + struct perf_evsel *leader = evsel->leader; struct perf_event_attr *attr = &evsel->attr; int track = !evsel->idx; /* only the first counter needs these */ @@ -499,6 +579,25 @@ void perf_evsel__config(struct perf_evsel *evsel, perf_evsel__set_sample_bit(evsel, IP); perf_evsel__set_sample_bit(evsel, TID); + if (evsel->sample_read) { + perf_evsel__set_sample_bit(evsel, READ); + + /* + * We need ID even in case of single event, because + * PERF_SAMPLE_READ process ID specific data. + */ + perf_evsel__set_sample_id(evsel, false); + + /* + * Apply group format only if we belong to group + * with more than one members. + */ + if (leader->nr_members > 1) { + attr->read_format |= PERF_FORMAT_GROUP; + attr->inherit = 0; + } + } + /* * We default some events to a 1 default interval. But keep * it a weak assumption overridable by the user. @@ -514,6 +613,15 @@ void perf_evsel__config(struct perf_evsel *evsel, } } + /* + * Disable sampling for all group members other + * than leader in case leader 'leads' the sampling. + */ + if ((leader != evsel) && leader->sample_read) { + attr->sample_freq = 0; + attr->sample_period = 0; + } + if (opts->no_samples) attr->sample_freq = 0; @@ -555,7 +663,7 @@ void perf_evsel__config(struct perf_evsel *evsel, } if (opts->sample_address) - attr->sample_type |= PERF_SAMPLE_DATA_SRC; + perf_evsel__set_sample_bit(evsel, DATA_SRC); if (opts->no_delay) { attr->watermark = 0; @@ -567,10 +675,13 @@ void perf_evsel__config(struct perf_evsel *evsel, } if (opts->sample_weight) - attr->sample_type |= PERF_SAMPLE_WEIGHT; + perf_evsel__set_sample_bit(evsel, WEIGHT); + + attr->mmap = track; + attr->comm = track; - attr->mmap = track; - attr->comm = track; + if (opts->sample_transaction) + perf_evsel__set_sample_bit(evsel, TRANSACTION); /* * XXX see the function comment above @@ -605,15 +716,15 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) return evsel->fd != NULL ? 0 : -ENOMEM; } -int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, - const char *filter) +static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthreads, + int ioc, void *arg) { int cpu, thread; for (cpu = 0; cpu < ncpus; cpu++) { for (thread = 0; thread < nthreads; thread++) { int fd = FD(evsel, cpu, thread), - err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter); + err = ioctl(fd, ioc, arg); if (err) return err; @@ -623,6 +734,21 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, return 0; } +int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, + const char *filter) +{ + return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + PERF_EVENT_IOC_SET_FILTER, + (void *)filter); +} + +int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + PERF_EVENT_IOC_ENABLE, + 0); +} + int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) { evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); @@ -817,12 +943,73 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) return fd; } +#define __PRINT_ATTR(fmt, cast, field) \ + fprintf(fp, " %-19s "fmt"\n", #field, cast attr->field) + +#define PRINT_ATTR_U32(field) __PRINT_ATTR("%u" , , field) +#define PRINT_ATTR_X32(field) __PRINT_ATTR("%#x", , field) +#define PRINT_ATTR_U64(field) __PRINT_ATTR("%" PRIu64, (uint64_t), field) +#define PRINT_ATTR_X64(field) __PRINT_ATTR("%#"PRIx64, (uint64_t), field) + +#define PRINT_ATTR2N(name1, field1, name2, field2) \ + fprintf(fp, " %-19s %u %-19s %u\n", \ + name1, attr->field1, name2, attr->field2) + +#define PRINT_ATTR2(field1, field2) \ + PRINT_ATTR2N(#field1, field1, #field2, field2) + +static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) +{ + size_t ret = 0; + + ret += fprintf(fp, "%.60s\n", graph_dotted_line); + ret += fprintf(fp, "perf_event_attr:\n"); + + ret += PRINT_ATTR_U32(type); + ret += PRINT_ATTR_U32(size); + ret += PRINT_ATTR_X64(config); + ret += PRINT_ATTR_U64(sample_period); + ret += PRINT_ATTR_U64(sample_freq); + ret += PRINT_ATTR_X64(sample_type); + ret += PRINT_ATTR_X64(read_format); + + ret += PRINT_ATTR2(disabled, inherit); + ret += PRINT_ATTR2(pinned, exclusive); + ret += PRINT_ATTR2(exclude_user, exclude_kernel); + ret += PRINT_ATTR2(exclude_hv, exclude_idle); + ret += PRINT_ATTR2(mmap, comm); + ret += PRINT_ATTR2(freq, inherit_stat); + ret += PRINT_ATTR2(enable_on_exec, task); + ret += PRINT_ATTR2(watermark, precise_ip); + ret += PRINT_ATTR2(mmap_data, sample_id_all); + ret += PRINT_ATTR2(exclude_host, exclude_guest); + ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel, + "excl.callchain_user", exclude_callchain_user); + ret += PRINT_ATTR_U32(mmap2); + + ret += PRINT_ATTR_U32(wakeup_events); + ret += PRINT_ATTR_U32(wakeup_watermark); + ret += PRINT_ATTR_X32(bp_type); + ret += PRINT_ATTR_X64(bp_addr); + ret += PRINT_ATTR_X64(config1); + ret += PRINT_ATTR_U64(bp_len); + ret += PRINT_ATTR_X64(config2); + ret += PRINT_ATTR_X64(branch_sample_type); + ret += PRINT_ATTR_X64(sample_regs_user); + ret += PRINT_ATTR_U32(sample_stack_user); + + ret += fprintf(fp, "%.60s\n", graph_dotted_line); + + return ret; +} + static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { int cpu, thread; unsigned long flags = 0; int pid = -1, err; + enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; if (evsel->fd == NULL && perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) @@ -834,12 +1021,17 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, } fallback_missing_features: + if (perf_missing_features.mmap2) + evsel->attr.mmap2 = 0; if (perf_missing_features.exclude_guest) evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; + if (verbose >= 2) + perf_event_attr__fprintf(&evsel->attr, stderr); + for (cpu = 0; cpu < cpus->nr; cpu++) { for (thread = 0; thread < threads->nr; thread++) { @@ -849,6 +1041,9 @@ retry_sample_id: pid = threads->map[thread]; group_fd = get_group_fd(evsel, cpu, thread); +retry_open: + pr_debug2("perf_event_open: pid %d cpu %d group_fd %d flags %#lx\n", + pid, cpus->map[cpu], group_fd, flags); FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr, pid, @@ -856,19 +1051,49 @@ retry_sample_id: group_fd, flags); if (FD(evsel, cpu, thread) < 0) { err = -errno; + pr_debug2("perf_event_open failed, error %d\n", + err); goto try_fallback; } + set_rlimit = NO_CHANGE; } } return 0; try_fallback: + /* + * perf stat needs between 5 and 22 fds per CPU. When we run out + * of them try to increase the limits. + */ + if (err == -EMFILE && set_rlimit < INCREASED_MAX) { + struct rlimit l; + int old_errno = errno; + + if (getrlimit(RLIMIT_NOFILE, &l) == 0) { + if (set_rlimit == NO_CHANGE) + l.rlim_cur = l.rlim_max; + else { + l.rlim_cur = l.rlim_max + 1000; + l.rlim_max = l.rlim_cur; + } + if (setrlimit(RLIMIT_NOFILE, &l) == 0) { + set_rlimit++; + errno = old_errno; + goto retry_open; + } + } + errno = old_errno; + } + if (err != -EINVAL || cpu > 0 || thread > 0) goto out_close; - if (!perf_missing_features.exclude_guest && - (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { + if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { + perf_missing_features.mmap2 = true; + goto fallback_missing_features; + } else if (!perf_missing_features.exclude_guest && + (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { perf_missing_features.exclude_guest = true; goto fallback_missing_features; } else if (!perf_missing_features.sample_id_all) { @@ -951,6 +1176,11 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, array += ((event->header.size - sizeof(event->header)) / sizeof(u64)) - 1; + if (type & PERF_SAMPLE_IDENTIFIER) { + sample->id = *array; + array--; + } + if (type & PERF_SAMPLE_CPU) { u.val64 = *array; if (swapped) { @@ -989,29 +1219,36 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, sample->pid = u.val32[0]; sample->tid = u.val32[1]; + array--; } return 0; } -static bool sample_overlap(const union perf_event *event, - const void *offset, u64 size) +static inline bool overflow(const void *endp, u16 max_size, const void *offset, + u64 size) { - const void *base = event; + return size > max_size || offset + size > endp; +} - if (offset + size > base + event->header.size) - return true; +#define OVERFLOW_CHECK(offset, size, max_size) \ + do { \ + if (overflow(endp, (max_size), (offset), (size))) \ + return -EFAULT; \ + } while (0) - return false; -} +#define OVERFLOW_CHECK_u64(offset) \ + OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64)) int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *data) { u64 type = evsel->attr.sample_type; - u64 regs_user = evsel->attr.sample_regs_user; bool swapped = evsel->needs_swap; const u64 *array; + u16 max_size = event->header.size; + const void *endp = (void *)event + max_size; + u64 sz; /* * used for cross-endian analysis. See git commit 65014ab3 @@ -1033,11 +1270,22 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array = event->sample.array; + /* + * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes + * up to PERF_SAMPLE_PERIOD. After that overflow() must be used to + * check the format does not go past the end of the event. + */ if (evsel->sample_size + sizeof(event->header) > event->header.size) return -EFAULT; + data->id = -1ULL; + if (type & PERF_SAMPLE_IDENTIFIER) { + data->id = *array; + array++; + } + if (type & PERF_SAMPLE_IP) { - data->ip = event->ip.ip; + data->ip = *array; array++; } @@ -1066,7 +1314,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; } - data->id = -1ULL; if (type & PERF_SAMPLE_ID) { data->id = *array; array++; @@ -1096,25 +1343,62 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } if (type & PERF_SAMPLE_READ) { - fprintf(stderr, "PERF_SAMPLE_READ is unsupported for now\n"); - return -1; + u64 read_format = evsel->attr.read_format; + + OVERFLOW_CHECK_u64(array); + if (read_format & PERF_FORMAT_GROUP) + data->read.group.nr = *array; + else + data->read.one.value = *array; + + array++; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + OVERFLOW_CHECK_u64(array); + data->read.time_enabled = *array; + array++; + } + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + OVERFLOW_CHECK_u64(array); + data->read.time_running = *array; + array++; + } + + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + const u64 max_group_nr = UINT64_MAX / + sizeof(struct sample_read_value); + + if (data->read.group.nr > max_group_nr) + return -EFAULT; + sz = data->read.group.nr * + sizeof(struct sample_read_value); + OVERFLOW_CHECK(array, sz, max_size); + data->read.group.values = + (struct sample_read_value *)array; + array = (void *)array + sz; + } else { + OVERFLOW_CHECK_u64(array); + data->read.one.id = *array; + array++; + } } if (type & PERF_SAMPLE_CALLCHAIN) { - if (sample_overlap(event, array, sizeof(data->callchain->nr))) - return -EFAULT; - - data->callchain = (struct ip_callchain *)array; + const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); - if (sample_overlap(event, array, data->callchain->nr)) + OVERFLOW_CHECK_u64(array); + data->callchain = (struct ip_callchain *)array++; + if (data->callchain->nr > max_callchain_nr) return -EFAULT; - - array += 1 + data->callchain->nr; + sz = data->callchain->nr * sizeof(u64); + OVERFLOW_CHECK(array, sz, max_size); + array = (void *)array + sz; } if (type & PERF_SAMPLE_RAW) { - const u64 *pdata; - + OVERFLOW_CHECK_u64(array); u.val64 = *array; if (WARN_ONCE(swapped, "Endianness of raw data not corrected!\n")) { @@ -1123,78 +1407,190 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, 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 = u.val32[0]; - pdata = (void *) array + sizeof(u32); - - if (sample_overlap(event, pdata, data->raw_size)) - return -EFAULT; + array = (void *)array + sizeof(u32); - data->raw_data = (void *) pdata; - - array = (void *)array + data->raw_size + sizeof(u32); + OVERFLOW_CHECK(array, data->raw_size, max_size); + data->raw_data = (void *)array; + array = (void *)array + data->raw_size; } if (type & PERF_SAMPLE_BRANCH_STACK) { - u64 sz; + const u64 max_branch_nr = UINT64_MAX / + sizeof(struct branch_entry); - data->branch_stack = (struct branch_stack *)array; - array++; /* nr */ + OVERFLOW_CHECK_u64(array); + data->branch_stack = (struct branch_stack *)array++; + if (data->branch_stack->nr > max_branch_nr) + return -EFAULT; sz = data->branch_stack->nr * sizeof(struct branch_entry); - sz /= sizeof(u64); - array += sz; + OVERFLOW_CHECK(array, sz, max_size); + array = (void *)array + sz; } if (type & PERF_SAMPLE_REGS_USER) { - /* First u64 tells us if we have any regs in sample. */ - u64 avail = *array++; + OVERFLOW_CHECK_u64(array); + data->user_regs.abi = *array; + array++; + + if (data->user_regs.abi) { + u64 regs_user = evsel->attr.sample_regs_user; - if (avail) { + sz = hweight_long(regs_user) * sizeof(u64); + OVERFLOW_CHECK(array, sz, max_size); data->user_regs.regs = (u64 *)array; - array += hweight_long(regs_user); + array = (void *)array + sz; } } if (type & PERF_SAMPLE_STACK_USER) { - u64 size = *array++; + OVERFLOW_CHECK_u64(array); + sz = *array++; data->user_stack.offset = ((char *)(array - 1) - (char *) event); - if (!size) { + if (!sz) { data->user_stack.size = 0; } else { + OVERFLOW_CHECK(array, sz, max_size); data->user_stack.data = (char *)array; - array += size / sizeof(*array); + array = (void *)array + sz; + OVERFLOW_CHECK_u64(array); data->user_stack.size = *array++; + if (WARN_ONCE(data->user_stack.size > sz, + "user stack dump failure\n")) + return -EFAULT; } } data->weight = 0; if (type & PERF_SAMPLE_WEIGHT) { + OVERFLOW_CHECK_u64(array); data->weight = *array; array++; } data->data_src = PERF_MEM_DATA_SRC_NONE; if (type & PERF_SAMPLE_DATA_SRC) { + OVERFLOW_CHECK_u64(array); data->data_src = *array; array++; } + data->transaction = 0; + if (type & PERF_SAMPLE_TRANSACTION) { + OVERFLOW_CHECK_u64(array); + data->transaction = *array; + array++; + } + return 0; } +size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, + u64 sample_regs_user, u64 read_format) +{ + size_t sz, result = sizeof(struct sample_event); + + if (type & PERF_SAMPLE_IDENTIFIER) + result += sizeof(u64); + + if (type & PERF_SAMPLE_IP) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TIME) + result += sizeof(u64); + + if (type & PERF_SAMPLE_ADDR) + result += sizeof(u64); + + if (type & PERF_SAMPLE_ID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_STREAM_ID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_CPU) + result += sizeof(u64); + + if (type & PERF_SAMPLE_PERIOD) + result += sizeof(u64); + + if (type & PERF_SAMPLE_READ) { + result += sizeof(u64); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + result += sizeof(u64); + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + result += sizeof(u64); + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + sz = sample->read.group.nr * + sizeof(struct sample_read_value); + result += sz; + } else { + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + sz = (sample->callchain->nr + 1) * sizeof(u64); + result += sz; + } + + if (type & PERF_SAMPLE_RAW) { + result += sizeof(u32); + result += sample->raw_size; + } + + if (type & PERF_SAMPLE_BRANCH_STACK) { + sz = sample->branch_stack->nr * sizeof(struct branch_entry); + sz += sizeof(u64); + result += sz; + } + + if (type & PERF_SAMPLE_REGS_USER) { + if (sample->user_regs.abi) { + result += sizeof(u64); + sz = hweight_long(sample_regs_user) * sizeof(u64); + result += sz; + } else { + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + sz = sample->user_stack.size; + result += sizeof(u64); + if (sz) { + result += sz; + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_WEIGHT) + result += sizeof(u64); + + if (type & PERF_SAMPLE_DATA_SRC) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TRANSACTION) + result += sizeof(u64); + + return result; +} + int perf_event__synthesize_sample(union perf_event *event, u64 type, + u64 sample_regs_user, u64 read_format, const struct perf_sample *sample, bool swapped) { u64 *array; - + size_t sz; /* * used for cross-endian analysis. See git commit 65014ab3 * for why this goofiness is needed. @@ -1203,8 +1599,13 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, array = event->sample.array; + if (type & PERF_SAMPLE_IDENTIFIER) { + *array = sample->id; + array++; + } + if (type & PERF_SAMPLE_IP) { - event->ip.ip = sample->ip; + *array = sample->ip; array++; } @@ -1262,6 +1663,102 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, array++; } + if (type & PERF_SAMPLE_READ) { + if (read_format & PERF_FORMAT_GROUP) + *array = sample->read.group.nr; + else + *array = sample->read.one.value; + array++; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + *array = sample->read.time_enabled; + array++; + } + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + *array = sample->read.time_running; + array++; + } + + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + sz = sample->read.group.nr * + sizeof(struct sample_read_value); + memcpy(array, sample->read.group.values, sz); + array = (void *)array + sz; + } else { + *array = sample->read.one.id; + array++; + } + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + sz = (sample->callchain->nr + 1) * sizeof(u64); + memcpy(array, sample->callchain, sz); + array = (void *)array + sz; + } + + if (type & PERF_SAMPLE_RAW) { + u.val32[0] = sample->raw_size; + if (WARN_ONCE(swapped, + "Endianness of raw data not corrected!\n")) { + /* + * Inverse of what is done in perf_evsel__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 = (void *)array + sizeof(u32); + + memcpy(array, sample->raw_data, sample->raw_size); + array = (void *)array + sample->raw_size; + } + + if (type & PERF_SAMPLE_BRANCH_STACK) { + sz = sample->branch_stack->nr * sizeof(struct branch_entry); + sz += sizeof(u64); + memcpy(array, sample->branch_stack, sz); + array = (void *)array + sz; + } + + if (type & PERF_SAMPLE_REGS_USER) { + if (sample->user_regs.abi) { + *array++ = sample->user_regs.abi; + sz = hweight_long(sample_regs_user) * sizeof(u64); + memcpy(array, sample->user_regs.regs, sz); + array = (void *)array + sz; + } else { + *array++ = 0; + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + sz = sample->user_stack.size; + *array++ = sz; + if (sz) { + memcpy(array, sample->user_stack.data, sz); + array = (void *)array + sz; + *array++ = sz; + } + } + + if (type & PERF_SAMPLE_WEIGHT) { + *array = sample->weight; + array++; + } + + if (type & PERF_SAMPLE_DATA_SRC) { + *array = sample->data_src; + array++; + } + + if (type & PERF_SAMPLE_TRANSACTION) { + *array = sample->transaction; + array++; + } + return 0; } @@ -1391,6 +1888,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value) bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), + bit_name(IDENTIFIER), { .name = NULL, } }; #undef bit_name @@ -1458,6 +1956,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, if_print(exclude_hv); if_print(exclude_idle); if_print(mmap); + if_print(mmap2); if_print(comm); if_print(freq); if_print(inherit_stat); @@ -1482,7 +1981,7 @@ out: bool perf_evsel__fallback(struct perf_evsel *evsel, int err, char *msg, size_t msgsize) { - if ((err == ENOENT || err == ENXIO) && + if ((err == ENOENT || err == ENXIO || err == ENODEV) && evsel->attr.type == PERF_TYPE_HARDWARE && evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) { /* diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 3f156ccc1acb..64ec8e1a7a28 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -38,6 +38,9 @@ struct perf_sample_id { struct hlist_node node; u64 id; struct perf_evsel *evsel; + + /* Holds total ID period value for PERF_SAMPLE_READ processing. */ + u64 period; }; /** struct perf_evsel - event selector @@ -45,6 +48,12 @@ struct perf_sample_id { * @name - Can be set to retain the original event name passed by the user, * so that when showing results in tools such as 'perf stat', we * show the name used, not some alias. + * @id_pos: the position of the event id (PERF_SAMPLE_ID or + * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of + * struct sample_event + * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or + * PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all + * is used there is an id sample appended to non-sample events */ struct perf_evsel { struct list_head node; @@ -65,17 +74,17 @@ struct perf_evsel { off_t id_offset; }; struct cgroup_sel *cgrp; - struct { - void *func; - void *data; - } handler; + void *handler; struct cpu_map *cpus; unsigned int sample_size; + int id_pos; + int is_pos; bool supported; bool needs_swap; /* parse modifier helper */ int exclude_GH; int nr_members; + int sample_read; struct perf_evsel *leader; char *group_name; }; @@ -100,6 +109,9 @@ void perf_evsel__delete(struct perf_evsel *evsel); void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts); +int __perf_evsel__sample_size(u64 sample_type); +void perf_evsel__calc_id_pos(struct perf_evsel *evsel); + bool perf_evsel__is_cache_op_valid(u8 type, u8 op); #define PERF_EVSEL__MAX_ALIASES 8 @@ -138,10 +150,12 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, #define perf_evsel__reset_sample_bit(evsel, bit) \ __perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit) -void perf_evsel__set_sample_id(struct perf_evsel *evsel); +void perf_evsel__set_sample_id(struct perf_evsel *evsel, + bool use_sample_identifier); int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, const char *filter); +int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus); @@ -180,6 +194,12 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1, (e1->attr.config == e2->attr.config); } +#define perf_evsel__cmp(a, b) \ + ((a) && \ + (b) && \ + (a)->attr.type == (b)->attr.type && \ + (a)->attr.config == (b)->attr.config) + int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale); diff --git a/tools/perf/util/fs.c b/tools/perf/util/fs.c new file mode 100644 index 000000000000..f5be1f26e724 --- /dev/null +++ b/tools/perf/util/fs.c @@ -0,0 +1,119 @@ + +/* TODO merge/factor into tools/lib/lk/debugfs.c */ + +#include "util.h" +#include "util/fs.h" + +static const char * const sysfs__fs_known_mountpoints[] = { + "/sys", + 0, +}; + +static const char * const procfs__known_mountpoints[] = { + "/proc", + 0, +}; + +struct fs { + const char *name; + const char * const *mounts; + char path[PATH_MAX + 1]; + bool found; + long magic; +}; + +enum { + FS__SYSFS = 0, + FS__PROCFS = 1, +}; + +static struct fs fs__entries[] = { + [FS__SYSFS] = { + .name = "sysfs", + .mounts = sysfs__fs_known_mountpoints, + .magic = SYSFS_MAGIC, + }, + [FS__PROCFS] = { + .name = "proc", + .mounts = procfs__known_mountpoints, + .magic = PROC_SUPER_MAGIC, + }, +}; + +static bool fs__read_mounts(struct fs *fs) +{ + bool found = false; + char type[100]; + FILE *fp; + + fp = fopen("/proc/mounts", "r"); + if (fp == NULL) + return NULL; + + while (!found && + fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n", + fs->path, type) == 2) { + + if (strcmp(type, fs->name) == 0) + found = true; + } + + fclose(fp); + return fs->found = found; +} + +static int fs__valid_mount(const char *fs, long magic) +{ + struct statfs st_fs; + + if (statfs(fs, &st_fs) < 0) + return -ENOENT; + else if (st_fs.f_type != magic) + return -ENOENT; + + return 0; +} + +static bool fs__check_mounts(struct fs *fs) +{ + const char * const *ptr; + + ptr = fs->mounts; + while (*ptr) { + if (fs__valid_mount(*ptr, fs->magic) == 0) { + fs->found = true; + strcpy(fs->path, *ptr); + return true; + } + ptr++; + } + + return false; +} + +static const char *fs__get_mountpoint(struct fs *fs) +{ + if (fs__check_mounts(fs)) + return fs->path; + + return fs__read_mounts(fs) ? fs->path : NULL; +} + +static const char *fs__mountpoint(int idx) +{ + struct fs *fs = &fs__entries[idx]; + + if (fs->found) + return (const char *)fs->path; + + return fs__get_mountpoint(fs); +} + +#define FS__MOUNTPOINT(name, idx) \ +const char *name##__mountpoint(void) \ +{ \ + return fs__mountpoint(idx); \ +} + +FS__MOUNTPOINT(sysfs, FS__SYSFS); +FS__MOUNTPOINT(procfs, FS__PROCFS); diff --git a/tools/perf/util/fs.h b/tools/perf/util/fs.h new file mode 100644 index 000000000000..5e09ce1bab0e --- /dev/null +++ b/tools/perf/util/fs.h @@ -0,0 +1,7 @@ +#ifndef __PERF_FS +#define __PERF_FS + +const char *sysfs__mountpoint(void); +const char *procfs__mountpoint(void); + +#endif /* __PERF_FS */ diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index 3ac38031d534..36a885d2cd22 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -22,7 +22,7 @@ do }' "Documentation/perf-$cmd.txt" done -echo "#ifdef LIBELF_SUPPORT" +echo "#ifdef HAVE_LIBELF_SUPPORT" sed -n -e 's/^perf-\([^ ]*\)[ ].* full.*/\1/p' command-list.txt | sort | while read cmd @@ -35,5 +35,5 @@ do p }' "Documentation/perf-$cmd.txt" done -echo "#endif /* LIBELF_SUPPORT */" +echo "#endif /* HAVE_LIBELF_SUPPORT */" echo "};" diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index a4dafbee2511..26d9520a0c1b 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -22,44 +22,13 @@ #include "vdso.h" #include "strbuf.h" #include "build-id.h" +#include "data.h" static bool no_buildid_cache = false; -static int trace_event_count; -static struct perf_trace_event_type *trace_events; - static u32 header_argc; static const char **header_argv; -int perf_header__push_event(u64 id, const char *name) -{ - struct perf_trace_event_type *nevents; - - if (strlen(name) > MAX_EVENT_NAME) - pr_warning("Event %s will be truncated\n", name); - - nevents = realloc(trace_events, (trace_event_count + 1) * sizeof(*trace_events)); - if (nevents == NULL) - return -ENOMEM; - trace_events = nevents; - - memset(&trace_events[trace_event_count], 0, sizeof(struct perf_trace_event_type)); - trace_events[trace_event_count].event_id = id; - strncpy(trace_events[trace_event_count].name, name, MAX_EVENT_NAME - 1); - trace_event_count++; - return 0; -} - -char *perf_header__find_event(u64 id) -{ - int i; - for (i = 0 ; i < trace_event_count; i++) { - if (trace_events[i].event_id == id) - return trace_events[i].name; - } - return NULL; -} - /* * magic2 = "PERFILE2" * must be a numerical value to let the endianness @@ -231,9 +200,11 @@ static int write_buildid(char *name, size_t name_len, u8 *build_id, return write_padded(fd, name, name_len + 1, len); } -static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, - u16 misc, int fd) +static int __dsos__write_buildid_table(struct list_head *head, + struct machine *machine, + pid_t pid, u16 misc, int fd) { + char nm[PATH_MAX]; struct dso *pos; dsos__for_each_with_build_id(pos, head) { @@ -247,6 +218,10 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, if (is_vdso_map(pos->short_name)) { name = (char *) VDSO__MAP_NAME; name_len = sizeof(VDSO__MAP_NAME) + 1; + } else if (dso__is_kcore(pos)) { + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + name_len = strlen(nm) + 1; } else { name = pos->long_name; name_len = pos->long_name_len + 1; @@ -272,10 +247,10 @@ static int machine__write_buildid_table(struct machine *machine, int fd) umisc = PERF_RECORD_MISC_GUEST_USER; } - err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid, - kmisc, fd); + err = __dsos__write_buildid_table(&machine->kernel_dsos, machine, + machine->pid, kmisc, fd); if (err == 0) - err = __dsos__write_buildid_table(&machine->user_dsos, + err = __dsos__write_buildid_table(&machine->user_dsos, machine, machine->pid, umisc, fd); return err; } @@ -407,23 +382,31 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *dso, const char *debugdir) +static int dso__cache_build_id(struct dso *dso, struct machine *machine, + const char *debugdir) { bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; bool is_vdso = is_vdso_map(dso->short_name); + char *name = dso->long_name; + char nm[PATH_MAX]; - return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), - dso->long_name, debugdir, - is_kallsyms, is_vdso); + if (dso__is_kcore(dso)) { + is_kallsyms = true; + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + } + return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, + debugdir, is_kallsyms, is_vdso); } -static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) +static int __dsos__cache_build_ids(struct list_head *head, + struct machine *machine, const char *debugdir) { struct dso *pos; int err = 0; dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, debugdir)) + if (dso__cache_build_id(pos, machine, debugdir)) err = -1; return err; @@ -431,8 +414,9 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) static int machine__cache_build_ids(struct machine *machine, const char *debugdir) { - int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir); + int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine, + debugdir); + ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir); return ret; } @@ -748,18 +732,19 @@ static int build_cpu_topo(struct cpu_topo *tp, int cpu) char filename[MAXPATHLEN]; char *buf = NULL, *p; size_t len = 0; + ssize_t sret; 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; + goto try_threads; + sret = getline(&buf, &len, fp); fclose(fp); + if (sret <= 0) + goto try_threads; p = strchr(buf, '\n'); if (p) @@ -775,7 +760,9 @@ static int build_cpu_topo(struct cpu_topo *tp, int cpu) buf = NULL; len = 0; } + ret = 0; +try_threads: sprintf(filename, THRD_SIB_FMT, cpu); fp = fopen(filename, "r"); if (!fp) @@ -1380,6 +1367,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) fprintf(fp, ", precise_ip = %d", evsel->attr.precise_ip); + fprintf(fp, ", attr_mmap2 = %d", evsel->attr.mmap2); + fprintf(fp, ", attr_mmap = %d", evsel->attr.mmap); + fprintf(fp, ", attr_mmap_data = %d", evsel->attr.mmap_data); if (evsel->ids) { fprintf(fp, ", id = {"); for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) { @@ -2200,7 +2190,7 @@ 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; + int fd = perf_data_file__fd(session->file); hd.fp = fp; hd.full = full; @@ -2257,7 +2247,7 @@ static int perf_header__adds_write(struct perf_header *header, sec_size = sizeof(*feat_sec) * nr_sections; - sec_start = header->data_offset + header->data_size; + sec_start = header->feat_offset; lseek(fd, sec_start + sec_size, SEEK_SET); for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { @@ -2304,6 +2294,7 @@ int perf_session__write_header(struct perf_session *session, struct perf_file_attr f_attr; struct perf_header *header = &session->header; struct perf_evsel *evsel; + u64 attr_offset; int err; lseek(fd, sizeof(f_header), SEEK_SET); @@ -2317,7 +2308,7 @@ int perf_session__write_header(struct perf_session *session, } } - header->attr_offset = lseek(fd, 0, SEEK_CUR); + attr_offset = lseek(fd, 0, SEEK_CUR); list_for_each_entry(evsel, &evlist->entries, node) { f_attr = (struct perf_file_attr){ @@ -2334,17 +2325,8 @@ int perf_session__write_header(struct perf_session *session, } } - header->event_offset = lseek(fd, 0, SEEK_CUR); - header->event_size = trace_event_count * sizeof(struct perf_trace_event_type); - if (trace_events) { - err = do_write(fd, trace_events, header->event_size); - if (err < 0) { - pr_debug("failed to write perf header events\n"); - return err; - } - } - header->data_offset = lseek(fd, 0, SEEK_CUR); + header->feat_offset = header->data_offset + header->data_size; if (at_exit) { err = perf_header__adds_write(header, evlist, fd); @@ -2357,17 +2339,14 @@ int perf_session__write_header(struct perf_session *session, .size = sizeof(f_header), .attr_size = sizeof(f_attr), .attrs = { - .offset = header->attr_offset, + .offset = attr_offset, .size = evlist->nr_entries * sizeof(f_attr), }, .data = { .offset = header->data_offset, .size = header->data_size, }, - .event_types = { - .offset = header->event_offset, - .size = header->event_size, - }, + /* event_types is ignored, store zeros */ }; memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features)); @@ -2417,7 +2396,7 @@ int perf_header__process_sections(struct perf_header *header, int fd, sec_size = sizeof(*feat_sec) * nr_sections; - lseek(fd, header->data_offset + header->data_size, SEEK_SET); + lseek(fd, header->feat_offset, SEEK_SET); err = perf_header__getbuffer64(header, fd, feat_sec, sec_size); if (err < 0) @@ -2523,6 +2502,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, /* check for legacy format */ ret = memcmp(&magic, __perf_magic1, sizeof(magic)); if (ret == 0) { + ph->version = PERF_HEADER_VERSION_1; pr_debug("legacy perf.data format\n"); if (is_pipe) return try_all_pipe_abis(hdr_sz, ph); @@ -2544,6 +2524,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, return -1; ph->needs_swap = true; + ph->version = PERF_HEADER_VERSION_2; return 0; } @@ -2614,10 +2595,9 @@ int perf_file_header__read(struct perf_file_header *header, memcpy(&ph->adds_features, &header->adds_features, sizeof(ph->adds_features)); - ph->event_offset = header->event_types.offset; - ph->event_size = header->event_types.size; ph->data_offset = header->data.offset; ph->data_size = header->data.size; + ph->feat_offset = header->data.offset + header->data.size; return 0; } @@ -2666,19 +2646,18 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, return 0; } -static int perf_header__read_pipe(struct perf_session *session, int fd) +static int perf_header__read_pipe(struct perf_session *session) { struct perf_header *header = &session->header; struct perf_pipe_file_header f_header; - if (perf_file_header__read_pipe(&f_header, header, fd, + if (perf_file_header__read_pipe(&f_header, header, + perf_data_file__fd(session->file), session->repipe) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; } - session->fd = fd; - return 0; } @@ -2772,24 +2751,38 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, return 0; } -int perf_session__read_header(struct perf_session *session, int fd) +int perf_session__read_header(struct perf_session *session) { + struct perf_data_file *file = session->file; struct perf_header *header = &session->header; struct perf_file_header f_header; struct perf_file_attr f_attr; u64 f_id; int nr_attrs, nr_ids, i, j; + int fd = perf_data_file__fd(file); session->evlist = perf_evlist__new(); if (session->evlist == NULL) return -ENOMEM; - if (session->fd_pipe) - return perf_header__read_pipe(session, fd); + if (perf_data_file__is_pipe(file)) + return perf_header__read_pipe(session); if (perf_file_header__read(&f_header, header, fd) < 0) return -EINVAL; + /* + * Sanity check that perf.data was written cleanly; data size is + * initialized to 0 and updated only if the on_exit function is run. + * If data size is still 0 then the file contains only partial + * information. Just warn user and process it as much as it can. + */ + if (f_header.data.size == 0) { + pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n" + "Was the 'perf record' command properly terminated?\n", + file->path); + } + nr_attrs = f_header.attrs.size / f_header.attr_size; lseek(fd, f_header.attrs.offset, SEEK_SET); @@ -2839,22 +2832,9 @@ int perf_session__read_header(struct perf_session *session, int fd) symbol_conf.nr_events = nr_attrs; - if (f_header.event_types.size) { - lseek(fd, f_header.event_types.offset, SEEK_SET); - trace_events = malloc(f_header.event_types.size); - if (trace_events == NULL) - return -ENOMEM; - if (perf_header__getbuffer64(header, fd, trace_events, - f_header.event_types.size)) - goto out_errno; - trace_event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); - } - perf_header__process_sections(header, fd, &session->pevent, perf_file_section__process); - lseek(fd, header->data_offset, SEEK_SET); - if (perf_evlist__prepare_tracepoint_events(session->evlist, session->pevent)) goto out_delete_evlist; @@ -2922,7 +2902,8 @@ int perf_event__synthesize_attrs(struct perf_tool *tool, return err; } -int perf_event__process_attr(union perf_event *event, +int perf_event__process_attr(struct perf_tool *tool __maybe_unused, + union perf_event *event, struct perf_evlist **pevlist) { u32 i, ids, n_ids; @@ -2961,64 +2942,6 @@ int perf_event__process_attr(union perf_event *event, return 0; } -int perf_event__synthesize_event_type(struct perf_tool *tool, - u64 event_id, char *name, - perf_event__handler_t process, - struct machine *machine) -{ - union perf_event ev; - size_t size = 0; - int err = 0; - - memset(&ev, 0, sizeof(ev)); - - ev.event_type.event_type.event_id = event_id; - memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME); - strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1); - - ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE; - size = strlen(ev.event_type.event_type.name); - size = PERF_ALIGN(size, sizeof(u64)); - ev.event_type.header.size = sizeof(ev.event_type) - - (sizeof(ev.event_type.event_type.name) - size); - - err = process(tool, &ev, NULL, machine); - - return err; -} - -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; - - for (i = 0; i < trace_event_count; i++) { - type = &trace_events[i]; - - err = perf_event__synthesize_event_type(tool, type->event_id, - type->name, process, - machine); - if (err) { - pr_debug("failed to create perf header event type\n"); - return err; - } - } - - return err; -} - -int perf_event__process_event_type(struct perf_tool *tool __maybe_unused, - union perf_event *event) -{ - if (perf_header__push_event(event->event_type.event_type.event_id, - event->event_type.event_type.name) < 0) - return -ENOMEM; - - return 0; -} - int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct perf_evlist *evlist, perf_event__handler_t process) @@ -3065,22 +2988,24 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, return aligned_size; } -int perf_event__process_tracing_data(union perf_event *event, +int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused, + union perf_event *event, struct perf_session *session) { ssize_t size_read, padding, size = event->tracing_data.size; - off_t offset = lseek(session->fd, 0, SEEK_CUR); + int fd = perf_data_file__fd(session->file); + off_t offset = lseek(fd, 0, SEEK_CUR); char buf[BUFSIZ]; /* setup for reading amidst mmap */ - lseek(session->fd, offset + sizeof(struct tracing_data_event), + lseek(fd, offset + sizeof(struct tracing_data_event), SEEK_SET); - size_read = trace_report(session->fd, &session->pevent, + size_read = trace_report(fd, &session->pevent, session->repipe); padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read; - if (readn(session->fd, buf, padding) < 0) { + if (readn(fd, buf, padding) < 0) { pr_err("%s: reading input file", __func__); return -1; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 16a3e83c584e..307c9aed972e 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -34,6 +34,11 @@ enum { HEADER_FEAT_BITS = 256, }; +enum perf_header_version { + PERF_HEADER_VERSION_1, + PERF_HEADER_VERSION_2, +}; + struct perf_file_section { u64 offset; u64 size; @@ -45,6 +50,7 @@ struct perf_file_header { u64 attr_size; struct perf_file_section attrs; struct perf_file_section data; + /* event_types is ignored */ struct perf_file_section event_types; DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); }; @@ -84,28 +90,24 @@ struct perf_session_env { }; struct perf_header { - bool needs_swap; - s64 attr_offset; - u64 data_offset; - u64 data_size; - u64 event_offset; - u64 event_size; + enum perf_header_version version; + bool needs_swap; + u64 data_offset; + u64 data_size; + u64 feat_offset; DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); - struct perf_session_env env; + struct perf_session_env env; }; struct perf_evlist; struct perf_session; -int perf_session__read_header(struct perf_session *session, int fd); +int perf_session__read_header(struct perf_session *session); int perf_session__write_header(struct perf_session *session, struct perf_evlist *evlist, int fd, bool at_exit); int perf_header__write_pipe(int fd); -int perf_header__push_event(u64 id, const char *name); -char *perf_header__find_event(u64 id); - 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); @@ -130,22 +132,14 @@ int perf_event__synthesize_attr(struct perf_tool *tool, 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(struct perf_tool *tool, - u64 event_id, char *name, - perf_event__handler_t process, - 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__process_attr(struct perf_tool *tool, union perf_event *event, + struct perf_evlist **pevlist); 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, +int perf_event__process_tracing_data(struct perf_tool *tool, + union perf_event *event, struct perf_session *session); int perf_event__synthesize_build_id(struct perf_tool *tool, diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index b11a6cfdb414..822903eaa201 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -24,7 +24,8 @@ enum hist_filter { struct callchain_param callchain_param = { .mode = CHAIN_GRAPH_REL, .min_percent = 0.5, - .order = ORDER_CALLEE + .order = ORDER_CALLEE, + .key = CCKEY_FUNCTION }; u16 hists__col_len(struct hists *hists, enum hist_column col) @@ -159,6 +160,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3); hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12); hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12); + + if (h->transaction) + hists__new_col_len(hists, HISTC_TRANSACTION, + hist_entry__transaction_len()); } void hists__output_recalc_col_len(struct hists *hists, int max_rows) @@ -345,7 +350,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists, struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; - int cmp; + int64_t cmp; p = &hists->entries_in->rb_node; @@ -394,6 +399,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists, if (!he) return NULL; + hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, hists->entries_in); out: @@ -401,74 +407,16 @@ out: return he; } -struct hist_entry *__hists__add_mem_entry(struct hists *self, - struct addr_location *al, - struct symbol *sym_parent, - struct mem_info *mi, - u64 period, - u64 weight) -{ - struct hist_entry entry = { - .thread = al->thread, - .ms = { - .map = al->map, - .sym = al->sym, - }, - .stat = { - .period = period, - .weight = weight, - .nr_events = 1, - }, - .cpu = al->cpu, - .ip = al->addr, - .level = al->level, - .parent = sym_parent, - .filtered = symbol__parent_filter(sym_parent), - .hists = self, - .mem_info = mi, - .branch_info = NULL, - }; - return add_hist_entry(self, &entry, al, period, weight); -} - -struct hist_entry *__hists__add_branch_entry(struct hists *self, - struct addr_location *al, - struct symbol *sym_parent, - struct branch_info *bi, - u64 period, - u64 weight) -{ - struct hist_entry entry = { - .thread = al->thread, - .ms = { - .map = bi->to.map, - .sym = bi->to.sym, - }, - .cpu = al->cpu, - .ip = bi->to.addr, - .level = al->level, - .stat = { - .period = period, - .nr_events = 1, - .weight = weight, - }, - .parent = sym_parent, - .filtered = symbol__parent_filter(sym_parent), - .branch_info = bi, - .hists = self, - .mem_info = NULL, - }; - - return add_hist_entry(self, &entry, al, period, weight); -} - -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, - u64 weight) + struct symbol *sym_parent, + struct branch_info *bi, + struct mem_info *mi, + u64 period, u64 weight, u64 transaction) { struct hist_entry entry = { .thread = al->thread, + .comm = thread__comm(al->thread), .ms = { .map = al->map, .sym = al->sym, @@ -477,18 +425,19 @@ struct hist_entry *__hists__add_entry(struct hists *self, .ip = al->addr, .level = al->level, .stat = { - .period = period, .nr_events = 1, + .period = period, .weight = weight, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent), - .hists = self, - .branch_info = NULL, - .mem_info = NULL, + .hists = hists, + .branch_info = bi, + .mem_info = mi, + .transaction = transaction, }; - return add_hist_entry(self, &entry, al, period, weight); + return add_hist_entry(hists, &entry, al, period, weight); } int64_t @@ -529,6 +478,7 @@ void hist_entry__free(struct hist_entry *he) { free(he->branch_info); free(he->mem_info); + free_srcline(he->srcline); free(he); } @@ -597,7 +547,7 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he) hists__filter_entry_by_symbol(hists, he); } -void hists__collapse_resort(struct hists *hists) +void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) { struct rb_root *root; struct rb_node *next; @@ -610,6 +560,8 @@ void hists__collapse_resort(struct hists *hists) next = rb_first(root); while (next) { + if (session_done()) + break; n = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&n->rb_node_in); @@ -622,6 +574,8 @@ void hists__collapse_resort(struct hists *hists) */ hists__apply_filters(hists, n); } + if (prog) + ui_progress__update(prog, 1); } } @@ -881,7 +835,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; - int cmp; + int64_t cmp; if (sort__need_collapse) root = &hists->entries_collapsed; @@ -912,6 +866,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, root); hists__inc_nr_entries(hists, he); + he->dummy = true; } out: return he; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 2d3790fd99bb..b621347a1585 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -5,6 +5,8 @@ #include <pthread.h> #include "callchain.h" #include "header.h" +#include "color.h" +#include "ui/progress.h" extern struct callchain_param callchain_param; @@ -45,6 +47,8 @@ enum hist_column { HISTC_CPU, HISTC_SRCLINE, HISTC_MISPREDICT, + HISTC_IN_TX, + HISTC_ABORT, HISTC_SYMBOL_FROM, HISTC_SYMBOL_TO, HISTC_DSO_FROM, @@ -57,6 +61,7 @@ enum hist_column { HISTC_MEM_TLB, HISTC_MEM_LVL, HISTC_MEM_SNOOP, + HISTC_TRANSACTION, HISTC_NR_COLS, /* Last entry */ }; @@ -79,54 +84,43 @@ struct hists { u16 col_len[HISTC_NR_COLS]; }; -struct hist_entry *__hists__add_entry(struct hists *self, +struct hist_entry *__hists__add_entry(struct hists *hists, struct addr_location *al, - struct symbol *parent, u64 period, - u64 weight); + struct symbol *parent, + struct branch_info *bi, + struct mem_info *mi, u64 period, + u64 weight, u64 transaction); 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__sort_snprintf(struct hist_entry *self, char *bf, size_t size, +int hist_entry__transaction_len(void); +int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size, struct hists *hists); void hist_entry__free(struct hist_entry *); -struct hist_entry *__hists__add_branch_entry(struct hists *self, - struct addr_location *al, - struct symbol *sym_parent, - struct branch_info *bi, - u64 period, - u64 weight); - -struct hist_entry *__hists__add_mem_entry(struct hists *self, - struct addr_location *al, - struct symbol *sym_parent, - struct mem_info *mi, - u64 period, - u64 weight); - -void hists__output_resort(struct hists *self); -void hists__collapse_resort(struct hists *self); +void hists__output_resort(struct hists *hists); +void hists__collapse_resort(struct hists *hists, struct ui_progress *prog); void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); void hists__output_recalc_col_len(struct hists *hists, int max_rows); void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h); -void hists__inc_nr_events(struct hists *self, u32 type); +void hists__inc_nr_events(struct hists *hists, u32 type); void events_stats__inc(struct events_stats *stats, u32 type); size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); -size_t hists__fprintf(struct hists *self, bool show_header, int max_rows, +size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, 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); +int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr); +int hist_entry__annotate(struct hist_entry *he, size_t privsize); void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); void hists__filter_by_symbol(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); -bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len); +u16 hists__col_len(struct hists *hists, enum hist_column col); +void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len); +bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len); void hists__reset_col_len(struct hists *hists); void hists__calc_col_len(struct hists *hists, struct hist_entry *he); @@ -141,10 +135,12 @@ struct perf_hpp { }; struct perf_hpp_fmt { - int (*header)(struct perf_hpp *hpp); - int (*width)(struct perf_hpp *hpp); - int (*color)(struct perf_hpp *hpp, struct hist_entry *he); - int (*entry)(struct perf_hpp *hpp, struct hist_entry *he); + int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp); + int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp); + int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he); + int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he); struct list_head list; }; @@ -157,7 +153,7 @@ extern struct list_head perf_hpp__list; extern struct perf_hpp_fmt perf_hpp__format[]; enum { - PERF_HPP__BASELINE, + /* Matches perf_hpp__format array. */ PERF_HPP__OVERHEAD, PERF_HPP__OVERHEAD_SYS, PERF_HPP__OVERHEAD_US, @@ -165,11 +161,6 @@ enum { PERF_HPP__OVERHEAD_GUEST_US, PERF_HPP__SAMPLES, PERF_HPP__PERIOD, - PERF_HPP__PERIOD_BASELINE, - PERF_HPP__DELTA, - PERF_HPP__RATIO, - PERF_HPP__WEIGHTED_DIFF, - PERF_HPP__FORMULA, PERF_HPP__MAX_INDEX }; @@ -177,8 +168,18 @@ enum { void perf_hpp__init(void); void perf_hpp__column_register(struct perf_hpp_fmt *format); void perf_hpp__column_enable(unsigned col); -int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, - bool color); + +static inline size_t perf_hpp__use_color(void) +{ + return !symbol_conf.field_sep; +} + +static inline size_t perf_hpp__color_overhead(void) +{ + return perf_hpp__use_color() ? + (COLOR_MAXLEN + sizeof(PERF_COLOR_RESET)) * PERF_HPP__MAX_INDEX + : 0; +} struct perf_evlist; @@ -188,7 +189,7 @@ struct hist_browser_timer { int refresh; }; -#ifdef SLANG_SUPPORT +#ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, struct hist_browser_timer *hbt); @@ -209,12 +210,9 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, return 0; } -static inline int hist_entry__tui_annotate(struct hist_entry *self - __maybe_unused, - struct perf_evsel *evsel - __maybe_unused, - struct hist_browser_timer *hbt - __maybe_unused) +static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct hist_browser_timer *hbt __maybe_unused) { return 0; } @@ -229,27 +227,5 @@ static inline int script_browse(const char *script_opt __maybe_unused) #define K_SWITCH_INPUT_DATA -3000 #endif -#ifdef GTK2_SUPPORT -int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help, - struct hist_browser_timer *hbt __maybe_unused, - float min_pcnt); -#else -static inline -int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused, - const char *help __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused, - float min_pcnt __maybe_unused) -{ - return 0; -} -#endif - -unsigned int hists__sort_list_width(struct hists *self); - -double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair); -double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair); -s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair); -int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair, - char *buf, size_t size); -double perf_diff__period_percent(struct hist_entry *he, u64 period); +unsigned int hists__sort_list_width(struct hists *hists); #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h index cf6727e99c44..8f149655f497 100644 --- a/tools/perf/util/include/dwarf-regs.h +++ b/tools/perf/util/include/dwarf-regs.h @@ -1,7 +1,7 @@ #ifndef _PERF_DWARF_REGS_H_ #define _PERF_DWARF_REGS_H_ -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT const char *get_arch_regstr(unsigned int n); #endif diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h index 96b919dae11c..b003ad7200b2 100644 --- a/tools/perf/util/include/linux/compiler.h +++ b/tools/perf/util/include/linux/compiler.h @@ -2,20 +2,29 @@ #define _PERF_LINUX_COMPILER_H_ #ifndef __always_inline -#define __always_inline inline +# define __always_inline inline __attribute__((always_inline)) #endif + #define __user + #ifndef __attribute_const__ -#define __attribute_const__ +# define __attribute_const__ #endif #ifndef __maybe_unused -#define __maybe_unused __attribute__((unused)) +# define __maybe_unused __attribute__((unused)) +#endif + +#ifndef __packed +# define __packed __attribute__((__packed__)) #endif -#define __packed __attribute__((__packed__)) #ifndef __force -#define __force +# define __force +#endif + +#ifndef __weak +# define __weak __attribute__((weak)) #endif #endif diff --git a/tools/perf/util/include/linux/magic.h b/tools/perf/util/include/linux/magic.h index 58b64ed4da12..07d63cf3e0f6 100644 --- a/tools/perf/util/include/linux/magic.h +++ b/tools/perf/util/include/linux/magic.h @@ -9,4 +9,8 @@ #define SYSFS_MAGIC 0x62656572 #endif +#ifndef PROC_SUPER_MAGIC +#define PROC_SUPER_MAGIC 0x9fa0 +#endif + #endif diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h index 6f19c548ecc0..97a800738226 100644 --- a/tools/perf/util/include/linux/string.h +++ b/tools/perf/util/include/linux/string.h @@ -1,3 +1,4 @@ #include <string.h> void *memdup(const void *src, size_t len); +int str_append(char **s, int *len, const char *a); diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c index 11a8d86f7fea..89715b64a315 100644 --- a/tools/perf/util/intlist.c +++ b/tools/perf/util/intlist.c @@ -20,6 +20,7 @@ static struct rb_node *intlist__node_new(struct rblist *rblist __maybe_unused, if (node != NULL) { node->i = i; + node->priv = NULL; rc = &node->rb_node; } @@ -57,22 +58,36 @@ void intlist__remove(struct intlist *ilist, struct int_node *node) rblist__remove_node(&ilist->rblist, &node->rb_node); } -struct int_node *intlist__find(struct intlist *ilist, int i) +static struct int_node *__intlist__findnew(struct intlist *ilist, + int i, bool create) { - struct int_node *node; + struct int_node *node = NULL; struct rb_node *rb_node; if (ilist == NULL) return NULL; - node = NULL; - rb_node = rblist__find(&ilist->rblist, (void *)((long)i)); + if (create) + rb_node = rblist__findnew(&ilist->rblist, (void *)((long)i)); + else + rb_node = rblist__find(&ilist->rblist, (void *)((long)i)); + if (rb_node) node = container_of(rb_node, struct int_node, rb_node); return node; } +struct int_node *intlist__find(struct intlist *ilist, int i) +{ + return __intlist__findnew(ilist, i, false); +} + +struct int_node *intlist__findnew(struct intlist *ilist, int i) +{ + return __intlist__findnew(ilist, i, true); +} + static int intlist__parse_list(struct intlist *ilist, const char *s) { char *sep; diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h index 62351dad848f..aa6877d36858 100644 --- a/tools/perf/util/intlist.h +++ b/tools/perf/util/intlist.h @@ -9,6 +9,7 @@ struct int_node { struct rb_node rb_node; int i; + void *priv; }; struct intlist { @@ -23,6 +24,7 @@ int intlist__add(struct intlist *ilist, int i); struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx); struct int_node *intlist__find(struct intlist *ilist, int i); +struct int_node *intlist__findnew(struct intlist *ilist, int i); static inline bool intlist__has_entry(struct intlist *ilist, int i) { diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b2ecad6ec46b..ce034c183a7e 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -25,24 +25,44 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->kmaps.machine = machine; machine->pid = pid; + machine->symbol_filter = NULL; + machine->root_dir = strdup(root_dir); if (machine->root_dir == NULL) return -ENOMEM; if (pid != HOST_KERNEL_ID) { - struct thread *thread = machine__findnew_thread(machine, pid); + struct thread *thread = machine__findnew_thread(machine, 0, + pid); char comm[64]; if (thread == NULL) return -ENOMEM; snprintf(comm, sizeof(comm), "[guest/%d]", pid); - thread__set_comm(thread, comm); + thread__set_comm(thread, comm, 0); } return 0; } +struct machine *machine__new_host(void) +{ + struct machine *machine = malloc(sizeof(*machine)); + + if (machine != NULL) { + machine__init(machine, "", HOST_KERNEL_ID); + + if (machine__create_kernel_maps(machine) < 0) + goto out_delete; + } + + return machine; +out_delete: + free(machine); + return NULL; +} + static void dsos__delete(struct list_head *dsos) { struct dso *pos, *n; @@ -95,6 +115,7 @@ void machines__init(struct machines *machines) { machine__init(&machines->host, "", HOST_KERNEL_ID); machines->guests = RB_ROOT; + machines->symbol_filter = NULL; } void machines__exit(struct machines *machines) @@ -118,6 +139,8 @@ struct machine *machines__add(struct machines *machines, pid_t pid, return NULL; } + machine->symbol_filter = machines->symbol_filter; + while (*p != NULL) { parent = *p; pos = rb_entry(parent, struct machine, rb_node); @@ -133,6 +156,21 @@ struct machine *machines__add(struct machines *machines, pid_t pid, return machine; } +void machines__set_symbol_filter(struct machines *machines, + symbol_filter_t symbol_filter) +{ + struct rb_node *nd; + + machines->symbol_filter = symbol_filter; + machines->host.symbol_filter = symbol_filter; + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *machine = rb_entry(nd, struct machine, rb_node); + + machine->symbol_filter = symbol_filter; + } +} + struct machine *machines__find(struct machines *machines, pid_t pid) { struct rb_node **p = &machines->guests.rb_node; @@ -233,7 +271,8 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size) return; } -static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, +static struct thread *__machine__findnew_thread(struct machine *machine, + pid_t pid, pid_t tid, bool create) { struct rb_node **p = &machine->threads.rb_node; @@ -241,23 +280,28 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p struct thread *th; /* - * Font-end cache - PID lookups come in blocks, + * Front-end cache - TID lookups come in blocks, * so most of the time we dont have to look up * the full rbtree: */ - if (machine->last_match && machine->last_match->pid == pid) + if (machine->last_match && machine->last_match->tid == tid) { + if (pid && pid != machine->last_match->pid_) + machine->last_match->pid_ = pid; return machine->last_match; + } while (*p != NULL) { parent = *p; th = rb_entry(parent, struct thread, rb_node); - if (th->pid == pid) { + if (th->tid == tid) { machine->last_match = th; + if (pid && pid != th->pid_) + th->pid_ = pid; return th; } - if (pid < th->pid) + if (tid < th->tid) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -266,7 +310,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p if (!create) return NULL; - th = thread__new(pid); + th = thread__new(pid, tid); if (th != NULL) { rb_link_node(&th->rb_node, parent, p); rb_insert_color(&th->rb_node, &machine->threads); @@ -276,24 +320,28 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p return th; } -struct thread *machine__findnew_thread(struct machine *machine, pid_t pid) +struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, + pid_t tid) { - return __machine__findnew_thread(machine, pid, true); + return __machine__findnew_thread(machine, pid, tid, true); } -struct thread *machine__find_thread(struct machine *machine, pid_t pid) +struct thread *machine__find_thread(struct machine *machine, pid_t tid) { - return __machine__findnew_thread(machine, pid, false); + return __machine__findnew_thread(machine, 0, tid, false); } -int machine__process_comm_event(struct machine *machine, union perf_event *event) +int machine__process_comm_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample) { - struct thread *thread = machine__findnew_thread(machine, event->comm.tid); + struct thread *thread = machine__findnew_thread(machine, + event->comm.pid, + event->comm.tid); if (dump_trace) perf_event__fprintf_comm(event, stdout); - if (thread == NULL || thread__set_comm(thread, event->comm.comm)) { + if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) { dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); return -1; } @@ -302,7 +350,7 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event } int machine__process_lost_event(struct machine *machine __maybe_unused, - union perf_event *event) + union perf_event *event, struct perf_sample *sample __maybe_unused) { dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", event->lost.id, event->lost.lost); @@ -628,10 +676,8 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type, struct map *map = machine->vmlinux_maps[type]; int ret = dso__load_vmlinux_path(map->dso, map, filter); - if (ret > 0) { + if (ret > 0) dso__set_loaded(map->dso, type); - map__reloc_vmlinux(map); - } return ret; } @@ -748,72 +794,44 @@ static int machine__set_modules_path(struct machine *machine) return map_groups__set_modules_path_dir(&machine->kmaps, modules_path); } -static int machine__create_modules(struct machine *machine) +static int machine__create_module(void *arg, const char *name, u64 start) { - char *line = NULL; - size_t n; - FILE *file; + struct machine *machine = arg; struct map *map; + + map = machine__new_module(machine, start, name); + if (map == NULL) + return -1; + + dso__kernel_module_get_build_id(map->dso, machine->root_dir); + + return 0; +} + +static int machine__create_modules(struct machine *machine) +{ const char *modules; char path[PATH_MAX]; - if (machine__is_default_guest(machine)) + if (machine__is_default_guest(machine)) { modules = symbol_conf.default_guest_modules; - else { - sprintf(path, "%s/proc/modules", machine->root_dir); + } else { + snprintf(path, PATH_MAX, "%s/proc/modules", machine->root_dir); modules = path; } - if (symbol__restricted_filename(path, "/proc/modules")) + if (symbol__restricted_filename(modules, "/proc/modules")) return -1; - file = fopen(modules, "r"); - if (file == NULL) + if (modules__parse(modules, machine, machine__create_module)) return -1; - while (!feof(file)) { - char name[PATH_MAX]; - u64 start; - char *sep; - int line_len; - - line_len = getline(&line, &n, file); - if (line_len < 0) - break; - - if (!line) - goto out_failure; - - line[--line_len] = '\0'; /* \n */ - - sep = strrchr(line, 'x'); - if (sep == NULL) - continue; - - hex2u64(sep + 1, &start); - - sep = strchr(line, ' '); - if (sep == NULL) - continue; - - *sep = '\0'; - - snprintf(name, sizeof(name), "[%s]", line); - map = machine__new_module(machine, start, name); - if (map == NULL) - goto out_delete_line; - dso__kernel_module_get_build_id(map->dso, machine->root_dir); - } - - free(line); - fclose(file); + if (!machine__set_modules_path(machine)) + return 0; - return machine__set_modules_path(machine); + pr_debug("Problems setting modules path maps, continuing anyway...\n"); -out_delete_line: - free(line); -out_failure: - return -1; + return 0; } int machine__create_kernel_maps(struct machine *machine) @@ -858,6 +876,18 @@ static void machine__set_kernel_mmap_len(struct machine *machine, } } +static bool machine__uses_kcore(struct machine *machine) +{ + struct dso *dso; + + list_for_each_entry(dso, &machine->kernel_dsos, node) { + if (dso__is_kcore(dso)) + return true; + } + + return false; +} + static int machine__process_kernel_mmap_event(struct machine *machine, union perf_event *event) { @@ -866,6 +896,10 @@ static int machine__process_kernel_mmap_event(struct machine *machine, enum dso_kernel_type kernel_type; bool is_kernel_mmap; + /* If we have maps from kcore then we do not need or want any others */ + if (machine__uses_kcore(machine)) + return 0; + machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix)); if (machine__is_host(machine)) kernel_type = DSO_TYPE_KERNEL; @@ -950,7 +984,9 @@ out_problem: return -1; } -int machine__process_mmap_event(struct machine *machine, union perf_event *event) +int machine__process_mmap2_event(struct machine *machine, + union perf_event *event, + struct perf_sample *sample __maybe_unused) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct thread *thread; @@ -959,7 +995,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event int ret = 0; if (dump_trace) - perf_event__fprintf_mmap(event, stdout); + perf_event__fprintf_mmap2(event, stdout); if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || cpumode == PERF_RECORD_MISC_KERNEL) { @@ -969,7 +1005,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event return 0; } - thread = machine__findnew_thread(machine, event->mmap.pid); + thread = machine__findnew_thread(machine, event->mmap2.pid, + event->mmap2.pid); if (thread == NULL) goto out_problem; @@ -978,10 +1015,12 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event else type = MAP__FUNCTION; - map = map__new(&machine->user_dsos, event->mmap.start, - event->mmap.len, event->mmap.pgoff, - event->mmap.pid, event->mmap.filename, - type); + map = map__new(&machine->user_dsos, event->mmap2.start, + event->mmap2.len, event->mmap2.pgoff, + event->mmap2.pid, event->mmap2.maj, + event->mmap2.min, event->mmap2.ino, + event->mmap2.ino_generation, + event->mmap2.filename, type); if (map == NULL) goto out_problem; @@ -990,24 +1029,54 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event return 0; out_problem: - dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); + dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n"); return 0; } -int machine__process_fork_event(struct machine *machine, union perf_event *event) +int machine__process_mmap_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample __maybe_unused) { - struct thread *thread = machine__findnew_thread(machine, event->fork.tid); - struct thread *parent = machine__findnew_thread(machine, event->fork.ptid); + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct thread *thread; + struct map *map; + enum map_type type; + int ret = 0; if (dump_trace) - perf_event__fprintf_task(event, stdout); + perf_event__fprintf_mmap(event, stdout); - if (thread == NULL || parent == NULL || - thread__fork(thread, parent) < 0) { - dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); - return -1; + if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || + cpumode == PERF_RECORD_MISC_KERNEL) { + ret = machine__process_kernel_mmap_event(machine, event); + if (ret < 0) + goto out_problem; + return 0; } + thread = machine__findnew_thread(machine, event->mmap.pid, + event->mmap.pid); + if (thread == NULL) + goto out_problem; + + if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) + type = MAP__VARIABLE; + else + type = MAP__FUNCTION; + + map = map__new(&machine->user_dsos, event->mmap.start, + event->mmap.len, event->mmap.pgoff, + event->mmap.pid, 0, 0, 0, 0, + event->mmap.filename, + type); + + if (map == NULL) + goto out_problem; + + thread__insert_map(thread, map); + return 0; + +out_problem: + dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); return 0; } @@ -1022,7 +1091,34 @@ static void machine__remove_thread(struct machine *machine, struct thread *th) list_add_tail(&th->node, &machine->dead_threads); } -int machine__process_exit_event(struct machine *machine, union perf_event *event) +int machine__process_fork_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample) +{ + struct thread *thread = machine__find_thread(machine, event->fork.tid); + struct thread *parent = machine__findnew_thread(machine, + event->fork.ppid, + event->fork.ptid); + + /* if a thread currently exists for the thread id remove it */ + if (thread != NULL) + machine__remove_thread(machine, thread); + + thread = machine__findnew_thread(machine, event->fork.pid, + event->fork.tid); + if (dump_trace) + perf_event__fprintf_task(event, stdout); + + if (thread == NULL || parent == NULL || + thread__fork(thread, parent, sample->time) < 0) { + dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); + return -1; + } + + return 0; +} + +int machine__process_exit_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample __maybe_unused) { struct thread *thread = machine__find_thread(machine, event->fork.tid); @@ -1030,26 +1126,29 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event perf_event__fprintf_task(event, stdout); if (thread != NULL) - machine__remove_thread(machine, thread); + thread__exited(thread); return 0; } -int machine__process_event(struct machine *machine, union perf_event *event) +int machine__process_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample) { int ret; switch (event->header.type) { case PERF_RECORD_COMM: - ret = machine__process_comm_event(machine, event); break; + ret = machine__process_comm_event(machine, event, sample); break; case PERF_RECORD_MMAP: - ret = machine__process_mmap_event(machine, event); break; + ret = machine__process_mmap_event(machine, event, sample); break; + case PERF_RECORD_MMAP2: + ret = machine__process_mmap2_event(machine, event, sample); break; case PERF_RECORD_FORK: - ret = machine__process_fork_event(machine, event); break; + ret = machine__process_fork_event(machine, event, sample); break; case PERF_RECORD_EXIT: - ret = machine__process_exit_event(machine, event); break; + ret = machine__process_exit_event(machine, event, sample); break; case PERF_RECORD_LOST: - ret = machine__process_lost_event(machine, event); break; + ret = machine__process_lost_event(machine, event, sample); break; default: ret = -1; break; @@ -1058,11 +1157,10 @@ int machine__process_event(struct machine *machine, union perf_event *event) return ret; } -static bool symbol__match_parent_regex(struct symbol *sym) +static bool symbol__match_regex(struct symbol *sym, regex_t *regex) { - if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0)) + if (sym->name && !regexec(regex, sym->name, 0, NULL, 0)) return 1; - return 0; } @@ -1094,7 +1192,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread, * or else, the symbol is unknown */ thread__find_addr_location(thread, machine, m, MAP__FUNCTION, - ip, &al, NULL); + ip, &al); if (al.sym) goto found; } @@ -1112,8 +1210,8 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread, memset(&al, 0, sizeof(al)); - thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, &al, - NULL); + thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, + &al); ams->addr = addr; ams->al_addr = al.addr; ams->sym = al.sym; @@ -1159,11 +1257,13 @@ struct branch_info *machine__resolve_bstack(struct machine *machine, static int machine__resolve_callchain_sample(struct machine *machine, struct thread *thread, struct ip_callchain *chain, - struct symbol **parent) - + struct symbol **parent, + struct addr_location *root_al, + int max_stack) { u8 cpumode = PERF_RECORD_MISC_USER; - unsigned int i; + int chain_nr = min(max_stack, (int)chain->nr); + int i; int err; callchain_cursor_reset(&callchain_cursor); @@ -1173,7 +1273,7 @@ static int machine__resolve_callchain_sample(struct machine *machine, return 0; } - for (i = 0; i < chain->nr; i++) { + for (i = 0; i < chain_nr; i++) { u64 ip; struct addr_location al; @@ -1208,11 +1308,18 @@ static int machine__resolve_callchain_sample(struct machine *machine, al.filtered = false; thread__find_addr_location(thread, machine, cpumode, - MAP__FUNCTION, ip, &al, NULL); + MAP__FUNCTION, ip, &al); if (al.sym != NULL) { if (sort__has_parent && !*parent && - symbol__match_parent_regex(al.sym)) + symbol__match_regex(al.sym, &parent_regex)) *parent = al.sym; + else if (have_ignore_callees && root_al && + symbol__match_regex(al.sym, &ignore_callees_regex)) { + /* Treat this symbol as the root, + forgetting its callees. */ + *root_al = al; + callchain_cursor_reset(&callchain_cursor); + } if (!symbol_conf.use_callchain) break; } @@ -1237,15 +1344,15 @@ int machine__resolve_callchain(struct machine *machine, struct perf_evsel *evsel, struct thread *thread, struct perf_sample *sample, - struct symbol **parent) - + struct symbol **parent, + struct addr_location *root_al, + int max_stack) { int ret; - callchain_cursor_reset(&callchain_cursor); - ret = machine__resolve_callchain_sample(machine, thread, - sample->callchain, parent); + sample->callchain, parent, + root_al, max_stack); if (ret) return ret; @@ -1264,3 +1371,26 @@ int machine__resolve_callchain(struct machine *machine, sample); } + +int machine__for_each_thread(struct machine *machine, + int (*fn)(struct thread *thread, void *p), + void *priv) +{ + struct rb_node *nd; + struct thread *thread; + int rc = 0; + + for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { + thread = rb_entry(nd, struct thread, rb_node); + rc = fn(thread, priv); + if (rc != 0) + return rc; + } + + list_for_each_entry(thread, &machine->dead_threads, node) { + rc = fn(thread, priv); + if (rc != 0) + return rc; + } + return rc; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 77940680f1fc..2389ba81fafe 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -5,6 +5,7 @@ #include <linux/rbtree.h> #include "map.h" +struct addr_location; struct branch_stack; struct perf_evsel; struct perf_sample; @@ -28,6 +29,7 @@ struct machine { struct list_head kernel_dsos; struct map_groups kmaps; struct map *vmlinux_maps[MAP__NR_TYPES]; + symbol_filter_t symbol_filter; }; static inline @@ -36,20 +38,29 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type) return machine->vmlinux_maps[type]; } -struct thread *machine__find_thread(struct machine *machine, pid_t pid); - -int machine__process_comm_event(struct machine *machine, union perf_event *event); -int machine__process_exit_event(struct machine *machine, union perf_event *event); -int machine__process_fork_event(struct machine *machine, union perf_event *event); -int machine__process_lost_event(struct machine *machine, union perf_event *event); -int machine__process_mmap_event(struct machine *machine, union perf_event *event); -int machine__process_event(struct machine *machine, union perf_event *event); +struct thread *machine__find_thread(struct machine *machine, pid_t tid); + +int machine__process_comm_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_exit_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_fork_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_lost_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_mmap_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_mmap2_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); typedef void (*machine__process_t)(struct machine *machine, void *data); struct machines { struct machine host; struct rb_root guests; + symbol_filter_t symbol_filter; }; void machines__init(struct machines *machines); @@ -67,6 +78,10 @@ struct machine *machines__findnew(struct machines *machines, pid_t pid); void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size); char *machine__mmap_name(struct machine *machine, char *bf, size_t size); +void machines__set_symbol_filter(struct machines *machines, + symbol_filter_t symbol_filter); + +struct machine *machine__new_host(void); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); void machine__delete_dead_threads(struct machine *machine); @@ -83,7 +98,9 @@ int machine__resolve_callchain(struct machine *machine, struct perf_evsel *evsel, struct thread *thread, struct perf_sample *sample, - struct symbol **parent); + struct symbol **parent, + struct addr_location *root_al, + int max_stack); /* * Default guest kernel is defined by parameter --guestkallsyms @@ -99,7 +116,8 @@ static inline bool machine__is_host(struct machine *machine) return machine ? machine->pid == HOST_KERNEL_ID : false; } -struct thread *machine__findnew_thread(struct machine *machine, pid_t pid); +struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, + pid_t tid); size_t machine__fprintf(struct machine *machine, FILE *fp); @@ -156,4 +174,8 @@ void machines__destroy_kernel_maps(struct machines *machines); size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); +int machine__for_each_thread(struct machine *machine, + int (*fn)(struct thread *thread, void *p), + void *priv); + #endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 8bcdf9e54089..ef5bc913ca7a 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -48,7 +48,8 @@ void map__init(struct map *map, enum map_type type, } struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, - u64 pgoff, u32 pid, char *filename, + u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, + u64 ino_gen, char *filename, enum map_type type) { struct map *map = malloc(sizeof(*map)); @@ -62,6 +63,11 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, vdso = is_vdso_map(filename); no_dso = is_no_dso_memory(filename); + map->maj = d_maj; + map->min = d_min; + map->ino = ino; + map->ino_generation = ino_gen; + if (anon) { snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid); filename = newfilename; @@ -166,7 +172,7 @@ int map__load(struct map *map, symbol_filter_t filter) pr_warning(", continuing without symbols\n"); return -1; } else if (nr == 0) { -#ifdef LIBELF_SUPPORT +#ifdef HAVE_LIBELF_SUPPORT const size_t len = strlen(name); const size_t real_len = len - sizeof(DSO__DELETED); @@ -182,12 +188,6 @@ int map__load(struct map *map, symbol_filter_t filter) #endif return -1; } - /* - * Only applies to the kernel, as its symtabs aren't relative like the - * module ones. - */ - if (map->dso->kernel) - map__reloc_vmlinux(map); return 0; } @@ -252,16 +252,49 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp) return fprintf(fp, "%s", dsoname); } -/* +/** + * map__rip_2objdump - convert symbol start address to objdump address. + * @map: memory map + * @rip: symbol start address + * * objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN. - * map->dso->adjust_symbols==1 for ET_EXEC-like cases. + * map->dso->adjust_symbols==1 for ET_EXEC-like cases except ET_REL which is + * relative to section start. + * + * Return: Address suitable for passing to "objdump --start-address=" */ u64 map__rip_2objdump(struct map *map, u64 rip) { - u64 addr = map->dso->adjust_symbols ? - map->unmap_ip(map, rip) : /* RIP -> IP */ - rip; - return addr; + if (!map->dso->adjust_symbols) + return rip; + + if (map->dso->rel) + return rip - map->pgoff; + + return map->unmap_ip(map, rip); +} + +/** + * map__objdump_2mem - convert objdump address to a memory address. + * @map: memory map + * @ip: objdump address + * + * Closely related to map__rip_2objdump(), this function takes an address from + * objdump and converts it to a memory address. Note this assumes that @map + * contains the address. To be sure the result is valid, check it forwards + * e.g. map__rip_2objdump(map->map_ip(map, map__objdump_2mem(map, ip))) == ip + * + * Return: Memory address. + */ +u64 map__objdump_2mem(struct map *map, u64 ip) +{ + if (!map->dso->adjust_symbols) + return map->unmap_ip(map, ip); + + if (map->dso->rel) + return map->unmap_ip(map, ip + map->pgoff); + + return ip; } void map_groups__init(struct map_groups *mg) @@ -367,6 +400,23 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, return NULL; } +int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter) +{ + if (ams->addr < ams->map->start || ams->addr > ams->map->end) { + if (ams->map->groups == NULL) + return -1; + ams->map = map_groups__find(ams->map->groups, ams->map->type, + ams->addr); + if (ams->map == NULL) + return -1; + } + + ams->al_addr = ams->map->map_ip(ams->map, ams->addr); + ams->sym = map__find_symbol(ams->map, ams->al_addr, filter); + + return ams->sym ? 0 : -1; +} + size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, int verbose, FILE *fp) { @@ -513,35 +563,6 @@ int map_groups__clone(struct map_groups *mg, return 0; } -static u64 map__reloc_map_ip(struct map *map, u64 ip) -{ - return ip + (s64)map->pgoff; -} - -static u64 map__reloc_unmap_ip(struct map *map, u64 ip) -{ - return ip - (s64)map->pgoff; -} - -void map__reloc_vmlinux(struct map *map) -{ - struct kmap *kmap = map__kmap(map); - s64 reloc; - - if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr) - return; - - reloc = (kmap->ref_reloc_sym->unrelocated_addr - - kmap->ref_reloc_sym->addr); - - if (!reloc) - return; - - map->map_ip = map__reloc_map_ip; - map->unmap_ip = map__reloc_unmap_ip; - map->pgoff = reloc; -} - void maps__insert(struct rb_root *maps, struct map *map) { struct rb_node **p = &maps->rb_node; @@ -586,3 +607,21 @@ struct map *maps__find(struct rb_root *maps, u64 ip) return NULL; } + +struct map *maps__first(struct rb_root *maps) +{ + struct rb_node *first = rb_first(maps); + + if (first) + return rb_entry(first, struct map, rb_node); + return NULL; +} + +struct map *maps__next(struct map *map) +{ + struct rb_node *next = rb_next(&map->rb_node); + + if (next) + return rb_entry(next, struct map, rb_node); + return NULL; +} diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index a887f2c9dfbb..e4e259c3ba16 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -36,6 +36,9 @@ struct map { bool erange_warned; u32 priv; u64 pgoff; + u32 maj, min; /* only valid for MMAP2 record */ + u64 ino; /* only valid for MMAP2 record */ + u64 ino_generation;/* only valid for MMAP2 record */ /* ip -> dso rip */ u64 (*map_ip)(struct map *, u64); @@ -81,6 +84,9 @@ static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip) /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */ u64 map__rip_2objdump(struct map *map, u64 rip); +/* objdump address -> memory address */ +u64 map__objdump_2mem(struct map *map, u64 ip); + struct symbol; typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); @@ -88,8 +94,9 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, - u64 pgoff, u32 pid, char *filename, - enum map_type type); + u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, + u64 ino_gen, + char *filename, enum map_type type); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); void map__delete(struct map *map); struct map *map__clone(struct map *map); @@ -112,6 +119,8 @@ size_t __map_groups__fprintf_maps(struct map_groups *mg, void maps__insert(struct rb_root *maps, struct map *map); void maps__remove(struct rb_root *maps, struct map *map); struct map *maps__find(struct rb_root *maps, u64 addr); +struct map *maps__first(struct rb_root *maps); +struct map *maps__next(struct map *map); void map_groups__init(struct map_groups *mg); void map_groups__exit(struct map_groups *mg); int map_groups__clone(struct map_groups *mg, @@ -139,6 +148,17 @@ static inline struct map *map_groups__find(struct map_groups *mg, return maps__find(&mg->maps[type], addr); } +static inline struct map *map_groups__first(struct map_groups *mg, + enum map_type type) +{ + return maps__first(&mg->maps[type]); +} + +static inline struct map *map_groups__next(struct map *map) +{ + return maps__next(map); +} + struct symbol *map_groups__find_symbol(struct map_groups *mg, enum map_type type, u64 addr, struct map **mapp, @@ -150,6 +170,10 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, struct map **mapp, symbol_filter_t filter); +struct addr_map_symbol; + +int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter); + static inline struct symbol *map_groups__find_function_by_name(struct map_groups *mg, const char *name, struct map **mapp, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 995fc25db8c6..c90e55cf7e82 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -6,7 +6,7 @@ #include "parse-options.h" #include "parse-events.h" #include "exec_cmd.h" -#include "string.h" +#include "linux/string.h" #include "symbol.h" #include "cache.h" #include "header.h" @@ -15,6 +15,7 @@ #define YY_EXTRA_TYPE int #include "parse-events-flex.h" #include "pmu.h" +#include "thread_map.h" #define MAX_NAME_LEN 100 @@ -108,6 +109,10 @@ static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { .symbol = "emulation-faults", .alias = "", }, + [PERF_COUNT_SW_DUMMY] = { + .symbol = "dummy", + .alias = "", + }, }; #define __PERF_EVENT_FIELD(config, name) \ @@ -217,6 +222,29 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) return NULL; } +struct tracepoint_path *tracepoint_name_to_path(const char *name) +{ + struct tracepoint_path *path = zalloc(sizeof(*path)); + char *str = strchr(name, ':'); + + if (path == NULL || str == NULL) { + free(path); + return NULL; + } + + path->system = strndup(name, str - name); + path->name = strdup(str+1); + + if (path->system == NULL || path->name == NULL) { + free(path->system); + free(path->name); + free(path); + path = NULL; + } + + return path; +} + const char *event_type(int type) { switch (type) { @@ -241,40 +269,29 @@ const char *event_type(int type) -static int __add_event(struct list_head **_list, int *idx, +static int __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct cpu_map *cpus) { struct perf_evsel *evsel; - struct list_head *list = *_list; - - if (!list) { - list = malloc(sizeof(*list)); - if (!list) - return -ENOMEM; - INIT_LIST_HEAD(list); - } event_attr_init(attr); evsel = perf_evsel__new(attr, (*idx)++); - if (!evsel) { - free(list); + if (!evsel) return -ENOMEM; - } evsel->cpus = cpus; if (name) evsel->name = strdup(name); list_add_tail(&evsel->node, list); - *_list = list; return 0; } -static int add_event(struct list_head **_list, int *idx, +static int add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name) { - return __add_event(_list, idx, attr, name, NULL); + return __add_event(list, idx, attr, name, NULL); } static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) @@ -295,7 +312,7 @@ static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES] return -1; } -int parse_events_add_cache(struct list_head **list, int *idx, +int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2) { struct perf_event_attr attr; @@ -356,31 +373,21 @@ int parse_events_add_cache(struct list_head **list, int *idx, return add_event(list, idx, &attr, name); } -static int add_tracepoint(struct list_head **listp, int *idx, +static int add_tracepoint(struct list_head *list, int *idx, char *sys_name, char *evt_name) { struct perf_evsel *evsel; - struct list_head *list = *listp; - - if (!list) { - list = malloc(sizeof(*list)); - if (!list) - return -ENOMEM; - INIT_LIST_HEAD(list); - } evsel = perf_evsel__newtp(sys_name, evt_name, (*idx)++); - if (!evsel) { - free(list); + if (!evsel) return -ENOMEM; - } list_add_tail(&evsel->node, list); - *listp = list; + return 0; } -static int add_tracepoint_multi_event(struct list_head **list, int *idx, +static int add_tracepoint_multi_event(struct list_head *list, int *idx, char *sys_name, char *evt_name) { char evt_path[MAXPATHLEN]; @@ -412,7 +419,7 @@ static int add_tracepoint_multi_event(struct list_head **list, int *idx, return ret; } -static int add_tracepoint_event(struct list_head **list, int *idx, +static int add_tracepoint_event(struct list_head *list, int *idx, char *sys_name, char *evt_name) { return strpbrk(evt_name, "*?") ? @@ -420,7 +427,7 @@ static int add_tracepoint_event(struct list_head **list, int *idx, add_tracepoint(list, idx, sys_name, evt_name); } -static int add_tracepoint_multi_sys(struct list_head **list, int *idx, +static int add_tracepoint_multi_sys(struct list_head *list, int *idx, char *sys_name, char *evt_name) { struct dirent *events_ent; @@ -452,7 +459,7 @@ static int add_tracepoint_multi_sys(struct list_head **list, int *idx, return ret; } -int parse_events_add_tracepoint(struct list_head **list, int *idx, +int parse_events_add_tracepoint(struct list_head *list, int *idx, char *sys, char *event) { int ret; @@ -507,7 +514,7 @@ do { \ return 0; } -int parse_events_add_breakpoint(struct list_head **list, int *idx, +int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type) { struct perf_event_attr attr; @@ -588,7 +595,7 @@ static int config_attr(struct perf_event_attr *attr, return 0; } -int parse_events_add_numeric(struct list_head **list, int *idx, +int parse_events_add_numeric(struct list_head *list, int *idx, u32 type, u64 config, struct list_head *head_config) { @@ -621,7 +628,7 @@ static char *pmu_event_name(struct list_head *head_terms) return NULL; } -int parse_events_add_pmu(struct list_head **list, int *idx, +int parse_events_add_pmu(struct list_head *list, int *idx, char *name, struct list_head *head_config) { struct perf_event_attr attr; @@ -664,6 +671,7 @@ void parse_events__set_leader(char *name, struct list_head *list) leader->group_name = name ? strdup(name) : NULL; } +/* list_event is assumed to point to malloc'ed memory */ void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all) { @@ -684,6 +692,8 @@ struct event_modifier { int eG; int precise; int exclude_GH; + int sample_read; + int pinned; }; static int get_event_modifier(struct event_modifier *mod, char *str, @@ -695,6 +705,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str, int eH = evsel ? evsel->attr.exclude_host : 0; int eG = evsel ? evsel->attr.exclude_guest : 0; int precise = evsel ? evsel->attr.precise_ip : 0; + int sample_read = 0; + int pinned = evsel ? evsel->attr.pinned : 0; int exclude = eu | ek | eh; int exclude_GH = evsel ? evsel->exclude_GH : 0; @@ -727,6 +739,10 @@ static int get_event_modifier(struct event_modifier *mod, char *str, /* use of precise requires exclude_guest */ if (!exclude_GH) eG = 1; + } else if (*str == 'S') { + sample_read = 1; + } else if (*str == 'D') { + pinned = 1; } else break; @@ -753,6 +769,9 @@ static int get_event_modifier(struct event_modifier *mod, char *str, mod->eG = eG; mod->precise = precise; mod->exclude_GH = exclude_GH; + mod->sample_read = sample_read; + mod->pinned = pinned; + return 0; } @@ -765,7 +784,7 @@ static int check_modifier(char *str) char *p = str; /* The sizeof includes 0 byte as well. */ - if (strlen(str) > (sizeof("ukhGHppp") - 1)) + if (strlen(str) > (sizeof("ukhGHpppSD") - 1)) return -1; while (*p) { @@ -803,6 +822,10 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) evsel->attr.exclude_host = mod.eH; evsel->attr.exclude_guest = mod.eG; evsel->exclude_GH = mod.exclude_GH; + evsel->sample_read = mod.sample_read; + + if (perf_evsel__is_group_leader(evsel)) + evsel->attr.pinned = mod.pinned; } return 0; @@ -820,6 +843,32 @@ int parse_events_name(struct list_head *list, char *name) return 0; } +static int parse_events__scanner(const char *str, void *data, int start_token); + +static int parse_events_fixup(int ret, const char *str, void *data, + int start_token) +{ + char *o = strdup(str); + char *s = NULL; + char *t = o; + char *p; + int len = 0; + + if (!o) + return ret; + while ((p = strsep(&t, ",")) != NULL) { + if (s) + str_append(&s, &len, ","); + str_append(&s, &len, "cpu/"); + str_append(&s, &len, p); + str_append(&s, &len, "/"); + } + free(o); + if (!s) + return -ENOMEM; + return parse_events__scanner(s, data, start_token); +} + static int parse_events__scanner(const char *str, void *data, int start_token) { YY_BUFFER_STATE buffer; @@ -840,6 +889,8 @@ static int parse_events__scanner(const char *str, void *data, int start_token) parse_events__flush_buffer(buffer, scanner); parse_events__delete_buffer(buffer, scanner); parse_events_lex_destroy(scanner); + if (ret && !strchr(str, '/')) + ret = parse_events_fixup(ret, str, data, start_token); return ret; } @@ -947,8 +998,10 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(tracing_events_path)) + if (debugfs_valid_mountpoint(tracing_events_path)) { + printf(" [ Tracepoints not available: %s ]\n", strerror(errno)); return; + } sys_dir = opendir(tracing_events_path); if (!sys_dir) @@ -1026,6 +1079,33 @@ int is_valid_tracepoint(const char *event_string) return 0; } +static bool is_event_supported(u8 type, unsigned config) +{ + bool ret = true; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = type, + .config = config, + .disabled = 1, + .exclude_kernel = 1, + }; + struct { + struct thread_map map; + int threads[1]; + } tmap = { + .map.nr = 1, + .threads = { 0 }, + }; + + evsel = perf_evsel__new(&attr, 0); + if (evsel) { + ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0; + perf_evsel__delete(evsel); + } + + return ret; +} + static void __print_events_type(u8 type, struct event_symbol *syms, unsigned max) { @@ -1033,14 +1113,16 @@ static void __print_events_type(u8 type, struct event_symbol *syms, unsigned i; for (i = 0; i < max ; i++, syms++) { + if (!is_event_supported(type, i)) + continue; + if (strlen(syms->alias)) snprintf(name, sizeof(name), "%s OR %s", syms->symbol, syms->alias); else snprintf(name, sizeof(name), "%s", syms->symbol); - printf(" %-50s [%s]\n", name, - event_type_descriptors[type]); + printf(" %-50s [%s]\n", name, event_type_descriptors[type]); } } @@ -1069,6 +1151,10 @@ int print_hwcache_events(const char *event_glob, bool name_only) if (event_glob != NULL && !strglobmatch(name, event_glob)) continue; + if (!is_event_supported(PERF_TYPE_HW_CACHE, + type | (op << 8) | (i << 16))) + continue; + if (name_only) printf("%s ", name); else @@ -1079,6 +1165,8 @@ int print_hwcache_events(const char *event_glob, bool name_only) } } + if (printed) + printf("\n"); return printed; } @@ -1096,6 +1184,9 @@ static void print_symbol_events(const char *event_glob, unsigned type, (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; + if (!is_event_supported(type, i)) + continue; + if (name_only) { printf("%s ", syms->symbol); continue; @@ -1133,11 +1224,12 @@ void print_events(const char *event_glob, bool name_only) print_hwcache_events(event_glob, name_only); + print_pmu_events(event_glob, name_only); + if (event_glob != NULL) return; if (!name_only) { - printf("\n"); printf(" %-50s [%s]\n", "rNNN", event_type_descriptors[PERF_TYPE_RAW]); @@ -1237,6 +1329,4 @@ void parse_events__free_terms(struct list_head *terms) list_for_each_entry_safe(term, h, terms, list) free(term); - - free(terms); } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 8a4859315fd9..f1cb4c4b3c70 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -23,6 +23,7 @@ struct tracepoint_path { }; extern struct tracepoint_path *tracepoint_id_to_path(u64 config); +extern struct tracepoint_path *tracepoint_name_to_path(const char *name); extern bool have_tracepoints(struct list_head *evlist); const char *event_type(int type); @@ -84,16 +85,16 @@ void parse_events__free_terms(struct list_head *terms); int parse_events__modifier_event(struct list_head *list, char *str, bool add); int parse_events__modifier_group(struct list_head *list, char *event_mod); int parse_events_name(struct list_head *list, char *name); -int parse_events_add_tracepoint(struct list_head **list, int *idx, +int parse_events_add_tracepoint(struct list_head *list, int *idx, char *sys, char *event); -int parse_events_add_numeric(struct list_head **list, int *idx, +int parse_events_add_numeric(struct list_head *list, int *idx, u32 type, u64 config, struct list_head *head_config); -int parse_events_add_cache(struct list_head **list, int *idx, +int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2); -int parse_events_add_breakpoint(struct list_head **list, int *idx, +int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type); -int parse_events_add_pmu(struct list_head **list, int *idx, +int parse_events_add_pmu(struct list_head *list, int *idx, char *pmu , struct list_head *head_config); void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index e9d1134c2c68..343299575b30 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -82,7 +82,8 @@ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ name [a-zA-Z_*?][a-zA-Z0-9_*?]* name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?]* -modifier_event [ukhpGH]+ +/* If you add a modifier you need to update check_modifier() */ +modifier_event [ukhpGHSD]+ modifier_bp [rwx]{1,3} %% @@ -125,6 +126,37 @@ modifier_bp [rwx]{1,3} } +<config>{ +config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); } +config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } +config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } +name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } +period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } +branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } +, { return ','; } +"/" { BEGIN(INITIAL); return '/'; } +{name_minus} { return str(yyscanner, PE_NAME); } +} + +<mem>{ +{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); } +: { return ':'; } +{num_dec} { return value(yyscanner, 10); } +{num_hex} { return value(yyscanner, 16); } + /* + * We need to separate 'mem:' scanner part, in order to get specific + * modifier bits parsed out. Otherwise we would need to handle PE_NAME + * and we'd need to parse it manually. During the escape from <mem> + * state we need to put the escaping char back, so we dont miss it. + */ +. { unput(*yytext); BEGIN(INITIAL); } + /* + * We destroy the scanner after reaching EOF, + * but anyway just to be sure get back to INIT state. + */ +<<EOF>> { BEGIN(INITIAL); } +} + cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); } stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } @@ -144,6 +176,7 @@ context-switches|cs { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); } alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } +dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } L1-dcache|l1-d|l1d|L1-data | L1-icache|l1-i|l1i|L1-instruction | @@ -160,18 +193,6 @@ speculative-read|speculative-load | refs|Reference|ops|access | misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); } -<config>{ -config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); } -config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } -config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } -name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } -period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } -branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } -, { return ','; } -"/" { BEGIN(INITIAL); return '/'; } -{name_minus} { return str(yyscanner, PE_NAME); } -} - mem: { BEGIN(mem); return PE_PREFIX_MEM; } r{num_raw_hex} { return raw(yyscanner); } {num_dec} { return value(yyscanner, 10); } @@ -187,25 +208,7 @@ r{num_raw_hex} { return raw(yyscanner); } "}" { return '}'; } = { return '='; } \n { } - -<mem>{ -{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); } -: { return ':'; } -{num_dec} { return value(yyscanner, 10); } -{num_hex} { return value(yyscanner, 16); } - /* - * We need to separate 'mem:' scanner part, in order to get specific - * modifier bits parsed out. Otherwise we would need to handle PE_NAME - * and we'd need to parse it manually. During the escape from <mem> - * state we need to put the escaping char back, so we dont miss it. - */ -. { unput(*yytext); BEGIN(INITIAL); } - /* - * We destroy the scanner after reaching EOF, - * but anyway just to be sure get back to INIT state. - */ -<<EOF>> { BEGIN(INITIAL); } -} +. { } %% diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index afc44c18dfe1..4eb67ec333f1 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -22,6 +22,13 @@ do { \ YYABORT; \ } while (0) +#define ALLOC_LIST(list) \ +do { \ + list = malloc(sizeof(*list)); \ + ABORT_ON(!list); \ + INIT_LIST_HEAD(list); \ +} while (0) + static inc_group_count(struct list_head *list, struct parse_events_evlist *data) { @@ -196,9 +203,10 @@ event_pmu: PE_NAME '/' event_config '/' { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3)); parse_events__free_terms($3); $$ = list; } @@ -212,11 +220,12 @@ event_legacy_symbol: value_sym '/' event_config '/' { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; int type = $1 >> 16; int config = $1 & 255; - ABORT_ON(parse_events_add_numeric(&list, &data->idx, + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, type, config, $3)); parse_events__free_terms($3); $$ = list; @@ -225,11 +234,12 @@ value_sym '/' event_config '/' value_sym sep_slash_dc { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; int type = $1 >> 16; int config = $1 & 255; - ABORT_ON(parse_events_add_numeric(&list, &data->idx, + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, type, config, NULL)); $$ = list; } @@ -238,27 +248,30 @@ event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5)); $$ = list; } | PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL)); $$ = list; } | PE_NAME_CACHE_TYPE { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL)); $$ = list; } @@ -266,9 +279,10 @@ event_legacy_mem: PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, + ALLOC_LIST(list); + ABORT_ON(parse_events_add_breakpoint(list, &data->idx, (void *) $2, $4)); $$ = list; } @@ -276,9 +290,10 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc PE_PREFIX_MEM PE_VALUE sep_dc { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, + ALLOC_LIST(list); + ABORT_ON(parse_events_add_breakpoint(list, &data->idx, (void *) $2, NULL)); $$ = list; } @@ -287,9 +302,10 @@ event_legacy_tracepoint: PE_NAME ':' PE_NAME { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3)); $$ = list; } @@ -297,9 +313,10 @@ event_legacy_numeric: PE_VALUE ':' PE_VALUE { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_numeric(&list, &data->idx, (u32)$1, $3, NULL)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL)); $$ = list; } @@ -307,9 +324,10 @@ event_legacy_raw: PE_RAW { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_numeric(&list, &data->idx, + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, PERF_TYPE_RAW, $1, NULL)); $$ = list; } diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 2bc9e70df7e2..31f404a032a9 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -339,10 +339,10 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, if (arg[1] != '-') { ctx->opt = arg + 1; if (internal_help && *ctx->opt == 'h') - return parse_options_usage(usagestr, options); + return usage_with_options_internal(usagestr, options, 0); switch (parse_short_opt(ctx, options)) { case -1: - return parse_options_usage(usagestr, options); + return parse_options_usage(usagestr, options, arg + 1, 1); case -2: goto unknown; default: @@ -352,10 +352,11 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, check_typos(arg + 1, options); while (ctx->opt) { if (internal_help && *ctx->opt == 'h') - return parse_options_usage(usagestr, options); + return usage_with_options_internal(usagestr, options, 0); + arg = ctx->opt; switch (parse_short_opt(ctx, options)) { case -1: - return parse_options_usage(usagestr, options); + return parse_options_usage(usagestr, options, arg, 1); case -2: /* fake a short option thing to hide the fact that we may have * started to parse aggregated stuff @@ -383,12 +384,12 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, if (internal_help && !strcmp(arg + 2, "help-all")) return usage_with_options_internal(usagestr, options, 1); if (internal_help && !strcmp(arg + 2, "help")) - return parse_options_usage(usagestr, options); + return usage_with_options_internal(usagestr, options, 0); if (!strcmp(arg + 2, "list-opts")) return PARSE_OPT_LIST; switch (parse_long_opt(ctx, arg + 2, options)) { case -1: - return parse_options_usage(usagestr, options); + return parse_options_usage(usagestr, options, arg + 2, 0); case -2: goto unknown; default: @@ -445,6 +446,89 @@ int parse_options(int argc, const char **argv, const struct option *options, #define USAGE_OPTS_WIDTH 24 #define USAGE_GAP 2 +static void print_option_help(const struct option *opts, int full) +{ + size_t pos; + int pad; + + if (opts->type == OPTION_GROUP) { + fputc('\n', stderr); + if (*opts->help) + fprintf(stderr, "%s\n", opts->help); + return; + } + if (!full && (opts->flags & PARSE_OPT_HIDDEN)) + return; + + pos = fprintf(stderr, " "); + if (opts->short_name) + pos += fprintf(stderr, "-%c", opts->short_name); + else + pos += fprintf(stderr, " "); + + if (opts->long_name && opts->short_name) + pos += fprintf(stderr, ", "); + if (opts->long_name) + pos += fprintf(stderr, "--%s", opts->long_name); + + switch (opts->type) { + case OPTION_ARGUMENT: + break; + case OPTION_LONG: + case OPTION_U64: + case OPTION_INTEGER: + case OPTION_UINTEGER: + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=<n>]"); + else + pos += fprintf(stderr, "[<n>]"); + else + pos += fprintf(stderr, " <n>"); + break; + case OPTION_CALLBACK: + if (opts->flags & PARSE_OPT_NOARG) + break; + /* FALLTHROUGH */ + case OPTION_STRING: + if (opts->argh) { + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=<%s>]", opts->argh); + else + pos += fprintf(stderr, "[<%s>]", opts->argh); + else + pos += fprintf(stderr, " <%s>", opts->argh); + } else { + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=...]"); + else + pos += fprintf(stderr, "[...]"); + else + pos += fprintf(stderr, " ..."); + } + break; + default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */ + case OPTION_END: + case OPTION_GROUP: + case OPTION_BIT: + case OPTION_BOOLEAN: + case OPTION_INCR: + case OPTION_SET_UINT: + case OPTION_SET_PTR: + break; + } + + if (pos <= USAGE_OPTS_WIDTH) + pad = USAGE_OPTS_WIDTH - pos; + else { + fputc('\n', stderr); + pad = USAGE_OPTS_WIDTH; + } + fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help); +} + int usage_with_options_internal(const char * const *usagestr, const struct option *opts, int full) { @@ -464,87 +548,9 @@ int usage_with_options_internal(const char * const *usagestr, if (opts->type != OPTION_GROUP) fputc('\n', stderr); - for (; opts->type != OPTION_END; opts++) { - size_t pos; - int pad; - - if (opts->type == OPTION_GROUP) { - fputc('\n', stderr); - if (*opts->help) - fprintf(stderr, "%s\n", opts->help); - continue; - } - if (!full && (opts->flags & PARSE_OPT_HIDDEN)) - continue; - - pos = fprintf(stderr, " "); - if (opts->short_name) - pos += fprintf(stderr, "-%c", opts->short_name); - else - pos += fprintf(stderr, " "); - - if (opts->long_name && opts->short_name) - pos += fprintf(stderr, ", "); - if (opts->long_name) - pos += fprintf(stderr, "--%s", opts->long_name); - - switch (opts->type) { - case OPTION_ARGUMENT: - break; - case OPTION_LONG: - case OPTION_U64: - case OPTION_INTEGER: - case OPTION_UINTEGER: - if (opts->flags & PARSE_OPT_OPTARG) - if (opts->long_name) - pos += fprintf(stderr, "[=<n>]"); - else - pos += fprintf(stderr, "[<n>]"); - else - pos += fprintf(stderr, " <n>"); - break; - case OPTION_CALLBACK: - if (opts->flags & PARSE_OPT_NOARG) - break; - /* FALLTHROUGH */ - case OPTION_STRING: - if (opts->argh) { - if (opts->flags & PARSE_OPT_OPTARG) - if (opts->long_name) - pos += fprintf(stderr, "[=<%s>]", opts->argh); - else - pos += fprintf(stderr, "[<%s>]", opts->argh); - else - pos += fprintf(stderr, " <%s>", opts->argh); - } else { - if (opts->flags & PARSE_OPT_OPTARG) - if (opts->long_name) - pos += fprintf(stderr, "[=...]"); - else - pos += fprintf(stderr, "[...]"); - else - pos += fprintf(stderr, " ..."); - } - break; - default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */ - case OPTION_END: - case OPTION_GROUP: - case OPTION_BIT: - case OPTION_BOOLEAN: - case OPTION_INCR: - case OPTION_SET_UINT: - case OPTION_SET_PTR: - break; - } + for ( ; opts->type != OPTION_END; opts++) + print_option_help(opts, full); - if (pos <= USAGE_OPTS_WIDTH) - pad = USAGE_OPTS_WIDTH - pos; - else { - fputc('\n', stderr); - pad = USAGE_OPTS_WIDTH; - } - fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help); - } fputc('\n', stderr); return PARSE_OPT_HELP; @@ -559,9 +565,45 @@ void usage_with_options(const char * const *usagestr, } int parse_options_usage(const char * const *usagestr, - const struct option *opts) + const struct option *opts, + const char *optstr, bool short_opt) { - return usage_with_options_internal(usagestr, opts, 0); + if (!usagestr) + goto opt; + + fprintf(stderr, "\n usage: %s\n", *usagestr++); + while (*usagestr && **usagestr) + fprintf(stderr, " or: %s\n", *usagestr++); + while (*usagestr) { + fprintf(stderr, "%s%s\n", + **usagestr ? " " : "", + *usagestr); + usagestr++; + } + fputc('\n', stderr); + +opt: + for ( ; opts->type != OPTION_END; opts++) { + if (short_opt) { + if (opts->short_name == *optstr) + break; + continue; + } + + if (opts->long_name == NULL) + continue; + + if (!prefixcmp(optstr, opts->long_name)) + break; + if (!prefixcmp(optstr, "no-") && + !prefixcmp(optstr + 3, opts->long_name)) + break; + } + + if (opts->type != OPTION_END) + print_option_help(opts, 0); + + return PARSE_OPT_HELP; } diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index 7bb5999940ca..b0241e28eaf7 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -158,7 +158,9 @@ struct parse_opt_ctx_t { }; extern int parse_options_usage(const char * const *usagestr, - const struct option *opts); + const struct option *opts, + const char *optstr, + bool short_opt); extern void parse_options_start(struct parse_opt_ctx_t *ctx, int argc, const char **argv, int flags); diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index a8c49548ca48..5d13cb45b317 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -22,19 +22,23 @@ static const char *get_perf_dir(void) return "."; } -#ifndef HAVE_STRLCPY -size_t strlcpy(char *dest, const char *src, size_t size) +/* + * If libc has strlcpy() then that version will override this + * implementation: + */ +size_t __weak strlcpy(char *dest, const char *src, size_t size) { size_t ret = strlen(src); if (size) { size_t len = (ret >= size) ? size - 1 : ret; + memcpy(dest, src, len); dest[len] = '\0'; } + return ret; } -#endif static char *get_pathname(void) { diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 5a4f2b6f3738..a3d42cd74919 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -1,7 +1,7 @@ #ifndef __PERF_REGS_H #define __PERF_REGS_H -#ifdef HAVE_PERF_REGS +#ifdef HAVE_PERF_REGS_SUPPORT #include <perf_regs.h> #else #define PERF_REGS_MASK 0 @@ -10,5 +10,5 @@ static inline const char *perf_reg_name(int id __maybe_unused) { return NULL; } -#endif /* HAVE_PERF_REGS */ +#endif /* HAVE_PERF_REGS_SUPPORT */ #endif /* __PERF_REGS_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 4c6f9c490a8d..c232d8dd410b 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -4,7 +4,7 @@ #include <unistd.h> #include <stdio.h> #include <dirent.h> -#include "sysfs.h" +#include "fs.h" #include "util.h" #include "pmu.h" #include "parse-events.h" @@ -73,13 +73,12 @@ int perf_pmu__format_parse(char *dir, struct list_head *head) * located at: * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes. */ -static int pmu_format(char *name, struct list_head *format) +static int pmu_format(const char *name, struct list_head *format) { struct stat st; char path[PATH_MAX]; - const char *sysfs; + const char *sysfs = sysfs__mountpoint(); - sysfs = sysfs_find_mountpoint(); if (!sysfs) return -1; @@ -162,13 +161,12 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) * Reading the pmu event aliases definition, which should be located at: * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes. */ -static int pmu_aliases(char *name, struct list_head *head) +static int pmu_aliases(const char *name, struct list_head *head) { struct stat st; char path[PATH_MAX]; - const char *sysfs; + const char *sysfs = sysfs__mountpoint(); - sysfs = sysfs_find_mountpoint(); if (!sysfs) return -1; @@ -208,15 +206,14 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, * located at: * /sys/bus/event_source/devices/<dev>/type as sysfs attribute. */ -static int pmu_type(char *name, __u32 *type) +static int pmu_type(const char *name, __u32 *type) { struct stat st; char path[PATH_MAX]; - const char *sysfs; FILE *file; int ret = 0; + const char *sysfs = sysfs__mountpoint(); - sysfs = sysfs_find_mountpoint(); if (!sysfs) return -1; @@ -241,11 +238,10 @@ static int pmu_type(char *name, __u32 *type) static void pmu_read_sysfs(void) { char path[PATH_MAX]; - const char *sysfs; DIR *dir; struct dirent *dent; + const char *sysfs = sysfs__mountpoint(); - sysfs = sysfs_find_mountpoint(); if (!sysfs) return; @@ -266,15 +262,14 @@ static void pmu_read_sysfs(void) closedir(dir); } -static struct cpu_map *pmu_cpumask(char *name) +static struct cpu_map *pmu_cpumask(const char *name) { struct stat st; char path[PATH_MAX]; - const char *sysfs; FILE *file; struct cpu_map *cpus; + const char *sysfs = sysfs__mountpoint(); - sysfs = sysfs_find_mountpoint(); if (!sysfs) return NULL; @@ -293,7 +288,7 @@ static struct cpu_map *pmu_cpumask(char *name) return cpus; } -static struct perf_pmu *pmu_lookup(char *name) +static struct perf_pmu *pmu_lookup(const char *name) { struct perf_pmu *pmu; LIST_HEAD(format); @@ -330,7 +325,7 @@ static struct perf_pmu *pmu_lookup(char *name) return pmu; } -static struct perf_pmu *pmu_find(char *name) +static struct perf_pmu *pmu_find(const char *name) { struct perf_pmu *pmu; @@ -356,7 +351,7 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu) return NULL; } -struct perf_pmu *perf_pmu__find(char *name) +struct perf_pmu *perf_pmu__find(const char *name) { struct perf_pmu *pmu; @@ -564,3 +559,92 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to) for (b = from; b <= to; b++) set_bit(b, bits); } + +static char *format_alias(char *buf, int len, struct perf_pmu *pmu, + struct perf_pmu_alias *alias) +{ + snprintf(buf, len, "%s/%s/", pmu->name, alias->name); + return buf; +} + +static char *format_alias_or(char *buf, int len, struct perf_pmu *pmu, + struct perf_pmu_alias *alias) +{ + snprintf(buf, len, "%s OR %s/%s/", alias->name, pmu->name, alias->name); + return buf; +} + +static int cmp_string(const void *a, const void *b) +{ + const char * const *as = a; + const char * const *bs = b; + return strcmp(*as, *bs); +} + +void print_pmu_events(const char *event_glob, bool name_only) +{ + struct perf_pmu *pmu; + struct perf_pmu_alias *alias; + char buf[1024]; + int printed = 0; + int len, j; + char **aliases; + + pmu = NULL; + len = 0; + while ((pmu = perf_pmu__scan(pmu)) != NULL) + list_for_each_entry(alias, &pmu->aliases, list) + len++; + aliases = malloc(sizeof(char *) * len); + if (!aliases) + return; + pmu = NULL; + j = 0; + while ((pmu = perf_pmu__scan(pmu)) != NULL) + list_for_each_entry(alias, &pmu->aliases, list) { + char *name = format_alias(buf, sizeof(buf), pmu, alias); + bool is_cpu = !strcmp(pmu->name, "cpu"); + + if (event_glob != NULL && + !(strglobmatch(name, event_glob) || + (!is_cpu && strglobmatch(alias->name, + event_glob)))) + continue; + aliases[j] = name; + if (is_cpu && !name_only) + aliases[j] = format_alias_or(buf, sizeof(buf), + pmu, alias); + aliases[j] = strdup(aliases[j]); + j++; + } + len = j; + qsort(aliases, len, sizeof(char *), cmp_string); + for (j = 0; j < len; j++) { + if (name_only) { + printf("%s ", aliases[j]); + continue; + } + printf(" %-50s [Kernel PMU event]\n", aliases[j]); + free(aliases[j]); + printed++; + } + if (printed) + printf("\n"); + free(aliases); +} + +bool pmu_have_event(const char *pname, const char *name) +{ + struct perf_pmu *pmu; + struct perf_pmu_alias *alias; + + pmu = NULL; + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + if (strcmp(pname, pmu->name)) + continue; + list_for_each_entry(alias, &pmu->aliases, list) + if (!strcmp(alias->name, name)) + return true; + } + return false; +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 32fe55b659fa..1179b26f244a 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -3,6 +3,7 @@ #include <linux/bitops.h> #include <linux/perf_event.h> +#include <stdbool.h> enum { PERF_PMU_FORMAT_VALUE_CONFIG, @@ -21,7 +22,7 @@ struct perf_pmu { struct list_head list; }; -struct perf_pmu *perf_pmu__find(char *name); +struct perf_pmu *perf_pmu__find(const char *name); int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms); int perf_pmu__config_terms(struct list_head *formats, @@ -40,5 +41,8 @@ int perf_pmu__format_parse(char *dir, struct list_head *head); struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); +void print_pmu_events(const char *event_glob, bool name_only); +bool pmu_have_event(const char *pname, const char *name); + int perf_pmu__test(void); #endif /* __PMU_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index aa04bf9c9ad7..9c6989ca2bea 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -47,7 +47,6 @@ #include "session.h" #define MAX_CMDLEN 256 -#define MAX_PROBE_ARGS 128 #define PERFPROBE_GROUP "probe" bool probe_event_dry_run; /* Dry run flag */ @@ -201,7 +200,7 @@ static int convert_to_perf_probe_point(struct probe_trace_point *tp, return 0; } -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT /* Open new debuginfo of given module */ static struct debuginfo *open_debuginfo(const char *module) { @@ -630,7 +629,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, return ret; } -#else /* !DWARF_SUPPORT */ +#else /* !HAVE_DWARF_SUPPORT */ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, struct perf_probe_point *pp) diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index be0329394d56..ffb657ffd327 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -115,35 +115,34 @@ static const Dwfl_Callbacks offline_callbacks = { }; /* Get a Dwarf from offline image */ -static int debuginfo__init_offline_dwarf(struct debuginfo *self, +static int debuginfo__init_offline_dwarf(struct debuginfo *dbg, const char *path) { - Dwfl_Module *mod; int fd; fd = open(path, O_RDONLY); if (fd < 0) return fd; - self->dwfl = dwfl_begin(&offline_callbacks); - if (!self->dwfl) + dbg->dwfl = dwfl_begin(&offline_callbacks); + if (!dbg->dwfl) goto error; - mod = dwfl_report_offline(self->dwfl, "", "", fd); - if (!mod) + dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd); + if (!dbg->mod) goto error; - self->dbg = dwfl_module_getdwarf(mod, &self->bias); - if (!self->dbg) + dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias); + if (!dbg->dbg) goto error; return 0; error: - if (self->dwfl) - dwfl_end(self->dwfl); + if (dbg->dwfl) + dwfl_end(dbg->dwfl); else close(fd); - memset(self, 0, sizeof(*self)); + memset(dbg, 0, sizeof(*dbg)); return -ENOENT; } @@ -181,24 +180,24 @@ static const Dwfl_Callbacks kernel_callbacks = { }; /* Get a Dwarf from live kernel image */ -static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self, +static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg, Dwarf_Addr addr) { - self->dwfl = dwfl_begin(&kernel_callbacks); - if (!self->dwfl) + dbg->dwfl = dwfl_begin(&kernel_callbacks); + if (!dbg->dwfl) return -EINVAL; /* Load the kernel dwarves: Don't care the result here */ - dwfl_linux_kernel_report_kernel(self->dwfl); - dwfl_linux_kernel_report_modules(self->dwfl); + dwfl_linux_kernel_report_kernel(dbg->dwfl); + dwfl_linux_kernel_report_modules(dbg->dwfl); - self->dbg = dwfl_addrdwarf(self->dwfl, addr, &self->bias); + dbg->dbg = dwfl_addrdwarf(dbg->dwfl, addr, &dbg->bias); /* Here, check whether we could get a real dwarf */ - if (!self->dbg) { + if (!dbg->dbg) { pr_debug("Failed to find kernel dwarf at %lx\n", (unsigned long)addr); - dwfl_end(self->dwfl); - memset(self, 0, sizeof(*self)); + dwfl_end(dbg->dwfl); + memset(dbg, 0, sizeof(*dbg)); return -ENOENT; } @@ -206,7 +205,7 @@ static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self, } #else /* With older elfutils, this just support kernel module... */ -static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self, +static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg, Dwarf_Addr addr __maybe_unused) { const char *path = kernel_get_module_path("kernel"); @@ -217,44 +216,45 @@ static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self, } pr_debug2("Use file %s for debuginfo\n", path); - return debuginfo__init_offline_dwarf(self, path); + return debuginfo__init_offline_dwarf(dbg, path); } #endif struct debuginfo *debuginfo__new(const char *path) { - struct debuginfo *self = zalloc(sizeof(struct debuginfo)); - if (!self) + struct debuginfo *dbg = zalloc(sizeof(*dbg)); + if (!dbg) return NULL; - if (debuginfo__init_offline_dwarf(self, path) < 0) { - free(self); - self = NULL; + if (debuginfo__init_offline_dwarf(dbg, path) < 0) { + free(dbg); + dbg = NULL; } - return self; + return dbg; } struct debuginfo *debuginfo__new_online_kernel(unsigned long addr) { - struct debuginfo *self = zalloc(sizeof(struct debuginfo)); - if (!self) + struct debuginfo *dbg = zalloc(sizeof(*dbg)); + + if (!dbg) return NULL; - if (debuginfo__init_online_kernel_dwarf(self, (Dwarf_Addr)addr) < 0) { - free(self); - self = NULL; + if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0) { + free(dbg); + dbg = NULL; } - return self; + return dbg; } -void debuginfo__delete(struct debuginfo *self) +void debuginfo__delete(struct debuginfo *dbg) { - if (self) { - if (self->dwfl) - dwfl_end(self->dwfl); - free(self); + if (dbg) { + if (dbg->dwfl) + dwfl_end(dbg->dwfl); + free(dbg); } } @@ -274,12 +274,15 @@ static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs) /* * Convert a location into trace_arg. * If tvar == NULL, this just checks variable can be converted. + * If fentry == true and vr_die is a parameter, do huristic search + * for the location fuzzed by function entry mcount. */ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, - Dwarf_Op *fb_ops, + Dwarf_Op *fb_ops, Dwarf_Die *sp_die, struct probe_trace_arg *tvar) { Dwarf_Attribute attr; + Dwarf_Addr tmp = 0; Dwarf_Op *op; size_t nops; unsigned int regn; @@ -292,12 +295,29 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, goto static_var; /* TODO: handle more than 1 exprs */ - if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL || - dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0 || - nops == 0) { - /* TODO: Support const_value */ + if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL) + return -EINVAL; /* Broken DIE ? */ + if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) { + ret = dwarf_entrypc(sp_die, &tmp); + if (ret || addr != tmp || + dwarf_tag(vr_die) != DW_TAG_formal_parameter || + dwarf_highpc(sp_die, &tmp)) + return -ENOENT; + /* + * This is fuzzed by fentry mcount. We try to find the + * parameter location at the earliest address. + */ + for (addr += 1; addr <= tmp; addr++) { + if (dwarf_getlocation_addr(&attr, addr, &op, + &nops, 1) > 0) + goto found; + } return -ENOENT; } +found: + if (nops == 0) + /* TODO: Support const_value */ + return -ENOENT; if (op->atom == DW_OP_addr) { static_var: @@ -564,7 +584,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, } if (die_find_member(&type, field->name, die_mem) == NULL) { - pr_warning("%s(tyep:%s) has no member %s.\n", varname, + pr_warning("%s(type:%s) has no member %s.\n", varname, dwarf_diename(&type), field->name); return -EINVAL; } @@ -601,7 +621,7 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) dwarf_diename(vr_die)); ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops, - pf->tvar); + &pf->sp_die, pf->tvar); if (ret == -ENOENT) pr_err("Failed to find the location of %s at this address.\n" " Perhaps, it has been optimized out.\n", pf->pvar->var); @@ -676,37 +696,42 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) } /* Convert subprogram DIE to trace point */ -static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr, - bool retprobe, struct probe_trace_point *tp) +static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, + Dwarf_Addr paddr, bool retprobe, + struct probe_trace_point *tp) { Dwarf_Addr eaddr, highaddr; - const char *name; - - /* Copy the name of probe point */ - name = dwarf_diename(sp_die); - if (name) { - if (dwarf_entrypc(sp_die, &eaddr) != 0) { - pr_warning("Failed to get entry address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (dwarf_highpc(sp_die, &highaddr) != 0) { - pr_warning("Failed to get end address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (paddr > highaddr) { - pr_warning("Offset specified is greater than size of %s\n", - dwarf_diename(sp_die)); - return -EINVAL; - } - tp->symbol = strdup(name); - if (tp->symbol == NULL) - return -ENOMEM; - tp->offset = (unsigned long)(paddr - eaddr); - } else - /* This function has no name. */ - tp->offset = (unsigned long)paddr; + GElf_Sym sym; + const char *symbol; + + /* Verify the address is correct */ + if (dwarf_entrypc(sp_die, &eaddr) != 0) { + pr_warning("Failed to get entry address of %s\n", + dwarf_diename(sp_die)); + return -ENOENT; + } + if (dwarf_highpc(sp_die, &highaddr) != 0) { + pr_warning("Failed to get end address of %s\n", + dwarf_diename(sp_die)); + return -ENOENT; + } + if (paddr > highaddr) { + pr_warning("Offset specified is greater than size of %s\n", + dwarf_diename(sp_die)); + return -EINVAL; + } + + /* Get an appropriate symbol from symtab */ + symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); + if (!symbol) { + pr_warning("Failed to find symbol at 0x%lx\n", + (unsigned long)paddr); + return -ENOENT; + } + tp->offset = (unsigned long)(paddr - sym.st_value); + tp->symbol = strdup(symbol); + if (!tp->symbol) + return -ENOMEM; /* Return probe must be on the head of a subprogram */ if (retprobe) { @@ -734,7 +759,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) } /* If not a real subprogram, find a real one */ - if (dwarf_tag(sc_die) != DW_TAG_subprogram) { + if (!die_is_func_def(sc_die)) { if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) { pr_warning("Failed to find probe point in any " "functions.\n"); @@ -980,12 +1005,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) struct dwarf_callback_param *param = data; struct probe_finder *pf = param->data; struct perf_probe_point *pp = &pf->pev->point; - Dwarf_Attribute attr; /* Check tag and diename */ - if (dwarf_tag(sp_die) != DW_TAG_subprogram || - !die_compare_name(sp_die, pp->function) || - dwarf_attr(sp_die, DW_AT_declaration, &attr)) + if (!die_is_func_def(sp_die) || + !die_compare_name(sp_die, pp->function)) return DWARF_CB_OK; /* Check declared file */ @@ -1061,7 +1084,7 @@ static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data) } /* Find probe points from debuginfo */ -static int debuginfo__find_probes(struct debuginfo *self, +static int debuginfo__find_probes(struct debuginfo *dbg, struct probe_finder *pf) { struct perf_probe_point *pp = &pf->pev->point; @@ -1072,7 +1095,7 @@ static int debuginfo__find_probes(struct debuginfo *self, #if _ELFUTILS_PREREQ(0, 142) /* Get the call frame information from this dwarf */ - pf->cfi = dwarf_getcfi(self->dbg); + pf->cfi = dwarf_getcfi(dbg->dbg); #endif off = 0; @@ -1091,7 +1114,7 @@ static int debuginfo__find_probes(struct debuginfo *self, .data = pf, }; - dwarf_getpubnames(self->dbg, pubname_search_cb, + dwarf_getpubnames(dbg->dbg, pubname_search_cb, &pubname_param, 0); if (pubname_param.found) { ret = probe_point_search_cb(&pf->sp_die, &probe_param); @@ -1101,9 +1124,9 @@ static int debuginfo__find_probes(struct debuginfo *self, } /* Loop on CUs (Compilation Unit) */ - while (!dwarf_nextcu(self->dbg, off, &noff, &cuhl, NULL, NULL, NULL)) { + while (!dwarf_nextcu(dbg->dbg, off, &noff, &cuhl, NULL, NULL, NULL)) { /* Get the DIE(Debugging Information Entry) of this CU */ - diep = dwarf_offdie(self->dbg, off + cuhl, &pf->cu_die); + diep = dwarf_offdie(dbg->dbg, off + cuhl, &pf->cu_die); if (!diep) continue; @@ -1134,12 +1157,80 @@ found: return ret; } +struct local_vars_finder { + struct probe_finder *pf; + struct perf_probe_arg *args; + int max_args; + int nargs; + int ret; +}; + +/* Collect available variables in this scope */ +static int copy_variables_cb(Dwarf_Die *die_mem, void *data) +{ + struct local_vars_finder *vf = data; + struct probe_finder *pf = vf->pf; + int tag; + + tag = dwarf_tag(die_mem); + if (tag == DW_TAG_formal_parameter || + tag == DW_TAG_variable) { + if (convert_variable_location(die_mem, vf->pf->addr, + vf->pf->fb_ops, &pf->sp_die, + NULL) == 0) { + vf->args[vf->nargs].var = (char *)dwarf_diename(die_mem); + if (vf->args[vf->nargs].var == NULL) { + vf->ret = -ENOMEM; + return DIE_FIND_CB_END; + } + pr_debug(" %s", vf->args[vf->nargs].var); + vf->nargs++; + } + } + + if (dwarf_haspc(die_mem, vf->pf->addr)) + return DIE_FIND_CB_CONTINUE; + else + return DIE_FIND_CB_SIBLING; +} + +static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf, + struct perf_probe_arg *args) +{ + Dwarf_Die die_mem; + int i; + int n = 0; + struct local_vars_finder vf = {.pf = pf, .args = args, + .max_args = MAX_PROBE_ARGS, .ret = 0}; + + for (i = 0; i < pf->pev->nargs; i++) { + /* var never be NULL */ + if (strcmp(pf->pev->args[i].var, "$vars") == 0) { + pr_debug("Expanding $vars into:"); + vf.nargs = n; + /* Special local variables */ + die_find_child(sc_die, copy_variables_cb, (void *)&vf, + &die_mem); + pr_debug(" (%d)\n", vf.nargs - n); + if (vf.ret < 0) + return vf.ret; + n = vf.nargs; + } else { + /* Copy normal argument */ + args[n] = pf->pev->args[i]; + n++; + } + } + return n; +} + /* Add a found probe point into trace event list */ 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); struct probe_trace_event *tev; + struct perf_probe_arg *args; int ret, i; /* Check number of tevs */ @@ -1151,7 +1242,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) tev = &tf->tevs[tf->ntevs++]; /* Trace point should be converted from subprogram DIE */ - ret = convert_to_trace_point(&pf->sp_die, pf->addr, + ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr, pf->pev->point.retprobe, &tev->point); if (ret < 0) return ret; @@ -1159,31 +1250,45 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) pr_debug("Probe point found: %s+%lu\n", tev->point.symbol, tev->point.offset); - /* Find each argument */ - tev->nargs = pf->pev->nargs; - tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); - if (tev->args == NULL) + /* Expand special probe argument if exist */ + args = zalloc(sizeof(struct perf_probe_arg) * MAX_PROBE_ARGS); + if (args == NULL) return -ENOMEM; - for (i = 0; i < pf->pev->nargs; i++) { - pf->pvar = &pf->pev->args[i]; + + ret = expand_probe_args(sc_die, pf, args); + if (ret < 0) + goto end; + + tev->nargs = ret; + tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); + if (tev->args == NULL) { + ret = -ENOMEM; + goto end; + } + + /* Find each argument */ + for (i = 0; i < tev->nargs; i++) { + pf->pvar = &args[i]; pf->tvar = &tev->args[i]; /* Variable should be found from scope DIE */ ret = find_variable(sc_die, pf); if (ret != 0) - return ret; + break; } - return 0; +end: + free(args); + return ret; } /* Find probe_trace_events specified by perf_probe_event from debuginfo */ -int debuginfo__find_trace_events(struct debuginfo *self, +int debuginfo__find_trace_events(struct debuginfo *dbg, struct perf_probe_event *pev, struct probe_trace_event **tevs, int max_tevs) { struct trace_event_finder tf = { .pf = {.pev = pev, .callback = add_probe_trace_event}, - .max_tevs = max_tevs}; + .mod = dbg->mod, .max_tevs = max_tevs}; int ret; /* Allocate result tevs array */ @@ -1194,7 +1299,7 @@ int debuginfo__find_trace_events(struct debuginfo *self, tf.tevs = *tevs; tf.ntevs = 0; - ret = debuginfo__find_probes(self, &tf.pf); + ret = debuginfo__find_probes(dbg, &tf.pf); if (ret < 0) { free(*tevs); *tevs = NULL; @@ -1220,7 +1325,8 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data) if (tag == DW_TAG_formal_parameter || tag == DW_TAG_variable) { ret = convert_variable_location(die_mem, af->pf.addr, - af->pf.fb_ops, NULL); + af->pf.fb_ops, &af->pf.sp_die, + NULL); if (ret == 0) { ret = die_get_varname(die_mem, buf, MAX_VAR_LEN); pr_debug2("Add new var: %s\n", buf); @@ -1252,7 +1358,7 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) vl = &af->vls[af->nvls++]; /* Trace point should be converted from subprogram DIE */ - ret = convert_to_trace_point(&pf->sp_die, pf->addr, + ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr, pf->pev->point.retprobe, &vl->point); if (ret < 0) return ret; @@ -1284,13 +1390,14 @@ out: } /* Find available variables at given probe point */ -int debuginfo__find_available_vars_at(struct debuginfo *self, +int debuginfo__find_available_vars_at(struct debuginfo *dbg, struct perf_probe_event *pev, struct variable_list **vls, int max_vls, bool externs) { struct available_var_finder af = { .pf = {.pev = pev, .callback = add_available_vars}, + .mod = dbg->mod, .max_vls = max_vls, .externs = externs}; int ret; @@ -1302,7 +1409,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *self, af.vls = *vls; af.nvls = 0; - ret = debuginfo__find_probes(self, &af.pf); + ret = debuginfo__find_probes(dbg, &af.pf); if (ret < 0) { /* Free vlist for error */ while (af.nvls--) { @@ -1320,19 +1427,19 @@ int debuginfo__find_available_vars_at(struct debuginfo *self, } /* Reverse search */ -int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr, +int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, struct perf_probe_point *ppt) { Dwarf_Die cudie, spdie, indie; - Dwarf_Addr _addr, baseaddr; - const char *fname = NULL, *func = NULL, *tmp; + Dwarf_Addr _addr = 0, baseaddr = 0; + const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp; int baseline = 0, lineno = 0, ret = 0; /* Adjust address with bias */ - addr += self->bias; + addr += dbg->bias; /* Find cu die */ - if (!dwarf_addrdie(self->dbg, (Dwarf_Addr)addr - self->bias, &cudie)) { + if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr - dbg->bias, &cudie)) { pr_warning("Failed to find debug information for address %lx\n", addr); ret = -EINVAL; @@ -1346,27 +1453,36 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr, /* Find a corresponding function (name, baseline and baseaddr) */ if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) { /* Get function entry information */ - tmp = dwarf_diename(&spdie); - if (!tmp || + func = basefunc = dwarf_diename(&spdie); + if (!func || dwarf_entrypc(&spdie, &baseaddr) != 0 || - dwarf_decl_line(&spdie, &baseline) != 0) + dwarf_decl_line(&spdie, &baseline) != 0) { + lineno = 0; goto post; - func = tmp; + } - if (addr == (unsigned long)baseaddr) + fname = dwarf_decl_file(&spdie); + if (addr == (unsigned long)baseaddr) { /* Function entry - Relative line number is 0 */ lineno = baseline; - else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr, - &indie)) { + goto post; + } + + /* Track down the inline functions step by step */ + while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr, + &indie)) { + /* There is an inline function */ if (dwarf_entrypc(&indie, &_addr) == 0 && - _addr == addr) + _addr == addr) { /* * addr is at an inline function entry. * In this case, lineno should be the call-site - * line number. + * line number. (overwrite lineinfo) */ lineno = die_get_call_lineno(&indie); - else { + fname = die_get_call_file(&indie); + break; + } else { /* * addr is in an inline function body. * Since lineno points one of the lines @@ -1374,19 +1490,27 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr, * be the entry line of the inline function. */ tmp = dwarf_diename(&indie); - if (tmp && - dwarf_decl_line(&spdie, &baseline) == 0) - func = tmp; + if (!tmp || + dwarf_decl_line(&indie, &baseline) != 0) + break; + func = tmp; + spdie = indie; } } + /* Verify the lineno and baseline are in a same file */ + tmp = dwarf_decl_file(&spdie); + if (!tmp || strcmp(tmp, fname) != 0) + lineno = 0; } post: /* Make a relative line number or an offset */ if (lineno) ppt->line = lineno - baseline; - else if (func) + else if (basefunc) { ppt->offset = addr - (unsigned long)baseaddr; + func = basefunc; + } /* Duplicate strings */ if (func) { @@ -1474,7 +1598,7 @@ static int line_range_inline_cb(Dwarf_Die *in_die, void *data) return 0; } -/* Search function from function name */ +/* Search function definition from function name */ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) { struct dwarf_callback_param *param = data; @@ -1485,7 +1609,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die))) return DWARF_CB_OK; - if (dwarf_tag(sp_die) == DW_TAG_subprogram && + if (die_is_func_def(sp_die) && die_compare_name(sp_die, lr->function)) { lf->fname = dwarf_decl_file(sp_die); dwarf_decl_line(sp_die, &lr->offset); @@ -1516,7 +1640,7 @@ static int find_line_range_by_func(struct line_finder *lf) return param.retval; } -int debuginfo__find_line_range(struct debuginfo *self, struct line_range *lr) +int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr) { struct line_finder lf = {.lr = lr, .found = 0}; int ret = 0; @@ -1533,7 +1657,7 @@ int debuginfo__find_line_range(struct debuginfo *self, struct line_range *lr) struct dwarf_callback_param line_range_param = { .data = (void *)&lf, .retval = 0}; - dwarf_getpubnames(self->dbg, pubname_search_cb, + dwarf_getpubnames(dbg->dbg, pubname_search_cb, &pubname_param, 0); if (pubname_param.found) { line_range_search_cb(&lf.sp_die, &line_range_param); @@ -1544,12 +1668,12 @@ int debuginfo__find_line_range(struct debuginfo *self, struct line_range *lr) /* Loop on CUs (Compilation Unit) */ while (!lf.found && ret >= 0) { - if (dwarf_nextcu(self->dbg, off, &noff, &cuhl, + if (dwarf_nextcu(dbg->dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0) break; /* Get the DIE(Debugging Information Entry) of this CU */ - diep = dwarf_offdie(self->dbg, off + cuhl, &lf.cu_die); + diep = dwarf_offdie(dbg->dbg, off + cuhl, &lf.cu_die); if (!diep) continue; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 17e94d0c36f9..ffc33cdd25cc 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -7,6 +7,7 @@ #define MAX_PROBE_BUFFER 1024 #define MAX_PROBES 128 +#define MAX_PROBE_ARGS 128 static inline int is_c_varname(const char *name) { @@ -14,7 +15,7 @@ static inline int is_c_varname(const char *name) return isalpha(name[0]) || name[0] == '_'; } -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT #include "dwarf-aux.h" @@ -23,31 +24,32 @@ static inline int is_c_varname(const char *name) /* debug information structure */ struct debuginfo { Dwarf *dbg; + Dwfl_Module *mod; Dwfl *dwfl; Dwarf_Addr bias; }; extern struct debuginfo *debuginfo__new(const char *path); extern struct debuginfo *debuginfo__new_online_kernel(unsigned long addr); -extern void debuginfo__delete(struct debuginfo *self); +extern void debuginfo__delete(struct debuginfo *dbg); /* Find probe_trace_events specified by perf_probe_event from debuginfo */ -extern int debuginfo__find_trace_events(struct debuginfo *self, +extern int debuginfo__find_trace_events(struct debuginfo *dbg, struct perf_probe_event *pev, struct probe_trace_event **tevs, int max_tevs); /* Find a perf_probe_point from debuginfo */ -extern int debuginfo__find_probe_point(struct debuginfo *self, +extern int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, struct perf_probe_point *ppt); /* Find a line range */ -extern int debuginfo__find_line_range(struct debuginfo *self, +extern int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr); /* Find available variables */ -extern int debuginfo__find_available_vars_at(struct debuginfo *self, +extern int debuginfo__find_available_vars_at(struct debuginfo *dbg, struct perf_probe_event *pev, struct variable_list **vls, int max_points, bool externs); @@ -77,6 +79,7 @@ struct probe_finder { struct trace_event_finder { struct probe_finder pf; + Dwfl_Module *mod; /* For solving symbols */ struct probe_trace_event *tevs; /* Found trace events */ int ntevs; /* Number of trace events */ int max_tevs; /* Max number of trace events */ @@ -84,6 +87,7 @@ struct trace_event_finder { struct available_var_finder { struct probe_finder pf; + Dwfl_Module *mod; /* For solving symbols */ struct variable_list *vls; /* Found variable lists */ int nvls; /* Number of variable lists */ int max_vls; /* Max no. of variable lists */ @@ -102,6 +106,6 @@ struct line_finder { int found; }; -#endif /* DWARF_SUPPORT */ +#endif /* HAVE_DWARF_SUPPORT */ #endif /*_PROBE_FINDER_H */ diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h index 4cedea59f518..c3cb6584d527 100644 --- a/tools/perf/util/pstack.h +++ b/tools/perf/util/pstack.h @@ -5,10 +5,10 @@ struct pstack; struct pstack *pstack__new(unsigned short max_nr_entries); -void pstack__delete(struct pstack *self); -bool pstack__empty(const struct pstack *self); -void pstack__remove(struct pstack *self, void *key); -void pstack__push(struct pstack *self, void *key); -void *pstack__pop(struct pstack *self); +void pstack__delete(struct pstack *pstack); +bool pstack__empty(const struct pstack *pstack); +void pstack__remove(struct pstack *pstack, void *key); +void pstack__push(struct pstack *pstack, void *key); +void *pstack__pop(struct pstack *pstack); #endif /* _PERF_PSTACK_ */ diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index f75ae1b9900c..239036fb2b2c 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -17,5 +17,5 @@ util/xyarray.c util/cgroup.c util/rblist.c util/strlist.c -util/sysfs.c +util/fs.c ../../lib/rbtree.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 925e0c3e6d91..4bf8ace7f511 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -8,18 +8,31 @@ #include "cpumap.h" #include "thread_map.h" +/* + * Support debug printing even though util/debug.c is not linked. That means + * implementing 'verbose' and 'eprintf'. + */ +int verbose; + +int eprintf(int level, const char *fmt, ...) +{ + va_list args; + int ret = 0; + + if (verbose >= level) { + va_start(args, fmt); + ret = vfprintf(stderr, fmt, args); + va_end(args); + } + + return ret; +} + /* Define PyVarObject_HEAD_INIT for python 2.5 */ #ifndef PyVarObject_HEAD_INIT # define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size, #endif -struct throttle_event { - struct perf_event_header header; - u64 time; - u64 id; - u64 stream_id; -}; - PyMODINIT_FUNC initperf(void); #define member_def(type, member, ptype, help) \ @@ -802,6 +815,8 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; + perf_evlist__mmap_consume(evlist, cpu); + if (pyevent == NULL) return PyErr_NoMemory(); @@ -967,6 +982,7 @@ static struct { { "COUNT_SW_PAGE_FAULTS_MAJ", PERF_COUNT_SW_PAGE_FAULTS_MAJ }, { "COUNT_SW_ALIGNMENT_FAULTS", PERF_COUNT_SW_ALIGNMENT_FAULTS }, { "COUNT_SW_EMULATION_FAULTS", PERF_COUNT_SW_EMULATION_FAULTS }, + { "COUNT_SW_DUMMY", PERF_COUNT_SW_DUMMY }, { "SAMPLE_IP", PERF_SAMPLE_IP }, { "SAMPLE_TID", PERF_SAMPLE_TID }, @@ -1015,6 +1031,7 @@ PyMODINIT_FUNC initperf(void) pyrf_cpu_map__setup_types() < 0) return; + /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); Py_INCREF(&pyrf_evlist__type); diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c index a16cdd2625ad..0dfe27d99458 100644 --- a/tools/perf/util/rblist.c +++ b/tools/perf/util/rblist.c @@ -48,10 +48,12 @@ void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node) rblist->node_delete(rblist, rb_node); } -struct rb_node *rblist__find(struct rblist *rblist, const void *entry) +static struct rb_node *__rblist__findnew(struct rblist *rblist, + const void *entry, + bool create) { struct rb_node **p = &rblist->entries.rb_node; - struct rb_node *parent = NULL; + struct rb_node *parent = NULL, *new_node = NULL; while (*p != NULL) { int rc; @@ -67,7 +69,26 @@ struct rb_node *rblist__find(struct rblist *rblist, const void *entry) return parent; } - return NULL; + if (create) { + new_node = rblist->node_new(rblist, entry); + if (new_node) { + rb_link_node(new_node, parent, p); + rb_insert_color(new_node, &rblist->entries); + ++rblist->nr_entries; + } + } + + return new_node; +} + +struct rb_node *rblist__find(struct rblist *rblist, const void *entry) +{ + return __rblist__findnew(rblist, entry, false); +} + +struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry) +{ + return __rblist__findnew(rblist, entry, true); } void rblist__init(struct rblist *rblist) diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h index 6d0cae5ae83d..ff9913b994c2 100644 --- a/tools/perf/util/rblist.h +++ b/tools/perf/util/rblist.h @@ -32,6 +32,7 @@ void rblist__delete(struct rblist *rblist); int rblist__add_node(struct rblist *rblist, const void *new_entry); void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node); struct rb_node *rblist__find(struct rblist *rblist, const void *entry); +struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry); struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx); static inline bool rblist__empty(const struct rblist *rblist) diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c new file mode 100644 index 000000000000..c8845b107f60 --- /dev/null +++ b/tools/perf/util/record.c @@ -0,0 +1,179 @@ +#include "evlist.h" +#include "evsel.h" +#include "cpumap.h" +#include "parse-events.h" +#include "fs.h" +#include "util.h" + +typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel); + +static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) +{ + struct perf_evlist *evlist; + struct perf_evsel *evsel; + int err = -EAGAIN, fd; + + evlist = perf_evlist__new(); + if (!evlist) + return -ENOMEM; + + if (parse_events(evlist, str)) + goto out_delete; + + evsel = perf_evlist__first(evlist); + + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + if (fd < 0) + goto out_delete; + close(fd); + + fn(evsel); + + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + if (fd < 0) { + if (errno == EINVAL) + err = -EINVAL; + goto out_delete; + } + close(fd); + err = 0; + +out_delete: + perf_evlist__delete(evlist); + return err; +} + +static bool perf_probe_api(setup_probe_fn_t fn) +{ + const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL}; + struct cpu_map *cpus; + int cpu, ret, i = 0; + + cpus = cpu_map__new(NULL); + if (!cpus) + return false; + cpu = cpus->map[0]; + cpu_map__delete(cpus); + + do { + ret = perf_do_probe_api(fn, cpu, try[i++]); + if (!ret) + return true; + } while (ret == -EAGAIN && try[i]); + + return false; +} + +static void perf_probe_sample_identifier(struct perf_evsel *evsel) +{ + evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER; +} + +bool perf_can_sample_identifier(void) +{ + return perf_probe_api(perf_probe_sample_identifier); +} + +void perf_evlist__config(struct perf_evlist *evlist, + struct perf_record_opts *opts) +{ + struct perf_evsel *evsel; + bool use_sample_identifier = false; + + /* + * Set the evsel leader links before we configure attributes, + * since some might depend on this info. + */ + if (opts->group) + perf_evlist__set_leader(evlist); + + 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) { + struct perf_evsel *first = perf_evlist__first(evlist); + + list_for_each_entry(evsel, &evlist->entries, node) { + if (evsel->attr.sample_type == first->attr.sample_type) + continue; + use_sample_identifier = perf_can_sample_identifier(); + break; + } + list_for_each_entry(evsel, &evlist->entries, node) + perf_evsel__set_sample_id(evsel, use_sample_identifier); + } + + perf_evlist__set_id_pos(evlist); +} + +static int get_max_rate(unsigned int *rate) +{ + char path[PATH_MAX]; + const char *procfs = procfs__mountpoint(); + + if (!procfs) + return -1; + + snprintf(path, PATH_MAX, + "%s/sys/kernel/perf_event_max_sample_rate", procfs); + + return filename__read_int(path, (int *) rate); +} + +static int perf_record_opts__config_freq(struct perf_record_opts *opts) +{ + bool user_freq = opts->user_freq != UINT_MAX; + unsigned int max_rate; + + if (opts->user_interval != ULLONG_MAX) + opts->default_interval = opts->user_interval; + if (user_freq) + opts->freq = opts->user_freq; + + /* + * User specified count overrides default frequency. + */ + if (opts->default_interval) + opts->freq = 0; + else if (opts->freq) { + opts->default_interval = opts->freq; + } else { + pr_err("frequency and count are zero, aborting\n"); + return -1; + } + + if (get_max_rate(&max_rate)) + return 0; + + /* + * User specified frequency is over current maximum. + */ + if (user_freq && (max_rate < opts->freq)) { + pr_err("Maximum frequency rate (%u) reached.\n" + "Please use -F freq option with lower value or consider\n" + "tweaking /proc/sys/kernel/perf_event_max_sample_rate.\n", + max_rate); + return -1; + } + + /* + * Default frequency is over current maximum. + */ + if (max_rate < opts->freq) { + pr_warning("Lowering default frequency rate to %u.\n" + "Please consider tweaking " + "/proc/sys/kernel/perf_event_max_sample_rate.\n", + max_rate); + opts->freq = max_rate; + } + + return 0; +} + +int perf_record_opts__config(struct perf_record_opts *opts) +{ + return perf_record_opts__config_freq(opts); +} diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index eacec859f299..d5e5969f6fea 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -261,7 +261,8 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __maybe_unused, - struct addr_location *al) + struct thread *thread, + struct addr_location *al) { struct format_field *field; static char handler[256]; @@ -272,8 +273,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, int cpu = sample->cpu; void *data = sample->raw_data; unsigned long long nsecs = sample->time; - struct thread *thread = al->thread; - char *comm = thread->comm; + const char *comm = thread__comm_str(thread); dSP; @@ -282,7 +282,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, event = find_cache_event(evsel); if (!event) - die("ug! no event found for type %" PRIu64, evsel->attr.config); + die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); pid = raw_field_value(event, "common_pid", data); @@ -351,7 +351,8 @@ static void perl_process_event_generic(union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __maybe_unused, - struct addr_location *al __maybe_unused) + struct thread *thread __maybe_unused, + struct addr_location *al __maybe_unused) { dSP; @@ -377,10 +378,11 @@ static void perl_process_event(union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, - struct addr_location *al) + struct thread *thread, + struct addr_location *al) { - perl_process_tracepoint(event, sample, evsel, machine, al); - perl_process_event_generic(event, sample, evsel, machine, al); + perl_process_tracepoint(event, sample, evsel, machine, thread, al); + perl_process_event_generic(event, sample, evsel, machine, thread, al); } static void run_start_sub(void) diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index e87aa5d9696b..53c20e7fd900 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -56,6 +56,17 @@ static void handler_call_die(const char *handler_name) Py_FatalError("problem in Python trace event handler"); } +/* + * Insert val into into the dictionary and decrement the reference counter. + * This is necessary for dictionaries since PyDict_SetItemString() does not + * steal a reference, as opposed to PyTuple_SetItem(). + */ +static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val) +{ + PyDict_SetItemString(dict, key, val); + Py_DECREF(val); +} + static void define_value(enum print_arg_type field_type, const char *ev_name, const char *field_name, @@ -225,6 +236,7 @@ static void python_process_tracepoint(union perf_event *perf_event struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __maybe_unused, + struct thread *thread, struct addr_location *al) { PyObject *handler, *retval, *context, *t, *obj, *dict = NULL; @@ -238,8 +250,7 @@ static void python_process_tracepoint(union perf_event *perf_event int cpu = sample->cpu; void *data = sample->raw_data; unsigned long long nsecs = sample->time; - struct thread *thread = al->thread; - char *comm = thread->comm; + const char *comm = thread__comm_str(thread); t = PyTuple_New(MAX_FIELDS); if (!t) @@ -279,11 +290,11 @@ static void python_process_tracepoint(union perf_event *perf_event PyTuple_SetItem(t, n++, PyInt_FromLong(pid)); PyTuple_SetItem(t, n++, PyString_FromString(comm)); } else { - PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu)); - PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s)); - PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns)); - PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid)); - PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm)); + pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu)); + pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s)); + pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns)); + pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid)); + pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm)); } for (field = event->format.fields; field; field = field->next) { if (field->flags & FIELD_IS_STRING) { @@ -313,7 +324,7 @@ static void python_process_tracepoint(union perf_event *perf_event if (handler) PyTuple_SetItem(t, n++, obj); else - PyDict_SetItemString(dict, field->name, obj); + pydict_set_item_string_decref(dict, field->name, obj); } if (!handler) @@ -345,12 +356,12 @@ static void python_process_general_event(union perf_event *perf_event struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __maybe_unused, + struct thread *thread, struct addr_location *al) { PyObject *handler, *retval, *t, *dict; static char handler_name[64]; unsigned n = 0; - struct thread *thread = al->thread; /* * Use the MAX_FIELDS to make the function expandable, though @@ -370,21 +381,21 @@ static void python_process_general_event(union perf_event *perf_event if (!handler || !PyCallable_Check(handler)) goto exit; - PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); - PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); + pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( (const char *)&evsel->attr, sizeof(evsel->attr))); - PyDict_SetItemString(dict, "sample", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize( (const char *)sample, sizeof(*sample))); - PyDict_SetItemString(dict, "raw_buf", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( (const char *)sample->raw_data, sample->raw_size)); - PyDict_SetItemString(dict, "comm", - PyString_FromString(thread->comm)); + pydict_set_item_string_decref(dict, "comm", + PyString_FromString(thread__comm_str(thread))); if (al->map) { - PyDict_SetItemString(dict, "dso", + pydict_set_item_string_decref(dict, "dso", PyString_FromString(al->map->dso->name)); } if (al->sym) { - PyDict_SetItemString(dict, "symbol", + pydict_set_item_string_decref(dict, "symbol", PyString_FromString(al->sym->name)); } @@ -404,17 +415,18 @@ static void python_process_event(union perf_event *perf_event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, + struct thread *thread, struct addr_location *al) { switch (evsel->attr.type) { case PERF_TYPE_TRACEPOINT: python_process_tracepoint(perf_event, sample, evsel, - machine, al); + machine, thread, al); break; /* Reserve for future process_hw/sw/raw APIs */ default: python_process_general_event(perf_event, sample, evsel, - machine, al); + machine, thread, al); } } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index cf1fe01b7e89..f36d24a02445 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,4 +1,5 @@ #include <linux/kernel.h> +#include <traceevent/event-parse.h> #include <byteswap.h> #include <unistd.h> @@ -12,72 +13,37 @@ #include "sort.h" #include "util.h" #include "cpumap.h" -#include "event-parse.h" #include "perf_regs.h" #include "vdso.h" -static int perf_session__open(struct perf_session *self, bool force) +static int perf_session__open(struct perf_session *session) { - struct stat input_stat; + struct perf_data_file *file = session->file; - if (!strcmp(self->filename, "-")) { - self->fd_pipe = true; - self->fd = STDIN_FILENO; - - if (perf_session__read_header(self, self->fd) < 0) - pr_err("incompatible file format (rerun with -v to learn more)"); - - return 0; - } - - self->fd = open(self->filename, O_RDONLY); - if (self->fd < 0) { - int err = errno; - - pr_err("failed to open %s: %s", self->filename, strerror(err)); - if (err == ENOENT && !strcmp(self->filename, "perf.data")) - pr_err(" (try 'perf record' first)"); - pr_err("\n"); - return -errno; - } - - if (fstat(self->fd, &input_stat) < 0) - goto out_close; - - if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) { - pr_err("file %s not owned by current user or root\n", - self->filename); - goto out_close; - } - - if (!input_stat.st_size) { - pr_info("zero-sized file (%s), nothing to do!\n", - self->filename); - goto out_close; - } - - if (perf_session__read_header(self, self->fd) < 0) { + if (perf_session__read_header(session) < 0) { pr_err("incompatible file format (rerun with -v to learn more)"); - goto out_close; + return -1; } - if (!perf_evlist__valid_sample_type(self->evlist)) { + if (perf_data_file__is_pipe(file)) + return 0; + + if (!perf_evlist__valid_sample_type(session->evlist)) { pr_err("non matching sample_type"); - goto out_close; + return -1; } - if (!perf_evlist__valid_sample_id_all(self->evlist)) { + if (!perf_evlist__valid_sample_id_all(session->evlist)) { pr_err("non matching sample_id_all"); - goto out_close; + return -1; } - self->size = input_stat.st_size; - return 0; + if (!perf_evlist__valid_read_format(session->evlist)) { + pr_err("non matching read_format"); + return -1; + } -out_close: - close(self->fd); - self->fd = -1; - return -1; + return 0; } void perf_session__set_id_hdr_size(struct perf_session *session) @@ -87,71 +53,70 @@ void perf_session__set_id_hdr_size(struct perf_session *session) machines__set_id_hdr_size(&session->machines, id_hdr_size); } -int perf_session__create_kernel_maps(struct perf_session *self) +int perf_session__create_kernel_maps(struct perf_session *session) { - int ret = machine__create_kernel_maps(&self->machines.host); + int ret = machine__create_kernel_maps(&session->machines.host); if (ret >= 0) - ret = machines__create_guest_kernel_maps(&self->machines); + ret = machines__create_guest_kernel_maps(&session->machines); return ret; } -static void perf_session__destroy_kernel_maps(struct perf_session *self) +static void perf_session__destroy_kernel_maps(struct perf_session *session) { - machines__destroy_kernel_maps(&self->machines); + machines__destroy_kernel_maps(&session->machines); } -struct perf_session *perf_session__new(const char *filename, int mode, - bool force, bool repipe, - struct perf_tool *tool) +struct perf_session *perf_session__new(struct perf_data_file *file, + bool repipe, struct perf_tool *tool) { - 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"; - } + struct perf_session *session = zalloc(sizeof(*session)); - len = strlen(filename); - self = zalloc(sizeof(*self) + len); - - if (self == NULL) + if (!session) goto out; - memcpy(self->filename, filename, len); - self->repipe = repipe; - INIT_LIST_HEAD(&self->ordered_samples.samples); - INIT_LIST_HEAD(&self->ordered_samples.sample_cache); - INIT_LIST_HEAD(&self->ordered_samples.to_free); - machines__init(&self->machines); + session->repipe = repipe; + INIT_LIST_HEAD(&session->ordered_samples.samples); + INIT_LIST_HEAD(&session->ordered_samples.sample_cache); + INIT_LIST_HEAD(&session->ordered_samples.to_free); + machines__init(&session->machines); - if (mode == O_RDONLY) { - if (perf_session__open(self, force) < 0) + if (file) { + if (perf_data_file__open(file)) goto out_delete; - perf_session__set_id_hdr_size(self); - } else if (mode == O_WRONLY) { + + session->file = file; + + if (perf_data_file__is_read(file)) { + if (perf_session__open(session) < 0) + goto out_close; + + perf_session__set_id_hdr_size(session); + } + } + + if (!file || perf_data_file__is_write(file)) { /* * In O_RDONLY mode this will be performed when reading the * kernel MMAP event, in perf_event__process_mmap(). */ - if (perf_session__create_kernel_maps(self) < 0) + if (perf_session__create_kernel_maps(session) < 0) goto out_delete; } if (tool && tool->ordering_requires_timestamps && - tool->ordered_samples && !perf_evlist__sample_id_all(self->evlist)) { + tool->ordered_samples && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); tool->ordered_samples = false; } -out: - return self; -out_delete: - perf_session__delete(self); + return session; + + out_close: + perf_data_file__close(file); + out_delete: + perf_session__delete(session); + out: return NULL; } @@ -181,19 +146,22 @@ static void perf_session_env__delete(struct perf_session_env *env) free(env->pmu_mappings); } -void perf_session__delete(struct perf_session *self) +void perf_session__delete(struct perf_session *session) { - perf_session__destroy_kernel_maps(self); - perf_session__delete_dead_threads(self); - perf_session__delete_threads(self); - perf_session_env__delete(&self->header.env); - machines__exit(&self->machines); - close(self->fd); - free(self); + perf_session__destroy_kernel_maps(session); + perf_session__delete_dead_threads(session); + perf_session__delete_threads(session); + perf_session_env__delete(&session->header.env); + machines__exit(&session->machines); + if (session->file) + perf_data_file__close(session->file); + free(session); vdso__exit(); } -static int process_event_synth_tracing_data_stub(union perf_event *event +static int process_event_synth_tracing_data_stub(struct perf_tool *tool + __maybe_unused, + union perf_event *event __maybe_unused, struct perf_session *session __maybe_unused) @@ -202,7 +170,8 @@ static int process_event_synth_tracing_data_stub(union perf_event *event return 0; } -static int process_event_synth_attr_stub(union perf_event *event __maybe_unused, +static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, struct perf_evlist **pevlist __maybe_unused) { @@ -238,23 +207,18 @@ static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, return 0; } -static int process_event_type_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused) -{ - dump_printf(": unhandled!\n"); - return 0; -} - static int process_finished_round(struct perf_tool *tool, union perf_event *event, struct perf_session *session); -static void perf_tool__fill_defaults(struct perf_tool *tool) +void perf_tool__fill_defaults(struct perf_tool *tool) { if (tool->sample == NULL) tool->sample = process_event_sample_stub; if (tool->mmap == NULL) tool->mmap = process_event_stub; + if (tool->mmap2 == NULL) + tool->mmap2 = process_event_stub; if (tool->comm == NULL) tool->comm = process_event_stub; if (tool->fork == NULL) @@ -271,8 +235,6 @@ static void perf_tool__fill_defaults(struct perf_tool *tool) 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) @@ -352,6 +314,25 @@ static void perf_event__mmap_swap(union perf_event *event, } } +static void perf_event__mmap2_swap(union perf_event *event, + bool sample_id_all) +{ + event->mmap2.pid = bswap_32(event->mmap2.pid); + event->mmap2.tid = bswap_32(event->mmap2.tid); + event->mmap2.start = bswap_64(event->mmap2.start); + event->mmap2.len = bswap_64(event->mmap2.len); + event->mmap2.pgoff = bswap_64(event->mmap2.pgoff); + event->mmap2.maj = bswap_32(event->mmap2.maj); + event->mmap2.min = bswap_32(event->mmap2.min); + event->mmap2.ino = bswap_64(event->mmap2.ino); + + if (sample_id_all) { + void *data = &event->mmap2.filename; + + data += PERF_ALIGN(strlen(data) + 1, sizeof(u64)); + swap_sample_id_all(event, data); + } +} static void perf_event__task_swap(union perf_event *event, bool sample_id_all) { event->fork.pid = bswap_32(event->fork.pid); @@ -377,6 +358,17 @@ static void perf_event__read_swap(union perf_event *event, bool sample_id_all) swap_sample_id_all(event, &event->read + 1); } +static void perf_event__throttle_swap(union perf_event *event, + bool sample_id_all) +{ + event->throttle.time = bswap_64(event->throttle.time); + event->throttle.id = bswap_64(event->throttle.id); + event->throttle.stream_id = bswap_64(event->throttle.stream_id); + + if (sample_id_all) + swap_sample_id_all(event, &event->throttle + 1); +} + static u8 revbyte(u8 b) { int rev = (b >> 4) | ((b & 0xf) << 4); @@ -422,6 +414,9 @@ void perf_event__attr_swap(struct perf_event_attr *attr) attr->bp_type = bswap_32(attr->bp_type); attr->bp_addr = bswap_64(attr->bp_addr); attr->bp_len = bswap_64(attr->bp_len); + attr->branch_sample_type = bswap_64(attr->branch_sample_type); + attr->sample_regs_user = bswap_64(attr->sample_regs_user); + attr->sample_stack_user = bswap_32(attr->sample_stack_user); swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64)); } @@ -456,11 +451,14 @@ typedef void (*perf_event__swap_op)(union perf_event *event, static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_MMAP] = perf_event__mmap_swap, + [PERF_RECORD_MMAP2] = perf_event__mmap2_swap, [PERF_RECORD_COMM] = perf_event__comm_swap, [PERF_RECORD_FORK] = perf_event__task_swap, [PERF_RECORD_EXIT] = perf_event__task_swap, [PERF_RECORD_LOST] = perf_event__all64_swap, [PERF_RECORD_READ] = perf_event__read_swap, + [PERF_RECORD_THROTTLE] = perf_event__throttle_swap, + [PERF_RECORD_UNTHROTTLE] = perf_event__throttle_swap, [PERF_RECORD_SAMPLE] = perf_event__all64_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, @@ -496,7 +494,7 @@ static int perf_session_deliver_event(struct perf_session *session, u64 file_offset); static int flush_sample_queue(struct perf_session *s, - struct perf_tool *tool) + struct perf_tool *tool) { struct ordered_samples *os = &s->ordered_samples; struct list_head *head = &os->samples; @@ -504,13 +502,20 @@ static int 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; + bool show_progress = limit == ULLONG_MAX; + struct ui_progress prog; int ret; if (!tool->ordered_samples || !limit) return 0; + if (show_progress) + ui_progress__init(&prog, os->nr_samples, "Processing time ordered events..."); + list_for_each_entry_safe(iter, tmp, head, list) { + if (session_done()) + return 0; + if (iter->timestamp > limit) break; @@ -527,11 +532,9 @@ static int flush_sample_queue(struct perf_session *s, os->last_flush = iter->timestamp; list_del(&iter->list); list_add(&iter->list, &os->sample_cache); - if (++idx >= progress_next) { - progress_next += os->nr_samples / 16; - ui_progress__update(idx, os->nr_samples, - "Processing time ordered events..."); - } + + if (show_progress) + ui_progress__update(&prog, 1); } if (list_empty(head)) { @@ -644,7 +647,7 @@ static void __queue_event(struct sample_queue *new, struct perf_session *s) #define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct sample_queue)) -static int perf_session_queue_event(struct perf_session *s, union perf_event *event, +int perf_session_queue_event(struct perf_session *s, union perf_event *event, struct perf_sample *sample, u64 file_offset) { struct ordered_samples *os = &s->ordered_samples; @@ -740,7 +743,7 @@ static void perf_session__print_tstamp(struct perf_session *session, union perf_event *event, struct perf_sample *sample) { - u64 sample_type = perf_evlist__sample_type(session->evlist); + u64 sample_type = __perf_evlist__combined_sample_type(session->evlist); if (event->header.type != PERF_RECORD_SAMPLE && !perf_evlist__sample_id_all(session->evlist)) { @@ -755,6 +758,36 @@ static void perf_session__print_tstamp(struct perf_session *session, printf("%" PRIu64 " ", sample->time); } +static void sample_read__printf(struct perf_sample *sample, u64 read_format) +{ + printf("... sample_read:\n"); + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + printf("...... time enabled %016" PRIx64 "\n", + sample->read.time_enabled); + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + printf("...... time running %016" PRIx64 "\n", + sample->read.time_running); + + if (read_format & PERF_FORMAT_GROUP) { + u64 i; + + printf(".... group nr %" PRIu64 "\n", sample->read.group.nr); + + for (i = 0; i < sample->read.group.nr; i++) { + struct sample_read_value *value; + + value = &sample->read.group.values[i]; + printf("..... id %016" PRIx64 + ", value %016" PRIx64 "\n", + value->id, value->value); + } + } else + printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n", + sample->read.one.id, sample->read.one.value); +} + static void dump_event(struct perf_session *session, union perf_event *event, u64 file_offset, struct perf_sample *sample) { @@ -804,11 +837,18 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_DATA_SRC) printf(" . data_src: 0x%"PRIx64"\n", sample->data_src); + + if (sample_type & PERF_SAMPLE_TRANSACTION) + printf("... transaction: %" PRIx64 "\n", sample->transaction); + + if (sample_type & PERF_SAMPLE_READ) + sample_read__printf(sample, evsel->attr.read_format); } static struct machine * perf_session__find_machine_for_cpumode(struct perf_session *session, - union perf_event *event) + union perf_event *event, + struct perf_sample *sample) { const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; @@ -817,10 +857,11 @@ static struct machine * (cpumode == PERF_RECORD_MISC_GUEST_USER))) { u32 pid; - if (event->header.type == PERF_RECORD_MMAP) + if (event->header.type == PERF_RECORD_MMAP + || event->header.type == PERF_RECORD_MMAP2) pid = event->mmap.pid; else - pid = event->ip.pid; + pid = sample->pid; return perf_session__findnew_machine(session, pid); } @@ -828,6 +869,75 @@ static struct machine * return &session->machines.host; } +static int deliver_sample_value(struct perf_session *session, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct sample_read_value *v, + struct machine *machine) +{ + struct perf_sample_id *sid; + + sid = perf_evlist__id2sid(session->evlist, v->id); + if (sid) { + sample->id = v->id; + sample->period = v->value - sid->period; + sid->period = v->value; + } + + if (!sid || sid->evsel == NULL) { + ++session->stats.nr_unknown_id; + return 0; + } + + return tool->sample(tool, event, sample, sid->evsel, machine); +} + +static int deliver_sample_group(struct perf_session *session, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + int ret = -EINVAL; + u64 i; + + for (i = 0; i < sample->read.group.nr; i++) { + ret = deliver_sample_value(session, tool, event, sample, + &sample->read.group.values[i], + machine); + if (ret) + break; + } + + return ret; +} + +static int +perf_session__deliver_sample(struct perf_session *session, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + /* We know evsel != NULL. */ + u64 sample_type = evsel->attr.sample_type; + u64 read_format = evsel->attr.read_format; + + /* Standard sample delievery. */ + if (!(sample_type & PERF_SAMPLE_READ)) + return tool->sample(tool, event, sample, evsel, machine); + + /* For PERF_SAMPLE_READ we have either single or group mode. */ + if (read_format & PERF_FORMAT_GROUP) + return deliver_sample_group(session, tool, event, sample, + machine); + else + return deliver_sample_value(session, tool, event, sample, + &sample->read.one, machine); +} + static int perf_session_deliver_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, @@ -857,7 +967,8 @@ static int perf_session_deliver_event(struct perf_session *session, hists__inc_nr_events(&evsel->hists, event->header.type); } - machine = perf_session__find_machine_for_cpumode(session, event); + machine = perf_session__find_machine_for_cpumode(session, event, + sample); switch (event->header.type) { case PERF_RECORD_SAMPLE: @@ -870,9 +981,12 @@ static int perf_session_deliver_event(struct perf_session *session, ++session->stats.nr_unprocessable_samples; return 0; } - return tool->sample(tool, event, sample, evsel, machine); + return perf_session__deliver_sample(session, tool, event, + sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); + case PERF_RECORD_MMAP2: + return tool->mmap2(tool, event, sample, machine); case PERF_RECORD_COMM: return tool->comm(tool, event, sample, machine); case PERF_RECORD_FORK: @@ -895,25 +1009,10 @@ static int perf_session_deliver_event(struct perf_session *session, } } -static int perf_session__preprocess_sample(struct perf_session *session, - union perf_event *event, struct perf_sample *sample) -{ - if (event->header.type != PERF_RECORD_SAMPLE || - !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN)) - return 0; - - if (!ip_callchain__valid(sample->callchain, event)) { - pr_debug("call-chain problem with event, skipping it.\n"); - ++session->stats.nr_invalid_chains; - session->stats.total_invalid_chains += sample->period; - return -EINVAL; - } - return 0; -} - static int perf_session__process_user_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool, u64 file_offset) { + int fd = perf_data_file__fd(session->file); int err; dump_event(session, event, file_offset, NULL); @@ -921,16 +1020,14 @@ static int perf_session__process_user_event(struct perf_session *session, union /* These events are processed right away */ switch (event->header.type) { case PERF_RECORD_HEADER_ATTR: - err = tool->attr(event, &session->evlist); + err = tool->attr(tool, event, &session->evlist); if (err == 0) perf_session__set_id_hdr_size(session); return err; - case PERF_RECORD_HEADER_EVENT_TYPE: - 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 tool->tracing_data(event, session); + lseek(fd, file_offset, SEEK_SET); + return tool->tracing_data(tool, event, session); case PERF_RECORD_HEADER_BUILD_ID: return tool->build_id(tool, event, session); case PERF_RECORD_FINISHED_ROUND: @@ -975,10 +1072,6 @@ static int perf_session__process_event(struct perf_session *session, if (ret) return ret; - /* Preprocess sample records - precheck callchains */ - if (perf_session__preprocess_sample(session, event, &sample)) - return 0; - if (tool->ordered_samples) { ret = perf_session_queue_event(session, event, &sample, file_offset); @@ -990,23 +1083,23 @@ static int perf_session__process_event(struct perf_session *session, file_offset); } -void perf_event_header__bswap(struct perf_event_header *self) +void perf_event_header__bswap(struct perf_event_header *hdr) { - self->type = bswap_32(self->type); - self->misc = bswap_16(self->misc); - self->size = bswap_16(self->size); + hdr->type = bswap_32(hdr->type); + hdr->misc = bswap_16(hdr->misc); + hdr->size = bswap_16(hdr->size); } struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) { - return machine__findnew_thread(&session->machines.host, pid); + return machine__findnew_thread(&session->machines.host, 0, pid); } -static struct thread *perf_session__register_idle_thread(struct perf_session *self) +static struct thread *perf_session__register_idle_thread(struct perf_session *session) { - struct thread *thread = perf_session__findnew(self, 0); + struct thread *thread = perf_session__findnew(session, 0); - if (thread == NULL || thread__set_comm(thread, "swapper")) { + if (thread == NULL || thread__set_comm(thread, "swapper", 0)) { pr_err("problem inserting idle task.\n"); thread = NULL; } @@ -1054,12 +1147,12 @@ static void perf_session__warn_about_errors(const struct perf_session *session, } } -#define session_done() (*(volatile int *)(&session_done)) volatile int session_done; -static int __perf_session__process_pipe_events(struct perf_session *self, +static int __perf_session__process_pipe_events(struct perf_session *session, struct perf_tool *tool) { + int fd = perf_data_file__fd(session->file); union perf_event *event; uint32_t size, cur_size = 0; void *buf = NULL; @@ -1078,7 +1171,7 @@ static int __perf_session__process_pipe_events(struct perf_session *self, return -errno; more: event = buf; - err = readn(self->fd, event, sizeof(struct perf_event_header)); + err = readn(fd, event, sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) goto done; @@ -1087,12 +1180,14 @@ more: goto out_err; } - if (self->header.needs_swap) + if (session->header.needs_swap) perf_event_header__bswap(&event->header); size = event->header.size; - if (size == 0) - size = 8; + if (size < sizeof(struct perf_event_header)) { + pr_err("bad event header size\n"); + goto out_err; + } if (size > cur_size) { void *new = realloc(buf, size); @@ -1108,7 +1203,7 @@ more: p += sizeof(struct perf_event_header); if (size - sizeof(struct perf_event_header)) { - err = readn(self->fd, p, size - sizeof(struct perf_event_header)); + err = readn(fd, p, size - sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) { pr_err("unexpected end of event stream\n"); @@ -1120,7 +1215,7 @@ more: } } - if ((skip = perf_session__process_event(self, event, tool, head)) < 0) { + if ((skip = perf_session__process_event(session, event, tool, head)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", head, event->header.size, event->header.type); err = -EINVAL; @@ -1135,11 +1230,13 @@ more: if (!session_done()) goto more; done: - err = 0; + /* do the final flush for ordered samples */ + session->ordered_samples.next_flush = ULLONG_MAX; + err = flush_sample_queue(session, tool); out_err: free(buf); - perf_session__warn_about_errors(self, tool); - perf_session_free_sample_buffers(self); + perf_session__warn_about_errors(session, tool); + perf_session_free_sample_buffers(session); return err; } @@ -1161,8 +1258,12 @@ fetch_mmaped_event(struct perf_session *session, if (session->header.needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size > mmap_size) + if (head + event->header.size > mmap_size) { + /* We're not fetching the event so swap back again */ + if (session->header.needs_swap) + perf_event_header__bswap(&event->header); return NULL; + } return event; } @@ -1183,12 +1284,14 @@ int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, u64 file_size, struct perf_tool *tool) { - u64 head, page_offset, file_offset, file_pos, progress_next; + int fd = perf_data_file__fd(session->file); + u64 head, page_offset, file_offset, file_pos; int err, mmap_prot, mmap_flags, map_idx = 0; size_t mmap_size; char *buf, *mmaps[NUM_MMAPS]; union perf_event *event; uint32_t size; + struct ui_progress prog; perf_tool__fill_defaults(tool); @@ -1196,10 +1299,10 @@ int __perf_session__process_events(struct perf_session *session, file_offset = page_offset; head = data_offset - page_offset; - if (data_offset + data_size < file_size) + if (data_size && (data_offset + data_size < file_size)) file_size = data_offset + data_size; - progress_next = file_size / 16; + ui_progress__init(&prog, file_size, "Processing events..."); mmap_size = MMAP_SIZE; if (mmap_size > file_size) @@ -1215,7 +1318,7 @@ int __perf_session__process_events(struct perf_session *session, mmap_flags = MAP_PRIVATE; } remap: - buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, session->fd, + buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd, file_offset); if (buf == MAP_FAILED) { pr_err("failed to mmap file\n"); @@ -1242,7 +1345,7 @@ more: size = event->header.size; - if (size == 0 || + if (size < sizeof(struct perf_event_header) || perf_session__process_event(session, event, tool, file_pos) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", file_offset + head, event->header.size, @@ -1254,16 +1357,15 @@ more: head += size; file_pos += size; - if (file_pos >= progress_next) { - progress_next += file_size / 16; - ui_progress__update(file_pos, file_size, - "Processing events..."); - } + ui_progress__update(&prog, size); + + if (session_done()) + goto out; if (file_pos < file_size) goto more; - err = 0; +out: /* do the final flush for ordered samples */ session->ordered_samples.next_flush = ULLONG_MAX; err = flush_sample_queue(session, tool); @@ -1274,33 +1376,37 @@ out_err: return err; } -int perf_session__process_events(struct perf_session *self, +int perf_session__process_events(struct perf_session *session, struct perf_tool *tool) { + u64 size = perf_data_file__size(session->file); int err; - if (perf_session__register_idle_thread(self) == NULL) + if (perf_session__register_idle_thread(session) == NULL) return -ENOMEM; - if (!self->fd_pipe) - err = __perf_session__process_events(self, - self->header.data_offset, - self->header.data_size, - self->size, tool); + if (!perf_data_file__is_pipe(session->file)) + err = __perf_session__process_events(session, + session->header.data_offset, + session->header.data_size, + size, tool); else - err = __perf_session__process_pipe_events(self, tool); + err = __perf_session__process_pipe_events(session, tool); return err; } bool perf_session__has_traces(struct perf_session *session, const char *msg) { - if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) { - pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg); - return false; + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &session->evlist->entries, node) { + if (evsel->attr.type == PERF_TYPE_TRACEPOINT) + return true; } - return true; + pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg); + return false; } int maps__set_kallsyms_ref_reloc_sym(struct map **maps, @@ -1334,15 +1440,15 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps, return 0; } -size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp) +size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp) { - return machines__fprintf_dsos(&self->machines, fp); + return machines__fprintf_dsos(&session->machines, fp); } -size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp, +size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm) { - return machines__fprintf_dsos_buildid(&self->machines, fp, skip, parm); + return machines__fprintf_dsos_buildid(&session->machines, fp, skip, parm); } size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) @@ -1383,13 +1489,18 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample, struct machine *machine, - int print_sym, int print_dso, int print_symoffset) + unsigned int print_opts, unsigned int stack_depth) { struct addr_location al; struct callchain_cursor_node *node; - - if (perf_event__preprocess_sample(event, machine, &al, sample, - NULL) < 0) { + int print_ip = print_opts & PRINT_IP_OPT_IP; + int print_sym = print_opts & PRINT_IP_OPT_SYM; + int print_dso = print_opts & PRINT_IP_OPT_DSO; + int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET; + int print_oneline = print_opts & PRINT_IP_OPT_ONELINE; + char s = print_oneline ? ' ' : '\t'; + + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { error("problem processing %d event, skipping it.\n", event->header.type); return; @@ -1397,37 +1508,51 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, if (symbol_conf.use_callchain && sample->callchain) { - if (machine__resolve_callchain(machine, evsel, al.thread, - sample, NULL) != 0) { + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); return; } callchain_cursor_commit(&callchain_cursor); - while (1) { + while (stack_depth) { node = callchain_cursor_current(&callchain_cursor); if (!node) break; - printf("\t%16" PRIx64, node->ip); + if (print_ip) + printf("%c%16" PRIx64, s, node->ip); + if (print_sym) { printf(" "); - symbol__fprintf_symname(node->sym, stdout); + if (print_symoffset) { + al.addr = node->ip; + al.map = node->map; + symbol__fprintf_symname_offs(node->sym, &al, stdout); + } else + symbol__fprintf_symname(node->sym, stdout); } + if (print_dso) { printf(" ("); map__fprintf_dsoname(node->map, stdout); printf(")"); } - printf("\n"); + + if (!print_oneline) + printf("\n"); callchain_cursor_advance(&callchain_cursor); + + stack_depth--; } } else { - printf("%16" PRIx64, sample->ip); + if (print_ip) + printf("%16" PRIx64, sample->ip); + if (print_sym) { printf(" "); if (print_symoffset) @@ -1489,13 +1614,14 @@ int perf_session__cpu_bitmap(struct perf_session *session, void perf_session__fprintf_info(struct perf_session *session, FILE *fp, bool full) { + int fd = perf_data_file__fd(session->file); struct stat st; int ret; if (session == NULL || fp == NULL) return; - ret = fstat(session->fd, &st); + ret = fstat(fd, &st); if (ret == -1) return; @@ -1510,52 +1636,26 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, const struct perf_evsel_str_handler *assocs, size_t nr_assocs) { - struct perf_evlist *evlist = session->evlist; - struct event_format *format; struct perf_evsel *evsel; - char *tracepoint, *name; size_t i; int err; for (i = 0; i < nr_assocs; i++) { - err = -ENOMEM; - tracepoint = strdup(assocs[i].name); - if (tracepoint == NULL) - goto out; - - err = -ENOENT; - name = strchr(tracepoint, ':'); - if (name == NULL) - goto out_free; - - *name++ = '\0'; - format = pevent_find_event_by_name(session->pevent, - tracepoint, name); - if (format == NULL) { - /* - * Adding a handler for an event not in the session, - * just ignore it. - */ - goto next; - } - - evsel = perf_evlist__find_tracepoint_by_id(evlist, format->id); + /* + * Adding a handler for an event not in the session, + * just ignore it. + */ + evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name); if (evsel == NULL) - goto next; + continue; err = -EEXIST; - if (evsel->handler.func != NULL) - goto out_free; - evsel->handler.func = assocs[i].handler; -next: - free(tracepoint); + if (evsel->handler != NULL) + goto out; + evsel->handler = assocs[i].handler; } err = 0; out: return err; - -out_free: - free(tracepoint); - goto out; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index f3b235ec7bf4..50f640958f0f 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -7,6 +7,7 @@ #include "machine.h" #include "symbol.h" #include "thread.h" +#include "data.h" #include <linux/rbtree.h> #include <linux/perf_event.h> @@ -29,65 +30,72 @@ struct ordered_samples { struct perf_session { struct perf_header header; - unsigned long size; struct machines machines; struct perf_evlist *evlist; struct pevent *pevent; struct events_stats stats; - int fd; - bool fd_pipe; bool repipe; - char *cwd; struct ordered_samples ordered_samples; - char filename[1]; + struct perf_data_file *file; }; +#define PRINT_IP_OPT_IP (1<<0) +#define PRINT_IP_OPT_SYM (1<<1) +#define PRINT_IP_OPT_DSO (1<<2) +#define PRINT_IP_OPT_SYMOFFSET (1<<3) +#define PRINT_IP_OPT_ONELINE (1<<4) + struct perf_tool; -struct perf_session *perf_session__new(const char *filename, int mode, - bool force, bool repipe, - struct perf_tool *tool); +struct perf_session *perf_session__new(struct perf_data_file *file, + bool repipe, struct perf_tool *tool); void perf_session__delete(struct perf_session *session); -void perf_event_header__bswap(struct perf_event_header *self); +void perf_event_header__bswap(struct perf_event_header *hdr); -int __perf_session__process_events(struct perf_session *self, +int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, u64 size, struct perf_tool *tool); -int perf_session__process_events(struct perf_session *self, +int perf_session__process_events(struct perf_session *session, struct perf_tool *tool); -int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel *evsel, +int perf_session_queue_event(struct perf_session *s, union perf_event *event, + struct perf_sample *sample, u64 file_offset); + +void perf_tool__fill_defaults(struct perf_tool *tool); + +int perf_session__resolve_callchain(struct perf_session *session, + 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); +bool perf_session__has_traces(struct perf_session *session, const char *msg); void mem_bswap_64(void *src, int byte_size); void mem_bswap_32(void *src, int byte_size); void perf_event__attr_swap(struct perf_event_attr *attr); -int perf_session__create_kernel_maps(struct perf_session *self); +int perf_session__create_kernel_maps(struct perf_session *session); void perf_session__set_id_hdr_size(struct perf_session *session); static inline -struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid) +struct machine *perf_session__find_machine(struct perf_session *session, pid_t pid) { - return machines__find(&self->machines, pid); + return machines__find(&session->machines, pid); } static inline -struct machine *perf_session__findnew_machine(struct perf_session *self, pid_t pid) +struct machine *perf_session__findnew_machine(struct perf_session *session, pid_t pid) { - return machines__findnew(&self->machines, pid); + return machines__findnew(&session->machines, pid); } -struct thread *perf_session__findnew(struct perf_session *self, pid_t pid); -size_t perf_session__fprintf(struct perf_session *self, FILE *fp); +struct thread *perf_session__findnew(struct perf_session *session, pid_t pid); +size_t perf_session__fprintf(struct perf_session *session, FILE *fp); -size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp); +size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp); size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp, bool (fn)(struct dso *dso, int parm), int parm); @@ -99,7 +107,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample, struct machine *machine, - int print_sym, int print_dso, int print_symoffset); + unsigned int print_opts, unsigned int stack_depth); int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); @@ -114,4 +122,8 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, #define perf_session__set_tracepoints_handlers(session, array) \ __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array)) + +extern volatile int session_done; + +#define session_done() (*(volatile int *)(&session_done)) #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 313a5a730112..3c1b75c8b9a6 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,5 +1,6 @@ #include "sort.h" #include "hist.h" +#include "comm.h" #include "symbol.h" regex_t parent_regex; @@ -7,6 +8,8 @@ const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; const char default_sort_order[] = "comm,dso,symbol"; const char *sort_order = default_sort_order; +regex_t ignore_callees_regex; +int have_ignore_callees = 0; int sort__need_collapse = 0; int sort__has_parent = 0; int sort__has_sym = 0; @@ -40,7 +43,7 @@ static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) return n; } -static int64_t cmp_null(void *l, void *r) +static int64_t cmp_null(const void *l, const void *r) { if (!l && !r) return 0; @@ -55,14 +58,15 @@ static int64_t cmp_null(void *l, void *r) static int64_t sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) { - return right->thread->pid - left->thread->pid; + return right->thread->tid - left->thread->tid; } -static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { + const char *comm = thread__comm_str(he->thread); return repsep_snprintf(bf, size, "%*s:%5d", width - 6, - self->thread->comm ?: "", self->thread->pid); + comm ?: "", he->thread->tid); } struct sort_entry sort_thread = { @@ -77,25 +81,21 @@ struct sort_entry sort_thread = { static int64_t sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) { - return right->thread->pid - left->thread->pid; + /* Compare the addr that should be unique among comm */ + return comm__str(right->comm) - comm__str(left->comm); } static int64_t sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) { - char *comm_l = left->thread->comm; - char *comm_r = right->thread->comm; - - if (!comm_l || !comm_r) - return cmp_null(comm_l, comm_r); - - return strcmp(comm_l, comm_r); + /* Compare the addr that should be unique among comm */ + return comm__str(right->comm) - comm__str(left->comm); } -static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*s", width, self->thread->comm); + return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm)); } struct sort_entry sort_comm = { @@ -146,10 +146,10 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf, return repsep_snprintf(bf, size, "%-*s", width, "[unknown]"); } -static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__dso_snprintf(self->ms.map, bf, size, width); + return _hist_entry__dso_snprintf(he->ms.map, bf, size, width); } struct sort_entry sort_dso = { @@ -180,9 +180,19 @@ static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r) static int64_t sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) { + int64_t ret; + if (!left->ms.sym && !right->ms.sym) return right->level - left->level; + /* + * comparing symbol address alone is not enough since it's a + * relative address within a dso. + */ + ret = sort__dso_cmp(left, right); + if (ret != 0) + return ret; + return _sort__sym_cmp(left->ms.sym, right->ms.sym); } @@ -222,11 +232,11 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, return ret; } -static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip, - self->level, bf, size, width); + return _hist_entry__sym_snprintf(he->ms.map, he->ms.sym, he->ip, + he->level, bf, size, width); } struct sort_entry sort_sym = { @@ -241,50 +251,32 @@ struct sort_entry sort_sym = { static int64_t sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) { - return (int64_t)(right->ip - left->ip); + if (!left->srcline) { + if (!left->ms.map) + left->srcline = SRCLINE_UNKNOWN; + else { + struct map *map = left->ms.map; + left->srcline = get_srcline(map->dso, + map__rip_2objdump(map, left->ip)); + } + } + if (!right->srcline) { + if (!right->ms.map) + right->srcline = SRCLINE_UNKNOWN; + else { + struct map *map = right->ms.map; + right->srcline = get_srcline(map->dso, + map__rip_2objdump(map, right->ip)); + } + } + return strcmp(left->srcline, right->srcline); } -static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width __maybe_unused) { - FILE *fp = NULL; - char cmd[PATH_MAX + 2], *path = self->srcline, *nl; - size_t line_len; - - if (path != NULL) - goto out_path; - - if (!self->ms.map) - goto out_ip; - - if (!strncmp(self->ms.map->dso->long_name, "/tmp/perf-", 10)) - goto out_ip; - - snprintf(cmd, sizeof(cmd), "addr2line -e %s %016" PRIx64, - self->ms.map->dso->long_name, self->ip); - fp = popen(cmd, "r"); - if (!fp) - goto out_ip; - - if (getline(&path, &line_len, fp) < 0 || !line_len) - goto out_ip; - self->srcline = strdup(path); - if (self->srcline == NULL) - goto out_ip; - - nl = strchr(self->srcline, '\n'); - if (nl != NULL) - *nl = '\0'; - path = self->srcline; -out_path: - if (fp) - pclose(fp); - return repsep_snprintf(bf, size, "%s", path); -out_ip: - if (fp) - pclose(fp); - return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip); + return repsep_snprintf(bf, size, "%s", he->srcline); } struct sort_entry sort_srcline = { @@ -308,11 +300,11 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) return strcmp(sym_l->name, sym_r->name); } -static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { return repsep_snprintf(bf, size, "%-*s", width, - self->parent ? self->parent->name : "[other]"); + he->parent ? he->parent->name : "[other]"); } struct sort_entry sort_parent = { @@ -330,10 +322,10 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right) return right->cpu - left->cpu; } -static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width) +static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*d", width, self->cpu); + return repsep_snprintf(bf, size, "%*d", width, he->cpu); } struct sort_entry sort_cpu = { @@ -352,10 +344,10 @@ sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) right->branch_info->from.map); } -static int hist_entry__dso_from_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__dso_snprintf(self->branch_info->from.map, + return _hist_entry__dso_snprintf(he->branch_info->from.map, bf, size, width); } @@ -366,10 +358,10 @@ sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) right->branch_info->to.map); } -static int hist_entry__dso_to_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__dso_snprintf(self->branch_info->to.map, + return _hist_entry__dso_snprintf(he->branch_info->to.map, bf, size, width); } @@ -397,21 +389,21 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) return _sort__sym_cmp(to_l->sym, to_r->sym); } -static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - struct addr_map_symbol *from = &self->branch_info->from; + struct addr_map_symbol *from = &he->branch_info->from; return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, - self->level, bf, size, width); + he->level, bf, size, width); } -static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - struct addr_map_symbol *to = &self->branch_info->to; + struct addr_map_symbol *to = &he->branch_info->to; return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, - self->level, bf, size, width); + he->level, bf, size, width); } @@ -454,13 +446,13 @@ sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right) return mp || p; } -static int hist_entry__mispredict_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width){ static const char *out = "N/A"; - if (self->branch_info->flags.predicted) + if (he->branch_info->flags.predicted) out = "N"; - else if (self->branch_info->flags.mispred) + else if (he->branch_info->flags.mispred) out = "Y"; return repsep_snprintf(bf, size, "%-*s", width, out); @@ -480,19 +472,19 @@ sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right) return (int64_t)(r - l); } -static int hist_entry__daddr_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { uint64_t addr = 0; struct map *map = NULL; struct symbol *sym = NULL; - if (self->mem_info) { - addr = self->mem_info->daddr.addr; - map = self->mem_info->daddr.map; - sym = self->mem_info->daddr.sym; + if (he->mem_info) { + addr = he->mem_info->daddr.addr; + map = he->mem_info->daddr.map; + sym = he->mem_info->daddr.sym; } - return _hist_entry__sym_snprintf(map, sym, addr, self->level, bf, size, + return _hist_entry__sym_snprintf(map, sym, addr, he->level, bf, size, width); } @@ -510,13 +502,13 @@ sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right) return _sort__dso_cmp(map_l, map_r); } -static int hist_entry__dso_daddr_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__dso_daddr_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { struct map *map = NULL; - if (self->mem_info) - map = self->mem_info->daddr.map; + if (he->mem_info) + map = he->mem_info->daddr.map; return _hist_entry__dso_snprintf(map, bf, size, width); } @@ -540,14 +532,14 @@ sort__locked_cmp(struct hist_entry *left, struct hist_entry *right) return (int64_t)(data_src_r.mem_lock - data_src_l.mem_lock); } -static int hist_entry__locked_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { const char *out; u64 mask = PERF_MEM_LOCK_NA; - if (self->mem_info) - mask = self->mem_info->data_src.mem_lock; + if (he->mem_info) + mask = he->mem_info->data_src.mem_lock; if (mask & PERF_MEM_LOCK_NA) out = "N/A"; @@ -589,7 +581,7 @@ static const char * const tlb_access[] = { }; #define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *)) -static int hist_entry__tlb_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { char out[64]; @@ -600,8 +592,8 @@ static int hist_entry__tlb_snprintf(struct hist_entry *self, char *bf, out[0] = '\0'; - if (self->mem_info) - m = self->mem_info->data_src.mem_dtlb; + if (he->mem_info) + m = he->mem_info->data_src.mem_dtlb; hit = m & PERF_MEM_TLB_HIT; miss = m & PERF_MEM_TLB_MISS; @@ -666,7 +658,7 @@ static const char * const mem_lvl[] = { }; #define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *)) -static int hist_entry__lvl_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { char out[64]; @@ -675,8 +667,8 @@ static int hist_entry__lvl_snprintf(struct hist_entry *self, char *bf, u64 m = PERF_MEM_LVL_NA; u64 hit, miss; - if (self->mem_info) - m = self->mem_info->data_src.mem_lvl; + if (he->mem_info) + m = he->mem_info->data_src.mem_lvl; out[0] = '\0'; @@ -734,7 +726,7 @@ static const char * const snoop_access[] = { }; #define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *)) -static int hist_entry__snoop_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { char out[64]; @@ -744,8 +736,8 @@ static int hist_entry__snoop_snprintf(struct hist_entry *self, char *bf, out[0] = '\0'; - if (self->mem_info) - m = self->mem_info->data_src.mem_snoop; + if (he->mem_info) + m = he->mem_info->data_src.mem_snoop; for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) { if (!(m & 0x1)) @@ -782,10 +774,10 @@ sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right) return he_weight(left) - he_weight(right); } -static int hist_entry__local_weight_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*llu", width, he_weight(self)); + return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he)); } struct sort_entry sort_local_weight = { @@ -801,10 +793,10 @@ sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right) return left->stat.weight - right->stat.weight; } -static int hist_entry__global_weight_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*llu", width, self->stat.weight); + return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight); } struct sort_entry sort_global_weight = { @@ -856,6 +848,127 @@ struct sort_entry sort_mem_snoop = { .se_width_idx = HISTC_MEM_SNOOP, }; +static int64_t +sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->branch_info->flags.abort != + right->branch_info->flags.abort; +} + +static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + static const char *out = "."; + + if (he->branch_info->flags.abort) + out = "A"; + return repsep_snprintf(bf, size, "%-*s", width, out); +} + +struct sort_entry sort_abort = { + .se_header = "Transaction abort", + .se_cmp = sort__abort_cmp, + .se_snprintf = hist_entry__abort_snprintf, + .se_width_idx = HISTC_ABORT, +}; + +static int64_t +sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->branch_info->flags.in_tx != + right->branch_info->flags.in_tx; +} + +static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + static const char *out = "."; + + if (he->branch_info->flags.in_tx) + out = "T"; + + return repsep_snprintf(bf, size, "%-*s", width, out); +} + +struct sort_entry sort_in_tx = { + .se_header = "Branch in transaction", + .se_cmp = sort__in_tx_cmp, + .se_snprintf = hist_entry__in_tx_snprintf, + .se_width_idx = HISTC_IN_TX, +}; + +static int64_t +sort__transaction_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->transaction - right->transaction; +} + +static inline char *add_str(char *p, const char *str) +{ + strcpy(p, str); + return p + strlen(str); +} + +static struct txbit { + unsigned flag; + const char *name; + int skip_for_len; +} txbits[] = { + { PERF_TXN_ELISION, "EL ", 0 }, + { PERF_TXN_TRANSACTION, "TX ", 1 }, + { PERF_TXN_SYNC, "SYNC ", 1 }, + { PERF_TXN_ASYNC, "ASYNC ", 0 }, + { PERF_TXN_RETRY, "RETRY ", 0 }, + { PERF_TXN_CONFLICT, "CON ", 0 }, + { PERF_TXN_CAPACITY_WRITE, "CAP-WRITE ", 1 }, + { PERF_TXN_CAPACITY_READ, "CAP-READ ", 0 }, + { 0, NULL, 0 } +}; + +int hist_entry__transaction_len(void) +{ + int i; + int len = 0; + + for (i = 0; txbits[i].name; i++) { + if (!txbits[i].skip_for_len) + len += strlen(txbits[i].name); + } + len += 4; /* :XX<space> */ + return len; +} + +static int hist_entry__transaction_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + u64 t = he->transaction; + char buf[128]; + char *p = buf; + int i; + + buf[0] = 0; + for (i = 0; txbits[i].name; i++) + if (txbits[i].flag & t) + p = add_str(p, txbits[i].name); + if (t && !(t & (PERF_TXN_SYNC|PERF_TXN_ASYNC))) + p = add_str(p, "NEITHER "); + if (t & PERF_TXN_ABORT_MASK) { + sprintf(p, ":%" PRIx64, + (t & PERF_TXN_ABORT_MASK) >> + PERF_TXN_ABORT_SHIFT); + p += strlen(p); + } + + return repsep_snprintf(bf, size, "%-*s", width, buf); +} + +struct sort_entry sort_transaction = { + .se_header = "Transaction ", + .se_cmp = sort__transaction_cmp, + .se_snprintf = hist_entry__transaction_snprintf, + .se_width_idx = HISTC_TRANSACTION, +}; + struct sort_dimension { const char *name; struct sort_entry *entry; @@ -872,6 +985,9 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_PARENT, "parent", sort_parent), DIM(SORT_CPU, "cpu", sort_cpu), DIM(SORT_SRCLINE, "srcline", sort_srcline), + DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight), + DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), + DIM(SORT_TRANSACTION, "transaction", sort_transaction), }; #undef DIM @@ -884,6 +1000,8 @@ static struct sort_dimension bstack_sort_dimensions[] = { DIM(SORT_SYM_FROM, "symbol_from", sort_sym_from), DIM(SORT_SYM_TO, "symbol_to", sort_sym_to), DIM(SORT_MISPREDICT, "mispredict", sort_mispredict), + DIM(SORT_IN_TX, "in_tx", sort_in_tx), + DIM(SORT_ABORT, "abort", sort_abort), }; #undef DIM @@ -891,8 +1009,6 @@ static struct sort_dimension bstack_sort_dimensions[] = { #define DIM(d, n, func) [d - __SORT_MEMORY_MODE] = { .name = n, .entry = &(func) } static struct sort_dimension memory_sort_dimensions[] = { - DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight), - DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym), DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso), DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked), @@ -1007,7 +1123,7 @@ int setup_sorting(void) return ret; } -static void sort_entry__setup_elide(struct sort_entry *self, +static void sort_entry__setup_elide(struct sort_entry *se, struct strlist *list, const char *list_name, FILE *fp) { @@ -1015,7 +1131,7 @@ static void sort_entry__setup_elide(struct sort_entry *self, if (fp != NULL) fprintf(fp, "# %s: %s\n", list_name, strlist__entry(list, 0)->s); - self->elide = true; + se->elide = true; } } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 45ac84c1e037..43e5ff42a609 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -22,13 +22,14 @@ #include "parse-events.h" #include "thread.h" -#include "sort.h" extern regex_t parent_regex; extern const char *sort_order; extern const char default_parent_pattern[]; extern const char *parent_pattern; extern const char default_sort_order[]; +extern regex_t ignore_callees_regex; +extern int have_ignore_callees; extern int sort__need_collapse; extern int sort__has_parent; extern int sort__has_sym; @@ -82,11 +83,16 @@ struct hist_entry { struct he_stat stat; struct map_symbol ms; struct thread *thread; + struct comm *comm; u64 ip; + u64 transaction; s32 cpu; struct hist_entry_diff diff; + /* We are added by hists__add_dummy_entry. */ + bool dummy; + /* XXX These two should move to some tree widget lib */ u16 row_offset; u16 nr_rows; @@ -138,6 +144,9 @@ enum sort_type { SORT_PARENT, SORT_CPU, SORT_SRCLINE, + SORT_LOCAL_WEIGHT, + SORT_GLOBAL_WEIGHT, + SORT_TRANSACTION, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, @@ -146,12 +155,12 @@ enum sort_type { SORT_SYM_FROM, SORT_SYM_TO, SORT_MISPREDICT, + SORT_ABORT, + SORT_IN_TX, /* memory mode specific sort keys */ __SORT_MEMORY_MODE, - SORT_LOCAL_WEIGHT = __SORT_MEMORY_MODE, - SORT_GLOBAL_WEIGHT, - SORT_MEM_DADDR_SYMBOL, + SORT_MEM_DADDR_SYMBOL = __SORT_MEMORY_MODE, SORT_MEM_DADDR_DSO, SORT_MEM_LOCKED, SORT_MEM_TLB, @@ -170,7 +179,7 @@ struct sort_entry { int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *); int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *); - int (*se_snprintf)(struct hist_entry *self, char *bf, size_t size, + int (*se_snprintf)(struct hist_entry *he, char *bf, size_t size, unsigned int width); u8 se_width_idx; bool elide; @@ -183,4 +192,6 @@ int setup_sorting(void); extern int sort_dimension__add(const char *); void sort__setup_elide(FILE *fp); +int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); + #endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c new file mode 100644 index 000000000000..d11aefbc4b8d --- /dev/null +++ b/tools/perf/util/srcline.c @@ -0,0 +1,265 @@ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <linux/kernel.h> + +#include "util/dso.h" +#include "util/util.h" +#include "util/debug.h" + +#ifdef HAVE_LIBBFD_SUPPORT + +/* + * Implement addr2line using libbfd. + */ +#define PACKAGE "perf" +#include <bfd.h> + +struct a2l_data { + const char *input; + unsigned long addr; + + bool found; + const char *filename; + const char *funcname; + unsigned line; + + bfd *abfd; + asymbol **syms; +}; + +static int bfd_error(const char *string) +{ + const char *errmsg; + + errmsg = bfd_errmsg(bfd_get_error()); + fflush(stdout); + + if (string) + pr_debug("%s: %s\n", string, errmsg); + else + pr_debug("%s\n", errmsg); + + return -1; +} + +static int slurp_symtab(bfd *abfd, struct a2l_data *a2l) +{ + long storage; + long symcount; + asymbol **syms; + bfd_boolean dynamic = FALSE; + + if ((bfd_get_file_flags(abfd) & HAS_SYMS) == 0) + return bfd_error(bfd_get_filename(abfd)); + + storage = bfd_get_symtab_upper_bound(abfd); + if (storage == 0L) { + storage = bfd_get_dynamic_symtab_upper_bound(abfd); + dynamic = TRUE; + } + if (storage < 0L) + return bfd_error(bfd_get_filename(abfd)); + + syms = malloc(storage); + if (dynamic) + symcount = bfd_canonicalize_dynamic_symtab(abfd, syms); + else + symcount = bfd_canonicalize_symtab(abfd, syms); + + if (symcount < 0) { + free(syms); + return bfd_error(bfd_get_filename(abfd)); + } + + a2l->syms = syms; + return 0; +} + +static void find_address_in_section(bfd *abfd, asection *section, void *data) +{ + bfd_vma pc, vma; + bfd_size_type size; + struct a2l_data *a2l = data; + + if (a2l->found) + return; + + if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0) + return; + + pc = a2l->addr; + vma = bfd_get_section_vma(abfd, section); + size = bfd_get_section_size(section); + + if (pc < vma || pc >= vma + size) + return; + + a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma, + &a2l->filename, &a2l->funcname, + &a2l->line); +} + +static struct a2l_data *addr2line_init(const char *path) +{ + bfd *abfd; + struct a2l_data *a2l = NULL; + + abfd = bfd_openr(path, NULL); + if (abfd == NULL) + return NULL; + + if (!bfd_check_format(abfd, bfd_object)) + goto out; + + a2l = zalloc(sizeof(*a2l)); + if (a2l == NULL) + goto out; + + a2l->abfd = abfd; + a2l->input = strdup(path); + if (a2l->input == NULL) + goto out; + + if (slurp_symtab(abfd, a2l)) + goto out; + + return a2l; + +out: + if (a2l) { + free((void *)a2l->input); + free(a2l); + } + bfd_close(abfd); + return NULL; +} + +static void addr2line_cleanup(struct a2l_data *a2l) +{ + if (a2l->abfd) + bfd_close(a2l->abfd); + free((void *)a2l->input); + free(a2l->syms); + free(a2l); +} + +static int addr2line(const char *dso_name, unsigned long addr, + char **file, unsigned int *line) +{ + int ret = 0; + struct a2l_data *a2l; + + a2l = addr2line_init(dso_name); + if (a2l == NULL) { + pr_warning("addr2line_init failed for %s\n", dso_name); + return 0; + } + + a2l->addr = addr; + bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l); + + if (a2l->found && a2l->filename) { + *file = strdup(a2l->filename); + *line = a2l->line; + + if (*file) + ret = 1; + } + + addr2line_cleanup(a2l); + return ret; +} + +#else /* HAVE_LIBBFD_SUPPORT */ + +static int addr2line(const char *dso_name, unsigned long addr, + char **file, unsigned int *line_nr) +{ + FILE *fp; + char cmd[PATH_MAX]; + char *filename = NULL; + size_t len; + char *sep; + int ret = 0; + + scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64, + dso_name, addr); + + fp = popen(cmd, "r"); + if (fp == NULL) { + pr_warning("popen failed for %s\n", dso_name); + return 0; + } + + if (getline(&filename, &len, fp) < 0 || !len) { + pr_warning("addr2line has no output for %s\n", dso_name); + goto out; + } + + sep = strchr(filename, '\n'); + if (sep) + *sep = '\0'; + + if (!strcmp(filename, "??:0")) { + pr_debug("no debugging info in %s\n", dso_name); + free(filename); + goto out; + } + + sep = strchr(filename, ':'); + if (sep) { + *sep++ = '\0'; + *file = filename; + *line_nr = strtoul(sep, NULL, 0); + ret = 1; + } +out: + pclose(fp); + return ret; +} +#endif /* HAVE_LIBBFD_SUPPORT */ + +char *get_srcline(struct dso *dso, unsigned long addr) +{ + char *file = NULL; + unsigned line = 0; + char *srcline; + char *dso_name = dso->long_name; + size_t size; + + if (!dso->has_srcline) + return SRCLINE_UNKNOWN; + + if (dso_name[0] == '[') + goto out; + + if (!strncmp(dso_name, "/tmp/perf-", 10)) + goto out; + + if (!addr2line(dso_name, addr, &file, &line)) + goto out; + + /* just calculate actual length */ + size = snprintf(NULL, 0, "%s:%u", file, line) + 1; + + srcline = malloc(size); + if (srcline) + snprintf(srcline, size, "%s:%u", file, line); + else + srcline = SRCLINE_UNKNOWN; + + free(file); + return srcline; + +out: + dso->has_srcline = 0; + return SRCLINE_UNKNOWN; +} + +void free_srcline(char *srcline) +{ + if (srcline && strcmp(srcline, SRCLINE_UNKNOWN) != 0) + free(srcline); +} diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 7c59c28afcc5..6506b3dfb605 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -10,6 +10,12 @@ void update_stats(struct stats *stats, u64 val) delta = val - stats->mean; stats->mean += delta / stats->n; stats->M2 += delta*(val - stats->mean); + + if (val > stats->max) + stats->max = val; + + if (val < stats->min) + stats->min = val; } double avg_stats(struct stats *stats) diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 588367c3c767..ae8ccd7227cf 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -6,6 +6,7 @@ struct stats { double n, mean, M2; + u64 max, min; }; void update_stats(struct stats *stats, u64 val); @@ -13,4 +14,12 @@ double avg_stats(struct stats *stats); double stddev_stats(struct stats *stats); double rel_stddev_stats(double stddev, double avg); +static inline void init_stats(struct stats *stats) +{ + stats->n = 0.0; + stats->mean = 0.0; + stats->M2 = 0.0; + stats->min = (u64) -1; + stats->max = 0; +} #endif diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c index 834c8ebfe38e..3edd0538161f 100644 --- a/tools/perf/util/strfilter.c +++ b/tools/perf/util/strfilter.c @@ -10,22 +10,22 @@ static const char *OP_not = "!"; /* Logical NOT */ #define is_operator(c) ((c) == '|' || (c) == '&' || (c) == '!') #define is_separator(c) (is_operator(c) || (c) == '(' || (c) == ')') -static void strfilter_node__delete(struct strfilter_node *self) +static void strfilter_node__delete(struct strfilter_node *node) { - if (self) { - if (self->p && !is_operator(*self->p)) - free((char *)self->p); - strfilter_node__delete(self->l); - strfilter_node__delete(self->r); - free(self); + if (node) { + if (node->p && !is_operator(*node->p)) + free((char *)node->p); + strfilter_node__delete(node->l); + strfilter_node__delete(node->r); + free(node); } } -void strfilter__delete(struct strfilter *self) +void strfilter__delete(struct strfilter *filter) { - if (self) { - strfilter_node__delete(self->root); - free(self); + if (filter) { + strfilter_node__delete(filter->root); + free(filter); } } @@ -62,15 +62,15 @@ static struct strfilter_node *strfilter_node__alloc(const char *op, struct strfilter_node *l, struct strfilter_node *r) { - struct strfilter_node *ret = zalloc(sizeof(struct strfilter_node)); + struct strfilter_node *node = zalloc(sizeof(*node)); - if (ret) { - ret->p = op; - ret->l = l; - ret->r = r; + if (node) { + node->p = op; + node->l = l; + node->r = r; } - return ret; + return node; } static struct strfilter_node *strfilter_node__new(const char *s, @@ -154,46 +154,46 @@ error: */ struct strfilter *strfilter__new(const char *rules, const char **err) { - struct strfilter *ret = zalloc(sizeof(struct strfilter)); + struct strfilter *filter = zalloc(sizeof(*filter)); const char *ep = NULL; - if (ret) - ret->root = strfilter_node__new(rules, &ep); + if (filter) + filter->root = strfilter_node__new(rules, &ep); - if (!ret || !ret->root || *ep != '\0') { + if (!filter || !filter->root || *ep != '\0') { if (err) *err = ep; - strfilter__delete(ret); - ret = NULL; + strfilter__delete(filter); + filter = NULL; } - return ret; + return filter; } -static bool strfilter_node__compare(struct strfilter_node *self, +static bool strfilter_node__compare(struct strfilter_node *node, const char *str) { - if (!self || !self->p) + if (!node || !node->p) return false; - switch (*self->p) { + switch (*node->p) { case '|': /* OR */ - return strfilter_node__compare(self->l, str) || - strfilter_node__compare(self->r, str); + return strfilter_node__compare(node->l, str) || + strfilter_node__compare(node->r, str); case '&': /* AND */ - return strfilter_node__compare(self->l, str) && - strfilter_node__compare(self->r, str); + return strfilter_node__compare(node->l, str) && + strfilter_node__compare(node->r, str); case '!': /* NOT */ - return !strfilter_node__compare(self->r, str); + return !strfilter_node__compare(node->r, str); default: - return strglobmatch(str, self->p); + return strglobmatch(str, node->p); } } /* Return true if STR matches the filter rules */ -bool strfilter__compare(struct strfilter *self, const char *str) +bool strfilter__compare(struct strfilter *filter, const char *str) { - if (!self) + if (!filter) return false; - return strfilter_node__compare(self->root, str); + return strfilter_node__compare(filter->root, str); } diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h index 00f58a7506de..fe611f3c9e39 100644 --- a/tools/perf/util/strfilter.h +++ b/tools/perf/util/strfilter.h @@ -30,19 +30,19 @@ struct strfilter *strfilter__new(const char *rules, const char **err); /** * strfilter__compare - compare given string and a string filter - * @self: String filter + * @filter: String filter * @str: target string * - * Compare @str and @self. Return true if the str match the rule + * Compare @str and @filter. Return true if the str match the rule */ -bool strfilter__compare(struct strfilter *self, const char *str); +bool strfilter__compare(struct strfilter *filter, const char *str); /** * strfilter__delete - delete a string filter - * @self: String filter to delete + * @filter: String filter to delete * - * Delete @self. + * Delete @filter. */ -void strfilter__delete(struct strfilter *self); +void strfilter__delete(struct strfilter *filter); #endif diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 29c7b2cb2521..f0b0c008c507 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -387,3 +387,27 @@ void *memdup(const void *src, size_t len) return p; } + +/** + * str_append - reallocate string and append another + * @s: pointer to string pointer + * @len: pointer to len (initialized) + * @a: string to append. + */ +int str_append(char **s, int *len, const char *a) +{ + int olen = *s ? strlen(*s) : 0; + int nlen = olen + strlen(a) + 1; + if (*len < nlen) { + *len = *len * 2; + if (*len < nlen) + *len = nlen; + *s = realloc(*s, *len); + if (!*s) + return -ENOMEM; + if (olen == 0) + **s = 0; + } + strcat(*s, a); + return 0; +} diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 4b12bf850325..eed0b96302af 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -8,6 +8,22 @@ #include "symbol.h" #include "debug.h" +#ifndef HAVE_ELF_GETPHDRNUM_SUPPORT +static int elf_getphdrnum(Elf *elf, size_t *dst) +{ + GElf_Ehdr gehdr; + GElf_Ehdr *ehdr; + + ehdr = gelf_getehdr(elf, &gehdr); + if (!ehdr) + return -1; + + *dst = ehdr->e_phnum; + + return 0; +} +#endif + #ifndef NT_GNU_BUILD_ID #define NT_GNU_BUILD_ID 3 #endif @@ -471,27 +487,27 @@ int filename__read_debuglink(const char *filename, char *debuglink, ek = elf_kind(elf); if (ek != ELF_K_ELF) - goto out_close; + goto out_elf_end; if (gelf_getehdr(elf, &ehdr) == NULL) { pr_err("%s: cannot get elf header.\n", __func__); - goto out_close; + goto out_elf_end; } sec = elf_section_by_name(elf, &ehdr, &shdr, ".gnu_debuglink", NULL); if (sec == NULL) - goto out_close; + goto out_elf_end; data = elf_getdata(sec, NULL); if (data == NULL) - goto out_close; + goto out_elf_end; /* the start of this section is a zero-terminated string */ strncpy(debuglink, data->d_buf, size); +out_elf_end: elf_end(elf); - out_close: close(fd); out: @@ -599,11 +615,13 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, if (dso->kernel == DSO_TYPE_USER) { GElf_Shdr shdr; ss->adjust_symbols = (ehdr.e_type == ET_EXEC || + ehdr.e_type == ET_REL || elf_section_by_name(elf, &ehdr, &shdr, ".gnu.prelink_undo", NULL) != NULL); } else { - ss->adjust_symbols = 0; + ss->adjust_symbols = ehdr.e_type == ET_EXEC || + ehdr.e_type == ET_REL; } ss->name = strdup(name); @@ -624,6 +642,37 @@ out_close: return err; } +/** + * ref_reloc_sym_not_found - has kernel relocation symbol been found. + * @kmap: kernel maps and relocation reference symbol + * + * This function returns %true if we are dealing with the kernel maps and the + * relocation reference symbol has not yet been found. Otherwise %false is + * returned. + */ +static bool ref_reloc_sym_not_found(struct kmap *kmap) +{ + return kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name && + !kmap->ref_reloc_sym->unrelocated_addr; +} + +/** + * ref_reloc - kernel relocation offset. + * @kmap: kernel maps and relocation reference symbol + * + * This function returns the offset of kernel addresses as determined by using + * the relocation reference symbol i.e. if the kernel has not been relocated + * then the return value is zero. + */ +static u64 ref_reloc(struct kmap *kmap) +{ + if (kmap && kmap->ref_reloc_sym && + kmap->ref_reloc_sym->unrelocated_addr) + return kmap->ref_reloc_sym->addr - + kmap->ref_reloc_sym->unrelocated_addr; + return 0; +} + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, symbol_filter_t filter, int kmodule) @@ -642,8 +691,17 @@ int dso__load_sym(struct dso *dso, struct map *map, Elf_Scn *sec, *sec_strndx; Elf *elf; int nr = 0; + bool remap_kernel = false, adjust_kernel_syms = false; dso->symtab_type = syms_ss->type; + dso->rel = syms_ss->ehdr.e_type == ET_REL; + + /* + * Modules may already have symbols from kallsyms, but those symbols + * have the wrong values for the dso maps, so remove them. + */ + if (kmodule && syms_ss->symtab) + symbols__delete(&dso->symbols[map->type]); if (!syms_ss->symtab) { syms_ss->symtab = syms_ss->dynsym; @@ -681,7 +739,31 @@ int dso__load_sym(struct dso *dso, struct map *map, nr_syms = shdr.sh_size / shdr.sh_entsize; memset(&sym, 0, sizeof(sym)); - dso->adjust_symbols = runtime_ss->adjust_symbols; + + /* + * The kernel relocation symbol is needed in advance in order to adjust + * kernel maps correctly. + */ + if (ref_reloc_sym_not_found(kmap)) { + elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) { + const char *elf_name = elf_sym__name(&sym, symstrs); + + if (strcmp(elf_name, kmap->ref_reloc_sym->name)) + continue; + kmap->ref_reloc_sym->unrelocated_addr = sym.st_value; + break; + } + } + + dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap); + /* + * Initial kernel and module mappings do not map to the dso. For + * function mappings, flag the fixups. + */ + if (map->type == MAP__FUNCTION && (dso->kernel || kmodule)) { + remap_kernel = true; + adjust_kernel_syms = dso->adjust_symbols; + } elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) { struct symbol *f; const char *elf_name = elf_sym__name(&sym, symstrs); @@ -690,10 +772,6 @@ int dso__load_sym(struct dso *dso, struct map *map, const char *section_name; bool used_opd = false; - if (kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name && - strcmp(elf_name, kmap->ref_reloc_sym->name) == 0) - kmap->ref_reloc_sym->unrelocated_addr = sym.st_value; - if (!is_label && !elf_sym__is_a(&sym, map->type)) continue; @@ -745,20 +823,55 @@ int dso__load_sym(struct dso *dso, struct map *map, (sym.st_value & 1)) --sym.st_value; - if (dso->kernel != DSO_TYPE_USER || kmodule) { + if (dso->kernel || kmodule) { char dso_name[PATH_MAX]; + /* Adjust symbol to map to file offset */ + if (adjust_kernel_syms) + sym.st_value -= shdr.sh_addr - shdr.sh_offset; + if (strcmp(section_name, (curr_dso->short_name + dso->short_name_len)) == 0) goto new_symbol; if (strcmp(section_name, ".text") == 0) { + /* + * The initial kernel mapping is based on + * kallsyms and identity maps. Overwrite it to + * map to the kernel dso. + */ + if (remap_kernel && dso->kernel) { + remap_kernel = false; + map->start = shdr.sh_addr + + ref_reloc(kmap); + map->end = map->start + shdr.sh_size; + map->pgoff = shdr.sh_offset; + map->map_ip = map__map_ip; + map->unmap_ip = map__unmap_ip; + /* Ensure maps are correctly ordered */ + map_groups__remove(kmap->kmaps, map); + map_groups__insert(kmap->kmaps, map); + } + + /* + * The initial module mapping is based on + * /proc/modules mapped to offset zero. + * Overwrite it to map to the module dso. + */ + if (remap_kernel && kmodule) { + remap_kernel = false; + map->pgoff = shdr.sh_offset; + } + curr_map = map; curr_dso = dso; goto new_symbol; } + if (!kmap) + goto new_symbol; + snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name); @@ -781,8 +894,16 @@ int dso__load_sym(struct dso *dso, struct map *map, dso__delete(curr_dso); goto out_elf_end; } - curr_map->map_ip = identity__map_ip; - curr_map->unmap_ip = identity__map_ip; + if (adjust_kernel_syms) { + curr_map->start = shdr.sh_addr + + ref_reloc(kmap); + curr_map->end = curr_map->start + + shdr.sh_size; + curr_map->pgoff = shdr.sh_offset; + } else { + curr_map->map_ip = identity__map_ip; + curr_map->unmap_ip = identity__map_ip; + } curr_dso->symtab_type = dso->symtab_type; map_groups__insert(kmap->kmaps, curr_map); dsos__add(&dso->node, curr_dso); @@ -846,6 +967,652 @@ out_elf_end: return err; } +static int elf_read_maps(Elf *elf, bool exe, mapfn_t mapfn, void *data) +{ + GElf_Phdr phdr; + size_t i, phdrnum; + int err; + u64 sz; + + if (elf_getphdrnum(elf, &phdrnum)) + return -1; + + for (i = 0; i < phdrnum; i++) { + if (gelf_getphdr(elf, i, &phdr) == NULL) + return -1; + if (phdr.p_type != PT_LOAD) + continue; + if (exe) { + if (!(phdr.p_flags & PF_X)) + continue; + } else { + if (!(phdr.p_flags & PF_R)) + continue; + } + sz = min(phdr.p_memsz, phdr.p_filesz); + if (!sz) + continue; + err = mapfn(phdr.p_vaddr, sz, phdr.p_offset, data); + if (err) + return err; + } + return 0; +} + +int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, + bool *is_64_bit) +{ + int err; + Elf *elf; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + return -1; + + if (is_64_bit) + *is_64_bit = (gelf_getclass(elf) == ELFCLASS64); + + err = elf_read_maps(elf, exe, mapfn, data); + + elf_end(elf); + return err; +} + +static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len) +{ + ssize_t r; + size_t n; + int err = -1; + char *buf = malloc(page_size); + + if (buf == NULL) + return -1; + + if (lseek(to, to_offs, SEEK_SET) != to_offs) + goto out; + + if (lseek(from, from_offs, SEEK_SET) != from_offs) + goto out; + + while (len) { + n = page_size; + if (len < n) + n = len; + /* Use read because mmap won't work on proc files */ + r = read(from, buf, n); + if (r < 0) + goto out; + if (!r) + break; + n = r; + r = write(to, buf, n); + if (r < 0) + goto out; + if ((size_t)r != n) + goto out; + len -= n; + } + + err = 0; +out: + free(buf); + return err; +} + +struct kcore { + int fd; + int elfclass; + Elf *elf; + GElf_Ehdr ehdr; +}; + +static int kcore__open(struct kcore *kcore, const char *filename) +{ + GElf_Ehdr *ehdr; + + kcore->fd = open(filename, O_RDONLY); + if (kcore->fd == -1) + return -1; + + kcore->elf = elf_begin(kcore->fd, ELF_C_READ, NULL); + if (!kcore->elf) + goto out_close; + + kcore->elfclass = gelf_getclass(kcore->elf); + if (kcore->elfclass == ELFCLASSNONE) + goto out_end; + + ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr); + if (!ehdr) + goto out_end; + + return 0; + +out_end: + elf_end(kcore->elf); +out_close: + close(kcore->fd); + return -1; +} + +static int kcore__init(struct kcore *kcore, char *filename, int elfclass, + bool temp) +{ + GElf_Ehdr *ehdr; + + kcore->elfclass = elfclass; + + if (temp) + kcore->fd = mkstemp(filename); + else + kcore->fd = open(filename, O_WRONLY | O_CREAT | O_EXCL, 0400); + if (kcore->fd == -1) + return -1; + + kcore->elf = elf_begin(kcore->fd, ELF_C_WRITE, NULL); + if (!kcore->elf) + goto out_close; + + if (!gelf_newehdr(kcore->elf, elfclass)) + goto out_end; + + ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr); + if (!ehdr) + goto out_end; + + return 0; + +out_end: + elf_end(kcore->elf); +out_close: + close(kcore->fd); + unlink(filename); + return -1; +} + +static void kcore__close(struct kcore *kcore) +{ + elf_end(kcore->elf); + close(kcore->fd); +} + +static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count) +{ + GElf_Ehdr *ehdr = &to->ehdr; + GElf_Ehdr *kehdr = &from->ehdr; + + memcpy(ehdr->e_ident, kehdr->e_ident, EI_NIDENT); + ehdr->e_type = kehdr->e_type; + ehdr->e_machine = kehdr->e_machine; + ehdr->e_version = kehdr->e_version; + ehdr->e_entry = 0; + ehdr->e_shoff = 0; + ehdr->e_flags = kehdr->e_flags; + ehdr->e_phnum = count; + ehdr->e_shentsize = 0; + ehdr->e_shnum = 0; + ehdr->e_shstrndx = 0; + + if (from->elfclass == ELFCLASS32) { + ehdr->e_phoff = sizeof(Elf32_Ehdr); + ehdr->e_ehsize = sizeof(Elf32_Ehdr); + ehdr->e_phentsize = sizeof(Elf32_Phdr); + } else { + ehdr->e_phoff = sizeof(Elf64_Ehdr); + ehdr->e_ehsize = sizeof(Elf64_Ehdr); + ehdr->e_phentsize = sizeof(Elf64_Phdr); + } + + if (!gelf_update_ehdr(to->elf, ehdr)) + return -1; + + if (!gelf_newphdr(to->elf, count)) + return -1; + + return 0; +} + +static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset, + u64 addr, u64 len) +{ + GElf_Phdr gphdr; + GElf_Phdr *phdr; + + phdr = gelf_getphdr(kcore->elf, idx, &gphdr); + if (!phdr) + return -1; + + phdr->p_type = PT_LOAD; + phdr->p_flags = PF_R | PF_W | PF_X; + phdr->p_offset = offset; + phdr->p_vaddr = addr; + phdr->p_paddr = 0; + phdr->p_filesz = len; + phdr->p_memsz = len; + phdr->p_align = page_size; + + if (!gelf_update_phdr(kcore->elf, idx, phdr)) + return -1; + + return 0; +} + +static off_t kcore__write(struct kcore *kcore) +{ + return elf_update(kcore->elf, ELF_C_WRITE); +} + +struct phdr_data { + off_t offset; + u64 addr; + u64 len; +}; + +struct kcore_copy_info { + u64 stext; + u64 etext; + u64 first_symbol; + u64 last_symbol; + u64 first_module; + u64 last_module_symbol; + struct phdr_data kernel_map; + struct phdr_data modules_map; +}; + +static int kcore_copy__process_kallsyms(void *arg, const char *name, char type, + u64 start) +{ + struct kcore_copy_info *kci = arg; + + if (!symbol_type__is_a(type, MAP__FUNCTION)) + return 0; + + if (strchr(name, '[')) { + if (start > kci->last_module_symbol) + kci->last_module_symbol = start; + return 0; + } + + if (!kci->first_symbol || start < kci->first_symbol) + kci->first_symbol = start; + + if (!kci->last_symbol || start > kci->last_symbol) + kci->last_symbol = start; + + if (!strcmp(name, "_stext")) { + kci->stext = start; + return 0; + } + + if (!strcmp(name, "_etext")) { + kci->etext = start; + return 0; + } + + return 0; +} + +static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci, + const char *dir) +{ + char kallsyms_filename[PATH_MAX]; + + scnprintf(kallsyms_filename, PATH_MAX, "%s/kallsyms", dir); + + if (symbol__restricted_filename(kallsyms_filename, "/proc/kallsyms")) + return -1; + + if (kallsyms__parse(kallsyms_filename, kci, + kcore_copy__process_kallsyms) < 0) + return -1; + + return 0; +} + +static int kcore_copy__process_modules(void *arg, + const char *name __maybe_unused, + u64 start) +{ + struct kcore_copy_info *kci = arg; + + if (!kci->first_module || start < kci->first_module) + kci->first_module = start; + + return 0; +} + +static int kcore_copy__parse_modules(struct kcore_copy_info *kci, + const char *dir) +{ + char modules_filename[PATH_MAX]; + + scnprintf(modules_filename, PATH_MAX, "%s/modules", dir); + + if (symbol__restricted_filename(modules_filename, "/proc/modules")) + return -1; + + if (modules__parse(modules_filename, kci, + kcore_copy__process_modules) < 0) + return -1; + + return 0; +} + +static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff, + u64 s, u64 e) +{ + if (p->addr || s < start || s >= end) + return; + + p->addr = s; + p->offset = (s - start) + pgoff; + p->len = e < end ? e - s : end - s; +} + +static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data) +{ + struct kcore_copy_info *kci = data; + u64 end = start + len; + + kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext, + kci->etext); + + kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module, + kci->last_module_symbol); + + return 0; +} + +static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf) +{ + if (elf_read_maps(elf, true, kcore_copy__read_map, kci) < 0) + return -1; + + return 0; +} + +static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir, + Elf *elf) +{ + if (kcore_copy__parse_kallsyms(kci, dir)) + return -1; + + if (kcore_copy__parse_modules(kci, dir)) + return -1; + + if (kci->stext) + kci->stext = round_down(kci->stext, page_size); + else + kci->stext = round_down(kci->first_symbol, page_size); + + if (kci->etext) { + kci->etext = round_up(kci->etext, page_size); + } else if (kci->last_symbol) { + kci->etext = round_up(kci->last_symbol, page_size); + kci->etext += page_size; + } + + kci->first_module = round_down(kci->first_module, page_size); + + if (kci->last_module_symbol) { + kci->last_module_symbol = round_up(kci->last_module_symbol, + page_size); + kci->last_module_symbol += page_size; + } + + if (!kci->stext || !kci->etext) + return -1; + + if (kci->first_module && !kci->last_module_symbol) + return -1; + + return kcore_copy__read_maps(kci, elf); +} + +static int kcore_copy__copy_file(const char *from_dir, const char *to_dir, + const char *name) +{ + char from_filename[PATH_MAX]; + char to_filename[PATH_MAX]; + + scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name); + scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name); + + return copyfile_mode(from_filename, to_filename, 0400); +} + +static int kcore_copy__unlink(const char *dir, const char *name) +{ + char filename[PATH_MAX]; + + scnprintf(filename, PATH_MAX, "%s/%s", dir, name); + + return unlink(filename); +} + +static int kcore_copy__compare_fds(int from, int to) +{ + char *buf_from; + char *buf_to; + ssize_t ret; + size_t len; + int err = -1; + + buf_from = malloc(page_size); + buf_to = malloc(page_size); + if (!buf_from || !buf_to) + goto out; + + while (1) { + /* Use read because mmap won't work on proc files */ + ret = read(from, buf_from, page_size); + if (ret < 0) + goto out; + + if (!ret) + break; + + len = ret; + + if (readn(to, buf_to, len) != (int)len) + goto out; + + if (memcmp(buf_from, buf_to, len)) + goto out; + } + + err = 0; +out: + free(buf_to); + free(buf_from); + return err; +} + +static int kcore_copy__compare_files(const char *from_filename, + const char *to_filename) +{ + int from, to, err = -1; + + from = open(from_filename, O_RDONLY); + if (from < 0) + return -1; + + to = open(to_filename, O_RDONLY); + if (to < 0) + goto out_close_from; + + err = kcore_copy__compare_fds(from, to); + + close(to); +out_close_from: + close(from); + return err; +} + +static int kcore_copy__compare_file(const char *from_dir, const char *to_dir, + const char *name) +{ + char from_filename[PATH_MAX]; + char to_filename[PATH_MAX]; + + scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name); + scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name); + + return kcore_copy__compare_files(from_filename, to_filename); +} + +/** + * kcore_copy - copy kallsyms, modules and kcore from one directory to another. + * @from_dir: from directory + * @to_dir: to directory + * + * This function copies kallsyms, modules and kcore files from one directory to + * another. kallsyms and modules are copied entirely. Only code segments are + * copied from kcore. It is assumed that two segments suffice: one for the + * kernel proper and one for all the modules. The code segments are determined + * from kallsyms and modules files. The kernel map starts at _stext or the + * lowest function symbol, and ends at _etext or the highest function symbol. + * The module map starts at the lowest module address and ends at the highest + * module symbol. Start addresses are rounded down to the nearest page. End + * addresses are rounded up to the nearest page. An extra page is added to the + * highest kernel symbol and highest module symbol to, hopefully, encompass that + * symbol too. Because it contains only code sections, the resulting kcore is + * unusual. One significant peculiarity is that the mapping (start -> pgoff) + * is not the same for the kernel map and the modules map. That happens because + * the data is copied adjacently whereas the original kcore has gaps. Finally, + * kallsyms and modules files are compared with their copies to check that + * modules have not been loaded or unloaded while the copies were taking place. + * + * Return: %0 on success, %-1 on failure. + */ +int kcore_copy(const char *from_dir, const char *to_dir) +{ + struct kcore kcore; + struct kcore extract; + size_t count = 2; + int idx = 0, err = -1; + off_t offset = page_size, sz, modules_offset = 0; + struct kcore_copy_info kci = { .stext = 0, }; + char kcore_filename[PATH_MAX]; + char extract_filename[PATH_MAX]; + + if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms")) + return -1; + + if (kcore_copy__copy_file(from_dir, to_dir, "modules")) + goto out_unlink_kallsyms; + + scnprintf(kcore_filename, PATH_MAX, "%s/kcore", from_dir); + scnprintf(extract_filename, PATH_MAX, "%s/kcore", to_dir); + + if (kcore__open(&kcore, kcore_filename)) + goto out_unlink_modules; + + if (kcore_copy__calc_maps(&kci, from_dir, kcore.elf)) + goto out_kcore_close; + + if (kcore__init(&extract, extract_filename, kcore.elfclass, false)) + goto out_kcore_close; + + if (!kci.modules_map.addr) + count -= 1; + + if (kcore__copy_hdr(&kcore, &extract, count)) + goto out_extract_close; + + if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr, + kci.kernel_map.len)) + goto out_extract_close; + + if (kci.modules_map.addr) { + modules_offset = offset + kci.kernel_map.len; + if (kcore__add_phdr(&extract, idx, modules_offset, + kci.modules_map.addr, kci.modules_map.len)) + goto out_extract_close; + } + + sz = kcore__write(&extract); + if (sz < 0 || sz > offset) + goto out_extract_close; + + if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset, + kci.kernel_map.len)) + goto out_extract_close; + + if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset, + extract.fd, modules_offset, + kci.modules_map.len)) + goto out_extract_close; + + if (kcore_copy__compare_file(from_dir, to_dir, "modules")) + goto out_extract_close; + + if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms")) + goto out_extract_close; + + err = 0; + +out_extract_close: + kcore__close(&extract); + if (err) + unlink(extract_filename); +out_kcore_close: + kcore__close(&kcore); +out_unlink_modules: + if (err) + kcore_copy__unlink(to_dir, "modules"); +out_unlink_kallsyms: + if (err) + kcore_copy__unlink(to_dir, "kallsyms"); + + return err; +} + +int kcore_extract__create(struct kcore_extract *kce) +{ + struct kcore kcore; + struct kcore extract; + size_t count = 1; + int idx = 0, err = -1; + off_t offset = page_size, sz; + + if (kcore__open(&kcore, kce->kcore_filename)) + return -1; + + strcpy(kce->extract_filename, PERF_KCORE_EXTRACT); + if (kcore__init(&extract, kce->extract_filename, kcore.elfclass, true)) + goto out_kcore_close; + + if (kcore__copy_hdr(&kcore, &extract, count)) + goto out_extract_close; + + if (kcore__add_phdr(&extract, idx, offset, kce->addr, kce->len)) + goto out_extract_close; + + sz = kcore__write(&extract); + if (sz < 0 || sz > offset) + goto out_extract_close; + + if (copy_bytes(kcore.fd, kce->offs, extract.fd, offset, kce->len)) + goto out_extract_close; + + err = 0; + +out_extract_close: + kcore__close(&extract); + if (err) + unlink(kce->extract_filename); +out_kcore_close: + kcore__close(&kcore); + + return err; +} + +void kcore_extract__delete(struct kcore_extract *kce) +{ + unlink(kce->extract_filename); +} + void symbol__elf_init(void) { elf_version(EV_CURRENT); diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index a7390cde63bc..2d2dd0532b5a 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -301,6 +301,28 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, return 0; } +int file__read_maps(int fd __maybe_unused, bool exe __maybe_unused, + mapfn_t mapfn __maybe_unused, void *data __maybe_unused, + bool *is_64_bit __maybe_unused) +{ + return -1; +} + +int kcore_extract__create(struct kcore_extract *kce __maybe_unused) +{ + return -1; +} + +void kcore_extract__delete(struct kcore_extract *kce __maybe_unused) +{ +} + +int kcore_copy(const char *from_dir __maybe_unused, + const char *to_dir __maybe_unused) +{ + return -1; +} + void symbol__elf_init(void) { } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index d5528e1cc03a..c0c36965fff0 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -51,6 +51,7 @@ static enum dso_binary_type binary_type_symtab[] = { DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, DSO_BINARY_TYPE__NOT_FOUND, }; @@ -87,6 +88,7 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb) { s64 a; s64 b; + size_t na, nb; /* Prefer a symbol with non zero length */ a = syma->end - syma->start; @@ -120,11 +122,21 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb) 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)) + /* Choose the symbol with the longest name */ + na = strlen(syma->name); + nb = strlen(symb->name); + if (na > nb) return SYMBOL_A; - else + else if (na < nb) + return SYMBOL_B; + + /* Avoid "SyS" kernel syscall aliases */ + if (na >= 3 && !strncmp(syma->name, "SyS", 3)) return SYMBOL_B; + if (na >= 10 && !strncmp(syma->name, "compat_SyS", 10)) + return SYMBOL_B; + + return SYMBOL_A; } void symbols__fixup_duplicate(struct rb_root *symbols) @@ -148,10 +160,12 @@ again: if (choose_best_symbol(curr, next) == SYMBOL_A) { rb_erase(&next->rb_node, symbols); + symbol__delete(next); goto again; } else { nd = rb_next(&curr->rb_node); rb_erase(&curr->rb_node, symbols); + symbol__delete(curr); } } } @@ -248,7 +262,10 @@ size_t symbol__fprintf_symname_offs(const struct symbol *sym, if (sym && sym->name) { length = fprintf(fp, "%s", sym->name); if (al) { - offset = al->addr - sym->start; + if (al->addr < sym->end) + offset = al->addr - sym->start; + else + offset = al->addr - al->map->start - sym->start; length += fprintf(fp, "+0x%lx", offset); } return length; @@ -316,6 +333,16 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip) return NULL; } +static struct symbol *symbols__first(struct rb_root *symbols) +{ + struct rb_node *n = rb_first(symbols); + + if (n) + return rb_entry(n, struct symbol, rb_node); + + return NULL; +} + struct symbol_name_rb_node { struct rb_node rb_node; struct symbol sym; @@ -386,6 +413,11 @@ struct symbol *dso__find_symbol(struct dso *dso, return symbols__find(&dso->symbols[type], addr); } +struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) +{ + return symbols__first(&dso->symbols[type]); +} + struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name) { @@ -470,6 +502,64 @@ out_failure: return -1; } +int modules__parse(const char *filename, void *arg, + int (*process_module)(void *arg, const char *name, + u64 start)) +{ + char *line = NULL; + size_t n; + FILE *file; + int err = 0; + + file = fopen(filename, "r"); + if (file == NULL) + return -1; + + while (1) { + char name[PATH_MAX]; + u64 start; + char *sep; + ssize_t line_len; + + line_len = getline(&line, &n, file); + if (line_len < 0) { + if (feof(file)) + break; + err = -1; + goto out; + } + + if (!line) { + err = -1; + goto out; + } + + line[--line_len] = '\0'; /* \n */ + + sep = strrchr(line, 'x'); + if (sep == NULL) + continue; + + hex2u64(sep + 1, &start); + + sep = strchr(line, ' '); + if (sep == NULL) + continue; + + *sep = '\0'; + + scnprintf(name, sizeof(name), "[%s]", line); + + err = process_module(arg, name, start); + if (err) + break; + } +out: + free(line); + fclose(file); + return err; +} + struct process_kallsyms_args { struct map *map; struct dso *dso; @@ -522,6 +612,53 @@ static int dso__load_all_kallsyms(struct dso *dso, const char *filename, return kallsyms__parse(filename, &args, map__process_kallsym_symbol); } +static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map, + symbol_filter_t filter) +{ + struct map_groups *kmaps = map__kmap(map)->kmaps; + struct map *curr_map; + struct symbol *pos; + int count = 0, moved = 0; + struct rb_root *root = &dso->symbols[map->type]; + struct rb_node *next = rb_first(root); + + while (next) { + char *module; + + pos = rb_entry(next, struct symbol, rb_node); + next = rb_next(&pos->rb_node); + + module = strchr(pos->name, '\t'); + if (module) + *module = '\0'; + + curr_map = map_groups__find(kmaps, map->type, pos->start); + + if (!curr_map || (filter && filter(curr_map, pos))) { + rb_erase(&pos->rb_node, root); + symbol__delete(pos); + } else { + pos->start -= curr_map->start - curr_map->pgoff; + if (pos->end) + pos->end -= curr_map->start - curr_map->pgoff; + if (curr_map != map) { + rb_erase(&pos->rb_node, root); + symbols__insert( + &curr_map->dso->symbols[curr_map->type], + pos); + ++moved; + } else { + ++count; + } + } + } + + /* Symbols have been adjusted */ + dso->adjust_symbols = 1; + + return count + moved; +} + /* * Split the symbols into maps, making sure there are no overlaps, i.e. the * kernel range is broken in several maps, named [kernel].N, as we don't have @@ -663,6 +800,356 @@ bool symbol__restricted_filename(const char *filename, return restricted; } +struct module_info { + struct rb_node rb_node; + char *name; + u64 start; +}; + +static void add_module(struct module_info *mi, struct rb_root *modules) +{ + struct rb_node **p = &modules->rb_node; + struct rb_node *parent = NULL; + struct module_info *m; + + while (*p != NULL) { + parent = *p; + m = rb_entry(parent, struct module_info, rb_node); + if (strcmp(mi->name, m->name) < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&mi->rb_node, parent, p); + rb_insert_color(&mi->rb_node, modules); +} + +static void delete_modules(struct rb_root *modules) +{ + struct module_info *mi; + struct rb_node *next = rb_first(modules); + + while (next) { + mi = rb_entry(next, struct module_info, rb_node); + next = rb_next(&mi->rb_node); + rb_erase(&mi->rb_node, modules); + free(mi->name); + free(mi); + } +} + +static struct module_info *find_module(const char *name, + struct rb_root *modules) +{ + struct rb_node *n = modules->rb_node; + + while (n) { + struct module_info *m; + int cmp; + + m = rb_entry(n, struct module_info, rb_node); + cmp = strcmp(name, m->name); + if (cmp < 0) + n = n->rb_left; + else if (cmp > 0) + n = n->rb_right; + else + return m; + } + + return NULL; +} + +static int __read_proc_modules(void *arg, const char *name, u64 start) +{ + struct rb_root *modules = arg; + struct module_info *mi; + + mi = zalloc(sizeof(struct module_info)); + if (!mi) + return -ENOMEM; + + mi->name = strdup(name); + mi->start = start; + + if (!mi->name) { + free(mi); + return -ENOMEM; + } + + add_module(mi, modules); + + return 0; +} + +static int read_proc_modules(const char *filename, struct rb_root *modules) +{ + if (symbol__restricted_filename(filename, "/proc/modules")) + return -1; + + if (modules__parse(filename, modules, __read_proc_modules)) { + delete_modules(modules); + return -1; + } + + return 0; +} + +int compare_proc_modules(const char *from, const char *to) +{ + struct rb_root from_modules = RB_ROOT; + struct rb_root to_modules = RB_ROOT; + struct rb_node *from_node, *to_node; + struct module_info *from_m, *to_m; + int ret = -1; + + if (read_proc_modules(from, &from_modules)) + return -1; + + if (read_proc_modules(to, &to_modules)) + goto out_delete_from; + + from_node = rb_first(&from_modules); + to_node = rb_first(&to_modules); + while (from_node) { + if (!to_node) + break; + + from_m = rb_entry(from_node, struct module_info, rb_node); + to_m = rb_entry(to_node, struct module_info, rb_node); + + if (from_m->start != to_m->start || + strcmp(from_m->name, to_m->name)) + break; + + from_node = rb_next(from_node); + to_node = rb_next(to_node); + } + + if (!from_node && !to_node) + ret = 0; + + delete_modules(&to_modules); +out_delete_from: + delete_modules(&from_modules); + + return ret; +} + +static int do_validate_kcore_modules(const char *filename, struct map *map, + struct map_groups *kmaps) +{ + struct rb_root modules = RB_ROOT; + struct map *old_map; + int err; + + err = read_proc_modules(filename, &modules); + if (err) + return err; + + old_map = map_groups__first(kmaps, map->type); + while (old_map) { + struct map *next = map_groups__next(old_map); + struct module_info *mi; + + if (old_map == map || old_map->start == map->start) { + /* The kernel map */ + old_map = next; + continue; + } + + /* Module must be in memory at the same address */ + mi = find_module(old_map->dso->short_name, &modules); + if (!mi || mi->start != old_map->start) { + err = -EINVAL; + goto out; + } + + old_map = next; + } +out: + delete_modules(&modules); + return err; +} + +/* + * If kallsyms is referenced by name then we look for filename in the same + * directory. + */ +static bool filename_from_kallsyms_filename(char *filename, + const char *base_name, + const char *kallsyms_filename) +{ + char *name; + + strcpy(filename, kallsyms_filename); + name = strrchr(filename, '/'); + if (!name) + return false; + + name += 1; + + if (!strcmp(name, "kallsyms")) { + strcpy(name, base_name); + return true; + } + + return false; +} + +static int validate_kcore_modules(const char *kallsyms_filename, + struct map *map) +{ + struct map_groups *kmaps = map__kmap(map)->kmaps; + char modules_filename[PATH_MAX]; + + if (!filename_from_kallsyms_filename(modules_filename, "modules", + kallsyms_filename)) + return -EINVAL; + + if (do_validate_kcore_modules(modules_filename, map, kmaps)) + return -EINVAL; + + return 0; +} + +struct kcore_mapfn_data { + struct dso *dso; + enum map_type type; + struct list_head maps; +}; + +static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) +{ + struct kcore_mapfn_data *md = data; + struct map *map; + + map = map__new2(start, md->dso, md->type); + if (map == NULL) + return -ENOMEM; + + map->end = map->start + len; + map->pgoff = pgoff; + + list_add(&map->node, &md->maps); + + return 0; +} + +static int dso__load_kcore(struct dso *dso, struct map *map, + const char *kallsyms_filename) +{ + struct map_groups *kmaps = map__kmap(map)->kmaps; + struct machine *machine = kmaps->machine; + struct kcore_mapfn_data md; + struct map *old_map, *new_map, *replacement_map = NULL; + bool is_64_bit; + int err, fd; + char kcore_filename[PATH_MAX]; + struct symbol *sym; + + /* This function requires that the map is the kernel map */ + if (map != machine->vmlinux_maps[map->type]) + return -EINVAL; + + if (!filename_from_kallsyms_filename(kcore_filename, "kcore", + kallsyms_filename)) + return -EINVAL; + + /* All modules must be present at their original addresses */ + if (validate_kcore_modules(kallsyms_filename, map)) + return -EINVAL; + + md.dso = dso; + md.type = map->type; + INIT_LIST_HEAD(&md.maps); + + fd = open(kcore_filename, O_RDONLY); + if (fd < 0) + return -EINVAL; + + /* Read new maps into temporary lists */ + err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md, + &is_64_bit); + if (err) + goto out_err; + + if (list_empty(&md.maps)) { + err = -EINVAL; + goto out_err; + } + + /* Remove old maps */ + old_map = map_groups__first(kmaps, map->type); + while (old_map) { + struct map *next = map_groups__next(old_map); + + if (old_map != map) + map_groups__remove(kmaps, old_map); + old_map = next; + } + + /* Find the kernel map using the first symbol */ + sym = dso__first_symbol(dso, map->type); + list_for_each_entry(new_map, &md.maps, node) { + if (sym && sym->start >= new_map->start && + sym->start < new_map->end) { + replacement_map = new_map; + break; + } + } + + if (!replacement_map) + replacement_map = list_entry(md.maps.next, struct map, node); + + /* Add new maps */ + while (!list_empty(&md.maps)) { + new_map = list_entry(md.maps.next, struct map, node); + list_del(&new_map->node); + if (new_map == replacement_map) { + map->start = new_map->start; + map->end = new_map->end; + map->pgoff = new_map->pgoff; + map->map_ip = new_map->map_ip; + map->unmap_ip = new_map->unmap_ip; + map__delete(new_map); + /* Ensure maps are correctly ordered */ + map_groups__remove(kmaps, map); + map_groups__insert(kmaps, map); + } else { + map_groups__insert(kmaps, new_map); + } + } + + /* + * Set the data type and long name so that kcore can be read via + * dso__data_read_addr(). + */ + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + dso->data_type = DSO_BINARY_TYPE__GUEST_KCORE; + else + dso->data_type = DSO_BINARY_TYPE__KCORE; + dso__set_long_name(dso, strdup(kcore_filename)); + + close(fd); + + if (map->type == MAP__FUNCTION) + pr_debug("Using %s for kernel object code\n", kcore_filename); + else + pr_debug("Using %s for kernel data\n", kcore_filename); + + return 0; + +out_err: + while (!list_empty(&md.maps)) { + map = list_entry(md.maps.next, struct map, node); + list_del(&map->node); + map__delete(map); + } + close(fd); + return -EINVAL; +} + int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, symbol_filter_t filter) { @@ -680,7 +1167,10 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, else dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; - return dso__split_kallsyms(dso, map, filter); + if (!dso__load_kcore(dso, map, filename)) + return dso__split_kallsyms_for_kcore(dso, map, filter); + else + return dso__split_kallsyms(dso, map, filter); } static int dso__load_perf_map(struct dso *dso, struct map *map, @@ -843,10 +1333,15 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (!runtime_ss && syms_ss) runtime_ss = syms_ss; - if (syms_ss) - ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, 0); - else + if (syms_ss) { + int km; + + km = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; + ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, km); + } else { ret = -1; + } if (ret > 0) { int nr_plt; @@ -888,8 +1383,11 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, char symfs_vmlinux[PATH_MAX]; enum dso_binary_type symtab_type; - snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s", - symbol_conf.symfs, vmlinux); + if (vmlinux[0] == '/') + snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux); + else + snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s", + symbol_conf.symfs, vmlinux); if (dso->kernel == DSO_TYPE_GUEST_KERNEL) symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX; @@ -903,6 +1401,10 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, symsrc__destroy(&ss); if (err > 0) { + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + dso->data_type = DSO_BINARY_TYPE__GUEST_VMLINUX; + else + dso->data_type = DSO_BINARY_TYPE__VMLINUX; dso__set_long_name(dso, (char *)vmlinux); dso__set_loaded(dso, map->type); pr_debug("Using %s for symbols\n", symfs_vmlinux); @@ -942,6 +1444,105 @@ out: return err; } +static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz) +{ + char kallsyms_filename[PATH_MAX]; + struct dirent *dent; + int ret = -1; + DIR *d; + + d = opendir(dir); + if (!d) + return -1; + + while (1) { + dent = readdir(d); + if (!dent) + break; + if (dent->d_type != DT_DIR) + continue; + scnprintf(kallsyms_filename, sizeof(kallsyms_filename), + "%s/%s/kallsyms", dir, dent->d_name); + if (!validate_kcore_modules(kallsyms_filename, map)) { + strlcpy(dir, kallsyms_filename, dir_sz); + ret = 0; + break; + } + } + + closedir(d); + + return ret; +} + +static char *dso__find_kallsyms(struct dso *dso, struct map *map) +{ + u8 host_build_id[BUILD_ID_SIZE]; + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + bool is_host = false; + char path[PATH_MAX]; + + if (!dso->has_build_id) { + /* + * Last resort, if we don't have a build-id and couldn't find + * any vmlinux file, try the running kernel kallsyms table. + */ + goto proc_kallsyms; + } + + if (sysfs__read_build_id("/sys/kernel/notes", host_build_id, + sizeof(host_build_id)) == 0) + is_host = dso__build_id_equal(dso, host_build_id); + + build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + + /* Use /proc/kallsyms if possible */ + if (is_host) { + DIR *d; + int fd; + + /* If no cached kcore go with /proc/kallsyms */ + scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", + buildid_dir, sbuild_id); + d = opendir(path); + if (!d) + goto proc_kallsyms; + closedir(d); + + /* + * Do not check the build-id cache, until we know we cannot use + * /proc/kcore. + */ + fd = open("/proc/kcore", O_RDONLY); + if (fd != -1) { + close(fd); + /* If module maps match go with /proc/kallsyms */ + if (!validate_kcore_modules("/proc/kallsyms", map)) + goto proc_kallsyms; + } + + /* Find kallsyms in build-id cache with kcore */ + if (!find_matching_kcore(map, path, sizeof(path))) + return strdup(path); + + goto proc_kallsyms; + } + + scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s", + buildid_dir, sbuild_id); + + if (access(path, F_OK)) { + pr_err("No kallsyms or vmlinux with build-id %s was found\n", + sbuild_id); + return NULL; + } + + return strdup(path); + +proc_kallsyms: + return strdup("/proc/kallsyms"); +} + static int dso__load_kernel_sym(struct dso *dso, struct map *map, symbol_filter_t filter) { @@ -968,73 +1569,33 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map, goto do_kallsyms; } - if (symbol_conf.vmlinux_name != NULL) { + if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) { err = dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, filter); if (err > 0) { dso__set_long_name(dso, strdup(symbol_conf.vmlinux_name)); dso->lname_alloc = 1; - goto out_fixup; + return err; } return err; } - if (vmlinux_path != NULL) { + if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) { err = dso__load_vmlinux_path(dso, map, filter); if (err > 0) - goto out_fixup; + return err; } /* do not try local files if a symfs was given */ if (symbol_conf.symfs[0] != 0) return -1; - /* - * Say the kernel DSO was created when processing the build-id header table, - * we have a build-id, so check if it is the same as the running kernel, - * using it if it is. - */ - if (dso->has_build_id) { - u8 kallsyms_build_id[BUILD_ID_SIZE]; - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - - if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id, - sizeof(kallsyms_build_id)) == 0) { - if (dso__build_id_equal(dso, kallsyms_build_id)) { - kallsyms_filename = "/proc/kallsyms"; - goto do_kallsyms; - } - } - /* - * Now look if we have it on the build-id cache in - * $HOME/.debug/[kernel.kallsyms]. - */ - build_id__sprintf(dso->build_id, sizeof(dso->build_id), - sbuild_id); - - if (asprintf(&kallsyms_allocated_filename, - "%s/.debug/[kernel.kallsyms]/%s", - getenv("HOME"), sbuild_id) == -1) { - pr_err("Not enough memory for kallsyms file lookup\n"); - return -1; - } + kallsyms_allocated_filename = dso__find_kallsyms(dso, map); + if (!kallsyms_allocated_filename) + return -1; - kallsyms_filename = kallsyms_allocated_filename; - - if (access(kallsyms_filename, F_OK)) { - pr_err("No kallsyms or vmlinux with build-id %s " - "was found\n", sbuild_id); - free(kallsyms_allocated_filename); - return -1; - } - } else { - /* - * Last resort, if we don't have a build-id and couldn't find - * any vmlinux file, try the running kernel kallsyms table. - */ - kallsyms_filename = "/proc/kallsyms"; - } + kallsyms_filename = kallsyms_allocated_filename; do_kallsyms: err = dso__load_kallsyms(dso, kallsyms_filename, map, filter); @@ -1042,9 +1603,8 @@ do_kallsyms: pr_debug("Using %s for symbols\n", kallsyms_filename); free(kallsyms_allocated_filename); - if (err > 0) { + if (err > 0 && !dso__is_kcore(dso)) { dso__set_long_name(dso, strdup("[kernel.kallsyms]")); -out_fixup: map__fixup_start(map); map__fixup_end(map); } @@ -1075,7 +1635,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, if (symbol_conf.default_guest_vmlinux_name != NULL) { err = dso__load_vmlinux(dso, map, symbol_conf.default_guest_vmlinux_name, filter); - goto out_try_fixup; + return err; } kallsyms_filename = symbol_conf.default_guest_kallsyms; @@ -1089,13 +1649,9 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, err = dso__load_kallsyms(dso, kallsyms_filename, map, filter); if (err > 0) pr_debug("Using %s for symbols\n", kallsyms_filename); - -out_try_fixup: - if (err > 0) { - if (kallsyms_filename != NULL) { - machine__mmap_name(machine, path, sizeof(path)); - dso__set_long_name(dso, strdup(path)); - } + if (err > 0 && !dso__is_kcore(dso)) { + machine__mmap_name(machine, path, sizeof(path)); + dso__set_long_name(dso, strdup(path)); map__fixup_start(map); map__fixup_end(map); } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 5f720dc076da..07de8fea2f48 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -13,7 +13,7 @@ #include <libgen.h> #include "build-id.h" -#ifdef LIBELF_SUPPORT +#ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> #include <gelf.h> #endif @@ -21,7 +21,7 @@ #include "dso.h" -#ifdef HAVE_CPLUS_DEMANGLE +#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT extern char *cplus_demangle(const char *, int); static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i) @@ -46,7 +46,7 @@ static inline char *bfd_demangle(void __maybe_unused *v, * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP; * for newer versions we can use mmap to reduce memory usage: */ -#ifdef LIBELF_MMAP +#ifdef HAVE_LIBELF_MMAP_SUPPORT # define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP #else # define PERF_ELF_C_READ_MMAP ELF_C_READ @@ -85,6 +85,7 @@ struct symbol_conf { unsigned short priv_size; unsigned short nr_events; bool try_vmlinux_path, + ignore_vmlinux, show_kernel_path, use_modules, sort_by_name, @@ -178,7 +179,7 @@ struct symsrc { int fd; enum dso_binary_type type; -#ifdef LIBELF_SUPPORT +#ifdef HAVE_LIBELF_SUPPORT Elf *elf; GElf_Ehdr ehdr; @@ -215,12 +216,16 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name); +struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, char type, u64 start)); +int modules__parse(const char *filename, void *arg, + int (*process_module)(void *arg, const char *name, + u64 start)); int filename__read_debuglink(const char *filename, char *debuglink, size_t size); @@ -247,4 +252,25 @@ void symbols__fixup_duplicate(struct rb_root *symbols); void symbols__fixup_end(struct rb_root *symbols); void __map_groups__fixup_end(struct map_groups *mg, enum map_type type); +typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); +int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, + bool *is_64_bit); + +#define PERF_KCORE_EXTRACT "/tmp/perf-kcore-XXXXXX" + +struct kcore_extract { + char *kcore_filename; + u64 addr; + u64 offs; + u64 len; + char extract_filename[sizeof(PERF_KCORE_EXTRACT)]; + int fd; +}; + +int kcore_extract__create(struct kcore_extract *kce); +void kcore_extract__delete(struct kcore_extract *kce); + +int kcore_copy(const char *from_dir, const char *to_dir); +int compare_proc_modules(const char *from, const char *to); + #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/sysfs.c b/tools/perf/util/sysfs.c deleted file mode 100644 index f71e9eafe15a..000000000000 --- a/tools/perf/util/sysfs.c +++ /dev/null @@ -1,60 +0,0 @@ - -#include "util.h" -#include "sysfs.h" - -static const char * const sysfs_known_mountpoints[] = { - "/sys", - 0, -}; - -static int sysfs_found; -char sysfs_mountpoint[PATH_MAX + 1]; - -static int sysfs_valid_mountpoint(const char *sysfs) -{ - struct statfs st_fs; - - if (statfs(sysfs, &st_fs) < 0) - return -ENOENT; - else if (st_fs.f_type != (long) SYSFS_MAGIC) - return -ENOENT; - - return 0; -} - -const char *sysfs_find_mountpoint(void) -{ - const char * const *ptr; - char type[100]; - FILE *fp; - - if (sysfs_found) - return (const char *) sysfs_mountpoint; - - ptr = sysfs_known_mountpoints; - while (*ptr) { - if (sysfs_valid_mountpoint(*ptr) == 0) { - sysfs_found = 1; - strcpy(sysfs_mountpoint, *ptr); - return sysfs_mountpoint; - } - ptr++; - } - - /* give up and parse /proc/mounts */ - fp = fopen("/proc/mounts", "r"); - if (fp == NULL) - return NULL; - - while (!sysfs_found && - fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n", - sysfs_mountpoint, type) == 2) { - - if (strcmp(type, "sysfs") == 0) - sysfs_found = 1; - } - - fclose(fp); - - return sysfs_found ? sysfs_mountpoint : NULL; -} diff --git a/tools/perf/util/sysfs.h b/tools/perf/util/sysfs.h deleted file mode 100644 index a813b7203938..000000000000 --- a/tools/perf/util/sysfs.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SYSFS_H__ -#define __SYSFS_H__ - -const char *sysfs_find_mountpoint(void); - -#endif /* __DEBUGFS_H__ */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 40399cbcca77..cd8e2f592719 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -6,85 +6,137 @@ #include "thread.h" #include "util.h" #include "debug.h" +#include "comm.h" -struct thread *thread__new(pid_t pid) +struct thread *thread__new(pid_t pid, pid_t tid) { - struct thread *self = zalloc(sizeof(*self)); - - if (self != NULL) { - map_groups__init(&self->mg); - self->pid = pid; - self->ppid = -1; - self->comm = malloc(32); - if (self->comm) - snprintf(self->comm, 32, ":%d", self->pid); + char *comm_str; + struct comm *comm; + struct thread *thread = zalloc(sizeof(*thread)); + + if (thread != NULL) { + map_groups__init(&thread->mg); + thread->pid_ = pid; + thread->tid = tid; + thread->ppid = -1; + INIT_LIST_HEAD(&thread->comm_list); + + comm_str = malloc(32); + if (!comm_str) + goto err_thread; + + snprintf(comm_str, 32, ":%d", tid); + comm = comm__new(comm_str, 0); + free(comm_str); + if (!comm) + goto err_thread; + + list_add(&comm->list, &thread->comm_list); + } + + return thread; + +err_thread: + free(thread); + return NULL; +} + +void thread__delete(struct thread *thread) +{ + struct comm *comm, *tmp; + + map_groups__exit(&thread->mg); + list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) { + list_del(&comm->list); + comm__free(comm); } - return self; + free(thread); } -void thread__delete(struct thread *self) +struct comm *thread__comm(const struct thread *thread) { - map_groups__exit(&self->mg); - free(self->comm); - free(self); + if (list_empty(&thread->comm_list)) + return NULL; + + return list_first_entry(&thread->comm_list, struct comm, list); } -int thread__set_comm(struct thread *self, const char *comm) +/* CHECKME: time should always be 0 if event aren't ordered */ +int thread__set_comm(struct thread *thread, const char *str, u64 timestamp) { - int err; - - if (self->comm) - free(self->comm); - self->comm = strdup(comm); - err = self->comm == NULL ? -ENOMEM : 0; - if (!err) { - self->comm_set = true; + struct comm *new, *curr = thread__comm(thread); + + /* Override latest entry if it had no specific time coverage */ + if (!curr->start) { + comm__override(curr, str, timestamp); + return 0; } - return err; + + new = comm__new(str, timestamp); + if (!new) + return -ENOMEM; + + list_add(&new->list, &thread->comm_list); + thread->comm_set = true; + + return 0; +} + +const char *thread__comm_str(const struct thread *thread) +{ + const struct comm *comm = thread__comm(thread); + + if (!comm) + return NULL; + + return comm__str(comm); } -int thread__comm_len(struct thread *self) +/* CHECKME: it should probably better return the max comm len from its comm list */ +int thread__comm_len(struct thread *thread) { - if (!self->comm_len) { - if (!self->comm) + if (!thread->comm_len) { + const char *comm = thread__comm_str(thread); + if (!comm) return 0; - self->comm_len = strlen(self->comm); + thread->comm_len = strlen(comm); } - return self->comm_len; + return thread->comm_len; } size_t thread__fprintf(struct thread *thread, FILE *fp) { - return fprintf(fp, "Thread %d %s\n", thread->pid, thread->comm) + + return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) + map_groups__fprintf(&thread->mg, verbose, fp); } -void thread__insert_map(struct thread *self, struct map *map) +void thread__insert_map(struct thread *thread, struct map *map) { - map_groups__fixup_overlappings(&self->mg, map, verbose, stderr); - map_groups__insert(&self->mg, map); + map_groups__fixup_overlappings(&thread->mg, map, verbose, stderr); + map_groups__insert(&thread->mg, map); } -int thread__fork(struct thread *self, struct thread *parent) +int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) { - int i; + int i, err; if (parent->comm_set) { - if (self->comm) - free(self->comm); - self->comm = strdup(parent->comm); - if (!self->comm) + const char *comm = thread__comm_str(parent); + if (!comm) return -ENOMEM; - self->comm_set = true; + err = thread__set_comm(thread, comm, timestamp); + if (!err) + return err; + thread->comm_set = true; } for (i = 0; i < MAP__NR_TYPES; ++i) - if (map_groups__clone(&self->mg, &parent->mg, i) < 0) + if (map_groups__clone(&thread->mg, &parent->mg, i) < 0) return -ENOMEM; - self->ppid = parent->pid; + thread->ppid = parent->tid; return 0; } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index eeb7ac62b9e3..897c1b2a750a 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -2,6 +2,7 @@ #define __PERF_THREAD_H #include <linux/rbtree.h> +#include <linux/list.h> #include <unistd.h> #include <sys/types.h> #include "symbol.h" @@ -12,31 +13,40 @@ struct thread { struct list_head node; }; struct map_groups mg; - pid_t pid; + pid_t pid_; /* Not all tools update this */ + pid_t tid; pid_t ppid; char shortname[3]; bool comm_set; - char *comm; + bool dead; /* if set thread has exited */ + struct list_head comm_list; int comm_len; void *priv; }; struct machine; +struct comm; -struct thread *thread__new(pid_t pid); -void thread__delete(struct thread *self); +struct thread *thread__new(pid_t pid, pid_t tid); +void thread__delete(struct thread *thread); +static inline void thread__exited(struct thread *thread) +{ + thread->dead = true; +} -int thread__set_comm(struct thread *self, const char *comm); -int thread__comm_len(struct thread *self); -void thread__insert_map(struct thread *self, struct map *map); -int thread__fork(struct thread *self, struct thread *parent); +int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp); +int thread__comm_len(struct thread *thread); +struct comm *thread__comm(const struct thread *thread); +const char *thread__comm_str(const struct thread *thread); +void thread__insert_map(struct thread *thread, struct map *map); +int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp); size_t thread__fprintf(struct thread *thread, FILE *fp); -static inline struct map *thread__find_map(struct thread *self, +static inline struct map *thread__find_map(struct thread *thread, enum map_type type, u64 addr) { - return self ? map_groups__find(&self->mg, type, addr) : NULL; + return thread ? map_groups__find(&thread->mg, type, addr) : NULL; } void thread__find_addr_map(struct thread *thread, struct machine *machine, @@ -45,6 +55,15 @@ void thread__find_addr_map(struct thread *thread, struct machine *machine, 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); + struct addr_location *al); + +static inline void *thread__priv(struct thread *thread) +{ + return thread->priv; +} + +static inline void thread__set_priv(struct thread *thread, void *p) +{ + thread->priv = p; +} #endif /* __PERF_THREAD_H */ diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index b0e1aadba8d5..4385816d3d49 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -18,12 +18,9 @@ typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event, 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, +typedef int (*event_attr_op)(struct perf_tool *tool, + 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); @@ -32,6 +29,7 @@ struct perf_tool { event_sample sample, read; event_op mmap, + mmap2, comm, fork, exit, @@ -39,8 +37,7 @@ struct perf_tool { throttle, unthrottle; event_attr_op attr; - event_synth_op tracing_data; - event_simple_op event_type; + event_op2 tracing_data; event_op2 finished_round, build_id; bool ordered_samples; diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index df46be93d902..88cfeaff600b 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -24,6 +24,7 @@ struct perf_top { u64 exact_samples; u64 guest_us_samples, guest_kernel_samples; int print_entries, count_filter, delay_secs; + int max_stack; bool hide_kernel_symbols, hide_user_symbols, zero; bool use_tui, use_stdio; bool kptr_restrict_warned; @@ -39,6 +40,8 @@ struct perf_top { float min_percent; }; +#define CONSOLE_CLEAR "[H[2J" + 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); #endif /* __PERF_TOP_H */ diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 3917eb9a8479..f3c9e551bd35 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -46,65 +46,6 @@ static int output_fd; -static const char *find_debugfs(void) -{ - const char *path = perf_debugfs_mount(NULL); - - if (!path) - pr_debug("Your kernel does not support the debugfs filesystem"); - - return path; -} - -/* - * Finds the path to the debugfs/tracing - * Allocates the string and stores it. - */ -static const char *find_tracing_dir(void) -{ - static char *tracing; - static int tracing_found; - const char *debugfs; - - if (tracing_found) - return tracing; - - debugfs = find_debugfs(); - if (!debugfs) - return NULL; - - tracing = malloc(strlen(debugfs) + 9); - if (!tracing) - return NULL; - - sprintf(tracing, "%s/tracing", debugfs); - - tracing_found = 1; - return tracing; -} - -static char *get_tracing_file(const char *name) -{ - const char *tracing; - char *file; - - tracing = find_tracing_dir(); - if (!tracing) - return NULL; - - file = malloc(strlen(tracing) + strlen(name) + 2); - if (!file) - return NULL; - - sprintf(file, "%s/%s", tracing, name); - return file; -} - -static void put_tracing_file(char *file) -{ - free(file); -} - int bigendian(void) { unsigned char str[] = { 0x1, 0x2, 0x3, 0x4, 0x0, 0x0, 0x0, 0x0}; @@ -160,7 +101,7 @@ out: return err; } -static int read_header_files(void) +static int record_header_files(void) { char *path; struct stat st; @@ -299,7 +240,7 @@ out: return err; } -static int read_ftrace_files(struct tracepoint_path *tps) +static int record_ftrace_files(struct tracepoint_path *tps) { char *path; int ret; @@ -328,7 +269,7 @@ static bool system_in_tp_list(char *sys, struct tracepoint_path *tps) return false; } -static int read_event_files(struct tracepoint_path *tps) +static int record_event_files(struct tracepoint_path *tps) { struct dirent *dent; struct stat st; @@ -403,7 +344,7 @@ out: return err; } -static int read_proc_kallsyms(void) +static int record_proc_kallsyms(void) { unsigned int size; const char *path = "/proc/kallsyms"; @@ -421,7 +362,7 @@ static int read_proc_kallsyms(void) return record_file(path, 4); } -static int read_ftrace_printk(void) +static int record_ftrace_printk(void) { unsigned int size; char *path; @@ -473,12 +414,27 @@ get_tracepoints_path(struct list_head *pattrs) if (pos->attr.type != PERF_TYPE_TRACEPOINT) continue; ++nr_tracepoints; + + if (pos->name) { + ppath->next = tracepoint_name_to_path(pos->name); + if (ppath->next) + goto next; + + if (strchr(pos->name, ':') == NULL) + goto try_id; + + goto error; + } + +try_id: ppath->next = tracepoint_id_to_path(pos->attr.config); if (!ppath->next) { +error: pr_debug("No memory to alloc tracepoints list\n"); put_tracepoints_path(&path); return NULL; } +next: ppath = ppath->next; } @@ -520,8 +476,6 @@ static int tracing_data_header(void) else buf[0] = 0; - read_trace_init(buf[0], buf[0]); - if (write(output_fd, buf, 1) != 1) return -1; @@ -583,19 +537,19 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, err = tracing_data_header(); if (err) goto out; - err = read_header_files(); + err = record_header_files(); if (err) goto out; - err = read_ftrace_files(tps); + err = record_ftrace_files(tps); if (err) goto out; - err = read_event_files(tps); + err = record_event_files(tps); if (err) goto out; - err = read_proc_kallsyms(); + err = record_proc_kallsyms(); if (err) goto out; - err = read_ftrace_printk(); + err = record_ftrace_printk(); out: /* diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 4454835a9ebc..6681f71f2f95 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -28,12 +28,6 @@ #include "util.h" #include "trace-event.h" -int header_page_size_size; -int header_page_ts_size; -int header_page_data_offset; - -bool latency_format; - struct pevent *read_trace_init(int file_bigendian, int host_bigendian) { struct pevent *pevent = pevent_alloc(); @@ -126,42 +120,6 @@ raw_field_value(struct event_format *event, const char *name, void *data) return val; } -void *raw_field_ptr(struct event_format *event, const char *name, void *data) -{ - struct format_field *field; - - field = pevent_find_any_field(event, name); - if (!field) - return NULL; - - if (field->flags & FIELD_IS_DYNAMIC) { - int offset; - - offset = *(int *)(data + field->offset); - offset &= 0xffff; - - return data + offset; - } - - return data + field->offset; -} - -int trace_parse_common_type(struct pevent *pevent, void *data) -{ - struct pevent_record record; - - record.data = data; - return pevent_data_type(pevent, &record); -} - -int trace_parse_common_pid(struct pevent *pevent, void *data) -{ - struct pevent_record record; - - record.data = data; - return pevent_data_pid(pevent, &record); -} - unsigned long long read_size(struct event_format *event, void *ptr, int size) { return pevent_read_number(event->pevent, ptr, size); @@ -192,7 +150,7 @@ void parse_proc_kallsyms(struct pevent *pevent, char *next = NULL; char *addr_str; char *mod; - char *fmt; + char *fmt = NULL; line = strtok_r(file, "\n", &next); while (line) { diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index af215c0d2379..f2112270c663 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -39,10 +39,6 @@ static int input_fd; -int file_bigendian; -int host_bigendian; -static int long_size; - static ssize_t trace_data_size; static bool repipe; @@ -216,7 +212,7 @@ static int read_ftrace_printk(struct pevent *pevent) static int read_header_files(struct pevent *pevent) { unsigned long long size; - char *header_event; + char *header_page; char buf[BUFSIZ]; int ret = 0; @@ -229,13 +225,26 @@ static int read_header_files(struct pevent *pevent) } size = read8(pevent); - skip(size); - /* - * The size field in the page is of type long, - * use that instead, since it represents the kernel. - */ - long_size = header_page_size_size; + header_page = malloc(size); + if (header_page == NULL) + return -1; + + if (do_read(header_page, size) < 0) { + pr_debug("did not read header page"); + free(header_page); + return -1; + } + + if (!pevent_parse_header_page(pevent, header_page, size, + pevent_get_long_size(pevent))) { + /* + * The commit field in the page is of type long, + * use that instead, since it represents the kernel. + */ + pevent_set_long_size(pevent, pevent->header_page_size_size); + } + free(header_page); if (do_read(buf, 13) < 0) return -1; @@ -246,14 +255,8 @@ static int read_header_files(struct pevent *pevent) } size = read8(pevent); - header_event = malloc(size); - if (header_event == NULL) - return -1; - - if (do_read(header_event, size) < 0) - ret = -1; + skip(size); - free(header_event); return ret; } @@ -349,6 +352,10 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe) int show_funcs = 0; int show_printk = 0; ssize_t size = -1; + int file_bigendian; + int host_bigendian; + int file_long_size; + int file_page_size; struct pevent *pevent; int err; @@ -391,12 +398,15 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe) if (do_read(buf, 1) < 0) goto out; - long_size = buf[0]; + file_long_size = buf[0]; - page_size = read4(pevent); - if (!page_size) + file_page_size = read4(pevent); + if (!file_page_size) goto out; + pevent_set_long_size(pevent, file_long_size); + pevent_set_page_size(pevent, file_page_size); + err = read_header_files(pevent); if (err) goto out; diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 8715a1006d00..95199e4eea97 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -39,7 +39,8 @@ static void process_event_unsupported(union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, struct perf_evsel *evsel __maybe_unused, struct machine *machine __maybe_unused, - struct addr_location *al __maybe_unused) + struct thread *thread __maybe_unused, + struct addr_location *al __maybe_unused) { } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 1978c398ad87..04df63114109 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -1,31 +1,15 @@ #ifndef _PERF_UTIL_TRACE_EVENT_H #define _PERF_UTIL_TRACE_EVENT_H +#include <traceevent/event-parse.h> #include "parse-events.h" -#include "event-parse.h" #include "session.h" struct machine; struct perf_sample; union perf_event; struct perf_tool; - -extern int header_page_size_size; -extern int header_page_ts_size; -extern int header_page_data_offset; - -extern bool latency_format; -extern struct pevent *perf_pevent; - -enum { - RINGBUF_TYPE_PADDING = 29, - RINGBUF_TYPE_TIME_EXTEND = 30, - RINGBUF_TYPE_TIME_STAMP = 31, -}; - -#ifndef TS_SHIFT -#define TS_SHIFT 27 -#endif +struct thread; int bigendian(void); @@ -37,26 +21,19 @@ int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size); int parse_event_file(struct pevent *pevent, char *buf, unsigned long size, char *sys); -struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu); - unsigned long long raw_field_value(struct event_format *event, const char *name, void *data); -void *raw_field_ptr(struct event_format *event, const char *name, void *data); void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size); void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size); ssize_t trace_report(int fd, struct pevent **pevent, bool repipe); -int trace_parse_common_type(struct pevent *pevent, void *data); -int trace_parse_common_pid(struct pevent *pevent, void *data); - struct event_format *trace_find_next_event(struct pevent *pevent, struct event_format *event); unsigned long long read_size(struct event_format *event, void *ptr, int size); unsigned long long eval_flag(const char *flag); -struct pevent_record *trace_read_data(struct pevent *pevent, int cpu); int read_tracing_data(int fd, struct list_head *pattrs); struct tracing_data { @@ -83,7 +60,8 @@ struct scripting_ops { struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, - struct addr_location *al); + struct thread *thread, + struct addr_location *al); int (*generate_script) (struct pevent *pevent, const char *outfile); }; diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c index 958723ba3d2e..2f891f7e70bf 100644 --- a/tools/perf/util/unwind.c +++ b/tools/perf/util/unwind.c @@ -473,7 +473,7 @@ static int entry(u64 ip, struct thread *thread, struct machine *machine, thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, &al, NULL); + MAP__FUNCTION, ip, &al); e.ip = ip; e.map = al.map; diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index cb6bc503a792..ec0c71a2ca2e 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -13,7 +13,7 @@ struct unwind_entry { typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); -#ifdef LIBUNWIND_SUPPORT +#ifdef HAVE_LIBUNWIND_SUPPORT int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct machine *machine, struct thread *thread, @@ -31,5 +31,5 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, { return 0; } -#endif /* LIBUNWIND_SUPPORT */ +#endif /* HAVE_LIBUNWIND_SUPPORT */ #endif /* __UNWIND_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 59d868add275..28a0a89c1f73 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,7 +1,7 @@ #include "../perf.h" #include "util.h" #include <sys/mman.h> -#ifdef BACKTRACE_SUPPORT +#ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #endif #include <stdio.h> @@ -55,17 +55,20 @@ int mkdir_p(char *path, mode_t mode) return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0; } -static int slow_copyfile(const char *from, const char *to) +static int slow_copyfile(const char *from, const char *to, mode_t mode) { - int err = 0; + int err = -1; char *line = NULL; size_t n; FILE *from_fp = fopen(from, "r"), *to_fp; + mode_t old_umask; if (from_fp == NULL) goto out; + old_umask = umask(mode ^ 0777); to_fp = fopen(to, "w"); + umask(old_umask); if (to_fp == NULL) goto out_fclose_from; @@ -82,7 +85,7 @@ out: return err; } -int copyfile(const char *from, const char *to) +int copyfile_mode(const char *from, const char *to, mode_t mode) { int fromfd, tofd; struct stat st; @@ -93,13 +96,13 @@ int copyfile(const char *from, const char *to) goto out; if (st.st_size == 0) /* /proc? do it slowly... */ - return slow_copyfile(from, to); + return slow_copyfile(from, to, mode); fromfd = open(from, O_RDONLY); if (fromfd < 0) goto out; - tofd = creat(to, 0755); + tofd = creat(to, mode); if (tofd < 0) goto out_close_from; @@ -121,6 +124,11 @@ out: return err; } +int copyfile(const char *from, const char *to) +{ + return copyfile_mode(from, to, 0755); +} + unsigned long convert_unit(unsigned long value, char *unit) { *unit = ' '; @@ -204,7 +212,7 @@ int hex2u64(const char *ptr, u64 *long_val) } /* Obtain a backtrace and print it to stdout. */ -#ifdef BACKTRACE_SUPPORT +#ifdef HAVE_BACKTRACE_SUPPORT void dump_stack(void) { void *array[16]; @@ -269,3 +277,139 @@ void perf_debugfs_set_path(const char *mntpt) snprintf(debugfs_mountpoint, strlen(debugfs_mountpoint), "%s", mntpt); set_tracing_events_path(mntpt); } + +static const char *find_debugfs(void) +{ + const char *path = perf_debugfs_mount(NULL); + + if (!path) + fprintf(stderr, "Your kernel does not support the debugfs filesystem"); + + return path; +} + +/* + * Finds the path to the debugfs/tracing + * Allocates the string and stores it. + */ +const char *find_tracing_dir(void) +{ + static char *tracing; + static int tracing_found; + const char *debugfs; + + if (tracing_found) + return tracing; + + debugfs = find_debugfs(); + if (!debugfs) + return NULL; + + tracing = malloc(strlen(debugfs) + 9); + if (!tracing) + return NULL; + + sprintf(tracing, "%s/tracing", debugfs); + + tracing_found = 1; + return tracing; +} + +char *get_tracing_file(const char *name) +{ + const char *tracing; + char *file; + + tracing = find_tracing_dir(); + if (!tracing) + return NULL; + + file = malloc(strlen(tracing) + strlen(name) + 2); + if (!file) + return NULL; + + sprintf(file, "%s/%s", tracing, name); + return file; +} + +void put_tracing_file(char *file) +{ + free(file); +} + +int parse_nsec_time(const char *str, u64 *ptime) +{ + u64 time_sec, time_nsec; + char *end; + + time_sec = strtoul(str, &end, 10); + if (*end != '.' && *end != '\0') + return -1; + + if (*end == '.') { + int i; + char nsec_buf[10]; + + if (strlen(++end) > 9) + return -1; + + strncpy(nsec_buf, end, 9); + nsec_buf[9] = '\0'; + + /* make it nsec precision */ + for (i = strlen(nsec_buf); i < 9; i++) + nsec_buf[i] = '0'; + + time_nsec = strtoul(nsec_buf, &end, 10); + if (*end != '\0') + return -1; + } else + time_nsec = 0; + + *ptime = time_sec * NSEC_PER_SEC + time_nsec; + return 0; +} + +unsigned long parse_tag_value(const char *str, struct parse_tag *tags) +{ + struct parse_tag *i = tags; + + while (i->tag) { + char *s; + + s = strchr(str, i->tag); + if (s) { + unsigned long int value; + char *endptr; + + value = strtoul(str, &endptr, 10); + if (s != endptr) + break; + + if (value > ULONG_MAX / i->mult) + break; + value *= i->mult; + return value; + } + i++; + } + + return (unsigned long) -1; +} + +int filename__read_int(const char *filename, int *value) +{ + char line[64]; + int fd = open(filename, O_RDONLY), err = -1; + + if (fd < 0) + return -1; + + if (read(fd, line, sizeof(line)) > 0) { + *value = atoi(line); + err = 0; + } + + close(fd); + return err; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 2732fad03908..c8f362daba87 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -80,6 +80,9 @@ extern char buildid_dir[]; extern char tracing_events_path[]; extern void perf_debugfs_set_path(const char *mountpoint); const char *perf_debugfs_mount(const char *mountpoint); +const char *find_tracing_dir(void); +char *get_tracing_file(const char *name); +void put_tracing_file(char *file); /* On most systems <limits.h> would have given us this, but * not on some systems (e.g. GNU/Hurd). @@ -125,6 +128,8 @@ const char *perf_debugfs_mount(const char *mountpoint); #endif #endif +#define PERF_GTK_DSO "libperf-gtk.so" + /* General helper functions */ extern void usage(const char *err) NORETURN; extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2))); @@ -205,6 +210,8 @@ static inline int has_extension(const char *filename, const char *ext) #define NSEC_PER_MSEC 1000000L #endif +int parse_nsec_time(const char *str, u64 *ptime); + extern unsigned char sane_ctype[256]; #define GIT_SPACE 0x01 #define GIT_DIGIT 0x02 @@ -236,6 +243,7 @@ static inline int sane_case(int x, int high) int mkdir_p(char *path, mode_t mode); int copyfile(const char *from, const char *to); +int copyfile_mode(const char *from, const char *to, mode_t mode); s64 perf_atoll(const char *str); char **argv_split(const char *str, int *argcp); @@ -265,6 +273,13 @@ bool is_power_of_2(unsigned long n) return (n != 0 && ((n & (n - 1)) == 0)); } +static inline unsigned next_pow2(unsigned x) +{ + if (!x) + return 1; + return 1ULL << (32 - __builtin_clz(x - 1)); +} + size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); @@ -276,4 +291,20 @@ void dump_stack(void); extern unsigned int page_size; void get_term_dimensions(struct winsize *ws); + +struct parse_tag { + char tag; + int mult; +}; + +unsigned long parse_tag_value(const char *str, struct parse_tag *tags); + +#define SRCLINE_UNKNOWN ((char *) "??:0") + +struct dso; + +char *get_srcline(struct dso *dso, unsigned long addr); +void free_srcline(char *srcline); + +int filename__read_int(const char *filename, int *value); #endif /* GIT_COMPAT_UTIL_H */ |