diff options
Diffstat (limited to 'tools/perf/util')
163 files changed, 33874 insertions, 14493 deletions
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN index 97d76562a1a..39f17507578 100755 --- a/tools/perf/util/PERF-VERSION-GEN +++ b/tools/perf/util/PERF-VERSION-GEN @@ -9,39 +9,42 @@ GVF=${OUTPUT}PERF-VERSION-FILE LF=' ' +# # First check if there is a .git to get the version from git describe -# otherwise try to get the version from the kernel makefile -if test -d ../../.git -o -f ../../.git && - VN=$(git describe --abbrev=4 HEAD 2>/dev/null) && - case "$VN" in - *$LF*) (exit 1) ;; - v[0-9]*) - git update-index -q --refresh - test -z "$(git diff-index --name-only HEAD --)" || - VN="$VN-dirty" ;; - esac +# otherwise try to get the version from the kernel Makefile +# +CID= +TAG= +if test -d ../../.git -o -f ../../.git then - VN=$(echo "$VN" | sed -e 's/-/./g'); -else - eval `grep '^VERSION\s*=' ../../Makefile|tr -d ' '` - eval `grep '^PATCHLEVEL\s*=' ../../Makefile|tr -d ' '` - eval `grep '^SUBLEVEL\s*=' ../../Makefile|tr -d ' '` - eval `grep '^EXTRAVERSION\s*=' ../../Makefile|tr -d ' '` - - VN="${VERSION}.${PATCHLEVEL}.${SUBLEVEL}${EXTRAVERSION}" + 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 "$TAG" +then + TAG=$(MAKEFLAGS= make -sC ../.. kernelversion) +fi +VN="$TAG$CID" +if test -n "$CID" +then + # format version string, strip trailing zero of sublevel: + VN=$(echo "$VN" | sed -e 's/-/./g;s/\([0-9]*[.][0-9]*\)[.]0/\1/') fi VN=$(expr "$VN" : v*'\(.*\)') if test -r $GVF then - VC=$(sed -e 's/^PERF_VERSION = //' <$GVF) + VC=$(sed -e 's/^#define PERF_VERSION "\(.*\)"/\1/' <$GVF) else VC=unset fi test "$VN" = "$VC" || { - echo >&2 "PERF_VERSION = $VN" - echo "PERF_VERSION = $VN" >$GVF + echo >&2 " PERF_VERSION = $VN" + echo "#define PERF_VERSION \"$VN\"" >$GVF } diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c index b8144e80bb1..c0b43ee40d9 100644 --- a/tools/perf/util/alias.c +++ b/tools/perf/util/alias.c @@ -3,7 +3,8 @@ static const char *alias_key; static char *alias_val; -static int alias_lookup_cb(const char *k, const char *v, void *cb __used) +static int alias_lookup_cb(const char *k, const char *v, + void *cb __maybe_unused) { if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) { if (!v) @@ -54,8 +55,7 @@ int split_cmdline(char *cmdline, const char ***argv) src++; c = cmdline[src]; if (!c) { - free(*argv); - *argv = NULL; + zfree(argv); return error("cmdline ends with \\"); } } @@ -67,8 +67,7 @@ int split_cmdline(char *cmdline, const char ***argv) cmdline[dst] = 0; if (quoted) { - free(*argv); - *argv = NULL; + zfree(argv); return error("unclosed quote"); } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c new file mode 100644 index 00000000000..809b4c50bea --- /dev/null +++ b/tools/perf/util/annotate.c @@ -0,0 +1,1412 @@ +/* + * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Parts came from builtin-annotate.c, see those files for further + * copyright notes. + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "util.h" +#include "ui/ui.h" +#include "sort.h" +#include "build-id.h" +#include "color.h" +#include "cache.h" +#include "symbol.h" +#include "debug.h" +#include "annotate.h" +#include "evsel.h" +#include <pthread.h> +#include <linux/bitops.h> + +const char *disassembler_style; +const char *objdump_path; + +static struct ins *ins__find(const char *name); +static int disasm_line__parse(char *line, char **namep, char **rawp); + +static void ins__delete(struct ins_operands *ops) +{ + zfree(&ops->source.raw); + zfree(&ops->source.name); + zfree(&ops->target.raw); + zfree(&ops->target.name); +} + +static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->raw); +} + +int ins__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + if (ins->ops->scnprintf) + return ins->ops->scnprintf(ins, bf, size, ops); + + return ins__raw_scnprintf(ins, bf, size, ops); +} + +static int call__parse(struct ins_operands *ops) +{ + char *endptr, *tok, *name; + + ops->target.addr = strtoull(ops->raw, &endptr, 16); + + name = strchr(endptr, '<'); + if (name == NULL) + goto indirect_call; + + name++; + + tok = strchr(name, '>'); + if (tok == NULL) + return -1; + + *tok = '\0'; + ops->target.name = strdup(name); + *tok = '>'; + + return ops->target.name == NULL ? -1 : 0; + +indirect_call: + tok = strchr(endptr, '('); + if (tok != NULL) { + ops->target.addr = 0; + return 0; + } + + tok = strchr(endptr, '*'); + if (tok == NULL) + return -1; + + ops->target.addr = strtoull(tok + 1, NULL, 16); + return 0; +} + +static int call__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + if (ops->target.name) + return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->target.name); + + if (ops->target.addr == 0) + return ins__raw_scnprintf(ins, bf, size, ops); + + return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr); +} + +static struct ins_ops call_ops = { + .parse = call__parse, + .scnprintf = call__scnprintf, +}; + +bool ins__is_call(const struct ins *ins) +{ + return ins->ops == &call_ops; +} + +static int jump__parse(struct ins_operands *ops) +{ + const char *s = strchr(ops->raw, '+'); + + ops->target.addr = strtoull(ops->raw, NULL, 16); + + if (s++ != NULL) + ops->target.offset = strtoull(s, NULL, 16); + else + ops->target.offset = UINT64_MAX; + + return 0; +} + +static int jump__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset); +} + +static struct ins_ops jump_ops = { + .parse = jump__parse, + .scnprintf = jump__scnprintf, +}; + +bool ins__is_jump(const struct ins *ins) +{ + return ins->ops == &jump_ops; +} + +static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep) +{ + char *endptr, *name, *t; + + if (strstr(raw, "(%rip)") == NULL) + return 0; + + *addrp = strtoull(comment, &endptr, 16); + name = strchr(endptr, '<'); + if (name == NULL) + return -1; + + name++; + + t = strchr(name, '>'); + if (t == NULL) + return 0; + + *t = '\0'; + *namep = strdup(name); + *t = '>'; + + return 0; +} + +static int lock__parse(struct ins_operands *ops) +{ + char *name; + + ops->locked.ops = zalloc(sizeof(*ops->locked.ops)); + if (ops->locked.ops == NULL) + return 0; + + if (disasm_line__parse(ops->raw, &name, &ops->locked.ops->raw) < 0) + goto out_free_ops; + + ops->locked.ins = ins__find(name); + if (ops->locked.ins == NULL) + goto out_free_ops; + + if (!ops->locked.ins->ops) + return 0; + + if (ops->locked.ins->ops->parse) + ops->locked.ins->ops->parse(ops->locked.ops); + + return 0; + +out_free_ops: + zfree(&ops->locked.ops); + return 0; +} + +static int lock__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + int printed; + + if (ops->locked.ins == NULL) + return ins__raw_scnprintf(ins, bf, size, ops); + + printed = scnprintf(bf, size, "%-6.6s ", ins->name); + return printed + ins__scnprintf(ops->locked.ins, bf + printed, + size - printed, ops->locked.ops); +} + +static void lock__delete(struct ins_operands *ops) +{ + zfree(&ops->locked.ops); + zfree(&ops->target.raw); + zfree(&ops->target.name); +} + +static struct ins_ops lock_ops = { + .free = lock__delete, + .parse = lock__parse, + .scnprintf = lock__scnprintf, +}; + +static int mov__parse(struct ins_operands *ops) +{ + char *s = strchr(ops->raw, ','), *target, *comment, prev; + + if (s == NULL) + return -1; + + *s = '\0'; + ops->source.raw = strdup(ops->raw); + *s = ','; + + if (ops->source.raw == NULL) + return -1; + + target = ++s; + + while (s[0] != '\0' && !isspace(s[0])) + ++s; + prev = *s; + *s = '\0'; + + ops->target.raw = strdup(target); + *s = prev; + + if (ops->target.raw == NULL) + goto out_free_source; + + comment = strchr(s, '#'); + if (comment == NULL) + return 0; + + while (comment[0] != '\0' && isspace(comment[0])) + ++comment; + + comment__symbol(ops->source.raw, comment, &ops->source.addr, &ops->source.name); + comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name); + + return 0; + +out_free_source: + zfree(&ops->source.raw); + return -1; +} + +static int mov__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + return scnprintf(bf, size, "%-6.6s %s,%s", ins->name, + ops->source.name ?: ops->source.raw, + ops->target.name ?: ops->target.raw); +} + +static struct ins_ops mov_ops = { + .parse = mov__parse, + .scnprintf = mov__scnprintf, +}; + +static int dec__parse(struct ins_operands *ops) +{ + char *target, *comment, *s, prev; + + target = s = ops->raw; + + while (s[0] != '\0' && !isspace(s[0])) + ++s; + prev = *s; + *s = '\0'; + + ops->target.raw = strdup(target); + *s = prev; + + if (ops->target.raw == NULL) + return -1; + + comment = strchr(s, '#'); + if (comment == NULL) + return 0; + + while (comment[0] != '\0' && isspace(comment[0])) + ++comment; + + comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name); + + return 0; +} + +static int dec__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + return scnprintf(bf, size, "%-6.6s %s", ins->name, + ops->target.name ?: ops->target.raw); +} + +static struct ins_ops dec_ops = { + .parse = dec__parse, + .scnprintf = dec__scnprintf, +}; + +static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size, + struct ins_operands *ops __maybe_unused) +{ + return scnprintf(bf, size, "%-6.6s", "nop"); +} + +static struct ins_ops nop_ops = { + .scnprintf = nop__scnprintf, +}; + +/* + * Must be sorted by name! + */ +static struct ins instructions[] = { + { .name = "add", .ops = &mov_ops, }, + { .name = "addl", .ops = &mov_ops, }, + { .name = "addq", .ops = &mov_ops, }, + { .name = "addw", .ops = &mov_ops, }, + { .name = "and", .ops = &mov_ops, }, + { .name = "bts", .ops = &mov_ops, }, + { .name = "call", .ops = &call_ops, }, + { .name = "callq", .ops = &call_ops, }, + { .name = "cmp", .ops = &mov_ops, }, + { .name = "cmpb", .ops = &mov_ops, }, + { .name = "cmpl", .ops = &mov_ops, }, + { .name = "cmpq", .ops = &mov_ops, }, + { .name = "cmpw", .ops = &mov_ops, }, + { .name = "cmpxch", .ops = &mov_ops, }, + { .name = "dec", .ops = &dec_ops, }, + { .name = "decl", .ops = &dec_ops, }, + { .name = "imul", .ops = &mov_ops, }, + { .name = "inc", .ops = &dec_ops, }, + { .name = "incl", .ops = &dec_ops, }, + { .name = "ja", .ops = &jump_ops, }, + { .name = "jae", .ops = &jump_ops, }, + { .name = "jb", .ops = &jump_ops, }, + { .name = "jbe", .ops = &jump_ops, }, + { .name = "jc", .ops = &jump_ops, }, + { .name = "jcxz", .ops = &jump_ops, }, + { .name = "je", .ops = &jump_ops, }, + { .name = "jecxz", .ops = &jump_ops, }, + { .name = "jg", .ops = &jump_ops, }, + { .name = "jge", .ops = &jump_ops, }, + { .name = "jl", .ops = &jump_ops, }, + { .name = "jle", .ops = &jump_ops, }, + { .name = "jmp", .ops = &jump_ops, }, + { .name = "jmpq", .ops = &jump_ops, }, + { .name = "jna", .ops = &jump_ops, }, + { .name = "jnae", .ops = &jump_ops, }, + { .name = "jnb", .ops = &jump_ops, }, + { .name = "jnbe", .ops = &jump_ops, }, + { .name = "jnc", .ops = &jump_ops, }, + { .name = "jne", .ops = &jump_ops, }, + { .name = "jng", .ops = &jump_ops, }, + { .name = "jnge", .ops = &jump_ops, }, + { .name = "jnl", .ops = &jump_ops, }, + { .name = "jnle", .ops = &jump_ops, }, + { .name = "jno", .ops = &jump_ops, }, + { .name = "jnp", .ops = &jump_ops, }, + { .name = "jns", .ops = &jump_ops, }, + { .name = "jnz", .ops = &jump_ops, }, + { .name = "jo", .ops = &jump_ops, }, + { .name = "jp", .ops = &jump_ops, }, + { .name = "jpe", .ops = &jump_ops, }, + { .name = "jpo", .ops = &jump_ops, }, + { .name = "jrcxz", .ops = &jump_ops, }, + { .name = "js", .ops = &jump_ops, }, + { .name = "jz", .ops = &jump_ops, }, + { .name = "lea", .ops = &mov_ops, }, + { .name = "lock", .ops = &lock_ops, }, + { .name = "mov", .ops = &mov_ops, }, + { .name = "movb", .ops = &mov_ops, }, + { .name = "movdqa",.ops = &mov_ops, }, + { .name = "movl", .ops = &mov_ops, }, + { .name = "movq", .ops = &mov_ops, }, + { .name = "movslq", .ops = &mov_ops, }, + { .name = "movzbl", .ops = &mov_ops, }, + { .name = "movzwl", .ops = &mov_ops, }, + { .name = "nop", .ops = &nop_ops, }, + { .name = "nopl", .ops = &nop_ops, }, + { .name = "nopw", .ops = &nop_ops, }, + { .name = "or", .ops = &mov_ops, }, + { .name = "orl", .ops = &mov_ops, }, + { .name = "test", .ops = &mov_ops, }, + { .name = "testb", .ops = &mov_ops, }, + { .name = "testl", .ops = &mov_ops, }, + { .name = "xadd", .ops = &mov_ops, }, + { .name = "xbeginl", .ops = &jump_ops, }, + { .name = "xbeginq", .ops = &jump_ops, }, +}; + +static int ins__cmp(const void *name, const void *insp) +{ + const struct ins *ins = insp; + + return strcmp(name, ins->name); +} + +static struct ins *ins__find(const char *name) +{ + const int nmemb = ARRAY_SIZE(instructions); + + return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp); +} + +int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym) +{ + struct annotation *notes = symbol__annotation(sym); + pthread_mutex_init(¬es->lock, NULL); + return 0; +} + +int symbol__alloc_hist(struct symbol *sym) +{ + struct annotation *notes = symbol__annotation(sym); + const size_t size = symbol__size(sym); + size_t sizeof_sym_hist; + + /* Check for overflow when calculating sizeof_sym_hist */ + if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(u64)) + return -1; + + sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64)); + + /* Check for overflow in zalloc argument */ + if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src)) + / symbol_conf.nr_events) + return -1; + + notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist); + if (notes->src == NULL) + return -1; + notes->src->sizeof_sym_hist = sizeof_sym_hist; + notes->src->nr_histograms = symbol_conf.nr_events; + INIT_LIST_HEAD(¬es->src->source); + return 0; +} + +void symbol__annotate_zero_histograms(struct symbol *sym) +{ + struct annotation *notes = symbol__annotation(sym); + + pthread_mutex_lock(¬es->lock); + if (notes->src != NULL) + memset(notes->src->histograms, 0, + notes->src->nr_histograms * notes->src->sizeof_sym_hist); + pthread_mutex_unlock(¬es->lock); +} + +static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, + struct annotation *notes, int evidx, u64 addr) +{ + unsigned offset; + struct sym_hist *h; + + pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr)); + + if (addr < sym->start || addr > sym->end) + return -ERANGE; + + offset = addr - sym->start; + h = annotation__histogram(notes, evidx); + h->sum++; + h->addr[offset]++; + + pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64 + ", evidx=%d] => %" PRIu64 "\n", sym->start, sym->name, + addr, addr - sym->start, evidx, h->addr[offset]); + return 0; +} + +static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, + int evidx, u64 addr) +{ + struct annotation *notes; + + if (sym == NULL) + return 0; + + notes = symbol__annotation(sym); + if (notes->src == NULL) { + if (symbol__alloc_hist(sym) < 0) + return -ENOMEM; + } + + return __symbol__inc_addr_samples(sym, map, notes, evidx, addr); +} + +int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx) +{ + return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr); +} + +int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip) +{ + return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip); +} + +static void disasm_line__init_ins(struct disasm_line *dl) +{ + dl->ins = ins__find(dl->name); + + if (dl->ins == NULL) + return; + + if (!dl->ins->ops) + return; + + if (dl->ins->ops->parse) + dl->ins->ops->parse(&dl->ops); +} + +static int disasm_line__parse(char *line, char **namep, char **rawp) +{ + char *name = line, tmp; + + while (isspace(name[0])) + ++name; + + if (name[0] == '\0') + return -1; + + *rawp = name + 1; + + while ((*rawp)[0] != '\0' && !isspace((*rawp)[0])) + ++*rawp; + + tmp = (*rawp)[0]; + (*rawp)[0] = '\0'; + *namep = strdup(name); + + if (*namep == NULL) + goto out_free_name; + + (*rawp)[0] = tmp; + + if ((*rawp)[0] != '\0') { + (*rawp)++; + while (isspace((*rawp)[0])) + ++(*rawp); + } + + return 0; + +out_free_name: + zfree(namep); + return -1; +} + +static struct disasm_line *disasm_line__new(s64 offset, char *line, size_t privsize) +{ + struct disasm_line *dl = zalloc(sizeof(*dl) + privsize); + + if (dl != NULL) { + dl->offset = offset; + dl->line = strdup(line); + if (dl->line == NULL) + goto out_delete; + + if (offset != -1) { + if (disasm_line__parse(dl->line, &dl->name, &dl->ops.raw) < 0) + goto out_free_line; + + disasm_line__init_ins(dl); + } + } + + return dl; + +out_free_line: + zfree(&dl->line); +out_delete: + free(dl); + return NULL; +} + +void disasm_line__free(struct disasm_line *dl) +{ + zfree(&dl->line); + zfree(&dl->name); + if (dl->ins && dl->ins->ops->free) + dl->ins->ops->free(&dl->ops); + else + ins__delete(&dl->ops); + free(dl); +} + +int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw) +{ + if (raw || !dl->ins) + return scnprintf(bf, size, "%-6.6s %s", dl->name, dl->ops.raw); + + return ins__scnprintf(dl->ins, bf, size, &dl->ops); +} + +static void disasm__add(struct list_head *head, struct disasm_line *line) +{ + list_add_tail(&line->node, head); +} + +struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos) +{ + list_for_each_entry_continue(pos, head, node) + if (pos->offset >= 0) + return pos; + + return NULL; +} + +double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, + s64 end, const char **path) +{ + struct source_line *src_line = notes->src->lines; + double percent = 0.0; + + if (src_line) { + size_t sizeof_src_line = sizeof(*src_line) + + sizeof(src_line->p) * (src_line->nr_pcnt - 1); + + while (offset < end) { + src_line = (void *)notes->src->lines + + (sizeof_src_line * offset); + + if (*path == NULL) + *path = src_line->path; + + percent += src_line->p[evidx].percent; + offset++; + } + } else { + struct sym_hist *h = annotation__histogram(notes, evidx); + unsigned int hits = 0; + + while (offset < end) + hits += h->addr[offset++]; + + if (h->sum) + percent = 100.0 * hits / h->sum; + } + + return percent; +} + +static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start, + struct perf_evsel *evsel, u64 len, int min_pcnt, int printed, + int max_lines, struct disasm_line *queue) +{ + static const char *prev_line; + static const char *prev_color; + + if (dl->offset != -1) { + const char *path = NULL; + double percent, max_percent = 0.0; + double *ppercents = &percent; + int i, nr_percent = 1; + const char *color; + struct annotation *notes = symbol__annotation(sym); + s64 offset = dl->offset; + const u64 addr = start + offset; + struct disasm_line *next; + + next = disasm__get_next_ip_line(¬es->src->source, dl); + + if (perf_evsel__is_group_event(evsel)) { + nr_percent = evsel->nr_members; + ppercents = calloc(nr_percent, sizeof(double)); + if (ppercents == NULL) + return -1; + } + + for (i = 0; i < nr_percent; i++) { + percent = disasm__calc_percent(notes, + notes->src->lines ? i : evsel->idx + i, + offset, + next ? next->offset : (s64) len, + &path); + + ppercents[i] = percent; + if (percent > max_percent) + max_percent = percent; + } + + if (max_percent < min_pcnt) + return -1; + + if (max_lines && printed >= max_lines) + return 1; + + if (queue != NULL) { + list_for_each_entry_from(queue, ¬es->src->source, node) { + if (queue == dl) + break; + disasm_line__print(queue, sym, start, evsel, len, + 0, 0, 1, NULL); + } + } + + color = get_percent_color(max_percent); + + /* + * Also color the filename and line if needed, with + * the same color than the percentage. Don't print it + * twice for close colored addr with the same filename:line + */ + if (path) { + if (!prev_line || strcmp(prev_line, path) + || color != prev_color) { + color_fprintf(stdout, color, " %s", path); + prev_line = path; + prev_color = color; + } + } + + for (i = 0; i < nr_percent; i++) { + percent = ppercents[i]; + color = get_percent_color(percent); + color_fprintf(stdout, color, " %7.2f", percent); + } + + printf(" : "); + color_fprintf(stdout, PERF_COLOR_MAGENTA, " %" PRIx64 ":", addr); + color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", dl->line); + + if (ppercents != &percent) + free(ppercents); + + } else if (max_lines && printed >= max_lines) + return 1; + else { + int width = 8; + + if (queue) + return -1; + + if (perf_evsel__is_group_event(evsel)) + width *= evsel->nr_members; + + if (!*dl->line) + printf(" %*s:\n", width, " "); + else + printf(" %*s: %s\n", width, " ", dl->line); + } + + return 0; +} + +/* + * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw) + * which looks like following + * + * 0000000000415500 <_init>: + * 415500: sub $0x8,%rsp + * 415504: mov 0x2f5ad5(%rip),%rax # 70afe0 <_DYNAMIC+0x2f8> + * 41550b: test %rax,%rax + * 41550e: je 415515 <_init+0x15> + * 415510: callq 416e70 <__gmon_start__@plt> + * 415515: add $0x8,%rsp + * 415519: retq + * + * it will be parsed and saved into struct disasm_line as + * <offset> <name> <ops.raw> + * + * The offset will be a relative offset from the start of the symbol and -1 + * means that it's not a disassembly line so should be treated differently. + * The ops.raw part will be parsed further according to type of the instruction. + */ +static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, + FILE *file, size_t privsize) +{ + struct annotation *notes = symbol__annotation(sym); + struct disasm_line *dl; + char *line = NULL, *parsed_line, *tmp, *tmp2, *c; + size_t line_len; + s64 line_ip, offset = -1; + + if (getline(&line, &line_len, file) < 0) + return -1; + + if (!line) + return -1; + + while (line_len != 0 && isspace(line[line_len - 1])) + line[--line_len] = '\0'; + + c = strchr(line, '\n'); + if (c) + *c = 0; + + line_ip = -1; + parsed_line = line; + + /* + * Strip leading spaces: + */ + tmp = line; + while (*tmp) { + if (*tmp != ' ') + break; + tmp++; + } + + if (*tmp) { + /* + * Parse hexa addresses followed by ':' + */ + line_ip = strtoull(tmp, &tmp2, 16); + if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0') + line_ip = -1; + } + + if (line_ip != -1) { + u64 start = map__rip_2objdump(map, sym->start), + end = map__rip_2objdump(map, sym->end); + + offset = line_ip - start; + if ((u64)line_ip < start || (u64)line_ip > end) + offset = -1; + else + parsed_line = tmp2 + 1; + } + + dl = disasm_line__new(offset, parsed_line, privsize); + free(line); + + 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; + char *filename = dso__build_id_filename(dso, NULL, 0); + bool free_filename = true; + char command[PATH_MAX * 2]; + 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", + symbol_conf.symfs, filename); + } + + if (filename == NULL) { + if (dso->has_build_id) { + pr_err("Can't annotate %s: not enough memory\n", + sym->name); + return -ENOMEM; + } + goto fallback; + } else if (readlink(symfs_filename, command, sizeof(command)) < 0 || + strstr(command, "[kernel.kallsyms]") || + access(symfs_filename, R_OK)) { + free(filename); +fallback: + /* + * If we don't have build-ids or the build-id file isn't in the + * cache, or is just a kallsyms file, well, lets hope that this + * DSO is the same as when 'perf record' ran. + */ + filename = (char *)dso->long_name; + snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", + symbol_conf.symfs, filename); + free_filename = false; + } + + 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; + + if (dso->annotate_warned) + goto out_free_filename; + + if (dso->has_build_id) { + build_id__sprintf(dso->build_id, + sizeof(dso->build_id), bf + 15); + build_id_msg = bf; + } + err = -ENOENT; + dso->annotate_warned = 1; + pr_err("Can't annotate %s:\n\n" + "No vmlinux file%s\nwas found in the path.\n\n" + "Please use:\n\n" + " perf buildid-cache -vu vmlinux\n\n" + "or:\n\n" + " --vmlinux vmlinux\n", + sym->name, build_id_msg ?: ""); + goto out_free_filename; + } + + pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__, + filename, sym->name, map->unmap_ip(map, sym->start), + map->unmap_ip(map, sym->end)); + + 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 2>/dev/null|grep -v %s|expand", + objdump_path ? objdump_path : "objdump", + disassembler_style ? "-M " : "", + disassembler_style ? disassembler_style : "", + map__rip_2objdump(map, sym->start), + map__rip_2objdump(map, sym->end+1), + symbol_conf.annotate_asm_raw ? "" : "--no-show-raw", + symbol_conf.annotate_src ? "-S" : "", + symfs_filename, filename); + + pr_debug("Executing: %s\n", command); + + file = popen(command, "r"); + if (!file) + goto out_free_filename; + + while (!feof(file)) + 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; +} + +static void insert_source_line(struct rb_root *root, struct source_line *src_line) +{ + struct source_line *iter; + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + int i, ret; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct source_line, node); + + ret = strcmp(iter->path, src_line->path); + if (ret == 0) { + for (i = 0; i < src_line->nr_pcnt; i++) + iter->p[i].percent_sum += src_line->p[i].percent; + return; + } + + if (ret < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + for (i = 0; i < src_line->nr_pcnt; i++) + src_line->p[i].percent_sum = src_line->p[i].percent; + + rb_link_node(&src_line->node, parent, p); + rb_insert_color(&src_line->node, root); +} + +static int cmp_source_line(struct source_line *a, struct source_line *b) +{ + int i; + + for (i = 0; i < a->nr_pcnt; i++) { + if (a->p[i].percent_sum == b->p[i].percent_sum) + continue; + return a->p[i].percent_sum > b->p[i].percent_sum; + } + + return 0; +} + +static void __resort_source_line(struct rb_root *root, struct source_line *src_line) +{ + struct source_line *iter; + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct source_line, node); + + if (cmp_source_line(src_line, iter)) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&src_line->node, parent, p); + rb_insert_color(&src_line->node, root); +} + +static void resort_source_line(struct rb_root *dest_root, struct rb_root *src_root) +{ + struct source_line *src_line; + struct rb_node *node; + + node = rb_first(src_root); + while (node) { + struct rb_node *next; + + src_line = rb_entry(node, struct source_line, node); + next = rb_next(node); + rb_erase(node, src_root); + + __resort_source_line(dest_root, src_line); + node = next; + } +} + +static void symbol__free_source_line(struct symbol *sym, int len) +{ + struct annotation *notes = symbol__annotation(sym); + struct source_line *src_line = notes->src->lines; + size_t sizeof_src_line; + int i; + + sizeof_src_line = sizeof(*src_line) + + (sizeof(src_line->p) * (src_line->nr_pcnt - 1)); + + for (i = 0; i < len; i++) { + free_srcline(src_line->path); + src_line = (void *)src_line + sizeof_src_line; + } + + zfree(¬es->src->lines); +} + +/* 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) +{ + u64 start; + int i, k; + int evidx = evsel->idx; + struct source_line *src_line; + struct annotation *notes = symbol__annotation(sym); + struct sym_hist *h = annotation__histogram(notes, evidx); + struct rb_root tmp_root = RB_ROOT; + int nr_pcnt = 1; + u64 h_sum = h->sum; + size_t sizeof_src_line = sizeof(struct source_line); + + if (perf_evsel__is_group_event(evsel)) { + for (i = 1; i < evsel->nr_members; i++) { + h = annotation__histogram(notes, evidx + i); + h_sum += h->sum; + } + nr_pcnt = evsel->nr_members; + sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->p); + } + + if (!h_sum) + return 0; + + src_line = notes->src->lines = calloc(len, sizeof_src_line); + if (!notes->src->lines) + return -1; + + start = map__rip_2objdump(map, sym->start); + + for (i = 0; i < len; i++) { + u64 offset; + double percent_max = 0.0; + + src_line->nr_pcnt = nr_pcnt; + + for (k = 0; k < nr_pcnt; k++) { + h = annotation__histogram(notes, evidx + k); + src_line->p[k].percent = 100.0 * h->addr[i] / h->sum; + + if (src_line->p[k].percent > percent_max) + percent_max = src_line->p[k].percent; + } + + if (percent_max <= 0.5) + goto next; + + offset = start + i; + src_line->path = get_srcline(map->dso, offset); + insert_source_line(&tmp_root, src_line); + + next: + src_line = (void *)src_line + sizeof_src_line; + } + + resort_source_line(root, &tmp_root); + return 0; +} + +static void print_summary(struct rb_root *root, const char *filename) +{ + struct source_line *src_line; + struct rb_node *node; + + printf("\nSorted summary for file %s\n", filename); + printf("----------------------------------------------\n\n"); + + if (RB_EMPTY_ROOT(root)) { + printf(" Nothing higher than %1.1f%%\n", MIN_GREEN); + return; + } + + node = rb_first(root); + while (node) { + double percent, percent_max = 0.0; + const char *color; + char *path; + int i; + + src_line = rb_entry(node, struct source_line, node); + for (i = 0; i < src_line->nr_pcnt; i++) { + percent = src_line->p[i].percent_sum; + color = get_percent_color(percent); + color_fprintf(stdout, color, " %7.2f", percent); + + if (percent > percent_max) + percent_max = percent; + } + + path = src_line->path; + color = get_percent_color(percent_max); + color_fprintf(stdout, color, " %s\n", path); + + node = rb_next(node); + } +} + +static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel) +{ + struct annotation *notes = symbol__annotation(sym); + struct sym_hist *h = annotation__histogram(notes, evsel->idx); + u64 len = symbol__size(sym), offset; + + for (offset = 0; offset < len; ++offset) + if (h->addr[offset] != 0) + printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2, + sym->start + offset, h->addr[offset]); + printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum); +} + +int symbol__annotate_printf(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, bool full_paths, + int min_pcnt, int max_lines, int context) +{ + struct dso *dso = map->dso; + char *filename; + const char *d_filename; + const char *evsel_name = perf_evsel__name(evsel); + struct annotation *notes = symbol__annotation(sym); + struct disasm_line *pos, *queue = NULL; + u64 start = map__rip_2objdump(map, sym->start); + int printed = 2, queue_len = 0; + int more = 0; + u64 len; + int width = 8; + int namelen, evsel_name_len, graph_dotted_len; + + filename = strdup(dso->long_name); + if (!filename) + return -ENOMEM; + + if (full_paths) + d_filename = filename; + else + d_filename = basename(filename); + + len = symbol__size(sym); + namelen = strlen(d_filename); + evsel_name_len = strlen(evsel_name); + + if (perf_evsel__is_group_event(evsel)) + width *= evsel->nr_members; + + printf(" %-*.*s| Source code & Disassembly of %s for %s\n", + width, width, "Percent", d_filename, evsel_name); + + graph_dotted_len = width + namelen + evsel_name_len; + printf("-%-*.*s-----------------------------------------\n", + graph_dotted_len, graph_dotted_len, graph_dotted_line); + + if (verbose) + symbol__annotate_hits(sym, evsel); + + list_for_each_entry(pos, ¬es->src->source, node) { + if (context && queue == NULL) { + queue = pos; + queue_len = 0; + } + + switch (disasm_line__print(pos, sym, start, evsel, len, + min_pcnt, printed, max_lines, + queue)) { + case 0: + ++printed; + if (context) { + printed += queue_len; + queue = NULL; + queue_len = 0; + } + break; + case 1: + /* filtered by max_lines */ + ++more; + break; + case -1: + default: + /* + * Filtered by min_pcnt or non IP lines when + * context != 0 + */ + if (!context) + break; + if (queue_len == context) + queue = list_entry(queue->node.next, typeof(*queue), node); + else + ++queue_len; + break; + } + } + + free(filename); + + return more; +} + +void symbol__annotate_zero_histogram(struct symbol *sym, int evidx) +{ + struct annotation *notes = symbol__annotation(sym); + struct sym_hist *h = annotation__histogram(notes, evidx); + + memset(h, 0, notes->src->sizeof_sym_hist); +} + +void symbol__annotate_decay_histogram(struct symbol *sym, int evidx) +{ + struct annotation *notes = symbol__annotation(sym); + struct sym_hist *h = annotation__histogram(notes, evidx); + int len = symbol__size(sym), offset; + + h->sum = 0; + for (offset = 0; offset < len; ++offset) { + h->addr[offset] = h->addr[offset] * 7 / 8; + h->sum += h->addr[offset]; + } +} + +void disasm__purge(struct list_head *head) +{ + struct disasm_line *pos, *n; + + list_for_each_entry_safe(pos, n, head, node) { + list_del(&pos->node); + disasm_line__free(pos); + } +} + +static size_t disasm_line__fprintf(struct disasm_line *dl, FILE *fp) +{ + size_t printed; + + if (dl->offset == -1) + return fprintf(fp, "%s\n", dl->line); + + printed = fprintf(fp, "%#" PRIx64 " %s", dl->offset, dl->name); + + if (dl->ops.raw[0] != '\0') { + printed += fprintf(fp, "%.*s %s\n", 6 - (int)printed, " ", + dl->ops.raw); + } + + return printed + fprintf(fp, "\n"); +} + +size_t disasm__fprintf(struct list_head *head, FILE *fp) +{ + struct disasm_line *pos; + size_t printed = 0; + + list_for_each_entry(pos, head, node) + printed += disasm_line__fprintf(pos, fp); + + return printed; +} + +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) +{ + struct dso *dso = map->dso; + struct rb_root source_line = RB_ROOT; + u64 len; + + if (symbol__annotate(sym, map, 0) < 0) + return -1; + + len = symbol__size(sym); + + if (print_lines) { + 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, + min_pcnt, max_lines, 0); + if (print_lines) + symbol__free_source_line(sym, len); + + disasm__purge(&symbol__annotation(sym)->src->source); + + return 0; +} + +int hist_entry__annotate(struct hist_entry *he, size_t privsize) +{ + return symbol__annotate(he->ms.sym, he->ms.map, privsize); +} + +bool ui__has_annotation(void) +{ + return use_browser == 1 && sort__has_sym; +} diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h new file mode 100644 index 00000000000..112d6e26815 --- /dev/null +++ b/tools/perf/util/annotate.h @@ -0,0 +1,177 @@ +#ifndef __PERF_ANNOTATE_H +#define __PERF_ANNOTATE_H + +#include <stdbool.h> +#include <stdint.h> +#include <linux/types.h> +#include "symbol.h" +#include "hist.h" +#include "sort.h" +#include <linux/list.h> +#include <linux/rbtree.h> +#include <pthread.h> + +struct ins; + +struct ins_operands { + char *raw; + struct { + char *raw; + char *name; + u64 addr; + u64 offset; + } target; + union { + struct { + char *raw; + char *name; + u64 addr; + } source; + struct { + struct ins *ins; + struct ins_operands *ops; + } locked; + }; +}; + +struct ins_ops { + void (*free)(struct ins_operands *ops); + int (*parse)(struct ins_operands *ops); + int (*scnprintf)(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops); +}; + +struct ins { + const char *name; + struct ins_ops *ops; +}; + +bool ins__is_jump(const struct ins *ins); +bool ins__is_call(const struct ins *ins); +int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops); + +struct annotation; + +struct disasm_line { + struct list_head node; + s64 offset; + char *line; + char *name; + struct ins *ins; + struct ins_operands ops; +}; + +static inline bool disasm_line__has_offset(const struct disasm_line *dl) +{ + return dl->ops.target.offset != UINT64_MAX; +} + +void disasm_line__free(struct disasm_line *dl); +struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos); +int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw); +size_t disasm__fprintf(struct list_head *head, FILE *fp); +double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, + s64 end, const char **path); + +struct sym_hist { + u64 sum; + u64 addr[0]; +}; + +struct source_line_percent { + double percent; + double percent_sum; +}; + +struct source_line { + struct rb_node node; + char *path; + int nr_pcnt; + struct source_line_percent p[1]; +}; + +/** struct annotated_source - symbols with hits have this attached as in sannotation + * + * @histogram: Array of addr hit histograms per event being monitored + * @lines: If 'print_lines' is specified, per source code line percentages + * @source: source parsed from a disassembler like objdump -dS + * + * lines is allocated, percentages calculated and all sorted by percentage + * when the annotation is about to be presented, so the percentages are for + * one of the entries in the histogram array, i.e. for the event/counter being + * presented. It is deallocated right after symbol__{tui,tty,etc}_annotate + * returns. + */ +struct annotated_source { + struct list_head source; + struct source_line *lines; + int nr_histograms; + int sizeof_sym_hist; + struct sym_hist histograms[0]; +}; + +struct annotation { + pthread_mutex_t lock; + struct annotated_source *src; +}; + +struct sannotation { + struct annotation annotation; + struct symbol symbol; +}; + +static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx) +{ + return (((void *)¬es->src->histograms) + + (notes->src->sizeof_sym_hist * idx)); +} + +static inline struct annotation *symbol__annotation(struct symbol *sym) +{ + struct sannotation *a = container_of(sym, struct sannotation, symbol); + return &a->annotation; +} + +int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx); + +int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr); + +int symbol__alloc_hist(struct symbol *sym); +void symbol__annotate_zero_histograms(struct symbol *sym); + +int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize); + +int hist_entry__annotate(struct hist_entry *he, size_t privsize); + +int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym); +int symbol__annotate_printf(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, bool full_paths, + int min_pcnt, int max_lines, int context); +void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); +void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); +void disasm__purge(struct list_head *head); + +bool ui__has_annotation(void); + +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 HAVE_SLANG_SUPPORT +int symbol__tui_annotate(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, + struct hist_browser_timer *hbt); +#else +static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, + struct map *map __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct hist_browser_timer *hbt + __maybe_unused) +{ + return 0; +} +#endif + +extern const char *disassembler_style; + +#endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/bitmap.c b/tools/perf/util/bitmap.c index 5e230acae1e..0a1adc1111f 100644 --- a/tools/perf/util/bitmap.c +++ b/tools/perf/util/bitmap.c @@ -19,3 +19,13 @@ int __bitmap_weight(const unsigned long *bitmap, int bits) return w; } + +void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits) +{ + int k; + int nr = BITS_TO_LONGS(bits); + + for (k = 0; k < nr; k++) + dst[k] = bitmap1[k] | bitmap2[k]; +} diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index e437edb7241..a904a4cfe7d 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -13,12 +13,19 @@ #include "symbol.h" #include <linux/kernel.h> #include "debug.h" +#include "session.h" +#include "tool.h" -static int build_id__mark_dso_hit(event_t *event, struct perf_session *session) +int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, + union perf_event *event, + 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 = perf_session__findnew(session, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->tid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", @@ -26,8 +33,8 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session) return -1; } - thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION, - event->ip.pid, event->ip.ip, &al); + thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, + sample->ip, &al); if (al.map != NULL) al.map->dso->hit = 1; @@ -35,37 +42,61 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session) return 0; } -static int event__exit_del_thread(event_t *self, struct perf_session *session) +static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample + __maybe_unused, + struct machine *machine) { - struct thread *thread = perf_session__findnew(session, self->fork.tid); + struct thread *thread = machine__findnew_thread(machine, + event->fork.pid, + event->fork.tid); - dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid, - self->fork.ppid, self->fork.ptid); + dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid, + event->fork.ppid, event->fork.ptid); if (thread) { - rb_erase(&thread->rb_node, &session->threads); - session->last_match = NULL; + rb_erase(&thread->rb_node, &machine->threads); + machine->last_match = NULL; thread__delete(thread); } return 0; } -struct perf_event_ops build_id__mark_dso_hit_ops = { +struct perf_tool build_id__mark_dso_hit_ops = { .sample = build_id__mark_dso_hit, - .mmap = event__process_mmap, - .fork = event__process_task, - .exit = event__exit_del_thread, + .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, + .build_id = perf_event__process_build_id, }; -char *dso__build_id_filename(struct dso *self, char *bf, size_t size) +int build_id__sprintf(const u8 *build_id, int len, char *bf) +{ + char *bid = bf; + const u8 *raw = build_id; + int i; + + for (i = 0; i < len; ++i) { + sprintf(bid, "%02x", *raw); + ++raw; + bid += 2; + } + + return raw - build_id; +} + +char *dso__build_id_filename(const 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 5dafb00eaa0..ae392561470 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -1,10 +1,18 @@ #ifndef PERF_BUILD_ID_H_ #define PERF_BUILD_ID_H_ 1 -#include "session.h" +#define BUILD_ID_SIZE 20 -extern struct perf_event_ops build_id__mark_dso_hit_ops; +#include "tool.h" +#include <linux/types.h> -char *dso__build_id_filename(struct dso *self, char *bf, size_t size); +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(const 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 a7729797fd9..7b176dd02e1 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -5,6 +5,7 @@ #include "util.h" #include "strbuf.h" #include "../perf.h" +#include "../ui/ui.h" #define CMD_EXEC_PATH "--exec-path" #define CMD_PERF_DIR "--perf-dir=" @@ -31,19 +32,6 @@ extern const char *pager_program; extern int pager_in_use(void); extern int pager_use_color; -extern int use_browser; - -#ifdef NO_NEWT_SUPPORT -static inline void setup_browser(void) -{ - setup_pager(); -} -static inline void exit_browser(bool wait_for_ok __used) {} -#else -void setup_browser(void); -void exit_browser(bool wait_for_ok); -#endif - char *alias_lookup(const char *alias); int split_cmdline(char *cmdline, const char ***argv); @@ -82,8 +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))); -#ifdef NO_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 e12d539417b..48b6d3f5001 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com> + * Copyright (C) 2009-2011, Frederic Weisbecker <fweisbec@gmail.com> * * Handle the callchains from the stream in an ad-hoc radix tree and then * sort them in an rbtree. @@ -15,21 +15,93 @@ #include <errno.h> #include <math.h> +#include "asm/bug.h" + +#include "hist.h" #include "util.h" +#include "sort.h" +#include "machine.h" #include "callchain.h" -bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event) +__thread struct callchain_cursor callchain_cursor; + +int +parse_callchain_report_opt(const char *arg) { - 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; -} + char *tok, *tok2; + char *endptr; + + symbol_conf.use_callchain = true; + + if (!arg) + return 0; + + tok = strtok((char *)arg, ","); + if (!tok) + return -1; + + /* get the output mode */ + if (!strncmp(tok, "graph", strlen(arg))) { + callchain_param.mode = CHAIN_GRAPH_ABS; + + } else if (!strncmp(tok, "flat", strlen(arg))) { + callchain_param.mode = CHAIN_FLAT; + } else if (!strncmp(tok, "fractal", strlen(arg))) { + callchain_param.mode = CHAIN_GRAPH_REL; + } else if (!strncmp(tok, "none", strlen(arg))) { + callchain_param.mode = CHAIN_NONE; + symbol_conf.use_callchain = false; + return 0; + } else { + return -1; + } -#define chain_for_each_child(child, parent) \ - list_for_each_entry(child, &parent->children, brothers) + /* get the min percentage */ + tok = strtok(NULL, ","); + if (!tok) + goto setup; -#define chain_for_each_child_safe(child, next, parent) \ - list_for_each_entry_safe(child, next, &parent->children, brothers) + callchain_param.min_percent = strtod(tok, &endptr); + if (tok == endptr) + return -1; + + /* get the print limit */ + tok2 = strtok(NULL, ","); + if (!tok2) + goto setup; + + if (tok2[0] != 'c') { + callchain_param.print_limit = strtoul(tok2, &endptr, 0); + tok2 = strtok(NULL, ","); + if (!tok2) + goto setup; + } + + /* get the call chain order */ + if (!strncmp(tok2, "caller", strlen("caller"))) + callchain_param.order = ORDER_CALLER; + else if (!strncmp(tok2, "callee", strlen("callee"))) + callchain_param.order = ORDER_CALLEE; + else + return -1; + + /* Get the sort key */ + tok2 = strtok(NULL, ","); + if (!tok2) + goto setup; + if (!strncmp(tok2, "function", strlen("function"))) + callchain_param.key = CCKEY_FUNCTION; + else if (!strncmp(tok2, "address", strlen("address"))) + callchain_param.key = CCKEY_ADDRESS; + else + return -1; +setup: + if (callchain_register_param(&callchain_param) < 0) { + pr_err("Can't register callchain params\n"); + return -1; + } + return 0; +} static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, @@ -38,14 +110,14 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct callchain_node *rnode; - u64 chain_cumul = cumul_hits(chain); + u64 chain_cumul = callchain_cumul_hits(chain); while (*p) { u64 rnode_cumul; parent = *p; rnode = rb_entry(parent, struct callchain_node, rb_node); - rnode_cumul = cumul_hits(rnode); + rnode_cumul = callchain_cumul_hits(rnode); switch (mode) { case CHAIN_FLAT: @@ -75,10 +147,16 @@ 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); @@ -90,7 +168,7 @@ __sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node, */ static void sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root, - u64 min_hit, struct callchain_param *param __used) + u64 min_hit, struct callchain_param *param __maybe_unused) { __sort_chain_flat(rb_root, &root->node, min_hit); } @@ -98,13 +176,18 @@ 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 (cumul_hits(child) >= min_hit) + if (callchain_cumul_hits(child) >= min_hit) rb_insert_callchain(&node->rb_root, child, CHAIN_GRAPH_ABS); } @@ -112,7 +195,7 @@ static void __sort_chain_graph_abs(struct callchain_node *node, static void sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_root *chain_root, - u64 min_hit, struct callchain_param *param __used) + u64 min_hit, struct callchain_param *param __maybe_unused) { __sort_chain_graph_abs(&chain_root->node, min_hit); rb_root->rb_node = chain_root->node.rb_root.rb_node; @@ -121,15 +204,20 @@ 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 (cumul_hits(child) >= min_hit) + if (callchain_cumul_hits(child) >= min_hit) rb_insert_callchain(&node->rb_root, child, CHAIN_GRAPH_REL); } @@ -137,13 +225,13 @@ static void __sort_chain_graph_rel(struct callchain_node *node, static void sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_root *chain_root, - u64 min_hit __used, struct callchain_param *param) + u64 min_hit __maybe_unused, struct callchain_param *param) { __sort_chain_graph_rel(&chain_root->node, param->min_percent / 100.0); rb_root->rb_node = chain_root->node.rb_root.rb_node; } -int register_callchain_param(struct callchain_param *param) +int callchain_register_param(struct callchain_param *param) { switch (param->mode) { case CHAIN_GRAPH_ABS: @@ -177,44 +265,46 @@ 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; - list_splice(&parent->children, &new->children); - INIT_LIST_HEAD(&parent->children); + new->rb_root_in = parent->rb_root_in; + parent->rb_root_in = RB_ROOT; - chain_for_each_child(next, new) - next->parent = new; + 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); + } + + /* 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->brothers, &parent->children); return new; } -struct resolved_ip { - u64 ip; - struct map_symbol ms; -}; - -struct resolved_chain { - u64 nr; - struct resolved_ip ips[0]; -}; - - /* * Fill the node with callchain values */ static void -fill_node(struct callchain_node *node, struct resolved_chain *chain, int start) +fill_node(struct callchain_node *node, struct callchain_cursor *cursor) { - unsigned int i; + struct callchain_cursor_node *cursor_node; + + node->val_nr = cursor->nr - cursor->pos; + if (!node->val_nr) + pr_warning("Warning: empty node in callchain tree\n"); + + cursor_node = callchain_cursor_current(cursor); - for (i = start; i < chain->nr; i++) { + while (cursor_node) { struct callchain_list *call; call = zalloc(sizeof(*call)); @@ -222,26 +312,41 @@ fill_node(struct callchain_node *node, struct resolved_chain *chain, int start) perror("not enough memory for the code path tree"); return; } - call->ip = chain->ips[i].ip; - call->ms = chain->ips[i].ms; + call->ip = cursor_node->ip; + call->ms.sym = cursor_node->sym; + call->ms.map = cursor_node->map; list_add_tail(&call->list, &node->val); + + callchain_cursor_advance(cursor); + cursor_node = callchain_cursor_current(cursor); } - node->val_nr = chain->nr - start; - if (!node->val_nr) - pr_warning("Warning: empty node in callchain tree\n"); } -static void -add_child(struct callchain_node *parent, struct resolved_chain *chain, - int start, u64 period) +static struct callchain_node * +add_child(struct callchain_node *parent, + struct callchain_cursor *cursor, + u64 period) { struct callchain_node *new; new = create_child(parent, false); - fill_node(new, chain, start); + fill_node(new, cursor); 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; } /* @@ -250,9 +355,10 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain, * Then create another child to host the given callchain of new branch */ static void -split_add_child(struct callchain_node *parent, struct resolved_chain *chain, - struct callchain_list *to_split, int idx_parents, int idx_local, - u64 period) +split_add_child(struct callchain_node *parent, + struct callchain_cursor *cursor, + struct callchain_list *to_split, + u64 idx_parents, u64 idx_local, u64 period) { struct callchain_node *new; struct list_head *old_tail; @@ -272,193 +378,297 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain, /* split the hits */ new->hit = parent->hit; new->children_hit = parent->children_hit; - parent->children_hit = cumul_hits(new); + parent->children_hit = callchain_cumul_hits(new); new->val_nr = parent->val_nr - idx_local; parent->val_nr = idx_local; /* create a new child for the new branch if any */ - if (idx_total < chain->nr) { + 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, chain, idx_total, 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; } } static int -append_chain(struct callchain_node *root, struct resolved_chain *chain, - unsigned int start, u64 period); +append_chain(struct callchain_node *root, + struct callchain_cursor *cursor, + u64 period); static void -append_chain_children(struct callchain_node *root, struct resolved_chain *chain, - unsigned int start, u64 period) +append_chain_children(struct callchain_node *root, + struct callchain_cursor *cursor, + 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, chain, start, period); + while (*p) { + s64 ret; + + parent = *p; + rnode = rb_entry(parent, struct callchain_node, rb_node_in); - if (!ret) + /* If at least first entry matches, rely to children */ + ret = append_chain(rnode, cursor, period); + if (ret == 0) 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, chain, start, 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; } static int -append_chain(struct callchain_node *root, struct resolved_chain *chain, - unsigned int start, u64 period) +append_chain(struct callchain_node *root, + struct callchain_cursor *cursor, + u64 period) { struct callchain_list *cnode; - unsigned int i = start; + u64 start = cursor->pos; bool found = false; + u64 matches; + int cmp = 0; /* * 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 symbol *sym; + struct callchain_cursor_node *node; - if (i == chain->nr) + node = callchain_cursor_current(cursor); + if (!node) break; - sym = chain->ips[i].ms.sym; - - if (cnode->ms.sym && sym) { - if (cnode->ms.sym->start != sym->start) - break; - } else if (cnode->ip != chain->ips[i].ip) + cmp = match_chain(node, cnode); + if (cmp) break; - if (!found) - found = true; - i++; + found = true; + + callchain_cursor_advance(cursor); } - /* matches not, relay on the parent */ - if (!found) - return -1; + /* matches not, relay no the parent */ + if (!found) { + WARN_ONCE(!cmp, "Chain comparison error\n"); + return cmp; + } + + matches = cursor->pos - start; /* we match only a part of the node. Split it and add the new chain */ - if (i - start < root->val_nr) { - split_add_child(root, chain, cnode, start, i - start, period); + if (matches < root->val_nr) { + split_add_child(root, cursor, cnode, start, matches, period); return 0; } /* we match 100% of the path, increment the hit */ - if (i - start == root->val_nr && i == chain->nr) { + if (matches == root->val_nr && cursor->pos == cursor->nr) { root->hit += period; return 0; } /* We match the node and still have a part remaining */ - append_chain_children(root, chain, i, period); + append_chain_children(root, cursor, period); return 0; } -static void filter_context(struct ip_callchain *old, struct resolved_chain *new, - struct map_symbol *syms) -{ - int i, j = 0; - - for (i = 0; i < (int)old->nr; i++) { - if (old->ips[i] >= PERF_CONTEXT_MAX) - continue; - - new->ips[j].ip = old->ips[i]; - new->ips[j].ms = syms[i]; - j++; - } - - new->nr = j; -} - - -int callchain_append(struct callchain_root *root, struct ip_callchain *chain, - struct map_symbol *syms, u64 period) +int callchain_append(struct callchain_root *root, + struct callchain_cursor *cursor, + u64 period) { - struct resolved_chain *filtered; - - if (!chain->nr) + if (!cursor->nr) return 0; - filtered = zalloc(sizeof(*filtered) + - chain->nr * sizeof(struct resolved_ip)); - if (!filtered) - return -ENOMEM; - - filter_context(chain, filtered, syms); - - if (!filtered->nr) - goto end; + callchain_cursor_commit(cursor); - append_chain_children(&root->node, filtered, 0, period); + append_chain_children(&root->node, cursor, period); - if (filtered->nr > root->max_depth) - root->max_depth = filtered->nr; -end: - free(filtered); + if (cursor->nr > root->max_depth) + root->max_depth = cursor->nr; return 0; } static int -merge_chain_branch(struct callchain_node *dst, struct callchain_node *src, - struct resolved_chain *chain) +merge_chain_branch(struct callchain_cursor *cursor, + struct callchain_node *dst, struct callchain_node *src) { - struct callchain_node *child, *next_child; + struct callchain_cursor_node **old_last = cursor->last; + struct callchain_node *child; struct callchain_list *list, *next_list; - int old_pos = chain->nr; + struct rb_node *n; + int old_pos = cursor->nr; int err = 0; list_for_each_entry_safe(list, next_list, &src->val, list) { - chain->ips[chain->nr].ip = list->ip; - chain->ips[chain->nr].ms = list->ms; - chain->nr++; + callchain_cursor_append(cursor, list->ip, + list->ms.map, list->ms.sym); list_del(&list->list); free(list); } - if (src->hit) - append_chain_children(dst, chain, 0, src->hit); + if (src->hit) { + callchain_cursor_commit(cursor); + append_chain_children(dst, cursor, src->hit); + } + + 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); - chain_for_each_child_safe(child, next_child, src) { - err = merge_chain_branch(dst, child, chain); + err = merge_chain_branch(cursor, dst, child); if (err) break; - list_del(&child->brothers); free(child); } - chain->nr = old_pos; + cursor->nr = old_pos; + cursor->last = old_last; return err; } -int callchain_merge(struct callchain_root *dst, struct callchain_root *src) +int callchain_merge(struct callchain_cursor *cursor, + struct callchain_root *dst, struct callchain_root *src) { - struct resolved_chain *chain; - int err; + return merge_chain_branch(cursor, &dst->node, &src->node); +} - chain = malloc(sizeof(*chain) + - src->max_depth * sizeof(struct resolved_ip)); - if (!chain) - return -ENOMEM; +int callchain_cursor_append(struct callchain_cursor *cursor, + u64 ip, struct map *map, struct symbol *sym) +{ + struct callchain_cursor_node *node = *cursor->last; - chain->nr = 0; + if (!node) { + node = calloc(1, sizeof(*node)); + if (!node) + return -ENOMEM; - err = merge_chain_branch(&dst->node, &src->node, chain); + *cursor->last = node; + } - free(chain); + node->ip = ip; + node->map = map; + node->sym = sym; - return err; + cursor->nr++; + + cursor->last = &node->next; + + return 0; +} + +int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent, + struct perf_evsel *evsel, struct addr_location *al, + int max_stack) +{ + if (sample->callchain == NULL) + return 0; + + if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain || + sort__has_parent) { + return machine__resolve_callchain(al->machine, evsel, al->thread, + sample, parent, al, max_stack); + } + return 0; +} + +int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample) +{ + if (!symbol_conf.use_callchain) + return 0; + return callchain_append(he->callchain, &callchain_cursor, sample->period); +} + +int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, + bool hide_unresolved) +{ + al->map = node->map; + al->sym = node->sym; + if (node->map) + al->addr = node->map->map_ip(node->map, node->ip); + else + al->addr = node->ip; + + if (al->sym == NULL) { + if (hide_unresolved) + return 0; + if (al->map == NULL) + goto out; + } + + if (al->map->groups == &al->machine->kmaps) { + if (machine__is_host(al->machine)) { + al->cpumode = PERF_RECORD_MISC_KERNEL; + al->level = 'k'; + } else { + al->cpumode = PERF_RECORD_MISC_GUEST_KERNEL; + al->level = 'g'; + } + } else { + if (machine__is_host(al->machine)) { + al->cpumode = PERF_RECORD_MISC_USER; + al->level = '.'; + } else if (perf_guest) { + al->cpumode = PERF_RECORD_MISC_GUEST_USER; + al->level = 'u'; + } else { + al->cpumode = PERF_RECORD_MISC_HYPERVISOR; + al->level = 'H'; + } + } + +out: + return 1; } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index c15fb8c24ad..8f84423a75d 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -7,6 +7,13 @@ #include "event.h" #include "symbol.h" +enum perf_call_graph_mode { + CALLCHAIN_NONE, + CALLCHAIN_FP, + CALLCHAIN_DWARF, + CALLCHAIN_MAX +}; + enum chain_mode { CHAIN_NONE, CHAIN_FLAT, @@ -14,13 +21,18 @@ enum chain_mode { CHAIN_GRAPH_REL }; +enum chain_order { + ORDER_CALLER, + ORDER_CALLEE +}; + struct callchain_node { struct callchain_node *parent; - struct list_head brothers; - 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; @@ -36,11 +48,18 @@ 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 { @@ -49,27 +68,112 @@ struct callchain_list { struct list_head list; }; +/* + * A callchain cursor is a single linked list that + * let one feed a callchain progressively. + * It keeps persistent allocated entries to minimize + * allocations. + */ +struct callchain_cursor_node { + u64 ip; + struct map *map; + struct symbol *sym; + struct callchain_cursor_node *next; +}; + +struct callchain_cursor { + u64 nr; + struct callchain_cursor_node *first; + struct callchain_cursor_node **last; + u64 pos; + struct callchain_cursor_node *curr; +}; + +extern __thread struct callchain_cursor callchain_cursor; + static inline void callchain_init(struct callchain_root *root) { - INIT_LIST_HEAD(&root->node.brothers); - 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; } -static inline u64 cumul_hits(struct callchain_node *node) +static inline u64 callchain_cumul_hits(struct callchain_node *node) { return node->hit + node->children_hit; } -int register_callchain_param(struct callchain_param *param); -int callchain_append(struct callchain_root *root, struct ip_callchain *chain, - struct map_symbol *syms, u64 period); -int callchain_merge(struct callchain_root *dst, struct callchain_root *src); +int callchain_register_param(struct callchain_param *param); +int callchain_append(struct callchain_root *root, + struct callchain_cursor *cursor, + u64 period); + +int callchain_merge(struct callchain_cursor *cursor, + struct callchain_root *dst, struct callchain_root *src); + +/* + * Initialize a cursor before adding entries inside, but keep + * the previously allocated entries as a cache. + */ +static inline void callchain_cursor_reset(struct callchain_cursor *cursor) +{ + cursor->nr = 0; + cursor->last = &cursor->first; +} + +int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, + struct map *map, struct symbol *sym); -bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event); +/* Close a cursor writing session. Initialize for the reader */ +static inline void callchain_cursor_commit(struct callchain_cursor *cursor) +{ + cursor->curr = cursor->first; + cursor->pos = 0; +} + +/* Cursor reading iteration helpers */ +static inline struct callchain_cursor_node * +callchain_cursor_current(struct callchain_cursor *cursor) +{ + if (cursor->pos == cursor->nr) + return NULL; + + return cursor->curr; +} + +static inline void callchain_cursor_advance(struct callchain_cursor *cursor) +{ + cursor->curr = cursor->curr->next; + cursor->pos++; +} + +struct option; +struct hist_entry; + +int record_parse_callchain(const char *arg, struct record_opts *opts); +int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); +int record_callchain_opt(const struct option *opt, const char *arg, int unset); + +int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent, + struct perf_evsel *evsel, struct addr_location *al, + int max_stack); +int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample); +int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, + bool hide_unresolved); + +extern const char record_callchain_help[]; +int parse_callchain_report_opt(const char *arg); + +static inline void callchain_cursor_snapshot(struct callchain_cursor *dest, + struct callchain_cursor *src) +{ + *dest = *src; + + dest->first = src->curr; + dest->nr -= src->pos; +} #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c new file mode 100644 index 00000000000..88f7be39943 --- /dev/null +++ b/tools/perf/util/cgroup.c @@ -0,0 +1,177 @@ +#include "util.h" +#include "../perf.h" +#include "parse-options.h" +#include "evsel.h" +#include "cgroup.h" +#include "evlist.h" + +int nr_cgroups; + +static int +cgroupfs_find_mountpoint(char *buf, size_t maxlen) +{ + FILE *fp; + char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1]; + char *token, *saved_ptr = NULL; + int found = 0; + + fp = fopen("/proc/mounts", "r"); + if (!fp) + return -1; + + /* + * in order to handle split hierarchy, we need to scan /proc/mounts + * and inspect every cgroupfs mount point to find one that has + * perf_event subsystem + */ + while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %" + STR(PATH_MAX)"s %*d %*d\n", + mountpoint, type, tokens) == 3) { + + if (!strcmp(type, "cgroup")) { + + token = strtok_r(tokens, ",", &saved_ptr); + + while (token != NULL) { + if (!strcmp(token, "perf_event")) { + found = 1; + break; + } + token = strtok_r(NULL, ",", &saved_ptr); + } + } + if (found) + break; + } + fclose(fp); + if (!found) + return -1; + + if (strlen(mountpoint) < maxlen) { + strcpy(buf, mountpoint); + return 0; + } + return -1; +} + +static int open_cgroup(char *name) +{ + char path[PATH_MAX + 1]; + char mnt[PATH_MAX + 1]; + int fd; + + + if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1)) + return -1; + + snprintf(path, PATH_MAX, "%s/%s", mnt, name); + + fd = open(path, O_RDONLY); + if (fd == -1) + fprintf(stderr, "no access to cgroup %s\n", path); + + return fd; +} + +static int add_cgroup(struct perf_evlist *evlist, char *str) +{ + struct perf_evsel *counter; + struct cgroup_sel *cgrp = NULL; + int n; + /* + * check if cgrp is already defined, if so we reuse it + */ + evlist__for_each(evlist, counter) { + cgrp = counter->cgrp; + if (!cgrp) + continue; + if (!strcmp(cgrp->name, str)) + break; + + cgrp = NULL; + } + + if (!cgrp) { + cgrp = zalloc(sizeof(*cgrp)); + if (!cgrp) + return -1; + + cgrp->name = str; + + cgrp->fd = open_cgroup(str); + if (cgrp->fd == -1) { + free(cgrp); + return -1; + } + } + + /* + * find corresponding event + * if add cgroup N, then need to find event N + */ + n = 0; + evlist__for_each(evlist, counter) { + if (n == nr_cgroups) + goto found; + n++; + } + if (cgrp->refcnt == 0) + free(cgrp); + + return -1; +found: + cgrp->refcnt++; + counter->cgrp = cgrp; + return 0; +} + +void close_cgroup(struct cgroup_sel *cgrp) +{ + if (!cgrp) + return; + + /* XXX: not reentrant */ + if (--cgrp->refcnt == 0) { + close(cgrp->fd); + zfree(&cgrp->name); + free(cgrp); + } +} + +int parse_cgroups(const struct option *opt __maybe_unused, const char *str, + int unset __maybe_unused) +{ + struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; + const char *p, *e, *eos = str + strlen(str); + char *s; + int ret; + + if (list_empty(&evlist->entries)) { + fprintf(stderr, "must define events before cgroups\n"); + return -1; + } + + for (;;) { + p = strchr(str, ','); + e = p ? p : eos; + + /* allow empty cgroups, i.e., skip */ + if (e - str) { + /* termination added */ + s = strndup(str, e - str); + if (!s) + return -1; + ret = add_cgroup(evlist, s); + if (ret) { + free(s); + return -1; + } + } + /* nr_cgroups is increased een for empty cgroups */ + nr_cgroups++; + if (!p) + break; + str = p+1; + } + return 0; +} diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h new file mode 100644 index 00000000000..89acd6debdc --- /dev/null +++ b/tools/perf/util/cgroup.h @@ -0,0 +1,17 @@ +#ifndef __CGROUP_H__ +#define __CGROUP_H__ + +struct option; + +struct cgroup_sel { + char *name; + int fd; + int refcnt; +}; + + +extern int nr_cgroups; /* number of explicit cgroups defined */ +extern void close_cgroup(struct cgroup_sel *cgrp); +extern int parse_cgroups(const struct option *opt, const char *str, int unset); + +#endif /* __CGROUP_H__ */ diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index e191eb9a667..87b8672eb41 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -1,5 +1,7 @@ +#include <linux/kernel.h> #include "cache.h" #include "color.h" +#include <math.h> int perf_use_color_default = -1; @@ -182,12 +184,12 @@ static int __color_vsnprintf(char *bf, size_t size, const char *color, } if (perf_use_color_default && *color) - r += snprintf(bf, size, "%s", color); - r += vsnprintf(bf + r, size - r, fmt, args); + r += scnprintf(bf, size, "%s", color); + r += vscnprintf(bf + r, size - r, fmt, args); if (perf_use_color_default && *color) - r += snprintf(bf + r, size - r, "%s", PERF_COLOR_RESET); + r += scnprintf(bf + r, size - r, "%s", PERF_COLOR_RESET); if (trail) - r += snprintf(bf + r, size - r, "%s", trail); + r += scnprintf(bf + r, size - r, "%s", trail); return r; } @@ -200,7 +202,7 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, * Auto-detect: */ if (perf_use_color_default < 0) { - if (isatty(1) || pager_in_use()) + if (isatty(fileno(fp)) || pager_in_use()) perf_use_color_default = 1; else perf_use_color_default = 0; @@ -297,10 +299,10 @@ const char *get_percent_color(double percent) * entries in green - and keep the low overhead places * normal: */ - if (percent >= MIN_RED) + if (fabs(percent) >= MIN_RED) color = PERF_COLOR_RED; else { - if (percent > MIN_GREEN) + if (fabs(percent) > MIN_GREEN) color = PERF_COLOR_GREEN; } return color; @@ -317,8 +319,19 @@ 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 value_color_snprintf(char *bf, size_t size, const char *fmt, double value) +{ + const char *color = get_percent_color(value); + return color_snprintf(bf, size, color, fmt, value); +} + +int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...) { - const char *color = get_percent_color(percent); - return color_snprintf(bf, size, color, fmt, percent); + va_list args; + double percent; + + va_start(args, fmt); + percent = va_arg(args, double); + va_end(args); + return value_color_snprintf(bf, size, fmt, percent); } diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index dea082b7960..7ff30a62a13 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -39,7 +39,8 @@ 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 value_color_snprintf(char *bf, size_t size, const char *fmt, double value); +int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...); int percent_color_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 00000000000..f9e777629e2 --- /dev/null +++ b/tools/perf/util/comm.c @@ -0,0 +1,122 @@ +#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); + zfree(&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; +} + +int comm__override(struct comm *comm, const char *str, u64 timestamp) +{ + struct comm_str *new, *old = comm->comm_str; + + new = comm_str__findnew(str, &comm_str_root); + if (!new) + return -ENOMEM; + + comm_str__get(new); + comm_str__put(old); + comm->comm_str = new; + comm->start = timestamp; + + return 0; +} + +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 00000000000..fac5bd51bef --- /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); +int comm__override(struct comm *comm, const char *str, u64 timestamp); + +#endif /* __PERF_COMM_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index e02d78cae70..24519e14ac5 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -1,5 +1,8 @@ /* - * GIT - The information manager from hell + * config.c + * + * Helper functions for parsing config items. + * Originally copied from GIT source. * * Copyright (C) Linus Torvalds, 2005 * Copyright (C) Johannes Schindelin, 2005 @@ -8,6 +11,7 @@ #include "util.h" #include "cache.h" #include "exec_cmd.h" +#include "util/hist.h" /* perf_hist_config */ #define MAXNAME (256) @@ -117,7 +121,7 @@ static char *parse_value(void) static inline int iskeychar(int c) { - return isalnum(c) || c == '-'; + return isalnum(c) || c == '-' || c == '_'; } static int get_value(config_fn_t fn, void *data, char *name, unsigned int len) @@ -339,18 +343,23 @@ const char *perf_config_dirname(const char *name, const char *value) return value; } -static int perf_default_core_config(const char *var __used, const char *value __used) +static int perf_default_core_config(const char *var __maybe_unused, + const char *value __maybe_unused) { - /* Add other config variables here and to Documentation/config.txt. */ + /* Add other config variables here. */ return 0; } -int perf_default_config(const char *var, const char *value, void *dummy __used) +int perf_default_config(const char *var, const char *value, + void *dummy __maybe_unused) { if (!prefixcmp(var, "core.")) return perf_default_core_config(var, value); - /* Add other config variables here and to Documentation/config.txt. */ + if (!prefixcmp(var, "hist.")) + return perf_hist_config(var, value); + + /* Add other config variables here. */ return 0; } @@ -399,7 +408,6 @@ static int perf_config_global(void) int perf_config(config_fn_t fn, void *data) { int ret = 0, found = 0; - char *repo_config = NULL; const char *home = NULL; /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */ @@ -414,19 +422,32 @@ int perf_config(config_fn_t fn, void *data) home = getenv("HOME"); if (perf_config_global() && home) { char *user_config = strdup(mkpath("%s/.perfconfig", home)); - if (!access(user_config, R_OK)) { - ret += perf_config_from_file(fn, user_config, data); - found += 1; + struct stat st; + + if (user_config == NULL) { + warning("Not enough memory to process %s/.perfconfig, " + "ignoring it.", home); + goto out; } - free(user_config); - } - repo_config = perf_pathdup("config"); - if (!access(repo_config, R_OK)) { - ret += perf_config_from_file(fn, repo_config, data); + if (stat(user_config, &st) < 0) + goto out_free; + + if (st.st_uid && (st.st_uid != geteuid())) { + warning("File %s not owned by current user or root, " + "ignoring it.", user_config); + goto out_free; + } + + if (!st.st_size) + goto out_free; + + ret += perf_config_from_file(fn, user_config, data); found += 1; +out_free: + free(user_config); } - free(repo_config); +out: if (found == 0) return -1; return ret; diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 0f9b8d7a7d7..c4e55b71010 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -1,49 +1,83 @@ #include "util.h" +#include <api/fs/fs.h> #include "../perf.h" #include "cpumap.h" #include <assert.h> #include <stdio.h> +#include <stdlib.h> -int cpumap[MAX_NR_CPUS]; - -static int default_cpu_map(void) +static struct cpu_map *cpu_map__default_new(void) { - int nr_cpus, i; + struct cpu_map *cpus; + int nr_cpus; nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); - assert(nr_cpus <= MAX_NR_CPUS); - assert((int)nr_cpus >= 0); + if (nr_cpus < 0) + return NULL; + + cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int)); + if (cpus != NULL) { + int i; + for (i = 0; i < nr_cpus; ++i) + cpus->map[i] = i; - for (i = 0; i < nr_cpus; ++i) - cpumap[i] = i; + cpus->nr = nr_cpus; + } - return nr_cpus; + return cpus; } -static int read_all_cpu_map(void) +static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) { - FILE *onlnf; + size_t payload_size = nr_cpus * sizeof(int); + struct cpu_map *cpus = malloc(sizeof(*cpus) + payload_size); + + if (cpus != NULL) { + cpus->nr = nr_cpus; + memcpy(cpus->map, tmp_cpus, payload_size); + } + + return cpus; +} + +struct cpu_map *cpu_map__read(FILE *file) +{ + struct cpu_map *cpus = NULL; int nr_cpus = 0; + int *tmp_cpus = NULL, *tmp; + int max_entries = 0; int n, cpu, prev; char sep; - onlnf = fopen("/sys/devices/system/cpu/online", "r"); - if (!onlnf) - return default_cpu_map(); - sep = 0; prev = -1; for (;;) { - n = fscanf(onlnf, "%u%c", &cpu, &sep); + n = fscanf(file, "%u%c", &cpu, &sep); if (n <= 0) break; if (prev >= 0) { - assert(nr_cpus + cpu - prev - 1 < MAX_NR_CPUS); + int new_max = nr_cpus + cpu - prev - 1; + + if (new_max >= max_entries) { + max_entries = new_max + MAX_NR_CPUS / 2; + tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + if (tmp == NULL) + goto out_free_tmp; + tmp_cpus = tmp; + } + while (++prev < cpu) - cpumap[nr_cpus++] = prev; + tmp_cpus[nr_cpus++] = prev; } - assert (nr_cpus < MAX_NR_CPUS); - cpumap[nr_cpus++] = cpu; + if (nr_cpus == max_entries) { + max_entries += MAX_NR_CPUS; + tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + if (tmp == NULL) + goto out_free_tmp; + tmp_cpus = tmp; + } + + tmp_cpus[nr_cpus++] = cpu; if (n == 2 && sep == '-') prev = cpu; else @@ -51,24 +85,44 @@ static int read_all_cpu_map(void) if (n == 1 || sep == '\n') break; } - fclose(onlnf); + if (nr_cpus > 0) - return nr_cpus; + cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); + else + cpus = cpu_map__default_new(); +out_free_tmp: + free(tmp_cpus); + return cpus; +} + +static struct cpu_map *cpu_map__read_all_cpu_map(void) +{ + struct cpu_map *cpus = NULL; + FILE *onlnf; + + onlnf = fopen("/sys/devices/system/cpu/online", "r"); + if (!onlnf) + return cpu_map__default_new(); - return default_cpu_map(); + cpus = cpu_map__read(onlnf); + fclose(onlnf); + return cpus; } -int read_cpu_map(const char *cpu_list) +struct cpu_map *cpu_map__new(const char *cpu_list) { + struct cpu_map *cpus = NULL; unsigned long start_cpu, end_cpu = 0; char *p = NULL; int i, nr_cpus = 0; + int *tmp_cpus = NULL, *tmp; + int max_entries = 0; if (!cpu_list) - return read_all_cpu_map(); + return cpu_map__read_all_cpu_map(); if (!isdigit(*cpu_list)) - goto invalid; + goto out; while (isdigit(*cpu_list)) { p = NULL; @@ -94,21 +148,332 @@ int read_cpu_map(const char *cpu_list) for (; start_cpu <= end_cpu; start_cpu++) { /* check for duplicates */ for (i = 0; i < nr_cpus; i++) - if (cpumap[i] == (int)start_cpu) + if (tmp_cpus[i] == (int)start_cpu) goto invalid; - assert(nr_cpus < MAX_NR_CPUS); - cpumap[nr_cpus++] = (int)start_cpu; + if (nr_cpus == max_entries) { + max_entries += MAX_NR_CPUS; + tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + if (tmp == NULL) + goto invalid; + tmp_cpus = tmp; + } + tmp_cpus[nr_cpus++] = (int)start_cpu; } if (*p) ++p; cpu_list = p; } - if (nr_cpus > 0) - return nr_cpus; - return default_cpu_map(); + if (nr_cpus > 0) + cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); + else + cpus = cpu_map__default_new(); invalid: - return -1; + free(tmp_cpus); +out: + return cpus; +} + +size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp) +{ + int i; + size_t printed = fprintf(fp, "%d cpu%s: ", + map->nr, map->nr > 1 ? "s" : ""); + for (i = 0; i < map->nr; ++i) + printed += fprintf(fp, "%s%d", i ? ", " : "", map->map[i]); + + return printed + fprintf(fp, "\n"); +} + +struct cpu_map *cpu_map__dummy_new(void) +{ + struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int)); + + if (cpus != NULL) { + cpus->nr = 1; + cpus->map[0] = -1; + } + + return cpus; +} + +void cpu_map__delete(struct cpu_map *map) +{ + free(map); +} + +int cpu_map__get_socket(struct cpu_map *map, int idx) +{ + FILE *fp; + const char *mnt; + char path[PATH_MAX]; + int cpu, ret; + + if (idx > map->nr) + return -1; + + cpu = map->map[idx]; + + mnt = sysfs__mountpoint(); + if (!mnt) + return -1; + + snprintf(path, PATH_MAX, + "%s/devices/system/cpu/cpu%d/topology/physical_package_id", + mnt, cpu); + + fp = fopen(path, "r"); + if (!fp) + return -1; + ret = fscanf(fp, "%d", &cpu); + fclose(fp); + return ret == 1 ? cpu : -1; +} + +static int cmp_ids(const void *a, const void *b) +{ + return *(int *)a - *(int *)b; +} + +static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, + int (*f)(struct cpu_map *map, int cpu)) +{ + struct cpu_map *c; + int nr = cpus->nr; + int cpu, s1, s2; + + /* allocate as much as possible */ + c = calloc(1, sizeof(*c) + nr * sizeof(int)); + if (!c) + return -1; + + for (cpu = 0; cpu < nr; cpu++) { + s1 = f(cpus, cpu); + for (s2 = 0; s2 < c->nr; s2++) { + if (s1 == c->map[s2]) + break; + } + if (s2 == c->nr) { + c->map[c->nr] = s1; + c->nr++; + } + } + /* ensure we process id in increasing order */ + qsort(c->map, c->nr, sizeof(int), cmp_ids); + + *res = c; + return 0; +} + +int cpu_map__get_core(struct cpu_map *map, int idx) +{ + FILE *fp; + const char *mnt; + char path[PATH_MAX]; + int cpu, ret, s; + + if (idx > map->nr) + return -1; + + cpu = map->map[idx]; + + mnt = sysfs__mountpoint(); + if (!mnt) + return -1; + + snprintf(path, PATH_MAX, + "%s/devices/system/cpu/cpu%d/topology/core_id", + mnt, cpu); + + fp = fopen(path, "r"); + if (!fp) + return -1; + ret = fscanf(fp, "%d", &cpu); + fclose(fp); + if (ret != 1) + return -1; + + s = cpu_map__get_socket(map, idx); + if (s == -1) + return -1; + + /* + * encode socket in upper 16 bits + * core_id is relative to socket, and + * we need a global id. So we combine + * socket+ core id + */ + return (s << 16) | (cpu & 0xffff); +} + +int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp) +{ + return cpu_map__build_map(cpus, sockp, cpu_map__get_socket); +} + +int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep) +{ + return cpu_map__build_map(cpus, corep, cpu_map__get_core); +} + +/* setup simple routines to easily access node numbers given a cpu number */ +static int get_max_num(char *path, int *max) +{ + size_t num; + char *buf; + int err = 0; + + if (filename__read_str(path, &buf, &num)) + return -1; + + buf[num] = '\0'; + + /* start on the right, to find highest node num */ + while (--num) { + if ((buf[num] == ',') || (buf[num] == '-')) { + num++; + break; + } + } + if (sscanf(&buf[num], "%d", max) < 1) { + err = -1; + goto out; + } + + /* convert from 0-based to 1-based */ + (*max)++; + +out: + free(buf); + return err; +} + +/* Determine highest possible cpu in the system for sparse allocation */ +static void set_max_cpu_num(void) +{ + const char *mnt; + char path[PATH_MAX]; + int ret = -1; + + /* set up default */ + max_cpu_num = 4096; + + mnt = sysfs__mountpoint(); + if (!mnt) + goto out; + + /* get the highest possible cpu number for a sparse allocation */ + ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt); + if (ret == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + goto out; + } + + ret = get_max_num(path, &max_cpu_num); + +out: + if (ret) + pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num); +} + +/* Determine highest possible node in the system for sparse allocation */ +static void set_max_node_num(void) +{ + const char *mnt; + char path[PATH_MAX]; + int ret = -1; + + /* set up default */ + max_node_num = 8; + + mnt = sysfs__mountpoint(); + if (!mnt) + goto out; + + /* get the highest possible cpu number for a sparse allocation */ + ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt); + if (ret == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + goto out; + } + + ret = get_max_num(path, &max_node_num); + +out: + if (ret) + pr_err("Failed to read max nodes, using default of %d\n", max_node_num); +} + +static int init_cpunode_map(void) +{ + int i; + + set_max_cpu_num(); + set_max_node_num(); + + cpunode_map = calloc(max_cpu_num, sizeof(int)); + if (!cpunode_map) { + pr_err("%s: calloc failed\n", __func__); + return -1; + } + + for (i = 0; i < max_cpu_num; i++) + cpunode_map[i] = -1; + + return 0; +} + +int cpu__setup_cpunode_map(void) +{ + struct dirent *dent1, *dent2; + DIR *dir1, *dir2; + unsigned int cpu, mem; + char buf[PATH_MAX]; + char path[PATH_MAX]; + const char *mnt; + int n; + + /* initialize globals */ + if (init_cpunode_map()) + return -1; + + mnt = sysfs__mountpoint(); + if (!mnt) + return 0; + + n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt); + if (n == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + return -1; + } + + dir1 = opendir(path); + if (!dir1) + return 0; + + /* walk tree and setup map */ + while ((dent1 = readdir(dir1)) != NULL) { + if (dent1->d_type != DT_DIR || sscanf(dent1->d_name, "node%u", &mem) < 1) + continue; + + n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name); + if (n == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + continue; + } + + dir2 = opendir(buf); + if (!dir2) + continue; + while ((dent2 = readdir(dir2)) != NULL) { + if (dent2->d_type != DT_LNK || sscanf(dent2->d_name, "cpu%u", &cpu) < 1) + continue; + cpunode_map[cpu] = mem; + } + closedir(dir2); + } + closedir(dir1); + return 0; } diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 3e60f56e490..61a65484900 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -1,7 +1,84 @@ #ifndef __PERF_CPUMAP_H #define __PERF_CPUMAP_H -extern int read_cpu_map(const char *cpu_list); -extern int cpumap[]; +#include <stdio.h> +#include <stdbool.h> + +#include "perf.h" +#include "util/debug.h" + +struct cpu_map { + int nr; + int map[]; +}; + +struct cpu_map *cpu_map__new(const char *cpu_list); +struct cpu_map *cpu_map__dummy_new(void); +void cpu_map__delete(struct cpu_map *map); +struct cpu_map *cpu_map__read(FILE *file); +size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); +int cpu_map__get_socket(struct cpu_map *map, int idx); +int cpu_map__get_core(struct cpu_map *map, int idx); +int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp); +int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep); + +static inline int cpu_map__socket(struct cpu_map *sock, int s) +{ + if (!sock || s > sock->nr || s < 0) + return 0; + return sock->map[s]; +} + +static inline int cpu_map__id_to_socket(int id) +{ + return id >> 16; +} + +static inline int cpu_map__id_to_cpu(int id) +{ + return id & 0xffff; +} + +static inline int cpu_map__nr(const struct cpu_map *map) +{ + return map ? map->nr : 1; +} + +static inline bool cpu_map__empty(const struct cpu_map *map) +{ + return map ? map->map[0] == -1 : true; +} + +int max_cpu_num; +int max_node_num; +int *cpunode_map; + +int cpu__setup_cpunode_map(void); + +static inline int cpu__max_node(void) +{ + if (unlikely(!max_node_num)) + pr_debug("cpu_map not initialized\n"); + + return max_node_num; +} + +static inline int cpu__max_cpu(void) +{ + if (unlikely(!max_cpu_num)) + pr_debug("cpu_map not initialized\n"); + + return max_cpu_num; +} + +static inline int cpu__get_node(int cpu) +{ + if (unlikely(cpunode_map == NULL)) { + pr_debug("cpu_map not initialized\n"); + return -1; + } + + return cpunode_map[cpu]; +} #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c index 35073621e5d..aada3ac5e89 100644 --- a/tools/perf/util/ctype.c +++ b/tools/perf/util/ctype.c @@ -3,7 +3,7 @@ * * No surprises, and works with signed and unsigned chars. */ -#include "cache.h" +#include "util.h" enum { S = GIT_SPACE, diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c new file mode 100644 index 00000000000..55de44ecebe --- /dev/null +++ b/tools/perf/util/data.c @@ -0,0 +1,133 @@ +#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) +{ + int fd; + + if (check_backup(file)) + return -1; + + fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); + + if (fd < 0) + pr_err("failed to open %s : %s\n", file->path, strerror(errno)); + + return fd; +} + +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); +} + +ssize_t perf_data_file__write(struct perf_data_file *file, + void *buf, size_t size) +{ + return writen(file->fd, buf, size); +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h new file mode 100644 index 00000000000..2b15d0c95c7 --- /dev/null +++ b/tools/perf/util/data.h @@ -0,0 +1,50 @@ +#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); +ssize_t perf_data_file__write(struct perf_data_file *file, + void *buf, size_t size); + +#endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index c8d81b00089..299b5558650 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -11,57 +11,66 @@ #include "event.h" #include "debug.h" #include "util.h" +#include "target.h" int verbose; bool dump_trace = false, quiet = false; -int eprintf(int level, const char *fmt, ...) +static int _eprintf(int level, const char *fmt, va_list args) { - va_list args; int ret = 0; if (verbose >= level) { - va_start(args, fmt); - if (use_browser > 0) - ret = ui_helpline__show_help(fmt, args); + if (use_browser >= 1) + ui_helpline__vshow(fmt, args); else ret = vfprintf(stderr, fmt, args); - va_end(args); } return ret; } -int dump_printf(const char *fmt, ...) +int eprintf(int level, const char *fmt, ...) { va_list args; - int ret = 0; + int ret; - if (dump_trace) { - va_start(args, fmt); - ret = vprintf(fmt, args); - va_end(args); - } + va_start(args, fmt); + ret = _eprintf(level, fmt, args); + va_end(args); return ret; } -static int dump_printf_color(const char *fmt, const char *color, ...) +/* + * Overloading libtraceevent standard info print + * function, display with -v in perf. + */ +void pr_stat(const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + _eprintf(1, fmt, args); + va_end(args); + eprintf(1, "\n"); +} + +int dump_printf(const char *fmt, ...) { va_list args; int ret = 0; if (dump_trace) { - va_start(args, color); - ret = color_vfprintf(stdout, color, fmt, args); + va_start(args, fmt); + ret = vprintf(fmt, args); va_end(args); } return ret; } - -void trace_event(event_t *event) +void trace_event(union perf_event *event) { unsigned char *raw_event = (void *)event; const char *color = PERF_COLOR_BLUE; @@ -70,29 +79,29 @@ void trace_event(event_t *event) if (!dump_trace) return; - dump_printf("."); - dump_printf_color("\n. ... raw event: size %d bytes\n", color, - event->header.size); + printf("."); + color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n", + event->header.size); for (i = 0; i < event->header.size; i++) { if ((i & 15) == 0) { - dump_printf("."); - dump_printf_color(" %04x: ", color, i); + printf("."); + color_fprintf(stdout, color, " %04x: ", i); } - dump_printf_color(" %02x", color, raw_event[i]); + color_fprintf(stdout, color, " %02x", raw_event[i]); if (((i & 15) == 15) || i == event->header.size-1) { - dump_printf_color(" ", color); + color_fprintf(stdout, color, " "); for (j = 0; j < 15-(i & 15); j++) - dump_printf_color(" ", color); + color_fprintf(stdout, color, " "); for (j = i & ~15; j <= i; j++) { - dump_printf_color("%c", color, - isprint(raw_event[j]) ? - raw_event[j] : '.'); + color_fprintf(stdout, color, "%c", + isprint(raw_event[j]) ? + raw_event[j] : '.'); } - dump_printf_color("\n", color); + color_fprintf(stdout, color, "\n"); } } - dump_printf(".\n"); + printf(".\n"); } diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 7b514082bba..443694c36b0 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -4,35 +4,19 @@ #include <stdbool.h> #include "event.h" +#include "../ui/helpline.h" +#include "../ui/progress.h" +#include "../ui/util.h" extern int verbose; extern bool quiet, dump_trace; int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); -void trace_event(event_t *event); +void trace_event(union perf_event *event); -struct ui_progress; +int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); +int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); -#ifdef NO_NEWT_SUPPORT -static inline int ui_helpline__show_help(const char *format __used, va_list ap __used) -{ - return 0; -} - -static inline struct ui_progress *ui_progress__new(const char *title __used, - u64 total __used) -{ - return (struct ui_progress *)1; -} - -static inline void ui_progress__update(struct ui_progress *self __used, - u64 curr __used) {} - -static inline void ui_progress__delete(struct ui_progress *self __used) {} -#else -extern char ui_helpline__last_msg[]; -int ui_helpline__show_help(const char *format, va_list ap); -#include "ui/progress.h" -#endif +void pr_stat(const char *fmt, ...); #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/debugfs.c b/tools/perf/util/debugfs.c deleted file mode 100644 index a88fefc0cc0..00000000000 --- a/tools/perf/util/debugfs.c +++ /dev/null @@ -1,240 +0,0 @@ -#include "util.h" -#include "debugfs.h" -#include "cache.h" - -static int debugfs_premounted; -static char debugfs_mountpoint[MAX_PATH+1]; - -static const char *debugfs_known_mountpoints[] = { - "/sys/kernel/debug/", - "/debug/", - 0, -}; - -/* use this to force a umount */ -void debugfs_force_cleanup(void) -{ - debugfs_find_mountpoint(); - debugfs_premounted = 0; - debugfs_umount(); -} - -/* construct a full path to a debugfs element */ -int debugfs_make_path(const char *element, char *buffer, int size) -{ - int len; - - if (strlen(debugfs_mountpoint) == 0) { - buffer[0] = '\0'; - return -1; - } - - len = strlen(debugfs_mountpoint) + strlen(element) + 1; - if (len >= size) - return len+1; - - snprintf(buffer, size-1, "%s/%s", debugfs_mountpoint, element); - return 0; -} - -static int debugfs_found; - -/* find the path to the mounted debugfs */ -const char *debugfs_find_mountpoint(void) -{ - const char **ptr; - char type[100]; - FILE *fp; - - if (debugfs_found) - return (const char *) debugfs_mountpoint; - - ptr = debugfs_known_mountpoints; - while (*ptr) { - if (debugfs_valid_mountpoint(*ptr) == 0) { - debugfs_found = 1; - strcpy(debugfs_mountpoint, *ptr); - return debugfs_mountpoint; - } - ptr++; - } - - /* give up and parse /proc/mounts */ - fp = fopen("/proc/mounts", "r"); - if (fp == NULL) - die("Can't open /proc/mounts for read"); - - while (fscanf(fp, "%*s %" - STR(MAX_PATH) - "s %99s %*s %*d %*d\n", - debugfs_mountpoint, type) == 2) { - if (strcmp(type, "debugfs") == 0) - break; - } - fclose(fp); - - if (strcmp(type, "debugfs") != 0) - return NULL; - - debugfs_found = 1; - - return debugfs_mountpoint; -} - -/* verify that a mountpoint is actually a debugfs instance */ - -int debugfs_valid_mountpoint(const char *debugfs) -{ - struct statfs st_fs; - - if (statfs(debugfs, &st_fs) < 0) - return -ENOENT; - else if (st_fs.f_type != (long) DEBUGFS_MAGIC) - return -ENOENT; - - return 0; -} - - -int debugfs_valid_entry(const char *path) -{ - struct stat st; - - if (stat(path, &st)) - return -errno; - - return 0; -} - -/* mount the debugfs somewhere if it's not mounted */ - -char *debugfs_mount(const char *mountpoint) -{ - /* see if it's already mounted */ - if (debugfs_find_mountpoint()) { - debugfs_premounted = 1; - return debugfs_mountpoint; - } - - /* if not mounted and no argument */ - if (mountpoint == NULL) { - /* see if environment variable set */ - mountpoint = getenv(PERF_DEBUGFS_ENVIRONMENT); - /* if no environment variable, use default */ - if (mountpoint == NULL) - mountpoint = "/sys/kernel/debug"; - } - - if (mount(NULL, mountpoint, "debugfs", 0, NULL) < 0) - return NULL; - - /* save the mountpoint */ - strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint)); - debugfs_found = 1; - - return debugfs_mountpoint; -} - -/* umount the debugfs */ - -int debugfs_umount(void) -{ - char umountcmd[128]; - int ret; - - /* if it was already mounted, leave it */ - if (debugfs_premounted) - return 0; - - /* make sure it's a valid mount point */ - ret = debugfs_valid_mountpoint(debugfs_mountpoint); - if (ret) - return ret; - - snprintf(umountcmd, sizeof(umountcmd), - "/bin/umount %s", debugfs_mountpoint); - return system(umountcmd); -} - -int debugfs_write(const char *entry, const char *value) -{ - char path[MAX_PATH+1]; - int ret, count; - int fd; - - /* construct the path */ - snprintf(path, sizeof(path), "%s/%s", debugfs_mountpoint, entry); - - /* verify that it exists */ - ret = debugfs_valid_entry(path); - if (ret) - return ret; - - /* get how many chars we're going to write */ - count = strlen(value); - - /* open the debugfs entry */ - fd = open(path, O_RDWR); - if (fd < 0) - return -errno; - - while (count > 0) { - /* write it */ - ret = write(fd, value, count); - if (ret <= 0) { - if (ret == EAGAIN) - continue; - close(fd); - return -errno; - } - count -= ret; - } - - /* close it */ - close(fd); - - /* return success */ - return 0; -} - -/* - * read a debugfs entry - * returns the number of chars read or a negative errno - */ -int debugfs_read(const char *entry, char *buffer, size_t size) -{ - char path[MAX_PATH+1]; - int ret; - int fd; - - /* construct the path */ - snprintf(path, sizeof(path), "%s/%s", debugfs_mountpoint, entry); - - /* verify that it exists */ - ret = debugfs_valid_entry(path); - if (ret) - return ret; - - /* open the debugfs entry */ - fd = open(path, O_RDONLY); - if (fd < 0) - return -errno; - - do { - /* read it */ - ret = read(fd, buffer, size); - if (ret == 0) { - close(fd); - return EOF; - } - } while (ret < 0 && errno == EAGAIN); - - /* close it */ - close(fd); - - /* make *sure* there's a null character at the end */ - buffer[ret] = '\0'; - - /* return the number of chars read */ - return ret; -} diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h deleted file mode 100644 index 83a02879745..00000000000 --- a/tools/perf/util/debugfs.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef __DEBUGFS_H__ -#define __DEBUGFS_H__ - -#include <sys/mount.h> - -#ifndef MAX_PATH -# define MAX_PATH 256 -#endif - -#ifndef STR -# define _STR(x) #x -# define STR(x) _STR(x) -#endif - -extern const char *debugfs_find_mountpoint(void); -extern int debugfs_valid_mountpoint(const char *debugfs); -extern int debugfs_valid_entry(const char *path); -extern char *debugfs_mount(const char *mountpoint); -extern int debugfs_umount(void); -extern int debugfs_write(const char *entry, const char *value); -extern int debugfs_read(const char *entry, char *buffer, size_t size); -extern void debugfs_force_cleanup(void); -extern int debugfs_make_path(const char *element, char *buffer, int size); - -#endif /* __DEBUGFS_H__ */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c new file mode 100644 index 00000000000..819f10414f0 --- /dev/null +++ b/tools/perf/util/dso.c @@ -0,0 +1,900 @@ +#include <asm/bug.h> +#include <sys/time.h> +#include <sys/resource.h> +#include "symbol.h" +#include "dso.h" +#include "machine.h" +#include "util.h" +#include "debug.h" + +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__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) + return '!'; + return origin[dso->symtab_type]; +} + +int dso__read_binary_type_filename(const struct dso *dso, + enum dso_binary_type type, + char *root_dir, char *filename, size_t size) +{ + char build_id_hex[BUILD_ID_SIZE * 2 + 1]; + int ret = 0; + + switch (type) { + case DSO_BINARY_TYPE__DEBUGLINK: { + char *debuglink; + + strncpy(filename, dso->long_name, size); + debuglink = filename + dso->long_name_len; + while (debuglink != filename && *debuglink != '/') + debuglink--; + if (*debuglink == '/') + debuglink++; + ret = filename__read_debuglink(dso->long_name, debuglink, + size - (debuglink - filename)); + } + break; + case DSO_BINARY_TYPE__BUILD_ID_CACHE: + /* skip the locally configured cache if a symfs is given */ + if (symbol_conf.symfs[0] || + (dso__build_id_filename(dso, filename, size) == NULL)) + ret = -1; + break; + + case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: + snprintf(filename, size, "%s/usr/lib/debug%s.debug", + symbol_conf.symfs, dso->long_name); + break; + + case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: + snprintf(filename, size, "%s/usr/lib/debug%s", + symbol_conf.symfs, dso->long_name); + break; + + case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + { + const char *last_slash; + size_t len; + size_t dir_size; + + last_slash = dso->long_name + dso->long_name_len; + while (last_slash != dso->long_name && *last_slash != '/') + last_slash--; + + len = scnprintf(filename, size, "%s", symbol_conf.symfs); + dir_size = last_slash - dso->long_name + 2; + if (dir_size > (size - len)) { + ret = -1; + break; + } + len += scnprintf(filename + len, dir_size, "%s", dso->long_name); + len += scnprintf(filename + len , size - len, ".debug%s", + last_slash); + break; + } + + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + if (!dso->has_build_id) { + ret = -1; + break; + } + + build_id__sprintf(dso->build_id, + sizeof(dso->build_id), + build_id_hex); + snprintf(filename, size, + "%s/usr/lib/debug/.build-id/%.2s/%s.debug", + symbol_conf.symfs, build_id_hex, build_id_hex + 2); + break; + + case DSO_BINARY_TYPE__VMLINUX: + case DSO_BINARY_TYPE__GUEST_VMLINUX: + case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + snprintf(filename, size, "%s%s", + symbol_conf.symfs, dso->long_name); + break; + + case DSO_BINARY_TYPE__GUEST_KMODULE: + snprintf(filename, size, "%s%s%s", symbol_conf.symfs, + root_dir, dso->long_name); + break; + + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + snprintf(filename, size, "%s%s", symbol_conf.symfs, + dso->long_name); + break; + + case DSO_BINARY_TYPE__KCORE: + case DSO_BINARY_TYPE__GUEST_KCORE: + snprintf(filename, size, "%s", dso->long_name); + break; + + default: + case DSO_BINARY_TYPE__KALLSYMS: + case DSO_BINARY_TYPE__GUEST_KALLSYMS: + case DSO_BINARY_TYPE__JAVA_JIT: + case DSO_BINARY_TYPE__NOT_FOUND: + ret = -1; + break; + } + + return ret; +} + +/* + * Global list of open DSOs and the counter. + */ +static LIST_HEAD(dso__data_open); +static long dso__data_open_cnt; + +static void dso__list_add(struct dso *dso) +{ + list_add_tail(&dso->data.open_entry, &dso__data_open); + dso__data_open_cnt++; +} + +static void dso__list_del(struct dso *dso) +{ + list_del(&dso->data.open_entry); + WARN_ONCE(dso__data_open_cnt <= 0, + "DSO data fd counter out of bounds."); + dso__data_open_cnt--; +} + +static void close_first_dso(void); + +static int do_open(char *name) +{ + int fd; + + do { + fd = open(name, O_RDONLY); + if (fd >= 0) + return fd; + + pr_debug("dso open failed, mmap: %s\n", strerror(errno)); + if (!dso__data_open_cnt || errno != EMFILE) + break; + + close_first_dso(); + } while (1); + + return -1; +} + +static int __open_dso(struct dso *dso, struct machine *machine) +{ + int fd; + char *root_dir = (char *)""; + char *name = malloc(PATH_MAX); + + if (!name) + return -ENOMEM; + + if (machine) + root_dir = machine->root_dir; + + if (dso__read_binary_type_filename(dso, dso->binary_type, + root_dir, name, PATH_MAX)) { + free(name); + return -EINVAL; + } + + fd = do_open(name); + free(name); + return fd; +} + +static void check_data_close(void); + +/** + * dso_close - Open DSO data file + * @dso: dso object + * + * Open @dso's data file descriptor and updates + * list/count of open DSO objects. + */ +static int open_dso(struct dso *dso, struct machine *machine) +{ + int fd = __open_dso(dso, machine); + + if (fd > 0) { + dso__list_add(dso); + /* + * Check if we crossed the allowed number + * of opened DSOs and close one if needed. + */ + check_data_close(); + } + + return fd; +} + +static void close_data_fd(struct dso *dso) +{ + if (dso->data.fd >= 0) { + close(dso->data.fd); + dso->data.fd = -1; + dso->data.file_size = 0; + dso__list_del(dso); + } +} + +/** + * dso_close - Close DSO data file + * @dso: dso object + * + * Close @dso's data file descriptor and updates + * list/count of open DSO objects. + */ +static void close_dso(struct dso *dso) +{ + close_data_fd(dso); +} + +static void close_first_dso(void) +{ + struct dso *dso; + + dso = list_first_entry(&dso__data_open, struct dso, data.open_entry); + close_dso(dso); +} + +static rlim_t get_fd_limit(void) +{ + struct rlimit l; + rlim_t limit = 0; + + /* Allow half of the current open fd limit. */ + if (getrlimit(RLIMIT_NOFILE, &l) == 0) { + if (l.rlim_cur == RLIM_INFINITY) + limit = l.rlim_cur; + else + limit = l.rlim_cur / 2; + } else { + pr_err("failed to get fd limit\n"); + limit = 1; + } + + return limit; +} + +static bool may_cache_fd(void) +{ + static rlim_t limit; + + if (!limit) + limit = get_fd_limit(); + + if (limit == RLIM_INFINITY) + return true; + + return limit > (rlim_t) dso__data_open_cnt; +} + +/* + * Check and close LRU dso if we crossed allowed limit + * for opened dso file descriptors. The limit is half + * of the RLIMIT_NOFILE files opened. +*/ +static void check_data_close(void) +{ + bool cache_fd = may_cache_fd(); + + if (!cache_fd) + close_first_dso(); +} + +/** + * dso__data_close - Close DSO data file + * @dso: dso object + * + * External interface to close @dso's data file descriptor. + */ +void dso__data_close(struct dso *dso) +{ + close_dso(dso); +} + +/** + * dso__data_fd - Get dso's data file descriptor + * @dso: dso object + * @machine: machine object + * + * External interface to find dso's file, open it and + * returns file descriptor. + */ +int dso__data_fd(struct dso *dso, struct machine *machine) +{ + enum dso_binary_type binary_type_data[] = { + DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__SYSTEM_PATH_DSO, + DSO_BINARY_TYPE__NOT_FOUND, + }; + int i = 0; + + if (dso->data.fd >= 0) + return dso->data.fd; + + if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) { + dso->data.fd = open_dso(dso, machine); + return dso->data.fd; + } + + do { + int fd; + + dso->binary_type = binary_type_data[i++]; + + fd = open_dso(dso, machine); + if (fd >= 0) + return dso->data.fd = fd; + + } while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND); + + return -EINVAL; +} + +static void +dso_cache__free(struct rb_root *root) +{ + struct rb_node *next = rb_first(root); + + while (next) { + struct dso_cache *cache; + + cache = rb_entry(next, struct dso_cache, rb_node); + next = rb_next(&cache->rb_node); + rb_erase(&cache->rb_node, root); + free(cache); + } +} + +static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset) +{ + struct rb_node * const *p = &root->rb_node; + const struct rb_node *parent = NULL; + struct dso_cache *cache; + + while (*p != NULL) { + u64 end; + + parent = *p; + cache = rb_entry(parent, struct dso_cache, rb_node); + end = cache->offset + DSO__DATA_CACHE_SIZE; + + if (offset < cache->offset) + p = &(*p)->rb_left; + else if (offset >= end) + p = &(*p)->rb_right; + else + return cache; + } + return NULL; +} + +static void +dso_cache__insert(struct rb_root *root, struct dso_cache *new) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct dso_cache *cache; + u64 offset = new->offset; + + while (*p != NULL) { + u64 end; + + parent = *p; + cache = rb_entry(parent, struct dso_cache, rb_node); + end = cache->offset + DSO__DATA_CACHE_SIZE; + + if (offset < cache->offset) + p = &(*p)->rb_left; + else if (offset >= end) + p = &(*p)->rb_right; + } + + rb_link_node(&new->rb_node, parent, p); + rb_insert_color(&new->rb_node, root); +} + +static ssize_t +dso_cache__memcpy(struct dso_cache *cache, u64 offset, + u8 *data, u64 size) +{ + u64 cache_offset = offset - cache->offset; + u64 cache_size = min(cache->size - cache_offset, size); + + memcpy(data, cache->data + cache_offset, cache_size); + return cache_size; +} + +static ssize_t +dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size) +{ + struct dso_cache *cache; + ssize_t ret; + + do { + u64 cache_offset; + + ret = -ENOMEM; + + cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE); + if (!cache) + break; + + cache_offset = offset & DSO__DATA_CACHE_MASK; + ret = -EINVAL; + + if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET)) + break; + + ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE); + if (ret <= 0) + break; + + cache->offset = cache_offset; + cache->size = ret; + dso_cache__insert(&dso->data.cache, cache); + + ret = dso_cache__memcpy(cache, offset, data, size); + + } while (0); + + if (ret <= 0) + free(cache); + + return ret; +} + +static ssize_t dso_cache_read(struct dso *dso, u64 offset, + u8 *data, ssize_t size) +{ + struct dso_cache *cache; + + cache = dso_cache__find(&dso->data.cache, offset); + if (cache) + return dso_cache__memcpy(cache, offset, data, size); + else + return dso_cache__read(dso, offset, data, size); +} + +/* + * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks + * in the rb_tree. Any read to already cached data is served + * by cached data. + */ +static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size) +{ + ssize_t r = 0; + u8 *p = data; + + do { + ssize_t ret; + + ret = dso_cache_read(dso, offset, p, size); + if (ret < 0) + return ret; + + /* Reached EOF, return what we have. */ + if (!ret) + break; + + BUG_ON(ret > size); + + r += ret; + p += ret; + offset += ret; + size -= ret; + + } while (size); + + return r; +} + +static int data_file_size(struct dso *dso) +{ + struct stat st; + + if (!dso->data.file_size) { + if (fstat(dso->data.fd, &st)) { + pr_err("dso mmap failed, fstat: %s\n", strerror(errno)); + return -1; + } + dso->data.file_size = st.st_size; + } + + return 0; +} + +static ssize_t data_read_offset(struct dso *dso, u64 offset, + u8 *data, ssize_t size) +{ + if (data_file_size(dso)) + return -1; + + /* Check the offset sanity. */ + if (offset > dso->data.file_size) + return -1; + + if (offset + size < offset) + return -1; + + return cached_read(dso, offset, data, size); +} + +/** + * dso__data_read_offset - Read data from dso file offset + * @dso: dso object + * @machine: machine object + * @offset: file offset + * @data: buffer to store data + * @size: size of the @data buffer + * + * External interface to read data from dso file offset. Open + * dso data file and use cached_read to get the data. + */ +ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size) +{ + if (dso__data_fd(dso, machine) < 0) + return -1; + + return data_read_offset(dso, offset, data, size); +} + +/** + * dso__data_read_addr - Read data from dso address + * @dso: dso object + * @machine: machine object + * @add: virtual memory address + * @data: buffer to store data + * @size: size of the @data buffer + * + * External interface to read data from dso address. + */ +ssize_t dso__data_read_addr(struct dso *dso, struct map *map, + struct machine *machine, u64 addr, + u8 *data, ssize_t size) +{ + u64 offset = map->map_ip(map, addr); + return dso__data_read_offset(dso, machine, offset, data, size); +} + +struct map *dso__new_map(const char *name) +{ + struct map *map = NULL; + struct dso *dso = dso__new(name); + + if (dso) + map = map__new2(0, dso, MAP__FUNCTION); + + return map; +} + +struct dso *dso__kernel_findnew(struct machine *machine, const char *name, + const char *short_name, int dso_type) +{ + /* + * The kernel dso could be created by build_id processing. + */ + struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name); + + /* + * We need to run this in all cases, since during the build_id + * processing we had no idea this was the kernel dso. + */ + if (dso != NULL) { + dso__set_short_name(dso, short_name, false); + dso->kernel = dso_type; + } + + return dso; +} + +void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) +{ + if (name == NULL) + return; + + if (dso->long_name_allocated) + free((char *)dso->long_name); + + dso->long_name = name; + dso->long_name_len = strlen(name); + dso->long_name_allocated = name_allocated; +} + +void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated) +{ + if (name == NULL) + return; + + if (dso->short_name_allocated) + free((char *)dso->short_name); + + dso->short_name = name; + dso->short_name_len = strlen(name); + dso->short_name_allocated = name_allocated; +} + +static void dso__set_basename(struct dso *dso) +{ + /* + * basename() may modify path buffer, so we must pass + * a copy. + */ + char *base, *lname = strdup(dso->long_name); + + if (!lname) + return; + + /* + * basename() may return a pointer to internal + * storage which is reused in subsequent calls + * so copy the result. + */ + base = strdup(basename(lname)); + + free(lname); + + if (!base) + return; + + dso__set_short_name(dso, base, true); +} + +int dso__name_len(const struct dso *dso) +{ + if (!dso) + return strlen("[unknown]"); + if (verbose) + return dso->long_name_len; + + return dso->short_name_len; +} + +bool dso__loaded(const struct dso *dso, enum map_type type) +{ + return dso->loaded & (1 << type); +} + +bool dso__sorted_by_name(const struct dso *dso, enum map_type type) +{ + return dso->sorted_by_name & (1 << type); +} + +void dso__set_sorted_by_name(struct dso *dso, enum map_type type) +{ + dso->sorted_by_name |= (1 << type); +} + +struct dso *dso__new(const char *name) +{ + struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1); + + if (dso != NULL) { + int i; + strcpy(dso->name, name); + dso__set_long_name(dso, dso->name, false); + dso__set_short_name(dso, dso->name, false); + for (i = 0; i < MAP__NR_TYPES; ++i) + dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; + dso->data.cache = RB_ROOT; + dso->data.fd = -1; + dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; + dso->binary_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->a2l_fails = 1; + dso->kernel = DSO_TYPE_USER; + dso->needs_swap = DSO_SWAP__UNSET; + INIT_LIST_HEAD(&dso->node); + INIT_LIST_HEAD(&dso->data.open_entry); + } + + return dso; +} + +void dso__delete(struct dso *dso) +{ + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) + symbols__delete(&dso->symbols[i]); + + if (dso->short_name_allocated) { + zfree((char **)&dso->short_name); + dso->short_name_allocated = false; + } + + if (dso->long_name_allocated) { + zfree((char **)&dso->long_name); + dso->long_name_allocated = false; + } + + dso__data_close(dso); + dso_cache__free(&dso->data.cache); + dso__free_a2l(dso); + zfree(&dso->symsrc_filename); + free(dso); +} + +void dso__set_build_id(struct dso *dso, void *build_id) +{ + memcpy(dso->build_id, build_id, sizeof(dso->build_id)); + dso->has_build_id = 1; +} + +bool dso__build_id_equal(const struct dso *dso, u8 *build_id) +{ + return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0; +} + +void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine) +{ + char path[PATH_MAX]; + + if (machine__is_default_guest(machine)) + return; + sprintf(path, "%s/sys/kernel/notes", machine->root_dir); + if (sysfs__read_build_id(path, dso->build_id, + sizeof(dso->build_id)) == 0) + dso->has_build_id = true; +} + +int dso__kernel_module_get_build_id(struct dso *dso, + const char *root_dir) +{ + char filename[PATH_MAX]; + /* + * kernel module short names are of the form "[module]" and + * we need just "module" here. + */ + const char *name = dso->short_name + 1; + + snprintf(filename, sizeof(filename), + "%s/sys/module/%.*s/notes/.note.gnu.build-id", + root_dir, (int)strlen(name) - 1, name); + + if (sysfs__read_build_id(filename, dso->build_id, + sizeof(dso->build_id)) == 0) + dso->has_build_id = true; + + return 0; +} + +bool __dsos__read_build_ids(struct list_head *head, bool with_hits) +{ + bool have_build_id = false; + struct dso *pos; + + list_for_each_entry(pos, head, node) { + if (with_hits && !pos->hit) + continue; + if (pos->has_build_id) { + have_build_id = true; + continue; + } + if (filename__read_build_id(pos->long_name, pos->build_id, + sizeof(pos->build_id)) > 0) { + have_build_id = true; + pos->has_build_id = true; + } + } + + return have_build_id; +} + +void dsos__add(struct list_head *head, struct dso *dso) +{ + list_add_tail(&dso->node, head); +} + +struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short) +{ + struct dso *pos; + + if (cmp_short) { + list_for_each_entry(pos, head, node) + if (strcmp(pos->short_name, name) == 0) + return pos; + return NULL; + } + list_for_each_entry(pos, head, node) + if (strcmp(pos->long_name, name) == 0) + return pos; + return NULL; +} + +struct dso *__dsos__findnew(struct list_head *head, const char *name) +{ + struct dso *dso = dsos__find(head, name, false); + + if (!dso) { + dso = dso__new(name); + if (dso != NULL) { + dsos__add(head, dso); + dso__set_basename(dso); + } + } + + return dso; +} + +size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm) +{ + struct dso *pos; + size_t ret = 0; + + list_for_each_entry(pos, head, node) { + if (skip && skip(pos, parm)) + continue; + ret += dso__fprintf_buildid(pos, fp); + ret += fprintf(fp, " %s\n", pos->long_name); + } + return ret; +} + +size_t __dsos__fprintf(struct list_head *head, FILE *fp) +{ + struct dso *pos; + size_t ret = 0; + + list_for_each_entry(pos, head, node) { + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) + ret += dso__fprintf(pos, i, fp); + } + + return ret; +} + +size_t dso__fprintf_buildid(struct dso *dso, FILE *fp) +{ + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + + build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + return fprintf(fp, "%s", sbuild_id); +} + +size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp) +{ + struct rb_node *nd; + size_t ret = fprintf(fp, "dso: %s (", dso->short_name); + + if (dso->short_name != dso->long_name) + ret += fprintf(fp, "%s, ", dso->long_name); + ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type], + dso__loaded(dso, type) ? "" : "NOT "); + ret += dso__fprintf_buildid(dso, fp); + ret += fprintf(fp, ")\n"); + for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) { + struct symbol *pos = rb_entry(nd, struct symbol, rb_node); + ret += symbol__fprintf(pos, fp); + } + + return ret; +} diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h new file mode 100644 index 00000000000..ad553ba257b --- /dev/null +++ b/tools/perf/util/dso.h @@ -0,0 +1,232 @@ +#ifndef __PERF_DSO +#define __PERF_DSO + +#include <linux/types.h> +#include <linux/rbtree.h> +#include <stdbool.h> +#include <linux/types.h> +#include "map.h" +#include "build-id.h" + +enum dso_binary_type { + DSO_BINARY_TYPE__KALLSYMS = 0, + DSO_BINARY_TYPE__GUEST_KALLSYMS, + DSO_BINARY_TYPE__VMLINUX, + DSO_BINARY_TYPE__GUEST_VMLINUX, + DSO_BINARY_TYPE__JAVA_JIT, + DSO_BINARY_TYPE__DEBUGLINK, + DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + 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, +}; + +enum dso_kernel_type { + DSO_TYPE_USER = 0, + DSO_TYPE_KERNEL, + DSO_TYPE_GUEST_KERNEL +}; + +enum dso_swap_type { + DSO_SWAP__UNSET, + DSO_SWAP__NO, + DSO_SWAP__YES, +}; + +#define DSO__SWAP(dso, type, val) \ +({ \ + type ____r = val; \ + BUG_ON(dso->needs_swap == DSO_SWAP__UNSET); \ + if (dso->needs_swap == DSO_SWAP__YES) { \ + switch (sizeof(____r)) { \ + case 2: \ + ____r = bswap_16(val); \ + break; \ + case 4: \ + ____r = bswap_32(val); \ + break; \ + case 8: \ + ____r = bswap_64(val); \ + break; \ + default: \ + BUG_ON(1); \ + } \ + } \ + ____r; \ +}) + +#define DSO__DATA_CACHE_SIZE 4096 +#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1) + +struct dso_cache { + struct rb_node rb_node; + u64 offset; + u64 size; + char data[0]; +}; + +struct dso { + struct list_head node; + struct rb_root symbols[MAP__NR_TYPES]; + struct rb_root symbol_names[MAP__NR_TYPES]; + void *a2l; + char *symsrc_filename; + unsigned int a2l_fails; + enum dso_kernel_type kernel; + enum dso_swap_type needs_swap; + enum dso_binary_type symtab_type; + enum dso_binary_type binary_type; + u8 adjust_symbols:1; + u8 has_build_id:1; + u8 has_srcline:1; + u8 hit:1; + u8 annotate_warned:1; + u8 short_name_allocated:1; + u8 long_name_allocated:1; + u8 sorted_by_name; + u8 loaded; + u8 rel; + u8 build_id[BUILD_ID_SIZE]; + const char *short_name; + const char *long_name; + u16 long_name_len; + u16 short_name_len; + + /* dso data file */ + struct { + struct rb_root cache; + int fd; + size_t file_size; + struct list_head open_entry; + } data; + + char name[0]; +}; + +/* dso__for_each_symbol - iterate over the symbols of given type + * + * @dso: the 'struct dso *' in which symbols itereated + * @pos: the 'struct symbol *' to use as a loop cursor + * @n: the 'struct rb_node *' to use as a temporary storage + * @type: the 'enum map_type' type of symbols + */ +#define dso__for_each_symbol(dso, pos, n, type) \ + symbols__for_each_entry(&(dso)->symbols[(type)], pos, n) + +static inline void dso__set_loaded(struct dso *dso, enum map_type type) +{ + dso->loaded |= (1 << type); +} + +struct dso *dso__new(const char *name); +void dso__delete(struct dso *dso); + +void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated); +void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated); + +int dso__name_len(const struct dso *dso); + +bool dso__loaded(const struct dso *dso, enum map_type type); + +bool dso__sorted_by_name(const struct dso *dso, enum map_type type); +void dso__set_sorted_by_name(struct dso *dso, enum map_type type); +void dso__sort_by_name(struct dso *dso, enum map_type type); + +void dso__set_build_id(struct dso *dso, void *build_id); +bool dso__build_id_equal(const struct dso *dso, u8 *build_id); +void dso__read_running_kernel_build_id(struct dso *dso, + struct machine *machine); +int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir); + +char dso__symtab_origin(const struct dso *dso); +int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, + char *root_dir, char *filename, size_t size); + +/* + * The dso__data_* external interface provides following functions: + * dso__data_fd + * dso__data_close + * dso__data_read_offset + * dso__data_read_addr + * + * Please refer to the dso.c object code for each function and + * arguments documentation. Following text tries to explain the + * dso file descriptor caching. + * + * The dso__data* interface allows caching of opened file descriptors + * to speed up the dso data accesses. The idea is to leave the file + * descriptor opened ideally for the whole life of the dso object. + * + * The current usage of the dso__data_* interface is as follows: + * + * Get DSO's fd: + * int fd = dso__data_fd(dso, machine); + * USE 'fd' SOMEHOW + * + * Read DSO's data: + * n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE); + * n = dso__data_read_addr(dso_0, &machine, 0, buf, BUFSIZE); + * + * Eventually close DSO's fd: + * dso__data_close(dso); + * + * It is not necessary to close the DSO object data file. Each time new + * DSO data file is opened, the limit (RLIMIT_NOFILE/2) is checked. Once + * it is crossed, the oldest opened DSO object is closed. + * + * The dso__delete function calls close_dso function to ensure the + * data file descriptor gets closed/unmapped before the dso object + * is freed. + * + * TODO +*/ +int dso__data_fd(struct dso *dso, struct machine *machine); +void dso__data_close(struct dso *dso); + +ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size); +ssize_t dso__data_read_addr(struct dso *dso, struct map *map, + struct machine *machine, u64 addr, + u8 *data, ssize_t size); + +struct map *dso__new_map(const char *name); +struct dso *dso__kernel_findnew(struct machine *machine, const char *name, + const char *short_name, int dso_type); + +void dsos__add(struct list_head *head, struct dso *dso); +struct dso *dsos__find(const struct list_head *head, const char *name, + bool cmp_short); +struct dso *__dsos__findnew(struct list_head *head, const char *name); +bool __dsos__read_build_ids(struct list_head *head, bool with_hits); + +size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm); +size_t __dsos__fprintf(struct list_head *head, FILE *fp); + +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->binary_type == DSO_BINARY_TYPE__VMLINUX || + dso->binary_type == DSO_BINARY_TYPE__GUEST_VMLINUX; +} + +static inline bool dso__is_kcore(struct dso *dso) +{ + return dso->binary_type == DSO_BINARY_TYPE__KCORE || + dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE; +} + +void dso__free_a2l(struct dso *dso); + +#endif /* __PERF_DSO */ diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c new file mode 100644 index 00000000000..cc66c4049e0 --- /dev/null +++ b/tools/perf/util/dwarf-aux.c @@ -0,0 +1,884 @@ +/* + * dwarf-aux.c : libdw auxiliary interfaces + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +#include <stdbool.h> +#include "util.h" +#include "debug.h" +#include "dwarf-aux.h" + +/** + * cu_find_realpath - Find the realpath of the target file + * @cu_die: A DIE(dwarf information entry) of CU(compilation Unit) + * @fname: The tail filename of the target file + * + * Find the real(long) path of @fname in @cu_die. + */ +const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname) +{ + Dwarf_Files *files; + size_t nfiles, i; + const char *src = NULL; + int ret; + + if (!fname) + return NULL; + + ret = dwarf_getsrcfiles(cu_die, &files, &nfiles); + if (ret != 0) + return NULL; + + for (i = 0; i < nfiles; i++) { + src = dwarf_filesrc(files, i, NULL, NULL); + if (strtailcmp(src, fname) == 0) + break; + } + if (i == nfiles) + return NULL; + return src; +} + +/** + * cu_get_comp_dir - Get the path of compilation directory + * @cu_die: a CU DIE + * + * Get the path of compilation directory of given @cu_die. + * Since this depends on DW_AT_comp_dir, older gcc will not + * embedded it. In that case, this returns NULL. + */ +const char *cu_get_comp_dir(Dwarf_Die *cu_die) +{ + Dwarf_Attribute attr; + if (dwarf_attr(cu_die, DW_AT_comp_dir, &attr) == NULL) + return NULL; + return dwarf_formstring(&attr); +} + +/** + * cu_find_lineinfo - Get a line number and file name for given address + * @cu_die: a CU DIE + * @addr: An address + * @fname: a pointer which returns the file name string + * @lineno: a pointer which returns the line number + * + * Find a line number and file name for @addr in @cu_die. + */ +int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr, + const char **fname, int *lineno) +{ + Dwarf_Line *line; + Dwarf_Addr laddr; + + line = dwarf_getsrc_die(cu_die, (Dwarf_Addr)addr); + if (line && dwarf_lineaddr(line, &laddr) == 0 && + addr == (unsigned long)laddr && dwarf_lineno(line, lineno) == 0) { + *fname = dwarf_linesrc(line, NULL, NULL); + if (!*fname) + /* line number is useless without filename */ + *lineno = 0; + } + + return *lineno ?: -ENOENT; +} + +static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data); + +/** + * cu_walk_functions_at - Walk on function DIEs at given address + * @cu_die: A CU DIE + * @addr: An address + * @callback: A callback which called with found DIEs + * @data: A user data + * + * Walk on function DIEs at given @addr in @cu_die. Passed DIEs + * should be subprogram or inlined-subroutines. + */ +int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, + int (*callback)(Dwarf_Die *, void *), void *data) +{ + Dwarf_Die die_mem; + Dwarf_Die *sc_die; + int ret = -ENOENT; + + /* Inlined function could be recursive. Trace it until fail */ + for (sc_die = die_find_realfunc(cu_die, addr, &die_mem); + sc_die != NULL; + sc_die = die_find_child(sc_die, __die_find_inline_cb, &addr, + &die_mem)) { + ret = callback(sc_die, data); + if (ret) + break; + } + + return ret; + +} + +/** + * die_compare_name - Compare diename and tname + * @dw_die: a DIE + * @tname: a string of target name + * + * Compare the name of @dw_die and @tname. Return false if @dw_die has no name. + */ +bool die_compare_name(Dwarf_Die *dw_die, const char *tname) +{ + const char *name; + name = dwarf_diename(dw_die); + return name ? (strcmp(tname, name) == 0) : false; +} + +/** + * die_get_call_lineno - Get callsite line number of inline-function instance + * @in_die: a DIE of an inlined function instance + * + * Get call-site line number of @in_die. This means from where the inline + * function is called. + */ +int die_get_call_lineno(Dwarf_Die *in_die) +{ + Dwarf_Attribute attr; + Dwarf_Word ret; + + if (!dwarf_attr(in_die, DW_AT_call_line, &attr)) + return -ENOENT; + + dwarf_formudata(&attr, &ret); + return (int)ret; +} + +/** + * die_get_type - Get type DIE + * @vr_die: a DIE of a variable + * @die_mem: where to store a type DIE + * + * Get a DIE of the type of given variable (@vr_die), and store + * it to die_mem. Return NULL if fails to get a type DIE. + */ +Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) +{ + Dwarf_Attribute attr; + + if (dwarf_attr_integrate(vr_die, DW_AT_type, &attr) && + dwarf_formref_die(&attr, die_mem)) + return die_mem; + else + return NULL; +} + +/* Get a type die, but skip qualifiers */ +static Dwarf_Die *__die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) +{ + int tag; + + do { + vr_die = die_get_type(vr_die, die_mem); + if (!vr_die) + break; + tag = dwarf_tag(vr_die); + } while (tag == DW_TAG_const_type || + tag == DW_TAG_restrict_type || + tag == DW_TAG_volatile_type || + tag == DW_TAG_shared_type); + + return vr_die; +} + +/** + * die_get_real_type - Get a type die, but skip qualifiers and typedef + * @vr_die: a DIE of a variable + * @die_mem: where to store a type DIE + * + * Get a DIE of the type of given variable (@vr_die), and store + * it to die_mem. Return NULL if fails to get a type DIE. + * If the type is qualifiers (e.g. const) or typedef, this skips it + * and tries to find real type (structure or basic types, e.g. int). + */ +Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) +{ + do { + vr_die = __die_get_real_type(vr_die, die_mem); + } while (vr_die && dwarf_tag(vr_die) == DW_TAG_typedef); + + return vr_die; +} + +/* Get attribute and translate it as a udata */ +static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name, + Dwarf_Word *result) +{ + Dwarf_Attribute attr; + + if (dwarf_attr(tp_die, attr_name, &attr) == NULL || + dwarf_formudata(&attr, result) != 0) + return -ENOENT; + + return 0; +} + +/* Get attribute and translate it as a sdata */ +static int die_get_attr_sdata(Dwarf_Die *tp_die, unsigned int attr_name, + Dwarf_Sword *result) +{ + Dwarf_Attribute attr; + + if (dwarf_attr(tp_die, attr_name, &attr) == NULL || + dwarf_formsdata(&attr, result) != 0) + return -ENOENT; + + return 0; +} + +/** + * die_is_signed_type - Check whether a type DIE is signed or not + * @tp_die: a DIE of a type + * + * Get the encoding of @tp_die and return true if the encoding + * is signed. + */ +bool die_is_signed_type(Dwarf_Die *tp_die) +{ + Dwarf_Word ret; + + if (die_get_attr_udata(tp_die, DW_AT_encoding, &ret)) + return false; + + return (ret == DW_ATE_signed_char || ret == DW_ATE_signed || + ret == DW_ATE_signed_fixed); +} + +/** + * 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 + * + * Get the offset of @mb_die in the data structure including @mb_die, and + * stores result offset to @offs. If any error occurs this returns errno. + */ +int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs) +{ + Dwarf_Attribute attr; + Dwarf_Op *expr; + size_t nexpr; + int ret; + + if (dwarf_attr(mb_die, DW_AT_data_member_location, &attr) == NULL) + return -ENOENT; + + if (dwarf_formudata(&attr, offs) != 0) { + /* DW_AT_data_member_location should be DW_OP_plus_uconst */ + ret = dwarf_getlocation(&attr, &expr, &nexpr); + if (ret < 0 || nexpr == 0) + return -ENOENT; + + if (expr[0].atom != DW_OP_plus_uconst || nexpr != 1) { + pr_debug("Unable to get offset:Unexpected OP %x (%zd)\n", + expr[0].atom, nexpr); + return -ENOTSUP; + } + *offs = (Dwarf_Word)expr[0].number; + } + return 0; +} + +/* Get the call file index number in CU DIE */ +static int die_get_call_fileno(Dwarf_Die *in_die) +{ + Dwarf_Sword idx; + + if (die_get_attr_sdata(in_die, DW_AT_call_file, &idx) == 0) + return (int)idx; + else + return -ENOENT; +} + +/* Get the declared file index number in CU DIE */ +static int die_get_decl_fileno(Dwarf_Die *pdie) +{ + Dwarf_Sword idx; + + if (die_get_attr_sdata(pdie, DW_AT_decl_file, &idx) == 0) + return (int)idx; + else + return -ENOENT; +} + +/** + * die_get_call_file - Get callsite file name of inlined function instance + * @in_die: a DIE of an inlined function instance + * + * Get call-site file name of @in_die. This means from which file the inline + * function is called. + */ +const char *die_get_call_file(Dwarf_Die *in_die) +{ + Dwarf_Die cu_die; + Dwarf_Files *files; + int idx; + + idx = die_get_call_fileno(in_die); + if (idx < 0 || !dwarf_diecu(in_die, &cu_die, NULL, NULL) || + dwarf_getsrcfiles(&cu_die, &files, NULL) != 0) + return NULL; + + return dwarf_filesrc(files, idx, NULL, NULL); +} + + +/** + * die_find_child - Generic DIE search function in DIE tree + * @rt_die: a root DIE + * @callback: a callback function + * @data: a user data passed to the callback function + * @die_mem: a buffer for result DIE + * + * Trace DIE tree from @rt_die and call @callback for each child DIE. + * If @callback returns DIE_FIND_CB_END, this stores the DIE into + * @die_mem and returns it. If @callback returns DIE_FIND_CB_CONTINUE, + * this continues to trace the tree. Optionally, @callback can return + * DIE_FIND_CB_CHILD and DIE_FIND_CB_SIBLING, those means trace only + * the children and trace only the siblings respectively. + * Returns NULL if @callback can't find any appropriate DIE. + */ +Dwarf_Die *die_find_child(Dwarf_Die *rt_die, + int (*callback)(Dwarf_Die *, void *), + void *data, Dwarf_Die *die_mem) +{ + Dwarf_Die child_die; + int ret; + + ret = dwarf_child(rt_die, die_mem); + if (ret != 0) + return NULL; + + do { + ret = callback(die_mem, data); + if (ret == DIE_FIND_CB_END) + return die_mem; + + if ((ret & DIE_FIND_CB_CHILD) && + die_find_child(die_mem, callback, data, &child_die)) { + memcpy(die_mem, &child_die, sizeof(Dwarf_Die)); + return die_mem; + } + } while ((ret & DIE_FIND_CB_SIBLING) && + dwarf_siblingof(die_mem, die_mem) == 0); + + return NULL; +} + +struct __addr_die_search_param { + Dwarf_Addr addr; + Dwarf_Die *die_mem; +}; + +/* die_find callback for non-inlined function search */ +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)); + return DWARF_CB_ABORT; + } + return DWARF_CB_OK; +} + +/** + * die_find_realfunc - Search a non-inlined function at given address + * @cu_die: a CU DIE which including @addr + * @addr: target address + * @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. + */ +Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr, + Dwarf_Die *die_mem) +{ + struct __addr_die_search_param ad; + ad.addr = addr; + ad.die_mem = die_mem; + /* dwarf_getscopes can't find subprogram. */ + if (!dwarf_getfuncs(cu_die, __die_search_func_cb, &ad, 0)) + return NULL; + else + return die_mem; +} + +/* die_find callback for inline function search */ +static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data) +{ + Dwarf_Addr *addr = data; + + if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine && + dwarf_haspc(die_mem, *addr)) + return DIE_FIND_CB_END; + + return DIE_FIND_CB_CONTINUE; +} + +/** + * 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 + * @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. + * If several inlined functions are expanded recursively, this trace + * it down and returns deepest one. + */ +Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, + Dwarf_Die *die_mem) +{ + Dwarf_Die tmp_die; + + sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr, &tmp_die); + if (!sp_die) + return NULL; + + /* Inlined function could be recursive. Trace it until fail */ + while (sp_die) { + memcpy(die_mem, sp_die, sizeof(Dwarf_Die)); + sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr, + &tmp_die); + } + + return die_mem; +} + +struct __instance_walk_param { + void *addr; + int (*callback)(Dwarf_Die *, void *); + void *data; + int retval; +}; + +static int __die_walk_instances_cb(Dwarf_Die *inst, void *data) +{ + struct __instance_walk_param *iwp = data; + Dwarf_Attribute attr_mem; + Dwarf_Die origin_mem; + Dwarf_Attribute *attr; + Dwarf_Die *origin; + int tmp; + + attr = dwarf_attr(inst, DW_AT_abstract_origin, &attr_mem); + if (attr == NULL) + return DIE_FIND_CB_CONTINUE; + + origin = dwarf_formref_die(attr, &origin_mem); + if (origin == NULL || origin->addr != iwp->addr) + return DIE_FIND_CB_CONTINUE; + + /* Ignore redundant instances */ + if (dwarf_tag(inst) == DW_TAG_inlined_subroutine) { + dwarf_decl_line(origin, &tmp); + if (die_get_call_lineno(inst) == tmp) { + tmp = die_get_decl_fileno(origin); + if (die_get_call_fileno(inst) == tmp) + return DIE_FIND_CB_CONTINUE; + } + } + + iwp->retval = iwp->callback(inst, iwp->data); + + return (iwp->retval) ? DIE_FIND_CB_END : DIE_FIND_CB_CONTINUE; +} + +/** + * die_walk_instances - Walk on instances of given DIE + * @or_die: an abstract original DIE + * @callback: a callback function which is called with instance DIE + * @data: user data + * + * Walk on the instances of give @in_die. @in_die must be an inlined function + * declartion. This returns the return value of @callback if it returns + * non-zero value, or -ENOENT if there is no instance. + */ +int die_walk_instances(Dwarf_Die *or_die, int (*callback)(Dwarf_Die *, void *), + void *data) +{ + Dwarf_Die cu_die; + Dwarf_Die die_mem; + struct __instance_walk_param iwp = { + .addr = or_die->addr, + .callback = callback, + .data = data, + .retval = -ENOENT, + }; + + if (dwarf_diecu(or_die, &cu_die, NULL, NULL) == NULL) + return -ENOENT; + + die_find_child(&cu_die, __die_walk_instances_cb, &iwp, &die_mem); + + return iwp.retval; +} + +/* Line walker internal parameters */ +struct __line_walk_param { + bool recursive; + line_walk_callback_t callback; + void *data; + int retval; +}; + +static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data) +{ + struct __line_walk_param *lw = data; + Dwarf_Addr addr = 0; + const char *fname; + int lineno; + + if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) { + fname = die_get_call_file(in_die); + lineno = die_get_call_lineno(in_die); + if (fname && lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) { + lw->retval = lw->callback(fname, lineno, addr, lw->data); + if (lw->retval != 0) + return DIE_FIND_CB_END; + } + } + if (!lw->recursive) + /* Don't need to search recursively */ + return DIE_FIND_CB_SIBLING; + + if (addr) { + fname = dwarf_decl_file(in_die); + if (fname && dwarf_decl_line(in_die, &lineno) == 0) { + lw->retval = lw->callback(fname, lineno, addr, lw->data); + if (lw->retval != 0) + return DIE_FIND_CB_END; + } + } + + /* Continue to search nested inlined function call-sites */ + return DIE_FIND_CB_CONTINUE; +} + +/* Walk on lines of blocks included in given DIE */ +static int __die_walk_funclines(Dwarf_Die *sp_die, bool recursive, + line_walk_callback_t callback, void *data) +{ + struct __line_walk_param lw = { + .recursive = recursive, + .callback = callback, + .data = data, + .retval = 0, + }; + Dwarf_Die die_mem; + Dwarf_Addr addr; + const char *fname; + int lineno; + + /* Handle function declaration line */ + fname = dwarf_decl_file(sp_die); + if (fname && dwarf_decl_line(sp_die, &lineno) == 0 && + dwarf_entrypc(sp_die, &addr) == 0) { + lw.retval = callback(fname, lineno, addr, data); + if (lw.retval != 0) + goto done; + } + die_find_child(sp_die, __die_walk_funclines_cb, &lw, &die_mem); +done: + return lw.retval; +} + +static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data) +{ + struct __line_walk_param *lw = data; + + lw->retval = __die_walk_funclines(sp_die, true, lw->callback, lw->data); + if (lw->retval != 0) + return DWARF_CB_ABORT; + + return DWARF_CB_OK; +} + +/** + * die_walk_lines - Walk on lines inside given DIE + * @rt_die: a root DIE (CU, subprogram or inlined_subroutine) + * @callback: callback routine + * @data: user data + * + * Walk on all lines inside given @rt_die and call @callback on each line. + * If the @rt_die is a function, walk only on the lines inside the function, + * otherwise @rt_die must be a CU DIE. + * Note that this walks not only dwarf line list, but also function entries + * and inline call-site. + */ +int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data) +{ + Dwarf_Lines *lines; + Dwarf_Line *line; + Dwarf_Addr addr; + const char *fname; + int lineno, ret = 0; + Dwarf_Die die_mem, *cu_die; + size_t nlines, i; + + /* Get the CU die */ + if (dwarf_tag(rt_die) != DW_TAG_compile_unit) + cu_die = dwarf_diecu(rt_die, &die_mem, NULL, NULL); + else + cu_die = rt_die; + if (!cu_die) { + pr_debug2("Failed to get CU from given DIE.\n"); + return -EINVAL; + } + + /* Get lines list in the CU */ + if (dwarf_getsrclines(cu_die, &lines, &nlines) != 0) { + pr_debug2("Failed to get source lines on this CU.\n"); + return -ENOENT; + } + pr_debug2("Get %zd lines from this CU\n", nlines); + + /* Walk on the lines on lines list */ + for (i = 0; i < nlines; i++) { + line = dwarf_onesrcline(lines, i); + if (line == NULL || + dwarf_lineno(line, &lineno) != 0 || + dwarf_lineaddr(line, &addr) != 0) { + pr_debug2("Failed to get line info. " + "Possible error in debuginfo.\n"); + continue; + } + /* Filter lines based on address */ + if (rt_die != cu_die) + /* + * Address filtering + * The line is included in given function, and + * no inline block includes it. + */ + if (!dwarf_haspc(rt_die, addr) || + die_find_inlinefunc(rt_die, addr, &die_mem)) + continue; + /* Get source line */ + fname = dwarf_linesrc(line, NULL, NULL); + + ret = callback(fname, lineno, addr, data); + if (ret != 0) + return ret; + } + + /* + * Dwarf lines doesn't include function declarations and inlined + * subroutines. We have to check functions list or given function. + */ + if (rt_die != cu_die) + /* + * Don't need walk functions recursively, because nested + * inlined functions don't have lines of the specified DIE. + */ + ret = __die_walk_funclines(rt_die, false, callback, data); + else { + struct __line_walk_param param = { + .callback = callback, + .data = data, + .retval = 0, + }; + dwarf_getfuncs(cu_die, __die_walk_culines_cb, ¶m, 0); + ret = param.retval; + } + + return ret; +} + +struct __find_variable_param { + const char *name; + Dwarf_Addr addr; +}; + +static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data) +{ + struct __find_variable_param *fvp = data; + Dwarf_Attribute attr; + int tag; + + tag = dwarf_tag(die_mem); + if ((tag == DW_TAG_formal_parameter || + tag == DW_TAG_variable) && + die_compare_name(die_mem, fvp->name) && + /* Does the DIE have location information or external instance? */ + (dwarf_attr(die_mem, DW_AT_external, &attr) || + dwarf_attr(die_mem, DW_AT_location, &attr))) + return DIE_FIND_CB_END; + if (dwarf_haspc(die_mem, fvp->addr)) + return DIE_FIND_CB_CONTINUE; + else + return DIE_FIND_CB_SIBLING; +} + +/** + * die_find_variable_at - Find a given name variable at given address + * @sp_die: a function DIE + * @name: variable name + * @addr: address + * @die_mem: a buffer for result DIE + * + * Find a variable DIE called @name at @addr in @sp_die. + */ +Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name, + Dwarf_Addr addr, Dwarf_Die *die_mem) +{ + struct __find_variable_param fvp = { .name = name, .addr = addr}; + + return die_find_child(sp_die, __die_find_variable_cb, (void *)&fvp, + die_mem); +} + +static int __die_find_member_cb(Dwarf_Die *die_mem, void *data) +{ + const char *name = data; + + if ((dwarf_tag(die_mem) == DW_TAG_member) && + die_compare_name(die_mem, name)) + return DIE_FIND_CB_END; + + return DIE_FIND_CB_SIBLING; +} + +/** + * die_find_member - Find a given name member in a data structure + * @st_die: a data structure type DIE + * @name: member name + * @die_mem: a buffer for result DIE + * + * Find a member DIE called @name in @st_die. + */ +Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name, + Dwarf_Die *die_mem) +{ + return die_find_child(st_die, __die_find_member_cb, (void *)name, + die_mem); +} + +/** + * die_get_typename - Get the name of given variable DIE + * @vr_die: a variable DIE + * @buf: a buffer for result type name + * @len: a max-length of @buf + * + * Get the name of @vr_die and stores it to @buf. Return the actual length + * of type name if succeeded. Return -E2BIG if @len is not enough long, and + * Return -ENOENT if failed to find type name. + * Note that the result will stores typedef name if possible, and stores + * "*(function_type)" if the type is a function pointer. + */ +int die_get_typename(Dwarf_Die *vr_die, char *buf, int len) +{ + Dwarf_Die type; + int tag, ret, ret2; + const char *tmp = ""; + + if (__die_get_real_type(vr_die, &type) == NULL) + return -ENOENT; + + tag = dwarf_tag(&type); + if (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type) + tmp = "*"; + else if (tag == DW_TAG_subroutine_type) { + /* Function pointer */ + ret = snprintf(buf, len, "(function_type)"); + return (ret >= len) ? -E2BIG : ret; + } else { + if (!dwarf_diename(&type)) + return -ENOENT; + if (tag == DW_TAG_union_type) + tmp = "union "; + else if (tag == DW_TAG_structure_type) + tmp = "struct "; + else if (tag == DW_TAG_enumeration_type) + tmp = "enum "; + /* Write a base name */ + ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type)); + return (ret >= len) ? -E2BIG : ret; + } + ret = die_get_typename(&type, buf, len); + if (ret > 0) { + ret2 = snprintf(buf + ret, len - ret, "%s", tmp); + ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret; + } + return ret; +} + +/** + * die_get_varname - Get the name and type of given variable DIE + * @vr_die: a variable DIE + * @buf: a buffer for type and variable name + * @len: the max-length of @buf + * + * Get the name and type of @vr_die and stores it in @buf as "type\tname". + */ +int die_get_varname(Dwarf_Die *vr_die, char *buf, int len) +{ + int ret, ret2; + + ret = die_get_typename(vr_die, buf, len); + if (ret < 0) { + pr_debug("Failed to get type, make it unknown.\n"); + ret = snprintf(buf, len, "(unknown_type)"); + } + if (ret > 0) { + ret2 = snprintf(buf + ret, len - ret, "\t%s", + dwarf_diename(vr_die)); + ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret; + } + return ret; +} + diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h new file mode 100644 index 00000000000..b4fe90c6cb2 --- /dev/null +++ b/tools/perf/util/dwarf-aux.h @@ -0,0 +1,118 @@ +#ifndef _DWARF_AUX_H +#define _DWARF_AUX_H +/* + * dwarf-aux.h : libdw auxiliary interfaces + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +#include <dwarf.h> +#include <elfutils/libdw.h> +#include <elfutils/libdwfl.h> +#include <elfutils/version.h> + +/* Find the realpath of the target file */ +extern const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname); + +/* Get DW_AT_comp_dir (should be NULL with older gcc) */ +extern const char *cu_get_comp_dir(Dwarf_Die *cu_die); + +/* Get a line number and file name for given address */ +extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, + const char **fname, int *lineno); + +/* Walk on funcitons at given address */ +extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, + int (*callback)(Dwarf_Die *, void *), void *data); + +/* 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); + +/* Get callsite line number of inline-function instance */ +extern int die_get_call_lineno(Dwarf_Die *in_die); + +/* Get callsite file name of inlined function instance */ +extern const char *die_get_call_file(Dwarf_Die *in_die); + +/* Get type die */ +extern Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem); + +/* Get a type die, but skip qualifiers and typedef */ +extern Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem); + +/* Check whether the DIE is signed or not */ +extern bool die_is_signed_type(Dwarf_Die *tp_die); + +/* Get data_member_location offset */ +extern int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs); + +/* Return values for die_find_child() callbacks */ +enum { + DIE_FIND_CB_END = 0, /* End of Search */ + DIE_FIND_CB_CHILD = 1, /* Search only children */ + DIE_FIND_CB_SIBLING = 2, /* Search only siblings */ + DIE_FIND_CB_CONTINUE = 3, /* Search children and siblings */ +}; + +/* Search child DIEs */ +extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die, + int (*callback)(Dwarf_Die *, void *), + void *data, Dwarf_Die *die_mem); + +/* Search a non-inlined function including given address */ +extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr, + Dwarf_Die *die_mem); + +/* 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); + +/* Walk on the instances of given DIE */ +extern int die_walk_instances(Dwarf_Die *in_die, + int (*callback)(Dwarf_Die *, void *), void *data); + +/* Walker on lines (Note: line number will not be sorted) */ +typedef int (* line_walk_callback_t) (const char *fname, int lineno, + Dwarf_Addr addr, void *data); + +/* + * Walk on lines inside given DIE. If the DIE is a subprogram, walk only on + * the lines inside the subprogram, otherwise the DIE must be a CU DIE. + */ +extern int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, + void *data); + +/* Find a variable called 'name' at given address */ +extern Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name, + Dwarf_Addr addr, Dwarf_Die *die_mem); + +/* Find a member called 'name' */ +extern Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name, + Dwarf_Die *die_mem); + +/* Get the name of given variable DIE */ +extern int die_get_typename(Dwarf_Die *vr_die, char *buf, int len); + +/* Get the name and type of given variable DIE, stored as "type\tname" */ +extern int die_get_varname(Dwarf_Die *vr_die, char *buf, int len); +#endif diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index dab9e754a28..d0281bdfa58 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,119 +1,174 @@ #include <linux/types.h> +#include <sys/mman.h> #include "event.h" #include "debug.h" -#include "session.h" +#include "hist.h" +#include "machine.h" #include "sort.h" #include "string.h" #include "strlist.h" #include "thread.h" +#include "thread_map.h" +#include "symbol/kallsyms.h" + +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", + [PERF_RECORD_THROTTLE] = "THROTTLE", + [PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE", + [PERF_RECORD_FORK] = "FORK", + [PERF_RECORD_READ] = "READ", + [PERF_RECORD_SAMPLE] = "SAMPLE", + [PERF_RECORD_HEADER_ATTR] = "ATTR", + [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", + [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", + [PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID", + [PERF_RECORD_FINISHED_ROUND] = "FINISHED_ROUND", +}; + +const char *perf_event__name(unsigned int id) +{ + if (id >= ARRAY_SIZE(perf_event__names)) + return "INVALID"; + if (!perf_event__names[id]) + return "UNKNOWN"; + return perf_event__names[id]; +} -const char *event__name[] = { - [0] = "TOTAL", - [PERF_RECORD_MMAP] = "MMAP", - [PERF_RECORD_LOST] = "LOST", - [PERF_RECORD_COMM] = "COMM", - [PERF_RECORD_EXIT] = "EXIT", - [PERF_RECORD_THROTTLE] = "THROTTLE", - [PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE", - [PERF_RECORD_FORK] = "FORK", - [PERF_RECORD_READ] = "READ", - [PERF_RECORD_SAMPLE] = "SAMPLE", - [PERF_RECORD_HEADER_ATTR] = "ATTR", - [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", - [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", - [PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID", +static struct perf_sample synth_sample = { + .pid = -1, + .tid = -1, + .time = -1, + .stream_id = -1, + .cpu = -1, + .period = 1, }; -static pid_t event__synthesize_comm(pid_t pid, int full, - event__handler_t process, - struct perf_session *session) +static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) { - event_t ev; char filename[PATH_MAX]; char bf[BUFSIZ]; FILE *fp; size_t size = 0; - DIR *tasks; - struct dirent dirent, *next; - pid_t tgid = 0; + pid_t tgid = -1; snprintf(filename, sizeof(filename), "/proc/%d/status", pid); fp = fopen(filename, "r"); if (fp == NULL) { -out_race: - /* - * We raced with a task exiting - just return: - */ pr_debug("couldn't open %s\n", filename); return 0; } - memset(&ev.comm, 0, sizeof(ev.comm)); - while (!ev.comm.comm[0] || !ev.comm.pid) { - if (fgets(bf, sizeof(bf), fp) == NULL) - goto out_failure; + while (!comm[0] || (tgid < 0)) { + if (fgets(bf, sizeof(bf), fp) == NULL) { + pr_warning("couldn't get COMM and pgid, malformed %s\n", + filename); + break; + } if (memcmp(bf, "Name:", 5) == 0) { char *name = bf + 5; while (*name && isspace(*name)) ++name; size = strlen(name) - 1; - memcpy(ev.comm.comm, name, size++); + if (size >= len) + size = len - 1; + memcpy(comm, name, size); + comm[size] = '\0'; + } else if (memcmp(bf, "Tgid:", 5) == 0) { char *tgids = bf + 5; while (*tgids && isspace(*tgids)) ++tgids; - tgid = ev.comm.pid = atoi(tgids); + tgid = atoi(tgids); } } - ev.comm.header.type = PERF_RECORD_COMM; - size = ALIGN(size, sizeof(u64)); - ev.comm.header.size = sizeof(ev.comm) - (sizeof(ev.comm.comm) - size); + fclose(fp); - if (!full) { - ev.comm.tid = pid; + return tgid; +} - process(&ev, session); - goto out_fclose; - } +static pid_t perf_event__synthesize_comm(struct perf_tool *tool, + union perf_event *event, pid_t pid, + perf_event__handler_t process, + struct machine *machine) +{ + size_t size; + pid_t tgid; - snprintf(filename, sizeof(filename), "/proc/%d/task", pid); + memset(&event->comm, 0, sizeof(event->comm)); - tasks = opendir(filename); - if (tasks == NULL) - goto out_race; + if (machine__is_host(machine)) + tgid = perf_event__get_comm_tgid(pid, event->comm.comm, + sizeof(event->comm.comm)); + else + tgid = machine->pid; - while (!readdir_r(tasks, &dirent, &next) && next) { - char *end; - pid = strtol(dirent.d_name, &end, 10); - if (*end) - continue; + if (tgid < 0) + goto out; - ev.comm.tid = pid; + event->comm.pid = tgid; + event->comm.header.type = PERF_RECORD_COMM; - process(&ev, session); - } - closedir(tasks); + size = strlen(event->comm.comm) + 1; + size = PERF_ALIGN(size, sizeof(u64)); + memset(event->comm.comm + size, 0, machine->id_hdr_size); + event->comm.header.size = (sizeof(event->comm) - + (sizeof(event->comm.comm) - size) + + machine->id_hdr_size); + event->comm.tid = pid; -out_fclose: - fclose(fp); + if (process(tool, event, &synth_sample, machine) != 0) + return -1; + +out: return tgid; +} + +static int perf_event__synthesize_fork(struct perf_tool *tool, + union perf_event *event, pid_t pid, + pid_t tgid, perf_event__handler_t process, + struct machine *machine) +{ + memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); + + /* this is really a clone event but we use fork to synthesize it */ + event->fork.ppid = tgid; + event->fork.ptid = tgid; + event->fork.pid = tgid; + event->fork.tid = pid; + event->fork.header.type = PERF_RECORD_FORK; + + event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size); + + if (process(tool, event, &synth_sample, machine) != 0) + return -1; -out_failure: - pr_warning("couldn't get COMM and pgid, malformed %s\n", filename); - return -1; + return 0; } -static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, - event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_mmap_events(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data) { char filename[PATH_MAX]; FILE *fp; + int rc = 0; + + if (machine__is_default_guest(machine)) + return 0; - snprintf(filename, sizeof(filename), "/proc/%d/maps", pid); + snprintf(filename, sizeof(filename), "%s/proc/%d/maps", + machine->root_dir, pid); fp = fopen(filename, "r"); if (fp == NULL) { @@ -124,123 +179,315 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, return -1; } + event->header.type = PERF_RECORD_MMAP2; + while (1) { - char bf[BUFSIZ], *pbf = bf; - event_t ev = { - .header = { - .type = PERF_RECORD_MMAP, - /* - * Just like the kernel, see __perf_event_mmap - * in kernel/perf_event.c - */ - .misc = PERF_RECORD_MISC_USER, - }, - }; - int n; + char bf[BUFSIZ]; + char prot[5]; + char execname[PATH_MAX]; + char anonstr[] = "//anon"; + unsigned int ino; size_t size; + ssize_t n; + if (fgets(bf, sizeof(bf), fp) == NULL) break; + /* ensure null termination since stack will be reused. */ + strcpy(execname, ""); + /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = hex2u64(pbf, &ev.mmap.start); - if (n < 0) - continue; - pbf += n + 1; - n = hex2u64(pbf, &ev.mmap.len); - if (n < 0) + n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n", + &event->mmap2.start, &event->mmap2.len, prot, + &event->mmap2.pgoff, &event->mmap2.maj, + &event->mmap2.min, + &ino, execname); + + /* + * Anon maps don't have the execname. + */ + if (n < 7) continue; - pbf += n + 3; - if (*pbf == 'x') { /* vm_exec */ - char *execname = strchr(bf, '/'); - /* Catch VDSO */ - if (execname == NULL) - execname = strstr(bf, "[vdso]"); + event->mmap2.ino = (u64)ino; - if (execname == NULL) - continue; + /* + * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c + */ + if (machine__is_host(machine)) + event->header.misc = PERF_RECORD_MISC_USER; + else + event->header.misc = PERF_RECORD_MISC_GUEST_USER; + + /* map protection and flags bits */ + event->mmap2.prot = 0; + event->mmap2.flags = 0; + if (prot[0] == 'r') + event->mmap2.prot |= PROT_READ; + if (prot[1] == 'w') + event->mmap2.prot |= PROT_WRITE; + if (prot[2] == 'x') + event->mmap2.prot |= PROT_EXEC; + + if (prot[3] == 's') + event->mmap2.flags |= MAP_SHARED; + else + event->mmap2.flags |= MAP_PRIVATE; - pbf += 3; - n = hex2u64(pbf, &ev.mmap.pgoff); + if (prot[2] != 'x') { + if (!mmap_data || prot[0] != 'r') + continue; - size = strlen(execname); - execname[size - 1] = '\0'; /* Remove \n */ - memcpy(ev.mmap.filename, execname, size); - size = ALIGN(size, sizeof(u64)); - ev.mmap.len -= ev.mmap.start; - ev.mmap.header.size = (sizeof(ev.mmap) - - (sizeof(ev.mmap.filename) - size)); - ev.mmap.pid = tgid; - ev.mmap.tid = pid; + event->header.misc |= PERF_RECORD_MISC_MMAP_DATA; + } - process(&ev, session); + if (!strcmp(execname, "")) + strcpy(execname, anonstr); + + size = strlen(execname) + 1; + memcpy(event->mmap2.filename, execname, size); + size = PERF_ALIGN(size, sizeof(u64)); + event->mmap2.len -= event->mmap.start; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size)); + memset(event->mmap2.filename + size, 0, machine->id_hdr_size); + event->mmap2.header.size += machine->id_hdr_size; + event->mmap2.pid = tgid; + event->mmap2.tid = pid; + + if (process(tool, event, &synth_sample, machine) != 0) { + rc = -1; + break; } } fclose(fp); - return 0; + return rc; } -int event__synthesize_modules(event__handler_t process, - struct perf_session *session, - struct machine *machine) +int perf_event__synthesize_modules(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) { + int rc = 0; struct rb_node *nd; struct map_groups *kmaps = &machine->kmaps; - u16 misc; + union perf_event *event = zalloc((sizeof(event->mmap) + + machine->id_hdr_size)); + if (event == NULL) { + pr_debug("Not enough memory synthesizing mmap event " + "for kernel modules\n"); + return -1; + } + + event->header.type = PERF_RECORD_MMAP; /* * kernel uses 0 for user space maps, see kernel/perf_event.c * __perf_event_mmap */ if (machine__is_host(machine)) - misc = PERF_RECORD_MISC_KERNEL; + event->header.misc = PERF_RECORD_MISC_KERNEL; else - misc = PERF_RECORD_MISC_GUEST_KERNEL; + event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) { - event_t ev; size_t size; struct map *pos = rb_entry(nd, struct map, rb_node); if (pos->dso->kernel) continue; - size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); - memset(&ev, 0, sizeof(ev)); - ev.mmap.header.misc = misc; - ev.mmap.header.type = PERF_RECORD_MMAP; - ev.mmap.header.size = (sizeof(ev.mmap) - - (sizeof(ev.mmap.filename) - size)); - ev.mmap.start = pos->start; - ev.mmap.len = pos->end - pos->start; - ev.mmap.pid = machine->pid; - - memcpy(ev.mmap.filename, pos->dso->long_name, + size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); + event->mmap.header.type = PERF_RECORD_MMAP; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size)); + memset(event->mmap.filename + size, 0, machine->id_hdr_size); + event->mmap.header.size += machine->id_hdr_size; + event->mmap.start = pos->start; + event->mmap.len = pos->end - pos->start; + event->mmap.pid = machine->pid; + + memcpy(event->mmap.filename, pos->dso->long_name, pos->dso->long_name_len + 1); - process(&ev, session); + if (process(tool, event, &synth_sample, machine) != 0) { + rc = -1; + break; + } + } + + free(event); + return rc; +} + +static int __event__synthesize_thread(union perf_event *comm_event, + union perf_event *mmap_event, + union perf_event *fork_event, + pid_t pid, int full, + perf_event__handler_t process, + struct perf_tool *tool, + struct machine *machine, bool mmap_data) +{ + char filename[PATH_MAX]; + DIR *tasks; + struct dirent dirent, *next; + pid_t tgid; + + /* special case: only send one comm event using passed in pid */ + if (!full) { + tgid = perf_event__synthesize_comm(tool, comm_event, pid, + process, machine); + + if (tgid == -1) + return -1; + + return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data); + } + + if (machine__is_default_guest(machine)) + return 0; + + snprintf(filename, sizeof(filename), "%s/proc/%d/task", + machine->root_dir, pid); + + tasks = opendir(filename); + if (tasks == NULL) { + pr_debug("couldn't open %s\n", filename); + return 0; + } + + while (!readdir_r(tasks, &dirent, &next) && next) { + char *end; + int rc = 0; + pid_t _pid; + + _pid = strtol(dirent.d_name, &end, 10); + if (*end) + continue; + + tgid = perf_event__synthesize_comm(tool, comm_event, _pid, + process, machine); + if (tgid == -1) + return -1; + + if (_pid == pid) { + /* process the parent's maps too */ + rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data); + } else { + /* only fork the tid's map, to save time */ + rc = perf_event__synthesize_fork(tool, fork_event, _pid, tgid, + process, machine); + } + + if (rc) + return rc; } + closedir(tasks); return 0; } -int event__synthesize_thread(pid_t pid, event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_thread_map(struct perf_tool *tool, + struct thread_map *threads, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data) { - pid_t tgid = event__synthesize_comm(pid, 1, process, session); - if (tgid == -1) - return -1; - return event__synthesize_mmap_events(pid, tgid, process, session); + union perf_event *comm_event, *mmap_event, *fork_event; + int err = -1, thread, j; + + comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); + if (comm_event == NULL) + goto out; + + mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size); + if (mmap_event == NULL) + goto out_free_comm; + + fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); + if (fork_event == NULL) + goto out_free_mmap; + + err = 0; + for (thread = 0; thread < threads->nr; ++thread) { + if (__event__synthesize_thread(comm_event, mmap_event, + fork_event, + threads->map[thread], 0, + process, tool, machine, + mmap_data)) { + err = -1; + break; + } + + /* + * comm.pid is set to thread group id by + * perf_event__synthesize_comm + */ + if ((int) comm_event->comm.pid != threads->map[thread]) { + bool need_leader = true; + + /* is thread group leader in thread_map? */ + for (j = 0; j < threads->nr; ++j) { + if ((int) comm_event->comm.pid == threads->map[j]) { + need_leader = false; + break; + } + } + + /* if not, generate events for it */ + if (need_leader && + __event__synthesize_thread(comm_event, mmap_event, + fork_event, + comm_event->comm.pid, 0, + process, tool, machine, + mmap_data)) { + err = -1; + break; + } + } + } + free(fork_event); +out_free_mmap: + free(mmap_event); +out_free_comm: + free(comm_event); +out: + return err; } -void event__synthesize_threads(event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, bool mmap_data) { DIR *proc; + char proc_path[PATH_MAX]; struct dirent dirent, *next; + union perf_event *comm_event, *mmap_event, *fork_event; + int err = -1; + + if (machine__is_default_guest(machine)) + return 0; + + comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); + if (comm_event == NULL) + goto out; + + mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size); + if (mmap_event == NULL) + goto out_free_comm; + + fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); + if (fork_event == NULL) + goto out_free_mmap; + + snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); + proc = opendir(proc_path); - proc = opendir("/proc"); + if (proc == NULL) + goto out_free_fork; while (!readdir_r(proc, &dirent, &next) && next) { char *end; @@ -248,11 +495,24 @@ void event__synthesize_threads(event__handler_t process, if (*end) /* only interested in proper numerical dirents */ continue; - - event__synthesize_thread(pid, process, session); + /* + * We may race with exiting thread, so don't stop just because + * one thread couldn't be synthesized. + */ + __event__synthesize_thread(comm_event, mmap_event, fork_event, pid, + 1, process, tool, machine, mmap_data); } + err = 0; closedir(proc); +out_free_fork: + free(fork_event); +out_free_mmap: + free(mmap_event); +out_free_comm: + free(comm_event); +out: + return err; } struct process_symbol_args { @@ -260,7 +520,8 @@ struct process_symbol_args { u64 start; }; -static int find_symbol_cb(void *arg, const char *name, char type, u64 start) +static int find_symbol_cb(void *arg, const char *name, char type, + u64 start) { struct process_symbol_args *args = arg; @@ -276,28 +537,39 @@ static int find_symbol_cb(void *arg, const char *name, char type, u64 start) return 1; } -int event__synthesize_kernel_mmap(event__handler_t process, - struct perf_session *session, - struct machine *machine, - const char *symbol_name) +u64 kallsyms__get_function_start(const char *kallsyms_filename, + const char *symbol_name) +{ + struct process_symbol_args args = { .name = symbol_name, }; + + if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0) + return 0; + + return args.start; +} + +int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) { size_t size; - const char *filename, *mmap_name; - char path[PATH_MAX]; + const char *mmap_name; char name_buff[PATH_MAX]; struct map *map; - - event_t ev = { - .header = { - .type = PERF_RECORD_MMAP, - }, - }; + struct kmap *kmap; + int err; /* * We should get this from /sys/kernel/sections/.text, but till that is * available use this, and after it is use this as a fallback for older * kernels. */ - struct process_symbol_args args = { .name = symbol_name, }; + union perf_event *event = zalloc((sizeof(event->mmap) + + machine->id_hdr_size)); + if (event == NULL) { + pr_debug("Not enough memory synthesizing mmap event " + "for kernel modules\n"); + return -1; + } mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff)); if (machine__is_host(machine)) { @@ -305,320 +577,191 @@ int event__synthesize_kernel_mmap(event__handler_t process, * kernel uses PERF_RECORD_MISC_USER for user space maps, * see kernel/perf_event.c __perf_event_mmap */ - ev.header.misc = PERF_RECORD_MISC_KERNEL; - filename = "/proc/kallsyms"; + event->header.misc = PERF_RECORD_MISC_KERNEL; } else { - ev.header.misc = PERF_RECORD_MISC_GUEST_KERNEL; - if (machine__is_default_guest(machine)) - filename = (char *) symbol_conf.default_guest_kallsyms; - else { - sprintf(path, "%s/proc/kallsyms", machine->root_dir); - filename = path; - } + event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; } - if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) - return -ENOENT; - map = machine->vmlinux_maps[MAP__FUNCTION]; - size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename), - "%s%s", mmap_name, symbol_name) + 1; - size = ALIGN(size, sizeof(u64)); - ev.mmap.header.size = (sizeof(ev.mmap) - - (sizeof(ev.mmap.filename) - size)); - ev.mmap.pgoff = args.start; - ev.mmap.start = map->start; - ev.mmap.len = map->end - ev.mmap.start; - ev.mmap.pid = machine->pid; - - return process(&ev, session); + kmap = map__kmap(map); + size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), + "%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1; + size = PERF_ALIGN(size, sizeof(u64)); + event->mmap.header.type = PERF_RECORD_MMAP; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); + event->mmap.pgoff = kmap->ref_reloc_sym->addr; + event->mmap.start = map->start; + event->mmap.len = map->end - event->mmap.start; + event->mmap.pid = machine->pid; + + err = process(tool, event, &synth_sample, machine); + free(event); + + return err; } -static void thread__comm_adjust(struct thread *self, struct hists *hists) +size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) { - char *comm = self->comm; - - if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep && - (!symbol_conf.comm_list || - strlist__has_entry(symbol_conf.comm_list, comm))) { - u16 slen = strlen(comm); - - if (hists__new_col_len(hists, HISTC_COMM, slen)) - hists__set_col_len(hists, HISTC_THREAD, slen + 6); - } + return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid); } -static int thread__set_comm_adjust(struct thread *self, const char *comm, - struct hists *hists) +int perf_event__process_comm(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - int ret = thread__set_comm(self, comm); - - if (ret) - return ret; - - thread__comm_adjust(self, hists); - - return 0; + return machine__process_comm_event(machine, event, sample); } -int event__process_comm(event_t *self, struct perf_session *session) +int perf_event__process_lost(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - struct thread *thread = perf_session__findnew(session, self->comm.tid); - - dump_printf(": %s:%d\n", self->comm.comm, self->comm.tid); - - if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm, - &session->hists)) { - dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); - return -1; - } - - return 0; + return machine__process_lost_event(machine, event, sample); } -int event__process_lost(event_t *self, struct perf_session *session) +size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) { - dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost); - session->hists.stats.total_lost += self->lost.lost; - return 0; + return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n", + event->mmap.pid, event->mmap.tid, event->mmap.start, + event->mmap.len, event->mmap.pgoff, + (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x', + event->mmap.filename); } -static void event_set_kernel_mmap_len(struct map **maps, event_t *self) +size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) { - maps[MAP__FUNCTION]->start = self->mmap.start; - maps[MAP__FUNCTION]->end = self->mmap.start + self->mmap.len; - /* - * Be a bit paranoid here, some perf.data file came with - * a zero sized synthesized MMAP event for the kernel. - */ - if (maps[MAP__FUNCTION]->end == 0) - maps[MAP__FUNCTION]->end = ~0UL; + return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 + " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n", + event->mmap2.pid, event->mmap2.tid, event->mmap2.start, + event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, + event->mmap2.min, event->mmap2.ino, + event->mmap2.ino_generation, + (event->mmap2.prot & PROT_READ) ? 'r' : '-', + (event->mmap2.prot & PROT_WRITE) ? 'w' : '-', + (event->mmap2.prot & PROT_EXEC) ? 'x' : '-', + (event->mmap2.flags & MAP_SHARED) ? 's' : 'p', + event->mmap2.filename); } -static int event__process_kernel_mmap(event_t *self, - struct perf_session *session) +int perf_event__process_mmap(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - struct map *map; - char kmmap_prefix[PATH_MAX]; - struct machine *machine; - enum dso_kernel_type kernel_type; - bool is_kernel_mmap; - - machine = perf_session__findnew_machine(session, self->mmap.pid); - if (!machine) { - pr_err("Can't find id %d's machine\n", self->mmap.pid); - goto out_problem; - } - - machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix)); - if (machine__is_host(machine)) - kernel_type = DSO_TYPE_KERNEL; - else - kernel_type = DSO_TYPE_GUEST_KERNEL; - - is_kernel_mmap = memcmp(self->mmap.filename, - kmmap_prefix, - strlen(kmmap_prefix)) == 0; - if (self->mmap.filename[0] == '/' || - (!is_kernel_mmap && self->mmap.filename[0] == '[')) { - - char short_module_name[1024]; - char *name, *dot; - - if (self->mmap.filename[0] == '/') { - name = strrchr(self->mmap.filename, '/'); - if (name == NULL) - goto out_problem; - - ++name; /* skip / */ - dot = strrchr(name, '.'); - if (dot == NULL) - goto out_problem; - snprintf(short_module_name, sizeof(short_module_name), - "[%.*s]", (int)(dot - name), name); - strxfrchar(short_module_name, '-', '_'); - } else - strcpy(short_module_name, self->mmap.filename); - - map = machine__new_module(machine, self->mmap.start, - self->mmap.filename); - if (map == NULL) - goto out_problem; - - name = strdup(short_module_name); - if (name == NULL) - goto out_problem; - - map->dso->short_name = name; - map->dso->sname_alloc = 1; - map->end = map->start + self->mmap.len; - } else if (is_kernel_mmap) { - const char *symbol_name = (self->mmap.filename + - strlen(kmmap_prefix)); - /* - * Should be there already, from the build-id table in - * the header. - */ - struct dso *kernel = __dsos__findnew(&machine->kernel_dsos, - kmmap_prefix); - if (kernel == NULL) - goto out_problem; - - kernel->kernel = kernel_type; - if (__machine__create_kernel_maps(machine, kernel) < 0) - goto out_problem; - - event_set_kernel_mmap_len(machine->vmlinux_maps, self); - perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, - symbol_name, - self->mmap.pgoff); - if (machine__is_default_guest(machine)) { - /* - * preload dso of guest kernel and modules - */ - dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION], - NULL); - } - } - return 0; -out_problem: - return -1; + return machine__process_mmap_event(machine, event, sample); } -int event__process_mmap(event_t *self, struct perf_session *session) +int perf_event__process_mmap2(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { - struct machine *machine; - struct thread *thread; - struct map *map; - u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - int ret = 0; - - dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n", - self->mmap.pid, self->mmap.tid, self->mmap.start, - self->mmap.len, self->mmap.pgoff, self->mmap.filename); - - if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || - cpumode == PERF_RECORD_MISC_KERNEL) { - ret = event__process_kernel_mmap(self, session); - if (ret < 0) - goto out_problem; - return 0; - } - - machine = perf_session__find_host_machine(session); - if (machine == NULL) - goto out_problem; - thread = perf_session__findnew(session, self->mmap.pid); - if (thread == NULL) - goto out_problem; - map = map__new(&machine->user_dsos, self->mmap.start, - self->mmap.len, self->mmap.pgoff, - self->mmap.pid, self->mmap.filename, - MAP__FUNCTION); - 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; + return machine__process_mmap2_event(machine, event, sample); } -int event__process_task(event_t *self, struct perf_session *session) +size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) { - struct thread *thread = perf_session__findnew(session, self->fork.tid); - struct thread *parent = perf_session__findnew(session, self->fork.ptid); - - dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid, - self->fork.ppid, self->fork.ptid); - - if (self->header.type == PERF_RECORD_EXIT) { - perf_session__remove_thread(session, thread); - return 0; - } + return fprintf(fp, "(%d:%d):(%d:%d)\n", + event->fork.pid, event->fork.tid, + event->fork.ppid, event->fork.ptid); +} - if (thread == NULL || parent == NULL || - thread__fork(thread, parent) < 0) { - dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); - return -1; - } +int perf_event__process_fork(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_fork_event(machine, event, sample); +} - return 0; +int perf_event__process_exit(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_exit_event(machine, event, sample); } -int event__process(event_t *event, struct perf_session *session) +size_t perf_event__fprintf(union perf_event *event, FILE *fp) { + size_t ret = fprintf(fp, "PERF_RECORD_%s", + perf_event__name(event->header.type)); + switch (event->header.type) { case PERF_RECORD_COMM: - event__process_comm(event, session); - break; - case PERF_RECORD_MMAP: - event__process_mmap(event, session); + ret += perf_event__fprintf_comm(event, fp); break; case PERF_RECORD_FORK: case PERF_RECORD_EXIT: - event__process_task(event, session); + ret += perf_event__fprintf_task(event, fp); break; - default: + 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"); } - return 0; + return ret; } -void thread__find_addr_map(struct thread *self, - struct perf_session *session, u8 cpumode, - enum map_type type, pid_t pid, u64 addr, +int perf_event__process(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_event(machine, event, sample); +} + +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 machine *machine = NULL; + struct map_groups *mg = thread->mg; + bool load_map = false; - al->thread = self; + al->machine = machine; + al->thread = thread; al->addr = addr; al->cpumode = cpumode; - al->filtered = false; + al->filtered = 0; + + if (machine == NULL) { + al->map = NULL; + return; + } if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; - machine = perf_session__find_host_machine(session); - if (machine == NULL) { - al->map = NULL; - return; - } mg = &machine->kmaps; + load_map = true; } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; - machine = perf_session__find_host_machine(session); } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { al->level = 'g'; - machine = perf_session__find_machine(session, pid); - if (machine == NULL) { - al->map = NULL; - return; - } mg = &machine->kmaps; + load_map = true; + } else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) { + al->level = 'u'; } else { - /* - * 'u' means guest os user space. - * TODO: We don't support guest user space. Might support late. - */ - if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) - al->level = 'u'; - else - al->level = 'H'; + al->level = 'H'; al->map = NULL; if ((cpumode == PERF_RECORD_MISC_GUEST_USER || cpumode == PERF_RECORD_MISC_GUEST_KERNEL) && !perf_guest) - al->filtered = true; + al->filtered |= (1 << HIST_FILTER__GUEST); if ((cpumode == PERF_RECORD_MISC_USER || cpumode == PERF_RECORD_MISC_KERNEL) && !perf_host) - al->filtered = true; + al->filtered |= (1 << HIST_FILTER__HOST); return; } @@ -635,201 +778,90 @@ try_again: * in the whole kernel symbol list. */ if ((long long)al->addr < 0 && - cpumode == PERF_RECORD_MISC_KERNEL && + cpumode == PERF_RECORD_MISC_USER && machine && mg != &machine->kmaps) { 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 *self, - struct perf_session *session, u8 cpumode, - enum map_type type, pid_t pid, u64 addr, - struct addr_location *al, - symbol_filter_t filter) +void thread__find_addr_location(struct thread *thread, struct machine *machine, + u8 cpumode, enum map_type type, u64 addr, + struct addr_location *al) { - thread__find_addr_map(self, session, cpumode, type, pid, addr, al); + thread__find_addr_map(thread, machine, cpumode, type, addr, al); if (al->map != NULL) - al->sym = map__find_symbol(al->map, al->addr, filter); + al->sym = map__find_symbol(al->map, al->addr, + machine->symbol_filter); else al->sym = NULL; } -static void dso__calc_col_width(struct dso *self, struct hists *hists) -{ - if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep && - (!symbol_conf.dso_list || - strlist__has_entry(symbol_conf.dso_list, self->name))) { - u16 slen = dso__name_len(self); - hists__new_col_len(hists, HISTC_DSO, slen); - } - - self->slen_calculated = 1; -} - -int event__preprocess_sample(const event_t *self, struct perf_session *session, - struct addr_location *al, struct sample_data *data, - symbol_filter_t filter) +int perf_event__preprocess_sample(const union perf_event *event, + struct machine *machine, + struct addr_location *al, + struct perf_sample *sample) { - u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread; + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->tid); - event__parse_sample(self, session->sample_type, data); - - dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld cpu:%d\n", - self->header.misc, data->pid, data->tid, data->ip, - data->period, data->cpu); - - if (session->sample_type & PERF_SAMPLE_CALLCHAIN) { - unsigned int i; - - dump_printf("... chain: nr:%Lu\n", data->callchain->nr); - - if (!ip_callchain__valid(data->callchain, self)) { - pr_debug("call-chain problem with event, " - "skipping it.\n"); - goto out_filtered; - } - - if (dump_trace) { - for (i = 0; i < data->callchain->nr; i++) - dump_printf("..... %2d: %016Lx\n", - i, data->callchain->ips[i]); - } - } - thread = perf_session__findnew(session, self->ip.pid); if (thread == NULL) return -1; - if (symbol_conf.comm_list && - !strlist__has_entry(symbol_conf.comm_list, thread->comm)) - 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 the host machine? + * Have we already created the kernel maps for this machine? * * This should have happened earlier, when we processed the kernel MMAP * events, but for older perf.data files there was no such thing, so do * it now. */ if (cpumode == PERF_RECORD_MISC_KERNEL && - session->host_machine.vmlinux_maps[MAP__FUNCTION] == NULL) - machine__create_kernel_maps(&session->host_machine); + machine->vmlinux_maps[MAP__FUNCTION] == NULL) + machine__create_kernel_maps(machine); - thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION, - self->ip.pid, self->ip.ip, al); + thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, + sample->ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); - al->sym = NULL; - al->cpu = data->cpu; - - if (al->map) { - if (symbol_conf.dso_list && - (!al->map || !al->map->dso || - !(strlist__has_entry(symbol_conf.dso_list, - al->map->dso->short_name) || - (al->map->dso->short_name != al->map->dso->long_name && - strlist__has_entry(symbol_conf.dso_list, - al->map->dso->long_name))))) - goto out_filtered; - /* - * We have to do this here as we may have a dso with no symbol - * hit that has a name longer than the ones with symbols - * sampled. - */ - if (!sort_dso.elide && !al->map->dso->slen_calculated) - dso__calc_col_width(al->map->dso, &session->hists); - al->sym = map__find_symbol(al->map, al->addr, filter); - } else { - const unsigned int unresolved_col_width = BITS_PER_LONG / 4; - - if (hists__col_len(&session->hists, HISTC_DSO) < unresolved_col_width && - !symbol_conf.col_width_list_str && !symbol_conf.field_sep && - !symbol_conf.dso_list) - hists__set_col_len(&session->hists, HISTC_DSO, - unresolved_col_width); - } - - if (symbol_conf.sym_list && al->sym && - !strlist__has_entry(symbol_conf.sym_list, al->sym->name)) - goto out_filtered; - - return 0; - -out_filtered: - al->filtered = true; - return 0; -} - -int event__parse_sample(const event_t *event, u64 type, struct sample_data *data) -{ - const u64 *array = event->sample.array; - - if (type & PERF_SAMPLE_IP) { - data->ip = event->ip.ip; - array++; - } - - if (type & PERF_SAMPLE_TID) { - u32 *p = (u32 *)array; - data->pid = p[0]; - data->tid = p[1]; - array++; - } + if (thread__is_filtered(thread)) + al->filtered |= (1 << HIST_FILTER__THREAD); - if (type & PERF_SAMPLE_TIME) { - data->time = *array; - array++; - } - - if (type & PERF_SAMPLE_ADDR) { - data->addr = *array; - array++; - } - - data->id = -1ULL; - if (type & PERF_SAMPLE_ID) { - data->id = *array; - array++; - } - - if (type & PERF_SAMPLE_STREAM_ID) { - data->stream_id = *array; - array++; - } - - if (type & PERF_SAMPLE_CPU) { - u32 *p = (u32 *)array; - data->cpu = *p; - array++; - } else - data->cpu = -1; + al->sym = NULL; + al->cpu = sample->cpu; - if (type & PERF_SAMPLE_PERIOD) { - data->period = *array; - array++; - } + if (al->map) { + struct dso *dso = al->map->dso; - if (type & PERF_SAMPLE_READ) { - pr_debug("PERF_SAMPLE_READ is unsuported for now\n"); - return -1; - } + if (symbol_conf.dso_list && + (!dso || !(strlist__has_entry(symbol_conf.dso_list, + dso->short_name) || + (dso->short_name != dso->long_name && + strlist__has_entry(symbol_conf.dso_list, + dso->long_name))))) { + al->filtered |= (1 << HIST_FILTER__DSO); + } - if (type & PERF_SAMPLE_CALLCHAIN) { - data->callchain = (struct ip_callchain *)array; - array += 1 + data->callchain->nr; + al->sym = map__find_symbol(al->map, al->addr, + machine->symbol_filter); } - if (type & PERF_SAMPLE_RAW) { - u32 *p = (u32 *)array; - data->raw_size = *p; - p++; - data->raw_data = p; + if (symbol_conf.sym_list && + (!al->sym || !strlist__has_entry(symbol_conf.sym_list, + al->sym->name))) { + al->filtered |= (1 << HIST_FILTER__SYMBOL); } return 0; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 8e790dae702..e5dd40addb3 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -2,26 +2,34 @@ #define __PERF_RECORD_H #include <limits.h> +#include <stdio.h> #include "../perf.h" #include "map.h" +#include "build-id.h" +#include "perf_regs.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; + u32 prot; + u32 flags; char filename[PATH_MAX]; }; @@ -56,12 +64,86 @@ 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_IDENTIFIER) + +/* perf sample has 16 bits size limit */ +#define PERF_SAMPLE_MAX_SIZE (1 << 16) + struct sample_event { struct perf_event_header header; u64 array[]; }; -struct sample_data { +struct regs_dump { + u64 abi; + u64 mask; + u64 *regs; + + /* Cached values/mask filled by first register access. */ + u64 cache_regs[PERF_REGS_MAX]; + u64 cache_mask; +}; + +struct stack_dump { + u16 offset; + u64 size; + 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 ip_callchain { + u64 nr; + u64 ips[0]; +}; + +struct branch_flags { + u64 mispred:1; + u64 predicted:1; + u64 in_tx:1; + u64 abort:1; + u64 reserved:60; +}; + +struct branch_entry { + u64 from; + u64 to; + struct branch_flags flags; +}; + +struct branch_stack { + u64 nr; + struct branch_entry entries[0]; +}; + +struct perf_sample { u64 ip; u32 pid, tid; u64 time; @@ -69,24 +151,37 @@ struct sample_data { u64 id; u64 stream_id; u64 period; + u64 weight; + u64 transaction; u32 cpu; u32 raw_size; + u64 data_src; void *raw_data; struct ip_callchain *callchain; + struct branch_stack *branch_stack; + struct regs_dump user_regs; + struct stack_dump user_stack; + struct sample_read read; }; -#define BUILD_ID_SIZE 20 +#define PERF_MEM_DATA_SRC_NONE \ + (PERF_MEM_S(OP, NA) |\ + PERF_MEM_S(LVL, NA) |\ + PERF_MEM_S(SNOOP, NA) |\ + PERF_MEM_S(LOCK, NA) |\ + PERF_MEM_S(TLB, NA)) struct build_id_event { struct perf_event_header header; pid_t pid; - u8 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))]; + u8 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))]; char filename[]; }; 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, @@ -116,52 +211,106 @@ struct tracing_data_event { u32 size; }; -typedef union event_union { +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; struct tracing_data_event tracing_data; struct build_id_event build_id; -} event_t; +}; -void event__print_totals(void); +void perf_event__print_totals(void); -struct perf_session; +struct perf_tool; +struct thread_map; -typedef int (*event__handler_t)(event_t *event, struct perf_session *session); +typedef int (*perf_event__handler_t)(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); -int event__synthesize_thread(pid_t pid, event__handler_t process, - struct perf_session *session); -void event__synthesize_threads(event__handler_t process, - struct perf_session *session); -int event__synthesize_kernel_mmap(event__handler_t process, - struct perf_session *session, - struct machine *machine, - const char *symbol_name); +int perf_event__synthesize_thread_map(struct perf_tool *tool, + struct thread_map *threads, + perf_event__handler_t process, + struct machine *machine, bool mmap_data); +int perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, bool mmap_data); +int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine); -int event__synthesize_modules(event__handler_t process, - struct perf_session *session, - struct machine *machine); +int perf_event__synthesize_modules(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine); -int event__process_comm(event_t *self, struct perf_session *session); -int event__process_lost(event_t *self, struct perf_session *session); -int event__process_mmap(event_t *self, struct perf_session *session); -int event__process_task(event_t *self, struct perf_session *session); -int event__process(event_t *event, struct perf_session *session); +int perf_event__process_comm(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process_lost(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process_mmap(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process_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, + struct machine *machine); +int perf_event__process_exit(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); struct addr_location; -int event__preprocess_sample(const event_t *self, struct perf_session *session, - struct addr_location *al, struct sample_data *data, - symbol_filter_t filter); -int event__parse_sample(const event_t *event, u64 type, struct sample_data *data); -extern const char *event__name[]; +int perf_event__preprocess_sample(const union perf_event *event, + struct machine *machine, + struct addr_location *al, + 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 read_format); +int perf_event__synthesize_sample(union perf_event *event, u64 type, + u64 read_format, + const struct perf_sample *sample, + bool swapped); + +int perf_event__synthesize_mmap_events(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data); + +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); + +u64 kallsyms__get_function_start(const char *kallsyms_filename, + const char *symbol_name); #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c new file mode 100644 index 00000000000..59ef2802fcf --- /dev/null +++ b/tools/perf/util/evlist.c @@ -0,0 +1,1245 @@ +/* + * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Parts came from builtin-{top,stat,record}.c, see those files for further + * copyright notes. + * + * Released under the GPL v2. (and only v2, not any later version) + */ +#include "util.h" +#include <api/fs/debugfs.h> +#include <poll.h> +#include "cpumap.h" +#include "thread_map.h" +#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> + +#include <linux/bitops.h> +#include <linux/hash.h> + +#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) +#define SID(e, x, y) xyarray__entry(e->sample_id, x, y) + +void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, + struct thread_map *threads) +{ + int i; + + for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i) + INIT_HLIST_HEAD(&evlist->heads[i]); + INIT_LIST_HEAD(&evlist->entries); + perf_evlist__set_maps(evlist, cpus, threads); + evlist->workload.pid = -1; +} + +struct perf_evlist *perf_evlist__new(void) +{ + struct perf_evlist *evlist = zalloc(sizeof(*evlist)); + + if (evlist != NULL) + perf_evlist__init(evlist, NULL, NULL); + + return evlist; +} + +struct perf_evlist *perf_evlist__new_default(void) +{ + struct perf_evlist *evlist = perf_evlist__new(); + + if (evlist && perf_evlist__add_default(evlist)) { + perf_evlist__delete(evlist); + evlist = NULL; + } + + return evlist; +} + +/** + * 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; + + evlist__for_each(evlist, evsel) + perf_evsel__calc_id_pos(evsel); + + perf_evlist__set_id_pos(evlist); +} + +static void perf_evlist__purge(struct perf_evlist *evlist) +{ + struct perf_evsel *pos, *n; + + evlist__for_each_safe(evlist, n, pos) { + list_del_init(&pos->node); + perf_evsel__delete(pos); + } + + evlist->nr_entries = 0; +} + +void perf_evlist__exit(struct perf_evlist *evlist) +{ + zfree(&evlist->mmap); + zfree(&evlist->pollfd); +} + +void perf_evlist__delete(struct perf_evlist *evlist) +{ + perf_evlist__munmap(evlist); + perf_evlist__close(evlist); + cpu_map__delete(evlist->cpus); + thread_map__delete(evlist->threads); + evlist->cpus = NULL; + evlist->threads = NULL; + perf_evlist__purge(evlist); + perf_evlist__exit(evlist); + free(evlist); +} + +void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) +{ + list_add_tail(&entry->node, &evlist->entries); + entry->idx = 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) +{ + struct perf_evsel *evsel, *leader; + + leader = list_entry(list->next, struct perf_evsel, node); + evsel = list_entry(list->prev, struct perf_evsel, node); + + leader->nr_members = evsel->idx - leader->idx + 1; + + __evlist__for_each(list, evsel) { + evsel->leader = leader; + } +} + +void perf_evlist__set_leader(struct perf_evlist *evlist) +{ + if (evlist->nr_entries) { + evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0; + __perf_evlist__set_leader(&evlist->entries); + } +} + +int perf_evlist__add_default(struct perf_evlist *evlist) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + }; + struct perf_evsel *evsel; + + event_attr_init(&attr); + + evsel = perf_evsel__new(&attr); + if (evsel == NULL) + goto error; + + /* use strdup() because free(evsel) assumes name is allocated */ + evsel->name = strdup("cycles"); + if (!evsel->name) + goto error_free; + + perf_evlist__add(evlist, evsel); + return 0; +error_free: + perf_evsel__delete(evsel); +error: + return -ENOMEM; +} + +static int perf_evlist__add_attrs(struct perf_evlist *evlist, + struct perf_event_attr *attrs, size_t nr_attrs) +{ + struct perf_evsel *evsel, *n; + LIST_HEAD(head); + size_t i; + + for (i = 0; i < nr_attrs; i++) { + evsel = perf_evsel__new_idx(attrs + i, evlist->nr_entries + i); + if (evsel == NULL) + goto out_delete_partial_list; + list_add_tail(&evsel->node, &head); + } + + perf_evlist__splice_list_tail(evlist, &head, nr_attrs); + + return 0; + +out_delete_partial_list: + __evlist__for_each_safe(&head, n, evsel) + perf_evsel__delete(evsel); + return -1; +} + +int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, + struct perf_event_attr *attrs, size_t nr_attrs) +{ + size_t i; + + for (i = 0; i < nr_attrs; i++) + event_attr_init(attrs + i); + + return perf_evlist__add_attrs(evlist, attrs, nr_attrs); +} + +struct perf_evsel * +perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type == PERF_TYPE_TRACEPOINT && + (int)evsel->attr.config == id) + return evsel; + } + + return NULL; +} + +struct perf_evsel * +perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, + const char *name) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + 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) +{ + struct perf_evsel *evsel = perf_evsel__newtp(sys, name); + + if (evsel == NULL) + return -1; + + evsel->handler = handler; + perf_evlist__add(evlist, evsel); + return 0; +} + +void perf_evlist__disable(struct perf_evlist *evlist) +{ + int cpu, thread; + struct perf_evsel *pos; + int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_threads = thread_map__nr(evlist->threads); + + for (cpu = 0; cpu < nr_cpus; cpu++) { + evlist__for_each(evlist, pos) { + if (!perf_evsel__is_group_leader(pos) || !pos->fd) + continue; + for (thread = 0; thread < nr_threads; thread++) + ioctl(FD(pos, cpu, thread), + PERF_EVENT_IOC_DISABLE, 0); + } + } +} + +void perf_evlist__enable(struct perf_evlist *evlist) +{ + int cpu, thread; + struct perf_evsel *pos; + int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_threads = thread_map__nr(evlist->threads); + + for (cpu = 0; cpu < nr_cpus; cpu++) { + evlist__for_each(evlist, pos) { + if (!perf_evsel__is_group_leader(pos) || !pos->fd) + continue; + for (thread = 0; thread < nr_threads; thread++) + ioctl(FD(pos, cpu, thread), + PERF_EVENT_IOC_ENABLE, 0); + } + } +} + +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); + int nr_threads = thread_map__nr(evlist->threads); + int nfds = nr_cpus * nr_threads * evlist->nr_entries; + evlist->pollfd = malloc(sizeof(struct pollfd) * nfds); + return evlist->pollfd != NULL ? 0 : -ENOMEM; +} + +void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd) +{ + fcntl(fd, F_SETFL, O_NONBLOCK); + evlist->pollfd[evlist->nr_fds].fd = fd; + evlist->pollfd[evlist->nr_fds].events = POLLIN; + evlist->nr_fds++; +} + +static void perf_evlist__id_hash(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, u64 id) +{ + int hash; + struct perf_sample_id *sid = SID(evsel, cpu, thread); + + sid->id = id; + sid->evsel = evsel; + hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS); + hlist_add_head(&sid->node, &evlist->heads[hash]); +} + +void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, + int cpu, int thread, u64 id) +{ + perf_evlist__id_hash(evlist, evsel, cpu, thread, id); + evsel->id[evsel->ids++] = id; +} + +static int perf_evlist__id_add_fd(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, int fd) +{ + 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) + return -1; + + if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + ++id_idx; + if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + ++id_idx; + + id = read_data[id_idx]; + + add: + perf_evlist__id_add(evlist, evsel, cpu, thread, id); + return 0; +} + +struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id) +{ + struct hlist_head *head; + struct perf_sample_id *sid; + int hash; + + 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; + + 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); + + 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]; + unsigned int head = perf_mmap__read_head(md); + unsigned int old = md->prev; + unsigned char *data = md->base + page_size; + union perf_event *event = NULL; + + if (evlist->overwrite) { + /* + * If we're further behind than half the buffer, there's a chance + * the writer will bite our tail and mess up the samples under us. + * + * If we somehow ended up ahead of the head, we got messed up. + * + * In either case, truncate and restart at head. + */ + int diff = head - old; + if (diff > md->mask / 2 || diff < 0) { + fprintf(stderr, "WARNING: failed to keep up with mmap data.\n"); + + /* + * head points to a known good entry, start there. + */ + old = head; + } + } + + if (old != head) { + size_t size; + + event = (union perf_event *)&data[old & md->mask]; + size = event->header.size; + + /* + * Event straddles the mmap boundary -- header should always + * be inside due to u64 alignment of output. + */ + 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; + + do { + cpy = min(md->mask + 1 - (offset & md->mask), len); + memcpy(dst, &data[offset & md->mask], cpy); + offset += cpy; + dst += cpy; + len -= cpy; + } while (len); + + event = (union perf_event *) md->event_copy; + } + + old += size; + } + + md->prev = old; + + 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); + } +} + +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; + + if (evlist->mmap == NULL) + return; + + for (i = 0; i < evlist->nr_mmaps; i++) + __perf_evlist__munmap(evlist, i); + + zfree(&evlist->mmap); +} + +static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) +{ + evlist->nr_mmaps = cpu_map__nr(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; +} + +static int __perf_evlist__mmap(struct perf_evlist *evlist, + int idx, int prot, int mask, int fd) +{ + evlist->mmap[idx].prev = 0; + evlist->mmap[idx].mask = mask; + evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot, + MAP_SHARED, fd, 0); + if (evlist->mmap[idx].base == MAP_FAILED) { + pr_debug2("failed to mmap perf event ring buffer, error %d\n", + errno); + evlist->mmap[idx].base = NULL; + return -1; + } + + perf_evlist__add_pollfd(evlist, fd); + return 0; +} + +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; + + evlist__for_each(evlist, evsel) { + 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++) { + 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++) + __perf_evlist__munmap(evlist, cpu); + return -1; +} + +static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, + int mask) +{ + 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; + + 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++) + __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; +} + +static long parse_pages_arg(const char *str, unsigned long min, + unsigned long max) +{ + unsigned long pages, val; + 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 }, + }; + + if (str == NULL) + return -EINVAL; + + val = parse_tag_value(str, tags); + if (val != (unsigned long) -1) { + /* we got file size value */ + pages = PERF_ALIGN(val, page_size) / page_size; + } else { + /* we got pages count value */ + char *eptr; + pages = strtoul(str, &eptr, 10); + if (*eptr != '\0') + return -EINVAL; + } + + if (pages == 0 && min == 0) { + /* leave number of pages at 0 */ + } else if (!is_power_of_2(pages)) { + /* round pages up to next power of 2 */ + pages = next_pow2_l(pages); + if (!pages) + return -EINVAL; + pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n", + pages * page_size, pages); + } + + if (pages > max) + return -EINVAL; + + return pages; +} + +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 max = UINT_MAX; + long pages; + + if (max > SIZE_MAX / page_size) + max = SIZE_MAX / page_size; + + pages = parse_pages_arg(str, 1, max); + if (pages < 0) { + pr_err("Invalid argument for --mmap_pages/-m\n"); + return -1; + } + + *mmap_pages = pages; + return 0; +} + +/** + * 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 consumption using + * perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this + * automatically. + * + * Return: %0 on success, negative error code otherwise. + */ +int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, + bool overwrite) +{ + struct perf_evsel *evsel; + const struct cpu_map *cpus = evlist->cpus; + const struct thread_map *threads = evlist->threads; + int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask; + + if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) + return -ENOMEM; + + if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0) + return -ENOMEM; + + evlist->overwrite = overwrite; + evlist->mmap_len = perf_evlist__mmap_size(pages); + pr_debug("mmap size %zuB\n", evlist->mmap_len); + mask = evlist->mmap_len - page_size - 1; + + evlist__for_each(evlist, evsel) { + if ((evsel->attr.read_format & PERF_FORMAT_ID) && + evsel->sample_id == NULL && + perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0) + return -ENOMEM; + } + + if (cpu_map__empty(cpus)) + return perf_evlist__mmap_per_thread(evlist, prot, mask); + + return perf_evlist__mmap_per_cpu(evlist, prot, mask); +} + +int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) +{ + evlist->threads = thread_map__new_str(target->pid, target->tid, + target->uid); + + if (evlist->threads == NULL) + return -1; + + if (target__uses_dummy_map(target)) + evlist->cpus = cpu_map__dummy_new(); + else + evlist->cpus = cpu_map__new(target->cpu_list); + + if (evlist->cpus == NULL) + goto out_delete_threads; + + return 0; + +out_delete_threads: + thread_map__delete(evlist->threads); + return -1; +} + +int perf_evlist__apply_filters(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + int err = 0; + const int ncpus = cpu_map__nr(evlist->cpus), + nthreads = thread_map__nr(evlist->threads); + + evlist__for_each(evlist, evsel) { + if (evsel->filter == NULL) + continue; + + err = perf_evsel__set_filter(evsel, ncpus, nthreads, evsel->filter); + if (err) + break; + } + + return err; +} + +int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) +{ + struct perf_evsel *evsel; + int err = 0; + const int ncpus = cpu_map__nr(evlist->cpus), + nthreads = thread_map__nr(evlist->threads); + + evlist__for_each(evlist, evsel) { + err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter); + if (err) + break; + } + + return err; +} + +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; + + evlist__for_each(evlist, pos) { + 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; + + evlist__for_each(evlist, evsel) + 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; + + evlist__for_each(evlist, pos) { + 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__read_format(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + return first->attr.read_format; +} + +u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + struct perf_sample *data; + u64 sample_type; + u16 size = 0; + + if (!first->attr.sample_id_all) + goto out; + + sample_type = first->attr.sample_type; + + if (sample_type & PERF_SAMPLE_TID) + size += sizeof(data->tid) * 2; + + if (sample_type & PERF_SAMPLE_TIME) + size += sizeof(data->time); + + if (sample_type & PERF_SAMPLE_ID) + size += sizeof(data->id); + + if (sample_type & PERF_SAMPLE_STREAM_ID) + size += sizeof(data->stream_id); + + if (sample_type & PERF_SAMPLE_CPU) + size += sizeof(data->cpu) * 2; + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + size += sizeof(data->id); +out: + return size; +} + +bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; + + evlist__for_each_continue(evlist, pos) { + if (first->attr.sample_id_all != pos->attr.sample_id_all) + return false; + } + + return true; +} + +bool perf_evlist__sample_id_all(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + return first->attr.sample_id_all; +} + +void perf_evlist__set_selected(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + evlist->selected = evsel; +} + +void perf_evlist__close(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + int ncpus = cpu_map__nr(evlist->cpus); + int nthreads = thread_map__nr(evlist->threads); + int n; + + evlist__for_each_reverse(evlist, evsel) { + n = evsel->cpus ? evsel->cpus->nr : ncpus; + perf_evsel__close(evsel, n, nthreads); + } +} + +int perf_evlist__open(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + int err; + + perf_evlist__update_id_pos(evlist); + + evlist__for_each(evlist, evsel) { + err = perf_evsel__open(evsel, evlist->cpus, evlist->threads); + if (err < 0) + goto out_err; + } + + return 0; +out_err: + perf_evlist__close(evlist); + errno = -err; + return err; +} + +int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *target, + const char *argv[], bool pipe_output, + void (*exec_error)(int signo, siginfo_t *info, void *ucontext)) +{ + int child_ready_pipe[2], go_pipe[2]; + char bf; + + if (pipe(child_ready_pipe) < 0) { + perror("failed to create 'ready' pipe"); + return -1; + } + + if (pipe(go_pipe) < 0) { + perror("failed to create 'go' pipe"); + goto out_close_ready_pipe; + } + + evlist->workload.pid = fork(); + if (evlist->workload.pid < 0) { + perror("failed to fork"); + goto out_close_pipes; + } + + if (!evlist->workload.pid) { + if (pipe_output) + dup2(2, 1); + + signal(SIGTERM, SIG_DFL); + + close(child_ready_pipe[0]); + close(go_pipe[1]); + fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); + + /* + * Tell the parent we're ready to go + */ + close(child_ready_pipe[1]); + + /* + * Wait until the parent tells us to go. + */ + if (read(go_pipe[0], &bf, 1) == -1) + perror("unable to read pipe"); + + execvp(argv[0], (char **)argv); + + if (exec_error) { + union sigval val; + + val.sival_int = errno; + if (sigqueue(getppid(), SIGUSR1, val)) + perror(argv[0]); + } else + perror(argv[0]); + exit(-1); + } + + if (exec_error) { + struct sigaction act = { + .sa_flags = SA_SIGINFO, + .sa_sigaction = exec_error, + }; + sigaction(SIGUSR1, &act, NULL); + } + + if (target__none(target)) + evlist->threads->map[0] = evlist->workload.pid; + + close(child_ready_pipe[1]); + close(go_pipe[0]); + /* + * wait for child to settle + */ + if (read(child_ready_pipe[0], &bf, 1) == -1) { + perror("unable to read pipe"); + goto out_close_pipes; + } + + fcntl(go_pipe[1], F_SETFD, FD_CLOEXEC); + evlist->workload.cork_fd = go_pipe[1]; + close(child_ready_pipe[0]); + return 0; + +out_close_pipes: + close(go_pipe[0]); + close(go_pipe[1]); +out_close_ready_pipe: + close(child_ready_pipe[0]); + close(child_ready_pipe[1]); + return -1; +} + +int perf_evlist__start_workload(struct perf_evlist *evlist) +{ + if (evlist->workload.cork_fd > 0) { + char bf = 0; + int ret; + /* + * Remove the cork, let it rip! + */ + ret = write(evlist->workload.cork_fd, &bf, 1); + if (ret < 0) + perror("enable to write to pipe"); + + close(evlist->workload.cork_fd); + return ret; + } + + return 0; +} + +int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, + struct perf_sample *sample) +{ + struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + + if (!evsel) + return -EFAULT; + return perf_evsel__parse_sample(evsel, event, sample); +} + +size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) +{ + struct perf_evsel *evsel; + size_t printed = 0; + + evlist__for_each(evlist, evsel) { + printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "", + perf_evsel__name(evsel)); + } + + 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); + + value = perf_event_paranoid(); + + 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; +} + +void perf_evlist__to_front(struct perf_evlist *evlist, + struct perf_evsel *move_evsel) +{ + struct perf_evsel *evsel, *n; + LIST_HEAD(move); + + if (move_evsel == perf_evlist__first(evlist)) + return; + + evlist__for_each_safe(evlist, n, evsel) { + if (evsel->leader == move_evsel->leader) + list_move_tail(&evsel->node, &move); + } + + list_splice(&move, &evlist->entries); +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h new file mode 100644 index 00000000000..f5173cd6369 --- /dev/null +++ b/tools/perf/util/evlist.h @@ -0,0 +1,265 @@ +#ifndef __PERF_EVLIST_H +#define __PERF_EVLIST_H 1 + +#include <linux/list.h> +#include <stdio.h> +#include "../perf.h" +#include "event.h" +#include "evsel.h" +#include "util.h" +#include <unistd.h> + +struct pollfd; +struct thread_map; +struct cpu_map; +struct record_opts; + +#define PERF_EVLIST__HLIST_BITS 8 +#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) + +struct perf_mmap { + void *base; + int mask; + unsigned int prev; + char event_copy[PERF_SAMPLE_MAX_SIZE]; +}; + +struct perf_evlist { + struct list_head entries; + struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; + int nr_entries; + int nr_groups; + int nr_fds; + int nr_mmaps; + size_t mmap_len; + int id_pos; + int is_pos; + u64 combined_sample_type; + struct { + int cork_fd; + pid_t pid; + } workload; + bool overwrite; + struct perf_mmap *mmap; + struct pollfd *pollfd; + struct thread_map *threads; + struct cpu_map *cpus; + struct perf_evsel *selected; +}; + +struct perf_evsel_str_handler { + const char *name; + void *handler; +}; + +struct perf_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); +void perf_evlist__delete(struct perf_evlist *evlist); + +void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry); +int perf_evlist__add_default(struct perf_evlist *evlist); +int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, + struct perf_event_attr *attrs, size_t nr_attrs); + +#define perf_evlist__add_default_attrs(evlist, array) \ + __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) + +int perf_evlist__add_newtp(struct perf_evlist *evlist, + const char *sys, const char *name, void *handler); + +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); + +void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); + +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); + +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 record_opts *opts); +int record_opts__config(struct record_opts *opts); + +int perf_evlist__prepare_workload(struct perf_evlist *evlist, + struct target *target, + const char *argv[], bool pipe_output, + void (*exec_error)(int signo, siginfo_t *info, + void *ucontext)); +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); + +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); + +static inline void perf_evlist__set_maps(struct perf_evlist *evlist, + struct cpu_map *cpus, + struct thread_map *threads) +{ + evlist->cpus = cpus; + evlist->threads = threads; +} + +int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target); +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__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); + +int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, + struct perf_sample *sample); + +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, + int nr_entries); + +static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist) +{ + return list_entry(evlist->entries.next, struct perf_evsel, node); +} + +static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) +{ + return list_entry(evlist->entries.prev, struct perf_evsel, node); +} + +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 = ACCESS_ONCE(pc->data_head); + rmb(); + return head; +} + +static inline void perf_mmap__write_tail(struct perf_mmap *md, + unsigned long tail) +{ + struct perf_event_mmap_page *pc = md->base; + + /* + * ensure all reads are done before we write the tail out. + */ + mb(); + pc->data_tail = tail; +} + +bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str); +void perf_evlist__to_front(struct perf_evlist *evlist, + struct perf_evsel *move_evsel); + +/** + * __evlist__for_each - iterate thru all the evsels + * @list: list_head instance to iterate + * @evsel: struct evsel iterator + */ +#define __evlist__for_each(list, evsel) \ + list_for_each_entry(evsel, list, node) + +/** + * evlist__for_each - iterate thru all the evsels + * @evlist: evlist instance to iterate + * @evsel: struct evsel iterator + */ +#define evlist__for_each(evlist, evsel) \ + __evlist__for_each(&(evlist)->entries, evsel) + +/** + * __evlist__for_each_continue - continue iteration thru all the evsels + * @list: list_head instance to iterate + * @evsel: struct evsel iterator + */ +#define __evlist__for_each_continue(list, evsel) \ + list_for_each_entry_continue(evsel, list, node) + +/** + * evlist__for_each_continue - continue iteration thru all the evsels + * @evlist: evlist instance to iterate + * @evsel: struct evsel iterator + */ +#define evlist__for_each_continue(evlist, evsel) \ + __evlist__for_each_continue(&(evlist)->entries, evsel) + +/** + * __evlist__for_each_reverse - iterate thru all the evsels in reverse order + * @list: list_head instance to iterate + * @evsel: struct evsel iterator + */ +#define __evlist__for_each_reverse(list, evsel) \ + list_for_each_entry_reverse(evsel, list, node) + +/** + * evlist__for_each_reverse - iterate thru all the evsels in reverse order + * @evlist: evlist instance to iterate + * @evsel: struct evsel iterator + */ +#define evlist__for_each_reverse(evlist, evsel) \ + __evlist__for_each_reverse(&(evlist)->entries, evsel) + +/** + * __evlist__for_each_safe - safely iterate thru all the evsels + * @list: list_head instance to iterate + * @tmp: struct evsel temp iterator + * @evsel: struct evsel iterator + */ +#define __evlist__for_each_safe(list, tmp, evsel) \ + list_for_each_entry_safe(evsel, tmp, list, node) + +/** + * evlist__for_each_safe - safely iterate thru all the evsels + * @evlist: evlist instance to iterate + * @evsel: struct evsel iterator + * @tmp: struct evsel temp iterator + */ +#define evlist__for_each_safe(evlist, tmp, evsel) \ + __evlist__for_each_safe(&(evlist)->entries, tmp, evsel) + +#endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c new file mode 100644 index 00000000000..8606175fe1e --- /dev/null +++ b/tools/perf/util/evsel.c @@ -0,0 +1,2036 @@ +/* + * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Parts came from builtin-{top,stat,record}.c, see those files for further + * copyright notes. + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include <byteswap.h> +#include <linux/bitops.h> +#include <api/fs/debugfs.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 "perf_regs.h" +#include "debug.h" +#include "trace-event.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)) + +int __perf_evsel__sample_size(u64 sample_type) +{ + u64 mask = sample_type & PERF_SAMPLE_MASK; + int size = 0; + int i; + + for (i = 0; i < 64; i++) { + if (mask & (1ULL << i)) + size++; + } + + size *= sizeof(u64); + + 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)); + hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; + hists->entries_in = &hists->entries_in_array[0]; + hists->entries_collapsed = RB_ROOT; + hists->entries = RB_ROOT; + pthread_mutex_init(&hists->lock, NULL); +} + +void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit) +{ + 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__reset_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit) +{ + 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, + bool can_sample_identifier) +{ + 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; +} + +void perf_evsel__init(struct perf_evsel *evsel, + struct perf_event_attr *attr, int idx) +{ + evsel->idx = idx; + evsel->attr = *attr; + evsel->leader = evsel; + evsel->unit = ""; + evsel->scale = 1.0; + 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_idx(struct perf_event_attr *attr, int idx) +{ + struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + + if (evsel != NULL) + perf_evsel__init(evsel, attr, idx); + + return evsel; +} + +struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx) +{ + struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + + if (evsel != NULL) { + struct perf_event_attr attr = { + .type = PERF_TYPE_TRACEPOINT, + .sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), + }; + + if (asprintf(&evsel->name, "%s:%s", sys, name) < 0) + goto out_free; + + evsel->tp_format = trace_event__tp_format(sys, name); + if (evsel->tp_format == NULL) + goto out_free; + + event_attr_init(&attr); + attr.config = evsel->tp_format->id; + attr.sample_period = 1; + perf_evsel__init(evsel, &attr, idx); + } + + return evsel; + +out_free: + zfree(&evsel->name); + free(evsel); + return NULL; +} + +const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = { + "cycles", + "instructions", + "cache-references", + "cache-misses", + "branches", + "branch-misses", + "bus-cycles", + "stalled-cycles-frontend", + "stalled-cycles-backend", + "ref-cycles", +}; + +static const char *__perf_evsel__hw_name(u64 config) +{ + if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config]) + return perf_evsel__hw_names[config]; + + return "unknown-hardware"; +} + +static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size) +{ + int colon = 0, r = 0; + struct perf_event_attr *attr = &evsel->attr; + bool exclude_guest_default = false; + +#define MOD_PRINT(context, mod) do { \ + if (!attr->exclude_##context) { \ + if (!colon) colon = ++r; \ + r += scnprintf(bf + r, size - r, "%c", mod); \ + } } while(0) + + if (attr->exclude_kernel || attr->exclude_user || attr->exclude_hv) { + MOD_PRINT(kernel, 'k'); + MOD_PRINT(user, 'u'); + MOD_PRINT(hv, 'h'); + exclude_guest_default = true; + } + + if (attr->precise_ip) { + if (!colon) + colon = ++r; + r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp"); + exclude_guest_default = true; + } + + if (attr->exclude_host || attr->exclude_guest == exclude_guest_default) { + MOD_PRINT(host, 'H'); + MOD_PRINT(guest, 'G'); + } +#undef MOD_PRINT + if (colon) + bf[colon - 1] = ':'; + return r; +} + +static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config)); + return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); +} + +const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = { + "cpu-clock", + "task-clock", + "page-faults", + "context-switches", + "cpu-migrations", + "minor-faults", + "major-faults", + "alignment-faults", + "emulation-faults", + "dummy", +}; + +static const char *__perf_evsel__sw_name(u64 config) +{ + if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config]) + return perf_evsel__sw_names[config]; + return "unknown-software"; +} + +static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config)); + return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); +} + +static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type) +{ + int r; + + r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr); + + if (type & HW_BREAKPOINT_R) + r += scnprintf(bf + r, size - r, "r"); + + if (type & HW_BREAKPOINT_W) + r += scnprintf(bf + r, size - r, "w"); + + if (type & HW_BREAKPOINT_X) + r += scnprintf(bf + r, size - r, "x"); + + return r; +} + +static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + struct perf_event_attr *attr = &evsel->attr; + int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type); + return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); +} + +const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] + [PERF_EVSEL__MAX_ALIASES] = { + { "L1-dcache", "l1-d", "l1d", "L1-data", }, + { "L1-icache", "l1-i", "l1i", "L1-instruction", }, + { "LLC", "L2", }, + { "dTLB", "d-tlb", "Data-TLB", }, + { "iTLB", "i-tlb", "Instruction-TLB", }, + { "branch", "branches", "bpu", "btb", "bpc", }, + { "node", }, +}; + +const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_EVSEL__MAX_ALIASES] = { + { "load", "loads", "read", }, + { "store", "stores", "write", }, + { "prefetch", "prefetches", "speculative-read", "speculative-load", }, +}; + +const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] + [PERF_EVSEL__MAX_ALIASES] = { + { "refs", "Reference", "ops", "access", }, + { "misses", "miss", }, +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x +#define CACHE_READ (1 << C(OP_READ)) +#define CACHE_WRITE (1 << C(OP_WRITE)) +#define CACHE_PREFETCH (1 << C(OP_PREFETCH)) +#define COP(x) (1 << x) + +/* + * cache operartion stat + * L1I : Read and prefetch only + * ITLB and BPU : Read-only + */ +static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = { + [C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(L1I)] = (CACHE_READ | CACHE_PREFETCH), + [C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(ITLB)] = (CACHE_READ), + [C(BPU)] = (CACHE_READ), + [C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), +}; + +bool perf_evsel__is_cache_op_valid(u8 type, u8 op) +{ + if (perf_evsel__hw_cache_stat[type] & COP(op)) + return true; /* valid */ + else + return false; /* invalid */ +} + +int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, + char *bf, size_t size) +{ + if (result) { + return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0], + perf_evsel__hw_cache_op[op][0], + perf_evsel__hw_cache_result[result][0]); + } + + return scnprintf(bf, size, "%s-%s", perf_evsel__hw_cache[type][0], + perf_evsel__hw_cache_op[op][1]); +} + +static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size) +{ + u8 op, result, type = (config >> 0) & 0xff; + const char *err = "unknown-ext-hardware-cache-type"; + + if (type > PERF_COUNT_HW_CACHE_MAX) + goto out_err; + + op = (config >> 8) & 0xff; + err = "unknown-ext-hardware-cache-op"; + if (op > PERF_COUNT_HW_CACHE_OP_MAX) + goto out_err; + + result = (config >> 16) & 0xff; + err = "unknown-ext-hardware-cache-result"; + if (result > PERF_COUNT_HW_CACHE_RESULT_MAX) + goto out_err; + + err = "invalid-cache"; + if (!perf_evsel__is_cache_op_valid(type, op)) + goto out_err; + + return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size); +out_err: + return scnprintf(bf, size, "%s", err); +} + +static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size); + return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); +} + +static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config); + return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); +} + +const char *perf_evsel__name(struct perf_evsel *evsel) +{ + char bf[128]; + + if (evsel->name) + return evsel->name; + + switch (evsel->attr.type) { + case PERF_TYPE_RAW: + perf_evsel__raw_name(evsel, bf, sizeof(bf)); + break; + + case PERF_TYPE_HARDWARE: + perf_evsel__hw_name(evsel, bf, sizeof(bf)); + break; + + case PERF_TYPE_HW_CACHE: + perf_evsel__hw_cache_name(evsel, bf, sizeof(bf)); + break; + + case PERF_TYPE_SOFTWARE: + perf_evsel__sw_name(evsel, bf, sizeof(bf)); + break; + + case PERF_TYPE_TRACEPOINT: + scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint"); + break; + + case PERF_TYPE_BREAKPOINT: + perf_evsel__bp_name(evsel, bf, sizeof(bf)); + break; + + default: + scnprintf(bf, sizeof(bf), "unknown attr type: %d", + evsel->attr.type); + break; + } + + evsel->name = strdup(bf); + + return evsel->name ?: "unknown"; +} + +const char *perf_evsel__group_name(struct perf_evsel *evsel) +{ + return evsel->group_name ?: "anon group"; +} + +int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) +{ + int ret; + struct perf_evsel *pos; + const char *group_name = perf_evsel__group_name(evsel); + + ret = scnprintf(buf, size, "%s", group_name); + + ret += scnprintf(buf + ret, size - ret, " { %s", + perf_evsel__name(evsel)); + + for_each_group_member(pos, evsel) + ret += scnprintf(buf + ret, size - ret, ", %s", + perf_evsel__name(pos)); + + ret += scnprintf(buf + ret, size - ret, " }"); + + return ret; +} + +static void +perf_evsel__config_callgraph(struct perf_evsel *evsel, + struct record_opts *opts) +{ + bool function = perf_evsel__is_function_event(evsel); + struct perf_event_attr *attr = &evsel->attr; + + perf_evsel__set_sample_bit(evsel, CALLCHAIN); + + if (opts->call_graph == CALLCHAIN_DWARF) { + if (!function) { + perf_evsel__set_sample_bit(evsel, REGS_USER); + perf_evsel__set_sample_bit(evsel, STACK_USER); + attr->sample_regs_user = PERF_REGS_MASK; + attr->sample_stack_user = opts->stack_dump_size; + attr->exclude_callchain_user = 1; + } else { + pr_info("Cannot use DWARF unwind for function trace event," + " falling back to framepointers.\n"); + } + } + + if (function) { + pr_info("Disabling user space callchains for function trace event.\n"); + attr->exclude_callchain_user = 1; + } +} + +/* + * The enable_on_exec/disabled value strategy: + * + * 1) For any type of traced program: + * - all independent events and group leaders are disabled + * - all group members are enabled + * + * Group members are ruled by group leaders. They need to + * be enabled, because the group scheduling relies on that. + * + * 2) For traced programs executed by perf: + * - all independent events and group leaders have + * enable_on_exec set + * - we don't specifically enable or disable any event during + * the record command + * + * Independent events and group leaders are initially disabled + * and get enabled by exec. Group members are ruled by group + * leaders as stated in 1). + * + * 3) For traced programs attached by perf (pid/tid): + * - we specifically enable or disable all events during + * the record command + * + * When attaching events to already running traced we + * enable/disable events specifically, as there's no + * initial traced exec call. + */ +void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) +{ + struct perf_evsel *leader = evsel->leader; + struct perf_event_attr *attr = &evsel->attr; + int track = !evsel->idx; /* only the first counter needs these */ + bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread; + + attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1; + attr->inherit = !opts->no_inherit; + + 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 have a default interval. But keep + * it a weak assumption overridable by the user. + */ + if (!attr->sample_period || (opts->user_freq != UINT_MAX || + opts->user_interval != ULLONG_MAX)) { + if (opts->freq) { + perf_evsel__set_sample_bit(evsel, PERIOD); + attr->freq = 1; + attr->sample_freq = opts->freq; + } else { + attr->sample_period = opts->default_interval; + } + } + + /* + * 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; + + if (opts->inherit_stat) + attr->inherit_stat = 1; + + if (opts->sample_address) { + perf_evsel__set_sample_bit(evsel, ADDR); + attr->mmap_data = track; + } + + if (opts->call_graph_enabled) + perf_evsel__config_callgraph(evsel, opts); + + if (target__has_cpu(&opts->target)) + perf_evsel__set_sample_bit(evsel, CPU); + + if (opts->period) + perf_evsel__set_sample_bit(evsel, PERIOD); + + if (!perf_missing_features.sample_id_all && + (opts->sample_time || !opts->no_inherit || + target__has_cpu(&opts->target) || per_cpu)) + perf_evsel__set_sample_bit(evsel, TIME); + + if (opts->raw_samples) { + perf_evsel__set_sample_bit(evsel, TIME); + perf_evsel__set_sample_bit(evsel, RAW); + perf_evsel__set_sample_bit(evsel, CPU); + } + + if (opts->sample_address) + perf_evsel__set_sample_bit(evsel, DATA_SRC); + + if (opts->no_buffering) { + attr->watermark = 0; + attr->wakeup_events = 1; + } + if (opts->branch_stack) { + perf_evsel__set_sample_bit(evsel, BRANCH_STACK); + attr->branch_sample_type = opts->branch_stack; + } + + if (opts->sample_weight) + perf_evsel__set_sample_bit(evsel, WEIGHT); + + attr->mmap = track; + attr->mmap2 = track && !perf_missing_features.mmap2; + attr->comm = track; + + if (opts->sample_transaction) + perf_evsel__set_sample_bit(evsel, TRANSACTION); + + /* + * XXX see the function comment above + * + * Disabling only independent events or group leaders, + * keeping group members enabled. + */ + if (perf_evsel__is_group_leader(evsel)) + attr->disabled = 1; + + /* + * Setting enable_on_exec for independent events and + * group leaders for traced executed by perf. + */ + if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) && + !opts->initial_delay) + attr->enable_on_exec = 1; +} + +int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + int cpu, thread; + evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); + + if (evsel->fd) { + for (cpu = 0; cpu < ncpus; cpu++) { + for (thread = 0; thread < nthreads; thread++) { + FD(evsel, cpu, thread) = -1; + } + } + } + + return evsel->fd != NULL ? 0 : -ENOMEM; +} + +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, ioc, arg); + + if (err) + return err; + } + } + + 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)); + if (evsel->sample_id == NULL) + return -ENOMEM; + + evsel->id = zalloc(ncpus * nthreads * sizeof(u64)); + if (evsel->id == NULL) { + xyarray__delete(evsel->sample_id); + evsel->sample_id = NULL; + return -ENOMEM; + } + + return 0; +} + +void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus) +{ + memset(evsel->counts, 0, (sizeof(*evsel->counts) + + (ncpus * sizeof(struct perf_counts_values)))); +} + +int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus) +{ + evsel->counts = zalloc((sizeof(*evsel->counts) + + (ncpus * sizeof(struct perf_counts_values)))); + return evsel->counts != NULL ? 0 : -ENOMEM; +} + +void perf_evsel__free_fd(struct perf_evsel *evsel) +{ + xyarray__delete(evsel->fd); + evsel->fd = NULL; +} + +void perf_evsel__free_id(struct perf_evsel *evsel) +{ + xyarray__delete(evsel->sample_id); + evsel->sample_id = NULL; + zfree(&evsel->id); +} + +void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + int cpu, thread; + + for (cpu = 0; cpu < ncpus; cpu++) + for (thread = 0; thread < nthreads; ++thread) { + close(FD(evsel, cpu, thread)); + FD(evsel, cpu, thread) = -1; + } +} + +void perf_evsel__free_counts(struct perf_evsel *evsel) +{ + zfree(&evsel->counts); +} + +void perf_evsel__exit(struct perf_evsel *evsel) +{ + assert(list_empty(&evsel->node)); + perf_evsel__free_fd(evsel); + perf_evsel__free_id(evsel); +} + +void perf_evsel__delete(struct perf_evsel *evsel) +{ + perf_evsel__exit(evsel); + close_cgroup(evsel->cgrp); + zfree(&evsel->group_name); + if (evsel->tp_format) + pevent_free_format(evsel->tp_format); + zfree(&evsel->name); + free(evsel); +} + +static inline void compute_deltas(struct perf_evsel *evsel, + int cpu, + struct perf_counts_values *count) +{ + struct perf_counts_values tmp; + + if (!evsel->prev_raw_counts) + return; + + if (cpu == -1) { + tmp = evsel->prev_raw_counts->aggr; + evsel->prev_raw_counts->aggr = *count; + } else { + tmp = evsel->prev_raw_counts->cpu[cpu]; + evsel->prev_raw_counts->cpu[cpu] = *count; + } + + count->val = count->val - tmp.val; + count->ena = count->ena - tmp.ena; + count->run = count->run - tmp.run; +} + +int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, + int cpu, int thread, bool scale) +{ + struct perf_counts_values count; + size_t nv = scale ? 3 : 1; + + if (FD(evsel, cpu, thread) < 0) + return -EINVAL; + + if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0) + return -ENOMEM; + + if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) + return -errno; + + compute_deltas(evsel, cpu, &count); + + if (scale) { + if (count.run == 0) + count.val = 0; + else if (count.run < count.ena) + count.val = (u64)((double)count.val * count.ena / count.run + 0.5); + } else + count.ena = count.run = 0; + + evsel->counts->cpu[cpu] = count; + return 0; +} + +int __perf_evsel__read(struct perf_evsel *evsel, + int ncpus, int nthreads, bool scale) +{ + size_t nv = scale ? 3 : 1; + int cpu, thread; + struct perf_counts_values *aggr = &evsel->counts->aggr, count; + + aggr->val = aggr->ena = aggr->run = 0; + + for (cpu = 0; cpu < ncpus; cpu++) { + for (thread = 0; thread < nthreads; thread++) { + if (FD(evsel, cpu, thread) < 0) + continue; + + if (readn(FD(evsel, cpu, thread), + &count, nv * sizeof(u64)) < 0) + return -errno; + + aggr->val += count.val; + if (scale) { + aggr->ena += count.ena; + aggr->run += count.run; + } + } + } + + compute_deltas(evsel, -1, aggr); + + evsel->counts->scaled = 0; + if (scale) { + if (aggr->run == 0) { + evsel->counts->scaled = -1; + aggr->val = 0; + return 0; + } + + if (aggr->run < aggr->ena) { + evsel->counts->scaled = 1; + aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5); + } + } else + aggr->ena = aggr->run = 0; + + return 0; +} + +static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) +{ + struct perf_evsel *leader = evsel->leader; + int fd; + + if (perf_evsel__is_group_leader(evsel)) + return -1; + + /* + * Leader must be already processed/open, + * if not it's a bug. + */ + BUG_ON(!leader->fd); + + fd = FD(leader, cpu, thread); + BUG_ON(fd == -1); + + 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) + return -ENOMEM; + + if (evsel->cgrp) { + flags = PERF_FLAG_PID_CGROUP; + pid = evsel->cgrp->fd; + } + +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++) { + int group_fd; + + if (!evsel->cgrp) + pid = threads->map[thread]; + + group_fd = get_group_fd(evsel, cpu, thread); +retry_open: + pr_debug2("sys_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, + cpus->map[cpu], + group_fd, flags); + if (FD(evsel, cpu, thread) < 0) { + err = -errno; + pr_debug2("sys_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.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) { + perf_missing_features.sample_id_all = true; + goto retry_sample_id; + } + +out_close: + do { + while (--thread >= 0) { + close(FD(evsel, cpu, thread)); + FD(evsel, cpu, thread) = -1; + } + thread = threads->nr; + } while (--cpu >= 0); + return err; +} + +void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + if (evsel->fd == NULL) + return; + + perf_evsel__close_fd(evsel, ncpus, nthreads); + perf_evsel__free_fd(evsel); +} + +static struct { + struct cpu_map map; + int cpus[1]; +} empty_cpu_map = { + .map.nr = 1, + .cpus = { -1, }, +}; + +static struct { + struct thread_map map; + int threads[1]; +} empty_thread_map = { + .map.nr = 1, + .threads = { -1, }, +}; + +int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, + struct thread_map *threads) +{ + if (cpus == NULL) { + /* Work around old compiler warnings about strict aliasing */ + cpus = &empty_cpu_map.map; + } + + if (threads == NULL) + threads = &empty_thread_map.map; + + return __perf_evsel__open(evsel, cpus, threads); +} + +int perf_evsel__open_per_cpu(struct perf_evsel *evsel, + struct cpu_map *cpus) +{ + return __perf_evsel__open(evsel, cpus, &empty_thread_map.map); +} + +int perf_evsel__open_per_thread(struct perf_evsel *evsel, + struct thread_map *threads) +{ + return __perf_evsel__open(evsel, &empty_cpu_map.map, threads); +} + +static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, + const union perf_event *event, + struct perf_sample *sample) +{ + u64 type = evsel->attr.sample_type; + const u64 *array = event->sample.array; + bool swapped = evsel->needs_swap; + union u64_swap u; + + 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) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + } + + sample->cpu = u.val32[0]; + array--; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + sample->stream_id = *array; + array--; + } + + if (type & PERF_SAMPLE_ID) { + sample->id = *array; + array--; + } + + if (type & PERF_SAMPLE_TIME) { + sample->time = *array; + array--; + } + + if (type & PERF_SAMPLE_TID) { + u.val64 = *array; + if (swapped) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + u.val32[1] = bswap_32(u.val32[1]); + } + + sample->pid = u.val32[0]; + sample->tid = u.val32[1]; + array--; + } + + return 0; +} + +static inline bool overflow(const void *endp, u16 max_size, const void *offset, + u64 size) +{ + return size > max_size || offset + size > endp; +} + +#define OVERFLOW_CHECK(offset, size, max_size) \ + do { \ + if (overflow(endp, (max_size), (offset), (size))) \ + return -EFAULT; \ + } while (0) + +#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; + 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 + * for why this goofiness is needed. + */ + union u64_swap u; + + memset(data, 0, sizeof(*data)); + data->cpu = data->pid = data->tid = -1; + data->stream_id = data->id = data->time = -1ULL; + data->period = evsel->attr.sample_period; + data->weight = 0; + + if (event->header.type != PERF_RECORD_SAMPLE) { + if (!evsel->attr.sample_id_all) + return 0; + return perf_evsel__parse_id_sample(evsel, event, data); + } + + 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 = *array; + array++; + } + + if (type & PERF_SAMPLE_TID) { + u.val64 = *array; + if (swapped) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + u.val32[1] = bswap_32(u.val32[1]); + } + + data->pid = u.val32[0]; + data->tid = u.val32[1]; + array++; + } + + if (type & PERF_SAMPLE_TIME) { + data->time = *array; + array++; + } + + data->addr = 0; + if (type & PERF_SAMPLE_ADDR) { + data->addr = *array; + array++; + } + + if (type & PERF_SAMPLE_ID) { + data->id = *array; + array++; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + data->stream_id = *array; + array++; + } + + if (type & PERF_SAMPLE_CPU) { + + u.val64 = *array; + if (swapped) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + } + + data->cpu = u.val32[0]; + array++; + } + + if (type & PERF_SAMPLE_PERIOD) { + data->period = *array; + array++; + } + + if (type & PERF_SAMPLE_READ) { + 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) { + const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); + + OVERFLOW_CHECK_u64(array); + data->callchain = (struct ip_callchain *)array++; + if (data->callchain->nr > max_callchain_nr) + return -EFAULT; + sz = data->callchain->nr * sizeof(u64); + OVERFLOW_CHECK(array, sz, max_size); + array = (void *)array + sz; + } + + if (type & PERF_SAMPLE_RAW) { + OVERFLOW_CHECK_u64(array); + u.val64 = *array; + if (WARN_ONCE(swapped, + "Endianness of raw data not corrected!\n")) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + u.val32[1] = bswap_32(u.val32[1]); + } + data->raw_size = u.val32[0]; + array = (void *)array + 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) { + const u64 max_branch_nr = UINT64_MAX / + sizeof(struct branch_entry); + + 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); + OVERFLOW_CHECK(array, sz, max_size); + array = (void *)array + sz; + } + + if (type & PERF_SAMPLE_REGS_USER) { + OVERFLOW_CHECK_u64(array); + data->user_regs.abi = *array; + array++; + + if (data->user_regs.abi) { + u64 mask = evsel->attr.sample_regs_user; + + sz = hweight_long(mask) * sizeof(u64); + OVERFLOW_CHECK(array, sz, max_size); + data->user_regs.mask = mask; + data->user_regs.regs = (u64 *)array; + array = (void *)array + sz; + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + OVERFLOW_CHECK_u64(array); + sz = *array++; + + data->user_stack.offset = ((char *)(array - 1) + - (char *) event); + + if (!sz) { + data->user_stack.size = 0; + } else { + OVERFLOW_CHECK(array, sz, max_size); + data->user_stack.data = (char *)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 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->user_regs.mask) * 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 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. + */ + union u64_swap u; + + array = event->sample.array; + + if (type & PERF_SAMPLE_IDENTIFIER) { + *array = sample->id; + array++; + } + + if (type & PERF_SAMPLE_IP) { + *array = sample->ip; + array++; + } + + if (type & PERF_SAMPLE_TID) { + u.val32[0] = sample->pid; + u.val32[1] = sample->tid; + if (swapped) { + /* + * Inverse of what is done in perf_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++; + } + + if (type & PERF_SAMPLE_TIME) { + *array = sample->time; + array++; + } + + if (type & PERF_SAMPLE_ADDR) { + *array = sample->addr; + array++; + } + + if (type & PERF_SAMPLE_ID) { + *array = sample->id; + array++; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + *array = sample->stream_id; + array++; + } + + if (type & PERF_SAMPLE_CPU) { + u.val32[0] = sample->cpu; + if (swapped) { + /* + * Inverse of what is done in perf_evsel__parse_sample + */ + u.val32[0] = bswap_32(u.val32[0]); + u.val64 = bswap_64(u.val64); + } + *array = u.val64; + array++; + } + + if (type & PERF_SAMPLE_PERIOD) { + *array = sample->period; + array++; + } + + 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->user_regs.mask) * 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; +} + +struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name) +{ + return pevent_find_field(evsel->tp_format, name); +} + +void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, + const char *name) +{ + struct format_field *field = perf_evsel__field(evsel, name); + int offset; + + if (!field) + return NULL; + + offset = field->offset; + + if (field->flags & FIELD_IS_DYNAMIC) { + offset = *(int *)(sample->raw_data + field->offset); + offset &= 0xffff; + } + + return sample->raw_data + offset; +} + +u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, + const char *name) +{ + struct format_field *field = perf_evsel__field(evsel, name); + void *ptr; + u64 value; + + if (!field) + return 0; + + ptr = sample->raw_data + field->offset; + + switch (field->size) { + case 1: + return *(u8 *)ptr; + case 2: + value = *(u16 *)ptr; + break; + case 4: + value = *(u32 *)ptr; + break; + case 8: + value = *(u64 *)ptr; + break; + default: + return 0; + } + + if (!evsel->needs_swap) + return value; + + switch (field->size) { + case 2: + return bswap_16(value); + case 4: + return bswap_32(value); + case 8: + return bswap_64(value); + default: + return 0; + } + + return 0; +} + +static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) +{ + va_list args; + int ret = 0; + + if (!*first) { + ret += fprintf(fp, ","); + } else { + ret += fprintf(fp, ":"); + *first = false; + } + + va_start(args, fmt); + ret += vfprintf(fp, fmt, args); + va_end(args); + return ret; +} + +static int __if_fprintf(FILE *fp, bool *first, const char *field, u64 value) +{ + if (value == 0) + return 0; + + return comma_fprintf(fp, first, " %s: %" PRIu64, field, value); +} + +#define if_print(field) printed += __if_fprintf(fp, &first, #field, evsel->attr.field) + +struct bit_names { + int bit; + const char *name; +}; + +static int bits__fprintf(FILE *fp, const char *field, u64 value, + struct bit_names *bits, bool *first) +{ + int i = 0, printed = comma_fprintf(fp, first, " %s: ", field); + bool first_bit = true; + + do { + if (value & bits[i].bit) { + printed += fprintf(fp, "%s%s", first_bit ? "" : "|", bits[i].name); + first_bit = false; + } + } while (bits[++i].name != NULL); + + return printed; +} + +static int sample_type__fprintf(FILE *fp, bool *first, u64 value) +{ +#define bit_name(n) { PERF_SAMPLE_##n, #n } + struct bit_names bits[] = { + bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), + 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 + return bits__fprintf(fp, "sample_type", value, bits, first); +} + +static int read_format__fprintf(FILE *fp, bool *first, u64 value) +{ +#define bit_name(n) { PERF_FORMAT_##n, #n } + struct bit_names bits[] = { + bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), + bit_name(ID), bit_name(GROUP), + { .name = NULL, } + }; +#undef bit_name + return bits__fprintf(fp, "read_format", value, bits, first); +} + +int perf_evsel__fprintf(struct perf_evsel *evsel, + struct perf_attr_details *details, FILE *fp) +{ + bool first = true; + int printed = 0; + + if (details->event_group) { + struct perf_evsel *pos; + + if (!perf_evsel__is_group_leader(evsel)) + return 0; + + if (evsel->nr_members > 1) + printed += fprintf(fp, "%s{", evsel->group_name ?: ""); + + printed += fprintf(fp, "%s", perf_evsel__name(evsel)); + for_each_group_member(pos, evsel) + printed += fprintf(fp, ",%s", perf_evsel__name(pos)); + + if (evsel->nr_members > 1) + printed += fprintf(fp, "}"); + goto out; + } + + printed += fprintf(fp, "%s", perf_evsel__name(evsel)); + + if (details->verbose || details->freq) { + printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64, + (u64)evsel->attr.sample_freq); + } + + if (details->verbose) { + if_print(type); + if_print(config); + if_print(config1); + if_print(config2); + if_print(size); + printed += sample_type__fprintf(fp, &first, evsel->attr.sample_type); + if (evsel->attr.read_format) + printed += read_format__fprintf(fp, &first, evsel->attr.read_format); + if_print(disabled); + if_print(inherit); + if_print(pinned); + if_print(exclusive); + if_print(exclude_user); + if_print(exclude_kernel); + if_print(exclude_hv); + if_print(exclude_idle); + if_print(mmap); + if_print(mmap2); + if_print(comm); + if_print(freq); + if_print(inherit_stat); + if_print(enable_on_exec); + if_print(task); + if_print(watermark); + if_print(precise_ip); + if_print(mmap_data); + if_print(sample_id_all); + if_print(exclude_host); + if_print(exclude_guest); + if_print(__reserved_1); + if_print(wakeup_events); + if_print(bp_type); + if_print(branch_sample_type); + } +out: + fputc('\n', fp); + return ++printed; +} + +bool perf_evsel__fallback(struct perf_evsel *evsel, int err, + char *msg, size_t msgsize) +{ + if ((err == ENOENT || err == ENXIO || err == ENODEV) && + evsel->attr.type == PERF_TYPE_HARDWARE && + evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) { + /* + * If it's cycles then fall back to hrtimer based + * cpu-clock-tick sw counter, which is always available even if + * no PMU support. + * + * PPC returns ENXIO until 2.6.37 (behavior changed with commit + * b0a873e). + */ + scnprintf(msg, msgsize, "%s", +"The cycles event is not supported, trying to fall back to cpu-clock-ticks"); + + evsel->attr.type = PERF_TYPE_SOFTWARE; + evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK; + + zfree(&evsel->name); + return true; + } + + return false; +} + +int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, + int err, char *msg, size_t size) +{ + switch (err) { + case EPERM: + case EACCES: + return scnprintf(msg, size, + "You may not have permission to collect %sstats.\n" + "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n" + " -1 - Not paranoid at all\n" + " 0 - Disallow raw tracepoint access for unpriv\n" + " 1 - Disallow cpu events for unpriv\n" + " 2 - Disallow kernel profiling for unpriv", + target->system_wide ? "system-wide " : ""); + case ENOENT: + return scnprintf(msg, size, "The %s event is not supported.", + perf_evsel__name(evsel)); + case EMFILE: + return scnprintf(msg, size, "%s", + "Too many events are opened.\n" + "Try again after reducing the number of events."); + case ENODEV: + if (target->cpu_list) + return scnprintf(msg, size, "%s", + "No such device - did you specify an out-of-range profile CPU?\n"); + break; + case EOPNOTSUPP: + if (evsel->attr.precise_ip) + return scnprintf(msg, size, "%s", + "\'precise\' request may not be supported. Try removing 'p' modifier."); +#if defined(__i386__) || defined(__x86_64__) + if (evsel->attr.type == PERF_TYPE_HARDWARE) + return scnprintf(msg, size, "%s", + "No hardware sampling interrupt available.\n" + "No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it."); +#endif + break; + default: + break; + } + + return scnprintf(msg, size, + "The sys_perf_event_open() syscall returned with %d (%s) for event (%s). \n" + "/bin/dmesg may provide additional information.\n" + "No CONFIG_PERF_EVENTS=y kernel support configured?\n", + err, strerror(err), perf_evsel__name(evsel)); +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h new file mode 100644 index 00000000000..a52e9a5bb2d --- /dev/null +++ b/tools/perf/util/evsel.h @@ -0,0 +1,365 @@ +#ifndef __PERF_EVSEL_H +#define __PERF_EVSEL_H 1 + +#include <linux/list.h> +#include <stdbool.h> +#include <stddef.h> +#include <linux/perf_event.h> +#include <linux/types.h> +#include "xyarray.h" +#include "cgroup.h" +#include "hist.h" +#include "symbol.h" + +struct perf_counts_values { + union { + struct { + u64 val; + u64 ena; + u64 run; + }; + u64 values[3]; + }; +}; + +struct perf_counts { + s8 scaled; + struct perf_counts_values aggr; + struct perf_counts_values cpu[]; +}; + +struct perf_evsel; + +/* + * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are + * more than one entry in the evlist. + */ +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 + * + * @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; + struct perf_event_attr attr; + char *filter; + struct xyarray *fd; + struct xyarray *sample_id; + u64 *id; + struct perf_counts *counts; + struct perf_counts *prev_raw_counts; + int idx; + u32 ids; + struct hists hists; + char *name; + double scale; + const char *unit; + struct event_format *tp_format; + union { + void *priv; + off_t id_offset; + }; + struct cgroup_sel *cgrp; + 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; +}; + +union u64_swap { + u64 val64; + u32 val32[2]; +}; + +#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists) + +struct cpu_map; +struct thread_map; +struct perf_evlist; +struct record_opts; + +struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx); + +static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr) +{ + return perf_evsel__new_idx(attr, 0); +} + +struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx); + +static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name) +{ + return perf_evsel__newtp_idx(sys, name, 0); +} + +struct event_format *event_format__new(const char *sys, const char *name); + +void perf_evsel__init(struct perf_evsel *evsel, + struct perf_event_attr *attr, int idx); +void perf_evsel__exit(struct perf_evsel *evsel); +void perf_evsel__delete(struct perf_evsel *evsel); + +void perf_evsel__config(struct perf_evsel *evsel, + struct 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 + +extern const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] + [PERF_EVSEL__MAX_ALIASES]; +extern const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_EVSEL__MAX_ALIASES]; +extern const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] + [PERF_EVSEL__MAX_ALIASES]; +extern const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX]; +extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX]; +int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, + char *bf, size_t size); +const char *perf_evsel__name(struct perf_evsel *evsel); + +const char *perf_evsel__group_name(struct perf_evsel *evsel); +int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size); + +int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); +int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); +int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); +void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus); +void perf_evsel__free_fd(struct perf_evsel *evsel); +void perf_evsel__free_id(struct perf_evsel *evsel); +void perf_evsel__free_counts(struct perf_evsel *evsel); +void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); + +void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit); +void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit); + +#define perf_evsel__set_sample_bit(evsel, bit) \ + __perf_evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit) + +#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, + 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); +int perf_evsel__open_per_thread(struct perf_evsel *evsel, + struct thread_map *threads); +int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, + struct thread_map *threads); +void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads); + +struct perf_sample; + +void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, + const char *name); +u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, + const char *name); + +static inline char *perf_evsel__strval(struct perf_evsel *evsel, + struct perf_sample *sample, + const char *name) +{ + return perf_evsel__rawptr(evsel, sample, name); +} + +struct format_field; + +struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name); + +#define perf_evsel__match(evsel, t, c) \ + (evsel->attr.type == PERF_TYPE_##t && \ + evsel->attr.config == PERF_COUNT_##c) + +static inline bool perf_evsel__match2(struct perf_evsel *e1, + struct perf_evsel *e2) +{ + return (e1->attr.type == e2->attr.type) && + (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); + +/** + * perf_evsel__read_on_cpu - Read out the results on a CPU and thread + * + * @evsel - event selector to read value + * @cpu - CPU of interest + * @thread - thread of interest + */ +static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel, + int cpu, int thread) +{ + return __perf_evsel__read_on_cpu(evsel, cpu, thread, false); +} + +/** + * perf_evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled + * + * @evsel - event selector to read value + * @cpu - CPU of interest + * @thread - thread of interest + */ +static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel, + int cpu, int thread) +{ + return __perf_evsel__read_on_cpu(evsel, cpu, thread, true); +} + +int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads, + bool scale); + +/** + * perf_evsel__read - Read the aggregate results on all CPUs + * + * @evsel - event selector to read value + * @ncpus - Number of cpus affected, from zero + * @nthreads - Number of threads affected, from zero + */ +static inline int perf_evsel__read(struct perf_evsel *evsel, + int ncpus, int nthreads) +{ + return __perf_evsel__read(evsel, ncpus, nthreads, false); +} + +/** + * perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled + * + * @evsel - event selector to read value + * @ncpus - Number of cpus affected, from zero + * @nthreads - Number of threads affected, from zero + */ +static inline int perf_evsel__read_scaled(struct perf_evsel *evsel, + int ncpus, int nthreads) +{ + return __perf_evsel__read(evsel, ncpus, nthreads, true); +} + +void hists__init(struct hists *hists); + +int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, + struct perf_sample *sample); + +static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel) +{ + return list_entry(evsel->node.next, struct perf_evsel, node); +} + +static inline struct perf_evsel *perf_evsel__prev(struct perf_evsel *evsel) +{ + return list_entry(evsel->node.prev, struct perf_evsel, node); +} + +/** + * perf_evsel__is_group_leader - Return whether given evsel is a leader event + * + * @evsel - evsel selector to be tested + * + * Return %true if @evsel is a group leader or a stand-alone event + */ +static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel) +{ + return evsel->leader == evsel; +} + +/** + * perf_evsel__is_group_event - Return whether given evsel is a group event + * + * @evsel - evsel selector to be tested + * + * Return %true iff event group view is enabled and @evsel is a actual group + * leader which has other members in the group + */ +static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel) +{ + if (!symbol_conf.event_group) + return false; + + return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1; +} + +/** + * perf_evsel__is_function_event - Return whether given evsel is a function + * trace event + * + * @evsel - evsel selector to be tested + * + * Return %true if event is function trace event + */ +static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel) +{ +#define FUNCTION_EVENT "ftrace:function" + + return evsel->name && + !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT)); + +#undef FUNCTION_EVENT +} + +struct perf_attr_details { + bool freq; + bool verbose; + bool event_group; +}; + +int perf_evsel__fprintf(struct perf_evsel *evsel, + struct perf_attr_details *details, FILE *fp); + +bool perf_evsel__fallback(struct perf_evsel *evsel, int err, + char *msg, size_t msgsize); +int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, + int err, char *msg, size_t size); + +static inline int perf_evsel__group_idx(struct perf_evsel *evsel) +{ + return evsel->idx - evsel->leader->idx; +} + +#define for_each_group_member(_evsel, _leader) \ +for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \ + (_evsel) && (_evsel)->leader == (_leader); \ + (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) + +#endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c index 67eeff57156..7adf4ad15d8 100644 --- a/tools/perf/util/exec_cmd.c +++ b/tools/perf/util/exec_cmd.c @@ -11,31 +11,12 @@ static const char *argv0_path; const char *system_path(const char *path) { -#ifdef RUNTIME_PREFIX - static const char *prefix; -#else static const char *prefix = PREFIX; -#endif struct strbuf d = STRBUF_INIT; if (is_absolute_path(path)) return path; -#ifdef RUNTIME_PREFIX - assert(argv0_path); - assert(is_absolute_path(argv0_path)); - - if (!prefix && - !(prefix = strip_path_suffix(argv0_path, PERF_EXEC_PATH)) && - !(prefix = strip_path_suffix(argv0_path, BINDIR)) && - !(prefix = strip_path_suffix(argv0_path, "perf"))) { - prefix = PREFIX; - fprintf(stderr, "RUNTIME_PREFIX requested, " - "but prefix computation failed. " - "Using static fallback '%s'.\n", prefix); - } -#endif - strbuf_addf(&d, "%s/%s", prefix, path); path = strbuf_detach(&d, NULL); return path; diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index f06f6fd148f..36a885d2cd2 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -21,4 +21,19 @@ do p }' "Documentation/perf-$cmd.txt" done + +echo "#ifdef HAVE_LIBELF_SUPPORT" +sed -n -e 's/^perf-\([^ ]*\)[ ].* full.*/\1/p' command-list.txt | +sort | +while read cmd +do + sed -n ' + /^NAME/,/perf-'"$cmd"'/H + ${ + x + s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ + p + }' "Documentation/perf-$cmd.txt" +done +echo "#endif /* HAVE_LIBELF_SUPPORT */" echo "};" diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d7e67b167ea..893f8e2df92 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1,5 +1,4 @@ -#define _FILE_OFFSET_BITS 64 - +#include "util.h" #include <sys/types.h> #include <byteswap.h> #include <unistd.h> @@ -7,183 +6,169 @@ #include <stdlib.h> #include <linux/list.h> #include <linux/kernel.h> +#include <linux/bitops.h> +#include <sys/utsname.h> -#include "util.h" +#include "evlist.h" +#include "evsel.h" #include "header.h" #include "../perf.h" #include "trace-event.h" #include "session.h" #include "symbol.h" #include "debug.h" +#include "cpumap.h" +#include "pmu.h" +#include "vdso.h" +#include "strbuf.h" +#include "build-id.h" +#include "data.h" static bool no_buildid_cache = false; +static u32 header_argc; +static const char **header_argv; + /* - * Create new perf.data header attribute: + * magic2 = "PERFILE2" + * must be a numerical value to let the endianness + * determine the memory layout. That way we are able + * to detect endianness when reading the perf.data file + * back. + * + * we check for legacy (PERFFILE) format. */ -struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr) -{ - struct perf_header_attr *self = malloc(sizeof(*self)); - - if (self != NULL) { - self->attr = *attr; - self->ids = 0; - self->size = 1; - self->id = malloc(sizeof(u64)); - if (self->id == NULL) { - free(self); - self = NULL; - } - } +static const char *__perf_magic1 = "PERFFILE"; +static const u64 __perf_magic2 = 0x32454c4946524550ULL; +static const u64 __perf_magic2_sw = 0x50455246494c4532ULL; - return self; -} +#define PERF_MAGIC __perf_magic2 -void perf_header_attr__delete(struct perf_header_attr *self) -{ - free(self->id); - free(self); -} +struct perf_file_attr { + struct perf_event_attr attr; + struct perf_file_section ids; +}; -int perf_header_attr__add_id(struct perf_header_attr *self, u64 id) +void perf_header__set_feat(struct perf_header *header, int feat) { - int pos = self->ids; - - self->ids++; - if (self->ids > self->size) { - int nsize = self->size * 2; - u64 *nid = realloc(self->id, nsize * sizeof(u64)); - - if (nid == NULL) - return -1; - - self->size = nsize; - self->id = nid; - } - self->id[pos] = id; - return 0; + set_bit(feat, header->adds_features); } -int perf_header__init(struct perf_header *self) +void perf_header__clear_feat(struct perf_header *header, int feat) { - self->size = 1; - self->attr = malloc(sizeof(void *)); - return self->attr == NULL ? -ENOMEM : 0; + clear_bit(feat, header->adds_features); } -void perf_header__exit(struct perf_header *self) +bool perf_header__has_feat(const struct perf_header *header, int feat) { - int i; - for (i = 0; i < self->attrs; ++i) - perf_header_attr__delete(self->attr[i]); - free(self->attr); + return test_bit(feat, header->adds_features); } -int perf_header__add_attr(struct perf_header *self, - struct perf_header_attr *attr) +static int do_write(int fd, const void *buf, size_t size) { - if (self->frozen) - return -1; - - if (self->attrs == self->size) { - int nsize = self->size * 2; - struct perf_header_attr **nattr; + while (size) { + int ret = write(fd, buf, size); - nattr = realloc(self->attr, nsize * sizeof(void *)); - if (nattr == NULL) - return -1; + if (ret < 0) + return -errno; - self->size = nsize; - self->attr = nattr; + size -= ret; + buf += ret; } - self->attr[self->attrs++] = attr; return 0; } -static int event_count; -static struct perf_trace_event_type *events; +#define NAME_ALIGN 64 -int perf_header__push_event(u64 id, const char *name) +static int write_padded(int fd, const void *bf, size_t count, + size_t count_aligned) { - if (strlen(name) > MAX_EVENT_NAME) - pr_warning("Event %s will be truncated\n", name); + static const char zero_buf[NAME_ALIGN]; + int err = do_write(fd, bf, count); - if (!events) { - events = malloc(sizeof(struct perf_trace_event_type)); - if (events == NULL) - return -ENOMEM; - } else { - struct perf_trace_event_type *nevents; + if (!err) + err = do_write(fd, zero_buf, count_aligned - count); - nevents = realloc(events, (event_count + 1) * sizeof(*events)); - if (nevents == NULL) - return -ENOMEM; - events = nevents; - } - memset(&events[event_count], 0, sizeof(struct perf_trace_event_type)); - events[event_count].event_id = id; - strncpy(events[event_count].name, name, MAX_EVENT_NAME - 1); - event_count++; - return 0; + return err; } -char *perf_header__find_event(u64 id) +static int do_write_string(int fd, const char *str) { - int i; - for (i = 0 ; i < event_count; i++) { - if (events[i].event_id == id) - return events[i].name; - } - return NULL; -} - -static const char *__perf_magic = "PERFFILE"; + u32 len, olen; + int ret; -#define PERF_MAGIC (*(u64 *)__perf_magic) + olen = strlen(str) + 1; + len = PERF_ALIGN(olen, NAME_ALIGN); -struct perf_file_attr { - struct perf_event_attr attr; - struct perf_file_section ids; -}; + /* write len, incl. \0 */ + ret = do_write(fd, &len, sizeof(len)); + if (ret < 0) + return ret; -void perf_header__set_feat(struct perf_header *self, int feat) -{ - set_bit(feat, self->adds_features); + return write_padded(fd, str, olen, len); } -bool perf_header__has_feat(const struct perf_header *self, int feat) +static char *do_read_string(int fd, struct perf_header *ph) { - return test_bit(feat, self->adds_features); -} + ssize_t sz, ret; + u32 len; + char *buf; -static int do_write(int fd, const void *buf, size_t size) -{ - while (size) { - int ret = write(fd, buf, size); + sz = readn(fd, &len, sizeof(len)); + if (sz < (ssize_t)sizeof(len)) + return NULL; - if (ret < 0) - return -errno; + if (ph->needs_swap) + len = bswap_32(len); - size -= ret; - buf += ret; + buf = malloc(len); + if (!buf) + return NULL; + + ret = readn(fd, buf, len); + if (ret == (ssize_t)len) { + /* + * strings are padded by zeroes + * thus the actual strlen of buf + * may be less than len + */ + return buf; } - return 0; + free(buf); + return NULL; } -#define NAME_ALIGN 64 - -static int write_padded(int fd, const void *bf, size_t count, - size_t count_aligned) +int +perf_header__set_cmdline(int argc, const char **argv) { - static const char zero_buf[NAME_ALIGN]; - int err = do_write(fd, bf, count); + int i; - if (!err) - err = do_write(fd, zero_buf, count_aligned - count); + /* + * If header_argv has already been set, do not override it. + * This allows a command to set the cmdline, parse args and + * then call another builtin function that implements a + * command -- e.g, cmd_kvm calling cmd_record. + */ + if (header_argv) + return 0; - return err; + header_argc = (u32)argc; + + /* do not include NULL termination */ + header_argv = calloc(argc, sizeof(char *)); + if (!header_argv) + return -ENOMEM; + + /* + * must copy argv contents because it gets moved + * around during option parsing + */ + for (i = 0; i < argc ; i++) + header_argv[i] = argv[i]; + + return 0; } #define dsos__for_each_with_build_id(pos, head) \ @@ -192,53 +177,81 @@ static int write_padded(int fd, const void *bf, size_t count, continue; \ else -static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, - u16 misc, int fd) +static int write_buildid(const char *name, size_t name_len, u8 *build_id, + pid_t pid, u16 misc, int fd) { + int err; + struct build_id_event b; + size_t len; + + len = name_len + 1; + len = PERF_ALIGN(len, NAME_ALIGN); + + memset(&b, 0, sizeof(b)); + memcpy(&b.build_id, build_id, BUILD_ID_SIZE); + b.pid = pid; + b.header.misc = misc; + b.header.size = sizeof(b) + len; + + err = do_write(fd, &b, sizeof(b)); + if (err < 0) + return err; + + return write_padded(fd, name, name_len + 1, len); +} + +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) { int err; - struct build_id_event b; - size_t len; + const char *name; + size_t name_len; if (!pos->hit) continue; - len = pos->long_name_len + 1; - len = ALIGN(len, NAME_ALIGN); - memset(&b, 0, sizeof(b)); - memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id)); - b.pid = pid; - b.header.misc = misc; - b.header.size = sizeof(b) + len; - err = do_write(fd, &b, sizeof(b)); - if (err < 0) - return err; - err = write_padded(fd, pos->long_name, - pos->long_name_len + 1, len); - if (err < 0) + + 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; + } + + err = write_buildid(name, name_len, pos->build_id, + pid, misc, fd); + if (err) return err; } return 0; } -static int machine__write_buildid_table(struct machine *self, int fd) +static int machine__write_buildid_table(struct machine *machine, int fd) { int err; u16 kmisc = PERF_RECORD_MISC_KERNEL, umisc = PERF_RECORD_MISC_USER; - if (!machine__is_host(self)) { + if (!machine__is_host(machine)) { kmisc = PERF_RECORD_MISC_GUEST_KERNEL; umisc = PERF_RECORD_MISC_GUEST_USER; } - err = __dsos__write_buildid_table(&self->kernel_dsos, self->pid, - kmisc, fd); + err = __dsos__write_buildid_table(&machine->kernel_dsos, machine, + machine->pid, kmisc, fd); if (err == 0) - err = __dsos__write_buildid_table(&self->user_dsos, - self->pid, umisc, fd); + err = __dsos__write_buildid_table(&machine->user_dsos, machine, + machine->pid, umisc, fd); return err; } @@ -247,12 +260,12 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd) struct perf_session *session = container_of(header, struct perf_session, header); struct rb_node *nd; - int err = machine__write_buildid_table(&session->host_machine, fd); + int err = machine__write_buildid_table(&session->machines.host, fd); if (err) return err; - for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); err = machine__write_buildid_table(pos, fd); if (err) @@ -262,32 +275,44 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd) } int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, - const char *name, bool is_kallsyms) + const char *name, bool is_kallsyms, bool is_vdso) { const size_t size = PATH_MAX; - char *filename = malloc(size), - *linkname = malloc(size), *targetname; + char *realname, *filename = zalloc(size), + *linkname = zalloc(size), *targetname; int len, err = -1; + bool slash = is_kallsyms || is_vdso; - if (filename == NULL || linkname == NULL) + if (is_kallsyms) { + if (symbol_conf.kptr_restrict) { + pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n"); + err = 0; + goto out_free; + } + realname = (char *) name; + } else + realname = realpath(name, NULL); + + if (realname == NULL || filename == NULL || linkname == NULL) goto out_free; - len = snprintf(filename, size, "%s%s%s", - debugdir, is_kallsyms ? "/" : "", name); + len = scnprintf(filename, size, "%s%s%s", + debugdir, slash ? "/" : "", + is_vdso ? VDSO__MAP_NAME : realname); if (mkdir_p(filename, 0755)) goto out_free; - snprintf(filename + len, sizeof(filename) - len, "/%s", sbuild_id); + snprintf(filename + len, size - len, "/%s", sbuild_id); if (access(filename, F_OK)) { if (is_kallsyms) { if (copyfile("/proc/kallsyms", filename)) goto out_free; - } else if (link(name, filename) && copyfile(name, filename)) + } else if (link(realname, filename) && copyfile(name, filename)) goto out_free; } - len = snprintf(linkname, size, "%s/.build-id/%.2s", + len = scnprintf(linkname, size, "%s/.build-id/%.2s", debugdir, sbuild_id); if (access(linkname, X_OK) && mkdir_p(linkname, 0755)) @@ -300,6 +325,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, if (symlink(targetname, linkname) == 0) err = 0; out_free: + if (!is_kallsyms) + free(realname); free(filename); free(linkname); return err; @@ -307,20 +334,21 @@ out_free: static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, const char *name, const char *debugdir, - bool is_kallsyms) + bool is_kallsyms, bool is_vdso) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; build_id__sprintf(build_id, build_id_size, sbuild_id); - return build_id_cache__add_s(sbuild_id, debugdir, name, is_kallsyms); + return build_id_cache__add_s(sbuild_id, debugdir, name, + is_kallsyms, is_vdso); } int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) { const size_t size = PATH_MAX; - char *filename = malloc(size), - *linkname = malloc(size); + char *filename = zalloc(size), + *linkname = zalloc(size); int err = -1; if (filename == NULL || linkname == NULL) @@ -332,7 +360,7 @@ int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) if (access(linkname, F_OK)) goto out_free; - if (readlink(linkname, filename, size) < 0) + if (readlink(linkname, filename, size - 1) < 0) goto out_free; if (unlink(linkname)) @@ -354,34 +382,45 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *self, const char *debugdir) +static int dso__cache_build_id(struct dso *dso, struct machine *machine, + const char *debugdir) { - bool is_kallsyms = self->kernel && self->long_name[0] != '/'; - - return build_id_cache__add_b(self->build_id, sizeof(self->build_id), - self->long_name, debugdir, is_kallsyms); + bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; + bool is_vdso = is_vdso_map(dso->short_name); + const char *name = dso->long_name; + char nm[PATH_MAX]; + + 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; } -static int machine__cache_build_ids(struct machine *self, const char *debugdir) +static int machine__cache_build_ids(struct machine *machine, const char *debugdir) { - int ret = __dsos__cache_build_ids(&self->kernel_dsos, debugdir); - ret |= __dsos__cache_build_ids(&self->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; } -static int perf_session__cache_build_ids(struct perf_session *self) +static int perf_session__cache_build_ids(struct perf_session *session) { struct rb_node *nd; int ret; @@ -392,28 +431,28 @@ static int perf_session__cache_build_ids(struct perf_session *self) if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) return -1; - ret = machine__cache_build_ids(&self->host_machine, debugdir); + ret = machine__cache_build_ids(&session->machines.host, debugdir); - for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret |= machine__cache_build_ids(pos, debugdir); } return ret ? -1 : 0; } -static bool machine__read_build_ids(struct machine *self, bool with_hits) +static bool machine__read_build_ids(struct machine *machine, bool with_hits) { - bool ret = __dsos__read_build_ids(&self->kernel_dsos, with_hits); - ret |= __dsos__read_build_ids(&self->user_dsos, with_hits); + bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits); + ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits); return ret; } -static bool perf_session__read_build_ids(struct perf_session *self, bool with_hits) +static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits) { struct rb_node *nd; - bool ret = machine__read_build_ids(&self->host_machine, with_hits); + bool ret = machine__read_build_ids(&session->machines.host, with_hits); - for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret |= machine__read_build_ids(pos, with_hits); } @@ -421,280 +460,1046 @@ static bool perf_session__read_build_ids(struct perf_session *self, bool with_hi return ret; } -static int perf_header__adds_write(struct perf_header *self, int fd) +static int write_tracing_data(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist) +{ + return read_tracing_data(fd, &evlist->entries); +} + + +static int write_build_id(int fd, struct perf_header *h, + struct perf_evlist *evlist __maybe_unused) { - int nr_sections; struct perf_session *session; - struct perf_file_section *feat_sec; - int sec_size; - u64 sec_start; - int idx = 0, err; + int err; - session = container_of(self, struct perf_session, header); - if (perf_session__read_build_ids(session, true)) - perf_header__set_feat(self, HEADER_BUILD_ID); + session = container_of(h, struct perf_session, header); - nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS); - if (!nr_sections) - return 0; + if (!perf_session__read_build_ids(session, true)) + return -1; - feat_sec = calloc(sizeof(*feat_sec), nr_sections); - if (feat_sec == NULL) - return -ENOMEM; + err = dsos__write_buildid_table(h, fd); + if (err < 0) { + pr_debug("failed to write buildid table\n"); + return err; + } + if (!no_buildid_cache) + perf_session__cache_build_ids(session); - sec_size = sizeof(*feat_sec) * nr_sections; + return 0; +} - sec_start = self->data_offset + self->data_size; - lseek(fd, sec_start + sec_size, SEEK_SET); +static int write_hostname(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + struct utsname uts; + int ret; - if (perf_header__has_feat(self, HEADER_TRACE_INFO)) { - struct perf_file_section *trace_sec; + ret = uname(&uts); + if (ret < 0) + return -1; - trace_sec = &feat_sec[idx++]; + return do_write_string(fd, uts.nodename); +} - /* Write trace info */ - trace_sec->offset = lseek(fd, 0, SEEK_CUR); - read_tracing_data(fd, attrs, nr_counters); - trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset; - } +static int write_osrelease(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + struct utsname uts; + int ret; - if (perf_header__has_feat(self, HEADER_BUILD_ID)) { - struct perf_file_section *buildid_sec; + ret = uname(&uts); + if (ret < 0) + return -1; - buildid_sec = &feat_sec[idx++]; + return do_write_string(fd, uts.release); +} - /* Write build-ids */ - buildid_sec->offset = lseek(fd, 0, SEEK_CUR); - err = dsos__write_buildid_table(self, fd); - if (err < 0) { - pr_debug("failed to write buildid table\n"); - goto out_free; +static int write_arch(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + struct utsname uts; + int ret; + + ret = uname(&uts); + if (ret < 0) + return -1; + + return do_write_string(fd, uts.machine); +} + +static int write_version(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + return do_write_string(fd, perf_version_string); +} + +static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ +#ifndef CPUINFO_PROC +#define CPUINFO_PROC NULL +#endif + FILE *file; + char *buf = NULL; + char *s, *p; + const char *search = CPUINFO_PROC; + size_t len = 0; + int ret = -1; + + if (!search) + return -1; + + file = fopen("/proc/cpuinfo", "r"); + if (!file) + return -1; + + while (getline(&buf, &len, file) > 0) { + ret = strncmp(buf, search, strlen(search)); + if (!ret) + break; + } + + if (ret) + goto done; + + s = buf; + + p = strchr(buf, ':'); + if (p && *(p+1) == ' ' && *(p+2)) + s = p + 2; + p = strchr(s, '\n'); + if (p) + *p = '\0'; + + /* squash extra space characters (branding string) */ + p = s; + while (*p) { + if (isspace(*p)) { + char *r = p + 1; + char *q = r; + *p = ' '; + while (*q && isspace(*q)) + q++; + if (q != (p+1)) + while ((*r++ = *q++)); } - buildid_sec->size = lseek(fd, 0, SEEK_CUR) - - buildid_sec->offset; - if (!no_buildid_cache) - perf_session__cache_build_ids(session); + p++; } + ret = do_write_string(fd, s); +done: + free(buf); + fclose(file); + return ret; +} - lseek(fd, sec_start, SEEK_SET); - err = do_write(fd, feat_sec, sec_size); - if (err < 0) - pr_debug("failed to write feature section\n"); -out_free: - free(feat_sec); - return err; +static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + long nr; + u32 nrc, nra; + int ret; + + nr = sysconf(_SC_NPROCESSORS_CONF); + if (nr < 0) + return -1; + + nrc = (u32)(nr & UINT_MAX); + + nr = sysconf(_SC_NPROCESSORS_ONLN); + if (nr < 0) + return -1; + + nra = (u32)(nr & UINT_MAX); + + ret = do_write(fd, &nrc, sizeof(nrc)); + if (ret < 0) + return ret; + + return do_write(fd, &nra, sizeof(nra)); } -int perf_header__write_pipe(int fd) +static int write_event_desc(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist) { - struct perf_pipe_file_header f_header; - int err; + struct perf_evsel *evsel; + u32 nre, nri, sz; + int ret; - f_header = (struct perf_pipe_file_header){ - .magic = PERF_MAGIC, - .size = sizeof(f_header), - }; + nre = evlist->nr_entries; - err = do_write(fd, &f_header, sizeof(f_header)); - if (err < 0) { - pr_debug("failed to write perf pipe header\n"); - return err; + /* + * write number of events + */ + ret = do_write(fd, &nre, sizeof(nre)); + if (ret < 0) + return ret; + + /* + * size of perf_event_attr struct + */ + sz = (u32)sizeof(evsel->attr); + ret = do_write(fd, &sz, sizeof(sz)); + if (ret < 0) + return ret; + + evlist__for_each(evlist, evsel) { + ret = do_write(fd, &evsel->attr, sz); + if (ret < 0) + return ret; + /* + * write number of unique id per event + * there is one id per instance of an event + * + * copy into an nri to be independent of the + * type of ids, + */ + nri = evsel->ids; + ret = do_write(fd, &nri, sizeof(nri)); + if (ret < 0) + return ret; + + /* + * write event string as passed on cmdline + */ + ret = do_write_string(fd, perf_evsel__name(evsel)); + if (ret < 0) + return ret; + /* + * write unique ids for this event + */ + ret = do_write(fd, evsel->id, evsel->ids * sizeof(u64)); + if (ret < 0) + return ret; } + return 0; +} + +static int write_cmdline(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + char buf[MAXPATHLEN]; + char proc[32]; + u32 i, n; + int ret; + + /* + * actual atual path to perf binary + */ + sprintf(proc, "/proc/%d/exe", getpid()); + ret = readlink(proc, buf, sizeof(buf)); + if (ret <= 0) + return -1; + /* readlink() does not add null termination */ + buf[ret] = '\0'; + + /* account for binary path */ + n = header_argc + 1; + + ret = do_write(fd, &n, sizeof(n)); + if (ret < 0) + return ret; + + ret = do_write_string(fd, buf); + if (ret < 0) + return ret; + + for (i = 0 ; i < header_argc; i++) { + ret = do_write_string(fd, header_argv[i]); + if (ret < 0) + return ret; + } return 0; } -int perf_header__write(struct perf_header *self, int fd, bool at_exit) +#define CORE_SIB_FMT \ + "/sys/devices/system/cpu/cpu%d/topology/core_siblings_list" +#define THRD_SIB_FMT \ + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list" + +struct cpu_topo { + u32 core_sib; + u32 thread_sib; + char **core_siblings; + char **thread_siblings; +}; + +static int build_cpu_topo(struct cpu_topo *tp, int cpu) { - struct perf_file_header f_header; - struct perf_file_attr f_attr; - struct perf_header_attr *attr; - int i, err; + FILE *fp; + 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) + goto try_threads; + + sret = getline(&buf, &len, fp); + fclose(fp); + if (sret <= 0) + goto try_threads; + + p = strchr(buf, '\n'); + if (p) + *p = '\0'; + + for (i = 0; i < tp->core_sib; i++) { + if (!strcmp(buf, tp->core_siblings[i])) + break; + } + if (i == tp->core_sib) { + tp->core_siblings[i] = buf; + tp->core_sib++; + buf = NULL; + len = 0; + } + ret = 0; - lseek(fd, sizeof(f_header), SEEK_SET); +try_threads: + sprintf(filename, THRD_SIB_FMT, cpu); + fp = fopen(filename, "r"); + if (!fp) + goto done; - for (i = 0; i < self->attrs; i++) { - attr = self->attr[i]; + if (getline(&buf, &len, fp) <= 0) + goto done; - attr->id_offset = lseek(fd, 0, SEEK_CUR); - err = do_write(fd, attr->id, attr->ids * sizeof(u64)); - if (err < 0) { - pr_debug("failed to write perf header\n"); - return err; - } + p = strchr(buf, '\n'); + if (p) + *p = '\0'; + + for (i = 0; i < tp->thread_sib; i++) { + if (!strcmp(buf, tp->thread_siblings[i])) + break; + } + if (i == tp->thread_sib) { + tp->thread_siblings[i] = buf; + tp->thread_sib++; + buf = NULL; } + ret = 0; +done: + if(fp) + fclose(fp); + free(buf); + return ret; +} +static void free_cpu_topo(struct cpu_topo *tp) +{ + u32 i; - self->attr_offset = lseek(fd, 0, SEEK_CUR); + if (!tp) + return; - for (i = 0; i < self->attrs; i++) { - attr = self->attr[i]; + for (i = 0 ; i < tp->core_sib; i++) + zfree(&tp->core_siblings[i]); - f_attr = (struct perf_file_attr){ - .attr = attr->attr, - .ids = { - .offset = attr->id_offset, - .size = attr->ids * sizeof(u64), - } - }; - err = do_write(fd, &f_attr, sizeof(f_attr)); - if (err < 0) { - pr_debug("failed to write perf header attribute\n"); - return err; - } + for (i = 0 ; i < tp->thread_sib; i++) + zfree(&tp->thread_siblings[i]); + + free(tp); +} + +static struct cpu_topo *build_cpu_topology(void) +{ + struct cpu_topo *tp; + void *addr; + u32 nr, i; + size_t sz; + long ncpus; + int ret = -1; + + ncpus = sysconf(_SC_NPROCESSORS_CONF); + if (ncpus < 0) + return NULL; + + nr = (u32)(ncpus & UINT_MAX); + + sz = nr * sizeof(char *); + + addr = calloc(1, sizeof(*tp) + 2 * sz); + if (!addr) + return NULL; + + tp = addr; + + addr += sizeof(*tp); + tp->core_siblings = addr; + addr += sz; + tp->thread_siblings = addr; + + for (i = 0; i < nr; i++) { + ret = build_cpu_topo(tp, i); + if (ret < 0) + break; } + if (ret) { + free_cpu_topo(tp); + tp = NULL; + } + return tp; +} - self->event_offset = lseek(fd, 0, SEEK_CUR); - self->event_size = event_count * sizeof(struct perf_trace_event_type); - if (events) { - err = do_write(fd, events, self->event_size); - if (err < 0) { - pr_debug("failed to write perf header events\n"); - return err; - } +static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + struct cpu_topo *tp; + u32 i; + int ret; + + tp = build_cpu_topology(); + if (!tp) + return -1; + + ret = do_write(fd, &tp->core_sib, sizeof(tp->core_sib)); + if (ret < 0) + goto done; + + for (i = 0; i < tp->core_sib; i++) { + ret = do_write_string(fd, tp->core_siblings[i]); + if (ret < 0) + goto done; } + ret = do_write(fd, &tp->thread_sib, sizeof(tp->thread_sib)); + if (ret < 0) + goto done; - self->data_offset = lseek(fd, 0, SEEK_CUR); + for (i = 0; i < tp->thread_sib; i++) { + ret = do_write_string(fd, tp->thread_siblings[i]); + if (ret < 0) + break; + } +done: + free_cpu_topo(tp); + return ret; +} - if (at_exit) { - err = perf_header__adds_write(self, fd); - if (err < 0) - return err; + + +static int write_total_mem(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + char *buf = NULL; + FILE *fp; + size_t len = 0; + int ret = -1, n; + uint64_t mem; + + fp = fopen("/proc/meminfo", "r"); + if (!fp) + return -1; + + while (getline(&buf, &len, fp) > 0) { + ret = strncmp(buf, "MemTotal:", 9); + if (!ret) + break; + } + if (!ret) { + n = sscanf(buf, "%*s %"PRIu64, &mem); + if (n == 1) + ret = do_write(fd, &mem, sizeof(mem)); } + free(buf); + fclose(fp); + return ret; +} - f_header = (struct perf_file_header){ - .magic = PERF_MAGIC, - .size = sizeof(f_header), - .attr_size = sizeof(f_attr), - .attrs = { - .offset = self->attr_offset, - .size = self->attrs * sizeof(f_attr), - }, - .data = { - .offset = self->data_offset, - .size = self->data_size, - }, - .event_types = { - .offset = self->event_offset, - .size = self->event_size, - }, - }; +static int write_topo_node(int fd, int node) +{ + char str[MAXPATHLEN]; + char field[32]; + char *buf = NULL, *p; + size_t len = 0; + FILE *fp; + u64 mem_total, mem_free, mem; + int ret = -1; + + sprintf(str, "/sys/devices/system/node/node%d/meminfo", node); + fp = fopen(str, "r"); + if (!fp) + return -1; - memcpy(&f_header.adds_features, &self->adds_features, sizeof(self->adds_features)); + while (getline(&buf, &len, fp) > 0) { + /* skip over invalid lines */ + if (!strchr(buf, ':')) + continue; + if (sscanf(buf, "%*s %*d %31s %"PRIu64, field, &mem) != 2) + goto done; + if (!strcmp(field, "MemTotal:")) + mem_total = mem; + if (!strcmp(field, "MemFree:")) + mem_free = mem; + } - lseek(fd, 0, SEEK_SET); - err = do_write(fd, &f_header, sizeof(f_header)); - if (err < 0) { - pr_debug("failed to write perf header\n"); - return err; + fclose(fp); + fp = NULL; + + ret = do_write(fd, &mem_total, sizeof(u64)); + if (ret) + goto done; + + ret = do_write(fd, &mem_free, sizeof(u64)); + if (ret) + goto done; + + ret = -1; + sprintf(str, "/sys/devices/system/node/node%d/cpulist", node); + + fp = fopen(str, "r"); + if (!fp) + goto done; + + if (getline(&buf, &len, fp) <= 0) + goto done; + + p = strchr(buf, '\n'); + if (p) + *p = '\0'; + + ret = do_write_string(fd, buf); +done: + free(buf); + if (fp) + fclose(fp); + return ret; +} + +static int write_numa_topology(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + char *buf = NULL; + size_t len = 0; + FILE *fp; + struct cpu_map *node_map = NULL; + char *c; + u32 nr, i, j; + int ret = -1; + + fp = fopen("/sys/devices/system/node/online", "r"); + if (!fp) + return -1; + + if (getline(&buf, &len, fp) <= 0) + goto done; + + c = strchr(buf, '\n'); + if (c) + *c = '\0'; + + node_map = cpu_map__new(buf); + if (!node_map) + goto done; + + nr = (u32)node_map->nr; + + ret = do_write(fd, &nr, sizeof(nr)); + if (ret < 0) + goto done; + + for (i = 0; i < nr; i++) { + j = (u32)node_map->map[i]; + ret = do_write(fd, &j, sizeof(j)); + if (ret < 0) + break; + + ret = write_topo_node(fd, i); + if (ret < 0) + break; + } +done: + free(buf); + fclose(fp); + free(node_map); + return ret; +} + +/* + * File format: + * + * struct pmu_mappings { + * u32 pmu_num; + * struct pmu_map { + * u32 type; + * char name[]; + * }[pmu_num]; + * }; + */ + +static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + struct perf_pmu *pmu = NULL; + off_t offset = lseek(fd, 0, SEEK_CUR); + __u32 pmu_num = 0; + int ret; + + /* write real pmu_num later */ + ret = do_write(fd, &pmu_num, sizeof(pmu_num)); + if (ret < 0) + return ret; + + while ((pmu = perf_pmu__scan(pmu))) { + if (!pmu->name) + continue; + pmu_num++; + + ret = do_write(fd, &pmu->type, sizeof(pmu->type)); + if (ret < 0) + return ret; + + ret = do_write_string(fd, pmu->name); + if (ret < 0) + return ret; + } + + if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) { + /* discard all */ + lseek(fd, offset, SEEK_SET); + return -1; } - lseek(fd, self->data_offset + self->data_size, SEEK_SET); - self->frozen = 1; return 0; } -static int perf_header__getbuffer64(struct perf_header *self, - int fd, void *buf, size_t size) +/* + * File format: + * + * struct group_descs { + * u32 nr_groups; + * struct group_desc { + * char name[]; + * u32 leader_idx; + * u32 nr_members; + * }[nr_groups]; + * }; + */ +static int write_group_desc(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist) { - if (do_read(fd, buf, size) <= 0) - return -1; + u32 nr_groups = evlist->nr_groups; + struct perf_evsel *evsel; + int ret; - if (self->needs_swap) - mem_bswap_64(buf, size); + ret = do_write(fd, &nr_groups, sizeof(nr_groups)); + if (ret < 0) + return ret; + + evlist__for_each(evlist, evsel) { + if (perf_evsel__is_group_leader(evsel) && + evsel->nr_members > 1) { + const char *name = evsel->group_name ?: "{anon_group}"; + u32 leader_idx = evsel->idx; + u32 nr_members = evsel->nr_members; + + ret = do_write_string(fd, name); + if (ret < 0) + return ret; + ret = do_write(fd, &leader_idx, sizeof(leader_idx)); + if (ret < 0) + return ret; + + ret = do_write(fd, &nr_members, sizeof(nr_members)); + if (ret < 0) + return ret; + } + } return 0; } -int perf_header__process_sections(struct perf_header *self, int fd, - int (*process)(struct perf_file_section *self, - struct perf_header *ph, - int feat, int fd)) +/* + * default get_cpuid(): nothing gets recorded + * actual implementation must be in arch/$(ARCH)/util/header.c + */ +int __attribute__ ((weak)) get_cpuid(char *buffer __maybe_unused, + size_t sz __maybe_unused) { - struct perf_file_section *feat_sec; - int nr_sections; - int sec_size; - int idx = 0; - int err = -1, feat = 1; + return -1; +} - nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS); - if (!nr_sections) - return 0; +static int write_cpuid(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + char buffer[64]; + int ret; - feat_sec = calloc(sizeof(*feat_sec), nr_sections); - if (!feat_sec) - return -1; + ret = get_cpuid(buffer, sizeof(buffer)); + if (!ret) + goto write_it; - sec_size = sizeof(*feat_sec) * nr_sections; + return -1; +write_it: + return do_write_string(fd, buffer); +} - lseek(fd, self->data_offset + self->data_size, SEEK_SET); +static int write_branch_stack(int fd __maybe_unused, + struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + return 0; +} - if (perf_header__getbuffer64(self, fd, feat_sec, sec_size)) - goto out_free; +static void print_hostname(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + fprintf(fp, "# hostname : %s\n", ph->env.hostname); +} - err = 0; - while (idx < nr_sections && feat < HEADER_LAST_FEATURE) { - if (perf_header__has_feat(self, feat)) { - struct perf_file_section *sec = &feat_sec[idx++]; +static void print_osrelease(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + fprintf(fp, "# os release : %s\n", ph->env.os_release); +} + +static void print_arch(struct perf_header *ph, int fd __maybe_unused, FILE *fp) +{ + fprintf(fp, "# arch : %s\n", ph->env.arch); +} + +static void print_cpudesc(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + fprintf(fp, "# cpudesc : %s\n", ph->env.cpu_desc); +} - err = process(sec, self, feat, fd); - if (err < 0) - break; +static void print_nrcpus(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + fprintf(fp, "# nrcpus online : %u\n", ph->env.nr_cpus_online); + fprintf(fp, "# nrcpus avail : %u\n", ph->env.nr_cpus_avail); +} + +static void print_version(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + fprintf(fp, "# perf version : %s\n", ph->env.version); +} + +static void print_cmdline(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + int nr, i; + char *str; + + nr = ph->env.nr_cmdline; + str = ph->env.cmdline; + + fprintf(fp, "# cmdline : "); + + for (i = 0; i < nr; i++) { + fprintf(fp, "%s ", str); + str += strlen(str) + 1; + } + fputc('\n', fp); +} + +static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + int nr, i; + char *str; + + nr = ph->env.nr_sibling_cores; + str = ph->env.sibling_cores; + + for (i = 0; i < nr; i++) { + fprintf(fp, "# sibling cores : %s\n", str); + str += strlen(str) + 1; + } + + nr = ph->env.nr_sibling_threads; + str = ph->env.sibling_threads; + + for (i = 0; i < nr; i++) { + fprintf(fp, "# sibling threads : %s\n", str); + str += strlen(str) + 1; + } +} + +static void free_event_desc(struct perf_evsel *events) +{ + struct perf_evsel *evsel; + + if (!events) + return; + + for (evsel = events; evsel->attr.size; evsel++) { + zfree(&evsel->name); + zfree(&evsel->id); + } + + free(events); +} + +static struct perf_evsel * +read_event_desc(struct perf_header *ph, int fd) +{ + struct perf_evsel *evsel, *events = NULL; + u64 *id; + void *buf = NULL; + u32 nre, sz, nr, i, j; + ssize_t ret; + size_t msz; + + /* number of events */ + ret = readn(fd, &nre, sizeof(nre)); + if (ret != (ssize_t)sizeof(nre)) + goto error; + + if (ph->needs_swap) + nre = bswap_32(nre); + + ret = readn(fd, &sz, sizeof(sz)); + if (ret != (ssize_t)sizeof(sz)) + goto error; + + if (ph->needs_swap) + sz = bswap_32(sz); + + /* buffer to hold on file attr struct */ + buf = malloc(sz); + if (!buf) + goto error; + + /* the last event terminates with evsel->attr.size == 0: */ + events = calloc(nre + 1, sizeof(*events)); + if (!events) + goto error; + + msz = sizeof(evsel->attr); + if (sz < msz) + msz = sz; + + for (i = 0, evsel = events; i < nre; evsel++, i++) { + evsel->idx = i; + + /* + * must read entire on-file attr struct to + * sync up with layout. + */ + ret = readn(fd, buf, sz); + if (ret != (ssize_t)sz) + goto error; + + if (ph->needs_swap) + perf_event__attr_swap(buf); + + memcpy(&evsel->attr, buf, msz); + + ret = readn(fd, &nr, sizeof(nr)); + if (ret != (ssize_t)sizeof(nr)) + goto error; + + if (ph->needs_swap) { + nr = bswap_32(nr); + evsel->needs_swap = true; + } + + evsel->name = do_read_string(fd, ph); + + if (!nr) + continue; + + id = calloc(nr, sizeof(*id)); + if (!id) + goto error; + evsel->ids = nr; + evsel->id = id; + + for (j = 0 ; j < nr; j++) { + ret = readn(fd, id, sizeof(*id)); + if (ret != (ssize_t)sizeof(*id)) + goto error; + if (ph->needs_swap) + *id = bswap_64(*id); + id++; } - ++feat; } -out_free: - free(feat_sec); - return err; +out: + free(buf); + return events; +error: + if (events) + free_event_desc(events); + events = NULL; + goto out; } -int perf_file_header__read(struct perf_file_header *self, - struct perf_header *ph, int fd) +static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) { - lseek(fd, 0, SEEK_SET); + struct perf_evsel *evsel, *events = read_event_desc(ph, fd); + u32 j; + u64 *id; - if (do_read(fd, self, sizeof(*self)) <= 0 || - memcmp(&self->magic, __perf_magic, sizeof(self->magic))) - return -1; + if (!events) { + fprintf(fp, "# event desc: not available or unable to read\n"); + return; + } + + for (evsel = events; evsel->attr.size; evsel++) { + fprintf(fp, "# event : name = %s, ", evsel->name); + + fprintf(fp, "type = %d, config = 0x%"PRIx64 + ", config1 = 0x%"PRIx64", config2 = 0x%"PRIx64, + evsel->attr.type, + (u64)evsel->attr.config, + (u64)evsel->attr.config1, + (u64)evsel->attr.config2); + + fprintf(fp, ", excl_usr = %d, excl_kern = %d", + evsel->attr.exclude_user, + evsel->attr.exclude_kernel); + + fprintf(fp, ", excl_host = %d, excl_guest = %d", + evsel->attr.exclude_host, + evsel->attr.exclude_guest); + + 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++) { + if (j) + fputc(',', fp); + fprintf(fp, " %"PRIu64, *id); + } + fprintf(fp, " }"); + } - if (self->attr_size != sizeof(struct perf_file_attr)) { - u64 attr_size = bswap_64(self->attr_size); + fputc('\n', fp); + } - if (attr_size != sizeof(struct perf_file_attr)) - return -1; + free_event_desc(events); +} + +static void print_total_mem(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + fprintf(fp, "# total memory : %Lu kB\n", ph->env.total_mem); +} - mem_bswap_64(self, offsetof(struct perf_file_header, - adds_features)); - ph->needs_swap = true; +static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + u32 nr, c, i; + char *str, *tmp; + uint64_t mem_total, mem_free; + + /* nr nodes */ + nr = ph->env.nr_numa_nodes; + str = ph->env.numa_nodes; + + for (i = 0; i < nr; i++) { + /* node number */ + c = strtoul(str, &tmp, 0); + if (*tmp != ':') + goto error; + + str = tmp + 1; + mem_total = strtoull(str, &tmp, 0); + if (*tmp != ':') + goto error; + + str = tmp + 1; + mem_free = strtoull(str, &tmp, 0); + if (*tmp != ':') + goto error; + + fprintf(fp, "# node%u meminfo : total = %"PRIu64" kB," + " free = %"PRIu64" kB\n", + c, mem_total, mem_free); + + str = tmp + 1; + fprintf(fp, "# node%u cpu list : %s\n", c, str); + + str += strlen(str) + 1; } + return; +error: + fprintf(fp, "# numa topology : not available\n"); +} - if (self->size != sizeof(*self)) { - /* Support the previous format */ - if (self->size == offsetof(typeof(*self), adds_features)) - bitmap_zero(self->adds_features, HEADER_FEAT_BITS); - else - return -1; +static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp) +{ + fprintf(fp, "# cpuid : %s\n", ph->env.cpuid); +} + +static void print_branch_stack(struct perf_header *ph __maybe_unused, + int fd __maybe_unused, FILE *fp) +{ + fprintf(fp, "# contains samples with branch stack\n"); +} + +static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + const char *delimiter = "# pmu mappings: "; + char *str, *tmp; + u32 pmu_num; + u32 type; + + pmu_num = ph->env.nr_pmu_mappings; + if (!pmu_num) { + fprintf(fp, "# pmu mappings: not available\n"); + return; } - memcpy(&ph->adds_features, &self->adds_features, - sizeof(ph->adds_features)); - /* - * FIXME: hack that assumes that if we need swap the perf.data file - * may be coming from an arch with a different word-size, ergo different - * DEFINE_BITMAP format, investigate more later, but for now its mostly - * safe to assume that we have a build-id section. Trace files probably - * have several other issues in this realm anyway... - */ - if (ph->needs_swap) { - memset(&ph->adds_features, 0, sizeof(ph->adds_features)); - perf_header__set_feat(ph, HEADER_BUILD_ID); + str = ph->env.pmu_mappings; + + while (pmu_num) { + type = strtoul(str, &tmp, 0); + if (*tmp != ':') + goto error; + + str = tmp + 1; + fprintf(fp, "%s%s = %" PRIu32, delimiter, str, type); + + delimiter = ", "; + str += strlen(str) + 1; + pmu_num--; } - ph->event_offset = self->event_types.offset; - ph->event_size = self->event_types.size; - ph->data_offset = self->data.offset; - ph->data_size = self->data.size; - return 0; + fprintf(fp, "\n"); + + if (!pmu_num) + return; +error: + fprintf(fp, "# pmu mappings: unable to read\n"); +} + +static void print_group_desc(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + struct perf_session *session; + struct perf_evsel *evsel; + u32 nr = 0; + + session = container_of(ph, struct perf_session, header); + + evlist__for_each(session->evlist, evsel) { + if (perf_evsel__is_group_leader(evsel) && + evsel->nr_members > 1) { + fprintf(fp, "# group: %s{%s", evsel->group_name ?: "", + perf_evsel__name(evsel)); + + nr = evsel->nr_members - 1; + } else if (nr) { + fprintf(fp, ",%s", perf_evsel__name(evsel)); + + if (--nr == 0) + fprintf(fp, "}\n"); + } + } } static int __event_process_build_id(struct build_id_event *bev, @@ -752,28 +1557,91 @@ out: return err; } -static int perf_header__read_build_ids(struct perf_header *self, - int input, u64 offset, u64 size) +static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, + int input, u64 offset, u64 size) { - struct perf_session *session = container_of(self, - struct perf_session, header); + struct perf_session *session = container_of(header, struct perf_session, header); + struct { + struct perf_event_header header; + u8 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))]; + char filename[0]; + } old_bev; struct build_id_event bev; char filename[PATH_MAX]; u64 limit = offset + size; + + while (offset < limit) { + ssize_t len; + + if (readn(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev)) + return -1; + + if (header->needs_swap) + perf_event_header__bswap(&old_bev.header); + + len = old_bev.header.size - sizeof(old_bev); + if (readn(input, filename, len) != len) + return -1; + + bev.header = old_bev.header; + + /* + * As the pid is the missing value, we need to fill + * it properly. The header.misc value give us nice hint. + */ + bev.pid = HOST_KERNEL_ID; + if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER || + bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL) + bev.pid = DEFAULT_GUEST_KERNEL_ID; + + memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id)); + __event_process_build_id(&bev, filename, session); + + offset += bev.header.size; + } + + return 0; +} + +static int perf_header__read_build_ids(struct perf_header *header, + int input, u64 offset, u64 size) +{ + struct perf_session *session = container_of(header, struct perf_session, header); + struct build_id_event bev; + char filename[PATH_MAX]; + u64 limit = offset + size, orig_offset = offset; int err = -1; while (offset < limit) { ssize_t len; - if (read(input, &bev, sizeof(bev)) != sizeof(bev)) + if (readn(input, &bev, sizeof(bev)) != sizeof(bev)) goto out; - if (self->needs_swap) + if (header->needs_swap) perf_event_header__bswap(&bev.header); len = bev.header.size - sizeof(bev); - if (read(input, filename, len) != len) + if (readn(input, filename, len) != len) goto out; + /* + * The a1645ce1 changeset: + * + * "perf: 'perf kvm' tool for monitoring guest performance from host" + * + * Added a field to struct build_id_event that broke the file + * format. + * + * Since the kernel build-id is the first entry, process the + * table using the old format if the well known + * '[kernel.kallsyms]' string for the kernel build-id has the + * first 4 characters chopped off (where the pid_t sits). + */ + if (memcmp(filename, "nel.kallsyms]", 13) == 0) { + if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1) + return -1; + return perf_header__read_build_ids_abi_quirk(header, input, offset, size); + } __event_process_build_id(&bev, filename, session); @@ -784,304 +1652,1248 @@ out: return err; } -static int perf_file_section__process(struct perf_file_section *self, - struct perf_header *ph, - int feat, int fd) +static int process_tracing_data(struct perf_file_section *section __maybe_unused, + struct perf_header *ph __maybe_unused, + int fd, void *data) +{ + ssize_t ret = trace_report(fd, data, false); + return ret < 0 ? -1 : 0; +} + +static int process_build_id(struct perf_file_section *section, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + if (perf_header__read_build_ids(ph, fd, section->offset, section->size)) + pr_debug("Failed to read buildids, continuing...\n"); + return 0; +} + +static int process_hostname(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.hostname = do_read_string(fd, ph); + return ph->env.hostname ? 0 : -ENOMEM; +} + +static int process_osrelease(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.os_release = do_read_string(fd, ph); + return ph->env.os_release ? 0 : -ENOMEM; +} + +static int process_version(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.version = do_read_string(fd, ph); + return ph->env.version ? 0 : -ENOMEM; +} + +static int process_arch(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.arch = do_read_string(fd, ph); + return ph->env.arch ? 0 : -ENOMEM; +} + +static int process_nrcpus(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ssize_t ret; + u32 nr; + + ret = readn(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + return -1; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_cpus_online = nr; + + ret = readn(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + return -1; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_cpus_avail = nr; + return 0; +} + +static int process_cpudesc(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.cpu_desc = do_read_string(fd, ph); + return ph->env.cpu_desc ? 0 : -ENOMEM; +} + +static int process_cpuid(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.cpuid = do_read_string(fd, ph); + return ph->env.cpuid ? 0 : -ENOMEM; +} + +static int process_total_mem(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) { - if (lseek(fd, self->offset, SEEK_SET) == (off_t)-1) { - pr_debug("Failed to lseek to %Ld offset for feature %d, " - "continuing...\n", self->offset, feat); + uint64_t mem; + ssize_t ret; + + ret = readn(fd, &mem, sizeof(mem)); + if (ret != sizeof(mem)) + return -1; + + if (ph->needs_swap) + mem = bswap_64(mem); + + ph->env.total_mem = mem; + return 0; +} + +static struct perf_evsel * +perf_evlist__find_by_index(struct perf_evlist *evlist, int idx) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + if (evsel->idx == idx) + return evsel; + } + + return NULL; +} + +static void +perf_evlist__set_event_name(struct perf_evlist *evlist, + struct perf_evsel *event) +{ + struct perf_evsel *evsel; + + if (!event->name) + return; + + evsel = perf_evlist__find_by_index(evlist, event->idx); + if (!evsel) + return; + + if (evsel->name) + return; + + evsel->name = strdup(event->name); +} + +static int +process_event_desc(struct perf_file_section *section __maybe_unused, + struct perf_header *header, int fd, + void *data __maybe_unused) +{ + struct perf_session *session; + struct perf_evsel *evsel, *events = read_event_desc(header, fd); + + if (!events) return 0; + + session = container_of(header, struct perf_session, header); + for (evsel = events; evsel->attr.size; evsel++) + perf_evlist__set_event_name(session->evlist, evsel); + + free_event_desc(events); + + return 0; +} + +static int process_cmdline(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ssize_t ret; + char *str; + u32 nr, i; + struct strbuf sb; + + ret = readn(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + return -1; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_cmdline = nr; + strbuf_init(&sb, 128); + + for (i = 0; i < nr; i++) { + str = do_read_string(fd, ph); + if (!str) + goto error; + + /* include a NULL character at the end */ + strbuf_add(&sb, str, strlen(str) + 1); + free(str); } + ph->env.cmdline = strbuf_detach(&sb, NULL); + return 0; - switch (feat) { - case HEADER_TRACE_INFO: - trace_report(fd, false); - break; +error: + strbuf_release(&sb); + return -1; +} - case HEADER_BUILD_ID: - if (perf_header__read_build_ids(ph, fd, self->offset, self->size)) - pr_debug("Failed to read buildids, continuing...\n"); - break; - default: - pr_debug("unknown feature %d, continuing...\n", feat); +static int process_cpu_topology(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ssize_t ret; + u32 nr, i; + char *str; + struct strbuf sb; + + ret = readn(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + return -1; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_sibling_cores = nr; + strbuf_init(&sb, 128); + + for (i = 0; i < nr; i++) { + str = do_read_string(fd, ph); + if (!str) + goto error; + + /* include a NULL character at the end */ + strbuf_add(&sb, str, strlen(str) + 1); + free(str); } + ph->env.sibling_cores = strbuf_detach(&sb, NULL); + + ret = readn(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + return -1; + + if (ph->needs_swap) + nr = bswap_32(nr); + ph->env.nr_sibling_threads = nr; + + for (i = 0; i < nr; i++) { + str = do_read_string(fd, ph); + if (!str) + goto error; + + /* include a NULL character at the end */ + strbuf_add(&sb, str, strlen(str) + 1); + free(str); + } + ph->env.sibling_threads = strbuf_detach(&sb, NULL); return 0; + +error: + strbuf_release(&sb); + return -1; } -static int perf_file_header__read_pipe(struct perf_pipe_file_header *self, - struct perf_header *ph, int fd, - bool repipe) +static int process_numa_topology(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) { - if (do_read(fd, self, sizeof(*self)) <= 0 || - memcmp(&self->magic, __perf_magic, sizeof(self->magic))) + ssize_t ret; + u32 nr, node, i; + char *str; + uint64_t mem_total, mem_free; + struct strbuf sb; + + /* nr nodes */ + ret = readn(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + goto error; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_numa_nodes = nr; + strbuf_init(&sb, 256); + + for (i = 0; i < nr; i++) { + /* node number */ + ret = readn(fd, &node, sizeof(node)); + if (ret != sizeof(node)) + goto error; + + ret = readn(fd, &mem_total, sizeof(u64)); + if (ret != sizeof(u64)) + goto error; + + ret = readn(fd, &mem_free, sizeof(u64)); + if (ret != sizeof(u64)) + goto error; + + if (ph->needs_swap) { + node = bswap_32(node); + mem_total = bswap_64(mem_total); + mem_free = bswap_64(mem_free); + } + + strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":", + node, mem_total, mem_free); + + str = do_read_string(fd, ph); + if (!str) + goto error; + + /* include a NULL character at the end */ + strbuf_add(&sb, str, strlen(str) + 1); + free(str); + } + ph->env.numa_nodes = strbuf_detach(&sb, NULL); + return 0; + +error: + strbuf_release(&sb); + return -1; +} + +static int process_pmu_mappings(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ssize_t ret; + char *name; + u32 pmu_num; + u32 type; + struct strbuf sb; + + ret = readn(fd, &pmu_num, sizeof(pmu_num)); + if (ret != sizeof(pmu_num)) return -1; - if (repipe && do_write(STDOUT_FILENO, self, sizeof(*self)) < 0) + if (ph->needs_swap) + pmu_num = bswap_32(pmu_num); + + if (!pmu_num) { + pr_debug("pmu mappings not available\n"); + return 0; + } + + ph->env.nr_pmu_mappings = pmu_num; + strbuf_init(&sb, 128); + + while (pmu_num) { + if (readn(fd, &type, sizeof(type)) != sizeof(type)) + goto error; + if (ph->needs_swap) + type = bswap_32(type); + + name = do_read_string(fd, ph); + if (!name) + goto error; + + strbuf_addf(&sb, "%u:%s", type, name); + /* include a NULL character at the end */ + strbuf_add(&sb, "", 1); + + free(name); + pmu_num--; + } + ph->env.pmu_mappings = strbuf_detach(&sb, NULL); + return 0; + +error: + strbuf_release(&sb); + return -1; +} + +static int process_group_desc(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + size_t ret = -1; + u32 i, nr, nr_groups; + struct perf_session *session; + struct perf_evsel *evsel, *leader = NULL; + struct group_desc { + char *name; + u32 leader_idx; + u32 nr_members; + } *desc; + + if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups)) return -1; - if (self->size != sizeof(*self)) { - u64 size = bswap_64(self->size); + if (ph->needs_swap) + nr_groups = bswap_32(nr_groups); - if (size != sizeof(*self)) - return -1; + ph->env.nr_groups = nr_groups; + if (!nr_groups) { + pr_debug("group desc not available\n"); + return 0; + } + + desc = calloc(nr_groups, sizeof(*desc)); + if (!desc) + return -1; - ph->needs_swap = true; + for (i = 0; i < nr_groups; i++) { + desc[i].name = do_read_string(fd, ph); + if (!desc[i].name) + goto out_free; + + if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32)) + goto out_free; + + if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32)) + goto out_free; + + if (ph->needs_swap) { + desc[i].leader_idx = bswap_32(desc[i].leader_idx); + desc[i].nr_members = bswap_32(desc[i].nr_members); + } } - return 0; + /* + * Rebuild group relationship based on the group_desc + */ + session = container_of(ph, struct perf_session, header); + session->evlist->nr_groups = nr_groups; + + i = nr = 0; + evlist__for_each(session->evlist, evsel) { + if (evsel->idx == (int) desc[i].leader_idx) { + evsel->leader = evsel; + /* {anon_group} is a dummy name */ + if (strcmp(desc[i].name, "{anon_group}")) { + evsel->group_name = desc[i].name; + desc[i].name = NULL; + } + evsel->nr_members = desc[i].nr_members; + + if (i >= nr_groups || nr > 0) { + pr_debug("invalid group desc\n"); + goto out_free; + } + + leader = evsel; + nr = evsel->nr_members - 1; + i++; + } else if (nr) { + /* This is a group member */ + evsel->leader = leader; + + nr--; + } + } + + if (i != nr_groups || nr != 0) { + pr_debug("invalid group desc\n"); + goto out_free; + } + + ret = 0; +out_free: + for (i = 0; i < nr_groups; i++) + zfree(&desc[i].name); + free(desc); + + return ret; } -static int perf_header__read_pipe(struct perf_session *session, int fd) +struct feature_ops { + int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); + void (*print)(struct perf_header *h, int fd, FILE *fp); + int (*process)(struct perf_file_section *section, + struct perf_header *h, int fd, void *data); + const char *name; + bool full_only; +}; + +#define FEAT_OPA(n, func) \ + [n] = { .name = #n, .write = write_##func, .print = print_##func } +#define FEAT_OPP(n, func) \ + [n] = { .name = #n, .write = write_##func, .print = print_##func, \ + .process = process_##func } +#define FEAT_OPF(n, func) \ + [n] = { .name = #n, .write = write_##func, .print = print_##func, \ + .process = process_##func, .full_only = true } + +/* feature_ops not implemented: */ +#define print_tracing_data NULL +#define print_build_id NULL + +static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { + FEAT_OPP(HEADER_TRACING_DATA, tracing_data), + FEAT_OPP(HEADER_BUILD_ID, build_id), + FEAT_OPP(HEADER_HOSTNAME, hostname), + FEAT_OPP(HEADER_OSRELEASE, osrelease), + FEAT_OPP(HEADER_VERSION, version), + FEAT_OPP(HEADER_ARCH, arch), + FEAT_OPP(HEADER_NRCPUS, nrcpus), + FEAT_OPP(HEADER_CPUDESC, cpudesc), + FEAT_OPP(HEADER_CPUID, cpuid), + FEAT_OPP(HEADER_TOTAL_MEM, total_mem), + FEAT_OPP(HEADER_EVENT_DESC, event_desc), + FEAT_OPP(HEADER_CMDLINE, cmdline), + FEAT_OPF(HEADER_CPU_TOPOLOGY, cpu_topology), + FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology), + FEAT_OPA(HEADER_BRANCH_STACK, branch_stack), + FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings), + FEAT_OPP(HEADER_GROUP_DESC, group_desc), +}; + +struct header_print_data { + FILE *fp; + bool full; /* extended list of headers */ +}; + +static int perf_file_section__fprintf_info(struct perf_file_section *section, + struct perf_header *ph, + int feat, int fd, void *data) { - struct perf_header *self = &session->header; - struct perf_pipe_file_header f_header; + struct header_print_data *hd = data; - if (perf_file_header__read_pipe(&f_header, self, fd, - session->repipe) < 0) { - pr_debug("incompatible file format\n"); - return -EINVAL; + if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { + pr_debug("Failed to lseek to %" PRIu64 " offset for feature " + "%d, continuing...\n", section->offset, feat); + return 0; + } + if (feat >= HEADER_LAST_FEATURE) { + pr_warning("unknown feature %d\n", feat); + return 0; } + if (!feat_ops[feat].print) + return 0; - session->fd = fd; + if (!feat_ops[feat].full_only || hd->full) + feat_ops[feat].print(ph, fd, hd->fp); + else + fprintf(hd->fp, "# %s info available, use -I to display\n", + feat_ops[feat].name); return 0; } -int perf_header__read(struct perf_session *session, int fd) +int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) { - struct perf_header *self = &session->header; - struct perf_file_header f_header; - struct perf_file_attr f_attr; - u64 f_id; - int nr_attrs, nr_ids, i, j; + struct header_print_data hd; + struct perf_header *header = &session->header; + int fd = perf_data_file__fd(session->file); + hd.fp = fp; + hd.full = full; + + perf_header__process_sections(header, fd, &hd, + perf_file_section__fprintf_info); + return 0; +} - if (session->fd_pipe) - return perf_header__read_pipe(session, fd); +static int do_write_feat(int fd, struct perf_header *h, int type, + struct perf_file_section **p, + struct perf_evlist *evlist) +{ + int err; + int ret = 0; - if (perf_file_header__read(&f_header, self, fd) < 0) { - pr_debug("incompatible file format\n"); - return -EINVAL; + if (perf_header__has_feat(h, type)) { + if (!feat_ops[type].write) + return -1; + + (*p)->offset = lseek(fd, 0, SEEK_CUR); + + err = feat_ops[type].write(fd, h, evlist); + if (err < 0) { + pr_debug("failed to write feature %d\n", type); + + /* undo anything written */ + lseek(fd, (*p)->offset, SEEK_SET); + + return -1; + } + (*p)->size = lseek(fd, 0, SEEK_CUR) - (*p)->offset; + (*p)++; } + return ret; +} - nr_attrs = f_header.attrs.size / sizeof(f_attr); - lseek(fd, f_header.attrs.offset, SEEK_SET); +static int perf_header__adds_write(struct perf_header *header, + struct perf_evlist *evlist, int fd) +{ + int nr_sections; + struct perf_file_section *feat_sec, *p; + int sec_size; + u64 sec_start; + int feat; + int err; - for (i = 0; i < nr_attrs; i++) { - struct perf_header_attr *attr; - off_t tmp; + nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); + if (!nr_sections) + return 0; - if (perf_header__getbuffer64(self, fd, &f_attr, sizeof(f_attr))) - goto out_errno; + feat_sec = p = calloc(nr_sections, sizeof(*feat_sec)); + if (feat_sec == NULL) + return -ENOMEM; - tmp = lseek(fd, 0, SEEK_CUR); + sec_size = sizeof(*feat_sec) * nr_sections; - attr = perf_header_attr__new(&f_attr.attr); - if (attr == NULL) - return -ENOMEM; + sec_start = header->feat_offset; + lseek(fd, sec_start + sec_size, SEEK_SET); - nr_ids = f_attr.ids.size / sizeof(u64); - lseek(fd, f_attr.ids.offset, SEEK_SET); + for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { + if (do_write_feat(fd, header, feat, &p, evlist)) + perf_header__clear_feat(header, feat); + } - for (j = 0; j < nr_ids; j++) { - if (perf_header__getbuffer64(self, fd, &f_id, sizeof(f_id))) - goto out_errno; + lseek(fd, sec_start, SEEK_SET); + /* + * may write more than needed due to dropped feature, but + * this is okay, reader will skip the mising entries + */ + err = do_write(fd, feat_sec, sec_size); + if (err < 0) + pr_debug("failed to write feature section\n"); + free(feat_sec); + return err; +} - if (perf_header_attr__add_id(attr, f_id) < 0) { - perf_header_attr__delete(attr); - return -ENOMEM; - } +int perf_header__write_pipe(int fd) +{ + struct perf_pipe_file_header f_header; + int err; + + f_header = (struct perf_pipe_file_header){ + .magic = PERF_MAGIC, + .size = sizeof(f_header), + }; + + err = do_write(fd, &f_header, sizeof(f_header)); + if (err < 0) { + pr_debug("failed to write perf pipe header\n"); + return err; + } + + return 0; +} + +int perf_session__write_header(struct perf_session *session, + struct perf_evlist *evlist, + int fd, bool at_exit) +{ + struct perf_file_header f_header; + 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); + + evlist__for_each(session->evlist, evsel) { + evsel->id_offset = lseek(fd, 0, SEEK_CUR); + err = do_write(fd, evsel->id, evsel->ids * sizeof(u64)); + if (err < 0) { + pr_debug("failed to write perf header\n"); + return err; } - if (perf_header__add_attr(self, attr) < 0) { - perf_header_attr__delete(attr); - return -ENOMEM; + } + + attr_offset = lseek(fd, 0, SEEK_CUR); + + evlist__for_each(evlist, evsel) { + f_attr = (struct perf_file_attr){ + .attr = evsel->attr, + .ids = { + .offset = evsel->id_offset, + .size = evsel->ids * sizeof(u64), + } + }; + err = do_write(fd, &f_attr, sizeof(f_attr)); + if (err < 0) { + pr_debug("failed to write perf header attribute\n"); + return err; } + } - lseek(fd, tmp, SEEK_SET); + if (!header->data_offset) + 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); + if (err < 0) + return err; } - if (f_header.event_types.size) { - lseek(fd, f_header.event_types.offset, SEEK_SET); - events = malloc(f_header.event_types.size); - if (events == NULL) - return -ENOMEM; - if (perf_header__getbuffer64(self, fd, events, - f_header.event_types.size)) - goto out_errno; - event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); + f_header = (struct perf_file_header){ + .magic = PERF_MAGIC, + .size = sizeof(f_header), + .attr_size = sizeof(f_attr), + .attrs = { + .offset = attr_offset, + .size = evlist->nr_entries * sizeof(f_attr), + }, + .data = { + .offset = header->data_offset, + .size = header->data_size, + }, + /* event_types is ignored, store zeros */ + }; + + memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features)); + + lseek(fd, 0, SEEK_SET); + err = do_write(fd, &f_header, sizeof(f_header)); + if (err < 0) { + pr_debug("failed to write perf header\n"); + return err; } + lseek(fd, header->data_offset + header->data_size, SEEK_SET); - perf_header__process_sections(self, fd, perf_file_section__process); + return 0; +} - lseek(fd, self->data_offset, SEEK_SET); +static int perf_header__getbuffer64(struct perf_header *header, + int fd, void *buf, size_t size) +{ + if (readn(fd, buf, size) <= 0) + return -1; + + if (header->needs_swap) + mem_bswap_64(buf, size); - self->frozen = 1; return 0; -out_errno: - return -errno; } -u64 perf_header__sample_type(struct perf_header *header) +int perf_header__process_sections(struct perf_header *header, int fd, + void *data, + int (*process)(struct perf_file_section *section, + struct perf_header *ph, + int feat, int fd, void *data)) { - u64 type = 0; - int i; + struct perf_file_section *feat_sec, *sec; + int nr_sections; + int sec_size; + int feat; + int err; - for (i = 0; i < header->attrs; i++) { - struct perf_header_attr *attr = header->attr[i]; + nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); + if (!nr_sections) + return 0; - if (!type) - type = attr->attr.sample_type; - else if (type != attr->attr.sample_type) - die("non matching sample_type"); + feat_sec = sec = calloc(nr_sections, sizeof(*feat_sec)); + if (!feat_sec) + return -1; + + sec_size = sizeof(*feat_sec) * nr_sections; + + lseek(fd, header->feat_offset, SEEK_SET); + + err = perf_header__getbuffer64(header, fd, feat_sec, sec_size); + if (err < 0) + goto out_free; + + for_each_set_bit(feat, header->adds_features, HEADER_LAST_FEATURE) { + err = process(sec++, header, feat, fd, data); + if (err < 0) + goto out_free; } + err = 0; +out_free: + free(feat_sec); + return err; +} - return type; +static const int attr_file_abi_sizes[] = { + [0] = PERF_ATTR_SIZE_VER0, + [1] = PERF_ATTR_SIZE_VER1, + [2] = PERF_ATTR_SIZE_VER2, + [3] = PERF_ATTR_SIZE_VER3, + 0, +}; + +/* + * In the legacy file format, the magic number is not used to encode endianness. + * hdr_sz was used to encode endianness. But given that hdr_sz can vary based + * on ABI revisions, we need to try all combinations for all endianness to + * detect the endianness. + */ +static int try_all_file_abis(uint64_t hdr_sz, struct perf_header *ph) +{ + uint64_t ref_size, attr_size; + int i; + + for (i = 0 ; attr_file_abi_sizes[i]; i++) { + ref_size = attr_file_abi_sizes[i] + + sizeof(struct perf_file_section); + if (hdr_sz != ref_size) { + attr_size = bswap_64(hdr_sz); + if (attr_size != ref_size) + continue; + + ph->needs_swap = true; + } + pr_debug("ABI%d perf.data file detected, need_swap=%d\n", + i, + ph->needs_swap); + return 0; + } + /* could not determine endianness */ + return -1; } -struct perf_event_attr * -perf_header__find_attr(u64 id, struct perf_header *header) +#define PERF_PIPE_HDR_VER0 16 + +static const size_t attr_pipe_abi_sizes[] = { + [0] = PERF_PIPE_HDR_VER0, + 0, +}; + +/* + * In the legacy pipe format, there is an implicit assumption that endiannesss + * between host recording the samples, and host parsing the samples is the + * same. This is not always the case given that the pipe output may always be + * redirected into a file and analyzed on a different machine with possibly a + * different endianness and perf_event ABI revsions in the perf tool itself. + */ +static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph) { + u64 attr_size; int i; + for (i = 0 ; attr_pipe_abi_sizes[i]; i++) { + if (hdr_sz != attr_pipe_abi_sizes[i]) { + attr_size = bswap_64(hdr_sz); + if (attr_size != hdr_sz) + continue; + + ph->needs_swap = true; + } + pr_debug("Pipe ABI%d perf.data file detected\n", i); + return 0; + } + return -1; +} + +bool is_perf_magic(u64 magic) +{ + if (!memcmp(&magic, __perf_magic1, sizeof(magic)) + || magic == __perf_magic2 + || magic == __perf_magic2_sw) + return true; + + return false; +} + +static int check_magic_endian(u64 magic, uint64_t hdr_sz, + bool is_pipe, struct perf_header *ph) +{ + int ret; + + /* 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); + + return try_all_file_abis(hdr_sz, ph); + } /* - * We set id to -1 if the data file doesn't contain sample - * ids. Check for this and avoid walking through the entire - * list of ids which may be large. + * the new magic number serves two purposes: + * - unique number to identify actual perf.data files + * - encode endianness of file */ - if (id == -1ULL) - return NULL; - for (i = 0; i < header->attrs; i++) { - struct perf_header_attr *attr = header->attr[i]; - int j; + /* check magic number with one endianness */ + if (magic == __perf_magic2) + return 0; + + /* check magic number with opposite endianness */ + if (magic != __perf_magic2_sw) + return -1; + + ph->needs_swap = true; + ph->version = PERF_HEADER_VERSION_2; + + return 0; +} + +int perf_file_header__read(struct perf_file_header *header, + struct perf_header *ph, int fd) +{ + ssize_t ret; + + lseek(fd, 0, SEEK_SET); + + ret = readn(fd, header, sizeof(*header)); + if (ret <= 0) + return -1; + + if (check_magic_endian(header->magic, + header->attr_size, false, ph) < 0) { + pr_debug("magic/endian check failed\n"); + return -1; + } - for (j = 0; j < attr->ids; j++) { - if (attr->id[j] == id) - return &attr->attr; + if (ph->needs_swap) { + mem_bswap_64(header, offsetof(struct perf_file_header, + adds_features)); + } + + if (header->size != sizeof(*header)) { + /* Support the previous format */ + if (header->size == offsetof(typeof(*header), adds_features)) + bitmap_zero(header->adds_features, HEADER_FEAT_BITS); + else + return -1; + } else if (ph->needs_swap) { + /* + * feature bitmap is declared as an array of unsigned longs -- + * not good since its size can differ between the host that + * generated the data file and the host analyzing the file. + * + * We need to handle endianness, but we don't know the size of + * the unsigned long where the file was generated. Take a best + * guess at determining it: try 64-bit swap first (ie., file + * created on a 64-bit host), and check if the hostname feature + * bit is set (this feature bit is forced on as of fbe96f2). + * If the bit is not, undo the 64-bit swap and try a 32-bit + * swap. If the hostname bit is still not set (e.g., older data + * file), punt and fallback to the original behavior -- + * clearing all feature bits and setting buildid. + */ + mem_bswap_64(&header->adds_features, + BITS_TO_U64(HEADER_FEAT_BITS)); + + if (!test_bit(HEADER_HOSTNAME, header->adds_features)) { + /* unswap as u64 */ + mem_bswap_64(&header->adds_features, + BITS_TO_U64(HEADER_FEAT_BITS)); + + /* unswap as u32 */ + mem_bswap_32(&header->adds_features, + BITS_TO_U32(HEADER_FEAT_BITS)); + } + + if (!test_bit(HEADER_HOSTNAME, header->adds_features)) { + bitmap_zero(header->adds_features, HEADER_FEAT_BITS); + set_bit(HEADER_BUILD_ID, header->adds_features); } } - return NULL; + memcpy(&ph->adds_features, &header->adds_features, + sizeof(ph->adds_features)); + + ph->data_offset = header->data.offset; + ph->data_size = header->data.size; + ph->feat_offset = header->data.offset + header->data.size; + return 0; } -int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, - event__handler_t process, - struct perf_session *session) +static int perf_file_section__process(struct perf_file_section *section, + struct perf_header *ph, + int feat, int fd, void *data) { - event_t *ev; - size_t size; - int err; + if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { + pr_debug("Failed to lseek to %" PRIu64 " offset for feature " + "%d, continuing...\n", section->offset, feat); + return 0; + } - size = sizeof(struct perf_event_attr); - size = ALIGN(size, sizeof(u64)); - size += sizeof(struct perf_event_header); - size += ids * sizeof(u64); + if (feat >= HEADER_LAST_FEATURE) { + pr_debug("unknown feature %d, continuing...\n", feat); + return 0; + } - ev = malloc(size); + if (!feat_ops[feat].process) + return 0; - ev->attr.attr = *attr; - memcpy(ev->attr.id, id, ids * sizeof(u64)); + return feat_ops[feat].process(section, ph, fd, data); +} - ev->attr.header.type = PERF_RECORD_HEADER_ATTR; - ev->attr.header.size = size; +static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, + struct perf_header *ph, int fd, + bool repipe) +{ + ssize_t ret; - err = process(ev, session); + ret = readn(fd, header, sizeof(*header)); + if (ret <= 0) + return -1; - free(ev); + if (check_magic_endian(header->magic, header->size, true, ph) < 0) { + pr_debug("endian/magic failed\n"); + return -1; + } - return err; + if (ph->needs_swap) + header->size = bswap_64(header->size); + + if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0) + return -1; + + return 0; } -int event__synthesize_attrs(struct perf_header *self, - event__handler_t process, - struct perf_session *session) +static int perf_header__read_pipe(struct perf_session *session) { - struct perf_header_attr *attr; - int i, err = 0; + struct perf_header *header = &session->header; + struct perf_pipe_file_header f_header; - for (i = 0; i < self->attrs; i++) { - attr = self->attr[i]; + 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; + } - err = event__synthesize_attr(&attr->attr, attr->ids, attr->id, - process, session); - if (err) { - pr_debug("failed to create perf header attribute\n"); - return err; - } + return 0; +} + +static int read_attr(int fd, struct perf_header *ph, + struct perf_file_attr *f_attr) +{ + struct perf_event_attr *attr = &f_attr->attr; + size_t sz, left; + size_t our_sz = sizeof(f_attr->attr); + ssize_t ret; + + memset(f_attr, 0, sizeof(*f_attr)); + + /* read minimal guaranteed structure */ + ret = readn(fd, attr, PERF_ATTR_SIZE_VER0); + if (ret <= 0) { + pr_debug("cannot read %d bytes of header attr\n", + PERF_ATTR_SIZE_VER0); + return -1; } - return err; + /* on file perf_event_attr size */ + sz = attr->size; + + if (ph->needs_swap) + sz = bswap_32(sz); + + if (sz == 0) { + /* assume ABI0 */ + sz = PERF_ATTR_SIZE_VER0; + } else if (sz > our_sz) { + pr_debug("file uses a more recent and unsupported ABI" + " (%zu bytes extra)\n", sz - our_sz); + return -1; + } + /* what we have not yet read and that we know about */ + left = sz - PERF_ATTR_SIZE_VER0; + if (left) { + void *ptr = attr; + ptr += PERF_ATTR_SIZE_VER0; + + ret = readn(fd, ptr, left); + } + /* read perf_file_section, ids are read in caller */ + ret = readn(fd, &f_attr->ids, sizeof(f_attr->ids)); + + return ret <= 0 ? -1 : 0; } -int event__process_attr(event_t *self, struct perf_session *session) +static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, + struct pevent *pevent) { - struct perf_header_attr *attr; - unsigned int i, ids, n_ids; + struct event_format *event; + char bf[128]; - attr = perf_header_attr__new(&self->attr.attr); - if (attr == NULL) - return -ENOMEM; + /* already prepared */ + if (evsel->tp_format) + return 0; - ids = self->header.size; - ids -= (void *)&self->attr.id - (void *)self; - n_ids = ids / sizeof(u64); + if (pevent == NULL) { + pr_debug("broken or missing trace data\n"); + return -1; + } - for (i = 0; i < n_ids; i++) { - if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) { - perf_header_attr__delete(attr); - return -ENOMEM; - } + event = pevent_find_event(pevent, evsel->attr.config); + if (event == NULL) + return -1; + + if (!evsel->name) { + snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name); + evsel->name = strdup(bf); + if (evsel->name == NULL) + return -1; } - if (perf_header__add_attr(&session->header, attr) < 0) { - perf_header_attr__delete(attr); + evsel->tp_format = event; + return 0; +} + +static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, + struct pevent *pevent) +{ + struct perf_evsel *pos; + + evlist__for_each(evlist, pos) { + if (pos->attr.type == PERF_TYPE_TRACEPOINT && + perf_evsel__prepare_tracepoint_event(pos, pevent)) + return -1; + } + + return 0; +} + +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 (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); } - perf_session__update_sample_type(session); + nr_attrs = f_header.attrs.size / f_header.attr_size; + lseek(fd, f_header.attrs.offset, SEEK_SET); + + for (i = 0; i < nr_attrs; i++) { + struct perf_evsel *evsel; + off_t tmp; + + if (read_attr(fd, header, &f_attr) < 0) + goto out_errno; + + if (header->needs_swap) + perf_event__attr_swap(&f_attr.attr); + + tmp = lseek(fd, 0, SEEK_CUR); + evsel = perf_evsel__new(&f_attr.attr); + + if (evsel == NULL) + goto out_delete_evlist; + + evsel->needs_swap = header->needs_swap; + /* + * Do it before so that if perf_evsel__alloc_id fails, this + * entry gets purged too at perf_evlist__delete(). + */ + perf_evlist__add(session->evlist, evsel); + + nr_ids = f_attr.ids.size / sizeof(u64); + /* + * We don't have the cpu and thread maps on the header, so + * for allocating the perf_sample_id table we fake 1 cpu and + * hattr->ids threads. + */ + if (perf_evsel__alloc_id(evsel, 1, nr_ids)) + goto out_delete_evlist; + + lseek(fd, f_attr.ids.offset, SEEK_SET); + + for (j = 0; j < nr_ids; j++) { + if (perf_header__getbuffer64(header, fd, &f_id, sizeof(f_id))) + goto out_errno; + + perf_evlist__id_add(session->evlist, evsel, 0, j, f_id); + } + + lseek(fd, tmp, SEEK_SET); + } + + symbol_conf.nr_events = nr_attrs; + + perf_header__process_sections(header, fd, &session->tevent, + perf_file_section__process); + + if (perf_evlist__prepare_tracepoint_events(session->evlist, + session->tevent.pevent)) + goto out_delete_evlist; return 0; +out_errno: + return -errno; + +out_delete_evlist: + perf_evlist__delete(session->evlist); + session->evlist = NULL; + return -ENOMEM; } -int event__synthesize_event_type(u64 event_id, char *name, - event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_attr(struct perf_tool *tool, + struct perf_event_attr *attr, u32 ids, u64 *id, + perf_event__handler_t process) { - event_t ev; - size_t size = 0; - int err = 0; + union perf_event *ev; + size_t size; + int err; - memset(&ev, 0, sizeof(ev)); + size = sizeof(struct perf_event_attr); + size = PERF_ALIGN(size, sizeof(u64)); + size += sizeof(struct perf_event_header); + size += ids * sizeof(u64); + + ev = malloc(size); + + if (ev == NULL) + return -ENOMEM; + + ev->attr.attr = *attr; + memcpy(ev->attr.id, id, ids * sizeof(u64)); - 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->attr.header.type = PERF_RECORD_HEADER_ATTR; + ev->attr.header.size = (u16)size; - ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE; - size = strlen(name); - size = ALIGN(size, sizeof(u64)); - ev.event_type.header.size = sizeof(ev.event_type) - - (sizeof(ev.event_type.event_type.name) - size); + if (ev->attr.header.size == size) + err = process(tool, ev, NULL, NULL); + else + err = -E2BIG; - err = process(&ev, session); + free(ev); return err; } -int event__synthesize_event_types(event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_attrs(struct perf_tool *tool, + struct perf_session *session, + perf_event__handler_t process) { - struct perf_trace_event_type *type; - int i, err = 0; - - for (i = 0; i < event_count; i++) { - type = &events[i]; + struct perf_evsel *evsel; + int err = 0; - err = event__synthesize_event_type(type->event_id, type->name, - process, session); + evlist__for_each(session->evlist, evsel) { + err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids, + evsel->id, process); if (err) { - pr_debug("failed to create perf header event type\n"); + pr_debug("failed to create perf header attribute\n"); return err; } } @@ -1089,79 +2901,138 @@ int event__synthesize_event_types(event__handler_t process, return err; } -int event__process_event_type(event_t *self, - struct perf_session *session __unused) +int perf_event__process_attr(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_evlist **pevlist) { - if (perf_header__push_event(self->event_type.event_type.event_id, - self->event_type.event_type.name) < 0) + u32 i, ids, n_ids; + struct perf_evsel *evsel; + struct perf_evlist *evlist = *pevlist; + + if (evlist == NULL) { + *pevlist = evlist = perf_evlist__new(); + if (evlist == NULL) + return -ENOMEM; + } + + evsel = perf_evsel__new(&event->attr.attr); + if (evsel == NULL) + return -ENOMEM; + + perf_evlist__add(evlist, evsel); + + ids = event->header.size; + ids -= (void *)&event->attr.id - (void *)event; + n_ids = ids / sizeof(u64); + /* + * We don't have the cpu and thread maps on the header, so + * for allocating the perf_sample_id table we fake 1 cpu and + * hattr->ids threads. + */ + if (perf_evsel__alloc_id(evsel, 1, n_ids)) return -ENOMEM; + for (i = 0; i < n_ids; i++) { + perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]); + } + + symbol_conf.nr_events = evlist->nr_entries; + return 0; } -int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs, - int nb_events, - event__handler_t process, - struct perf_session *session __unused) +int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, + struct perf_evlist *evlist, + perf_event__handler_t process) { - event_t ev; + union perf_event ev; + struct tracing_data *tdata; ssize_t size = 0, aligned_size = 0, padding; - int err = 0; + int err __maybe_unused = 0; + + /* + * We are going to store the size of the data followed + * by the data contents. Since the fd descriptor is a pipe, + * we cannot seek back to store the size of the data once + * we know it. Instead we: + * + * - write the tracing data to the temp file + * - get/write the data size to pipe + * - write the tracing data from the temp file + * to the pipe + */ + tdata = tracing_data_get(&evlist->entries, fd, true); + if (!tdata) + return -1; memset(&ev, 0, sizeof(ev)); ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA; - size = read_tracing_data_size(fd, pattrs, nb_events); - if (size <= 0) - return size; - aligned_size = ALIGN(size, sizeof(u64)); + size = tdata->size; + aligned_size = PERF_ALIGN(size, sizeof(u64)); padding = aligned_size - size; ev.tracing_data.header.size = sizeof(ev.tracing_data); ev.tracing_data.size = aligned_size; - process(&ev, session); + process(tool, &ev, NULL, NULL); + + /* + * The put function will copy all the tracing data + * stored in temp file to the pipe. + */ + tracing_data_put(tdata); - err = read_tracing_data(fd, pattrs, nb_events); write_padded(fd, NULL, 0, padding); return aligned_size; } -int event__process_tracing_data(event_t *self, - struct perf_session *session) +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 = self->tracing_data.size; - off_t offset = lseek(session->fd, 0, SEEK_CUR); + ssize_t size_read, padding, size = event->tracing_data.size; + 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->repipe); - - padding = ALIGN(size_read, sizeof(u64)) - size_read; + size_read = trace_report(fd, &session->tevent, + session->repipe); + padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read; - if (read(session->fd, buf, padding) < 0) - die("reading input file"); + if (readn(fd, buf, padding) < 0) { + pr_err("%s: reading input file", __func__); + return -1; + } if (session->repipe) { int retw = write(STDOUT_FILENO, buf, padding); - if (retw <= 0 || retw != padding) - die("repiping tracing data padding"); + if (retw <= 0 || retw != padding) { + pr_err("%s: repiping tracing data padding", __func__); + return -1; + } } - if (size_read + padding != size) - die("tracing data size mismatch"); + if (size_read + padding != size) { + pr_err("%s: tracing data size mismatch", __func__); + return -1; + } + + perf_evlist__prepare_tracepoint_events(session->evlist, + session->tevent.pevent); return size_read + padding; } -int event__synthesize_build_id(struct dso *pos, u16 misc, - event__handler_t process, - struct machine *machine, - struct perf_session *session) +int perf_event__synthesize_build_id(struct perf_tool *tool, + struct dso *pos, u16 misc, + perf_event__handler_t process, + struct machine *machine) { - event_t ev; + union perf_event ev; size_t len; int err = 0; @@ -1171,7 +3042,7 @@ int event__synthesize_build_id(struct dso *pos, u16 misc, memset(&ev, 0, sizeof(ev)); len = pos->long_name_len + 1; - len = ALIGN(len, NAME_ALIGN); + len = PERF_ALIGN(len, NAME_ALIGN); memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id)); ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; ev.build_id.header.misc = misc; @@ -1179,16 +3050,17 @@ int event__synthesize_build_id(struct dso *pos, u16 misc, ev.build_id.header.size = sizeof(ev.build_id) + len; memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len); - err = process(&ev, session); + err = process(tool, &ev, NULL, machine); return err; } -int event__process_build_id(event_t *self, - struct perf_session *session) +int perf_event__process_build_id(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session) { - __event_process_build_id(&self->build_id, - self->build_id.filename, + __event_process_build_id(&event->build_id, + event->build_id.filename, session); return 0; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 402ac2454cf..d08cfe49940 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -1,28 +1,43 @@ #ifndef __PERF_HEADER_H #define __PERF_HEADER_H -#include "../../../include/linux/perf_event.h" +#include <linux/perf_event.h> #include <sys/types.h> #include <stdbool.h> -#include "types.h" -#include "event.h" - #include <linux/bitmap.h> +#include <linux/types.h> +#include "event.h" -struct perf_header_attr { - struct perf_event_attr attr; - int ids, size; - u64 *id; - off_t id_offset; -}; enum { - HEADER_TRACE_INFO = 1, + HEADER_RESERVED = 0, /* always cleared */ + HEADER_FIRST_FEATURE = 1, + HEADER_TRACING_DATA = 1, HEADER_BUILD_ID, + + HEADER_HOSTNAME, + HEADER_OSRELEASE, + HEADER_VERSION, + HEADER_ARCH, + HEADER_NRCPUS, + HEADER_CPUDESC, + HEADER_CPUID, + HEADER_TOTAL_MEM, + HEADER_CMDLINE, + HEADER_EVENT_DESC, + HEADER_CPU_TOPOLOGY, + HEADER_NUMA_TOPOLOGY, + HEADER_BRANCH_STACK, + HEADER_PMU_MAPPINGS, + HEADER_GROUP_DESC, HEADER_LAST_FEATURE, + HEADER_FEAT_BITS = 256, }; -#define HEADER_FEAT_BITS 256 +enum perf_header_version { + PERF_HEADER_VERSION_1, + PERF_HEADER_VERSION_2, +}; struct perf_file_section { u64 offset; @@ -35,6 +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); }; @@ -46,82 +62,98 @@ struct perf_pipe_file_header { struct perf_header; -int perf_file_header__read(struct perf_file_header *self, +int perf_file_header__read(struct perf_file_header *header, struct perf_header *ph, int fd); +struct perf_session_env { + char *hostname; + char *os_release; + char *version; + char *arch; + int nr_cpus_online; + int nr_cpus_avail; + char *cpu_desc; + char *cpuid; + unsigned long long total_mem; + + int nr_cmdline; + int nr_sibling_cores; + int nr_sibling_threads; + int nr_numa_nodes; + int nr_pmu_mappings; + int nr_groups; + char *cmdline; + char *sibling_cores; + char *sibling_threads; + char *numa_nodes; + char *pmu_mappings; +}; + struct perf_header { - int frozen; - int attrs, size; - bool needs_swap; - struct perf_header_attr **attr; - 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; }; -int perf_header__init(struct perf_header *self); -void perf_header__exit(struct perf_header *self); +struct perf_evlist; +struct perf_session; -int perf_header__read(struct perf_session *session, int fd); -int perf_header__write(struct perf_header *self, int fd, bool at_exit); +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__add_attr(struct perf_header *self, - struct perf_header_attr *attr); - -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); -struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr); -void perf_header_attr__delete(struct perf_header_attr *self); +int perf_header__set_cmdline(int argc, const char **argv); -int perf_header_attr__add_id(struct perf_header_attr *self, u64 id); +int perf_header__process_sections(struct perf_header *header, int fd, + void *data, + int (*process)(struct perf_file_section *section, + struct perf_header *ph, + int feat, int fd, void *data)); -u64 perf_header__sample_type(struct perf_header *header); -struct perf_event_attr * -perf_header__find_attr(u64 id, struct perf_header *header); -void perf_header__set_feat(struct perf_header *self, int feat); -bool perf_header__has_feat(const struct perf_header *self, int feat); - -int perf_header__process_sections(struct perf_header *self, int fd, - int (*process)(struct perf_file_section *self, - struct perf_header *ph, - int feat, int fd)); +int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full); int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, - const char *name, bool is_kallsyms); + const char *name, bool is_kallsyms, bool is_vdso); int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir); -int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, - event__handler_t process, - struct perf_session *session); -int event__synthesize_attrs(struct perf_header *self, - event__handler_t process, - struct perf_session *session); -int event__process_attr(event_t *self, struct perf_session *session); - -int event__synthesize_event_type(u64 event_id, char *name, - event__handler_t process, +int perf_event__synthesize_attr(struct perf_tool *tool, + struct perf_event_attr *attr, u32 ids, u64 *id, + perf_event__handler_t process); +int perf_event__synthesize_attrs(struct perf_tool *tool, + struct perf_session *session, + perf_event__handler_t process); +int perf_event__process_attr(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(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session); + +int perf_event__synthesize_build_id(struct perf_tool *tool, + struct dso *pos, u16 misc, + perf_event__handler_t process, + struct machine *machine); +int perf_event__process_build_id(struct perf_tool *tool, + union perf_event *event, struct perf_session *session); -int event__synthesize_event_types(event__handler_t process, - struct perf_session *session); -int event__process_event_type(event_t *self, - struct perf_session *session); - -int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs, - int nb_events, - event__handler_t process, - struct perf_session *session); -int event__process_tracing_data(event_t *self, - struct perf_session *session); - -int event__synthesize_build_id(struct dso *pos, u16 misc, - event__handler_t process, - struct machine *machine, - struct perf_session *session); -int event__process_build_id(event_t *self, struct perf_session *session); +bool is_perf_magic(u64 magic); + +/* + * arch specific callback + */ +int get_cpuid(char *buffer, size_t sz); #endif /* __PERF_HEADER_H */ diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c index 6f2975a0035..86c37c47226 100644 --- a/tools/perf/util/help.c +++ b/tools/perf/util/help.c @@ -3,6 +3,7 @@ #include "exec_cmd.h" #include "levenshtein.h" #include "help.h" +#include <termios.h> void add_cmdname(struct cmdnames *cmds, const char *name, size_t len) { @@ -21,8 +22,8 @@ static void clean_cmdnames(struct cmdnames *cmds) unsigned int i; for (i = 0; i < cmds->cnt; ++i) - free(cmds->names[i]); - free(cmds->names); + zfree(&cmds->names[i]); + zfree(&cmds->names); cmds->cnt = 0; cmds->alloc = 0; } @@ -262,9 +263,8 @@ static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old) for (i = 0; i < old->cnt; i++) cmds->names[cmds->cnt++] = old->names[i]; - free(old->names); + zfree(&old->names); old->cnt = 0; - old->names = NULL; } const char *help_unknown_cmd(const char *cmd) @@ -331,7 +331,8 @@ const char *help_unknown_cmd(const char *cmd) exit(1); } -int cmd_version(int argc __used, const char **argv __used, const char *prefix __used) +int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused, + const char *prefix __maybe_unused) { printf("perf version %s\n", perf_version_string); return 0; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 2022e874099..30df6187ee0 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -3,111 +3,348 @@ #include "hist.h" #include "session.h" #include "sort.h" +#include "evsel.h" +#include "annotate.h" #include <math.h> -enum hist_filter { - HIST_FILTER__DSO, - HIST_FILTER__THREAD, - HIST_FILTER__PARENT, -}; +static bool hists__filter_entry_by_dso(struct hists *hists, + struct hist_entry *he); +static bool hists__filter_entry_by_thread(struct hists *hists, + struct hist_entry *he); +static bool hists__filter_entry_by_symbol(struct hists *hists, + struct hist_entry *he); struct callchain_param callchain_param = { .mode = CHAIN_GRAPH_REL, - .min_percent = 0.5 + .min_percent = 0.5, + .order = ORDER_CALLEE, + .key = CCKEY_FUNCTION }; -u16 hists__col_len(struct hists *self, enum hist_column col) +u16 hists__col_len(struct hists *hists, enum hist_column col) { - return self->col_len[col]; + return hists->col_len[col]; } -void hists__set_col_len(struct hists *self, enum hist_column col, u16 len) +void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len) { - self->col_len[col] = len; + hists->col_len[col] = len; } -bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len) +bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len) { - if (len > hists__col_len(self, col)) { - hists__set_col_len(self, col, len); + if (len > hists__col_len(hists, col)) { + hists__set_col_len(hists, col, len); return true; } return false; } -static void hists__reset_col_len(struct hists *self) +void hists__reset_col_len(struct hists *hists) { enum hist_column col; for (col = 0; col < HISTC_NR_COLS; ++col) - hists__set_col_len(self, col, 0); + hists__set_col_len(hists, col, 0); +} + +static void hists__set_unres_dso_col_len(struct hists *hists, int dso) +{ + const unsigned int unresolved_col_width = BITS_PER_LONG / 4; + + if (hists__col_len(hists, dso) < unresolved_col_width && + !symbol_conf.col_width_list_str && !symbol_conf.field_sep && + !symbol_conf.dso_list) + hists__set_col_len(hists, dso, unresolved_col_width); } -static void hists__calc_col_len(struct hists *self, struct hist_entry *h) +void hists__calc_col_len(struct hists *hists, struct hist_entry *h) { + const unsigned int unresolved_col_width = BITS_PER_LONG / 4; + int symlen; u16 len; - if (h->ms.sym) - hists__new_col_len(self, HISTC_SYMBOL, h->ms.sym->namelen); + /* + * +4 accounts for '[x] ' priv level info + * +2 accounts for 0x prefix on raw addresses + * +3 accounts for ' y ' symtab origin info + */ + if (h->ms.sym) { + symlen = h->ms.sym->namelen + 4; + if (verbose) + symlen += BITS_PER_LONG / 4 + 2 + 3; + hists__new_col_len(hists, HISTC_SYMBOL, symlen); + } else { + symlen = unresolved_col_width + 4 + 2; + hists__new_col_len(hists, HISTC_SYMBOL, symlen); + hists__set_unres_dso_col_len(hists, HISTC_DSO); + } len = thread__comm_len(h->thread); - if (hists__new_col_len(self, HISTC_COMM, len)) - hists__set_col_len(self, HISTC_THREAD, len + 6); + if (hists__new_col_len(hists, HISTC_COMM, len)) + hists__set_col_len(hists, HISTC_THREAD, len + 6); if (h->ms.map) { len = dso__name_len(h->ms.map->dso); - hists__new_col_len(self, HISTC_DSO, len); + hists__new_col_len(hists, HISTC_DSO, len); } + + if (h->parent) + hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen); + + if (h->branch_info) { + if (h->branch_info->from.sym) { + symlen = (int)h->branch_info->from.sym->namelen + 4; + if (verbose) + symlen += BITS_PER_LONG / 4 + 2 + 3; + hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen); + + symlen = dso__name_len(h->branch_info->from.map->dso); + hists__new_col_len(hists, HISTC_DSO_FROM, symlen); + } else { + symlen = unresolved_col_width + 4 + 2; + hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen); + hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM); + } + + if (h->branch_info->to.sym) { + symlen = (int)h->branch_info->to.sym->namelen + 4; + if (verbose) + symlen += BITS_PER_LONG / 4 + 2 + 3; + hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); + + symlen = dso__name_len(h->branch_info->to.map->dso); + hists__new_col_len(hists, HISTC_DSO_TO, symlen); + } else { + symlen = unresolved_col_width + 4 + 2; + hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); + hists__set_unres_dso_col_len(hists, HISTC_DSO_TO); + } + } + + if (h->mem_info) { + if (h->mem_info->daddr.sym) { + symlen = (int)h->mem_info->daddr.sym->namelen + 4 + + unresolved_col_width + 2; + hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, + symlen); + hists__new_col_len(hists, HISTC_MEM_DCACHELINE, + symlen + 1); + } else { + symlen = unresolved_col_width + 4 + 2; + hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, + symlen); + } + if (h->mem_info->daddr.map) { + symlen = dso__name_len(h->mem_info->daddr.map->dso); + hists__new_col_len(hists, HISTC_MEM_DADDR_DSO, + symlen); + } else { + symlen = unresolved_col_width + 4 + 2; + hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO); + } + } else { + symlen = unresolved_col_width + 4 + 2; + hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); + hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO); + } + + hists__new_col_len(hists, HISTC_MEM_LOCKED, 6); + hists__new_col_len(hists, HISTC_MEM_TLB, 22); + hists__new_col_len(hists, HISTC_MEM_SNOOP, 12); + 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()); } -static void hist_entry__add_cpumode_period(struct hist_entry *self, - unsigned int cpumode, u64 period) +void hists__output_recalc_col_len(struct hists *hists, int max_rows) +{ + struct rb_node *next = rb_first(&hists->entries); + struct hist_entry *n; + int row = 0; + + hists__reset_col_len(hists); + + while (next && row++ < max_rows) { + n = rb_entry(next, struct hist_entry, rb_node); + if (!n->filtered) + hists__calc_col_len(hists, n); + next = rb_next(&n->rb_node); + } +} + +static void he_stat__add_cpumode_period(struct he_stat *he_stat, + unsigned int cpumode, u64 period) { switch (cpumode) { case PERF_RECORD_MISC_KERNEL: - self->period_sys += period; + he_stat->period_sys += period; break; case PERF_RECORD_MISC_USER: - self->period_us += period; + he_stat->period_us += period; break; case PERF_RECORD_MISC_GUEST_KERNEL: - self->period_guest_sys += period; + he_stat->period_guest_sys += period; break; case PERF_RECORD_MISC_GUEST_USER: - self->period_guest_us += period; + he_stat->period_guest_us += period; break; default: break; } } +static void he_stat__add_period(struct he_stat *he_stat, u64 period, + u64 weight) +{ + + he_stat->period += period; + he_stat->weight += weight; + he_stat->nr_events += 1; +} + +static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) +{ + dest->period += src->period; + dest->period_sys += src->period_sys; + dest->period_us += src->period_us; + dest->period_guest_sys += src->period_guest_sys; + dest->period_guest_us += src->period_guest_us; + dest->nr_events += src->nr_events; + dest->weight += src->weight; +} + +static void he_stat__decay(struct he_stat *he_stat) +{ + he_stat->period = (he_stat->period * 7) / 8; + he_stat->nr_events = (he_stat->nr_events * 7) / 8; + /* XXX need decay for weight too? */ +} + +static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) +{ + u64 prev_period = he->stat.period; + u64 diff; + + if (prev_period == 0) + return true; + + he_stat__decay(&he->stat); + if (symbol_conf.cumulate_callchain) + he_stat__decay(he->stat_acc); + + diff = prev_period - he->stat.period; + + hists->stats.total_period -= diff; + if (!he->filtered) + hists->stats.total_non_filtered_period -= diff; + + return he->stat.period == 0; +} + +void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) +{ + struct rb_node *next = rb_first(&hists->entries); + struct hist_entry *n; + + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + /* + * We may be annotating this, for instance, so keep it here in + * case some it gets new samples, we'll eventually free it when + * the user stops browsing and it agains gets fully decayed. + */ + if (((zap_user && n->level == '.') || + (zap_kernel && n->level != '.') || + hists__decay_entry(hists, n)) && + !n->used) { + rb_erase(&n->rb_node, &hists->entries); + + if (sort__need_collapse) + rb_erase(&n->rb_node_in, &hists->entries_collapsed); + + --hists->nr_entries; + if (!n->filtered) + --hists->nr_non_filtered_entries; + + hist_entry__free(n); + } + } +} + /* * histogram, sorted on item, collects periods */ -static struct hist_entry *hist_entry__new(struct hist_entry *template) +static struct hist_entry *hist_entry__new(struct hist_entry *template, + bool sample_self) { - size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0; - struct hist_entry *self = malloc(sizeof(*self) + callchain_size); + size_t callchain_size = 0; + struct hist_entry *he; - if (self != NULL) { - *self = *template; - self->nr_events = 1; - if (self->ms.map) - self->ms.map->referenced = true; - if (symbol_conf.use_callchain) - callchain_init(self->callchain); - } + if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) + callchain_size = sizeof(struct callchain_root); - return self; -} + he = zalloc(sizeof(*he) + callchain_size); -static void hists__inc_nr_entries(struct hists *self, struct hist_entry *h) -{ - if (!h->filtered) { - hists__calc_col_len(self, h); - ++self->nr_entries; + if (he != NULL) { + *he = *template; + + if (symbol_conf.cumulate_callchain) { + he->stat_acc = malloc(sizeof(he->stat)); + if (he->stat_acc == NULL) { + free(he); + return NULL; + } + memcpy(he->stat_acc, &he->stat, sizeof(he->stat)); + if (!sample_self) + memset(&he->stat, 0, sizeof(he->stat)); + } + + if (he->ms.map) + he->ms.map->referenced = true; + + if (he->branch_info) { + /* + * This branch info is (a part of) allocated from + * sample__resolve_bstack() and will be freed after + * adding new entries. So we need to save a copy. + */ + he->branch_info = malloc(sizeof(*he->branch_info)); + if (he->branch_info == NULL) { + free(he->stat_acc); + free(he); + return NULL; + } + + memcpy(he->branch_info, template->branch_info, + sizeof(*he->branch_info)); + + if (he->branch_info->from.map) + he->branch_info->from.map->referenced = true; + if (he->branch_info->to.map) + he->branch_info->to.map->referenced = true; + } + + if (he->mem_info) { + if (he->mem_info->iaddr.map) + he->mem_info->iaddr.map->referenced = true; + if (he->mem_info->daddr.map) + he->mem_info->daddr.map->referenced = true; + } + + if (symbol_conf.use_callchain) + callchain_init(he->callchain); + + INIT_LIST_HEAD(&he->pairs.node); } + + return he; } static u8 symbol__parent_filter(const struct symbol *parent) @@ -117,37 +354,55 @@ static u8 symbol__parent_filter(const struct symbol *parent) return 0; } -struct hist_entry *__hists__add_entry(struct hists *self, - struct addr_location *al, - struct symbol *sym_parent, u64 period) +static struct hist_entry *add_hist_entry(struct hists *hists, + struct hist_entry *entry, + struct addr_location *al, + bool sample_self) { - struct rb_node **p = &self->entries.rb_node; + struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; - struct hist_entry entry = { - .thread = al->thread, - .ms = { - .map = al->map, - .sym = al->sym, - }, - .cpu = al->cpu, - .ip = al->addr, - .level = al->level, - .period = period, - .parent = sym_parent, - .filtered = symbol__parent_filter(sym_parent), - }; - int cmp; + int64_t cmp; + u64 period = entry->stat.period; + u64 weight = entry->stat.weight; + + p = &hists->entries_in->rb_node; while (*p != NULL) { parent = *p; - he = rb_entry(parent, struct hist_entry, rb_node); + he = rb_entry(parent, struct hist_entry, rb_node_in); - cmp = hist_entry__cmp(&entry, he); + /* + * Make sure that it receives arguments in a same order as + * hist_entry__collapse() so that we can use an appropriate + * function when searching an entry regardless which sort + * keys were used. + */ + cmp = hist_entry__cmp(he, entry); if (!cmp) { - he->period += period; - ++he->nr_events; + if (sample_self) + he_stat__add_period(&he->stat, period, weight); + if (symbol_conf.cumulate_callchain) + he_stat__add_period(he->stat_acc, period, weight); + + /* + * This mem info was allocated from sample__resolve_mem + * and will not be used anymore. + */ + zfree(&entry->mem_info); + + /* If the map of an existing hist_entry has + * become out-of-date due to an exec() or + * similar, update it. Otherwise we will + * mis-adjust symbol addresses when computing + * the history counter to increment. + */ + if (he->ms.map != entry->ms.map) { + he->ms.map = entry->ms.map; + if (he->ms.map) + he->ms.map->referenced = true; + } goto out; } @@ -157,1022 +412,1003 @@ struct hist_entry *__hists__add_entry(struct hists *self, p = &(*p)->rb_right; } - he = hist_entry__new(&entry); + he = hist_entry__new(entry, sample_self); if (!he) return NULL; - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, &self->entries); - hists__inc_nr_entries(self, he); + + rb_link_node(&he->rb_node_in, parent, p); + rb_insert_color(&he->rb_node_in, hists->entries_in); out: - hist_entry__add_cpumode_period(he, al->cpumode, period); + if (sample_self) + he_stat__add_cpumode_period(&he->stat, al->cpumode, period); + if (symbol_conf.cumulate_callchain) + he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period); return he; } -int64_t -hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) +struct hist_entry *__hists__add_entry(struct hists *hists, + struct addr_location *al, + struct symbol *sym_parent, + struct branch_info *bi, + struct mem_info *mi, + u64 period, u64 weight, u64 transaction, + bool sample_self) { - struct sort_entry *se; - int64_t cmp = 0; - - list_for_each_entry(se, &hist_entry__sort_list, list) { - cmp = se->se_cmp(left, right); - if (cmp) - break; - } + struct hist_entry entry = { + .thread = al->thread, + .comm = thread__comm(al->thread), + .ms = { + .map = al->map, + .sym = al->sym, + }, + .cpu = al->cpu, + .cpumode = al->cpumode, + .ip = al->addr, + .level = al->level, + .stat = { + .nr_events = 1, + .period = period, + .weight = weight, + }, + .parent = sym_parent, + .filtered = symbol__parent_filter(sym_parent) | al->filtered, + .hists = hists, + .branch_info = bi, + .mem_info = mi, + .transaction = transaction, + }; - return cmp; + return add_hist_entry(hists, &entry, al, sample_self); } -int64_t -hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) +static int +iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) { - struct sort_entry *se; - int64_t cmp = 0; + return 0; +} - list_for_each_entry(se, &hist_entry__sort_list, list) { - int64_t (*f)(struct hist_entry *, struct hist_entry *); +static int +iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + return 0; +} - f = se->se_collapse ?: se->se_cmp; +static int +iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct perf_sample *sample = iter->sample; + struct mem_info *mi; - cmp = f(left, right); - if (cmp) - break; - } + mi = sample__resolve_mem(sample, al); + if (mi == NULL) + return -ENOMEM; - return cmp; + iter->priv = mi; + return 0; } -void hist_entry__free(struct hist_entry *he) +static int +iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al) { - free(he); -} + u64 cost; + struct mem_info *mi = iter->priv; + struct hist_entry *he; -/* - * collapse the histogram - */ + if (mi == NULL) + return -EINVAL; + + cost = iter->sample->weight; + if (!cost) + cost = 1; + + /* + * must pass period=weight in order to get the correct + * sorting from hists__collapse_resort() which is solely + * based on periods. We want sorting be done on nr_events * weight + * and this is indirectly achieved by passing period=weight here + * and the he_stat__add_period() function. + */ + he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi, + cost, cost, 0, true); + if (!he) + return -ENOMEM; + + iter->he = he; + return 0; +} -static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he) +static int +iter_finish_mem_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) { - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct hist_entry *iter; - int64_t cmp; + struct perf_evsel *evsel = iter->evsel; + struct hist_entry *he = iter->he; + int err = -EINVAL; - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); + if (he == NULL) + goto out; - cmp = hist_entry__collapse(iter, he); + hists__inc_nr_samples(&evsel->hists, he->filtered); - if (!cmp) { - iter->period += he->period; - if (symbol_conf.use_callchain) - callchain_merge(iter->callchain, he->callchain); - hist_entry__free(he); - return false; - } + err = hist_entry__append_callchain(he, iter->sample); - if (cmp < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } +out: + /* + * We don't need to free iter->priv (mem_info) here since + * the mem info was either already freed in add_hist_entry() or + * passed to a new hist entry by hist_entry__new(). + */ + iter->priv = NULL; - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, root); - return true; + iter->he = NULL; + return err; } -void hists__collapse_resort(struct hists *self) +static int +iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct rb_root tmp; - struct rb_node *next; - struct hist_entry *n; + struct branch_info *bi; + struct perf_sample *sample = iter->sample; - if (!sort__need_collapse) - return; + bi = sample__resolve_bstack(sample, al); + if (!bi) + return -ENOMEM; - tmp = RB_ROOT; - next = rb_first(&self->entries); - self->nr_entries = 0; - hists__reset_col_len(self); + iter->curr = 0; + iter->total = sample->branch_stack->nr; - while (next) { - n = rb_entry(next, struct hist_entry, rb_node); - next = rb_next(&n->rb_node); + iter->priv = bi; + return 0; +} - rb_erase(&n->rb_node, &self->entries); - if (collapse__insert_entry(&tmp, n)) - hists__inc_nr_entries(self, n); - } +static int +iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) +{ + /* to avoid calling callback function */ + iter->he = NULL; - self->entries = tmp; + return 0; } -/* - * reverse the map, sort on period. - */ - -static void __hists__insert_output_entry(struct rb_root *entries, - struct hist_entry *he, - u64 min_callchain_hits) +static int +iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct rb_node **p = &entries->rb_node; - struct rb_node *parent = NULL; - struct hist_entry *iter; - - if (symbol_conf.use_callchain) - callchain_param.sort(&he->sorted_chain, he->callchain, - min_callchain_hits, &callchain_param); + struct branch_info *bi = iter->priv; + int i = iter->curr; - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); + if (bi == NULL) + return 0; - if (he->period > iter->period) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } + if (iter->curr >= iter->total) + return 0; - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, entries); + al->map = bi[i].to.map; + al->sym = bi[i].to.sym; + al->addr = bi[i].to.addr; + return 1; } -void hists__output_resort(struct hists *self) +static int +iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) { - struct rb_root tmp; - struct rb_node *next; - struct hist_entry *n; - u64 min_callchain_hits; + struct branch_info *bi; + struct perf_evsel *evsel = iter->evsel; + struct hist_entry *he = NULL; + int i = iter->curr; + int err = 0; - min_callchain_hits = self->stats.total_period * (callchain_param.min_percent / 100); + bi = iter->priv; - tmp = RB_ROOT; - next = rb_first(&self->entries); + if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym)) + goto out; - self->nr_entries = 0; - hists__reset_col_len(self); + /* + * The report shows the percentage of total branches captured + * and not events sampled. Thus we use a pseudo period of 1. + */ + he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL, + 1, 1, 0, true); + if (he == NULL) + return -ENOMEM; - while (next) { - n = rb_entry(next, struct hist_entry, rb_node); - next = rb_next(&n->rb_node); + hists__inc_nr_samples(&evsel->hists, he->filtered); - rb_erase(&n->rb_node, &self->entries); - __hists__insert_output_entry(&tmp, n, min_callchain_hits); - hists__inc_nr_entries(self, n); - } +out: + iter->he = he; + iter->curr++; + return err; +} + +static int +iter_finish_branch_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) +{ + zfree(&iter->priv); + iter->he = NULL; - self->entries = tmp; + return iter->curr >= iter->total ? 0 : -1; } -static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) +static int +iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) { - int i; - int ret = fprintf(fp, " "); + return 0; +} + +static int +iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al) +{ + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; + struct hist_entry *he; - for (i = 0; i < left_margin; i++) - ret += fprintf(fp, " "); + he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + sample->period, sample->weight, + sample->transaction, true); + if (he == NULL) + return -ENOMEM; - return ret; + iter->he = he; + return 0; } -static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask, - int left_margin) +static int +iter_finish_normal_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) { - int i; - size_t ret = callchain__fprintf_left_margin(fp, left_margin); + struct hist_entry *he = iter->he; + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; - for (i = 0; i < depth; i++) - if (depth_mask & (1 << i)) - ret += fprintf(fp, "| "); - else - ret += fprintf(fp, " "); + if (he == NULL) + return 0; + + iter->he = NULL; - ret += fprintf(fp, "\n"); + hists__inc_nr_samples(&evsel->hists, he->filtered); - return ret; + return hist_entry__append_callchain(he, sample); } -static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, - int depth, int depth_mask, int period, - u64 total_samples, int hits, - int left_margin) +static int +iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused, + struct addr_location *al __maybe_unused) { - int i; - size_t ret = 0; + struct hist_entry **he_cache; - ret += callchain__fprintf_left_margin(fp, left_margin); - for (i = 0; i < depth; i++) { - if (depth_mask & (1 << i)) - ret += fprintf(fp, "|"); - else - ret += fprintf(fp, " "); - if (!period && i == depth - 1) { - double percent; - - percent = hits * 100.0 / total_samples; - ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent); - } else - ret += fprintf(fp, "%s", " "); - } - if (chain->ms.sym) - ret += fprintf(fp, "%s\n", chain->ms.sym->name); - else - ret += fprintf(fp, "%p\n", (void *)(long)chain->ip); + callchain_cursor_commit(&callchain_cursor); - return ret; -} + /* + * This is for detecting cycles or recursions so that they're + * cumulated only one time to prevent entries more than 100% + * overhead. + */ + he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1)); + if (he_cache == NULL) + return -ENOMEM; -static struct symbol *rem_sq_bracket; -static struct callchain_list rem_hits; + iter->priv = he_cache; + iter->curr = 0; + + return 0; +} -static void init_rem_hits(void) +static int +iter_add_single_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al) { - rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6); - if (!rem_sq_bracket) { - fprintf(stderr, "Not enough memory to display remaining hits\n"); - return; - } + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; + struct hist_entry **he_cache = iter->priv; + struct hist_entry *he; + int err = 0; + + he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + sample->period, sample->weight, + sample->transaction, true); + if (he == NULL) + return -ENOMEM; + + iter->he = he; + he_cache[iter->curr++] = he; + + callchain_append(he->callchain, &callchain_cursor, sample->period); + + /* + * We need to re-initialize the cursor since callchain_append() + * advanced the cursor to the end. + */ + callchain_cursor_commit(&callchain_cursor); + + hists__inc_nr_samples(&evsel->hists, he->filtered); - strcpy(rem_sq_bracket->name, "[...]"); - rem_hits.ms.sym = rem_sq_bracket; + return err; } -static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self, - u64 total_samples, int depth, - int depth_mask, int left_margin) +static int +iter_next_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al) { - struct rb_node *node, *next; - struct callchain_node *child; - struct callchain_list *chain; - int new_depth_mask = depth_mask; - u64 new_total; - u64 remaining; - size_t ret = 0; - int i; - uint entries_printed = 0; + struct callchain_cursor_node *node; - if (callchain_param.mode == CHAIN_GRAPH_REL) - new_total = self->children_hit; - else - new_total = total_samples; + node = callchain_cursor_current(&callchain_cursor); + if (node == NULL) + return 0; - remaining = new_total; + return fill_callchain_info(al, node, iter->hide_unresolved); +} - node = rb_first(&self->rb_root); - while (node) { - u64 cumul; +static int +iter_add_next_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al) +{ + struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; + struct hist_entry **he_cache = iter->priv; + struct hist_entry *he; + struct hist_entry he_tmp = { + .cpu = al->cpu, + .thread = al->thread, + .comm = thread__comm(al->thread), + .ip = al->addr, + .ms = { + .map = al->map, + .sym = al->sym, + }, + .parent = iter->parent, + }; + int i; + struct callchain_cursor cursor; - child = rb_entry(node, struct callchain_node, rb_node); - cumul = cumul_hits(child); - remaining -= cumul; + callchain_cursor_snapshot(&cursor, &callchain_cursor); - /* - * The depth mask manages the output of pipes that show - * the depth. We don't want to keep the pipes of the current - * level for the last child of this depth. - * Except if we have remaining filtered hits. They will - * supersede the last child - */ - next = rb_next(node); - if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining)) - new_depth_mask &= ~(1 << (depth - 1)); + callchain_cursor_advance(&callchain_cursor); - /* - * But we keep the older depth mask for the line separator - * to keep the level link until we reach the last child - */ - ret += ipchain__fprintf_graph_line(fp, depth, depth_mask, - left_margin); - i = 0; - list_for_each_entry(chain, &child->val, list) { - ret += ipchain__fprintf_graph(fp, chain, depth, - new_depth_mask, i++, - new_total, - cumul, - left_margin); + /* + * Check if there's duplicate entries in the callchain. + * It's possible that it has cycles or recursive calls. + */ + for (i = 0; i < iter->curr; i++) { + if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) { + /* to avoid calling callback function */ + iter->he = NULL; + return 0; } - ret += __callchain__fprintf_graph(fp, child, new_total, - depth + 1, - new_depth_mask | (1 << depth), - left_margin); - node = next; - if (++entries_printed == callchain_param.print_limit) - break; } - if (callchain_param.mode == CHAIN_GRAPH_REL && - remaining && remaining != new_total) { + he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL, + sample->period, sample->weight, + sample->transaction, false); + if (he == NULL) + return -ENOMEM; - if (!rem_sq_bracket) - return ret; + iter->he = he; + he_cache[iter->curr++] = he; - new_depth_mask &= ~(1 << (depth - 1)); + callchain_append(he->callchain, &cursor, sample->period); + return 0; +} - ret += ipchain__fprintf_graph(fp, &rem_hits, depth, - new_depth_mask, 0, new_total, - remaining, left_margin); - } +static int +iter_finish_cumulative_entry(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused) +{ + zfree(&iter->priv); + iter->he = NULL; - return ret; + return 0; } -static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self, - u64 total_samples, int left_margin) +const struct hist_iter_ops hist_iter_mem = { + .prepare_entry = iter_prepare_mem_entry, + .add_single_entry = iter_add_single_mem_entry, + .next_entry = iter_next_nop_entry, + .add_next_entry = iter_add_next_nop_entry, + .finish_entry = iter_finish_mem_entry, +}; + +const struct hist_iter_ops hist_iter_branch = { + .prepare_entry = iter_prepare_branch_entry, + .add_single_entry = iter_add_single_branch_entry, + .next_entry = iter_next_branch_entry, + .add_next_entry = iter_add_next_branch_entry, + .finish_entry = iter_finish_branch_entry, +}; + +const struct hist_iter_ops hist_iter_normal = { + .prepare_entry = iter_prepare_normal_entry, + .add_single_entry = iter_add_single_normal_entry, + .next_entry = iter_next_nop_entry, + .add_next_entry = iter_add_next_nop_entry, + .finish_entry = iter_finish_normal_entry, +}; + +const struct hist_iter_ops hist_iter_cumulative = { + .prepare_entry = iter_prepare_cumulative_entry, + .add_single_entry = iter_add_single_cumulative_entry, + .next_entry = iter_next_cumulative_entry, + .add_next_entry = iter_add_next_cumulative_entry, + .finish_entry = iter_finish_cumulative_entry, +}; + +int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, + struct perf_evsel *evsel, struct perf_sample *sample, + int max_stack_depth, void *arg) { - struct callchain_list *chain; - bool printed = false; - int i = 0; - int ret = 0; - u32 entries_printed = 0; + int err, err2; - list_for_each_entry(chain, &self->val, list) { - if (!i++ && sort__first_dimension == SORT_SYM) - continue; + err = sample__resolve_callchain(sample, &iter->parent, evsel, al, + max_stack_depth); + if (err) + return err; - if (!printed) { - ret += callchain__fprintf_left_margin(fp, left_margin); - ret += fprintf(fp, "|\n"); - ret += callchain__fprintf_left_margin(fp, left_margin); - ret += fprintf(fp, "---"); + iter->evsel = evsel; + iter->sample = sample; - left_margin += 3; - printed = true; - } else - ret += callchain__fprintf_left_margin(fp, left_margin); + err = iter->ops->prepare_entry(iter, al); + if (err) + goto out; - if (chain->ms.sym) - ret += fprintf(fp, " %s\n", chain->ms.sym->name); - else - ret += fprintf(fp, " %p\n", (void *)(long)chain->ip); + err = iter->ops->add_single_entry(iter, al); + if (err) + goto out; - if (++entries_printed == callchain_param.print_limit) + if (iter->he && iter->add_entry_cb) { + err = iter->add_entry_cb(iter, al, true, arg); + if (err) + goto out; + } + + while (iter->ops->next_entry(iter, al)) { + err = iter->ops->add_next_entry(iter, al); + if (err) break; + + if (iter->he && iter->add_entry_cb) { + err = iter->add_entry_cb(iter, al, false, arg); + if (err) + goto out; + } } - ret += __callchain__fprintf_graph(fp, self, total_samples, 1, 1, left_margin); +out: + err2 = iter->ops->finish_entry(iter, al); + if (!err) + err = err2; - return ret; + return err; } -static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self, - u64 total_samples) +int64_t +hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) { - struct callchain_list *chain; - size_t ret = 0; - - if (!self) - return 0; - - ret += callchain__fprintf_flat(fp, self->parent, total_samples); - + struct perf_hpp_fmt *fmt; + int64_t cmp = 0; - list_for_each_entry(chain, &self->val, list) { - if (chain->ip >= PERF_CONTEXT_MAX) + perf_hpp__for_each_sort_list(fmt) { + if (perf_hpp__should_skip(fmt)) continue; - if (chain->ms.sym) - ret += fprintf(fp, " %s\n", chain->ms.sym->name); - else - ret += fprintf(fp, " %p\n", - (void *)(long)chain->ip); + + cmp = fmt->cmp(left, right); + if (cmp) + break; } - return ret; + return cmp; } -static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, - u64 total_samples, int left_margin) +int64_t +hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) { - struct rb_node *rb_node; - struct callchain_node *chain; - size_t ret = 0; - u32 entries_printed = 0; + struct perf_hpp_fmt *fmt; + int64_t cmp = 0; - rb_node = rb_first(&self->sorted_chain); - while (rb_node) { - double percent; + perf_hpp__for_each_sort_list(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; - chain = rb_entry(rb_node, struct callchain_node, rb_node); - percent = chain->hit * 100.0 / total_samples; - switch (callchain_param.mode) { - case CHAIN_FLAT: - ret += percent_color_fprintf(fp, " %6.2f%%\n", - percent); - ret += callchain__fprintf_flat(fp, chain, total_samples); - break; - case CHAIN_GRAPH_ABS: /* Falldown */ - case CHAIN_GRAPH_REL: - ret += callchain__fprintf_graph(fp, chain, total_samples, - left_margin); - case CHAIN_NONE: - default: - break; - } - ret += fprintf(fp, "\n"); - if (++entries_printed == callchain_param.print_limit) + cmp = fmt->collapse(left, right); + if (cmp) break; - rb_node = rb_next(rb_node); } - return ret; + return cmp; } -int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, - struct hists *hists, struct hists *pair_hists, - bool show_displacement, long displacement, - bool color, u64 session_total) +void hist_entry__free(struct hist_entry *he) { - struct sort_entry *se; - u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us; - const char *sep = symbol_conf.field_sep; - int ret; + zfree(&he->branch_info); + zfree(&he->mem_info); + zfree(&he->stat_acc); + free_srcline(he->srcline); + free(he); +} - if (symbol_conf.exclude_other && !self->parent) - return 0; +/* + * collapse the histogram + */ - if (pair_hists) { - period = self->pair ? self->pair->period : 0; - total = pair_hists->stats.total_period; - period_sys = self->pair ? self->pair->period_sys : 0; - period_us = self->pair ? self->pair->period_us : 0; - period_guest_sys = self->pair ? self->pair->period_guest_sys : 0; - period_guest_us = self->pair ? self->pair->period_guest_us : 0; - } else { - period = self->period; - total = session_total; - period_sys = self->period_sys; - period_us = self->period_us; - period_guest_sys = self->period_guest_sys; - period_guest_us = self->period_guest_us; - } +static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, + struct rb_root *root, + struct hist_entry *he) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + int64_t cmp; - if (total) { - if (color) - ret = percent_color_snprintf(s, size, - sep ? "%.2f" : " %6.2f%%", - (period * 100.0) / total); - else - ret = snprintf(s, size, sep ? "%.2f" : " %6.2f%%", - (period * 100.0) / total); - if (symbol_conf.show_cpu_utilization) { - ret += percent_color_snprintf(s + ret, size - ret, - sep ? "%.2f" : " %6.2f%%", - (period_sys * 100.0) / total); - ret += percent_color_snprintf(s + ret, size - ret, - sep ? "%.2f" : " %6.2f%%", - (period_us * 100.0) / total); - if (perf_guest) { - ret += percent_color_snprintf(s + ret, - size - ret, - sep ? "%.2f" : " %6.2f%%", - (period_guest_sys * 100.0) / - total); - ret += percent_color_snprintf(s + ret, - size - ret, - sep ? "%.2f" : " %6.2f%%", - (period_guest_us * 100.0) / - total); + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node_in); + + cmp = hist_entry__collapse(iter, he); + + if (!cmp) { + he_stat__add_stat(&iter->stat, &he->stat); + if (symbol_conf.cumulate_callchain) + he_stat__add_stat(iter->stat_acc, he->stat_acc); + + if (symbol_conf.use_callchain) { + callchain_cursor_reset(&callchain_cursor); + callchain_merge(&callchain_cursor, + iter->callchain, + he->callchain); } + hist_entry__free(he); + return false; } - } else - ret = snprintf(s, size, sep ? "%lld" : "%12lld ", period); - if (symbol_conf.show_nr_samples) { - if (sep) - ret += snprintf(s + ret, size - ret, "%c%lld", *sep, period); + if (cmp < 0) + p = &(*p)->rb_left; else - ret += snprintf(s + ret, size - ret, "%11lld", period); + p = &(*p)->rb_right; } - if (pair_hists) { - char bf[32]; - double old_percent = 0, new_percent = 0, diff; - - if (total > 0) - old_percent = (period * 100.0) / total; - if (session_total > 0) - new_percent = (self->period * 100.0) / session_total; - - diff = new_percent - old_percent; + rb_link_node(&he->rb_node_in, parent, p); + rb_insert_color(&he->rb_node_in, root); + return true; +} - if (fabs(diff) >= 0.01) - snprintf(bf, sizeof(bf), "%+4.2F%%", diff); - else - snprintf(bf, sizeof(bf), " "); +static struct rb_root *hists__get_rotate_entries_in(struct hists *hists) +{ + struct rb_root *root; - if (sep) - ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf); - else - ret += snprintf(s + ret, size - ret, "%11.11s", bf); - - if (show_displacement) { - if (displacement) - snprintf(bf, sizeof(bf), "%+4ld", displacement); - else - snprintf(bf, sizeof(bf), " "); - - if (sep) - ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf); - else - ret += snprintf(s + ret, size - ret, "%6.6s", bf); - } - } + pthread_mutex_lock(&hists->lock); - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; + root = hists->entries_in; + if (++hists->entries_in > &hists->entries_in_array[1]) + hists->entries_in = &hists->entries_in_array[0]; - ret += snprintf(s + ret, size - ret, "%s", sep ?: " "); - ret += se->se_snprintf(self, s + ret, size - ret, - hists__col_len(hists, se->se_width_idx)); - } + pthread_mutex_unlock(&hists->lock); - return ret; + return root; } -int hist_entry__fprintf(struct hist_entry *self, struct hists *hists, - struct hists *pair_hists, bool show_displacement, - long displacement, FILE *fp, u64 session_total) +static void hists__apply_filters(struct hists *hists, struct hist_entry *he) { - char bf[512]; - hist_entry__snprintf(self, bf, sizeof(bf), hists, pair_hists, - show_displacement, displacement, - true, session_total); - return fprintf(fp, "%s\n", bf); + hists__filter_entry_by_dso(hists, he); + hists__filter_entry_by_thread(hists, he); + hists__filter_entry_by_symbol(hists, he); } -static size_t hist_entry__fprintf_callchain(struct hist_entry *self, - struct hists *hists, FILE *fp, - u64 session_total) +void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) { - int left_margin = 0; + struct rb_root *root; + struct rb_node *next; + struct hist_entry *n; - if (sort__first_dimension == SORT_COMM) { - struct sort_entry *se = list_first_entry(&hist_entry__sort_list, - typeof(*se), list); - left_margin = hists__col_len(hists, se->se_width_idx); - left_margin -= thread__comm_len(self->thread); - } + if (!sort__need_collapse) + return; + + root = hists__get_rotate_entries_in(hists); + next = rb_first(root); - return hist_entry_callchain__fprintf(fp, self, session_total, - left_margin); + while (next) { + if (session_done()) + break; + n = rb_entry(next, struct hist_entry, rb_node_in); + next = rb_next(&n->rb_node_in); + + rb_erase(&n->rb_node_in, root); + if (hists__collapse_insert_entry(hists, &hists->entries_collapsed, n)) { + /* + * If it wasn't combined with one of the entries already + * collapsed, we need to apply the filters that may have + * been set by, say, the hist_browser. + */ + hists__apply_filters(hists, n); + } + if (prog) + ui_progress__update(prog, 1); + } } -size_t hists__fprintf(struct hists *self, struct hists *pair, - bool show_displacement, FILE *fp) +static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { - struct sort_entry *se; - struct rb_node *nd; - size_t ret = 0; - unsigned long position = 1; - long displacement = 0; - unsigned int width; - const char *sep = symbol_conf.field_sep; - const char *col_width = symbol_conf.col_width_list_str; - - init_rem_hits(); + struct perf_hpp_fmt *fmt; + int64_t cmp = 0; - fprintf(fp, "# %s", pair ? "Baseline" : "Overhead"); + perf_hpp__for_each_sort_list(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; - if (symbol_conf.show_nr_samples) { - if (sep) - fprintf(fp, "%cSamples", *sep); - else - fputs(" Samples ", fp); + cmp = fmt->sort(a, b); + if (cmp) + break; } - if (symbol_conf.show_cpu_utilization) { - if (sep) { - ret += fprintf(fp, "%csys", *sep); - ret += fprintf(fp, "%cus", *sep); - if (perf_guest) { - ret += fprintf(fp, "%cguest sys", *sep); - ret += fprintf(fp, "%cguest us", *sep); - } - } else { - ret += fprintf(fp, " sys "); - ret += fprintf(fp, " us "); - if (perf_guest) { - ret += fprintf(fp, " guest sys "); - ret += fprintf(fp, " guest us "); - } - } - } + return cmp; +} - if (pair) { - if (sep) - ret += fprintf(fp, "%cDelta", *sep); - else - ret += fprintf(fp, " Delta "); +static void hists__reset_filter_stats(struct hists *hists) +{ + hists->nr_non_filtered_entries = 0; + hists->stats.total_non_filtered_period = 0; +} - if (show_displacement) { - if (sep) - ret += fprintf(fp, "%cDisplacement", *sep); - else - ret += fprintf(fp, " Displ"); - } - } +void hists__reset_stats(struct hists *hists) +{ + hists->nr_entries = 0; + hists->stats.total_period = 0; - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - if (sep) { - fprintf(fp, "%c%s", *sep, se->se_header); - continue; - } - width = strlen(se->se_header); - if (symbol_conf.col_width_list_str) { - if (col_width) { - hists__set_col_len(self, se->se_width_idx, - atoi(col_width)); - col_width = strchr(col_width, ','); - if (col_width) - ++col_width; - } - } - if (!hists__new_col_len(self, se->se_width_idx, width)) - width = hists__col_len(self, se->se_width_idx); - fprintf(fp, " %*s", width, se->se_header); - } - fprintf(fp, "\n"); - - if (sep) - goto print_entries; - - fprintf(fp, "# ........"); - if (symbol_conf.show_nr_samples) - fprintf(fp, " .........."); - if (pair) { - fprintf(fp, " .........."); - if (show_displacement) - fprintf(fp, " ....."); - } - list_for_each_entry(se, &hist_entry__sort_list, list) { - unsigned int i; + hists__reset_filter_stats(hists); +} - if (se->elide) - continue; +static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h) +{ + hists->nr_non_filtered_entries++; + hists->stats.total_non_filtered_period += h->stat.period; +} - fprintf(fp, " "); - width = hists__col_len(self, se->se_width_idx); - if (width == 0) - width = strlen(se->se_header); - for (i = 0; i < width; i++) - fprintf(fp, "."); - } +void hists__inc_stats(struct hists *hists, struct hist_entry *h) +{ + if (!h->filtered) + hists__inc_filter_stats(hists, h); - fprintf(fp, "\n#\n"); + hists->nr_entries++; + hists->stats.total_period += h->stat.period; +} -print_entries: - for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); +static void __hists__insert_output_entry(struct rb_root *entries, + struct hist_entry *he, + u64 min_callchain_hits) +{ + struct rb_node **p = &entries->rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; - if (show_displacement) { - if (h->pair != NULL) - displacement = ((long)h->pair->position - - (long)position); - else - displacement = 0; - ++position; - } - ret += hist_entry__fprintf(h, self, pair, show_displacement, - displacement, fp, self->stats.total_period); + if (symbol_conf.use_callchain) + callchain_param.sort(&he->sorted_chain, he->callchain, + min_callchain_hits, &callchain_param); - if (symbol_conf.use_callchain) - ret += hist_entry__fprintf_callchain(h, self, fp, - self->stats.total_period); - if (h->ms.map == NULL && verbose > 1) { - __map_groups__fprintf_maps(&h->thread->mg, - MAP__FUNCTION, verbose, fp); - fprintf(fp, "%.10s end\n", graph_dotted_line); - } - } + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); - free(rem_sq_bracket); + if (hist_entry__sort(he, iter) > 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } - return ret; + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, entries); } -/* - * See hists__fprintf to match the column widths - */ -unsigned int hists__sort_list_width(struct hists *self) +void hists__output_resort(struct hists *hists) { - struct sort_entry *se; - int ret = 9; /* total % */ + struct rb_root *root; + struct rb_node *next; + struct hist_entry *n; + u64 min_callchain_hits; - if (symbol_conf.show_cpu_utilization) { - ret += 7; /* count_sys % */ - ret += 6; /* count_us % */ - if (perf_guest) { - ret += 13; /* count_guest_sys % */ - ret += 12; /* count_guest_us % */ - } - } + min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100); + + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; - if (symbol_conf.show_nr_samples) - ret += 11; + next = rb_first(root); + hists->entries = RB_ROOT; - list_for_each_entry(se, &hist_entry__sort_list, list) - if (!se->elide) - ret += 2 + hists__col_len(self, se->se_width_idx); + hists__reset_stats(hists); + hists__reset_col_len(hists); - if (verbose) /* Addr + origin */ - ret += 3 + BITS_PER_LONG / 4; + while (next) { + n = rb_entry(next, struct hist_entry, rb_node_in); + next = rb_next(&n->rb_node_in); + + __hists__insert_output_entry(&hists->entries, n, min_callchain_hits); + hists__inc_stats(hists, n); - return ret; + if (!n->filtered) + hists__calc_col_len(hists, n); + } } -static void hists__remove_entry_filter(struct hists *self, struct hist_entry *h, +static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h, enum hist_filter filter) { h->filtered &= ~(1 << filter); if (h->filtered) return; - ++self->nr_entries; - if (h->ms.unfolded) - self->nr_entries += h->nr_rows; + /* force fold unfiltered entry for simplicity */ + h->ms.unfolded = false; h->row_offset = 0; - self->stats.total_period += h->period; - self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events; - hists__calc_col_len(self, h); + hists->stats.nr_non_filtered_samples += h->stat.nr_events; + + hists__inc_filter_stats(hists, h); + hists__calc_col_len(hists, h); } -void hists__filter_by_dso(struct hists *self, const struct dso *dso) + +static bool hists__filter_entry_by_dso(struct hists *hists, + struct hist_entry *he) +{ + if (hists->dso_filter != NULL && + (he->ms.map == NULL || he->ms.map->dso != hists->dso_filter)) { + he->filtered |= (1 << HIST_FILTER__DSO); + return true; + } + + return false; +} + +void hists__filter_by_dso(struct hists *hists) { struct rb_node *nd; - self->nr_entries = self->stats.total_period = 0; - self->stats.nr_events[PERF_RECORD_SAMPLE] = 0; - hists__reset_col_len(self); + hists->stats.nr_non_filtered_samples = 0; + + hists__reset_filter_stats(hists); + hists__reset_col_len(hists); - for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { + for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); if (symbol_conf.exclude_other && !h->parent) continue; - if (dso != NULL && (h->ms.map == NULL || h->ms.map->dso != dso)) { - h->filtered |= (1 << HIST_FILTER__DSO); + if (hists__filter_entry_by_dso(hists, h)) continue; - } - hists__remove_entry_filter(self, h, HIST_FILTER__DSO); + hists__remove_entry_filter(hists, h, HIST_FILTER__DSO); + } +} + +static bool hists__filter_entry_by_thread(struct hists *hists, + struct hist_entry *he) +{ + if (hists->thread_filter != NULL && + he->thread != hists->thread_filter) { + he->filtered |= (1 << HIST_FILTER__THREAD); + return true; } + + return false; } -void hists__filter_by_thread(struct hists *self, const struct thread *thread) +void hists__filter_by_thread(struct hists *hists) { struct rb_node *nd; - self->nr_entries = self->stats.total_period = 0; - self->stats.nr_events[PERF_RECORD_SAMPLE] = 0; - hists__reset_col_len(self); + hists->stats.nr_non_filtered_samples = 0; - for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { + hists__reset_filter_stats(hists); + hists__reset_col_len(hists); + + for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - if (thread != NULL && h->thread != thread) { - h->filtered |= (1 << HIST_FILTER__THREAD); + if (hists__filter_entry_by_thread(hists, h)) continue; - } - hists__remove_entry_filter(self, h, HIST_FILTER__THREAD); + hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD); } } -static int symbol__alloc_hist(struct symbol *self) +static bool hists__filter_entry_by_symbol(struct hists *hists, + struct hist_entry *he) { - struct sym_priv *priv = symbol__priv(self); - const int size = (sizeof(*priv->hist) + - (self->end - self->start) * sizeof(u64)); + if (hists->symbol_filter_str != NULL && + (!he->ms.sym || strstr(he->ms.sym->name, + hists->symbol_filter_str) == NULL)) { + he->filtered |= (1 << HIST_FILTER__SYMBOL); + return true; + } - priv->hist = zalloc(size); - return priv->hist == NULL ? -1 : 0; + return false; } -int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip) +void hists__filter_by_symbol(struct hists *hists) { - unsigned int sym_size, offset; - struct symbol *sym = self->ms.sym; - struct sym_priv *priv; - struct sym_hist *h; - - if (!sym || !self->ms.map) - return 0; - - priv = symbol__priv(sym); - if (priv->hist == NULL && symbol__alloc_hist(sym) < 0) - return -ENOMEM; - - sym_size = sym->end - sym->start; - offset = ip - sym->start; - - pr_debug3("%s: ip=%#Lx\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip)); + struct rb_node *nd; - if (offset >= sym_size) - return 0; + hists->stats.nr_non_filtered_samples = 0; - h = priv->hist; - h->sum++; - h->ip[offset]++; + hists__reset_filter_stats(hists); + hists__reset_col_len(hists); - pr_debug3("%#Lx %s: period++ [ip: %#Lx, %#Lx] => %Ld\n", self->ms.sym->start, - self->ms.sym->name, ip, ip - self->ms.sym->start, h->ip[offset]); - return 0; -} + for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); -static struct objdump_line *objdump_line__new(s64 offset, char *line, size_t privsize) -{ - struct objdump_line *self = malloc(sizeof(*self) + privsize); + if (hists__filter_entry_by_symbol(hists, h)) + continue; - if (self != NULL) { - self->offset = offset; - self->line = line; + hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL); } - - return self; } -void objdump_line__free(struct objdump_line *self) +void events_stats__inc(struct events_stats *stats, u32 type) { - free(self->line); - free(self); + ++stats->nr_events[0]; + ++stats->nr_events[type]; } -static void objdump__add_line(struct list_head *head, struct objdump_line *line) +void hists__inc_nr_events(struct hists *hists, u32 type) { - list_add_tail(&line->node, head); + events_stats__inc(&hists->stats, type); } -struct objdump_line *objdump__get_next_ip_line(struct list_head *head, - struct objdump_line *pos) +void hists__inc_nr_samples(struct hists *hists, bool filtered) { - list_for_each_entry_continue(pos, head, node) - if (pos->offset >= 0) - return pos; - - return NULL; + events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE); + if (!filtered) + hists->stats.nr_non_filtered_samples++; } -static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file, - struct list_head *head, size_t privsize) +static struct hist_entry *hists__add_dummy_entry(struct hists *hists, + struct hist_entry *pair) { - struct symbol *sym = self->ms.sym; - struct objdump_line *objdump_line; - char *line = NULL, *tmp, *tmp2, *c; - size_t line_len; - s64 line_ip, offset = -1; + struct rb_root *root; + struct rb_node **p; + struct rb_node *parent = NULL; + struct hist_entry *he; + int64_t cmp; - if (getline(&line, &line_len, file) < 0) - return -1; + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; - if (!line) - return -1; + p = &root->rb_node; - while (line_len != 0 && isspace(line[line_len - 1])) - line[--line_len] = '\0'; + while (*p != NULL) { + parent = *p; + he = rb_entry(parent, struct hist_entry, rb_node_in); - c = strchr(line, '\n'); - if (c) - *c = 0; + cmp = hist_entry__collapse(he, pair); - line_ip = -1; + if (!cmp) + goto out; - /* - * Strip leading spaces: - */ - tmp = line; - while (*tmp) { - if (*tmp != ' ') - break; - tmp++; + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; } - if (*tmp) { - /* - * Parse hexa addresses followed by ':' - */ - line_ip = strtoull(tmp, &tmp2, 16); - if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0') - line_ip = -1; + he = hist_entry__new(pair, true); + if (he) { + memset(&he->stat, 0, sizeof(he->stat)); + he->hists = hists; + rb_link_node(&he->rb_node_in, parent, p); + rb_insert_color(&he->rb_node_in, root); + hists__inc_stats(hists, he); + he->dummy = true; } +out: + return he; +} - if (line_ip != -1) { - u64 start = map__rip_2objdump(self->ms.map, sym->start), - end = map__rip_2objdump(self->ms.map, sym->end); +static struct hist_entry *hists__find_entry(struct hists *hists, + struct hist_entry *he) +{ + struct rb_node *n; - offset = line_ip - start; - if (offset < 0 || (u64)line_ip > end) - offset = -1; - } + if (sort__need_collapse) + n = hists->entries_collapsed.rb_node; + else + n = hists->entries_in->rb_node; - objdump_line = objdump_line__new(offset, line, privsize); - if (objdump_line == NULL) { - free(line); - return -1; + while (n) { + struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node_in); + int64_t cmp = hist_entry__collapse(iter, he); + + if (cmp < 0) + n = n->rb_left; + else if (cmp > 0) + n = n->rb_right; + else + return iter; } - objdump__add_line(head, objdump_line); - return 0; + return NULL; } -int hist_entry__annotate(struct hist_entry *self, struct list_head *head, - size_t privsize) +/* + * Look for pairs to link to the leader buckets (hist_entries): + */ +void hists__match(struct hists *leader, struct hists *other) { - struct symbol *sym = self->ms.sym; - struct map *map = self->ms.map; - struct dso *dso = map->dso; - char *filename = dso__build_id_filename(dso, NULL, 0); - bool free_filename = true; - char command[PATH_MAX * 2]; - FILE *file; - int err = 0; - u64 len; - - if (filename == NULL) { - if (dso->has_build_id) { - pr_err("Can't annotate %s: not enough memory\n", - sym->name); - return -ENOMEM; - } - goto fallback; - } else if (readlink(filename, command, sizeof(command)) < 0 || - strstr(command, "[kernel.kallsyms]") || - access(filename, R_OK)) { - free(filename); -fallback: - /* - * If we don't have build-ids or the build-id file isn't in the - * cache, or is just a kallsyms file, well, lets hope that this - * DSO is the same as when 'perf record' ran. - */ - filename = dso->long_name; - free_filename = false; - } - - if (dso->origin == DSO__ORIG_KERNEL) { - if (dso->annotate_warned) - goto out_free_filename; - err = -ENOENT; - dso->annotate_warned = 1; - pr_err("Can't annotate %s: No vmlinux file was found in the " - "path\n", sym->name); - goto out_free_filename; - } + struct rb_root *root; + struct rb_node *nd; + struct hist_entry *pos, *pair; - pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__, - filename, sym->name, map->unmap_ip(map, sym->start), - map->unmap_ip(map, sym->end)); + if (sort__need_collapse) + root = &leader->entries_collapsed; + else + root = leader->entries_in; - len = sym->end - sym->start; + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node_in); + pair = hists__find_entry(other, pos); - pr_debug("annotating [%p] %30s : [%p] %30s\n", - dso, dso->long_name, sym, sym->name); + if (pair) + hist_entry__add_pair(pair, pos); + } +} - snprintf(command, sizeof(command), - "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS -C %s|grep -v %s|expand", - map__rip_2objdump(map, sym->start), - map__rip_2objdump(map, sym->end), - filename, filename); +/* + * Look for entries in the other hists that are not present in the leader, if + * we find them, just add a dummy entry on the leader hists, with period=0, + * nr_events=0, to serve as the list header. + */ +int hists__link(struct hists *leader, struct hists *other) +{ + struct rb_root *root; + struct rb_node *nd; + struct hist_entry *pos, *pair; - pr_debug("Executing: %s\n", command); + if (sort__need_collapse) + root = &other->entries_collapsed; + else + root = other->entries_in; - file = popen(command, "r"); - if (!file) - goto out_free_filename; + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node_in); - while (!feof(file)) - if (hist_entry__parse_objdump_line(self, file, head, privsize) < 0) - break; + if (!hist_entry__has_pairs(pos)) { + pair = hists__add_dummy_entry(leader, pos); + if (pair == NULL) + return -1; + hist_entry__add_pair(pos, pair); + } + } - pclose(file); -out_free_filename: - if (free_filename) - free(filename); - return err; + return 0; } -void hists__inc_nr_events(struct hists *self, u32 type) +u64 hists__total_period(struct hists *hists) { - ++self->stats.nr_events[0]; - ++self->stats.nr_events[type]; + return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period : + hists->stats.total_period; } -size_t hists__fprintf_nr_events(struct hists *self, FILE *fp) +int parse_filter_percentage(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) { - int i; - size_t ret = 0; + if (!strcmp(arg, "relative")) + symbol_conf.filter_relative = true; + else if (!strcmp(arg, "absolute")) + symbol_conf.filter_relative = false; + else + return -1; - for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) { - if (!event__name[i]) - continue; - ret += fprintf(fp, "%10s events: %10d\n", - event__name[i], self->stats.nr_events[i]); - } + return 0; +} + +int perf_hist_config(const char *var, const char *value) +{ + if (!strcmp(var, "hist.percentage")) + return parse_filter_percentage(NULL, value, 0); - return ret; + return 0; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 587d375d343..742f49a8572 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -2,39 +2,25 @@ #define __PERF_HIST_H #include <linux/types.h> +#include <pthread.h> #include "callchain.h" +#include "header.h" +#include "color.h" +#include "ui/progress.h" extern struct callchain_param callchain_param; struct hist_entry; struct addr_location; struct symbol; -struct rb_root; -struct objdump_line { - struct list_head node; - s64 offset; - char *line; -}; - -void objdump_line__free(struct objdump_line *self); -struct objdump_line *objdump__get_next_ip_line(struct list_head *head, - struct objdump_line *pos); - -struct sym_hist { - u64 sum; - u64 ip[0]; -}; - -struct sym_ext { - struct rb_node node; - double percent; - char *path; -}; - -struct sym_priv { - struct sym_hist *hist; - struct sym_ext *ext; +enum hist_filter { + HIST_FILTER__DSO, + HIST_FILTER__THREAD, + HIST_FILTER__PARENT, + HIST_FILTER__SYMBOL, + HIST_FILTER__GUEST, + HIST_FILTER__HOST, }; /* @@ -51,9 +37,16 @@ struct sym_priv { */ struct events_stats { u64 total_period; + u64 total_non_filtered_period; u64 total_lost; + u64 total_invalid_chains; u32 nr_events[PERF_RECORD_HEADER_MAX]; + u32 nr_non_filtered_samples; + u32 nr_lost_warned; u32 nr_unknown_events; + u32 nr_invalid_chains; + u32 nr_unknown_id; + u32 nr_unprocessable_samples; }; enum hist_column { @@ -63,86 +56,292 @@ enum hist_column { HISTC_COMM, HISTC_PARENT, HISTC_CPU, + HISTC_SRCLINE, + HISTC_MISPREDICT, + HISTC_IN_TX, + HISTC_ABORT, + HISTC_SYMBOL_FROM, + HISTC_SYMBOL_TO, + HISTC_DSO_FROM, + HISTC_DSO_TO, + HISTC_LOCAL_WEIGHT, + HISTC_GLOBAL_WEIGHT, + HISTC_MEM_DADDR_SYMBOL, + HISTC_MEM_DADDR_DSO, + HISTC_MEM_LOCKED, + HISTC_MEM_TLB, + HISTC_MEM_LVL, + HISTC_MEM_SNOOP, + HISTC_MEM_DCACHELINE, + HISTC_TRANSACTION, HISTC_NR_COLS, /* Last entry */ }; +struct thread; +struct dso; + struct hists { - struct rb_node rb_node; + struct rb_root entries_in_array[2]; + struct rb_root *entries_in; struct rb_root entries; + struct rb_root entries_collapsed; u64 nr_entries; + u64 nr_non_filtered_entries; + const struct thread *thread_filter; + const struct dso *dso_filter; + const char *uid_filter_str; + const char *symbol_filter_str; + pthread_mutex_t lock; struct events_stats stats; - u64 config; u64 event_stream; - u32 type; u16 col_len[HISTC_NR_COLS]; }; -struct hist_entry *__hists__add_entry(struct hists *self, +struct hist_entry_iter; + +struct hist_iter_ops { + int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *); + int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *); + int (*next_entry)(struct hist_entry_iter *, struct addr_location *); + int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *); + int (*finish_entry)(struct hist_entry_iter *, struct addr_location *); +}; + +struct hist_entry_iter { + int total; + int curr; + + bool hide_unresolved; + + struct perf_evsel *evsel; + struct perf_sample *sample; + struct hist_entry *he; + struct symbol *parent; + void *priv; + + const struct hist_iter_ops *ops; + /* user-defined callback function (optional) */ + int (*add_entry_cb)(struct hist_entry_iter *iter, + struct addr_location *al, bool single, void *arg); +}; + +extern const struct hist_iter_ops hist_iter_normal; +extern const struct hist_iter_ops hist_iter_branch; +extern const struct hist_iter_ops hist_iter_mem; +extern const struct hist_iter_ops hist_iter_cumulative; + +struct hist_entry *__hists__add_entry(struct hists *hists, struct addr_location *al, - struct symbol *parent, u64 period); -extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *); -extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *); -int hist_entry__fprintf(struct hist_entry *self, struct hists *hists, - struct hists *pair_hists, bool show_displacement, - long displacement, FILE *fp, u64 total); -int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size, - struct hists *hists, struct hists *pair_hists, - bool show_displacement, long displacement, - bool color, u64 total); + struct symbol *parent, + struct branch_info *bi, + struct mem_info *mi, u64 period, + u64 weight, u64 transaction, + bool sample_self); +int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, + struct perf_evsel *evsel, struct perf_sample *sample, + int max_stack_depth, void *arg); + +int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); +int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); +int hist_entry__transaction_len(void); +int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size, + struct hists *hists); void hist_entry__free(struct hist_entry *); -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); + +u64 hists__total_period(struct hists *hists); +void hists__reset_stats(struct hists *hists); +void hists__inc_stats(struct hists *hists, struct hist_entry *h); +void hists__inc_nr_events(struct hists *hists, u32 type); +void hists__inc_nr_samples(struct hists *hists, bool filtered); +void events_stats__inc(struct events_stats *stats, u32 type); +size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); + +size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, + int max_cols, float min_pcnt, FILE *fp); + +void hists__filter_by_dso(struct hists *hists); +void hists__filter_by_thread(struct hists *hists); +void hists__filter_by_symbol(struct hists *hists); + +static inline bool hists__has_filter(struct hists *hists) +{ + return hists->thread_filter || hists->dso_filter || + hists->symbol_filter_str; +} + +u16 hists__col_len(struct hists *hists, enum hist_column col); +void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len); +bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len); +void hists__reset_col_len(struct hists *hists); +void hists__calc_col_len(struct hists *hists, struct hist_entry *he); + +void hists__match(struct hists *leader, struct hists *other); +int hists__link(struct hists *leader, struct hists *other); + +struct perf_hpp { + char *buf; + size_t size; + const char *sep; + void *ptr; +}; + +struct perf_hpp_fmt { + int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel); + int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel); + 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); + int64_t (*cmp)(struct hist_entry *a, struct hist_entry *b); + int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b); + int64_t (*sort)(struct hist_entry *a, struct hist_entry *b); + + struct list_head list; + struct list_head sort_list; + bool elide; +}; + +extern struct list_head perf_hpp__list; +extern struct list_head perf_hpp__sort_list; + +#define perf_hpp__for_each_format(format) \ + list_for_each_entry(format, &perf_hpp__list, list) + +#define perf_hpp__for_each_format_safe(format, tmp) \ + list_for_each_entry_safe(format, tmp, &perf_hpp__list, list) + +#define perf_hpp__for_each_sort_list(format) \ + list_for_each_entry(format, &perf_hpp__sort_list, sort_list) + +#define perf_hpp__for_each_sort_list_safe(format, tmp) \ + list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list) + +extern struct perf_hpp_fmt perf_hpp__format[]; + +enum { + /* Matches perf_hpp__format array. */ + PERF_HPP__OVERHEAD, + PERF_HPP__OVERHEAD_SYS, + PERF_HPP__OVERHEAD_US, + PERF_HPP__OVERHEAD_GUEST_SYS, + PERF_HPP__OVERHEAD_GUEST_US, + PERF_HPP__OVERHEAD_ACC, + PERF_HPP__SAMPLES, + PERF_HPP__PERIOD, -void hists__inc_nr_events(struct hists *self, u32 type); -size_t hists__fprintf_nr_events(struct hists *self, FILE *fp); + PERF_HPP__MAX_INDEX +}; + +void perf_hpp__init(void); +void perf_hpp__column_register(struct perf_hpp_fmt *format); +void perf_hpp__column_unregister(struct perf_hpp_fmt *format); +void perf_hpp__column_enable(unsigned col); +void perf_hpp__column_disable(unsigned col); +void perf_hpp__cancel_cumulate(void); + +void perf_hpp__register_sort_field(struct perf_hpp_fmt *format); +void perf_hpp__setup_output_field(void); +void perf_hpp__reset_output_field(void); +void perf_hpp__append_sort_keys(void); + +bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); +bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); -size_t hists__fprintf(struct hists *self, struct hists *pair, - bool show_displacement, FILE *fp); +static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format) +{ + return format->elide; +} -int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip); -int hist_entry__annotate(struct hist_entry *self, struct list_head *head, - size_t privsize); +void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists); -void hists__filter_by_dso(struct hists *self, const struct dso *dso); -void hists__filter_by_thread(struct hists *self, const struct thread *thread); +typedef u64 (*hpp_field_fn)(struct hist_entry *he); +typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front); +typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...); -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); +int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, + hpp_field_fn get_field, const char *fmt, + hpp_snprint_fn print_fn, bool fmt_percent); +int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he, + hpp_field_fn get_field, const char *fmt, + hpp_snprint_fn print_fn, bool fmt_percent); -#ifdef NO_NEWT_SUPPORT -static inline int hists__browse(struct hists *self __used, - const char *helpline __used, - const char *ev_name __used) +static inline void advance_hpp(struct perf_hpp *hpp, int inc) { - return 0; + hpp->buf += inc; + hpp->size -= inc; } -static inline int hists__tui_browse_tree(struct rb_root *self __used, - const char *help __used) +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; + +struct hist_browser_timer { + void (*timer)(void *arg); + void *arg; + int refresh; +}; + +#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); + +int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, + struct hist_browser_timer *hbt, + float min_pcnt, + struct perf_session_env *env); +int script_browse(const char *script_opt); +#else +static inline +int perf_evlist__tui_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, + struct perf_session_env *env __maybe_unused) { return 0; } -static inline int hist_entry__tui_annotate(struct hist_entry *self __used) +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; } -#define KEY_LEFT -1 -#define KEY_RIGHT -2 -#else -#include <newt.h> -int hists__browse(struct hists *self, const char *helpline, - const char *ev_name); -int hist_entry__tui_annotate(struct hist_entry *self); -#define KEY_LEFT NEWT_KEY_LEFT -#define KEY_RIGHT NEWT_KEY_RIGHT +static inline int script_browse(const char *script_opt __maybe_unused) +{ + return 0; +} -int hists__tui_browse_tree(struct rb_root *self, const char *help); +#define K_LEFT -1000 +#define K_RIGHT -2000 +#define K_SWITCH_INPUT_DATA -3000 #endif -unsigned int hists__sort_list_width(struct hists *self); +unsigned int hists__sort_list_width(struct hists *hists); + +struct option; +int parse_filter_percentage(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused); +int perf_hist_config(const char *var, const char *value); #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h new file mode 100644 index 00000000000..6789d788d49 --- /dev/null +++ b/tools/perf/util/include/asm/alternative-asm.h @@ -0,0 +1,8 @@ +#ifndef _PERF_ASM_ALTERNATIVE_ASM_H +#define _PERF_ASM_ALTERNATIVE_ASM_H + +/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ + +#define altinstruction_entry # + +#endif diff --git a/tools/perf/util/include/asm/bug.h b/tools/perf/util/include/asm/bug.h deleted file mode 100644 index 7fcc6810adc..00000000000 --- a/tools/perf/util/include/asm/bug.h +++ /dev/null @@ -1,22 +0,0 @@ -#ifndef _PERF_ASM_GENERIC_BUG_H -#define _PERF_ASM_GENERIC_BUG_H - -#define __WARN_printf(arg...) do { fprintf(stderr, arg); } while (0) - -#define WARN(condition, format...) ({ \ - int __ret_warn_on = !!(condition); \ - if (unlikely(__ret_warn_on)) \ - __WARN_printf(format); \ - unlikely(__ret_warn_on); \ -}) - -#define WARN_ONCE(condition, format...) ({ \ - static int __warned; \ - int __ret_warn_once = !!(condition); \ - \ - if (unlikely(__ret_warn_once)) \ - if (WARN(!__warned, format)) \ - __warned = 1; \ - unlikely(__ret_warn_once); \ -}) -#endif diff --git a/tools/perf/util/include/asm/byteorder.h b/tools/perf/util/include/asm/byteorder.h index b722abe3a62..2a9bdc06630 100644 --- a/tools/perf/util/include/asm/byteorder.h +++ b/tools/perf/util/include/asm/byteorder.h @@ -1,2 +1,2 @@ #include <asm/types.h> -#include "../../../../include/linux/swab.h" +#include "../../../../include/uapi/linux/swab.h" diff --git a/tools/perf/util/include/asm/cpufeature.h b/tools/perf/util/include/asm/cpufeature.h new file mode 100644 index 00000000000..acffd5e4d1d --- /dev/null +++ b/tools/perf/util/include/asm/cpufeature.h @@ -0,0 +1,9 @@ + +#ifndef PERF_CPUFEATURE_H +#define PERF_CPUFEATURE_H + +/* cpufeature.h ... dummy header file for including arch/x86/lib/memcpy_64.S */ + +#define X86_FEATURE_REP_GOOD 0 + +#endif /* PERF_CPUFEATURE_H */ diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h new file mode 100644 index 00000000000..afe38199e92 --- /dev/null +++ b/tools/perf/util/include/asm/dwarf2.h @@ -0,0 +1,13 @@ + +#ifndef PERF_DWARF2_H +#define PERF_DWARF2_H + +/* dwarf2.h ... dummy header file for including arch/x86/lib/mem{cpy,set}_64.S */ + +#define CFI_STARTPROC +#define CFI_ENDPROC +#define CFI_REMEMBER_STATE +#define CFI_RESTORE_STATE + +#endif /* PERF_DWARF2_H */ + diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h new file mode 100644 index 00000000000..d82b170bb21 --- /dev/null +++ b/tools/perf/util/include/asm/hash.h @@ -0,0 +1,6 @@ +#ifndef __ASM_GENERIC_HASH_H +#define __ASM_GENERIC_HASH_H + +/* Stub */ + +#endif /* __ASM_GENERIC_HASH_H */ diff --git a/tools/perf/util/include/asm/unistd_32.h b/tools/perf/util/include/asm/unistd_32.h new file mode 100644 index 00000000000..8b137891791 --- /dev/null +++ b/tools/perf/util/include/asm/unistd_32.h @@ -0,0 +1 @@ + diff --git a/tools/perf/util/include/asm/unistd_64.h b/tools/perf/util/include/asm/unistd_64.h new file mode 100644 index 00000000000..8b137891791 --- /dev/null +++ b/tools/perf/util/include/asm/unistd_64.h @@ -0,0 +1 @@ + diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h index cf6727e99c4..8f149655f49 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/bitmap.h b/tools/perf/util/include/linux/bitmap.h index eda4416efa0..01ffd12dc79 100644 --- a/tools/perf/util/include/linux/bitmap.h +++ b/tools/perf/util/include/linux/bitmap.h @@ -4,7 +4,12 @@ #include <string.h> #include <linux/bitops.h> +#define DECLARE_BITMAP(name,bits) \ + unsigned long name[BITS_TO_LONGS(bits)] + int __bitmap_weight(const unsigned long *bitmap, int bits); +void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, int bits); #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ @@ -32,4 +37,13 @@ static inline int bitmap_weight(const unsigned long *src, int nbits) return __bitmap_weight(src, nbits); } +static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, int nbits) +{ + if (small_const_nbits(nbits)) + *dst = *src1 | *src2; + else + __bitmap_or(dst, src1, src2, nbits); +} + #endif /* _PERF_BITOPS_H */ diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h index bb4ac2e0538..dadfa7e5428 100644 --- a/tools/perf/util/include/linux/bitops.h +++ b/tools/perf/util/include/linux/bitops.h @@ -2,17 +2,41 @@ #define _PERF_LINUX_BITOPS_H_ #include <linux/kernel.h> +#include <linux/compiler.h> #include <asm/hweight.h> +#ifndef __WORDSIZE +#define __WORDSIZE (__SIZEOF_LONG__ * 8) +#endif + #define BITS_PER_LONG __WORDSIZE #define BITS_PER_BYTE 8 #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) +#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64)) +#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) +#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE) + +#define for_each_set_bit(bit, addr, size) \ + for ((bit) = find_first_bit((addr), (size)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + +/* same as for_each_set_bit() but use bit as value to start with */ +#define for_each_set_bit_from(bit, addr, size) \ + for ((bit) = find_next_bit((addr), (size), (bit)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) static inline void set_bit(int nr, unsigned long *addr) { addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG); } +static inline void clear_bit(int nr, unsigned long *addr) +{ + addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG)); +} + static __always_inline int test_bit(unsigned int nr, const unsigned long *addr) { return ((1UL << (nr % BITS_PER_LONG)) & @@ -24,4 +48,113 @@ static inline unsigned long hweight_long(unsigned long w) return sizeof(w) == 4 ? hweight32(w) : hweight64(w); } +#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) + +/** + * __ffs - find first bit in word. + * @word: The word to search + * + * Undefined if no bit exists, so code should check against 0 first. + */ +static __always_inline unsigned long __ffs(unsigned long word) +{ + int num = 0; + +#if BITS_PER_LONG == 64 + if ((word & 0xffffffff) == 0) { + num += 32; + word >>= 32; + } +#endif + if ((word & 0xffff) == 0) { + num += 16; + word >>= 16; + } + if ((word & 0xff) == 0) { + num += 8; + word >>= 8; + } + if ((word & 0xf) == 0) { + num += 4; + word >>= 4; + } + if ((word & 0x3) == 0) { + num += 2; + word >>= 2; + } + if ((word & 0x1) == 0) + num += 1; + return num; +} + +typedef const unsigned long __attribute__((__may_alias__)) long_alias_t; + +/* + * Find the first set bit in a memory region. + */ +static inline unsigned long +find_first_bit(const unsigned long *addr, unsigned long size) +{ + long_alias_t *p = (long_alias_t *) addr; + unsigned long result = 0; + unsigned long tmp; + + while (size & ~(BITS_PER_LONG-1)) { + if ((tmp = *(p++))) + goto found; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + + tmp = (*p) & (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found: + return result + __ffs(tmp); +} + +/* + * Find the next set bit in a memory region. + */ +static inline unsigned long +find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) +{ + const unsigned long *p = addr + BITOP_WORD(offset); + unsigned long result = offset & ~(BITS_PER_LONG-1); + unsigned long tmp; + + if (offset >= size) + return size; + size -= result; + offset %= BITS_PER_LONG; + if (offset) { + tmp = *(p++); + tmp &= (~0UL << offset); + if (size < BITS_PER_LONG) + goto found_first; + if (tmp) + goto found_middle; + size -= BITS_PER_LONG; + result += BITS_PER_LONG; + } + while (size & ~(BITS_PER_LONG-1)) { + if ((tmp = *(p++))) + goto found_middle; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = *p; + +found_first: + tmp &= (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found_middle: + return result + __ffs(tmp); +} + #endif diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h deleted file mode 100644 index 791f9dd27eb..00000000000 --- a/tools/perf/util/include/linux/compiler.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _PERF_LINUX_COMPILER_H_ -#define _PERF_LINUX_COMPILER_H_ - -#ifndef __always_inline -#define __always_inline inline -#endif -#define __user -#define __attribute_const__ - -#define __used __attribute__((__unused__)) - -#endif diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h new file mode 100644 index 00000000000..c10a35e1afb --- /dev/null +++ b/tools/perf/util/include/linux/const.h @@ -0,0 +1 @@ +#include "../../../../include/uapi/linux/const.h" diff --git a/tools/perf/util/include/linux/hash.h b/tools/perf/util/include/linux/hash.h deleted file mode 100644 index 201f5739799..00000000000 --- a/tools/perf/util/include/linux/hash.h +++ /dev/null @@ -1,5 +0,0 @@ -#include "../../../../include/linux/hash.h" - -#ifndef PERF_HASH_H -#define PERF_HASH_H -#endif diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index 1eb804fd3fb..9844c31b7c2 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -8,8 +8,8 @@ #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) -#define ALIGN(x,a) __ALIGN_MASK(x,(typeof(x))(a)-1) -#define __ALIGN_MASK(x,mask) (((x)+(mask))&~(mask)) +#define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1) +#define __PERF_ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) #ifndef offsetof #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) @@ -46,9 +46,22 @@ _min1 < _min2 ? _min1 : _min2; }) #endif +#ifndef roundup +#define roundup(x, y) ( \ +{ \ + const typeof(y) __y = y; \ + (((x) + (__y - 1)) / __y) * __y; \ +} \ +) +#endif + #ifndef BUG_ON +#ifdef NDEBUG +#define BUG_ON(cond) do { if (cond) {} } while (0) +#else #define BUG_ON(cond) assert(!(cond)) #endif +#endif /* * Both need more care to handle endianness @@ -81,12 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...) return (i >= ssize) ? (ssize - 1) : i; } -static inline unsigned long -simple_strtoul(const char *nptr, char **endptr, int base) -{ - return strtoul(nptr, endptr, base); -} - int eprintf(int level, const char *fmt, ...) __attribute__((format(printf, 2, 3))); @@ -108,4 +115,14 @@ int eprintf(int level, #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) +/* + * This looks more complex than it should be. But we need to + * get the type for the ~ right in round_down (it needs to be + * as wide as the result!), and we want to evaluate the macro + * arguments just once each. + */ +#define __round_mask(x, y) ((__typeof__(x))((y)-1)) +#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +#define round_down(x, y) ((x) & ~__round_mask(x, y)) + #endif diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h new file mode 100644 index 00000000000..06387cffe12 --- /dev/null +++ b/tools/perf/util/include/linux/linkage.h @@ -0,0 +1,13 @@ + +#ifndef PERF_LINUX_LINKAGE_H_ +#define PERF_LINUX_LINKAGE_H_ + +/* linkage.h ... for including arch/x86/lib/memcpy_64.S */ + +#define ENTRY(name) \ + .globl name; \ + name: + +#define ENDPROC(name) + +#endif /* PERF_LINUX_LINKAGE_H_ */ diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h index f5ca26e53fb..76ddbc72634 100644 --- a/tools/perf/util/include/linux/list.h +++ b/tools/perf/util/include/linux/list.h @@ -1,3 +1,6 @@ +#include <linux/kernel.h> +#include <linux/types.h> + #include "../../../../include/linux/list.h" #ifndef PERF_LIST_H @@ -22,5 +25,5 @@ static inline void list_del_range(struct list_head *begin, * @head: the head for your list. */ #define list_for_each_from(pos, head) \ - for (; prefetch(pos->next), pos != (head); pos = pos->next) + for (; pos != (head); pos = pos->next) #endif diff --git a/tools/perf/util/include/linux/module.h b/tools/perf/util/include/linux/module.h deleted file mode 100644 index b43e2dc21e0..00000000000 --- a/tools/perf/util/include/linux/module.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef PERF_LINUX_MODULE_H -#define PERF_LINUX_MODULE_H - -#define EXPORT_SYMBOL(name) - -#endif diff --git a/tools/perf/util/include/linux/prefetch.h b/tools/perf/util/include/linux/prefetch.h deleted file mode 100644 index 7841e485d8c..00000000000 --- a/tools/perf/util/include/linux/prefetch.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef PERF_LINUX_PREFETCH_H -#define PERF_LINUX_PREFETCH_H - -static inline void prefetch(void *a __attribute__((unused))) { } - -#endif diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h index 7a243a14303..2a030c5af3a 100644 --- a/tools/perf/util/include/linux/rbtree.h +++ b/tools/perf/util/include/linux/rbtree.h @@ -1 +1,2 @@ +#include <stdbool.h> #include "../../../../include/linux/rbtree.h" diff --git a/tools/perf/util/include/linux/rbtree_augmented.h b/tools/perf/util/include/linux/rbtree_augmented.h new file mode 100644 index 00000000000..9d6fcdf1788 --- /dev/null +++ b/tools/perf/util/include/linux/rbtree_augmented.h @@ -0,0 +1,2 @@ +#include <stdbool.h> +#include "../../../../include/linux/rbtree_augmented.h" diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h index 3b2f5900276..97a80073822 100644 --- a/tools/perf/util/include/linux/string.h +++ b/tools/perf/util/include/linux/string.h @@ -1 +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/include/linux/types.h b/tools/perf/util/include/linux/types.h deleted file mode 100644 index 12de3b8112f..00000000000 --- a/tools/perf/util/include/linux/types.h +++ /dev/null @@ -1,21 +0,0 @@ -#ifndef _PERF_LINUX_TYPES_H_ -#define _PERF_LINUX_TYPES_H_ - -#include <asm/types.h> - -#define DECLARE_BITMAP(name,bits) \ - unsigned long name[BITS_TO_LONGS(bits)] - -struct list_head { - struct list_head *next, *prev; -}; - -struct hlist_head { - struct hlist_node *first; -}; - -struct hlist_node { - struct hlist_node *next, **pprev; -}; - -#endif diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c new file mode 100644 index 00000000000..89715b64a31 --- /dev/null +++ b/tools/perf/util/intlist.c @@ -0,0 +1,146 @@ +/* + * Based on intlist.c by: + * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Licensed under the GPLv2. + */ + +#include <errno.h> +#include <stdlib.h> +#include <linux/compiler.h> + +#include "intlist.h" + +static struct rb_node *intlist__node_new(struct rblist *rblist __maybe_unused, + const void *entry) +{ + int i = (int)((long)entry); + struct rb_node *rc = NULL; + struct int_node *node = malloc(sizeof(*node)); + + if (node != NULL) { + node->i = i; + node->priv = NULL; + rc = &node->rb_node; + } + + return rc; +} + +static void int_node__delete(struct int_node *ilist) +{ + free(ilist); +} + +static void intlist__node_delete(struct rblist *rblist __maybe_unused, + struct rb_node *rb_node) +{ + struct int_node *node = container_of(rb_node, struct int_node, rb_node); + + int_node__delete(node); +} + +static int intlist__node_cmp(struct rb_node *rb_node, const void *entry) +{ + int i = (int)((long)entry); + struct int_node *node = container_of(rb_node, struct int_node, rb_node); + + return node->i - i; +} + +int intlist__add(struct intlist *ilist, int i) +{ + return rblist__add_node(&ilist->rblist, (void *)((long)i)); +} + +void intlist__remove(struct intlist *ilist, struct int_node *node) +{ + rblist__remove_node(&ilist->rblist, &node->rb_node); +} + +static struct int_node *__intlist__findnew(struct intlist *ilist, + int i, bool create) +{ + struct int_node *node = NULL; + struct rb_node *rb_node; + + if (ilist == NULL) + return NULL; + + 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; + int err; + + do { + long value = strtol(s, &sep, 10); + err = -EINVAL; + if (*sep != ',' && *sep != '\0') + break; + err = intlist__add(ilist, value); + if (err) + break; + s = sep + 1; + } while (*sep != '\0'); + + return err; +} + +struct intlist *intlist__new(const char *slist) +{ + struct intlist *ilist = malloc(sizeof(*ilist)); + + if (ilist != NULL) { + rblist__init(&ilist->rblist); + ilist->rblist.node_cmp = intlist__node_cmp; + ilist->rblist.node_new = intlist__node_new; + ilist->rblist.node_delete = intlist__node_delete; + + if (slist && intlist__parse_list(ilist, slist)) + goto out_delete; + } + + return ilist; +out_delete: + intlist__delete(ilist); + return NULL; +} + +void intlist__delete(struct intlist *ilist) +{ + if (ilist != NULL) + rblist__delete(&ilist->rblist); +} + +struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx) +{ + struct int_node *node = NULL; + struct rb_node *rb_node; + + rb_node = rblist__entry(&ilist->rblist, idx); + if (rb_node) + node = container_of(rb_node, struct int_node, rb_node); + + return node; +} diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h new file mode 100644 index 00000000000..aa6877d3685 --- /dev/null +++ b/tools/perf/util/intlist.h @@ -0,0 +1,77 @@ +#ifndef __PERF_INTLIST_H +#define __PERF_INTLIST_H + +#include <linux/rbtree.h> +#include <stdbool.h> + +#include "rblist.h" + +struct int_node { + struct rb_node rb_node; + int i; + void *priv; +}; + +struct intlist { + struct rblist rblist; +}; + +struct intlist *intlist__new(const char *slist); +void intlist__delete(struct intlist *ilist); + +void intlist__remove(struct intlist *ilist, struct int_node *in); +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) +{ + return intlist__find(ilist, i) != NULL; +} + +static inline bool intlist__empty(const struct intlist *ilist) +{ + return rblist__empty(&ilist->rblist); +} + +static inline unsigned int intlist__nr_entries(const struct intlist *ilist) +{ + return rblist__nr_entries(&ilist->rblist); +} + +/* For intlist iteration */ +static inline struct int_node *intlist__first(struct intlist *ilist) +{ + struct rb_node *rn = rb_first(&ilist->rblist.entries); + return rn ? rb_entry(rn, struct int_node, rb_node) : NULL; +} +static inline struct int_node *intlist__next(struct int_node *in) +{ + struct rb_node *rn; + if (!in) + return NULL; + rn = rb_next(&in->rb_node); + return rn ? rb_entry(rn, struct int_node, rb_node) : NULL; +} + +/** + * intlist_for_each - iterate over a intlist + * @pos: the &struct int_node to use as a loop cursor. + * @ilist: the &struct intlist for loop. + */ +#define intlist__for_each(pos, ilist) \ + for (pos = intlist__first(ilist); pos; pos = intlist__next(pos)) + +/** + * intlist_for_each_safe - iterate over a intlist safe against removal of + * int_node + * @pos: the &struct int_node to use as a loop cursor. + * @n: another &struct int_node to use as temporary storage. + * @ilist: the &struct intlist for loop. + */ +#define intlist__for_each_safe(pos, n, ilist) \ + for (pos = intlist__first(ilist), n = intlist__next(pos); pos;\ + pos = n, n = intlist__next(n)) +#endif /* __PERF_INTLIST_H */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c new file mode 100644 index 00000000000..c73e1fc12e5 --- /dev/null +++ b/tools/perf/util/machine.c @@ -0,0 +1,1422 @@ +#include "callchain.h" +#include "debug.h" +#include "event.h" +#include "evsel.h" +#include "hist.h" +#include "machine.h" +#include "map.h" +#include "sort.h" +#include "strlist.h" +#include "thread.h" +#include <stdbool.h> +#include <symbol/kallsyms.h> +#include "unwind.h" + +int machine__init(struct machine *machine, const char *root_dir, pid_t pid) +{ + map_groups__init(&machine->kmaps); + RB_CLEAR_NODE(&machine->rb_node); + INIT_LIST_HEAD(&machine->user_dsos); + INIT_LIST_HEAD(&machine->kernel_dsos); + + machine->threads = RB_ROOT; + INIT_LIST_HEAD(&machine->dead_threads); + machine->last_match = NULL; + + machine->kmaps.machine = machine; + machine->pid = pid; + + machine->symbol_filter = NULL; + machine->id_hdr_size = 0; + + 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, 0, + pid); + char comm[64]; + + if (thread == NULL) + return -ENOMEM; + + snprintf(comm, sizeof(comm), "[guest/%d]", pid); + 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; + + list_for_each_entry_safe(pos, n, dsos, node) { + list_del(&pos->node); + dso__delete(pos); + } +} + +void machine__delete_dead_threads(struct machine *machine) +{ + struct thread *n, *t; + + list_for_each_entry_safe(t, n, &machine->dead_threads, node) { + list_del(&t->node); + thread__delete(t); + } +} + +void machine__delete_threads(struct machine *machine) +{ + struct rb_node *nd = rb_first(&machine->threads); + + while (nd) { + struct thread *t = rb_entry(nd, struct thread, rb_node); + + rb_erase(&t->rb_node, &machine->threads); + nd = rb_next(nd); + thread__delete(t); + } +} + +void machine__exit(struct machine *machine) +{ + map_groups__exit(&machine->kmaps); + dsos__delete(&machine->user_dsos); + dsos__delete(&machine->kernel_dsos); + zfree(&machine->root_dir); +} + +void machine__delete(struct machine *machine) +{ + machine__exit(machine); + free(machine); +} + +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) +{ + machine__exit(&machines->host); + /* XXX exit guest */ +} + +struct machine *machines__add(struct machines *machines, pid_t pid, + const char *root_dir) +{ + struct rb_node **p = &machines->guests.rb_node; + struct rb_node *parent = NULL; + struct machine *pos, *machine = malloc(sizeof(*machine)); + + if (machine == NULL) + return NULL; + + if (machine__init(machine, root_dir, pid) != 0) { + free(machine); + return NULL; + } + + machine->symbol_filter = machines->symbol_filter; + + while (*p != NULL) { + parent = *p; + pos = rb_entry(parent, struct machine, rb_node); + if (pid < pos->pid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&machine->rb_node, parent, p); + rb_insert_color(&machine->rb_node, &machines->guests); + + 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; + struct rb_node *parent = NULL; + struct machine *machine; + struct machine *default_machine = NULL; + + if (pid == HOST_KERNEL_ID) + return &machines->host; + + while (*p != NULL) { + parent = *p; + machine = rb_entry(parent, struct machine, rb_node); + if (pid < machine->pid) + p = &(*p)->rb_left; + else if (pid > machine->pid) + p = &(*p)->rb_right; + else + return machine; + if (!machine->pid) + default_machine = machine; + } + + return default_machine; +} + +struct machine *machines__findnew(struct machines *machines, pid_t pid) +{ + char path[PATH_MAX]; + const char *root_dir = ""; + struct machine *machine = machines__find(machines, pid); + + if (machine && (machine->pid == pid)) + goto out; + + if ((pid != HOST_KERNEL_ID) && + (pid != DEFAULT_GUEST_KERNEL_ID) && + (symbol_conf.guestmount)) { + sprintf(path, "%s/%d", symbol_conf.guestmount, pid); + if (access(path, R_OK)) { + static struct strlist *seen; + + if (!seen) + seen = strlist__new(true, NULL); + + if (!strlist__has_entry(seen, path)) { + pr_err("Can't access file %s\n", path); + strlist__add(seen, path); + } + machine = NULL; + goto out; + } + root_dir = path; + } + + machine = machines__add(machines, pid, root_dir); +out: + return machine; +} + +void machines__process_guests(struct machines *machines, + machine__process_t process, void *data) +{ + struct rb_node *nd; + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + process(pos, data); + } +} + +char *machine__mmap_name(struct machine *machine, char *bf, size_t size) +{ + if (machine__is_host(machine)) + snprintf(bf, size, "[%s]", "kernel.kallsyms"); + else if (machine__is_default_guest(machine)) + snprintf(bf, size, "[%s]", "guest.kernel.kallsyms"); + else { + snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms", + machine->pid); + } + + return bf; +} + +void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size) +{ + struct rb_node *node; + struct machine *machine; + + machines->host.id_hdr_size = id_hdr_size; + + for (node = rb_first(&machines->guests); node; node = rb_next(node)) { + machine = rb_entry(node, struct machine, rb_node); + machine->id_hdr_size = id_hdr_size; + } + + return; +} + +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; + struct rb_node *parent = NULL; + struct thread *th; + + /* + * 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->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->tid == tid) { + machine->last_match = th; + if (pid && pid != th->pid_) + th->pid_ = pid; + return th; + } + + if (tid < th->tid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + if (!create) + return NULL; + + th = thread__new(pid, tid); + if (th != NULL) { + rb_link_node(&th->rb_node, parent, p); + rb_insert_color(&th->rb_node, &machine->threads); + machine->last_match = th; + + /* + * We have to initialize map_groups separately + * after rb tree is updated. + * + * The reason is that we call machine__findnew_thread + * within thread__init_map_groups to find the thread + * leader and that would screwed the rb tree. + */ + if (thread__init_map_groups(th, machine)) + return NULL; + } + + return th; +} + +struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, + pid_t tid) +{ + return __machine__findnew_thread(machine, pid, tid, true); +} + +struct thread *machine__find_thread(struct machine *machine, pid_t pid, + pid_t tid) +{ + return __machine__findnew_thread(machine, pid, tid, false); +} + +int machine__process_comm_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample) +{ + struct thread *thread = machine__findnew_thread(machine, + event->comm.pid, + event->comm.tid); + + if (dump_trace) + perf_event__fprintf_comm(event, stdout); + + if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) { + dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); + return -1; + } + + return 0; +} + +int machine__process_lost_event(struct machine *machine __maybe_unused, + union perf_event *event, struct perf_sample *sample __maybe_unused) +{ + dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", + event->lost.id, event->lost.lost); + return 0; +} + +struct map *machine__new_module(struct machine *machine, u64 start, + const char *filename) +{ + struct map *map; + struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename); + + if (dso == NULL) + return NULL; + + map = map__new2(start, dso, MAP__FUNCTION); + if (map == NULL) + return NULL; + + if (machine__is_host(machine)) + dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; + else + dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; + map_groups__insert(&machine->kmaps, map); + return map; +} + +size_t machines__fprintf_dsos(struct machines *machines, FILE *fp) +{ + struct rb_node *nd; + size_t ret = __dsos__fprintf(&machines->host.kernel_dsos, fp) + + __dsos__fprintf(&machines->host.user_dsos, fp); + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + ret += __dsos__fprintf(&pos->kernel_dsos, fp); + ret += __dsos__fprintf(&pos->user_dsos, fp); + } + + return ret; +} + +size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm) +{ + return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) + + __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm); +} + +size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm) +{ + struct rb_node *nd; + size_t ret = machine__fprintf_dsos_buildid(&machines->host, fp, skip, parm); + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + ret += machine__fprintf_dsos_buildid(pos, fp, skip, parm); + } + return ret; +} + +size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) +{ + int i; + size_t printed = 0; + struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso; + + if (kdso->has_build_id) { + char filename[PATH_MAX]; + if (dso__build_id_filename(kdso, filename, sizeof(filename))) + printed += fprintf(fp, "[0] %s\n", filename); + } + + for (i = 0; i < vmlinux_path__nr_entries; ++i) + printed += fprintf(fp, "[%d] %s\n", + i + kdso->has_build_id, vmlinux_path[i]); + + return printed; +} + +size_t machine__fprintf(struct machine *machine, FILE *fp) +{ + size_t ret = 0; + struct rb_node *nd; + + for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { + struct thread *pos = rb_entry(nd, struct thread, rb_node); + + ret += thread__fprintf(pos, fp); + } + + return ret; +} + +static struct dso *machine__get_kernel(struct machine *machine) +{ + const char *vmlinux_name = NULL; + struct dso *kernel; + + if (machine__is_host(machine)) { + vmlinux_name = symbol_conf.vmlinux_name; + if (!vmlinux_name) + vmlinux_name = "[kernel.kallsyms]"; + + kernel = dso__kernel_findnew(machine, vmlinux_name, + "[kernel]", + DSO_TYPE_KERNEL); + } else { + char bf[PATH_MAX]; + + if (machine__is_default_guest(machine)) + vmlinux_name = symbol_conf.default_guest_vmlinux_name; + if (!vmlinux_name) + vmlinux_name = machine__mmap_name(machine, bf, + sizeof(bf)); + + kernel = dso__kernel_findnew(machine, vmlinux_name, + "[guest.kernel]", + DSO_TYPE_GUEST_KERNEL); + } + + if (kernel != NULL && (!kernel->has_build_id)) + dso__read_running_kernel_build_id(kernel, machine); + + return kernel; +} + +struct process_args { + u64 start; +}; + +static void machine__get_kallsyms_filename(struct machine *machine, char *buf, + size_t bufsz) +{ + if (machine__is_default_guest(machine)) + scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms); + else + scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir); +} + +const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; + +/* Figure out the start address of kernel map from /proc/kallsyms. + * Returns the name of the start symbol in *symbol_name. Pass in NULL as + * symbol_name if it's not that important. + */ +static u64 machine__get_kernel_start_addr(struct machine *machine, + const char **symbol_name) +{ + char filename[PATH_MAX]; + int i; + const char *name; + u64 addr = 0; + + machine__get_kallsyms_filename(machine, filename, PATH_MAX); + + if (symbol__restricted_filename(filename, "/proc/kallsyms")) + return 0; + + for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { + addr = kallsyms__get_function_start(filename, name); + if (addr) + break; + } + + if (symbol_name) + *symbol_name = name; + + return addr; +} + +int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) +{ + enum map_type type; + u64 start = machine__get_kernel_start_addr(machine, NULL); + + for (type = 0; type < MAP__NR_TYPES; ++type) { + struct kmap *kmap; + + machine->vmlinux_maps[type] = map__new2(start, kernel, type); + if (machine->vmlinux_maps[type] == NULL) + return -1; + + machine->vmlinux_maps[type]->map_ip = + machine->vmlinux_maps[type]->unmap_ip = + identity__map_ip; + kmap = map__kmap(machine->vmlinux_maps[type]); + kmap->kmaps = &machine->kmaps; + map_groups__insert(&machine->kmaps, + machine->vmlinux_maps[type]); + } + + return 0; +} + +void machine__destroy_kernel_maps(struct machine *machine) +{ + enum map_type type; + + for (type = 0; type < MAP__NR_TYPES; ++type) { + struct kmap *kmap; + + if (machine->vmlinux_maps[type] == NULL) + continue; + + kmap = map__kmap(machine->vmlinux_maps[type]); + map_groups__remove(&machine->kmaps, + machine->vmlinux_maps[type]); + if (kmap->ref_reloc_sym) { + /* + * ref_reloc_sym is shared among all maps, so free just + * on one of them. + */ + if (type == MAP__FUNCTION) { + zfree((char **)&kmap->ref_reloc_sym->name); + zfree(&kmap->ref_reloc_sym); + } else + kmap->ref_reloc_sym = NULL; + } + + map__delete(machine->vmlinux_maps[type]); + machine->vmlinux_maps[type] = NULL; + } +} + +int machines__create_guest_kernel_maps(struct machines *machines) +{ + int ret = 0; + struct dirent **namelist = NULL; + int i, items = 0; + char path[PATH_MAX]; + pid_t pid; + char *endp; + + if (symbol_conf.default_guest_vmlinux_name || + symbol_conf.default_guest_modules || + symbol_conf.default_guest_kallsyms) { + machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID); + } + + if (symbol_conf.guestmount) { + items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL); + if (items <= 0) + return -ENOENT; + for (i = 0; i < items; i++) { + if (!isdigit(namelist[i]->d_name[0])) { + /* Filter out . and .. */ + continue; + } + pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10); + if ((*endp != '\0') || + (endp == namelist[i]->d_name) || + (errno == ERANGE)) { + pr_debug("invalid directory (%s). Skipping.\n", + namelist[i]->d_name); + continue; + } + sprintf(path, "%s/%s/proc/kallsyms", + symbol_conf.guestmount, + namelist[i]->d_name); + ret = access(path, R_OK); + if (ret) { + pr_debug("Can't access file %s\n", path); + goto failure; + } + machines__create_kernel_maps(machines, pid); + } +failure: + free(namelist); + } + + return ret; +} + +void machines__destroy_kernel_maps(struct machines *machines) +{ + struct rb_node *next = rb_first(&machines->guests); + + machine__destroy_kernel_maps(&machines->host); + + while (next) { + struct machine *pos = rb_entry(next, struct machine, rb_node); + + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, &machines->guests); + machine__delete(pos); + } +} + +int machines__create_kernel_maps(struct machines *machines, pid_t pid) +{ + struct machine *machine = machines__findnew(machines, pid); + + if (machine == NULL) + return -1; + + return machine__create_kernel_maps(machine); +} + +int machine__load_kallsyms(struct machine *machine, const char *filename, + enum map_type type, symbol_filter_t filter) +{ + struct map *map = machine->vmlinux_maps[type]; + int ret = dso__load_kallsyms(map->dso, filename, map, filter); + + if (ret > 0) { + dso__set_loaded(map->dso, type); + /* + * Since /proc/kallsyms will have multiple sessions for the + * kernel, with modules between them, fixup the end of all + * sections. + */ + __map_groups__fixup_end(&machine->kmaps, type); + } + + return ret; +} + +int machine__load_vmlinux_path(struct machine *machine, enum map_type type, + symbol_filter_t filter) +{ + struct map *map = machine->vmlinux_maps[type]; + int ret = dso__load_vmlinux_path(map->dso, map, filter); + + if (ret > 0) + dso__set_loaded(map->dso, type); + + return ret; +} + +static void map_groups__fixup_end(struct map_groups *mg) +{ + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) + __map_groups__fixup_end(mg, i); +} + +static char *get_kernel_version(const char *root_dir) +{ + char version[PATH_MAX]; + FILE *file; + char *name, *tmp; + const char *prefix = "Linux version "; + + sprintf(version, "%s/proc/version", root_dir); + file = fopen(version, "r"); + if (!file) + return NULL; + + version[0] = '\0'; + tmp = fgets(version, sizeof(version), file); + fclose(file); + + name = strstr(version, prefix); + if (!name) + return NULL; + name += strlen(prefix); + tmp = strchr(name, ' '); + if (tmp) + *tmp = '\0'; + + return strdup(name); +} + +static int map_groups__set_modules_path_dir(struct map_groups *mg, + const char *dir_name, int depth) +{ + struct dirent *dent; + DIR *dir = opendir(dir_name); + int ret = 0; + + if (!dir) { + pr_debug("%s: cannot open %s dir\n", __func__, dir_name); + return -1; + } + + while ((dent = readdir(dir)) != NULL) { + char path[PATH_MAX]; + struct stat st; + + /*sshfs might return bad dent->d_type, so we have to stat*/ + snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name); + if (stat(path, &st)) + continue; + + if (S_ISDIR(st.st_mode)) { + if (!strcmp(dent->d_name, ".") || + !strcmp(dent->d_name, "..")) + continue; + + /* Do not follow top-level source and build symlinks */ + if (depth == 0) { + if (!strcmp(dent->d_name, "source") || + !strcmp(dent->d_name, "build")) + continue; + } + + ret = map_groups__set_modules_path_dir(mg, path, + depth + 1); + if (ret < 0) + goto out; + } else { + char *dot = strrchr(dent->d_name, '.'), + dso_name[PATH_MAX]; + struct map *map; + char *long_name; + + if (dot == NULL || strcmp(dot, ".ko")) + continue; + snprintf(dso_name, sizeof(dso_name), "[%.*s]", + (int)(dot - dent->d_name), dent->d_name); + + strxfrchar(dso_name, '-', '_'); + map = map_groups__find_by_name(mg, MAP__FUNCTION, + dso_name); + if (map == NULL) + continue; + + long_name = strdup(path); + if (long_name == NULL) { + ret = -1; + goto out; + } + dso__set_long_name(map->dso, long_name, true); + dso__kernel_module_get_build_id(map->dso, ""); + } + } + +out: + closedir(dir); + return ret; +} + +static int machine__set_modules_path(struct machine *machine) +{ + char *version; + char modules_path[PATH_MAX]; + + version = get_kernel_version(machine->root_dir); + if (!version) + return -1; + + snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s", + machine->root_dir, version); + free(version); + + return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0); +} + +static int machine__create_module(void *arg, const char *name, u64 start) +{ + 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)) { + modules = symbol_conf.default_guest_modules; + } else { + snprintf(path, PATH_MAX, "%s/proc/modules", machine->root_dir); + modules = path; + } + + if (symbol__restricted_filename(modules, "/proc/modules")) + return -1; + + if (modules__parse(modules, machine, machine__create_module)) + return -1; + + if (!machine__set_modules_path(machine)) + return 0; + + pr_debug("Problems setting modules path maps, continuing anyway...\n"); + + return 0; +} + +int machine__create_kernel_maps(struct machine *machine) +{ + struct dso *kernel = machine__get_kernel(machine); + const char *name; + u64 addr = machine__get_kernel_start_addr(machine, &name); + if (!addr) + return -1; + + if (kernel == NULL || + __machine__create_kernel_maps(machine, kernel) < 0) + return -1; + + if (symbol_conf.use_modules && machine__create_modules(machine) < 0) { + if (machine__is_host(machine)) + pr_debug("Problems creating module maps, " + "continuing anyway...\n"); + else + pr_debug("Problems creating module maps for guest %d, " + "continuing anyway...\n", machine->pid); + } + + /* + * Now that we have all the maps created, just set the ->end of them: + */ + map_groups__fixup_end(&machine->kmaps); + + if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, + addr)) { + machine__destroy_kernel_maps(machine); + return -1; + } + + return 0; +} + +static void machine__set_kernel_mmap_len(struct machine *machine, + union perf_event *event) +{ + int i; + + for (i = 0; i < MAP__NR_TYPES; i++) { + machine->vmlinux_maps[i]->start = event->mmap.start; + machine->vmlinux_maps[i]->end = (event->mmap.start + + event->mmap.len); + /* + * Be a bit paranoid here, some perf.data file came with + * a zero sized synthesized MMAP event for the kernel. + */ + if (machine->vmlinux_maps[i]->end == 0) + machine->vmlinux_maps[i]->end = ~0ULL; + } +} + +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) +{ + struct map *map; + char kmmap_prefix[PATH_MAX]; + 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; + else + kernel_type = DSO_TYPE_GUEST_KERNEL; + + is_kernel_mmap = memcmp(event->mmap.filename, + kmmap_prefix, + strlen(kmmap_prefix) - 1) == 0; + if (event->mmap.filename[0] == '/' || + (!is_kernel_mmap && event->mmap.filename[0] == '[')) { + + char short_module_name[1024]; + char *name, *dot; + + if (event->mmap.filename[0] == '/') { + name = strrchr(event->mmap.filename, '/'); + if (name == NULL) + goto out_problem; + + ++name; /* skip / */ + dot = strrchr(name, '.'); + if (dot == NULL) + goto out_problem; + snprintf(short_module_name, sizeof(short_module_name), + "[%.*s]", (int)(dot - name), name); + strxfrchar(short_module_name, '-', '_'); + } else + strcpy(short_module_name, event->mmap.filename); + + map = machine__new_module(machine, event->mmap.start, + event->mmap.filename); + if (map == NULL) + goto out_problem; + + name = strdup(short_module_name); + if (name == NULL) + goto out_problem; + + dso__set_short_name(map->dso, name, true); + map->end = map->start + event->mmap.len; + } else if (is_kernel_mmap) { + const char *symbol_name = (event->mmap.filename + + strlen(kmmap_prefix)); + /* + * Should be there already, from the build-id table in + * the header. + */ + struct dso *kernel = __dsos__findnew(&machine->kernel_dsos, + kmmap_prefix); + if (kernel == NULL) + goto out_problem; + + kernel->kernel = kernel_type; + if (__machine__create_kernel_maps(machine, kernel) < 0) + goto out_problem; + + machine__set_kernel_mmap_len(machine, event); + + /* + * Avoid using a zero address (kptr_restrict) for the ref reloc + * symbol. Effectively having zero here means that at record + * time /proc/sys/kernel/kptr_restrict was non zero. + */ + if (event->mmap.pgoff != 0) { + maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, + symbol_name, + event->mmap.pgoff); + } + + if (machine__is_default_guest(machine)) { + /* + * preload dso of guest kernel and modules + */ + dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION], + NULL); + } + } + return 0; +out_problem: + return -1; +} + +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; + struct map *map; + enum map_type type; + int ret = 0; + + if (dump_trace) + perf_event__fprintf_mmap2(event, stdout); + + 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->mmap2.pid, + event->mmap2.tid); + 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->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.prot, + event->mmap2.flags, + event->mmap2.filename, type); + + if (map == NULL) + goto out_problem; + + thread__insert_map(thread, map); + return 0; + +out_problem: + dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n"); + return 0; +} + +int machine__process_mmap_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; + struct map *map; + enum map_type type; + int ret = 0; + + if (dump_trace) + perf_event__fprintf_mmap(event, stdout); + + 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.tid); + 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, 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; +} + +static void machine__remove_thread(struct machine *machine, struct thread *th) +{ + machine->last_match = NULL; + rb_erase(&th->rb_node, &machine->threads); + /* + * We may have references to this thread, for instance in some hist_entry + * instances, so just move them to a separate list. + */ + list_add_tail(&th->node, &machine->dead_threads); +} + +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.pid, + 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.pid, + event->fork.tid); + + if (dump_trace) + perf_event__fprintf_task(event, stdout); + + if (thread != NULL) + thread__exited(thread); + + return 0; +} + +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, sample); break; + case PERF_RECORD_MMAP: + 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, sample); break; + case PERF_RECORD_EXIT: + ret = machine__process_exit_event(machine, event, sample); break; + case PERF_RECORD_LOST: + ret = machine__process_lost_event(machine, event, sample); break; + default: + ret = -1; + break; + } + + return ret; +} + +static bool symbol__match_regex(struct symbol *sym, regex_t *regex) +{ + if (sym->name && !regexec(regex, sym->name, 0, NULL, 0)) + return 1; + return 0; +} + +static void ip__resolve_ams(struct machine *machine, struct thread *thread, + struct addr_map_symbol *ams, + u64 ip) +{ + struct addr_location al; + + memset(&al, 0, sizeof(al)); + /* + * We cannot use the header.misc hint to determine whether a + * branch stack address is user, kernel, guest, hypervisor. + * Branches may straddle the kernel/user/hypervisor boundaries. + * Thus, we have to try consecutively until we find a match + * or else, the symbol is unknown + */ + thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al); + + ams->addr = ip; + ams->al_addr = al.addr; + ams->sym = al.sym; + ams->map = al.map; +} + +static void ip__resolve_data(struct machine *machine, struct thread *thread, + u8 m, struct addr_map_symbol *ams, u64 addr) +{ + struct addr_location al; + + memset(&al, 0, sizeof(al)); + + thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, + &al); + ams->addr = addr; + ams->al_addr = al.addr; + ams->sym = al.sym; + ams->map = al.map; +} + +struct mem_info *sample__resolve_mem(struct perf_sample *sample, + struct addr_location *al) +{ + struct mem_info *mi = zalloc(sizeof(*mi)); + + if (!mi) + return NULL; + + ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip); + ip__resolve_data(al->machine, al->thread, al->cpumode, + &mi->daddr, sample->addr); + mi->data_src.val = sample->data_src; + + return mi; +} + +struct branch_info *sample__resolve_bstack(struct perf_sample *sample, + struct addr_location *al) +{ + unsigned int i; + const struct branch_stack *bs = sample->branch_stack; + struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info)); + + if (!bi) + return NULL; + + for (i = 0; i < bs->nr; i++) { + ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to); + ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from); + bi[i].flags = bs->entries[i].flags; + } + return bi; +} + +static int machine__resolve_callchain_sample(struct machine *machine, + struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent, + struct addr_location *root_al, + int max_stack) +{ + u8 cpumode = PERF_RECORD_MISC_USER; + int chain_nr = min(max_stack, (int)chain->nr); + int i; + int err; + + callchain_cursor_reset(&callchain_cursor); + + if (chain->nr > PERF_MAX_STACK_DEPTH) { + pr_warning("corrupted callchain. skipping...\n"); + return 0; + } + + for (i = 0; i < chain_nr; i++) { + u64 ip; + struct addr_location al; + + if (callchain_param.order == ORDER_CALLEE) + ip = chain->ips[i]; + else + ip = chain->ips[chain->nr - i - 1]; + + if (ip >= PERF_CONTEXT_MAX) { + switch (ip) { + case PERF_CONTEXT_HV: + cpumode = PERF_RECORD_MISC_HYPERVISOR; + break; + case PERF_CONTEXT_KERNEL: + cpumode = PERF_RECORD_MISC_KERNEL; + break; + case PERF_CONTEXT_USER: + cpumode = PERF_RECORD_MISC_USER; + break; + default: + pr_debug("invalid callchain context: " + "%"PRId64"\n", (s64) ip); + /* + * It seems the callchain is corrupted. + * Discard all. + */ + callchain_cursor_reset(&callchain_cursor); + return 0; + } + continue; + } + + al.filtered = 0; + thread__find_addr_location(thread, machine, cpumode, + MAP__FUNCTION, ip, &al); + if (al.sym != NULL) { + if (sort__has_parent && !*parent && + 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); + } + } + + err = callchain_cursor_append(&callchain_cursor, + ip, al.map, al.sym); + if (err) + return err; + } + + return 0; +} + +static int unwind_entry(struct unwind_entry *entry, void *arg) +{ + struct callchain_cursor *cursor = arg; + return callchain_cursor_append(cursor, entry->ip, + entry->map, entry->sym); +} + +int machine__resolve_callchain(struct machine *machine, + struct perf_evsel *evsel, + struct thread *thread, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack) +{ + int ret; + + ret = machine__resolve_callchain_sample(machine, thread, + sample->callchain, parent, + root_al, max_stack); + if (ret) + return ret; + + /* Can we do dwarf post unwind? */ + if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) && + (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER))) + return 0; + + /* Bail out if nothing was captured. */ + if ((!sample->user_regs.regs) || + (!sample->user_stack.size)) + return 0; + + return unwind__get_entries(unwind_entry, &callchain_cursor, machine, + thread, sample, max_stack); + +} + +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; +} + +int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, + struct target *target, struct thread_map *threads, + perf_event__handler_t process, bool data_mmap) +{ + if (target__has_task(target)) + return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap); + else if (target__has_cpu(target)) + return perf_event__synthesize_threads(tool, process, machine, data_mmap); + /* command specified */ + return 0; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h new file mode 100644 index 00000000000..c8c74a11939 --- /dev/null +++ b/tools/perf/util/machine.h @@ -0,0 +1,194 @@ +#ifndef __PERF_MACHINE_H +#define __PERF_MACHINE_H + +#include <sys/types.h> +#include <linux/rbtree.h> +#include "map.h" +#include "event.h" + +struct addr_location; +struct branch_stack; +struct perf_evsel; +struct perf_sample; +struct symbol; +struct thread; +union perf_event; + +/* Native host kernel uses -1 as pid index in machine */ +#define HOST_KERNEL_ID (-1) +#define DEFAULT_GUEST_KERNEL_ID (0) + +extern const char *ref_reloc_sym_names[]; + +struct machine { + struct rb_node rb_node; + pid_t pid; + u16 id_hdr_size; + char *root_dir; + struct rb_root threads; + struct list_head dead_threads; + struct thread *last_match; + struct list_head user_dsos; + struct list_head kernel_dsos; + struct map_groups kmaps; + struct map *vmlinux_maps[MAP__NR_TYPES]; + symbol_filter_t symbol_filter; +}; + +static inline +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, + 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); +void machines__exit(struct machines *machines); + +void machines__process_guests(struct machines *machines, + machine__process_t process, void *data); + +struct machine *machines__add(struct machines *machines, pid_t pid, + const char *root_dir); +struct machine *machines__find_host(struct machines *machines); +struct machine *machines__find(struct machines *machines, pid_t pid); +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); +void machine__delete_threads(struct machine *machine); +void machine__delete(struct machine *machine); + +struct branch_info *sample__resolve_bstack(struct perf_sample *sample, + struct addr_location *al); +struct mem_info *sample__resolve_mem(struct perf_sample *sample, + struct addr_location *al); +int machine__resolve_callchain(struct machine *machine, + struct perf_evsel *evsel, + struct thread *thread, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack); + +/* + * Default guest kernel is defined by parameter --guestkallsyms + * and --guestmodules + */ +static inline bool machine__is_default_guest(struct machine *machine) +{ + return machine ? machine->pid == DEFAULT_GUEST_KERNEL_ID : false; +} + +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, + pid_t tid); + +size_t machine__fprintf(struct machine *machine, FILE *fp); + +static inline +struct symbol *machine__find_kernel_symbol(struct machine *machine, + enum map_type type, u64 addr, + struct map **mapp, + symbol_filter_t filter) +{ + return map_groups__find_symbol(&machine->kmaps, type, addr, + mapp, filter); +} + +static inline +struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr, + struct map **mapp, + symbol_filter_t filter) +{ + return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr, + mapp, filter); +} + +static inline +struct symbol *machine__find_kernel_function_by_name(struct machine *machine, + const char *name, + struct map **mapp, + symbol_filter_t filter) +{ + return map_groups__find_function_by_name(&machine->kmaps, name, mapp, + filter); +} + +struct map *machine__new_module(struct machine *machine, u64 start, + const char *filename); + +int machine__load_kallsyms(struct machine *machine, const char *filename, + enum map_type type, symbol_filter_t filter); +int machine__load_vmlinux_path(struct machine *machine, enum map_type type, + symbol_filter_t filter); + +size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm); +size_t machines__fprintf_dsos(struct machines *machines, FILE *fp); +size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm); + +void machine__destroy_kernel_maps(struct machine *machine); +int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel); +int machine__create_kernel_maps(struct machine *machine); + +int machines__create_kernel_maps(struct machines *machines, pid_t pid); +int machines__create_guest_kernel_maps(struct machines *machines); +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); + +int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, + struct target *target, struct thread_map *threads, + perf_event__handler_t process, bool data_mmap); +static inline +int machine__synthesize_threads(struct machine *machine, struct target *target, + struct thread_map *threads, bool data_mmap) +{ + return __machine__synthesize_threads(machine, NULL, target, threads, + perf_event__process, data_mmap); +} + +#endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 3a7eb6ec0ee..25c571f4cba 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -1,11 +1,18 @@ #include "symbol.h" #include <errno.h> +#include <inttypes.h> #include <limits.h> #include <stdlib.h> #include <string.h> #include <stdio.h> #include <unistd.h> #include "map.h" +#include "thread.h" +#include "strlist.h" +#include "vdso.h" +#include "build-id.h" +#include "util.h" +#include <linux/string.h> const char *map_type__name[MAP__NR_TYPES] = { [MAP__FUNCTION] = "Functions", @@ -14,104 +21,245 @@ const char *map_type__name[MAP__NR_TYPES] = { static inline int is_anon_memory(const char *filename) { - return strcmp(filename, "//anon") == 0; + return !strcmp(filename, "//anon") || + !strcmp(filename, "/dev/zero (deleted)") || + !strcmp(filename, "/anon_hugepage (deleted)"); } -void map__init(struct map *self, enum map_type type, +static inline int is_no_dso_memory(const char *filename) +{ + return !strncmp(filename, "[stack", 6) || + !strcmp(filename, "[heap]"); +} + +static inline int is_android_lib(const char *filename) +{ + return !strncmp(filename, "/data/app-lib", 13) || + !strncmp(filename, "/system/lib", 11); +} + +static inline bool replace_android_lib(const char *filename, char *newfilename) +{ + const char *libname; + char *app_abi; + size_t app_abi_length, new_length; + size_t lib_length = 0; + + libname = strrchr(filename, '/'); + if (libname) + lib_length = strlen(libname); + + app_abi = getenv("APP_ABI"); + if (!app_abi) + return false; + + app_abi_length = strlen(app_abi); + + if (!strncmp(filename, "/data/app-lib", 13)) { + char *apk_path; + + if (!app_abi_length) + return false; + + new_length = 7 + app_abi_length + lib_length; + + apk_path = getenv("APK_PATH"); + if (apk_path) { + new_length += strlen(apk_path) + 1; + if (new_length > PATH_MAX) + return false; + snprintf(newfilename, new_length, + "%s/libs/%s/%s", apk_path, app_abi, libname); + } else { + if (new_length > PATH_MAX) + return false; + snprintf(newfilename, new_length, + "libs/%s/%s", app_abi, libname); + } + return true; + } + + if (!strncmp(filename, "/system/lib/", 11)) { + char *ndk, *app; + const char *arch; + size_t ndk_length; + size_t app_length; + + ndk = getenv("NDK_ROOT"); + app = getenv("APP_PLATFORM"); + + if (!(ndk && app)) + return false; + + ndk_length = strlen(ndk); + app_length = strlen(app); + + if (!(ndk_length && app_length && app_abi_length)) + return false; + + arch = !strncmp(app_abi, "arm", 3) ? "arm" : + !strncmp(app_abi, "mips", 4) ? "mips" : + !strncmp(app_abi, "x86", 3) ? "x86" : NULL; + + if (!arch) + return false; + + new_length = 27 + ndk_length + + app_length + lib_length + + strlen(arch); + + if (new_length > PATH_MAX) + return false; + snprintf(newfilename, new_length, + "%s/platforms/%s/arch-%s/usr/lib/%s", + ndk, app, arch, libname); + + return true; + } + return false; +} + +void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso) { - self->type = type; - self->start = start; - self->end = end; - self->pgoff = pgoff; - self->dso = dso; - self->map_ip = map__map_ip; - self->unmap_ip = map__unmap_ip; - RB_CLEAR_NODE(&self->rb_node); - self->groups = NULL; - self->referenced = false; + map->type = type; + map->start = start; + map->end = end; + map->pgoff = pgoff; + map->reloc = 0; + map->dso = dso; + map->map_ip = map__map_ip; + map->unmap_ip = map__unmap_ip; + RB_CLEAR_NODE(&map->rb_node); + map->groups = NULL; + map->referenced = false; + map->erange_warned = false; } 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, u32 prot, u32 flags, char *filename, enum map_type type) { - struct map *self = malloc(sizeof(*self)); + struct map *map = malloc(sizeof(*map)); - if (self != NULL) { + if (map != NULL) { char newfilename[PATH_MAX]; struct dso *dso; - int anon; + int anon, no_dso, vdso, android; + android = is_android_lib(filename); anon = is_anon_memory(filename); + vdso = is_vdso_map(filename); + no_dso = is_no_dso_memory(filename); - if (anon) { + map->maj = d_maj; + map->min = d_min; + map->ino = ino; + map->ino_generation = ino_gen; + map->prot = prot; + map->flags = flags; + + if ((anon || no_dso) && type == MAP__FUNCTION) { snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid); filename = newfilename; } - dso = __dsos__findnew(dsos__list, filename); + if (android) { + if (replace_android_lib(filename, newfilename)) + filename = newfilename; + } + + if (vdso) { + pgoff = 0; + dso = vdso__dso_findnew(dsos__list); + } else + dso = __dsos__findnew(dsos__list, filename); + if (dso == NULL) goto out_delete; - map__init(self, type, start, start + len, pgoff, dso); + map__init(map, type, start, start + len, pgoff, dso); - if (anon) { -set_identity: - self->map_ip = self->unmap_ip = identity__map_ip; - } else if (strcmp(filename, "[vdso]") == 0) { - dso__set_loaded(dso, self->type); - goto set_identity; + if (anon || no_dso) { + map->map_ip = map->unmap_ip = identity__map_ip; + + /* + * Set memory without DSO as loaded. All map__find_* + * functions still return NULL, and we avoid the + * unnecessary map__load warning. + */ + if (type != MAP__FUNCTION) + dso__set_loaded(dso, map->type); } } - return self; + return map; out_delete: - free(self); + free(map); return NULL; } -void map__delete(struct map *self) +/* + * Constructor variant for modules (where we know from /proc/modules where + * they are loaded) and for vmlinux, where only after we load all the + * symbols we'll know where it starts and ends. + */ +struct map *map__new2(u64 start, struct dso *dso, enum map_type type) +{ + struct map *map = calloc(1, (sizeof(*map) + + (dso->kernel ? sizeof(struct kmap) : 0))); + if (map != NULL) { + /* + * ->end will be filled after we load all the symbols + */ + map__init(map, type, start, 0, 0, dso); + } + + return map; +} + +void map__delete(struct map *map) { - free(self); + free(map); } -void map__fixup_start(struct map *self) +void map__fixup_start(struct map *map) { - struct rb_root *symbols = &self->dso->symbols[self->type]; + struct rb_root *symbols = &map->dso->symbols[map->type]; struct rb_node *nd = rb_first(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - self->start = sym->start; + map->start = sym->start; } } -void map__fixup_end(struct map *self) +void map__fixup_end(struct map *map) { - struct rb_root *symbols = &self->dso->symbols[self->type]; + struct rb_root *symbols = &map->dso->symbols[map->type]; struct rb_node *nd = rb_last(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - self->end = sym->end; + map->end = sym->end; } } #define DSO__DELETED "(deleted)" -int map__load(struct map *self, symbol_filter_t filter) +int map__load(struct map *map, symbol_filter_t filter) { - const char *name = self->dso->long_name; + const char *name = map->dso->long_name; int nr; - if (dso__loaded(self->dso, self->type)) + if (dso__loaded(map->dso, map->type)) return 0; - nr = dso__load(self->dso, self, filter); + nr = dso__load(map->dso, map, filter); if (nr < 0) { - if (self->dso->has_build_id) { + if (map->dso->has_build_id) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - build_id__sprintf(self->dso->build_id, - sizeof(self->dso->build_id), + build_id__sprintf(map->dso->build_id, + sizeof(map->dso->build_id), sbuild_id); pr_warning("%s with build id %s not found", name, sbuild_id); @@ -121,62 +269,50 @@ int map__load(struct map *self, symbol_filter_t filter) pr_warning(", continuing without symbols\n"); return -1; } else if (nr == 0) { +#ifdef HAVE_LIBELF_SUPPORT const size_t len = strlen(name); const size_t real_len = len - sizeof(DSO__DELETED); if (len > sizeof(DSO__DELETED) && strcmp(name + real_len + 1, DSO__DELETED) == 0) { - pr_warning("%.*s was updated, restart the long " - "running apps that use it!\n", + pr_warning("%.*s was updated (is prelink enabled?). " + "Restart the long running apps that use it!\n", (int)real_len, name); } else { pr_warning("no symbols found in %s, maybe install " "a debug package?\n", name); } - +#endif return -1; } - /* - * Only applies to the kernel, as its symtabs aren't relative like the - * module ones. - */ - if (self->dso->kernel) - map__reloc_vmlinux(self); return 0; } -struct symbol *map__find_symbol(struct map *self, u64 addr, +struct symbol *map__find_symbol(struct map *map, u64 addr, symbol_filter_t filter) { - if (map__load(self, filter) < 0) + if (map__load(map, filter) < 0) return NULL; - return dso__find_symbol(self->dso, self->type, addr); + return dso__find_symbol(map->dso, map->type, addr); } -struct symbol *map__find_symbol_by_name(struct map *self, const char *name, +struct symbol *map__find_symbol_by_name(struct map *map, const char *name, symbol_filter_t filter) { - if (map__load(self, filter) < 0) + if (map__load(map, filter) < 0) return NULL; - if (!dso__sorted_by_name(self->dso, self->type)) - dso__sort_by_name(self->dso, self->type); + if (!dso__sorted_by_name(map->dso, map->type)) + dso__sort_by_name(map->dso, map->type); - return dso__find_symbol_by_name(self->dso, self->type, name); + return dso__find_symbol_by_name(map->dso, map->type, name); } -struct map *map__clone(struct map *self) +struct map *map__clone(struct map *map) { - struct map *map = malloc(sizeof(*self)); - - if (!map) - return NULL; - - memcpy(map, self, sizeof(*self)); - - return map; + return memdup(map, sizeof(*map)); } int map__overlap(struct map *l, struct map *r) @@ -193,81 +329,159 @@ int map__overlap(struct map *l, struct map *r) return 0; } -size_t map__fprintf(struct map *self, FILE *fp) +size_t map__fprintf(struct map *map, FILE *fp) { - return fprintf(fp, " %Lx-%Lx %Lx %s\n", - self->start, self->end, self->pgoff, self->dso->name); + return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n", + map->start, map->end, map->pgoff, map->dso->name); } -/* +size_t map__fprintf_dsoname(struct map *map, FILE *fp) +{ + const char *dsoname = "[unknown]"; + + if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else if (map->dso->name) + dsoname = map->dso->name; + } + + return fprintf(fp, "%s", dsoname); +} + +int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, + FILE *fp) +{ + char *srcline; + int ret = 0; + + if (map && map->dso) { + srcline = get_srcline(map->dso, + map__rip_2objdump(map, addr)); + if (srcline != SRCLINE_UNKNOWN) + ret = fprintf(fp, "%s%s", prefix, srcline); + free_srcline(srcline); + } + return ret; +} + +/** + * 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->reloc; } -u64 map__objdump_2ip(struct map *map, u64 addr) +/** + * 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) { - u64 ip = map->dso->adjust_symbols ? - addr : - map->unmap_ip(map, addr); /* RIP -> IP */ - return 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 + map->reloc; } -void map_groups__init(struct map_groups *self) +void map_groups__init(struct map_groups *mg) { int i; for (i = 0; i < MAP__NR_TYPES; ++i) { - self->maps[i] = RB_ROOT; - INIT_LIST_HEAD(&self->removed_maps[i]); + mg->maps[i] = RB_ROOT; + INIT_LIST_HEAD(&mg->removed_maps[i]); } - self->machine = NULL; + mg->machine = NULL; + mg->refcnt = 1; } -static void maps__delete(struct rb_root *self) +static void maps__delete(struct rb_root *maps) { - struct rb_node *next = rb_first(self); + struct rb_node *next = rb_first(maps); while (next) { struct map *pos = rb_entry(next, struct map, rb_node); next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, self); + rb_erase(&pos->rb_node, maps); map__delete(pos); } } -static void maps__delete_removed(struct list_head *self) +static void maps__delete_removed(struct list_head *maps) { struct map *pos, *n; - list_for_each_entry_safe(pos, n, self, node) { + list_for_each_entry_safe(pos, n, maps, node) { list_del(&pos->node); map__delete(pos); } } -void map_groups__exit(struct map_groups *self) +void map_groups__exit(struct map_groups *mg) { int i; for (i = 0; i < MAP__NR_TYPES; ++i) { - maps__delete(&self->maps[i]); - maps__delete_removed(&self->removed_maps[i]); + maps__delete(&mg->maps[i]); + maps__delete_removed(&mg->removed_maps[i]); } } -void map_groups__flush(struct map_groups *self) +struct map_groups *map_groups__new(void) +{ + struct map_groups *mg = malloc(sizeof(*mg)); + + if (mg != NULL) + map_groups__init(mg); + + return mg; +} + +void map_groups__delete(struct map_groups *mg) +{ + map_groups__exit(mg); + free(mg); +} + +void map_groups__put(struct map_groups *mg) +{ + if (--mg->refcnt == 0) + map_groups__delete(mg); +} + +void map_groups__flush(struct map_groups *mg) { int type; for (type = 0; type < MAP__NR_TYPES; type++) { - struct rb_root *root = &self->maps[type]; + struct rb_root *root = &mg->maps[type]; struct rb_node *next = rb_first(root); while (next) { @@ -279,19 +493,20 @@ void map_groups__flush(struct map_groups *self) * instance in some hist_entry instances, so * just move them to a separate list. */ - list_add_tail(&pos->node, &self->removed_maps[pos->type]); + list_add_tail(&pos->node, &mg->removed_maps[pos->type]); } } } -struct symbol *map_groups__find_symbol(struct map_groups *self, +struct symbol *map_groups__find_symbol(struct map_groups *mg, enum map_type type, u64 addr, struct map **mapp, symbol_filter_t filter) { - struct map *map = map_groups__find(self, type, addr); + struct map *map = map_groups__find(mg, type, addr); - if (map != NULL) { + /* Ensure map is loaded before using map->map_ip */ + if (map != NULL && map__load(map, filter) >= 0) { if (mapp != NULL) *mapp = map; return map__find_symbol(map, map->map_ip(map, addr), filter); @@ -300,7 +515,7 @@ struct symbol *map_groups__find_symbol(struct map_groups *self, return NULL; } -struct symbol *map_groups__find_symbol_by_name(struct map_groups *self, +struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, enum map_type type, const char *name, struct map **mapp, @@ -308,7 +523,7 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *self, { struct rb_node *nd; - for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) { struct map *pos = rb_entry(nd, struct map, rb_node); struct symbol *sym = map__find_symbol_by_name(pos, name, filter); @@ -322,13 +537,30 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *self, return NULL; } -size_t __map_groups__fprintf_maps(struct map_groups *self, +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) { size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); struct rb_node *nd; - for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) { struct map *pos = rb_entry(nd, struct map, rb_node); printed += fprintf(fp, "Map:"); printed += map__fprintf(pos, fp); @@ -341,22 +573,22 @@ size_t __map_groups__fprintf_maps(struct map_groups *self, return printed; } -size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp) +size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_maps(self, i, verbose, fp); + printed += __map_groups__fprintf_maps(mg, i, verbose, fp); return printed; } -static size_t __map_groups__fprintf_removed_maps(struct map_groups *self, +static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg, enum map_type type, int verbose, FILE *fp) { struct map *pos; size_t printed = 0; - list_for_each_entry(pos, &self->removed_maps[type], node) { + list_for_each_entry(pos, &mg->removed_maps[type], node) { printed += fprintf(fp, "Map:"); printed += map__fprintf(pos, fp); if (verbose > 1) { @@ -367,26 +599,26 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *self, return printed; } -static size_t map_groups__fprintf_removed_maps(struct map_groups *self, +static size_t map_groups__fprintf_removed_maps(struct map_groups *mg, int verbose, FILE *fp) { size_t printed = 0, i; for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_removed_maps(self, i, verbose, fp); + printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp); return printed; } -size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp) +size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp) { - size_t printed = map_groups__fprintf_maps(self, verbose, fp); + size_t printed = map_groups__fprintf_maps(mg, verbose, fp); printed += fprintf(fp, "Removed maps:\n"); - return printed + map_groups__fprintf_removed_maps(self, verbose, fp); + return printed + map_groups__fprintf_removed_maps(mg, verbose, fp); } -int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, +int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, int verbose, FILE *fp) { - struct rb_root *root = &self->maps[map->type]; + struct rb_root *root = &mg->maps[map->type]; struct rb_node *next = rb_first(root); int err = 0; @@ -417,7 +649,7 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, } before->end = map->start - 1; - map_groups__insert(self, before); + map_groups__insert(mg, before); if (verbose >= 2) map__fprintf(before, fp); } @@ -431,7 +663,7 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, } after->start = map->end + 1; - map_groups__insert(self, after); + map_groups__insert(mg, after); if (verbose >= 2) map__fprintf(after, fp); } @@ -440,7 +672,7 @@ move_map: * If we have references, just move them to a separate list. */ if (pos->referenced) - list_add_tail(&pos->node, &self->removed_maps[map->type]); + list_add_tail(&pos->node, &mg->removed_maps[map->type]); else map__delete(pos); @@ -454,7 +686,7 @@ move_map: /* * XXX This should not really _copy_ te maps, but refcount them. */ -int map_groups__clone(struct map_groups *self, +int map_groups__clone(struct map_groups *mg, struct map_groups *parent, enum map_type type) { struct rb_node *nd; @@ -463,40 +695,11 @@ int map_groups__clone(struct map_groups *self, struct map *new = map__clone(map); if (new == NULL) return -ENOMEM; - map_groups__insert(self, new); + map_groups__insert(mg, new); } return 0; } -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 *self) -{ - struct kmap *kmap = map__kmap(self); - 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; - - self->map_ip = map__reloc_map_ip; - self->unmap_ip = map__reloc_unmap_ip; - self->pgoff = reloc; -} - void maps__insert(struct rb_root *maps, struct map *map) { struct rb_node **p = &maps->rb_node; @@ -517,9 +720,9 @@ void maps__insert(struct rb_root *maps, struct map *map) rb_insert_color(&map->rb_node, maps); } -void maps__remove(struct rb_root *self, struct map *map) +void maps__remove(struct rb_root *maps, struct map *map) { - rb_erase(&map->rb_node, self); + rb_erase(&map->rb_node, maps); } struct map *maps__find(struct rb_root *maps, u64 ip) @@ -542,141 +745,20 @@ struct map *maps__find(struct rb_root *maps, u64 ip) return NULL; } -int machine__init(struct machine *self, const char *root_dir, pid_t pid) -{ - map_groups__init(&self->kmaps); - RB_CLEAR_NODE(&self->rb_node); - INIT_LIST_HEAD(&self->user_dsos); - INIT_LIST_HEAD(&self->kernel_dsos); - - self->kmaps.machine = self; - self->pid = pid; - self->root_dir = strdup(root_dir); - return self->root_dir == NULL ? -ENOMEM : 0; -} - -static void dsos__delete(struct list_head *self) -{ - struct dso *pos, *n; - - list_for_each_entry_safe(pos, n, self, node) { - list_del(&pos->node); - dso__delete(pos); - } -} - -void machine__exit(struct machine *self) -{ - map_groups__exit(&self->kmaps); - dsos__delete(&self->user_dsos); - dsos__delete(&self->kernel_dsos); - free(self->root_dir); - self->root_dir = NULL; -} - -void machine__delete(struct machine *self) +struct map *maps__first(struct rb_root *maps) { - machine__exit(self); - free(self); -} + struct rb_node *first = rb_first(maps); -struct machine *machines__add(struct rb_root *self, pid_t pid, - const char *root_dir) -{ - struct rb_node **p = &self->rb_node; - struct rb_node *parent = NULL; - struct machine *pos, *machine = malloc(sizeof(*machine)); - - if (!machine) - return NULL; - - if (machine__init(machine, root_dir, pid) != 0) { - free(machine); - return NULL; - } - - while (*p != NULL) { - parent = *p; - pos = rb_entry(parent, struct machine, rb_node); - if (pid < pos->pid) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&machine->rb_node, parent, p); - rb_insert_color(&machine->rb_node, self); - - return machine; -} - -struct machine *machines__find(struct rb_root *self, pid_t pid) -{ - struct rb_node **p = &self->rb_node; - struct rb_node *parent = NULL; - struct machine *machine; - struct machine *default_machine = NULL; - - while (*p != NULL) { - parent = *p; - machine = rb_entry(parent, struct machine, rb_node); - if (pid < machine->pid) - p = &(*p)->rb_left; - else if (pid > machine->pid) - p = &(*p)->rb_right; - else - return machine; - if (!machine->pid) - default_machine = machine; - } - - return default_machine; -} - -struct machine *machines__findnew(struct rb_root *self, pid_t pid) -{ - char path[PATH_MAX]; - const char *root_dir; - struct machine *machine = machines__find(self, pid); - - if (!machine || machine->pid != pid) { - if (pid == HOST_KERNEL_ID || pid == DEFAULT_GUEST_KERNEL_ID) - root_dir = ""; - else { - if (!symbol_conf.guestmount) - goto out; - sprintf(path, "%s/%d", symbol_conf.guestmount, pid); - if (access(path, R_OK)) { - pr_err("Can't access file %s\n", path); - goto out; - } - root_dir = path; - } - machine = machines__add(self, pid, root_dir); - } - -out: - return machine; -} - -void machines__process(struct rb_root *self, machine__process_t process, void *data) -{ - struct rb_node *nd; - - for (nd = rb_first(self); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - process(pos, data); - } + if (first) + return rb_entry(first, struct map, rb_node); + return NULL; } -char *machine__mmap_name(struct machine *self, char *bf, size_t size) +struct map *maps__next(struct map *map) { - if (machine__is_host(self)) - snprintf(bf, size, "[%s]", "kernel.kallsyms"); - else if (machine__is_default_guest(self)) - snprintf(bf, size, "[%s]", "guest.kernel.kallsyms"); - else - snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms", self->pid); + struct rb_node *next = rb_next(&map->rb_node); - return bf; + 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 b397c038372..7758c72522e 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -6,7 +6,7 @@ #include <linux/rbtree.h> #include <stdio.h> #include <stdbool.h> -#include "types.h" +#include <linux/types.h> enum map_type { MAP__FUNCTION = 0, @@ -18,9 +18,11 @@ enum map_type { extern const char *map_type__name[MAP__NR_TYPES]; struct dso; +struct ip_callchain; struct ref_reloc_sym; struct map_groups; struct machine; +struct perf_evsel; struct map { union { @@ -31,8 +33,15 @@ struct map { u64 end; u8 /* enum map_type */ type; bool referenced; + bool erange_warned; u32 priv; + u32 prot; + u32 flags; u64 pgoff; + u64 reloc; + 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); @@ -52,31 +61,23 @@ struct map_groups { struct rb_root maps[MAP__NR_TYPES]; struct list_head removed_maps[MAP__NR_TYPES]; struct machine *machine; + int refcnt; }; -/* Native host kernel uses -1 as pid index in machine */ -#define HOST_KERNEL_ID (-1) -#define DEFAULT_GUEST_KERNEL_ID (0) - -struct machine { - struct rb_node rb_node; - pid_t pid; - char *root_dir; - struct list_head user_dsos; - struct list_head kernel_dsos; - struct map_groups kmaps; - struct map *vmlinux_maps[MAP__NR_TYPES]; -}; +struct map_groups *map_groups__new(void); +void map_groups__delete(struct map_groups *mg); -static inline -struct map *machine__kernel_map(struct machine *self, enum map_type type) +static inline struct map_groups *map_groups__get(struct map_groups *mg) { - return self->vmlinux_maps[type]; + ++mg->refcnt; + return mg; } -static inline struct kmap *map__kmap(struct map *self) +void map_groups__put(struct map_groups *mg); + +static inline struct kmap *map__kmap(struct map *map) { - return (struct kmap *)(self + 1); + return (struct kmap *)(map + 1); } static inline u64 map__map_ip(struct map *map, u64 ip) @@ -89,7 +90,7 @@ static inline u64 map__unmap_ip(struct map *map, u64 ip) return ip + map->start - map->pgoff; } -static inline u64 identity__map_ip(struct map *map __used, u64 ip) +static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip) { return ip; } @@ -97,141 +98,123 @@ static inline u64 identity__map_ip(struct map *map __used, u64 ip) /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */ u64 map__rip_2objdump(struct map *map, u64 rip); -u64 map__objdump_2ip(struct map *map, u64 addr); + +/* objdump address -> memory address */ +u64 map__objdump_2mem(struct map *map, u64 ip); struct symbol; +/* map__for_each_symbol - iterate over the symbols in the given map + * + * @map: the 'struct map *' in which symbols itereated + * @pos: the 'struct symbol *' to use as a loop cursor + * @n: the 'struct rb_node *' to use as a temporary storage + * Note: caller must ensure map->dso is not NULL (map is loaded). + */ +#define map__for_each_symbol(map, pos, n) \ + dso__for_each_symbol(map->dso, pos, n, map->type) + typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); -void map__init(struct map *self, enum map_type type, +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); -void map__delete(struct map *self); -struct map *map__clone(struct map *self); + u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, + u64 ino_gen, u32 prot, u32 flags, + 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); int map__overlap(struct map *l, struct map *r); -size_t map__fprintf(struct map *self, FILE *fp); +size_t map__fprintf(struct map *map, FILE *fp); +size_t map__fprintf_dsoname(struct map *map, FILE *fp); +int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, + FILE *fp); -int map__load(struct map *self, symbol_filter_t filter); -struct symbol *map__find_symbol(struct map *self, +int map__load(struct map *map, symbol_filter_t filter); +struct symbol *map__find_symbol(struct map *map, u64 addr, symbol_filter_t filter); -struct symbol *map__find_symbol_by_name(struct map *self, const char *name, +struct symbol *map__find_symbol_by_name(struct map *map, const char *name, symbol_filter_t filter); -void map__fixup_start(struct map *self); -void map__fixup_end(struct map *self); +void map__fixup_start(struct map *map); +void map__fixup_end(struct map *map); -void map__reloc_vmlinux(struct map *self); +void map__reloc_vmlinux(struct map *map); -size_t __map_groups__fprintf_maps(struct map_groups *self, +size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, int verbose, FILE *fp); void maps__insert(struct rb_root *maps, struct map *map); -void maps__remove(struct rb_root *self, struct map *map); +void maps__remove(struct rb_root *maps, struct map *map); struct map *maps__find(struct rb_root *maps, u64 addr); -void map_groups__init(struct map_groups *self); -void map_groups__exit(struct map_groups *self); -int map_groups__clone(struct map_groups *self, +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, struct map_groups *parent, enum map_type type); -size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp); -size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp); - -typedef void (*machine__process_t)(struct machine *self, void *data); - -void machines__process(struct rb_root *self, machine__process_t process, void *data); -struct machine *machines__add(struct rb_root *self, pid_t pid, - const char *root_dir); -struct machine *machines__find_host(struct rb_root *self); -struct machine *machines__find(struct rb_root *self, pid_t pid); -struct machine *machines__findnew(struct rb_root *self, pid_t pid); -char *machine__mmap_name(struct machine *self, char *bf, size_t size); -int machine__init(struct machine *self, const char *root_dir, pid_t pid); -void machine__exit(struct machine *self); -void machine__delete(struct machine *self); - -/* - * Default guest kernel is defined by parameter --guestkallsyms - * and --guestmodules - */ -static inline bool machine__is_default_guest(struct machine *self) +size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp); +size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp); + +int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, + u64 addr); + +static inline void map_groups__insert(struct map_groups *mg, struct map *map) { - return self ? self->pid == DEFAULT_GUEST_KERNEL_ID : false; + maps__insert(&mg->maps[map->type], map); + map->groups = mg; } -static inline bool machine__is_host(struct machine *self) +static inline void map_groups__remove(struct map_groups *mg, struct map *map) { - return self ? self->pid == HOST_KERNEL_ID : false; + maps__remove(&mg->maps[map->type], map); } -static inline void map_groups__insert(struct map_groups *self, struct map *map) +static inline struct map *map_groups__find(struct map_groups *mg, + enum map_type type, u64 addr) { - maps__insert(&self->maps[map->type], map); - map->groups = self; + return maps__find(&mg->maps[type], addr); } -static inline void map_groups__remove(struct map_groups *self, struct map *map) +static inline struct map *map_groups__first(struct map_groups *mg, + enum map_type type) { - maps__remove(&self->maps[map->type], map); + return maps__first(&mg->maps[type]); } -static inline struct map *map_groups__find(struct map_groups *self, - enum map_type type, u64 addr) +static inline struct map *map_groups__next(struct map *map) { - return maps__find(&self->maps[type], addr); + return maps__next(map); } -struct symbol *map_groups__find_symbol(struct map_groups *self, +struct symbol *map_groups__find_symbol(struct map_groups *mg, enum map_type type, u64 addr, struct map **mapp, symbol_filter_t filter); -struct symbol *map_groups__find_symbol_by_name(struct map_groups *self, +struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, enum map_type type, const char *name, struct map **mapp, symbol_filter_t filter); -static inline -struct symbol *machine__find_kernel_symbol(struct machine *self, - enum map_type type, u64 addr, - struct map **mapp, - symbol_filter_t filter) -{ - return map_groups__find_symbol(&self->kmaps, type, addr, mapp, filter); -} +struct addr_map_symbol; -static inline -struct symbol *machine__find_kernel_function(struct machine *self, u64 addr, - struct map **mapp, - symbol_filter_t filter) -{ - return machine__find_kernel_symbol(self, MAP__FUNCTION, addr, mapp, filter); -} +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 *self, +struct symbol *map_groups__find_function_by_name(struct map_groups *mg, const char *name, struct map **mapp, symbol_filter_t filter) { - return map_groups__find_symbol_by_name(self, MAP__FUNCTION, name, mapp, filter); -} - -static inline -struct symbol *machine__find_kernel_function_by_name(struct machine *self, - const char *name, - struct map **mapp, - symbol_filter_t filter) -{ - return map_groups__find_function_by_name(&self->kmaps, name, mapp, - filter); + return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter); } -int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, +int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, int verbose, FILE *fp); -struct map *map_groups__find_by_name(struct map_groups *self, +struct map *map_groups__find_by_name(struct map_groups *mg, enum map_type type, const char *name); -struct map *machine__new_module(struct machine *self, u64 start, const char *filename); -void map_groups__flush(struct map_groups *self); +void map_groups__flush(struct map_groups *mg); #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c index 1915de20dca..31ee02d4e98 100644 --- a/tools/perf/util/pager.c +++ b/tools/perf/util/pager.c @@ -57,9 +57,13 @@ void setup_pager(void) } if (!pager) pager = getenv("PAGER"); + if (!(pager || access("/usr/bin/pager", X_OK))) + pager = "/usr/bin/pager"; + if (!(pager || access("/usr/bin/less", X_OK))) + pager = "/usr/bin/less"; if (!pager) - pager = "less"; - else if (!*pager || !strcmp(pager, "cat")) + pager = "cat"; + if (!*pager || !strcmp(pager, "cat")) return; spawned_pager = 1; /* means we are emitting to terminal */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4af5bd59cfd..1e15df10a88 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1,130 +1,128 @@ -#include "../../../include/linux/hw_breakpoint.h" +#include <linux/hw_breakpoint.h> #include "util.h" #include "../perf.h" +#include "evlist.h" +#include "evsel.h" #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" -#include "debugfs.h" +#include <api/fs/debugfs.h> +#include "parse-events-bison.h" +#define YY_EXTRA_TYPE int +#include "parse-events-flex.h" +#include "pmu.h" +#include "thread_map.h" -int nr_counters; - -struct perf_event_attr attrs[MAX_COUNTERS]; -char *filters[MAX_COUNTERS]; +#define MAX_NAME_LEN 100 struct event_symbol { - u8 type; - u64 config; const char *symbol; const char *alias; }; -enum event_result { - EVT_FAILED, - EVT_HANDLED, - EVT_HANDLED_ALL +#ifdef PARSER_DEBUG +extern int parse_events_debug; +#endif +int parse_events_parse(void *data, void *scanner); + +static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = { + .symbol = "cpu-cycles", + .alias = "cycles", + }, + [PERF_COUNT_HW_INSTRUCTIONS] = { + .symbol = "instructions", + .alias = "", + }, + [PERF_COUNT_HW_CACHE_REFERENCES] = { + .symbol = "cache-references", + .alias = "", + }, + [PERF_COUNT_HW_CACHE_MISSES] = { + .symbol = "cache-misses", + .alias = "", + }, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { + .symbol = "branch-instructions", + .alias = "branches", + }, + [PERF_COUNT_HW_BRANCH_MISSES] = { + .symbol = "branch-misses", + .alias = "", + }, + [PERF_COUNT_HW_BUS_CYCLES] = { + .symbol = "bus-cycles", + .alias = "", + }, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = { + .symbol = "stalled-cycles-frontend", + .alias = "idle-cycles-frontend", + }, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = { + .symbol = "stalled-cycles-backend", + .alias = "idle-cycles-backend", + }, + [PERF_COUNT_HW_REF_CPU_CYCLES] = { + .symbol = "ref-cycles", + .alias = "", + }, }; -char debugfs_path[MAXPATHLEN]; - -#define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x -#define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x - -static struct event_symbol event_symbols[] = { - { CHW(CPU_CYCLES), "cpu-cycles", "cycles" }, - { CHW(INSTRUCTIONS), "instructions", "" }, - { CHW(CACHE_REFERENCES), "cache-references", "" }, - { CHW(CACHE_MISSES), "cache-misses", "" }, - { CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" }, - { CHW(BRANCH_MISSES), "branch-misses", "" }, - { CHW(BUS_CYCLES), "bus-cycles", "" }, - - { CSW(CPU_CLOCK), "cpu-clock", "" }, - { CSW(TASK_CLOCK), "task-clock", "" }, - { CSW(PAGE_FAULTS), "page-faults", "faults" }, - { CSW(PAGE_FAULTS_MIN), "minor-faults", "" }, - { CSW(PAGE_FAULTS_MAJ), "major-faults", "" }, - { CSW(CONTEXT_SWITCHES), "context-switches", "cs" }, - { CSW(CPU_MIGRATIONS), "cpu-migrations", "migrations" }, - { CSW(ALIGNMENT_FAULTS), "alignment-faults", "" }, - { CSW(EMULATION_FAULTS), "emulation-faults", "" }, +static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { + [PERF_COUNT_SW_CPU_CLOCK] = { + .symbol = "cpu-clock", + .alias = "", + }, + [PERF_COUNT_SW_TASK_CLOCK] = { + .symbol = "task-clock", + .alias = "", + }, + [PERF_COUNT_SW_PAGE_FAULTS] = { + .symbol = "page-faults", + .alias = "faults", + }, + [PERF_COUNT_SW_CONTEXT_SWITCHES] = { + .symbol = "context-switches", + .alias = "cs", + }, + [PERF_COUNT_SW_CPU_MIGRATIONS] = { + .symbol = "cpu-migrations", + .alias = "migrations", + }, + [PERF_COUNT_SW_PAGE_FAULTS_MIN] = { + .symbol = "minor-faults", + .alias = "", + }, + [PERF_COUNT_SW_PAGE_FAULTS_MAJ] = { + .symbol = "major-faults", + .alias = "", + }, + [PERF_COUNT_SW_ALIGNMENT_FAULTS] = { + .symbol = "alignment-faults", + .alias = "", + }, + [PERF_COUNT_SW_EMULATION_FAULTS] = { + .symbol = "emulation-faults", + .alias = "", + }, + [PERF_COUNT_SW_DUMMY] = { + .symbol = "dummy", + .alias = "", + }, }; #define __PERF_EVENT_FIELD(config, name) \ ((config & PERF_EVENT_##name##_MASK) >> PERF_EVENT_##name##_SHIFT) -#define PERF_EVENT_RAW(config) __PERF_EVENT_FIELD(config, RAW) +#define PERF_EVENT_RAW(config) __PERF_EVENT_FIELD(config, RAW) #define PERF_EVENT_CONFIG(config) __PERF_EVENT_FIELD(config, CONFIG) -#define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE) +#define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE) #define PERF_EVENT_ID(config) __PERF_EVENT_FIELD(config, EVENT) -static const char *hw_event_names[] = { - "cycles", - "instructions", - "cache-references", - "cache-misses", - "branches", - "branch-misses", - "bus-cycles", -}; - -static const char *sw_event_names[] = { - "cpu-clock-msecs", - "task-clock-msecs", - "page-faults", - "context-switches", - "CPU-migrations", - "minor-faults", - "major-faults", - "alignment-faults", - "emulation-faults", -}; - -#define MAX_ALIASES 8 - -static const char *hw_cache[][MAX_ALIASES] = { - { "L1-dcache", "l1-d", "l1d", "L1-data", }, - { "L1-icache", "l1-i", "l1i", "L1-instruction", }, - { "LLC", "L2" }, - { "dTLB", "d-tlb", "Data-TLB", }, - { "iTLB", "i-tlb", "Instruction-TLB", }, - { "branch", "branches", "bpu", "btb", "bpc", }, -}; - -static const char *hw_cache_op[][MAX_ALIASES] = { - { "load", "loads", "read", }, - { "store", "stores", "write", }, - { "prefetch", "prefetches", "speculative-read", "speculative-load", }, -}; - -static const char *hw_cache_result[][MAX_ALIASES] = { - { "refs", "Reference", "ops", "access", }, - { "misses", "miss", }, -}; - -#define C(x) PERF_COUNT_HW_CACHE_##x -#define CACHE_READ (1 << C(OP_READ)) -#define CACHE_WRITE (1 << C(OP_WRITE)) -#define CACHE_PREFETCH (1 << C(OP_PREFETCH)) -#define COP(x) (1 << x) - -/* - * cache operartion stat - * L1I : Read and prefetch only - * ITLB and BPU : Read-only - */ -static unsigned long hw_cache_stat[C(MAX)] = { - [C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), - [C(L1I)] = (CACHE_READ | CACHE_PREFETCH), - [C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), - [C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), - [C(ITLB)] = (CACHE_READ), - [C(BPU)] = (CACHE_READ), -}; - #define for_each_subsystem(sys_dir, sys_dirent, sys_next) \ while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next) \ if (sys_dirent.d_type == DT_DIR && \ @@ -136,7 +134,7 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) char evt_path[MAXPATHLEN]; int fd; - snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path, + snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path, sys_dir->d_name, evt_dir->d_name); fd = open(evt_path, O_RDONLY); if (fd < 0) @@ -161,22 +159,22 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) struct tracepoint_path *path = NULL; DIR *sys_dir, *evt_dir; struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; - char id_buf[4]; + char id_buf[24]; int fd; u64 id; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(debugfs_path)) + if (debugfs_valid_mountpoint(tracing_events_path)) return NULL; - sys_dir = opendir(debugfs_path); + sys_dir = opendir(tracing_events_path); if (!sys_dir) return NULL; for_each_subsystem(sys_dir, sys_dirent, sys_next) { - snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path, + snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_dirent.d_name); evt_dir = opendir(dir_path); if (!evt_dir) @@ -206,7 +204,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) } path->name = malloc(MAX_EVENT_LENGTH); if (!path->name) { - free(path->system); + zfree(&path->system); free(path); return NULL; } @@ -224,99 +222,43 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) return NULL; } -#define TP_PATH_LEN (MAX_EVENT_LENGTH * 2 + 1) -static const char *tracepoint_id_to_name(u64 config) +struct tracepoint_path *tracepoint_name_to_path(const char *name) { - static char buf[TP_PATH_LEN]; - struct tracepoint_path *path; + struct tracepoint_path *path = zalloc(sizeof(*path)); + char *str = strchr(name, ':'); - path = tracepoint_id_to_path(config); - if (path) { - snprintf(buf, TP_PATH_LEN, "%s:%s", path->system, path->name); - free(path->name); - free(path->system); + if (path == NULL || str == NULL) { free(path); - } else - snprintf(buf, TP_PATH_LEN, "%s:%s", "unknown", "unknown"); - - return buf; -} - -static int is_cache_op_valid(u8 cache_type, u8 cache_op) -{ - if (hw_cache_stat[cache_type] & COP(cache_op)) - return 1; /* valid */ - else - return 0; /* invalid */ -} - -static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result) -{ - static char name[50]; - - if (cache_result) { - sprintf(name, "%s-%s-%s", hw_cache[cache_type][0], - hw_cache_op[cache_op][0], - hw_cache_result[cache_result][0]); - } else { - sprintf(name, "%s-%s", hw_cache[cache_type][0], - hw_cache_op[cache_op][1]); + return NULL; } - return name; -} + path->system = strndup(name, str - name); + path->name = strdup(str+1); -const char *event_name(int counter) -{ - u64 config = attrs[counter].config; - int type = attrs[counter].type; + if (path->system == NULL || path->name == NULL) { + zfree(&path->system); + zfree(&path->name); + free(path); + path = NULL; + } - return __event_name(type, config); + return path; } -const char *__event_name(int type, u64 config) +const char *event_type(int type) { - static char buf[32]; - - if (type == PERF_TYPE_RAW) { - sprintf(buf, "raw 0x%llx", config); - return buf; - } - switch (type) { case PERF_TYPE_HARDWARE: - if (config < PERF_COUNT_HW_MAX) - return hw_event_names[config]; - return "unknown-hardware"; - - case PERF_TYPE_HW_CACHE: { - u8 cache_type, cache_op, cache_result; - - cache_type = (config >> 0) & 0xff; - if (cache_type > PERF_COUNT_HW_CACHE_MAX) - return "unknown-ext-hardware-cache-type"; - - cache_op = (config >> 8) & 0xff; - if (cache_op > PERF_COUNT_HW_CACHE_OP_MAX) - return "unknown-ext-hardware-cache-op"; - - cache_result = (config >> 16) & 0xff; - if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX) - return "unknown-ext-hardware-cache-result"; - - if (!is_cache_op_valid(cache_type, cache_op)) - return "invalid-cache"; - - return event_cache_name(cache_type, cache_op, cache_result); - } + return "hardware"; case PERF_TYPE_SOFTWARE: - if (config < PERF_COUNT_SW_MAX) - return sw_event_names[config]; - return "unknown-software"; + return "software"; case PERF_TYPE_TRACEPOINT: - return tracepoint_id_to_name(config); + return "tracepoint"; + + case PERF_TYPE_HW_CACHE: + return "hardware-cache"; default: break; @@ -325,66 +267,93 @@ const char *__event_name(int type, u64 config) return "unknown"; } -static int parse_aliases(const char **str, const char *names[][MAX_ALIASES], int size) + + +static struct perf_evsel * +__add_event(struct list_head *list, int *idx, + struct perf_event_attr *attr, + char *name, struct cpu_map *cpus) +{ + struct perf_evsel *evsel; + + event_attr_init(attr); + + evsel = perf_evsel__new_idx(attr, (*idx)++); + if (!evsel) + return NULL; + + evsel->cpus = cpus; + if (name) + evsel->name = strdup(name); + list_add_tail(&evsel->node, list); + return evsel; +} + +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) ? 0 : -ENOMEM; +} + +static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) { int i, j; int n, longest = -1; for (i = 0; i < size; i++) { - for (j = 0; j < MAX_ALIASES && names[i][j]; j++) { + for (j = 0; j < PERF_EVSEL__MAX_ALIASES && names[i][j]; j++) { n = strlen(names[i][j]); - if (n > longest && !strncasecmp(*str, names[i][j], n)) + if (n > longest && !strncasecmp(str, names[i][j], n)) longest = n; } - if (longest > 0) { - *str += longest; + if (longest > 0) return i; - } } return -1; } -static enum event_result -parse_generic_hw_event(const char **str, struct perf_event_attr *attr) +int parse_events_add_cache(struct list_head *list, int *idx, + char *type, char *op_result1, char *op_result2) { - const char *s = *str; + struct perf_event_attr attr; + char name[MAX_NAME_LEN]; int cache_type = -1, cache_op = -1, cache_result = -1; + char *op_result[2] = { op_result1, op_result2 }; + int i, n; - cache_type = parse_aliases(&s, hw_cache, PERF_COUNT_HW_CACHE_MAX); /* * No fallback - if we cannot get a clear cache type * then bail out: */ + cache_type = parse_aliases(type, perf_evsel__hw_cache, + PERF_COUNT_HW_CACHE_MAX); if (cache_type == -1) - return EVT_FAILED; + return -EINVAL; - while ((cache_op == -1 || cache_result == -1) && *s == '-') { - ++s; + n = snprintf(name, MAX_NAME_LEN, "%s", type); + + for (i = 0; (i < 2) && (op_result[i]); i++) { + char *str = op_result[i]; + + n += snprintf(name + n, MAX_NAME_LEN - n, "-%s", str); if (cache_op == -1) { - cache_op = parse_aliases(&s, hw_cache_op, - PERF_COUNT_HW_CACHE_OP_MAX); + cache_op = parse_aliases(str, perf_evsel__hw_cache_op, + PERF_COUNT_HW_CACHE_OP_MAX); if (cache_op >= 0) { - if (!is_cache_op_valid(cache_type, cache_op)) - return 0; + if (!perf_evsel__is_cache_op_valid(cache_type, cache_op)) + return -EINVAL; continue; } } if (cache_result == -1) { - cache_result = parse_aliases(&s, hw_cache_result, - PERF_COUNT_HW_CACHE_RESULT_MAX); + cache_result = parse_aliases(str, perf_evsel__hw_cache_result, + PERF_COUNT_HW_CACHE_RESULT_MAX); if (cache_result >= 0) continue; } - - /* - * Can't parse this as a cache op or result, so back up - * to the '-'. - */ - --s; - break; } /* @@ -399,307 +368,361 @@ parse_generic_hw_event(const char **str, struct perf_event_attr *attr) if (cache_result == -1) cache_result = PERF_COUNT_HW_CACHE_RESULT_ACCESS; - attr->config = cache_type | (cache_op << 8) | (cache_result << 16); - attr->type = PERF_TYPE_HW_CACHE; - - *str = s; - return EVT_HANDLED; + memset(&attr, 0, sizeof(attr)); + attr.config = cache_type | (cache_op << 8) | (cache_result << 16); + attr.type = PERF_TYPE_HW_CACHE; + return add_event(list, idx, &attr, name); } -static enum event_result -parse_single_tracepoint_event(char *sys_name, - const char *evt_name, - unsigned int evt_length, - struct perf_event_attr *attr, - const char **strp) +static int add_tracepoint(struct list_head *list, int *idx, + char *sys_name, char *evt_name) { - char evt_path[MAXPATHLEN]; - char id_buf[4]; - u64 id; - int fd; - - snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path, - sys_name, evt_name); - - fd = open(evt_path, O_RDONLY); - if (fd < 0) - return EVT_FAILED; - - if (read(fd, id_buf, sizeof(id_buf)) < 0) { - close(fd); - return EVT_FAILED; - } - - close(fd); - id = atoll(id_buf); - attr->config = id; - attr->type = PERF_TYPE_TRACEPOINT; - *strp = evt_name + evt_length; - - attr->sample_type |= PERF_SAMPLE_RAW; - attr->sample_type |= PERF_SAMPLE_TIME; - attr->sample_type |= PERF_SAMPLE_CPU; + struct perf_evsel *evsel; - attr->sample_period = 1; + evsel = perf_evsel__newtp_idx(sys_name, evt_name, (*idx)++); + if (!evsel) + return -ENOMEM; + list_add_tail(&evsel->node, list); - return EVT_HANDLED; + return 0; } -/* sys + ':' + event + ':' + flags*/ -#define MAX_EVOPT_LEN (MAX_EVENT_LENGTH * 2 + 2 + 128) -static enum event_result -parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp, - char *flags) +static int add_tracepoint_multi_event(struct list_head *list, int *idx, + char *sys_name, char *evt_name) { char evt_path[MAXPATHLEN]; struct dirent *evt_ent; DIR *evt_dir; + int ret = 0; - snprintf(evt_path, MAXPATHLEN, "%s/%s", debugfs_path, sys_name); + snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name); evt_dir = opendir(evt_path); - if (!evt_dir) { perror("Can't open event dir"); - return EVT_FAILED; + return -1; } - while ((evt_ent = readdir(evt_dir))) { - char event_opt[MAX_EVOPT_LEN + 1]; - int len; - + while (!ret && (evt_ent = readdir(evt_dir))) { if (!strcmp(evt_ent->d_name, ".") || !strcmp(evt_ent->d_name, "..") || !strcmp(evt_ent->d_name, "enable") || !strcmp(evt_ent->d_name, "filter")) continue; - if (!strglobmatch(evt_ent->d_name, evt_exp)) + if (!strglobmatch(evt_ent->d_name, evt_name)) continue; - len = snprintf(event_opt, MAX_EVOPT_LEN, "%s:%s%s%s", sys_name, - evt_ent->d_name, flags ? ":" : "", - flags ?: ""); - if (len < 0) - return EVT_FAILED; - - if (parse_events(NULL, event_opt, 0)) - return EVT_FAILED; + ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name); } - return EVT_HANDLED_ALL; + closedir(evt_dir); + return ret; } - -static enum event_result parse_tracepoint_event(const char **strp, - struct perf_event_attr *attr) +static int add_tracepoint_event(struct list_head *list, int *idx, + char *sys_name, char *evt_name) { - const char *evt_name; - char *flags; - char sys_name[MAX_EVENT_LENGTH]; - unsigned int sys_length, evt_length; + return strpbrk(evt_name, "*?") ? + add_tracepoint_multi_event(list, idx, sys_name, evt_name) : + add_tracepoint(list, idx, sys_name, evt_name); +} - if (debugfs_valid_mountpoint(debugfs_path)) - return 0; +static int add_tracepoint_multi_sys(struct list_head *list, int *idx, + char *sys_name, char *evt_name) +{ + struct dirent *events_ent; + DIR *events_dir; + int ret = 0; - evt_name = strchr(*strp, ':'); - if (!evt_name) - return EVT_FAILED; + events_dir = opendir(tracing_events_path); + if (!events_dir) { + perror("Can't open event dir"); + return -1; + } - sys_length = evt_name - *strp; - if (sys_length >= MAX_EVENT_LENGTH) - return 0; + while (!ret && (events_ent = readdir(events_dir))) { + if (!strcmp(events_ent->d_name, ".") + || !strcmp(events_ent->d_name, "..") + || !strcmp(events_ent->d_name, "enable") + || !strcmp(events_ent->d_name, "header_event") + || !strcmp(events_ent->d_name, "header_page")) + continue; - strncpy(sys_name, *strp, sys_length); - sys_name[sys_length] = '\0'; - evt_name = evt_name + 1; + if (!strglobmatch(events_ent->d_name, sys_name)) + continue; - flags = strchr(evt_name, ':'); - if (flags) { - /* split it out: */ - evt_name = strndup(evt_name, flags - evt_name); - flags++; + ret = add_tracepoint_event(list, idx, events_ent->d_name, + evt_name); } - evt_length = strlen(evt_name); - if (evt_length >= MAX_EVENT_LENGTH) - return EVT_FAILED; + closedir(events_dir); + return ret; +} + +int parse_events_add_tracepoint(struct list_head *list, int *idx, + char *sys, char *event) +{ + int ret; + + ret = debugfs_valid_mountpoint(tracing_events_path); + if (ret) + return ret; - if (strpbrk(evt_name, "*?")) { - *strp = evt_name + evt_length; - return parse_multiple_tracepoint_event(sys_name, evt_name, - flags); - } else - return parse_single_tracepoint_event(sys_name, evt_name, - evt_length, attr, strp); + if (strpbrk(sys, "*?")) + return add_tracepoint_multi_sys(list, idx, sys, event); + else + return add_tracepoint_event(list, idx, sys, event); } -static enum event_result -parse_breakpoint_type(const char *type, const char **strp, - struct perf_event_attr *attr) +static int +parse_breakpoint_type(const char *type, struct perf_event_attr *attr) { int i; for (i = 0; i < 3; i++) { - if (!type[i]) + if (!type || !type[i]) break; +#define CHECK_SET_TYPE(bit) \ +do { \ + if (attr->bp_type & bit) \ + return -EINVAL; \ + else \ + attr->bp_type |= bit; \ +} while (0) + switch (type[i]) { case 'r': - attr->bp_type |= HW_BREAKPOINT_R; + CHECK_SET_TYPE(HW_BREAKPOINT_R); break; case 'w': - attr->bp_type |= HW_BREAKPOINT_W; + CHECK_SET_TYPE(HW_BREAKPOINT_W); break; case 'x': - attr->bp_type |= HW_BREAKPOINT_X; + CHECK_SET_TYPE(HW_BREAKPOINT_X); break; default: - return EVT_FAILED; + return -EINVAL; } } + +#undef CHECK_SET_TYPE + if (!attr->bp_type) /* Default */ attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W; - *strp = type + i; - - return EVT_HANDLED; + return 0; } -static enum event_result -parse_breakpoint_event(const char **strp, struct perf_event_attr *attr) +int parse_events_add_breakpoint(struct list_head *list, int *idx, + void *ptr, char *type) { - const char *target; - const char *type; - char *endaddr; - u64 addr; - enum event_result err; - - target = strchr(*strp, ':'); - if (!target) - return EVT_FAILED; - - if (strncmp(*strp, "mem", target - *strp) != 0) - return EVT_FAILED; - - target++; - - addr = strtoull(target, &endaddr, 0); - if (target == endaddr) - return EVT_FAILED; - - attr->bp_addr = addr; - *strp = endaddr; + struct perf_event_attr attr; - type = strchr(target, ':'); + memset(&attr, 0, sizeof(attr)); + attr.bp_addr = (unsigned long) ptr; - /* If no type is defined, just rw as default */ - if (!type) { - attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W; - } else { - err = parse_breakpoint_type(++type, strp, attr); - if (err == EVT_FAILED) - return EVT_FAILED; - } + if (parse_breakpoint_type(type, &attr)) + return -EINVAL; /* * We should find a nice way to override the access length * Provide some defaults for now */ - if (attr->bp_type == HW_BREAKPOINT_X) - attr->bp_len = sizeof(long); + if (attr.bp_type == HW_BREAKPOINT_X) + attr.bp_len = sizeof(long); else - attr->bp_len = HW_BREAKPOINT_LEN_4; + attr.bp_len = HW_BREAKPOINT_LEN_4; - attr->type = PERF_TYPE_BREAKPOINT; + attr.type = PERF_TYPE_BREAKPOINT; + attr.sample_period = 1; - return EVT_HANDLED; + return add_event(list, idx, &attr, NULL); } -static int check_events(const char *str, unsigned int i) +static int config_term(struct perf_event_attr *attr, + struct parse_events_term *term) { - int n; +#define CHECK_TYPE_VAL(type) \ +do { \ + if (PARSE_EVENTS__TERM_TYPE_ ## type != term->type_val) \ + return -EINVAL; \ +} while (0) + + switch (term->type_term) { + case PARSE_EVENTS__TERM_TYPE_CONFIG: + CHECK_TYPE_VAL(NUM); + attr->config = term->val.num; + break; + case PARSE_EVENTS__TERM_TYPE_CONFIG1: + CHECK_TYPE_VAL(NUM); + attr->config1 = term->val.num; + break; + case PARSE_EVENTS__TERM_TYPE_CONFIG2: + CHECK_TYPE_VAL(NUM); + attr->config2 = term->val.num; + break; + case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: + CHECK_TYPE_VAL(NUM); + attr->sample_period = term->val.num; + break; + case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: + /* + * TODO uncomment when the field is available + * attr->branch_sample_type = term->val.num; + */ + break; + case PARSE_EVENTS__TERM_TYPE_NAME: + CHECK_TYPE_VAL(STR); + break; + default: + return -EINVAL; + } + + return 0; +#undef CHECK_TYPE_VAL +} - n = strlen(event_symbols[i].symbol); - if (!strncmp(str, event_symbols[i].symbol, n)) - return n; +static int config_attr(struct perf_event_attr *attr, + struct list_head *head, int fail) +{ + struct parse_events_term *term; + + list_for_each_entry(term, head, list) + if (config_term(attr, term) && fail) + return -EINVAL; - n = strlen(event_symbols[i].alias); - if (n) - if (!strncmp(str, event_symbols[i].alias, n)) - return n; return 0; } -static enum event_result -parse_symbolic_event(const char **strp, struct perf_event_attr *attr) +int parse_events_add_numeric(struct list_head *list, int *idx, + u32 type, u64 config, + struct list_head *head_config) +{ + struct perf_event_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.type = type; + attr.config = config; + + if (head_config && + config_attr(&attr, head_config, 1)) + return -EINVAL; + + return add_event(list, idx, &attr, NULL); +} + +static int parse_events__is_name_term(struct parse_events_term *term) { - const char *str = *strp; - unsigned int i; - int n; + return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME; +} - for (i = 0; i < ARRAY_SIZE(event_symbols); i++) { - n = check_events(str, i); - if (n > 0) { - attr->type = event_symbols[i].type; - attr->config = event_symbols[i].config; - *strp = str + n; - return EVT_HANDLED; - } - } - return EVT_FAILED; +static char *pmu_event_name(struct list_head *head_terms) +{ + struct parse_events_term *term; + + list_for_each_entry(term, head_terms, list) + if (parse_events__is_name_term(term)) + return term->val.str; + + return NULL; } -static enum event_result -parse_raw_event(const char **strp, struct perf_event_attr *attr) +int parse_events_add_pmu(struct list_head *list, int *idx, + char *name, struct list_head *head_config) { - const char *str = *strp; - u64 config; - int n; + struct perf_event_attr attr; + struct perf_pmu *pmu; + struct perf_evsel *evsel; + const char *unit; + double scale; + + pmu = perf_pmu__find(name); + if (!pmu) + return -EINVAL; - if (*str != 'r') - return EVT_FAILED; - n = hex2u64(str + 1, &config); - if (n > 0) { - *strp = str + n + 1; - attr->type = PERF_TYPE_RAW; - attr->config = config; - return EVT_HANDLED; + memset(&attr, 0, sizeof(attr)); + + if (perf_pmu__check_alias(pmu, head_config, &unit, &scale)) + return -EINVAL; + + /* + * Configure hardcoded terms first, no need to check + * return value when called with fail == 0 ;) + */ + config_attr(&attr, head_config, 0); + + if (perf_pmu__config(pmu, &attr, head_config)) + return -EINVAL; + + evsel = __add_event(list, idx, &attr, pmu_event_name(head_config), + pmu->cpus); + if (evsel) { + evsel->unit = unit; + evsel->scale = scale; } - return EVT_FAILED; + + return evsel ? 0 : -ENOMEM; } -static enum event_result -parse_numeric_event(const char **strp, struct perf_event_attr *attr) +int parse_events__modifier_group(struct list_head *list, + char *event_mod) { - const char *str = *strp; - char *endp; - unsigned long type; - u64 config; + return parse_events__modifier_event(list, event_mod, true); +} - type = strtoul(str, &endp, 0); - if (endp > str && type < PERF_TYPE_MAX && *endp == ':') { - str = endp + 1; - config = strtoul(str, &endp, 0); - if (endp > str) { - attr->type = type; - attr->config = config; - *strp = endp; - return EVT_HANDLED; - } - } - return EVT_FAILED; +void parse_events__set_leader(char *name, struct list_head *list) +{ + struct perf_evsel *leader; + + __perf_evlist__set_leader(list); + leader = list_entry(list->next, struct perf_evsel, node); + leader->group_name = name ? strdup(name) : NULL; } -static enum event_result -parse_event_modifier(const char **strp, struct perf_event_attr *attr) +/* 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) { - const char *str = *strp; - int exclude = 0; - int eu = 0, ek = 0, eh = 0, precise = 0; + /* + * Called for single event definition. Update the + * 'all event' list, and reinit the 'single event' + * list, for next event definition. + */ + list_splice_tail(list_event, list_all); + free(list_event); +} + +struct event_modifier { + int eu; + int ek; + int eh; + int eH; + int eG; + int precise; + int exclude_GH; + int sample_read; + int pinned; +}; + +static int get_event_modifier(struct event_modifier *mod, char *str, + struct perf_evsel *evsel) +{ + int eu = evsel ? evsel->attr.exclude_user : 0; + int ek = evsel ? evsel->attr.exclude_kernel : 0; + int eh = evsel ? evsel->attr.exclude_hv : 0; + 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; + + memset(mod, 0, sizeof(*mod)); - if (*str++ != ':') - return 0; while (*str) { if (*str == 'u') { if (!exclude) @@ -713,148 +736,252 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr) if (!exclude) exclude = eu = ek = eh = 1; eh = 0; + } else if (*str == 'G') { + if (!exclude_GH) + exclude_GH = eG = eH = 1; + eG = 0; + } else if (*str == 'H') { + if (!exclude_GH) + exclude_GH = eG = eH = 1; + eH = 0; } else if (*str == 'p') { precise++; + /* 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; ++str; } - if (str >= *strp + 2) { - *strp = str; - attr->exclude_user = eu; - attr->exclude_kernel = ek; - attr->exclude_hv = eh; - attr->precise_ip = precise; - return 1; - } + + /* + * precise ip: + * + * 0 - SAMPLE_IP can have arbitrary skid + * 1 - SAMPLE_IP must have constant skid + * 2 - SAMPLE_IP requested to have 0 skid + * 3 - SAMPLE_IP must have 0 skid + * + * See also PERF_RECORD_MISC_EXACT_IP + */ + if (precise > 3) + return -EINVAL; + + mod->eu = eu; + mod->ek = ek; + mod->eh = eh; + mod->eH = eH; + mod->eG = eG; + mod->precise = precise; + mod->exclude_GH = exclude_GH; + mod->sample_read = sample_read; + mod->pinned = pinned; + return 0; } /* - * Each event can have multiple symbolic names. - * Symbolic names are (almost) exactly matched. + * Basic modifier sanity check to validate it contains only one + * instance of any modifier (apart from 'p') present. */ -static enum event_result -parse_event_symbols(const char **str, struct perf_event_attr *attr) +static int check_modifier(char *str) { - enum event_result ret; + char *p = str; - ret = parse_tracepoint_event(str, attr); - if (ret != EVT_FAILED) - goto modifier; + /* The sizeof includes 0 byte as well. */ + if (strlen(str) > (sizeof("ukhGHpppSD") - 1)) + return -1; - ret = parse_raw_event(str, attr); - if (ret != EVT_FAILED) - goto modifier; + while (*p) { + if (*p != 'p' && strchr(p + 1, *p)) + return -1; + p++; + } - ret = parse_numeric_event(str, attr); - if (ret != EVT_FAILED) - goto modifier; + return 0; +} - ret = parse_symbolic_event(str, attr); - if (ret != EVT_FAILED) - goto modifier; +int parse_events__modifier_event(struct list_head *list, char *str, bool add) +{ + struct perf_evsel *evsel; + struct event_modifier mod; - ret = parse_generic_hw_event(str, attr); - if (ret != EVT_FAILED) - goto modifier; + if (str == NULL) + return 0; - ret = parse_breakpoint_event(str, attr); - if (ret != EVT_FAILED) - goto modifier; + if (check_modifier(str)) + return -EINVAL; - fprintf(stderr, "invalid or unsupported event: '%s'\n", *str); - fprintf(stderr, "Run 'perf list' for a list of valid events\n"); - return EVT_FAILED; + if (!add && get_event_modifier(&mod, str, NULL)) + return -EINVAL; -modifier: - parse_event_modifier(str, attr); + __evlist__for_each(list, evsel) { + if (add && get_event_modifier(&mod, str, evsel)) + return -EINVAL; + + evsel->attr.exclude_user = mod.eu; + evsel->attr.exclude_kernel = mod.ek; + evsel->attr.exclude_hv = mod.eh; + evsel->attr.precise_ip = mod.precise; + 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 ret; + return 0; } -static int store_event_type(const char *orgname) +int parse_events_name(struct list_head *list, char *name) { - char filename[PATH_MAX], *c; - FILE *file; - int id, n; + struct perf_evsel *evsel; - sprintf(filename, "%s/", debugfs_path); - strncat(filename, orgname, strlen(orgname)); - strcat(filename, "/id"); + __evlist__for_each(list, evsel) { + if (!evsel->name) + evsel->name = strdup(name); + } - c = strchr(filename, ':'); - if (c) - *c = '/'; + return 0; +} - file = fopen(filename, "r"); - if (!file) - return 0; - n = fscanf(file, "%i", &id); - fclose(file); - if (n < 1) { - pr_err("cannot store event ID\n"); - return -EINVAL; +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, "/"); } - return perf_header__push_event(id, orgname); + free(o); + if (!s) + return -ENOMEM; + return parse_events__scanner(s, data, start_token); } -int parse_events(const struct option *opt __used, const char *str, int unset __used) +static int parse_events__scanner(const char *str, void *data, int start_token) { - struct perf_event_attr attr; - enum event_result ret; + YY_BUFFER_STATE buffer; + void *scanner; + int ret; + + ret = parse_events_lex_init_extra(start_token, &scanner); + if (ret) + return ret; + + buffer = parse_events__scan_string(str, scanner); + +#ifdef PARSER_DEBUG + parse_events_debug = 1; +#endif + ret = parse_events_parse(data, scanner); + + 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; +} - if (strchr(str, ':')) - if (store_event_type(str) < 0) - return -1; +/* + * parse event config string, return a list of event terms. + */ +int parse_events_terms(struct list_head *terms, const char *str) +{ + struct parse_events_terms data = { + .terms = NULL, + }; + int ret; + + ret = parse_events__scanner(str, &data, PE_START_TERMS); + if (!ret) { + list_splice(data.terms, terms); + zfree(&data.terms); + return 0; + } - for (;;) { - if (nr_counters == MAX_COUNTERS) - return -1; + if (data.terms) + parse_events__free_terms(data.terms); + return ret; +} - memset(&attr, 0, sizeof(attr)); - ret = parse_event_symbols(&str, &attr); - if (ret == EVT_FAILED) - return -1; +int parse_events(struct perf_evlist *evlist, const char *str) +{ + struct parse_events_evlist data = { + .list = LIST_HEAD_INIT(data.list), + .idx = evlist->nr_entries, + }; + int ret; + + ret = parse_events__scanner(str, &data, PE_START_EVENTS); + if (!ret) { + int entries = data.idx - evlist->nr_entries; + perf_evlist__splice_list_tail(evlist, &data.list, entries); + evlist->nr_groups += data.nr_groups; + return 0; + } - if (!(*str == 0 || *str == ',' || isspace(*str))) - return -1; + /* + * There are 2 users - builtin-record and builtin-test objects. + * Both call perf_evlist__delete in case of error, so we dont + * need to bother. + */ + return ret; +} - if (ret != EVT_HANDLED_ALL) { - attrs[nr_counters] = attr; - nr_counters++; - } +int parse_events_option(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; + int ret = parse_events(evlist, str); - if (*str == 0) - break; - if (*str == ',') - ++str; - while (isspace(*str)) - ++str; + if (ret) { + fprintf(stderr, "invalid or unsupported event: '%s'\n", str); + fprintf(stderr, "Run 'perf list' for a list of valid events\n"); } - - return 0; + return ret; } -int parse_filter(const struct option *opt __used, const char *str, - int unset __used) +int parse_filter(const struct option *opt, const char *str, + int unset __maybe_unused) { - int i = nr_counters - 1; - int len = strlen(str); + struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; + struct perf_evsel *last = NULL; + + if (evlist->nr_entries > 0) + last = perf_evlist__last(evlist); - if (i < 0 || attrs[i].type != PERF_TYPE_TRACEPOINT) { + if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) { fprintf(stderr, "-F option should follow a -e tracepoint option\n"); return -1; } - filters[i] = malloc(len + 1); - if (!filters[i]) { + last->filter = strdup(str); + if (last->filter == NULL) { fprintf(stderr, "not enough memory to hold filter string\n"); return -1; } - strcpy(filters[i], str); return 0; } @@ -872,32 +999,47 @@ static const char * const event_type_descriptors[] = { * Print the events from <debugfs_mount_point>/tracing/events */ -static void print_tracepoint_events(void) +void print_tracepoint_events(const char *subsys_glob, const char *event_glob, + bool name_only) { DIR *sys_dir, *evt_dir; struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(debugfs_path)) + if (debugfs_valid_mountpoint(tracing_events_path)) { + printf(" [ Tracepoints not available: %s ]\n", strerror(errno)); return; + } - sys_dir = opendir(debugfs_path); + sys_dir = opendir(tracing_events_path); if (!sys_dir) return; for_each_subsystem(sys_dir, sys_dirent, sys_next) { + if (subsys_glob != NULL && + !strglobmatch(sys_dirent.d_name, subsys_glob)) + continue; - snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path, + snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_dirent.d_name); evt_dir = opendir(dir_path); if (!evt_dir) continue; for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + if (event_glob != NULL && + !strglobmatch(evt_dirent.d_name, event_glob)) + continue; + + if (name_only) { + printf("%s:%s ", sys_dirent.d_name, evt_dirent.d_name); + continue; + } + snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent.d_name, evt_dirent.d_name); - printf(" %-42s [%s]\n", evt_path, + printf(" %-50s [%s]\n", evt_path, event_type_descriptors[PERF_TYPE_TRACEPOINT]); } closedir(evt_dir); @@ -906,60 +1048,307 @@ static void print_tracepoint_events(void) } /* - * Print the help text for the event symbols: + * Check whether event is in <debugfs_mount_point>/tracing/events */ -void print_events(void) + +int is_valid_tracepoint(const char *event_string) { - struct event_symbol *syms = event_symbols; - unsigned int i, type, op, prev_type = -1; - char name[40]; + DIR *sys_dir, *evt_dir; + struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; + char evt_path[MAXPATHLEN]; + char dir_path[MAXPATHLEN]; - printf("\n"); - printf("List of pre-defined events (to be used in -e):\n"); + if (debugfs_valid_mountpoint(tracing_events_path)) + return 0; - for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) { - type = syms->type; + sys_dir = opendir(tracing_events_path); + if (!sys_dir) + return 0; - if (type != prev_type) - printf("\n"); + for_each_subsystem(sys_dir, sys_dirent, sys_next) { + + snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, + sys_dirent.d_name); + evt_dir = opendir(dir_path); + if (!evt_dir) + continue; + + for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + snprintf(evt_path, MAXPATHLEN, "%s:%s", + sys_dirent.d_name, evt_dirent.d_name); + if (!strcmp(evt_path, event_string)) { + closedir(evt_dir); + closedir(sys_dir); + return 1; + } + } + closedir(evt_dir); + } + closedir(sys_dir); + return 0; +} + +static bool is_event_supported(u8 type, unsigned config) +{ + bool ret = true; + int open_return; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = type, + .config = config, + .disabled = 1, + }; + struct { + struct thread_map map; + int threads[1]; + } tmap = { + .map.nr = 1, + .threads = { 0 }, + }; + + evsel = perf_evsel__new(&attr); + if (evsel) { + open_return = perf_evsel__open(evsel, NULL, &tmap.map); + ret = open_return >= 0; + + if (open_return == -EACCES) { + /* + * This happens if the paranoid value + * /proc/sys/kernel/perf_event_paranoid is set to 2 + * Re-run with exclude_kernel set; we don't do that + * by default as some ARM machines do not support it. + * + */ + evsel->attr.exclude_kernel = 1; + 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) +{ + char name[64]; + unsigned i; + + for (i = 0; i < max ; i++, syms++) { + if (!is_event_supported(type, i)) + continue; if (strlen(syms->alias)) - sprintf(name, "%s OR %s", syms->symbol, syms->alias); + snprintf(name, sizeof(name), "%s OR %s", + syms->symbol, syms->alias); else - strcpy(name, syms->symbol); - printf(" %-42s [%s]\n", name, - event_type_descriptors[type]); + snprintf(name, sizeof(name), "%s", syms->symbol); - prev_type = type; + printf(" %-50s [%s]\n", name, event_type_descriptors[type]); } +} + +void print_events_type(u8 type) +{ + if (type == PERF_TYPE_SOFTWARE) + __print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX); + else + __print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX); +} + +int print_hwcache_events(const char *event_glob, bool name_only) +{ + unsigned int type, op, i, printed = 0; + char name[64]; - printf("\n"); for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { /* skip invalid cache type */ - if (!is_cache_op_valid(type, op)) + if (!perf_evsel__is_cache_op_valid(type, op)) continue; for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - printf(" %-42s [%s]\n", - event_cache_name(type, op, i), - event_type_descriptors[PERF_TYPE_HW_CACHE]); + __perf_evsel__hw_cache_type_op_res_name(type, op, i, + name, sizeof(name)); + 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 + printf(" %-50s [%s]\n", name, + event_type_descriptors[PERF_TYPE_HW_CACHE]); + ++printed; } } } - printf("\n"); - printf(" %-42s [%s]\n", - "rNNN (see 'perf list --help' on how to encode it)", - event_type_descriptors[PERF_TYPE_RAW]); - printf("\n"); + if (printed) + printf("\n"); + return printed; +} + +static void print_symbol_events(const char *event_glob, unsigned type, + struct event_symbol *syms, unsigned max, + bool name_only) +{ + unsigned i, printed = 0; + char name[MAX_NAME_LEN]; - printf(" %-42s [%s]\n", - "mem:<addr>[:access]", + for (i = 0; i < max; i++, syms++) { + + if (event_glob != NULL && + !(strglobmatch(syms->symbol, event_glob) || + (syms->alias && strglobmatch(syms->alias, event_glob)))) + continue; + + if (!is_event_supported(type, i)) + continue; + + if (name_only) { + printf("%s ", syms->symbol); + continue; + } + + if (strlen(syms->alias)) + snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias); + else + strncpy(name, syms->symbol, MAX_NAME_LEN); + + printf(" %-50s [%s]\n", name, event_type_descriptors[type]); + + printed++; + } + + if (printed) + printf("\n"); +} + +/* + * Print the help text for the event symbols: + */ +void print_events(const char *event_glob, bool name_only) +{ + if (!name_only) { + printf("\n"); + printf("List of pre-defined events (to be used in -e):\n"); + } + + print_symbol_events(event_glob, PERF_TYPE_HARDWARE, + event_symbols_hw, PERF_COUNT_HW_MAX, name_only); + + print_symbol_events(event_glob, PERF_TYPE_SOFTWARE, + event_symbols_sw, PERF_COUNT_SW_MAX, 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(" %-50s [%s]\n", + "rNNN", + event_type_descriptors[PERF_TYPE_RAW]); + printf(" %-50s [%s]\n", + "cpu/t1=v1[,t2=v2,t3 ...]/modifier", + event_type_descriptors[PERF_TYPE_RAW]); + printf(" (see 'man perf-list' on how to encode it)\n"); + printf("\n"); + + printf(" %-50s [%s]\n", + "mem:<addr>[:access]", event_type_descriptors[PERF_TYPE_BREAKPOINT]); - printf("\n"); + printf("\n"); + } + + print_tracepoint_events(NULL, NULL, name_only); +} + +int parse_events__is_hardcoded_term(struct parse_events_term *term) +{ + return term->type_term != PARSE_EVENTS__TERM_TYPE_USER; +} + +static int new_term(struct parse_events_term **_term, int type_val, + int type_term, char *config, + char *str, u64 num) +{ + struct parse_events_term *term; + + term = zalloc(sizeof(*term)); + if (!term) + return -ENOMEM; + + INIT_LIST_HEAD(&term->list); + term->type_val = type_val; + term->type_term = type_term; + term->config = config; + + switch (type_val) { + case PARSE_EVENTS__TERM_TYPE_NUM: + term->val.num = num; + break; + case PARSE_EVENTS__TERM_TYPE_STR: + term->val.str = str; + break; + default: + free(term); + return -EINVAL; + } + + *_term = term; + return 0; +} + +int parse_events_term__num(struct parse_events_term **term, + int type_term, char *config, u64 num) +{ + return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term, + config, NULL, num); +} + +int parse_events_term__str(struct parse_events_term **term, + int type_term, char *config, char *str) +{ + return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term, + config, str, 0); +} - print_tracepoint_events(); +int parse_events_term__sym_hw(struct parse_events_term **term, + char *config, unsigned idx) +{ + struct event_symbol *sym; + + BUG_ON(idx >= PERF_COUNT_HW_MAX); + sym = &event_symbols_hw[idx]; + + if (config) + return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, + PARSE_EVENTS__TERM_TYPE_USER, config, + (char *) sym->symbol, 0); + else + return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, + PARSE_EVENTS__TERM_TYPE_USER, + (char *) "event", (char *) sym->symbol, 0); +} + +int parse_events_term__clone(struct parse_events_term **new, + struct parse_events_term *term) +{ + return new_term(new, term->type_val, term->type_term, term->config, + term->val.str, term->val.num); +} + +void parse_events__free_terms(struct list_head *terms) +{ + struct parse_events_term *term, *h; - exit(129); + list_for_each_entry_safe(term, h, terms, list) + free(term); } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index fc4ab3fe877..df094b4ed5e 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -4,6 +4,15 @@ * Parse symbolic events/counts passed in as options: */ +#include <linux/list.h> +#include <stdbool.h> +#include <linux/types.h> +#include <linux/perf_event.h> + +struct list_head; +struct perf_evsel; +struct perf_evlist; + struct option; struct tracepoint_path { @@ -13,25 +22,91 @@ struct tracepoint_path { }; extern struct tracepoint_path *tracepoint_id_to_path(u64 config); -extern bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events); - -extern int nr_counters; - -extern struct perf_event_attr attrs[MAX_COUNTERS]; -extern char *filters[MAX_COUNTERS]; +extern struct tracepoint_path *tracepoint_name_to_path(const char *name); +extern bool have_tracepoints(struct list_head *evlist); -extern const char *event_name(int ctr); -extern const char *__event_name(int type, u64 config); +const char *event_type(int type); -extern int parse_events(const struct option *opt, const char *str, int unset); +extern int parse_events_option(const struct option *opt, const char *str, + int unset); +extern int parse_events(struct perf_evlist *evlist, const char *str); +extern int parse_events_terms(struct list_head *terms, const char *str); extern int parse_filter(const struct option *opt, const char *str, int unset); #define EVENTS_HELP_MAX (128*1024) -extern void print_events(void); +enum { + PARSE_EVENTS__TERM_TYPE_NUM, + PARSE_EVENTS__TERM_TYPE_STR, +}; -extern char debugfs_path[]; -extern int valid_debugfs_mount(const char *debugfs); +enum { + PARSE_EVENTS__TERM_TYPE_USER, + PARSE_EVENTS__TERM_TYPE_CONFIG, + PARSE_EVENTS__TERM_TYPE_CONFIG1, + PARSE_EVENTS__TERM_TYPE_CONFIG2, + PARSE_EVENTS__TERM_TYPE_NAME, + PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD, + PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE, +}; + +struct parse_events_term { + char *config; + union { + char *str; + u64 num; + } val; + int type_val; + int type_term; + struct list_head list; +}; + +struct parse_events_evlist { + struct list_head list; + int idx; + int nr_groups; +}; + +struct parse_events_terms { + struct list_head *terms; +}; + +int parse_events__is_hardcoded_term(struct parse_events_term *term); +int parse_events_term__num(struct parse_events_term **_term, + int type_term, char *config, u64 num); +int parse_events_term__str(struct parse_events_term **_term, + int type_term, char *config, char *str); +int parse_events_term__sym_hw(struct parse_events_term **term, + char *config, unsigned idx); +int parse_events_term__clone(struct parse_events_term **new, + struct parse_events_term *term); +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, + char *sys, char *event); +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, + char *type, char *op_result1, char *op_result2); +int parse_events_add_breakpoint(struct list_head *list, int *idx, + void *ptr, char *type); +int parse_events_add_pmu(struct list_head *list, int *idx, + char *pmu , struct list_head *head_config); +void parse_events__set_leader(char *name, struct list_head *list); +void parse_events_update_lists(struct list_head *list_event, + struct list_head *list_all); +void parse_events_error(void *data, void *scanner, char const *msg); +void print_events(const char *event_glob, bool name_only); +void print_events_type(u8 type); +void print_tracepoint_events(const char *subsys_glob, const char *event_glob, + bool name_only); +int print_hwcache_events(const char *event_glob, bool name_only); +extern int is_valid_tracepoint(const char *event_string); + +extern int valid_debugfs_mount(const char *debugfs); #endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l new file mode 100644 index 00000000000..343299575b3 --- /dev/null +++ b/tools/perf/util/parse-events.l @@ -0,0 +1,218 @@ + +%option reentrant +%option bison-bridge +%option prefix="parse_events_" +%option stack + +%{ +#include <errno.h> +#include "../perf.h" +#include "parse-events-bison.h" +#include "parse-events.h" + +char *parse_events_get_text(yyscan_t yyscanner); +YYSTYPE *parse_events_get_lval(yyscan_t yyscanner); + +static int __value(YYSTYPE *yylval, char *str, int base, int token) +{ + u64 num; + + errno = 0; + num = strtoull(str, NULL, base); + if (errno) + return PE_ERROR; + + yylval->num = num; + return token; +} + +static int value(yyscan_t scanner, int base) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + return __value(yylval, text, base, PE_VALUE); +} + +static int raw(yyscan_t scanner) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + return __value(yylval, text + 1, 16, PE_RAW); +} + +static int str(yyscan_t scanner, int token) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + yylval->str = strdup(text); + return token; +} + +static int sym(yyscan_t scanner, int type, int config) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + + yylval->num = (type << 16) + config; + return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW; +} + +static int term(yyscan_t scanner, int type) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + + yylval->num = type; + return PE_TERM; +} + +%} + +%x mem +%s config +%x event + +group [^,{}/]*[{][^}]*[}][^,{}/]* +event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* +event [^,{}/]+ + +num_dec [0-9]+ +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\-_*?]* +/* If you add a modifier you need to update check_modifier() */ +modifier_event [ukhpGHSD]+ +modifier_bp [rwx]{1,3} + +%% + +%{ + { + int start_token; + + start_token = parse_events_get_extra(yyscanner); + + if (start_token == PE_START_TERMS) + BEGIN(config); + else if (start_token == PE_START_EVENTS) + BEGIN(event); + + if (start_token) { + parse_events_set_extra(NULL, yyscanner); + return start_token; + } + } +%} + +<event>{ + +{group} { + BEGIN(INITIAL); yyless(0); + } + +{event_pmu} | +{event} { + str(yyscanner, PE_EVENT_NAME); + BEGIN(INITIAL); yyless(0); + return PE_EVENT_NAME; + } + +. | +<<EOF>> { + BEGIN(INITIAL); yyless(0); + } + +} + +<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); } +instructions { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); } +cache-references { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); } +cache-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); } +branch-instructions|branches { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } +branch-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); } +bus-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); } +ref-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); } +cpu-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); } +task-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); } +page-faults|faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); } +minor-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); } +major-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); } +context-switches|cs { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); } +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 | +LLC|L2 | +dTLB|d-tlb|Data-TLB | +iTLB|i-tlb|Instruction-TLB | +branch|branches|bpu|btb|bpc | +node { return str(yyscanner, PE_NAME_CACHE_TYPE); } + +load|loads|read | +store|stores|write | +prefetch|prefetches | +speculative-read|speculative-load | +refs|Reference|ops|access | +misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); } + +mem: { BEGIN(mem); return PE_PREFIX_MEM; } +r{num_raw_hex} { return raw(yyscanner); } +{num_dec} { return value(yyscanner, 10); } +{num_hex} { return value(yyscanner, 16); } + +{modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } +{name} { return str(yyscanner, PE_NAME); } +"/" { BEGIN(config); return '/'; } +- { return '-'; } +, { BEGIN(event); return ','; } +: { return ':'; } +"{" { BEGIN(event); return '{'; } +"}" { return '}'; } += { return '='; } +\n { } +. { } + +%% + +int parse_events_wrap(void *scanner __maybe_unused) +{ + return 1; +} diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y new file mode 100644 index 00000000000..0bc87ba46bf --- /dev/null +++ b/tools/perf/util/parse-events.y @@ -0,0 +1,454 @@ +%pure-parser +%parse-param {void *_data} +%parse-param {void *scanner} +%lex-param {void* scanner} + +%{ + +#define YYDEBUG 1 + +#include <linux/compiler.h> +#include <linux/list.h> +#include <linux/types.h> +#include "util.h" +#include "parse-events.h" +#include "parse-events-bison.h" + +extern int parse_events_lex (YYSTYPE* lvalp, void* scanner); + +#define ABORT_ON(val) \ +do { \ + if (val) \ + 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) +{ + /* Count groups only have more than 1 members */ + if (!list_is_last(list->next, list)) + data->nr_groups++; +} + +%} + +%token PE_START_EVENTS PE_START_TERMS +%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM +%token PE_EVENT_NAME +%token PE_NAME +%token PE_MODIFIER_EVENT PE_MODIFIER_BP +%token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT +%token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP +%token PE_ERROR +%type <num> PE_VALUE +%type <num> PE_VALUE_SYM_HW +%type <num> PE_VALUE_SYM_SW +%type <num> PE_RAW +%type <num> PE_TERM +%type <str> PE_NAME +%type <str> PE_NAME_CACHE_TYPE +%type <str> PE_NAME_CACHE_OP_RESULT +%type <str> PE_MODIFIER_EVENT +%type <str> PE_MODIFIER_BP +%type <str> PE_EVENT_NAME +%type <num> value_sym +%type <head> event_config +%type <term> event_term +%type <head> event_pmu +%type <head> event_legacy_symbol +%type <head> event_legacy_cache +%type <head> event_legacy_mem +%type <head> event_legacy_tracepoint +%type <head> event_legacy_numeric +%type <head> event_legacy_raw +%type <head> event_def +%type <head> event_mod +%type <head> event_name +%type <head> event +%type <head> events +%type <head> group_def +%type <head> group +%type <head> groups + +%union +{ + char *str; + u64 num; + struct list_head *head; + struct parse_events_term *term; +} +%% + +start: +PE_START_EVENTS start_events +| +PE_START_TERMS start_terms + +start_events: groups +{ + struct parse_events_evlist *data = _data; + + parse_events_update_lists($1, &data->list); +} + +groups: +groups ',' group +{ + struct list_head *list = $1; + struct list_head *group = $3; + + parse_events_update_lists(group, list); + $$ = list; +} +| +groups ',' event +{ + struct list_head *list = $1; + struct list_head *event = $3; + + parse_events_update_lists(event, list); + $$ = list; +} +| +group +| +event + +group: +group_def ':' PE_MODIFIER_EVENT +{ + struct list_head *list = $1; + + ABORT_ON(parse_events__modifier_group(list, $3)); + $$ = list; +} +| +group_def + +group_def: +PE_NAME '{' events '}' +{ + struct list_head *list = $3; + + inc_group_count(list, _data); + parse_events__set_leader($1, list); + $$ = list; +} +| +'{' events '}' +{ + struct list_head *list = $2; + + inc_group_count(list, _data); + parse_events__set_leader(NULL, list); + $$ = list; +} + +events: +events ',' event +{ + struct list_head *event = $3; + struct list_head *list = $1; + + parse_events_update_lists(event, list); + $$ = list; +} +| +event + +event: event_mod + +event_mod: +event_name PE_MODIFIER_EVENT +{ + struct list_head *list = $1; + + /* + * Apply modifier on all events added by single event definition + * (there could be more events added for multiple tracepoint + * definitions via '*?'. + */ + ABORT_ON(parse_events__modifier_event(list, $2, false)); + $$ = list; +} +| +event_name + +event_name: +PE_EVENT_NAME event_def +{ + ABORT_ON(parse_events_name($2, $1)); + free($1); + $$ = $2; +} +| +event_def + +event_def: event_pmu | + event_legacy_symbol | + event_legacy_cache sep_dc | + event_legacy_mem | + event_legacy_tracepoint sep_dc | + event_legacy_numeric sep_dc | + event_legacy_raw sep_dc + +event_pmu: +PE_NAME '/' event_config '/' +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3)); + parse_events__free_terms($3); + $$ = list; +} + +value_sym: +PE_VALUE_SYM_HW +| +PE_VALUE_SYM_SW + +event_legacy_symbol: +value_sym '/' event_config '/' +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + int type = $1 >> 16; + int config = $1 & 255; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, + type, config, $3)); + parse_events__free_terms($3); + $$ = list; +} +| +value_sym sep_slash_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + int type = $1 >> 16; + int config = $1 & 255; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, + type, config, NULL)); + $$ = list; +} + +event_legacy_cache: +PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5)); + $$ = list; +} +| +PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL)); + $$ = list; +} +| +PE_NAME_CACHE_TYPE +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL)); + $$ = list; +} + +event_legacy_mem: +PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + (void *) $2, $4)); + $$ = list; +} +| +PE_PREFIX_MEM PE_VALUE sep_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + (void *) $2, NULL)); + $$ = list; +} + +event_legacy_tracepoint: +PE_NAME '-' PE_NAME ':' PE_NAME +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + char sys_name[128]; + snprintf(&sys_name, 128, "%s-%s", $1, $3); + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_tracepoint(list, &data->idx, &sys_name, $5)); + $$ = list; +} +| +PE_NAME ':' PE_NAME +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3)); + $$ = list; +} + +event_legacy_numeric: +PE_VALUE ':' PE_VALUE +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL)); + $$ = list; +} + +event_legacy_raw: +PE_RAW +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, + PERF_TYPE_RAW, $1, NULL)); + $$ = list; +} + +start_terms: event_config +{ + struct parse_events_terms *data = _data; + data->terms = $1; +} + +event_config: +event_config ',' event_term +{ + struct list_head *head = $1; + struct parse_events_term *term = $3; + + ABORT_ON(!head); + list_add_tail(&term->list, head); + $$ = $1; +} +| +event_term +{ + struct list_head *head = malloc(sizeof(*head)); + struct parse_events_term *term = $1; + + ABORT_ON(!head); + INIT_LIST_HEAD(head); + list_add_tail(&term->list, head); + $$ = head; +} + +event_term: +PE_NAME '=' PE_NAME +{ + struct parse_events_term *term; + + ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3)); + $$ = term; +} +| +PE_NAME '=' PE_VALUE +{ + struct parse_events_term *term; + + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3)); + $$ = term; +} +| +PE_NAME '=' PE_VALUE_SYM_HW +{ + struct parse_events_term *term; + int config = $3 & 255; + + ABORT_ON(parse_events_term__sym_hw(&term, $1, config)); + $$ = term; +} +| +PE_NAME +{ + struct parse_events_term *term; + + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, 1)); + $$ = term; +} +| +PE_VALUE_SYM_HW +{ + struct parse_events_term *term; + int config = $1 & 255; + + ABORT_ON(parse_events_term__sym_hw(&term, NULL, config)); + $$ = term; +} +| +PE_TERM '=' PE_NAME +{ + struct parse_events_term *term; + + ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3)); + $$ = term; +} +| +PE_TERM '=' PE_VALUE +{ + struct parse_events_term *term; + + ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3)); + $$ = term; +} +| +PE_TERM +{ + struct parse_events_term *term; + + ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1)); + $$ = term; +} + +sep_dc: ':' | + +sep_slash_dc: '/' | ':' | + +%% + +void parse_events_error(void *data __maybe_unused, void *scanner __maybe_unused, + char const *msg __maybe_unused) +{ +} diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 99d02aa57db..bf48092983c 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -1,6 +1,7 @@ #include "util.h" #include "parse-options.h" #include "cache.h" +#include "header.h" #define OPT_SHORT 1 #define OPT_UNSET 2 @@ -77,6 +78,8 @@ static int get_value(struct parse_opt_ctx_t *p, case OPTION_BOOLEAN: *(bool *)opt->value = unset ? false : true; + if (opt->set) + *(bool *)opt->set = true; return 0; case OPTION_INCR: @@ -223,6 +226,24 @@ static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg, return 0; } if (!rest) { + if (!prefixcmp(options->long_name, "no-")) { + /* + * The long name itself starts with "no-", so + * accept the option without "no-" so that users + * do not have to enter "no-no-" to get the + * negation. + */ + rest = skip_prefix(arg, options->long_name + 3); + if (rest) { + flags |= OPT_UNSET; + goto match; + } + /* Abbreviated case */ + if (!prefixcmp(options->long_name + 3, arg)) { + flags |= OPT_UNSET; + goto is_abbreviated; + } + } /* abbreviated? */ if (!strncmp(options->long_name, arg, arg_end - arg)) { is_abbreviated: @@ -258,6 +279,7 @@ is_abbreviated: if (!rest) continue; } +match: if (*rest) { if (*rest != '=') continue; @@ -338,10 +360,10 @@ 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: @@ -351,10 +373,11 @@ 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 @@ -382,10 +405,14 @@ 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_OPTS; + if (!strcmp(arg + 2, "list-cmds")) + return PARSE_OPT_LIST_SUBCMDS; 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: @@ -408,17 +435,45 @@ int parse_options_end(struct parse_opt_ctx_t *ctx) return ctx->cpidx + ctx->argc; } -int parse_options(int argc, const char **argv, const struct option *options, - const char * const usagestr[], int flags) +int parse_options_subcommand(int argc, const char **argv, const struct option *options, + const char *const subcommands[], const char *usagestr[], int flags) { struct parse_opt_ctx_t ctx; + perf_header__set_cmdline(argc, argv); + + /* build usage string if it's not provided */ + if (subcommands && !usagestr[0]) { + struct strbuf buf = STRBUF_INIT; + + strbuf_addf(&buf, "perf %s [<options>] {", argv[0]); + for (int i = 0; subcommands[i]; i++) { + if (i) + strbuf_addstr(&buf, "|"); + strbuf_addstr(&buf, subcommands[i]); + } + strbuf_addstr(&buf, "}"); + + usagestr[0] = strdup(buf.buf); + strbuf_release(&buf); + } + parse_options_start(&ctx, argc, argv, flags); switch (parse_options_step(&ctx, options, usagestr)) { case PARSE_OPT_HELP: exit(129); case PARSE_OPT_DONE: break; + case PARSE_OPT_LIST_OPTS: + while (options->type != OPTION_END) { + printf("--%s ", options->long_name); + options++; + } + exit(130); + case PARSE_OPT_LIST_SUBCMDS: + for (int i = 0; subcommands[i]; i++) + printf("%s ", subcommands[i]); + exit(130); default: /* PARSE_OPT_UNKNOWN */ if (ctx.argv[0][1] == '-') { error("unknown option `%s'", ctx.argv[0] + 2); @@ -431,9 +486,99 @@ int parse_options(int argc, const char **argv, const struct option *options, return parse_options_end(&ctx); } +int parse_options(int argc, const char **argv, const struct option *options, + const char * const usagestr[], int flags) +{ + return parse_options_subcommand(argc, argv, options, NULL, + (const char **) usagestr, flags); +} + #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) { @@ -453,87 +598,9 @@ 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; + for ( ; opts->type != OPTION_END; opts++) + print_option_help(opts, full); - 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; - } - - 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; @@ -548,13 +615,50 @@ 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; } -int parse_opt_verbosity_cb(const struct option *opt, const char *arg __used, +int parse_opt_verbosity_cb(const struct option *opt, + const char *arg __maybe_unused, int unset) { int *target = opt->value; diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index c7d72dce54b..d8dac8ac5f3 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -82,6 +82,9 @@ typedef int parse_opt_cb(const struct option *, const char *arg, int unset); * OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in * the value when met. * CALLBACKS can use it like they want. + * + * `set`:: + * whether an option was set by the user */ struct option { enum parse_opt_type type; @@ -94,6 +97,7 @@ struct option { int flags; parse_opt_cb *callback; intptr_t defval; + bool *set; }; #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v ) @@ -103,6 +107,10 @@ struct option { #define OPT_GROUP(h) { .type = OPTION_GROUP, .help = (h) } #define OPT_BIT(s, l, v, h, b) { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) } #define OPT_BOOLEAN(s, l, v, h) { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) } +#define OPT_BOOLEAN_SET(s, l, v, os, h) \ + { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), \ + .value = check_vtype(v, bool *), .help = (h), \ + .set = check_vtype(os, bool *)} #define OPT_INCR(s, l, v, h) { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) } #define OPT_SET_UINT(s, l, v, h, i) { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) } #define OPT_SET_PTR(s, l, v, h, p) { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) } @@ -119,6 +127,10 @@ struct option { { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG } #define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT } +#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\ + .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\ + .flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG} /* parse_options() will filter out the processed options and leave the * non-option argments in argv[]. @@ -128,6 +140,11 @@ extern int parse_options(int argc, const char **argv, const struct option *options, const char * const usagestr[], int flags); +extern int parse_options_subcommand(int argc, const char **argv, + const struct option *options, + const char *const subcommands[], + const char *usagestr[], int flags); + extern NORETURN void usage_with_options(const char * const *usagestr, const struct option *options); @@ -136,6 +153,8 @@ extern NORETURN void usage_with_options(const char * const *usagestr, enum { PARSE_OPT_HELP = -1, PARSE_OPT_DONE, + PARSE_OPT_LIST_OPTS, + PARSE_OPT_LIST_SUBCMDS, PARSE_OPT_UNKNOWN, }; @@ -153,7 +172,9 @@ 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 bd749771142..5d13cb45b31 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 "."; } -#ifdef NO_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.c b/tools/perf/util/perf_regs.c new file mode 100644 index 00000000000..43168fb0d9a --- /dev/null +++ b/tools/perf/util/perf_regs.c @@ -0,0 +1,27 @@ +#include <errno.h> +#include "perf_regs.h" +#include "event.h" + +int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) +{ + int i, idx = 0; + u64 mask = regs->mask; + + if (regs->cache_mask & (1 << id)) + goto out; + + if (!(mask & (1 << id))) + return -EINVAL; + + for (i = 0; i < id; i++) { + if (mask & (1 << i)) + idx++; + } + + regs->cache_mask |= (1 << id); + regs->cache_regs[id] = regs->regs[idx]; + +out: + *valp = regs->cache_regs[id]; + return 0; +} diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h new file mode 100644 index 00000000000..980dbf76bc9 --- /dev/null +++ b/tools/perf/util/perf_regs.h @@ -0,0 +1,29 @@ +#ifndef __PERF_REGS_H +#define __PERF_REGS_H + +#include <linux/types.h> + +struct regs_dump; + +#ifdef HAVE_PERF_REGS_SUPPORT +#include <perf_regs.h> + +int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); + +#else +#define PERF_REGS_MASK 0 +#define PERF_REGS_MAX 0 + +static inline const char *perf_reg_name(int id __maybe_unused) +{ + return NULL; +} + +static inline int perf_reg_value(u64 *valp __maybe_unused, + struct regs_dump *regs __maybe_unused, + int id __maybe_unused) +{ + return 0; +} +#endif /* HAVE_PERF_REGS_SUPPORT */ +#endif /* __PERF_REGS_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c new file mode 100644 index 00000000000..7a811eb61f7 --- /dev/null +++ b/tools/perf/util/pmu.c @@ -0,0 +1,796 @@ +#include <linux/list.h> +#include <sys/types.h> +#include <unistd.h> +#include <stdio.h> +#include <dirent.h> +#include <api/fs/fs.h> +#include <locale.h> +#include "util.h" +#include "pmu.h" +#include "parse-events.h" +#include "cpumap.h" + +#define UNIT_MAX_LEN 31 /* max length for event unit name */ + +struct perf_pmu_alias { + char *name; + struct list_head terms; + struct list_head list; + char unit[UNIT_MAX_LEN+1]; + double scale; +}; + +struct perf_pmu_format { + char *name; + int value; + DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS); + struct list_head list; +}; + +#define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/" + +int perf_pmu_parse(struct list_head *list, char *name); +extern FILE *perf_pmu_in; + +static LIST_HEAD(pmus); + +/* + * Parse & process all the sysfs attributes located under + * the directory specified in 'dir' parameter. + */ +int perf_pmu__format_parse(char *dir, struct list_head *head) +{ + struct dirent *evt_ent; + DIR *format_dir; + int ret = 0; + + format_dir = opendir(dir); + if (!format_dir) + return -EINVAL; + + while (!ret && (evt_ent = readdir(format_dir))) { + char path[PATH_MAX]; + char *name = evt_ent->d_name; + FILE *file; + + if (!strcmp(name, ".") || !strcmp(name, "..")) + continue; + + snprintf(path, PATH_MAX, "%s/%s", dir, name); + + ret = -EINVAL; + file = fopen(path, "r"); + if (!file) + break; + + perf_pmu_in = file; + ret = perf_pmu_parse(head, name); + fclose(file); + } + + closedir(format_dir); + return ret; +} + +/* + * Reading/parsing the default pmu format definition, which should be + * located at: + * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes. + */ +static int pmu_format(const char *name, struct list_head *format) +{ + struct stat st; + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + snprintf(path, PATH_MAX, + "%s" EVENT_SOURCE_DEVICE_PATH "%s/format", sysfs, name); + + if (stat(path, &st) < 0) + return 0; /* no error if format does not exist */ + + if (perf_pmu__format_parse(path, format)) + return -1; + + return 0; +} + +static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name) +{ + struct stat st; + ssize_t sret; + char scale[128]; + int fd, ret = -1; + char path[PATH_MAX]; + const char *lc; + + snprintf(path, PATH_MAX, "%s/%s.scale", dir, name); + + fd = open(path, O_RDONLY); + if (fd == -1) + return -1; + + if (fstat(fd, &st) < 0) + goto error; + + sret = read(fd, scale, sizeof(scale)-1); + if (sret < 0) + goto error; + + scale[sret] = '\0'; + /* + * save current locale + */ + lc = setlocale(LC_NUMERIC, NULL); + + /* + * force to C locale to ensure kernel + * scale string is converted correctly. + * kernel uses default C locale. + */ + setlocale(LC_NUMERIC, "C"); + + alias->scale = strtod(scale, NULL); + + /* restore locale */ + setlocale(LC_NUMERIC, lc); + + ret = 0; +error: + close(fd); + return ret; +} + +static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *name) +{ + char path[PATH_MAX]; + ssize_t sret; + int fd; + + snprintf(path, PATH_MAX, "%s/%s.unit", dir, name); + + fd = open(path, O_RDONLY); + if (fd == -1) + return -1; + + sret = read(fd, alias->unit, UNIT_MAX_LEN); + if (sret < 0) + goto error; + + close(fd); + + alias->unit[sret] = '\0'; + + return 0; +error: + close(fd); + alias->unit[0] = '\0'; + return -1; +} + +static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file) +{ + struct perf_pmu_alias *alias; + char buf[256]; + int ret; + + ret = fread(buf, 1, sizeof(buf), file); + if (ret == 0) + return -EINVAL; + buf[ret] = 0; + + alias = malloc(sizeof(*alias)); + if (!alias) + return -ENOMEM; + + INIT_LIST_HEAD(&alias->terms); + alias->scale = 1.0; + alias->unit[0] = '\0'; + + ret = parse_events_terms(&alias->terms, buf); + if (ret) { + free(alias); + return ret; + } + + alias->name = strdup(name); + /* + * load unit name and scale if available + */ + perf_pmu__parse_unit(alias, dir, name); + perf_pmu__parse_scale(alias, dir, name); + + list_add_tail(&alias->list, list); + + return 0; +} + +/* + * Process all the sysfs attributes located under the directory + * specified in 'dir' parameter. + */ +static int pmu_aliases_parse(char *dir, struct list_head *head) +{ + struct dirent *evt_ent; + DIR *event_dir; + size_t len; + int ret = 0; + + event_dir = opendir(dir); + if (!event_dir) + return -EINVAL; + + while (!ret && (evt_ent = readdir(event_dir))) { + char path[PATH_MAX]; + char *name = evt_ent->d_name; + FILE *file; + + if (!strcmp(name, ".") || !strcmp(name, "..")) + continue; + + /* + * skip .unit and .scale info files + * parsed in perf_pmu__new_alias() + */ + len = strlen(name); + if (len > 5 && !strcmp(name + len - 5, ".unit")) + continue; + if (len > 6 && !strcmp(name + len - 6, ".scale")) + continue; + + snprintf(path, PATH_MAX, "%s/%s", dir, name); + + ret = -EINVAL; + file = fopen(path, "r"); + if (!file) + break; + + ret = perf_pmu__new_alias(head, dir, name, file); + fclose(file); + } + + closedir(event_dir); + return ret; +} + +/* + * 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(const char *name, struct list_head *head) +{ + struct stat st; + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + snprintf(path, PATH_MAX, + "%s/bus/event_source/devices/%s/events", sysfs, name); + + if (stat(path, &st) < 0) + return 0; /* no error if 'events' does not exist */ + + if (pmu_aliases_parse(path, head)) + return -1; + + return 0; +} + +static int pmu_alias_terms(struct perf_pmu_alias *alias, + struct list_head *terms) +{ + struct parse_events_term *term, *cloned; + LIST_HEAD(list); + int ret; + + list_for_each_entry(term, &alias->terms, list) { + ret = parse_events_term__clone(&cloned, term); + if (ret) { + parse_events__free_terms(&list); + return ret; + } + list_add_tail(&cloned->list, &list); + } + list_splice(&list, terms); + return 0; +} + +/* + * Reading/parsing the default pmu type value, which should be + * located at: + * /sys/bus/event_source/devices/<dev>/type as sysfs attribute. + */ +static int pmu_type(const char *name, __u32 *type) +{ + struct stat st; + char path[PATH_MAX]; + FILE *file; + int ret = 0; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + snprintf(path, PATH_MAX, + "%s" EVENT_SOURCE_DEVICE_PATH "%s/type", sysfs, name); + + if (stat(path, &st) < 0) + return -1; + + file = fopen(path, "r"); + if (!file) + return -EINVAL; + + if (1 != fscanf(file, "%u", type)) + ret = -1; + + fclose(file); + return ret; +} + +/* Add all pmus in sysfs to pmu list: */ +static void pmu_read_sysfs(void) +{ + char path[PATH_MAX]; + DIR *dir; + struct dirent *dent; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return; + + snprintf(path, PATH_MAX, + "%s" EVENT_SOURCE_DEVICE_PATH, sysfs); + + dir = opendir(path); + if (!dir) + return; + + while ((dent = readdir(dir))) { + if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) + continue; + /* add to static LIST_HEAD(pmus): */ + perf_pmu__find(dent->d_name); + } + + closedir(dir); +} + +static struct cpu_map *pmu_cpumask(const char *name) +{ + struct stat st; + char path[PATH_MAX]; + FILE *file; + struct cpu_map *cpus; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return NULL; + + snprintf(path, PATH_MAX, + "%s/bus/event_source/devices/%s/cpumask", sysfs, name); + + if (stat(path, &st) < 0) + return NULL; + + file = fopen(path, "r"); + if (!file) + return NULL; + + cpus = cpu_map__read(file); + fclose(file); + return cpus; +} + +static struct perf_pmu *pmu_lookup(const char *name) +{ + struct perf_pmu *pmu; + LIST_HEAD(format); + LIST_HEAD(aliases); + __u32 type; + + /* + * The pmu data we store & need consists of the pmu + * type value and format definitions. Load both right + * now. + */ + if (pmu_format(name, &format)) + return NULL; + + if (pmu_aliases(name, &aliases)) + return NULL; + + if (pmu_type(name, &type)) + return NULL; + + pmu = zalloc(sizeof(*pmu)); + if (!pmu) + return NULL; + + pmu->cpus = pmu_cpumask(name); + + INIT_LIST_HEAD(&pmu->format); + INIT_LIST_HEAD(&pmu->aliases); + list_splice(&format, &pmu->format); + list_splice(&aliases, &pmu->aliases); + pmu->name = strdup(name); + pmu->type = type; + list_add_tail(&pmu->list, &pmus); + return pmu; +} + +static struct perf_pmu *pmu_find(const char *name) +{ + struct perf_pmu *pmu; + + list_for_each_entry(pmu, &pmus, list) + if (!strcmp(pmu->name, name)) + return pmu; + + return NULL; +} + +struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu) +{ + /* + * pmu iterator: If pmu is NULL, we start at the begin, + * otherwise return the next pmu. Returns NULL on end. + */ + if (!pmu) { + pmu_read_sysfs(); + pmu = list_prepare_entry(pmu, &pmus, list); + } + list_for_each_entry_continue(pmu, &pmus, list) + return pmu; + return NULL; +} + +struct perf_pmu *perf_pmu__find(const char *name) +{ + struct perf_pmu *pmu; + + /* + * Once PMU is loaded it stays in the list, + * so we keep us from multiple reading/parsing + * the pmu format definitions. + */ + pmu = pmu_find(name); + if (pmu) + return pmu; + + return pmu_lookup(name); +} + +static struct perf_pmu_format * +pmu_find_format(struct list_head *formats, char *name) +{ + struct perf_pmu_format *format; + + list_for_each_entry(format, formats, list) + if (!strcmp(format->name, name)) + return format; + + return NULL; +} + +/* + * Returns value based on the format definition (format parameter) + * and unformated value (value parameter). + * + * TODO maybe optimize a little ;) + */ +static __u64 pmu_format_value(unsigned long *format, __u64 value) +{ + unsigned long fbit, vbit; + __u64 v = 0; + + for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) { + + if (!test_bit(fbit, format)) + continue; + + if (!(value & (1llu << vbit++))) + continue; + + v |= (1llu << fbit); + } + + return v; +} + +/* + * Setup one of config[12] attr members based on the + * user input data - term parameter. + */ +static int pmu_config_term(struct list_head *formats, + struct perf_event_attr *attr, + struct parse_events_term *term) +{ + struct perf_pmu_format *format; + __u64 *vp; + + /* + * Support only for hardcoded and numnerial terms. + * Hardcoded terms should be already in, so nothing + * to be done for them. + */ + if (parse_events__is_hardcoded_term(term)) + return 0; + + if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) + return -EINVAL; + + format = pmu_find_format(formats, term->config); + if (!format) + return -EINVAL; + + switch (format->value) { + case PERF_PMU_FORMAT_VALUE_CONFIG: + vp = &attr->config; + break; + case PERF_PMU_FORMAT_VALUE_CONFIG1: + vp = &attr->config1; + break; + case PERF_PMU_FORMAT_VALUE_CONFIG2: + vp = &attr->config2; + break; + default: + return -EINVAL; + } + + /* + * XXX If we ever decide to go with string values for + * non-hardcoded terms, here's the place to translate + * them into value. + */ + *vp |= pmu_format_value(format->bits, term->val.num); + return 0; +} + +int perf_pmu__config_terms(struct list_head *formats, + struct perf_event_attr *attr, + struct list_head *head_terms) +{ + struct parse_events_term *term; + + list_for_each_entry(term, head_terms, list) + if (pmu_config_term(formats, attr, term)) + return -EINVAL; + + return 0; +} + +/* + * Configures event's 'attr' parameter based on the: + * 1) users input - specified in terms parameter + * 2) pmu format definitions - specified by pmu parameter + */ +int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, + struct list_head *head_terms) +{ + attr->type = pmu->type; + return perf_pmu__config_terms(&pmu->format, attr, head_terms); +} + +static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu, + struct parse_events_term *term) +{ + struct perf_pmu_alias *alias; + char *name; + + if (parse_events__is_hardcoded_term(term)) + return NULL; + + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { + if (term->val.num != 1) + return NULL; + if (pmu_find_format(&pmu->format, term->config)) + return NULL; + name = term->config; + } else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { + if (strcasecmp(term->config, "event")) + return NULL; + name = term->val.str; + } else { + return NULL; + } + + list_for_each_entry(alias, &pmu->aliases, list) { + if (!strcasecmp(alias->name, name)) + return alias; + } + return NULL; +} + + +static int check_unit_scale(struct perf_pmu_alias *alias, + const char **unit, double *scale) +{ + /* + * Only one term in event definition can + * define unit and scale, fail if there's + * more than one. + */ + if ((*unit && alias->unit) || + (*scale && alias->scale)) + return -EINVAL; + + if (alias->unit) + *unit = alias->unit; + + if (alias->scale) + *scale = alias->scale; + + return 0; +} + +/* + * Find alias in the terms list and replace it with the terms + * defined for the alias + */ +int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, + const char **unit, double *scale) +{ + struct parse_events_term *term, *h; + struct perf_pmu_alias *alias; + int ret; + + /* + * Mark unit and scale as not set + * (different from default values, see below) + */ + *unit = NULL; + *scale = 0.0; + + list_for_each_entry_safe(term, h, head_terms, list) { + alias = pmu_find_alias(pmu, term); + if (!alias) + continue; + ret = pmu_alias_terms(alias, &term->list); + if (ret) + return ret; + + ret = check_unit_scale(alias, unit, scale); + if (ret) + return ret; + + list_del(&term->list); + free(term); + } + + /* + * if no unit or scale foundin aliases, then + * set defaults as for evsel + * unit cannot left to NULL + */ + if (*unit == NULL) + *unit = ""; + + if (*scale == 0.0) + *scale = 1.0; + + return 0; +} + +int perf_pmu__new_format(struct list_head *list, char *name, + int config, unsigned long *bits) +{ + struct perf_pmu_format *format; + + format = zalloc(sizeof(*format)); + if (!format) + return -ENOMEM; + + format->name = strdup(name); + format->value = config; + memcpy(format->bits, bits, sizeof(format->bits)); + + list_add_tail(&format->list, list); + return 0; +} + +void perf_pmu__set_format(unsigned long *bits, long from, long to) +{ + long b; + + if (!to) + to = from; + + memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS)); + 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]); + zfree(&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 new file mode 100644 index 00000000000..c14a543ce1f --- /dev/null +++ b/tools/perf/util/pmu.h @@ -0,0 +1,49 @@ +#ifndef __PMU_H +#define __PMU_H + +#include <linux/bitmap.h> +#include <linux/perf_event.h> +#include <stdbool.h> + +enum { + PERF_PMU_FORMAT_VALUE_CONFIG, + PERF_PMU_FORMAT_VALUE_CONFIG1, + PERF_PMU_FORMAT_VALUE_CONFIG2, +}; + +#define PERF_PMU_FORMAT_BITS 64 + +struct perf_pmu { + char *name; + __u32 type; + struct cpu_map *cpus; + struct list_head format; + struct list_head aliases; + struct list_head list; +}; + +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, + struct perf_event_attr *attr, + struct list_head *head_terms); +int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, + const char **unit, double *scale); +struct list_head *perf_pmu__alias(struct perf_pmu *pmu, + struct list_head *head_terms); +int perf_pmu_wrap(void); +void perf_pmu_error(struct list_head *list, char *name, char const *msg); + +int perf_pmu__new_format(struct list_head *list, char *name, + int config, unsigned long *bits); +void perf_pmu__set_format(unsigned long *bits, long from, long to); +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/pmu.l b/tools/perf/util/pmu.l new file mode 100644 index 00000000000..a15d9fbd7c0 --- /dev/null +++ b/tools/perf/util/pmu.l @@ -0,0 +1,43 @@ +%option prefix="perf_pmu_" + +%{ +#include <stdlib.h> +#include <linux/bitops.h> +#include "pmu.h" +#include "pmu-bison.h" + +static int value(int base) +{ + long num; + + errno = 0; + num = strtoul(perf_pmu_text, NULL, base); + if (errno) + return PP_ERROR; + + perf_pmu_lval.num = num; + return PP_VALUE; +} + +%} + +num_dec [0-9]+ + +%% + +{num_dec} { return value(10); } +config { return PP_CONFIG; } +config1 { return PP_CONFIG1; } +config2 { return PP_CONFIG2; } +- { return '-'; } +: { return ':'; } +, { return ','; } +. { ; } +\n { ; } + +%% + +int perf_pmu_wrap(void) +{ + return 1; +} diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y new file mode 100644 index 00000000000..bfd7e850986 --- /dev/null +++ b/tools/perf/util/pmu.y @@ -0,0 +1,92 @@ + +%parse-param {struct list_head *format} +%parse-param {char *name} + +%{ + +#include <linux/compiler.h> +#include <linux/list.h> +#include <linux/bitmap.h> +#include <string.h> +#include "pmu.h" + +extern int perf_pmu_lex (void); + +#define ABORT_ON(val) \ +do { \ + if (val) \ + YYABORT; \ +} while (0) + +%} + +%token PP_CONFIG PP_CONFIG1 PP_CONFIG2 +%token PP_VALUE PP_ERROR +%type <num> PP_VALUE +%type <bits> bit_term +%type <bits> bits + +%union +{ + unsigned long num; + DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS); +} + +%% + +format: +format format_term +| +format_term + +format_term: +PP_CONFIG ':' bits +{ + ABORT_ON(perf_pmu__new_format(format, name, + PERF_PMU_FORMAT_VALUE_CONFIG, + $3)); +} +| +PP_CONFIG1 ':' bits +{ + ABORT_ON(perf_pmu__new_format(format, name, + PERF_PMU_FORMAT_VALUE_CONFIG1, + $3)); +} +| +PP_CONFIG2 ':' bits +{ + ABORT_ON(perf_pmu__new_format(format, name, + PERF_PMU_FORMAT_VALUE_CONFIG2, + $3)); +} + +bits: +bits ',' bit_term +{ + bitmap_or($$, $1, $3, 64); +} +| +bit_term +{ + memcpy($$, $1, sizeof($1)); +} + +bit_term: +PP_VALUE '-' PP_VALUE +{ + perf_pmu__set_format($$, $1, $3); +} +| +PP_VALUE +{ + perf_pmu__set_format($$, $1, 0); +} + +%% + +void perf_pmu_error(struct list_head *list __maybe_unused, + char *name __maybe_unused, + char const *msg __maybe_unused) +{ +} diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 3b6a5297bf1..9a0a1839a37 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -19,7 +19,6 @@ * */ -#define _GNU_SOURCE #include <sys/utsname.h> #include <sys/types.h> #include <sys/stat.h> @@ -31,24 +30,23 @@ #include <string.h> #include <stdarg.h> #include <limits.h> +#include <elf.h> -#undef _GNU_SOURCE #include "util.h" #include "event.h" -#include "string.h" #include "strlist.h" #include "debug.h" #include "cache.h" #include "color.h" #include "symbol.h" #include "thread.h" -#include "debugfs.h" -#include "trace-event.h" /* For __unused */ +#include <api/fs/debugfs.h> +#include "trace-event.h" /* For __maybe_unused */ #include "probe-event.h" #include "probe-finder.h" +#include "session.h" #define MAX_CMDLEN 256 -#define MAX_PROBE_ARGS 128 #define PERFPROBE_GROUP "probe" bool probe_event_dry_run; /* Dry run flag */ @@ -72,31 +70,32 @@ static int e_snprintf(char *str, size_t size, const char *format, ...) } static char *synthesize_perf_probe_point(struct perf_probe_point *pp); -static struct machine machine; +static void clear_probe_trace_event(struct probe_trace_event *tev); +static struct machine *host_machine; /* Initialize symbol maps and path of vmlinux/modules */ -static int init_vmlinux(void) +static int init_symbol_maps(bool user_only) { int ret; symbol_conf.sort_by_name = true; - if (symbol_conf.vmlinux_name == NULL) - symbol_conf.try_vmlinux_path = true; - else - pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); ret = symbol__init(); if (ret < 0) { pr_debug("Failed to init symbol map.\n"); goto out; } - ret = machine__init(&machine, "", HOST_KERNEL_ID); - if (ret < 0) - goto out; + if (host_machine || user_only) /* already initialized */ + return 0; - if (machine__create_kernel_maps(&machine) < 0) { - pr_debug("machine__create_kernel_maps "); - goto out; + if (symbol_conf.vmlinux_name) + pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); + + host_machine = machine__new_host(); + if (!host_machine) { + pr_debug("machine__new_host() failed.\n"); + symbol__exit(); + ret = -1; } out: if (ret < 0) @@ -104,106 +103,386 @@ out: return ret; } +static void exit_symbol_maps(void) +{ + if (host_machine) { + machine__delete(host_machine); + host_machine = NULL; + } + symbol__exit(); +} + static struct symbol *__find_kernel_function_by_name(const char *name, struct map **mapp) { - return machine__find_kernel_function_by_name(&machine, name, mapp, + return machine__find_kernel_function_by_name(host_machine, name, mapp, NULL); } -const char *kernel_get_module_path(const char *module) +static struct symbol *__find_kernel_function(u64 addr, struct map **mapp) +{ + return machine__find_kernel_function(host_machine, addr, mapp, NULL); +} + +static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void) +{ + /* kmap->ref_reloc_sym should be set if host_machine is initialized */ + struct kmap *kmap; + + if (map__load(host_machine->vmlinux_maps[MAP__FUNCTION], NULL) < 0) + return NULL; + + kmap = map__kmap(host_machine->vmlinux_maps[MAP__FUNCTION]); + return kmap->ref_reloc_sym; +} + +static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc) +{ + struct ref_reloc_sym *reloc_sym; + struct symbol *sym; + struct map *map; + + /* ref_reloc_sym is just a label. Need a special fix*/ + reloc_sym = kernel_get_ref_reloc_sym(); + if (reloc_sym && strcmp(name, reloc_sym->name) == 0) + return (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr; + else { + sym = __find_kernel_function_by_name(name, &map); + if (sym) + return map->unmap_ip(map, sym->start) - + (reloc) ? 0 : map->reloc; + } + return 0; +} + +static struct map *kernel_get_module_map(const char *module) +{ + struct rb_node *nd; + struct map_groups *grp = &host_machine->kmaps; + + /* A file path -- this is an offline module */ + if (module && strchr(module, '/')) + return machine__new_module(host_machine, 0, module); + + if (!module) + module = "kernel"; + + for (nd = rb_first(&grp->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) { + struct map *pos = rb_entry(nd, struct map, rb_node); + if (strncmp(pos->dso->short_name + 1, module, + pos->dso->short_name_len - 2) == 0) { + return pos; + } + } + return NULL; +} + +static struct dso *kernel_get_module_dso(const char *module) { struct dso *dso; + struct map *map; + const char *vmlinux_name; if (module) { - list_for_each_entry(dso, &machine.kernel_dsos, node) { + list_for_each_entry(dso, &host_machine->kernel_dsos, node) { if (strncmp(dso->short_name + 1, module, dso->short_name_len - 2) == 0) goto found; } pr_debug("Failed to find module %s.\n", module); return NULL; + } + + map = host_machine->vmlinux_maps[MAP__FUNCTION]; + dso = map->dso; + + vmlinux_name = symbol_conf.vmlinux_name; + if (vmlinux_name) { + if (dso__load_vmlinux(dso, map, vmlinux_name, false, NULL) <= 0) + return NULL; } else { - dso = machine.vmlinux_maps[MAP__FUNCTION]->dso; - if (dso__load_vmlinux_path(dso, - machine.vmlinux_maps[MAP__FUNCTION], NULL) < 0) { + if (dso__load_vmlinux_path(dso, map, NULL) <= 0) { pr_debug("Failed to load kernel map.\n"); return NULL; } } found: - return dso->long_name; + return dso; } -#ifdef DWARF_SUPPORT -static int open_vmlinux(const char *module) +const char *kernel_get_module_path(const char *module) { - const char *path = kernel_get_module_path(module); - if (!path) { - pr_err("Failed to find path of %s module", module ?: "kernel"); - return -ENOENT; + struct dso *dso = kernel_get_module_dso(module); + return (dso) ? dso->long_name : NULL; +} + +static int convert_exec_to_group(const char *exec, char **result) +{ + char *ptr1, *ptr2, *exec_copy; + char buf[64]; + int ret; + + exec_copy = strdup(exec); + if (!exec_copy) + return -ENOMEM; + + ptr1 = basename(exec_copy); + if (!ptr1) { + ret = -EINVAL; + goto out; } - pr_debug("Try to open %s\n", path); - return open(path, O_RDONLY); + + ptr2 = strpbrk(ptr1, "-._"); + if (ptr2) + *ptr2 = '\0'; + ret = e_snprintf(buf, 64, "%s_%s", PERFPROBE_GROUP, ptr1); + if (ret < 0) + goto out; + + *result = strdup(buf); + ret = *result ? 0 : -ENOMEM; + +out: + free(exec_copy); + return ret; +} + +static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) +{ + int i; + + for (i = 0; i < ntevs; i++) + clear_probe_trace_event(tevs + i); +} + +#ifdef HAVE_DWARF_SUPPORT + +/* Open new debuginfo of given module */ +static struct debuginfo *open_debuginfo(const char *module) +{ + const char *path = module; + + if (!module || !strchr(module, '/')) { + path = kernel_get_module_path(module); + if (!path) { + pr_err("Failed to find path of %s module.\n", + module ?: "kernel"); + return NULL; + } + } + return debuginfo__new(path); +} + +static int get_text_start_address(const char *exec, unsigned long *address) +{ + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + int fd, ret = -ENOENT; + + fd = open(exec, O_RDONLY); + if (fd < 0) + return -errno; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + return -EINVAL; + + if (gelf_getehdr(elf, &ehdr) == NULL) + goto out; + + if (!elf_section_by_name(elf, &ehdr, &shdr, ".text", NULL)) + goto out; + + *address = shdr.sh_addr - shdr.sh_offset; + ret = 0; +out: + elf_end(elf); + return ret; } /* * Convert trace point to probe point with debuginfo - * Currently only handles kprobes. */ -static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, - struct perf_probe_point *pp) +static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, + struct perf_probe_point *pp, + bool is_kprobe) { - struct symbol *sym; - struct map *map; - u64 addr; + struct debuginfo *dinfo = NULL; + unsigned long stext = 0; + u64 addr = tp->address; int ret = -ENOENT; - sym = __find_kernel_function_by_name(tp->symbol, &map); - if (sym) { - addr = map->unmap_ip(map, sym->start + tp->offset); - pr_debug("try to find %s+%ld@%llx\n", tp->symbol, - tp->offset, addr); - ret = find_perf_probe_point((unsigned long)addr, pp); + /* convert the address to dwarf address */ + if (!is_kprobe) { + if (!addr) { + ret = -EINVAL; + goto error; + } + ret = get_text_start_address(tp->module, &stext); + if (ret < 0) + goto error; + addr += stext; + } else { + addr = kernel_get_symbol_address_by_name(tp->symbol, false); + if (addr == 0) + goto error; + addr += tp->offset; } - if (ret <= 0) { - pr_debug("Failed to find corresponding probes from " - "debuginfo. Use kprobe event information.\n"); - pp->function = strdup(tp->symbol); - if (pp->function == NULL) + + pr_debug("try to find information at %" PRIx64 " in %s\n", addr, + tp->module ? : "kernel"); + + dinfo = open_debuginfo(tp->module); + if (dinfo) { + ret = debuginfo__find_probe_point(dinfo, + (unsigned long)addr, pp); + debuginfo__delete(dinfo); + } else { + pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr); + ret = -ENOENT; + } + + if (ret > 0) { + pp->retprobe = tp->retprobe; + return 0; + } +error: + pr_debug("Failed to find corresponding probes from debuginfo.\n"); + return ret ? : -ENOENT; +} + +static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, + int ntevs, const char *exec) +{ + int i, ret = 0; + unsigned long stext = 0; + + if (!exec) + return 0; + + ret = get_text_start_address(exec, &stext); + if (ret < 0) + return ret; + + for (i = 0; i < ntevs && ret >= 0; i++) { + /* point.address is the addres of point.symbol + point.offset */ + tevs[i].point.address -= stext; + tevs[i].point.module = strdup(exec); + if (!tevs[i].point.module) { + ret = -ENOMEM; + break; + } + tevs[i].uprobes = true; + } + + return ret; +} + +static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, + int ntevs, const char *module) +{ + int i, ret = 0; + char *tmp; + + if (!module) + return 0; + + tmp = strrchr(module, '/'); + if (tmp) { + /* This is a module path -- get the module name */ + module = strdup(tmp + 1); + if (!module) return -ENOMEM; - pp->offset = tp->offset; + tmp = strchr(module, '.'); + if (tmp) + *tmp = '\0'; + tmp = (char *)module; /* For free() */ } - pp->retprobe = tp->retprobe; + for (i = 0; i < ntevs; i++) { + tevs[i].point.module = strdup(module); + if (!tevs[i].point.module) { + ret = -ENOMEM; + break; + } + } + + free(tmp); + return ret; +} + +/* Post processing the probe events */ +static int post_process_probe_trace_events(struct probe_trace_event *tevs, + int ntevs, const char *module, + bool uprobe) +{ + struct ref_reloc_sym *reloc_sym; + char *tmp; + int i; + + if (uprobe) + return add_exec_to_probe_trace_events(tevs, ntevs, module); + + /* Note that currently ref_reloc_sym based probe is not for drivers */ + if (module) + return add_module_to_probe_trace_events(tevs, ntevs, module); + + reloc_sym = kernel_get_ref_reloc_sym(); + if (!reloc_sym) { + pr_warning("Relocated base symbol is not found!\n"); + return -EINVAL; + } + + for (i = 0; i < ntevs; i++) { + if (tevs[i].point.address) { + tmp = strdup(reloc_sym->name); + if (!tmp) + return -ENOMEM; + free(tevs[i].point.symbol); + tevs[i].point.symbol = tmp; + tevs[i].point.offset = tevs[i].point.address - + reloc_sym->unrelocated_addr; + } + } return 0; } /* Try to find perf_probe_event with debuginfo */ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, - struct probe_trace_event **tevs, - int max_tevs, const char *module) + struct probe_trace_event **tevs, + int max_tevs, const char *target) { bool need_dwarf = perf_probe_event_need_dwarf(pev); - int fd, ntevs; + struct debuginfo *dinfo; + int ntevs, ret = 0; + + dinfo = open_debuginfo(target); - fd = open_vmlinux(module); - if (fd < 0) { + if (!dinfo) { if (need_dwarf) { pr_warning("Failed to open debuginfo file.\n"); - return fd; + return -ENOENT; } - pr_debug("Could not open vmlinux. Try to use symbols.\n"); + pr_debug("Could not open debuginfo. Try to use symbols.\n"); return 0; } - /* Searching trace events corresponding to probe event */ - ntevs = find_probe_trace_events(fd, pev, tevs, max_tevs); - close(fd); + pr_debug("Try to find probe point from debuginfo.\n"); + /* Searching trace events corresponding to a probe event */ + ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs); + + debuginfo__delete(dinfo); if (ntevs > 0) { /* Succeeded to find trace events */ - pr_debug("find %d probe_trace_events.\n", ntevs); - return ntevs; + pr_debug("Found %d probe_trace_events.\n", ntevs); + ret = post_process_probe_trace_events(*tevs, ntevs, + target, pev->uprobes); + if (ret < 0) { + clear_probe_trace_events(*tevs, ntevs); + zfree(tevs); + } + return ret < 0 ? ret : ntevs; } if (ntevs == 0) { /* No error but failed to find probe point. */ @@ -217,7 +496,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, pr_warning("Warning: No dwarf info found in the vmlinux - " "please rebuild kernel with CONFIG_DEBUG_INFO=y.\n"); if (!need_dwarf) { - pr_debug("Trying to use symbols.\nn"); + pr_debug("Trying to use symbols.\n"); return 0; } } @@ -269,15 +548,13 @@ static int get_real_path(const char *raw_path, const char *comp_dir, case EFAULT: raw_path = strchr(++raw_path, '/'); if (!raw_path) { - free(*new_path); - *new_path = NULL; + zfree(new_path); return -ENOENT; } continue; default: - free(*new_path); - *new_path = NULL; + zfree(new_path); return -errno; } } @@ -286,72 +563,76 @@ static int get_real_path(const char *raw_path, const char *comp_dir, #define LINEBUF_SIZE 256 #define NR_ADDITIONAL_LINES 2 -static int show_one_line(FILE *fp, int l, bool skip, bool show_num) +static int __show_one_line(FILE *fp, int l, bool skip, bool show_num) { char buf[LINEBUF_SIZE]; - const char *color = PERF_COLOR_BLUE; - - if (fgets(buf, LINEBUF_SIZE, fp) == NULL) - goto error; - if (!skip) { - if (show_num) - fprintf(stdout, "%7d %s", l, buf); - else - color_fprintf(stdout, color, " %s", buf); - } + const char *color = show_num ? "" : PERF_COLOR_BLUE; + const char *prefix = NULL; - while (strlen(buf) == LINEBUF_SIZE - 1 && - buf[LINEBUF_SIZE - 2] != '\n') { + do { if (fgets(buf, LINEBUF_SIZE, fp) == NULL) goto error; - if (!skip) { - if (show_num) - fprintf(stdout, "%s", buf); - else - color_fprintf(stdout, color, "%s", buf); + if (skip) + continue; + if (!prefix) { + prefix = show_num ? "%7d " : " "; + color_fprintf(stdout, color, prefix, l); } - } + color_fprintf(stdout, color, "%s", buf); - return 0; + } while (strchr(buf, '\n') == NULL); + + return 1; error: - if (feof(fp)) - pr_warning("Source file is shorter than expected.\n"); - else + if (ferror(fp)) { pr_warning("File read error: %s\n", strerror(errno)); + return -1; + } + return 0; +} - return -1; +static int _show_one_line(FILE *fp, int l, bool skip, bool show_num) +{ + int rv = __show_one_line(fp, l, skip, show_num); + if (rv == 0) { + pr_warning("Source file is shorter than expected.\n"); + rv = -1; + } + return rv; } +#define show_one_line_with_num(f,l) _show_one_line(f,l,false,true) +#define show_one_line(f,l) _show_one_line(f,l,false,false) +#define skip_one_line(f,l) _show_one_line(f,l,true,false) +#define show_one_line_or_eof(f,l) __show_one_line(f,l,false,false) + /* * Show line-range always requires debuginfo to find source file and * line number. */ -int show_line_range(struct line_range *lr, const char *module) +static int __show_line_range(struct line_range *lr, const char *module) { int l = 1; - struct line_node *ln; + struct int_node *ln; + struct debuginfo *dinfo; FILE *fp; - int fd, ret; + int ret; char *tmp; /* Search a line range */ - ret = init_vmlinux(); - if (ret < 0) - return ret; - - fd = open_vmlinux(module); - if (fd < 0) { + dinfo = open_debuginfo(module); + if (!dinfo) { pr_warning("Failed to open debuginfo file.\n"); - return fd; + return -ENOENT; } - ret = find_line_range(fd, lr); - close(fd); - if (ret == 0) { + ret = debuginfo__find_line_range(dinfo, lr); + debuginfo__delete(dinfo); + if (ret == 0 || ret == -ENOENT) { pr_warning("Specified source line is not found.\n"); return -ENOENT; } else if (ret < 0) { - pr_warning("Debuginfo analysis failed. (%d)\n", ret); + pr_warning("Debuginfo analysis failed.\n"); return ret; } @@ -360,17 +641,17 @@ int show_line_range(struct line_range *lr, const char *module) ret = get_real_path(tmp, lr->comp_dir, &lr->path); free(tmp); /* Free old path */ if (ret < 0) { - pr_warning("Failed to find source file. (%d)\n", ret); + pr_warning("Failed to find source file path.\n"); return ret; } setup_pager(); if (lr->function) - fprintf(stdout, "<%s:%d>\n", lr->function, + fprintf(stdout, "<%s@%s:%d>\n", lr->function, lr->path, lr->start - lr->offset); else - fprintf(stdout, "<%s:%d>\n", lr->file, lr->start); + fprintf(stdout, "<%s:%d>\n", lr->path, lr->start); fp = fopen(lr->path, "r"); if (fp == NULL) { @@ -379,194 +660,288 @@ int show_line_range(struct line_range *lr, const char *module) return -errno; } /* Skip to starting line number */ - while (l < lr->start && ret >= 0) - ret = show_one_line(fp, l++, true, false); - if (ret < 0) - goto end; + while (l < lr->start) { + ret = skip_one_line(fp, l++); + if (ret < 0) + goto end; + } - list_for_each_entry(ln, &lr->line_list, list) { - while (ln->line > l && ret >= 0) - ret = show_one_line(fp, (l++) - lr->offset, - false, false); - if (ret >= 0) - ret = show_one_line(fp, (l++) - lr->offset, - false, true); + intlist__for_each(ln, lr->line_list) { + for (; ln->i > l; l++) { + ret = show_one_line(fp, l - lr->offset); + if (ret < 0) + goto end; + } + ret = show_one_line_with_num(fp, l++ - lr->offset); if (ret < 0) goto end; } if (lr->end == INT_MAX) lr->end = l + NR_ADDITIONAL_LINES; - while (l <= lr->end && !feof(fp) && ret >= 0) - ret = show_one_line(fp, (l++) - lr->offset, false, false); + while (l <= lr->end) { + ret = show_one_line_or_eof(fp, l++ - lr->offset); + if (ret <= 0) + break; + } end: fclose(fp); return ret; } -static int show_available_vars_at(int fd, struct perf_probe_event *pev, - int max_vls, bool externs) +int show_line_range(struct line_range *lr, const char *module) +{ + int ret; + + ret = init_symbol_maps(false); + if (ret < 0) + return ret; + ret = __show_line_range(lr, module); + exit_symbol_maps(); + + return ret; +} + +static int show_available_vars_at(struct debuginfo *dinfo, + struct perf_probe_event *pev, + int max_vls, struct strfilter *_filter, + bool externs) { char *buf; - int ret, i; + int ret, i, nvars; struct str_node *node; struct variable_list *vls = NULL, *vl; + const char *var; buf = synthesize_perf_probe_point(&pev->point); if (!buf) return -EINVAL; pr_debug("Searching variables at %s\n", buf); - ret = find_available_vars_at(fd, pev, &vls, max_vls, externs); - if (ret > 0) { - /* Some variables were found */ - fprintf(stdout, "Available variables at %s\n", buf); - for (i = 0; i < ret; i++) { - vl = &vls[i]; - /* - * A probe point might be converted to - * several trace points. - */ - fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol, - vl->point.offset); - free(vl->point.symbol); - if (vl->vars) { - strlist__for_each(node, vl->vars) + ret = debuginfo__find_available_vars_at(dinfo, pev, &vls, + max_vls, externs); + if (ret <= 0) { + if (ret == 0 || ret == -ENOENT) { + pr_err("Failed to find the address of %s\n", buf); + ret = -ENOENT; + } else + pr_warning("Debuginfo analysis failed.\n"); + goto end; + } + + /* Some variables are found */ + fprintf(stdout, "Available variables at %s\n", buf); + for (i = 0; i < ret; i++) { + vl = &vls[i]; + /* + * A probe point might be converted to + * several trace points. + */ + fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol, + vl->point.offset); + zfree(&vl->point.symbol); + nvars = 0; + if (vl->vars) { + strlist__for_each(node, vl->vars) { + var = strchr(node->s, '\t') + 1; + if (strfilter__compare(_filter, var)) { fprintf(stdout, "\t\t%s\n", node->s); - strlist__delete(vl->vars); - } else - fprintf(stdout, "(No variables)\n"); + nvars++; + } + } + strlist__delete(vl->vars); } - free(vls); - } else - pr_err("Failed to find variables at %s (%d)\n", buf, ret); - + if (nvars == 0) + fprintf(stdout, "\t\t(No matched variables)\n"); + } + free(vls); +end: free(buf); return ret; } /* Show available variables on given probe point */ int show_available_vars(struct perf_probe_event *pevs, int npevs, - int max_vls, const char *module, bool externs) + int max_vls, const char *module, + struct strfilter *_filter, bool externs) { - int i, fd, ret = 0; + int i, ret = 0; + struct debuginfo *dinfo; - ret = init_vmlinux(); + ret = init_symbol_maps(false); if (ret < 0) return ret; - fd = open_vmlinux(module); - if (fd < 0) { + dinfo = open_debuginfo(module); + if (!dinfo) { pr_warning("Failed to open debuginfo file.\n"); - return fd; + ret = -ENOENT; + goto out; } setup_pager(); for (i = 0; i < npevs && ret >= 0; i++) - ret = show_available_vars_at(fd, &pevs[i], max_vls, externs); + ret = show_available_vars_at(dinfo, &pevs[i], max_vls, _filter, + externs); - close(fd); + debuginfo__delete(dinfo); +out: + exit_symbol_maps(); 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) +static int +find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused, + struct perf_probe_point *pp __maybe_unused, + bool is_kprobe __maybe_unused) { - struct symbol *sym; - - sym = __find_kernel_function_by_name(tp->symbol, NULL); - if (!sym) { - pr_err("Failed to find symbol %s in kernel.\n", tp->symbol); - return -ENOENT; - } - pp->function = strdup(tp->symbol); - if (pp->function == NULL) - return -ENOMEM; - pp->offset = tp->offset; - pp->retprobe = tp->retprobe; - - return 0; + return -ENOSYS; } static int try_to_find_probe_trace_events(struct perf_probe_event *pev, - struct probe_trace_event **tevs __unused, - int max_tevs __unused, const char *mod __unused) + struct probe_trace_event **tevs __maybe_unused, + int max_tevs __maybe_unused, + const char *target __maybe_unused) { if (perf_probe_event_need_dwarf(pev)) { pr_warning("Debuginfo-analysis is not supported.\n"); return -ENOSYS; } + return 0; } -int show_line_range(struct line_range *lr __unused, const char *module __unused) +int show_line_range(struct line_range *lr __maybe_unused, + const char *module __maybe_unused) { pr_warning("Debuginfo-analysis is not supported.\n"); return -ENOSYS; } -int show_available_vars(struct perf_probe_event *pevs __unused, - int npevs __unused, int max_vls __unused, - const char *module __unused, bool externs __unused) +int show_available_vars(struct perf_probe_event *pevs __maybe_unused, + int npevs __maybe_unused, int max_vls __maybe_unused, + const char *module __maybe_unused, + struct strfilter *filter __maybe_unused, + bool externs __maybe_unused) { pr_warning("Debuginfo-analysis is not supported.\n"); return -ENOSYS; } #endif +void line_range__clear(struct line_range *lr) +{ + free(lr->function); + free(lr->file); + free(lr->path); + free(lr->comp_dir); + intlist__delete(lr->line_list); + memset(lr, 0, sizeof(*lr)); +} + +int line_range__init(struct line_range *lr) +{ + memset(lr, 0, sizeof(*lr)); + lr->line_list = intlist__new(NULL); + if (!lr->line_list) + return -ENOMEM; + else + return 0; +} + +static int parse_line_num(char **ptr, int *val, const char *what) +{ + const char *start = *ptr; + + errno = 0; + *val = strtol(*ptr, ptr, 0); + if (errno || *ptr == start) { + semantic_error("'%s' is not a valid number.\n", what); + return -EINVAL; + } + return 0; +} + +/* + * Stuff 'lr' according to the line range described by 'arg'. + * The line range syntax is described by: + * + * SRC[:SLN[+NUM|-ELN]] + * FNC[@SRC][:SLN[+NUM|-ELN]] + */ int parse_line_range_desc(const char *arg, struct line_range *lr) { - const char *ptr; - char *tmp; - /* - * <Syntax> - * SRC:SLN[+NUM|-ELN] - * FUNC[:SLN[+NUM|-ELN]] - */ - ptr = strchr(arg, ':'); - if (ptr) { - lr->start = (int)strtoul(ptr + 1, &tmp, 0); - if (*tmp == '+') { - lr->end = lr->start + (int)strtoul(tmp + 1, &tmp, 0); - lr->end--; /* - * Adjust the number of lines here. - * If the number of lines == 1, the - * the end of line should be equal to - * the start of line. - */ - } else if (*tmp == '-') - lr->end = (int)strtoul(tmp + 1, &tmp, 0); - else - lr->end = INT_MAX; + char *range, *file, *name = strdup(arg); + int err; + + if (!name) + return -ENOMEM; + + lr->start = 0; + lr->end = INT_MAX; + + range = strchr(name, ':'); + if (range) { + *range++ = '\0'; + + err = parse_line_num(&range, &lr->start, "start line"); + if (err) + goto err; + + if (*range == '+' || *range == '-') { + const char c = *range++; + + err = parse_line_num(&range, &lr->end, "end line"); + if (err) + goto err; + + if (c == '+') { + lr->end += lr->start; + /* + * Adjust the number of lines here. + * If the number of lines == 1, the + * the end of line should be equal to + * the start of line. + */ + lr->end--; + } + } + pr_debug("Line range is %d to %d\n", lr->start, lr->end); + + err = -EINVAL; if (lr->start > lr->end) { semantic_error("Start line must be smaller" " than end line.\n"); - return -EINVAL; + goto err; } - if (*tmp != '\0') { - semantic_error("Tailing with invalid character '%d'.\n", - *tmp); - return -EINVAL; + if (*range != '\0') { + semantic_error("Tailing with invalid str '%s'.\n", range); + goto err; } - tmp = strndup(arg, (ptr - arg)); - } else { - tmp = strdup(arg); - lr->end = INT_MAX; } - if (tmp == NULL) - return -ENOMEM; - - if (strchr(tmp, '.')) - lr->file = tmp; + file = strchr(name, '@'); + if (file) { + *file = '\0'; + lr->file = strdup(++file); + if (lr->file == NULL) { + err = -ENOMEM; + goto err; + } + lr->function = name; + } else if (strchr(name, '.')) + lr->file = name; else - lr->function = tmp; + lr->function = name; return 0; +err: + free(name); + return err; } /* Check the name is good for event/group */ @@ -690,39 +1065,40 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) /* Exclusion check */ if (pp->lazy_line && pp->line) { - semantic_error("Lazy pattern can't be used with line number."); + semantic_error("Lazy pattern can't be used with" + " line number.\n"); return -EINVAL; } if (pp->lazy_line && pp->offset) { - semantic_error("Lazy pattern can't be used with offset."); + semantic_error("Lazy pattern can't be used with offset.\n"); return -EINVAL; } if (pp->line && pp->offset) { - semantic_error("Offset can't be used with line number."); + semantic_error("Offset can't be used with line number.\n"); return -EINVAL; } if (!pp->line && !pp->lazy_line && pp->file && !pp->function) { semantic_error("File always requires line number or " - "lazy pattern."); + "lazy pattern.\n"); return -EINVAL; } if (pp->offset && !pp->function) { - semantic_error("Offset requires an entry function."); + semantic_error("Offset requires an entry function.\n"); return -EINVAL; } if (pp->retprobe && !pp->function) { - semantic_error("Return probe requires an entry function."); + semantic_error("Return probe requires an entry function.\n"); return -EINVAL; } if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) { semantic_error("Offset/Line/Lazy pattern can't be used with " - "return probe."); + "return probe.\n"); return -EINVAL; } @@ -892,11 +1268,12 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev) /* Parse probe_events event into struct probe_point */ static int parse_probe_trace_command(const char *cmd, - struct probe_trace_event *tev) + struct probe_trace_event *tev) { struct probe_trace_point *tp = &tev->point; char pr; char *p; + char *argv0_str = NULL, *fmt, *fmt1_str, *fmt2_str, *fmt3_str; int ret, i, argc; char **argv; @@ -913,23 +1290,54 @@ static int parse_probe_trace_command(const char *cmd, } /* Scan event and group name. */ - ret = sscanf(argv[0], "%c:%a[^/ \t]/%a[^ \t]", - &pr, (float *)(void *)&tev->group, - (float *)(void *)&tev->event); - if (ret != 3) { + argv0_str = strdup(argv[0]); + if (argv0_str == NULL) { + ret = -ENOMEM; + goto out; + } + fmt1_str = strtok_r(argv0_str, ":", &fmt); + fmt2_str = strtok_r(NULL, "/", &fmt); + fmt3_str = strtok_r(NULL, " \t", &fmt); + if (fmt1_str == NULL || strlen(fmt1_str) != 1 || fmt2_str == NULL + || fmt3_str == NULL) { semantic_error("Failed to parse event name: %s\n", argv[0]); ret = -EINVAL; goto out; } + pr = fmt1_str[0]; + tev->group = strdup(fmt2_str); + tev->event = strdup(fmt3_str); + if (tev->group == NULL || tev->event == NULL) { + ret = -ENOMEM; + goto out; + } pr_debug("Group:%s Event:%s probe:%c\n", tev->group, tev->event, pr); tp->retprobe = (pr == 'r'); - /* Scan function name and offset */ - ret = sscanf(argv[1], "%a[^+]+%lu", (float *)(void *)&tp->symbol, - &tp->offset); - if (ret == 1) - tp->offset = 0; + /* Scan module name(if there), function name and offset */ + p = strchr(argv[1], ':'); + if (p) { + tp->module = strndup(argv[1], p - argv[1]); + p++; + } else + p = argv[1]; + fmt1_str = strtok_r(p, "+", &fmt); + if (fmt1_str[0] == '0') /* only the address started with 0x */ + tp->address = strtoul(fmt1_str, NULL, 0); + else { + /* Only the symbol-based probe has offset */ + tp->symbol = strdup(fmt1_str); + if (tp->symbol == NULL) { + ret = -ENOMEM; + goto out; + } + fmt2_str = strtok_r(NULL, "", &fmt); + if (fmt2_str == NULL) + tp->offset = 0; + else + tp->offset = strtoul(fmt2_str, NULL, 10); + } tev->nargs = argc - 2; tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); @@ -953,6 +1361,7 @@ static int parse_probe_trace_command(const char *cmd, } ret = 0; out: + free(argv0_str); argv_free(argv); return ret; } @@ -996,7 +1405,7 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len) return tmp - buf; error: - pr_debug("Failed to synthesize perf probe argument: %s", + pr_debug("Failed to synthesize perf probe argument: %s\n", strerror(-ret)); return ret; } @@ -1024,13 +1433,13 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp) goto error; } if (pp->file) { - len = strlen(pp->file) - 31; - if (len < 0) - len = 0; - tmp = strchr(pp->file + len, '/'); - if (!tmp) - tmp = pp->file + len; - ret = e_snprintf(file, 32, "@%s", tmp + 1); + tmp = pp->file; + len = strlen(tmp); + if (len > 30) { + tmp = strchr(pp->file + len - 30, '/'); + tmp = tmp ? tmp + 1 : pp->file + len - 30; + } + ret = e_snprintf(file, 32, "@%s", tmp); if (ret <= 0) goto error; } @@ -1046,10 +1455,9 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp) return buf; error: - pr_debug("Failed to synthesize perf probe point: %s", + pr_debug("Failed to synthesize perf probe point: %s\n", strerror(-ret)); - if (buf) - free(buf); + free(buf); return NULL; } @@ -1171,13 +1579,28 @@ char *synthesize_probe_trace_command(struct probe_trace_event *tev) if (buf == NULL) return NULL; - len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s+%lu", - tp->retprobe ? 'r' : 'p', - tev->group, tev->event, - tp->symbol, tp->offset); + len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p', + tev->group, tev->event); if (len <= 0) goto error; + /* Uprobes must have tp->address and tp->module */ + if (tev->uprobes && (!tp->address || !tp->module)) + goto error; + + /* Use the tp->address for uprobes */ + if (tev->uprobes) + ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx", + tp->module, tp->address); + else + ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu", + tp->module ?: "", tp->module ? ":" : "", + tp->symbol, tp->offset); + + if (ret <= 0) + goto error; + len += ret; + for (i = 0; i < tev->nargs; i++) { ret = synthesize_probe_trace_arg(&tev->args[i], buf + len, MAX_CMDLEN - len); @@ -1192,8 +1615,81 @@ error: return NULL; } +static int find_perf_probe_point_from_map(struct probe_trace_point *tp, + struct perf_probe_point *pp, + bool is_kprobe) +{ + struct symbol *sym = NULL; + struct map *map; + u64 addr; + int ret = -ENOENT; + + if (!is_kprobe) { + map = dso__new_map(tp->module); + if (!map) + goto out; + addr = tp->address; + sym = map__find_symbol(map, addr, NULL); + } else { + addr = kernel_get_symbol_address_by_name(tp->symbol, true); + if (addr) { + addr += tp->offset; + sym = __find_kernel_function(addr, &map); + } + } + if (!sym) + goto out; + + pp->retprobe = tp->retprobe; + pp->offset = addr - map->unmap_ip(map, sym->start); + pp->function = strdup(sym->name); + ret = pp->function ? 0 : -ENOMEM; + +out: + if (map && !is_kprobe) { + dso__delete(map->dso); + map__delete(map); + } + + return ret; +} + +static int convert_to_perf_probe_point(struct probe_trace_point *tp, + struct perf_probe_point *pp, + bool is_kprobe) +{ + char buf[128]; + int ret; + + ret = find_perf_probe_point_from_dwarf(tp, pp, is_kprobe); + if (!ret) + return 0; + ret = find_perf_probe_point_from_map(tp, pp, is_kprobe); + if (!ret) + return 0; + + pr_debug("Failed to find probe point from both of dwarf and map.\n"); + + if (tp->symbol) { + pp->function = strdup(tp->symbol); + pp->offset = tp->offset; + } else if (!tp->module && !is_kprobe) { + ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address); + if (ret < 0) + return ret; + pp->function = strdup(buf); + pp->offset = 0; + } + if (pp->function == NULL) + return -ENOMEM; + + pp->retprobe = tp->retprobe; + + return 0; +} + static int convert_to_perf_probe_event(struct probe_trace_event *tev, - struct perf_probe_event *pev) + struct perf_probe_event *pev, bool is_kprobe) { char buf[64] = ""; int i, ret; @@ -1205,7 +1701,7 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev, return -ENOMEM; /* Convert trace_point to probe_point */ - ret = kprobe_convert_to_perf_probe(&tev->point, &pev->point); + ret = convert_to_perf_probe_point(&tev->point, &pev->point, is_kprobe); if (ret < 0) return ret; @@ -1238,34 +1734,25 @@ void clear_perf_probe_event(struct perf_probe_event *pev) struct perf_probe_arg_field *field, *next; int i; - if (pev->event) - free(pev->event); - if (pev->group) - free(pev->group); - if (pp->file) - free(pp->file); - if (pp->function) - free(pp->function); - if (pp->lazy_line) - free(pp->lazy_line); + free(pev->event); + free(pev->group); + free(pp->file); + free(pp->function); + free(pp->lazy_line); + for (i = 0; i < pev->nargs; i++) { - if (pev->args[i].name) - free(pev->args[i].name); - if (pev->args[i].var) - free(pev->args[i].var); - if (pev->args[i].type) - free(pev->args[i].type); + free(pev->args[i].name); + free(pev->args[i].var); + free(pev->args[i].type); field = pev->args[i].field; while (field) { next = field->next; - if (field->name) - free(field->name); + zfree(&field->name); free(field); field = next; } } - if (pev->args) - free(pev->args); + free(pev->args); memset(pev, 0, sizeof(*pev)); } @@ -1274,19 +1761,14 @@ static void clear_probe_trace_event(struct probe_trace_event *tev) struct probe_trace_arg_ref *ref, *next; int i; - if (tev->event) - free(tev->event); - if (tev->group) - free(tev->group); - if (tev->point.symbol) - free(tev->point.symbol); + free(tev->event); + free(tev->group); + free(tev->point.symbol); + free(tev->point.module); for (i = 0; i < tev->nargs; i++) { - if (tev->args[i].name) - free(tev->args[i].name); - if (tev->args[i].value) - free(tev->args[i].value); - if (tev->args[i].type) - free(tev->args[i].type); + free(tev->args[i].name); + free(tev->args[i].value); + free(tev->args[i].type); ref = tev->args[i].ref; while (ref) { next = ref->next; @@ -1294,12 +1776,30 @@ static void clear_probe_trace_event(struct probe_trace_event *tev) ref = next; } } - if (tev->args) - free(tev->args); + free(tev->args); memset(tev, 0, sizeof(*tev)); } -static int open_kprobe_events(bool readwrite) +static void print_warn_msg(const char *file, bool is_kprobe) +{ + + if (errno == ENOENT) { + const char *config; + + if (!is_kprobe) + config = "CONFIG_UPROBE_EVENTS"; + else + config = "CONFIG_KPROBE_EVENTS"; + + pr_warning("%s file does not exist - please rebuild kernel" + " with %s.\n", file, config); + } else + pr_warning("Failed to open %s file: %s\n", file, + strerror(errno)); +} + +static int open_probe_events(const char *trace_file, bool readwrite, + bool is_kprobe) { char buf[PATH_MAX]; const char *__debugfs; @@ -1311,27 +1811,31 @@ static int open_kprobe_events(bool readwrite) return -ENOENT; } - ret = e_snprintf(buf, PATH_MAX, "%stracing/kprobe_events", __debugfs); + ret = e_snprintf(buf, PATH_MAX, "%s/%s", __debugfs, trace_file); if (ret >= 0) { pr_debug("Opening %s write=%d\n", buf, readwrite); if (readwrite && !probe_event_dry_run) ret = open(buf, O_RDWR, O_APPEND); else ret = open(buf, O_RDONLY, 0); - } - if (ret < 0) { - if (errno == ENOENT) - pr_warning("kprobe_events file does not exist - please" - " rebuild kernel with CONFIG_KPROBE_EVENT.\n"); - else - pr_warning("Failed to open kprobe_events file: %s\n", - strerror(errno)); + if (ret < 0) + print_warn_msg(buf, is_kprobe); } return ret; } -/* Get raw string list of current kprobe_events */ +static int open_kprobe_events(bool readwrite) +{ + return open_probe_events("tracing/kprobe_events", readwrite, true); +} + +static int open_uprobe_events(bool readwrite) +{ + return open_probe_events("tracing/uprobe_events", readwrite, false); +} + +/* Get raw string list of current kprobe_events or uprobe_events */ static struct strlist *get_probe_trace_command_rawlist(int fd) { int ret, idx; @@ -1364,7 +1868,8 @@ static struct strlist *get_probe_trace_command_rawlist(int fd) } /* Show an event */ -static int show_perf_probe_event(struct perf_probe_event *pev) +static int show_perf_probe_event(struct perf_probe_event *pev, + const char *module) { int i, ret; char buf[128]; @@ -1380,6 +1885,8 @@ static int show_perf_probe_event(struct perf_probe_event *pev) return ret; printf(" %-20s (on %s", buf, place); + if (module) + printf(" in %s", module); if (pev->nargs > 0) { printf(" with"); @@ -1396,38 +1903,29 @@ static int show_perf_probe_event(struct perf_probe_event *pev) return ret; } -/* List up current perf-probe events */ -int show_perf_probe_events(void) +static int __show_perf_probe_events(int fd, bool is_kprobe) { - int fd, ret; + int ret = 0; struct probe_trace_event tev; struct perf_probe_event pev; struct strlist *rawlist; struct str_node *ent; - setup_pager(); - ret = init_vmlinux(); - if (ret < 0) - return ret; - memset(&tev, 0, sizeof(tev)); memset(&pev, 0, sizeof(pev)); - fd = open_kprobe_events(false); - if (fd < 0) - return fd; - rawlist = get_probe_trace_command_rawlist(fd); - close(fd); if (!rawlist) return -ENOENT; strlist__for_each(ent, rawlist) { ret = parse_probe_trace_command(ent->s, &tev); if (ret >= 0) { - ret = convert_to_perf_probe_event(&tev, &pev); + ret = convert_to_perf_probe_event(&tev, &pev, + is_kprobe); if (ret >= 0) - ret = show_perf_probe_event(&pev); + ret = show_perf_probe_event(&pev, + tev.point.module); } clear_perf_probe_event(&pev); clear_probe_trace_event(&tev); @@ -1439,6 +1937,34 @@ int show_perf_probe_events(void) return ret; } +/* List up current perf-probe events */ +int show_perf_probe_events(void) +{ + int fd, ret; + + setup_pager(); + fd = open_kprobe_events(false); + + if (fd < 0) + return fd; + + ret = init_symbol_maps(false); + if (ret < 0) + return ret; + + ret = __show_perf_probe_events(fd, true); + close(fd); + + fd = open_uprobe_events(false); + if (fd >= 0) { + ret = __show_perf_probe_events(fd, false); + close(fd); + } + + exit_symbol_maps(); + return ret; +} + /* Get current perf-probe event names */ static struct strlist *get_probe_trace_event_names(int fd, bool include_group) { @@ -1544,7 +2070,11 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, const char *event, *group; struct strlist *namelist; - fd = open_kprobe_events(true); + if (pev->uprobes) + fd = open_uprobe_events(true); + else + fd = open_kprobe_events(true); + if (fd < 0) return fd; /* Get current event names */ @@ -1555,7 +2085,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, } ret = 0; - printf("Add new event%s\n", (ntevs > 1) ? "s:" : ":"); + printf("Added new event%s\n", (ntevs > 1) ? "s:" : ":"); for (i = 0; i < ntevs; i++) { tev = &tevs[i]; if (pev->event) @@ -1594,7 +2124,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, group = pev->group; pev->event = tev->event; pev->group = tev->group; - show_perf_probe_event(pev); + show_perf_probe_event(pev, tev->point.module); /* Trick here - restore current event/group */ pev->event = (char *)event; pev->group = (char *)group; @@ -1610,7 +2140,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, if (ret >= 0) { /* Show how to use the event. */ - printf("\nYou can now use it on all perf tools, such as:\n\n"); + printf("\nYou can now use it in all perf tools, such as:\n\n"); printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group, tev->event); } @@ -1620,78 +2150,175 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, return ret; } -static int convert_to_probe_trace_events(struct perf_probe_event *pev, - struct probe_trace_event **tevs, - int max_tevs, const char *module) +static char *looking_function_name; +static int num_matched_functions; + +static int probe_function_filter(struct map *map __maybe_unused, + struct symbol *sym) +{ + if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) && + strcmp(looking_function_name, sym->name) == 0) { + num_matched_functions++; + return 0; + } + return 1; +} + +#define strdup_or_goto(str, label) \ + ({ char *__p = strdup(str); if (!__p) goto label; __p; }) + +/* + * Find probe function addresses from map. + * Return an error or the number of found probe_trace_event + */ +static int find_probe_trace_events_from_map(struct perf_probe_event *pev, + struct probe_trace_event **tevs, + int max_tevs, const char *target) { + struct map *map = NULL; + struct kmap *kmap = NULL; + struct ref_reloc_sym *reloc_sym = NULL; struct symbol *sym; - int ret = 0, i; + struct rb_node *nd; struct probe_trace_event *tev; + struct perf_probe_point *pp = &pev->point; + struct probe_trace_point *tp; + int ret, i; - /* Convert perf_probe_event with debuginfo */ - ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, module); - if (ret != 0) - return ret; + /* Init maps of given executable or kernel */ + if (pev->uprobes) + map = dso__new_map(target); + else + map = kernel_get_module_map(target); + if (!map) { + ret = -EINVAL; + goto out; + } - /* Allocate trace event buffer */ - tev = *tevs = zalloc(sizeof(struct probe_trace_event)); - if (tev == NULL) - return -ENOMEM; + /* + * Load matched symbols: Since the different local symbols may have + * same name but different addresses, this lists all the symbols. + */ + num_matched_functions = 0; + looking_function_name = pp->function; + ret = map__load(map, probe_function_filter); + if (ret || num_matched_functions == 0) { + pr_err("Failed to find symbol %s in %s\n", pp->function, + target ? : "kernel"); + ret = -ENOENT; + goto out; + } else if (num_matched_functions > max_tevs) { + pr_err("Too many functions matched in %s\n", + target ? : "kernel"); + ret = -E2BIG; + goto out; + } + + if (!pev->uprobes) { + kmap = map__kmap(map); + reloc_sym = kmap->ref_reloc_sym; + if (!reloc_sym) { + pr_warning("Relocated base symbol is not found!\n"); + ret = -EINVAL; + goto out; + } + } - /* Copy parameters */ - tev->point.symbol = strdup(pev->point.function); - if (tev->point.symbol == NULL) { + /* Setup result trace-probe-events */ + *tevs = zalloc(sizeof(*tev) * num_matched_functions); + if (!*tevs) { ret = -ENOMEM; - goto error; + goto out; } - tev->point.offset = pev->point.offset; - tev->point.retprobe = pev->point.retprobe; - tev->nargs = pev->nargs; - if (tev->nargs) { - tev->args = zalloc(sizeof(struct probe_trace_arg) - * tev->nargs); - if (tev->args == NULL) { - ret = -ENOMEM; - goto error; + + ret = 0; + map__for_each_symbol(map, sym, nd) { + tev = (*tevs) + ret; + tp = &tev->point; + if (ret == num_matched_functions) { + pr_warning("Too many symbols are listed. Skip it.\n"); + break; + } + ret++; + + if (pp->offset > sym->end - sym->start) { + pr_warning("Offset %ld is bigger than the size of %s\n", + pp->offset, sym->name); + ret = -ENOENT; + goto err_out; + } + /* Add one probe point */ + tp->address = map->unmap_ip(map, sym->start) + pp->offset; + if (reloc_sym) { + tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out); + tp->offset = tp->address - reloc_sym->addr; + } else { + tp->symbol = strdup_or_goto(sym->name, nomem_out); + tp->offset = pp->offset; + } + tp->retprobe = pp->retprobe; + if (target) + tev->point.module = strdup_or_goto(target, nomem_out); + tev->uprobes = pev->uprobes; + tev->nargs = pev->nargs; + if (tev->nargs) { + tev->args = zalloc(sizeof(struct probe_trace_arg) * + tev->nargs); + if (tev->args == NULL) + goto nomem_out; } for (i = 0; i < tev->nargs; i++) { - if (pev->args[i].name) { - tev->args[i].name = strdup(pev->args[i].name); - if (tev->args[i].name == NULL) { - ret = -ENOMEM; - goto error; - } - } - tev->args[i].value = strdup(pev->args[i].var); - if (tev->args[i].value == NULL) { - ret = -ENOMEM; - goto error; - } - if (pev->args[i].type) { - tev->args[i].type = strdup(pev->args[i].type); - if (tev->args[i].type == NULL) { - ret = -ENOMEM; - goto error; - } - } + if (pev->args[i].name) + tev->args[i].name = + strdup_or_goto(pev->args[i].name, + nomem_out); + + tev->args[i].value = strdup_or_goto(pev->args[i].var, + nomem_out); + if (pev->args[i].type) + tev->args[i].type = + strdup_or_goto(pev->args[i].type, + nomem_out); } } - /* Currently just checking function name from symbol map */ - sym = __find_kernel_function_by_name(tev->point.symbol, NULL); - if (!sym) { - pr_warning("Kernel symbol \'%s\' not found.\n", - tev->point.symbol); - ret = -ENOENT; - goto error; +out: + if (map && pev->uprobes) { + /* Only when using uprobe(exec) map needs to be released */ + dso__delete(map->dso); + map__delete(map); } - - return 1; -error: - clear_probe_trace_event(tev); - free(tev); - *tevs = NULL; return ret; + +nomem_out: + ret = -ENOMEM; +err_out: + clear_probe_trace_events(*tevs, num_matched_functions); + zfree(tevs); + goto out; +} + +static int convert_to_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event **tevs, + int max_tevs, const char *target) +{ + int ret; + + if (pev->uprobes && !pev->group) { + /* Replace group name if not given */ + ret = convert_exec_to_group(target, &pev->group); + if (ret != 0) { + pr_warning("Failed to make a group name.\n"); + return ret; + } + } + + /* Convert perf_probe_event with debuginfo */ + ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target); + if (ret != 0) + return ret; /* Found in debuginfo or got an error */ + + return find_probe_trace_events_from_map(pev, tevs, max_tevs, target); } struct __event_package { @@ -1701,17 +2328,18 @@ struct __event_package { }; int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, - int max_tevs, const char *module, bool force_add) + int max_tevs, const char *target, bool force_add) { int i, j, ret; struct __event_package *pkgs; + ret = 0; pkgs = zalloc(sizeof(struct __event_package) * npevs); + if (pkgs == NULL) return -ENOMEM; - /* Init vmlinux path */ - ret = init_vmlinux(); + ret = init_symbol_maps(pevs->uprobes); if (ret < 0) { free(pkgs); return ret; @@ -1724,24 +2352,28 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, ret = convert_to_probe_trace_events(pkgs[i].pev, &pkgs[i].tevs, max_tevs, - module); + target); if (ret < 0) goto end; pkgs[i].ntevs = ret; } /* Loop 2: add all events */ - for (i = 0; i < npevs && ret >= 0; i++) + for (i = 0; i < npevs; i++) { ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs, pkgs[i].ntevs, force_add); + if (ret < 0) + break; + } end: /* Loop 3: cleanup and free trace events */ for (i = 0; i < npevs; i++) { for (j = 0; j < pkgs[i].ntevs; j++) clear_probe_trace_event(&pkgs[i].tevs[j]); - free(pkgs[i].tevs); + zfree(&pkgs[i].tevs); } free(pkgs); + exit_symbol_maps(); return ret; } @@ -1768,33 +2400,27 @@ static int __del_trace_probe_event(int fd, struct str_node *ent) pr_debug("Writing event: %s\n", buf); ret = write(fd, buf, strlen(buf)); - if (ret < 0) + if (ret < 0) { + ret = -errno; goto error; + } - printf("Remove event: %s\n", ent->s); + printf("Removed event: %s\n", ent->s); return 0; error: pr_warning("Failed to delete event: %s\n", strerror(-ret)); return ret; } -static int del_trace_probe_event(int fd, const char *group, - const char *event, struct strlist *namelist) +static int del_trace_probe_event(int fd, const char *buf, + struct strlist *namelist) { - char buf[128]; struct str_node *ent, *n; - int found = 0, ret = 0; - - ret = e_snprintf(buf, 128, "%s:%s", group, event); - if (ret < 0) { - pr_err("Failed to copy event."); - return ret; - } + int ret = -1; if (strpbrk(buf, "*?")) { /* Glob-exp */ strlist__for_each_safe(ent, n, namelist) if (strglobmatch(ent->s, buf)) { - found++; ret = __del_trace_probe_event(fd, ent); if (ret < 0) break; @@ -1803,40 +2429,43 @@ static int del_trace_probe_event(int fd, const char *group, } else { ent = strlist__find(namelist, buf); if (ent) { - found++; ret = __del_trace_probe_event(fd, ent); if (ret >= 0) strlist__remove(namelist, ent); } } - if (found == 0 && ret >= 0) - pr_info("Info: Event \"%s\" does not exist.\n", buf); return ret; } int del_perf_probe_events(struct strlist *dellist) { - int fd, ret = 0; + int ret = -1, ufd = -1, kfd = -1; + char buf[128]; const char *group, *event; char *p, *str; struct str_node *ent; - struct strlist *namelist; - - fd = open_kprobe_events(true); - if (fd < 0) - return fd; + struct strlist *namelist = NULL, *unamelist = NULL; /* Get current event names */ - namelist = get_probe_trace_event_names(fd, true); - if (namelist == NULL) - return -EINVAL; + kfd = open_kprobe_events(true); + if (kfd < 0) + return kfd; + + namelist = get_probe_trace_event_names(kfd, true); + ufd = open_uprobe_events(true); + + if (ufd >= 0) + unamelist = get_probe_trace_event_names(ufd, true); + + if (namelist == NULL && unamelist == NULL) + goto error; strlist__for_each(ent, dellist) { str = strdup(ent->s); if (str == NULL) { ret = -ENOMEM; - break; + goto error; } pr_debug("Parsing: %s\n", str); p = strchr(str, ':'); @@ -1848,14 +2477,96 @@ int del_perf_probe_events(struct strlist *dellist) group = "*"; event = str; } + + ret = e_snprintf(buf, 128, "%s:%s", group, event); + if (ret < 0) { + pr_err("Failed to copy event."); + free(str); + goto error; + } + pr_debug("Group: %s, Event: %s\n", group, event); - ret = del_trace_probe_event(fd, group, event, namelist); + + if (namelist) + ret = del_trace_probe_event(kfd, buf, namelist); + + if (unamelist && ret != 0) + ret = del_trace_probe_event(ufd, buf, unamelist); + + if (ret != 0) + pr_info("Info: Event \"%s\" does not exist.\n", buf); + free(str); - if (ret < 0) - break; } - strlist__delete(namelist); - close(fd); + +error: + if (kfd >= 0) { + strlist__delete(namelist); + close(kfd); + } + + if (ufd >= 0) { + strlist__delete(unamelist); + close(ufd); + } + + return ret; +} + +/* TODO: don't use a global variable for filter ... */ +static struct strfilter *available_func_filter; + +/* + * If a symbol corresponds to a function with global binding and + * matches filter return 0. For all others return 1. + */ +static int filter_available_functions(struct map *map __maybe_unused, + struct symbol *sym) +{ + if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) && + strfilter__compare(available_func_filter, sym->name)) + return 0; + return 1; +} + +int show_available_funcs(const char *target, struct strfilter *_filter, + bool user) +{ + struct map *map; + int ret; + + ret = init_symbol_maps(user); + if (ret < 0) + return ret; + + /* Get a symbol map */ + if (user) + map = dso__new_map(target); + else + map = kernel_get_module_map(target); + if (!map) { + pr_err("Failed to get a map for %s\n", (target) ? : "kernel"); + return -EINVAL; + } + + /* Load symbols with given filter */ + available_func_filter = _filter; + if (map__load(map, filter_available_functions)) { + pr_err("Failed to load symbols in %s\n", (target) ? : "kernel"); + goto end; + } + if (!dso__sorted_by_name(map->dso, map->type)) + dso__sort_by_name(map->dso, map->type); + + /* Show all (filtered) symbols */ + setup_pager(); + dso__fprintf_symbols_by_name(map->dso, map->type, stdout); +end: + if (user) { + dso__delete(map->dso); + map__delete(map); + } + exit_symbol_maps(); return ret; } diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 5accbedfea3..776c9347a3b 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -2,14 +2,18 @@ #define _PROBE_EVENT_H #include <stdbool.h> +#include "intlist.h" #include "strlist.h" +#include "strfilter.h" extern bool probe_event_dry_run; -/* kprobe-tracer tracing point */ +/* kprobe-tracer and uprobe-tracer tracing point */ struct probe_trace_point { char *symbol; /* Base symbol */ + char *module; /* Module name */ unsigned long offset; /* Offset from symbol */ + unsigned long address; /* Actual address of the trace point */ bool retprobe; /* Return probe flag */ }; @@ -19,7 +23,7 @@ struct probe_trace_arg_ref { long offset; /* Offset value */ }; -/* kprobe-tracer tracing argument */ +/* kprobe-tracer and uprobe-tracer tracing argument */ struct probe_trace_arg { char *name; /* Argument name */ char *value; /* Base value */ @@ -27,12 +31,13 @@ struct probe_trace_arg { struct probe_trace_arg_ref *ref; /* Referencing offset */ }; -/* kprobe-tracer tracing event (point + arg) */ +/* kprobe-tracer and uprobe-tracer tracing event (point + arg) */ struct probe_trace_event { char *event; /* Event name */ char *group; /* Group name */ struct probe_trace_point point; /* Trace point */ int nargs; /* Number of args */ + bool uprobes; /* uprobes only */ struct probe_trace_arg *args; /* Arguments */ }; @@ -68,16 +73,10 @@ struct perf_probe_event { char *group; /* Group name */ struct perf_probe_point point; /* Probe point */ int nargs; /* Number of arguments */ + bool uprobes; struct perf_probe_arg *args; /* Arguments */ }; - -/* Line number container */ -struct line_node { - struct list_head list; - int line; -}; - /* Line range */ struct line_range { char *file; /* File name */ @@ -87,7 +86,7 @@ struct line_range { int offset; /* Start line offset */ char *path; /* Real path name */ char *comp_dir; /* Compile directory */ - struct list_head line_list; /* Visible lines */ + struct intlist *line_list; /* Visible lines */ }; /* List of variables */ @@ -115,6 +114,12 @@ extern void clear_perf_probe_event(struct perf_probe_event *pev); /* Command string to line-range */ extern int parse_line_range_desc(const char *cmd, struct line_range *lr); +/* Release line range members */ +extern void line_range__clear(struct line_range *lr); + +/* Initialize line range */ +extern int line_range__init(struct line_range *lr); + /* Internal use: Return kernel/module path */ extern const char *kernel_get_module_path(const char *module); @@ -126,8 +131,9 @@ extern int show_perf_probe_events(void); extern int show_line_range(struct line_range *lr, const char *module); extern int show_available_vars(struct perf_probe_event *pevs, int npevs, int max_probe_points, const char *module, - bool externs); - + struct strfilter *filter, bool externs); +extern int show_available_funcs(const char *module, struct strfilter *filter, + bool user); /* Maximum index number of event-name postfix */ #define MAX_EVENT_INDEX 1024 diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 3991d73d1cf..98e30476641 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -30,11 +30,13 @@ #include <stdlib.h> #include <string.h> #include <stdarg.h> -#include <ctype.h> #include <dwarf-regs.h> +#include <linux/bitops.h> #include "event.h" +#include "dso.h" #include "debug.h" +#include "intlist.h" #include "util.h" #include "symbol.h" #include "probe-finder.h" @@ -42,103 +44,7 @@ /* Kprobe tracer basic type is up to u64 */ #define MAX_BASIC_TYPE_BITS 64 -/* - * Compare the tail of two strings. - * Return 0 if whole of either string is same as another's tail part. - */ -static int strtailcmp(const char *s1, const char *s2) -{ - int i1 = strlen(s1); - int i2 = strlen(s2); - while (--i1 >= 0 && --i2 >= 0) { - if (s1[i1] != s2[i2]) - return s1[i1] - s2[i2]; - } - return 0; -} - -/* Line number list operations */ - -/* Add a line to line number list */ -static int line_list__add_line(struct list_head *head, int line) -{ - struct line_node *ln; - struct list_head *p; - - /* Reverse search, because new line will be the last one */ - list_for_each_entry_reverse(ln, head, list) { - if (ln->line < line) { - p = &ln->list; - goto found; - } else if (ln->line == line) /* Already exist */ - return 1; - } - /* List is empty, or the smallest entry */ - p = head; -found: - pr_debug("line list: add a line %u\n", line); - ln = zalloc(sizeof(struct line_node)); - if (ln == NULL) - return -ENOMEM; - ln->line = line; - INIT_LIST_HEAD(&ln->list); - list_add(&ln->list, p); - return 0; -} - -/* Check if the line in line number list */ -static int line_list__has_line(struct list_head *head, int line) -{ - struct line_node *ln; - - /* Reverse search, because new line will be the last one */ - list_for_each_entry(ln, head, list) - if (ln->line == line) - return 1; - - return 0; -} - -/* Init line number list */ -static void line_list__init(struct list_head *head) -{ - INIT_LIST_HEAD(head); -} - -/* Free line number list */ -static void line_list__free(struct list_head *head) -{ - struct line_node *ln; - while (!list_empty(head)) { - ln = list_first_entry(head, struct line_node, list); - list_del(&ln->list); - free(ln); - } -} - /* Dwarf FL wrappers */ - -static int __linux_kernel_find_elf(Dwfl_Module *mod, - void **userdata, - const char *module_name, - Dwarf_Addr base, - char **file_name, Elf **elfp) -{ - int fd; - const char *path = kernel_get_module_path(module_name); - - if (path) { - fd = open(path, O_RDONLY); - if (fd >= 0) { - *file_name = strdup(path); - return fd; - } - } - /* If failed, try to call standard method */ - return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base, - file_name, elfp); -} - static char *debuginfo_path; /* Currently dummy */ static const Dwfl_Callbacks offline_callbacks = { @@ -151,391 +57,94 @@ static const Dwfl_Callbacks offline_callbacks = { .find_elf = dwfl_build_id_find_elf, }; -static const Dwfl_Callbacks kernel_callbacks = { - .find_debuginfo = dwfl_standard_find_debuginfo, - .debuginfo_path = &debuginfo_path, - - .find_elf = __linux_kernel_find_elf, - .section_address = dwfl_linux_kernel_module_section_address, -}; - /* Get a Dwarf from offline image */ -static Dwarf *dwfl_init_offline_dwarf(int fd, Dwfl **dwflp, Dwarf_Addr *bias) +static int debuginfo__init_offline_dwarf(struct debuginfo *dbg, + const char *path) { - Dwfl_Module *mod; - Dwarf *dbg = NULL; - - if (!dwflp) - return NULL; + int fd; - *dwflp = dwfl_begin(&offline_callbacks); - if (!*dwflp) - return NULL; + fd = open(path, O_RDONLY); + if (fd < 0) + return fd; - mod = dwfl_report_offline(*dwflp, "", "", fd); - if (!mod) + dbg->dwfl = dwfl_begin(&offline_callbacks); + if (!dbg->dwfl) goto error; - dbg = dwfl_module_getdwarf(mod, bias); - if (!dbg) { -error: - dwfl_end(*dwflp); - *dwflp = NULL; - } - return dbg; -} - -/* Get a Dwarf from live kernel image */ -static Dwarf *dwfl_init_live_kernel_dwarf(Dwarf_Addr addr, Dwfl **dwflp, - Dwarf_Addr *bias) -{ - Dwarf *dbg; - - if (!dwflp) - return NULL; - - *dwflp = dwfl_begin(&kernel_callbacks); - if (!*dwflp) - return NULL; - - /* Load the kernel dwarves: Don't care the result here */ - dwfl_linux_kernel_report_kernel(*dwflp); - dwfl_linux_kernel_report_modules(*dwflp); - - dbg = dwfl_addrdwarf(*dwflp, addr, bias); - /* Here, check whether we could get a real dwarf */ - if (!dbg) { - dwfl_end(*dwflp); - *dwflp = NULL; - } - return dbg; -} - -/* Dwarf wrappers */ - -/* Find the realpath of the target file. */ -static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname) -{ - Dwarf_Files *files; - size_t nfiles, i; - const char *src = NULL; - int ret; - - if (!fname) - return NULL; - - ret = dwarf_getsrcfiles(cu_die, &files, &nfiles); - if (ret != 0) - return NULL; - - for (i = 0; i < nfiles; i++) { - src = dwarf_filesrc(files, i, NULL, NULL); - if (strtailcmp(src, fname) == 0) - break; - } - if (i == nfiles) - return NULL; - return src; -} - -/* Get DW_AT_comp_dir (should be NULL with older gcc) */ -static const char *cu_get_comp_dir(Dwarf_Die *cu_die) -{ - Dwarf_Attribute attr; - if (dwarf_attr(cu_die, DW_AT_comp_dir, &attr) == NULL) - return NULL; - return dwarf_formstring(&attr); -} - -/* Compare diename and tname */ -static bool die_compare_name(Dwarf_Die *dw_die, const char *tname) -{ - const char *name; - name = dwarf_diename(dw_die); - return name ? (strcmp(tname, name) == 0) : false; -} + dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd); + if (!dbg->mod) + goto error; -/* Get type die */ -static Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) -{ - Dwarf_Attribute attr; + dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias); + if (!dbg->dbg) + goto error; - if (dwarf_attr_integrate(vr_die, DW_AT_type, &attr) && - dwarf_formref_die(&attr, die_mem)) - return die_mem; + return 0; +error: + if (dbg->dwfl) + dwfl_end(dbg->dwfl); else - return NULL; -} + close(fd); + memset(dbg, 0, sizeof(*dbg)); -/* Get a type die, but skip qualifiers */ -static Dwarf_Die *__die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) -{ - int tag; - - do { - vr_die = die_get_type(vr_die, die_mem); - if (!vr_die) - break; - tag = dwarf_tag(vr_die); - } while (tag == DW_TAG_const_type || - tag == DW_TAG_restrict_type || - tag == DW_TAG_volatile_type || - tag == DW_TAG_shared_type); - - return vr_die; -} - -/* Get a type die, but skip qualifiers and typedef */ -static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) -{ - do { - vr_die = __die_get_real_type(vr_die, die_mem); - } while (vr_die && dwarf_tag(vr_die) == DW_TAG_typedef); - - return vr_die; -} - -static bool die_is_signed_type(Dwarf_Die *tp_die) -{ - Dwarf_Attribute attr; - Dwarf_Word ret; - - if (dwarf_attr(tp_die, DW_AT_encoding, &attr) == NULL || - dwarf_formudata(&attr, &ret) != 0) - return false; - - return (ret == DW_ATE_signed_char || ret == DW_ATE_signed || - ret == DW_ATE_signed_fixed); -} - -static int die_get_byte_size(Dwarf_Die *tp_die) -{ - Dwarf_Attribute attr; - Dwarf_Word ret; - - if (dwarf_attr(tp_die, DW_AT_byte_size, &attr) == NULL || - dwarf_formudata(&attr, &ret) != 0) - return 0; - - return (int)ret; + return -ENOENT; } -/* Get data_member_location offset */ -static int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs) +static struct debuginfo *__debuginfo__new(const char *path) { - Dwarf_Attribute attr; - Dwarf_Op *expr; - size_t nexpr; - int ret; - - if (dwarf_attr(mb_die, DW_AT_data_member_location, &attr) == NULL) - return -ENOENT; - - if (dwarf_formudata(&attr, offs) != 0) { - /* DW_AT_data_member_location should be DW_OP_plus_uconst */ - ret = dwarf_getlocation(&attr, &expr, &nexpr); - if (ret < 0 || nexpr == 0) - return -ENOENT; - - if (expr[0].atom != DW_OP_plus_uconst || nexpr != 1) { - pr_debug("Unable to get offset:Unexpected OP %x (%zd)\n", - expr[0].atom, nexpr); - return -ENOTSUP; - } - *offs = (Dwarf_Word)expr[0].number; - } - return 0; -} - -/* Return values for die_find callbacks */ -enum { - DIE_FIND_CB_FOUND = 0, /* End of Search */ - DIE_FIND_CB_CHILD = 1, /* Search only children */ - DIE_FIND_CB_SIBLING = 2, /* Search only siblings */ - DIE_FIND_CB_CONTINUE = 3, /* Search children and siblings */ -}; - -/* Search a child die */ -static Dwarf_Die *die_find_child(Dwarf_Die *rt_die, - int (*callback)(Dwarf_Die *, void *), - void *data, Dwarf_Die *die_mem) -{ - Dwarf_Die child_die; - int ret; - - ret = dwarf_child(rt_die, die_mem); - if (ret != 0) + struct debuginfo *dbg = zalloc(sizeof(*dbg)); + if (!dbg) return NULL; - do { - ret = callback(die_mem, data); - if (ret == DIE_FIND_CB_FOUND) - return die_mem; - - if ((ret & DIE_FIND_CB_CHILD) && - die_find_child(die_mem, callback, data, &child_die)) { - memcpy(die_mem, &child_die, sizeof(Dwarf_Die)); - return die_mem; - } - } while ((ret & DIE_FIND_CB_SIBLING) && - dwarf_siblingof(die_mem, die_mem) == 0); - - return NULL; + if (debuginfo__init_offline_dwarf(dbg, path) < 0) + zfree(&dbg); + if (dbg) + pr_debug("Open Debuginfo file: %s\n", path); + return dbg; } -struct __addr_die_search_param { - Dwarf_Addr addr; - Dwarf_Die *die_mem; +enum dso_binary_type distro_dwarf_types[] = { + DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, + DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__NOT_FOUND, }; -static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) +struct debuginfo *debuginfo__new(const char *path) { - struct __addr_die_search_param *ad = data; + enum dso_binary_type *type; + char buf[PATH_MAX], nil = '\0'; + struct dso *dso; + struct debuginfo *dinfo = NULL; + + /* Try to open distro debuginfo files */ + dso = dso__new(path); + if (!dso) + goto out; - if (dwarf_tag(fn_die) == DW_TAG_subprogram && - dwarf_haspc(fn_die, ad->addr)) { - memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die)); - return DWARF_CB_ABORT; + for (type = distro_dwarf_types; + !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND; + type++) { + if (dso__read_binary_type_filename(dso, *type, &nil, + buf, PATH_MAX) < 0) + continue; + dinfo = __debuginfo__new(buf); } - return DWARF_CB_OK; -} - -/* Search a real subprogram including this line, */ -static Dwarf_Die *die_find_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr, - Dwarf_Die *die_mem) -{ - struct __addr_die_search_param ad; - ad.addr = addr; - ad.die_mem = die_mem; - /* dwarf_getscopes can't find subprogram. */ - if (!dwarf_getfuncs(cu_die, __die_search_func_cb, &ad, 0)) - return NULL; - else - return die_mem; -} - -/* die_find callback for inline function search */ -static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data) -{ - Dwarf_Addr *addr = data; + dso__delete(dso); - if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine && - dwarf_haspc(die_mem, *addr)) - return DIE_FIND_CB_FOUND; - - return DIE_FIND_CB_CONTINUE; -} - -/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */ -static Dwarf_Die *die_find_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); -} - -struct __find_variable_param { - const char *name; - Dwarf_Addr addr; -}; - -static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data) -{ - struct __find_variable_param *fvp = data; - int tag; - - tag = dwarf_tag(die_mem); - if ((tag == DW_TAG_formal_parameter || - tag == DW_TAG_variable) && - die_compare_name(die_mem, fvp->name)) - return DIE_FIND_CB_FOUND; - - if (dwarf_haspc(die_mem, fvp->addr)) - return DIE_FIND_CB_CONTINUE; - else - return DIE_FIND_CB_SIBLING; -} - -/* Find a variable called 'name' at given address */ -static Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name, - Dwarf_Addr addr, Dwarf_Die *die_mem) -{ - struct __find_variable_param fvp = { .name = name, .addr = addr}; - - return die_find_child(sp_die, __die_find_variable_cb, (void *)&fvp, - die_mem); -} - -static int __die_find_member_cb(Dwarf_Die *die_mem, void *data) -{ - const char *name = data; - - if ((dwarf_tag(die_mem) == DW_TAG_member) && - die_compare_name(die_mem, name)) - return DIE_FIND_CB_FOUND; - - return DIE_FIND_CB_SIBLING; -} - -/* Find a member called 'name' */ -static Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name, - Dwarf_Die *die_mem) -{ - return die_find_child(st_die, __die_find_member_cb, (void *)name, - die_mem); -} - -/* Get the name of given variable DIE */ -static int die_get_typename(Dwarf_Die *vr_die, char *buf, int len) -{ - Dwarf_Die type; - int tag, ret, ret2; - const char *tmp = ""; - - if (__die_get_real_type(vr_die, &type) == NULL) - return -ENOENT; - - tag = dwarf_tag(&type); - if (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type) - tmp = "*"; - else if (tag == DW_TAG_subroutine_type) { - /* Function pointer */ - ret = snprintf(buf, len, "(function_type)"); - return (ret >= len) ? -E2BIG : ret; - } else { - if (!dwarf_diename(&type)) - return -ENOENT; - if (tag == DW_TAG_union_type) - tmp = "union "; - else if (tag == DW_TAG_structure_type) - tmp = "struct "; - /* Write a base name */ - ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type)); - return (ret >= len) ? -E2BIG : ret; - } - ret = die_get_typename(&type, buf, len); - if (ret > 0) { - ret2 = snprintf(buf + ret, len - ret, "%s", tmp); - ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret; - } - return ret; +out: + /* if failed to open all distro debuginfo, open given binary */ + return dinfo ? : __debuginfo__new(path); } -/* Get the name and type of given variable DIE, stored as "type\tname" */ -static int die_get_varname(Dwarf_Die *vr_die, char *buf, int len) +void debuginfo__delete(struct debuginfo *dbg) { - int ret, ret2; - - ret = die_get_typename(vr_die, buf, len); - if (ret < 0) { - pr_debug("Failed to get type, make it unknown.\n"); - ret = snprintf(buf, len, "(unknown_type)"); + if (dbg) { + if (dbg->dwfl) + dwfl_end(dbg->dwfl); + free(dbg); } - if (ret > 0) { - ret2 = snprintf(buf + ret, len - ret, "\t%s", - dwarf_diename(vr_die)); - ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret; - } - return ret; } /* @@ -554,12 +163,15 @@ 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; @@ -572,12 +184,29 @@ 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: @@ -627,8 +256,8 @@ static_var: regs = get_arch_regstr(regn); if (!regs) { /* This should be a bug in DWARF or this tool */ - pr_warning("Mapping for DWARF register number %u " - "missing on this architecture.", regn); + pr_warning("Mapping for the register number %u " + "missing on this architecture.\n", regn); return -ERANGE; } @@ -644,6 +273,8 @@ static_var: return 0; } +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_LONG / sizeof(long)) + static int convert_variable_type(Dwarf_Die *vr_die, struct probe_trace_arg *tvar, const char *cast) @@ -651,6 +282,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, struct probe_trace_arg_ref **ref_ptr = &tvar->ref; Dwarf_Die type; char buf[16]; + int bsize, boffs, total; int ret; /* TODO: check all types */ @@ -660,6 +292,18 @@ static int convert_variable_type(Dwarf_Die *vr_die, return (tvar->type == NULL) ? -ENOMEM : 0; } + bsize = dwarf_bitsize(vr_die); + if (bsize > 0) { + /* This is a bitfield */ + boffs = dwarf_bitoffset(vr_die); + total = dwarf_bytesize(vr_die); + if (boffs < 0 || total < 0) + return -ENOENT; + ret = snprintf(buf, 16, "b%d@%d/%zd", bsize, boffs, + BYTES_TO_BITS(total)); + goto formatted; + } + if (die_get_real_type(vr_die, &type) == NULL) { pr_warning("Failed to get a type information of %s.\n", dwarf_diename(vr_die)); @@ -674,15 +318,16 @@ static int convert_variable_type(Dwarf_Die *vr_die, if (ret != DW_TAG_pointer_type && ret != DW_TAG_array_type) { pr_warning("Failed to cast into string: " - "%s(%s) is not a pointer nor array.", + "%s(%s) is not a pointer nor array.\n", dwarf_diename(vr_die), dwarf_diename(&type)); return -EINVAL; } + if (die_get_real_type(&type, &type) == NULL) { + pr_warning("Failed to get a type" + " information.\n"); + return -ENOENT; + } if (ret == DW_TAG_pointer_type) { - if (die_get_real_type(&type, &type) == NULL) { - pr_warning("Failed to get a type information."); - return -ENOENT; - } while (*ref_ptr) ref_ptr = &(*ref_ptr)->next; /* Add new reference with offset +0 */ @@ -695,7 +340,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, if (!die_compare_name(&type, "char") && !die_compare_name(&type, "unsigned char")) { pr_warning("Failed to cast into string: " - "%s is not (unsigned) char *.", + "%s is not (unsigned) char *.\n", dwarf_diename(vr_die)); return -EINVAL; } @@ -703,29 +348,32 @@ static int convert_variable_type(Dwarf_Die *vr_die, return (tvar->type == NULL) ? -ENOMEM : 0; } - ret = die_get_byte_size(&type) * 8; - if (ret) { - /* Check the bitwidth */ - if (ret > MAX_BASIC_TYPE_BITS) { - pr_info("%s exceeds max-bitwidth." - " Cut down to %d bits.\n", - dwarf_diename(&type), MAX_BASIC_TYPE_BITS); - ret = MAX_BASIC_TYPE_BITS; - } - - ret = snprintf(buf, 16, "%c%d", - die_is_signed_type(&type) ? 's' : 'u', ret); - if (ret < 0 || ret >= 16) { - if (ret >= 16) - ret = -E2BIG; - pr_warning("Failed to convert variable type: %s\n", - strerror(-ret)); - return ret; - } - tvar->type = strdup(buf); - if (tvar->type == NULL) - return -ENOMEM; + ret = dwarf_bytesize(&type); + if (ret <= 0) + /* No size ... try to use default type */ + return 0; + ret = BYTES_TO_BITS(ret); + + /* Check the bitwidth */ + if (ret > MAX_BASIC_TYPE_BITS) { + pr_info("%s exceeds max-bitwidth. Cut down to %d bits.\n", + dwarf_diename(&type), MAX_BASIC_TYPE_BITS); + ret = MAX_BASIC_TYPE_BITS; + } + ret = snprintf(buf, 16, "%c%d", + die_is_signed_type(&type) ? 's' : 'u', ret); + +formatted: + if (ret < 0 || ret >= 16) { + if (ret >= 16) + ret = -E2BIG; + pr_warning("Failed to convert variable type: %s\n", + strerror(-ret)); + return ret; } + tvar->type = strdup(buf); + if (tvar->type == NULL) + return -ENOMEM; return 0; } @@ -768,7 +416,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, else *ref_ptr = ref; } - ref->offset += die_get_byte_size(&type) * field->index; + ref->offset += dwarf_bytesize(&type) * field->index; if (!field->next) /* Save vr_die for converting types */ memcpy(die_mem, vr_die, sizeof(*die_mem)); @@ -786,8 +434,10 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, return -ENOENT; } /* Verify it is a data structure */ - if (dwarf_tag(&type) != DW_TAG_structure_type) { - pr_warning("%s is not a data structure.\n", varname); + tag = dwarf_tag(&type); + if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) { + pr_warning("%s is not a data structure nor an union.\n", + varname); return -EINVAL; } @@ -800,13 +450,14 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, *ref_ptr = ref; } else { /* Verify it is a data structure */ - if (tag != DW_TAG_structure_type) { - pr_warning("%s is not a data structure.\n", varname); + if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) { + pr_warning("%s is not a data structure nor an union.\n", + varname); return -EINVAL; } if (field->name[0] == '[') { - pr_err("Semantic error: %s is not a pointor nor array.", - varname); + pr_err("Semantic error: %s is not a pointor" + " nor array.\n", varname); return -EINVAL; } if (field->ref) { @@ -822,16 +473,21 @@ 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; } /* Get the offset of the field */ - ret = die_get_data_member_location(die_mem, &offs); - if (ret < 0) { - pr_warning("Failed to get the offset of %s.\n", field->name); - return ret; + if (tag == DW_TAG_union_type) { + offs = 0; + } else { + ret = die_get_data_member_location(die_mem, &offs); + if (ret < 0) { + pr_warning("Failed to get the offset of %s.\n", + field->name); + return ret; + } } ref->offset += (long)offs; @@ -854,13 +510,13 @@ 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); - if (ret == -ENOENT) + &pf->sp_die, pf->tvar); + if (ret == -ENOENT || ret == -EINVAL) pr_err("Failed to find the location of %s at this address.\n" " Perhaps, it has been optimized out.\n", pf->pvar->var); else if (ret == -ENOTSUP) pr_err("Sorry, we don't support this variable location yet.\n"); - else if (pf->pvar->field) { + else if (ret == 0 && pf->pvar->field) { ret = convert_variable_fields(vr_die, pf->pvar->var, pf->pvar->field, &pf->tvar->ref, &die_mem); @@ -872,12 +528,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) return ret; } -/* Find a variable in a subprogram die */ -static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) +/* Find a variable in a scope DIE */ +static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) { - Dwarf_Die vr_die, *scopes; + Dwarf_Die vr_die; char buf[32], *ptr; - int ret, nscopes; + int ret = 0; if (!is_c_varname(pf->pvar->var)) { /* Copy raw parameters */ @@ -912,64 +568,65 @@ static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) if (pf->tvar->name == NULL) return -ENOMEM; - pr_debug("Searching '%s' variable in context.\n", - pf->pvar->var); + pr_debug("Searching '%s' variable in context.\n", pf->pvar->var); /* Search child die for local variables and parameters. */ - if (die_find_variable_at(sp_die, pf->pvar->var, pf->addr, &vr_die)) - ret = convert_variable(&vr_die, pf); - else { - /* Search upper class */ - nscopes = dwarf_getscopes_die(sp_die, &scopes); - while (nscopes-- > 1) { - pr_debug("Searching variables in %s\n", - dwarf_diename(&scopes[nscopes])); - /* We should check this scope, so give dummy address */ - if (die_find_variable_at(&scopes[nscopes], - pf->pvar->var, 0, - &vr_die)) { - ret = convert_variable(&vr_die, pf); - goto found; - } - } - if (scopes) - free(scopes); - ret = -ENOENT; + if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) { + /* Search again in global variables */ + if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die)) + pr_warning("Failed to find '%s' in this function.\n", + pf->pvar->var); + ret = -ENOENT; } -found: - if (ret < 0) - pr_warning("Failed to find '%s' in this function.\n", - pf->pvar->var); + if (ret >= 0) + ret = convert_variable(&vr_die, pf); + return ret; } /* 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; - 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 pc of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - 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; + Dwarf_Addr eaddr, highaddr; + 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->address = (unsigned long)paddr; + tp->symbol = strdup(symbol); + if (!tp->symbol) + return -ENOMEM; /* Return probe must be on the head of a subprogram */ if (retprobe) { if (eaddr != paddr) { pr_warning("Return probe must be on the head of" - " a real function\n"); + " a real function.\n"); return -EINVAL; } tp->retprobe = true; @@ -978,27 +635,30 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr, return 0; } -/* Call probe_finder callback with real subprogram DIE */ -static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf) +/* Call probe_finder callback with scope DIE */ +static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) { - Dwarf_Die die_mem; Dwarf_Attribute fb_attr; size_t nops; int ret; - /* If no real subprogram, find a real one */ - if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) { - sp_die = die_find_real_subprogram(&pf->cu_die, - pf->addr, &die_mem); - if (!sp_die) { + if (!sc_die) { + pr_err("Caller must pass a scope DIE. Program error.\n"); + return -EINVAL; + } + + /* If not a real subprogram, find a real one */ + if (!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"); return -ENOENT; } - } + } else + memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die)); - /* Get the frame base attribute/ops */ - dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr); + /* Get the frame base attribute/ops from subprogram */ + dwarf_attr(&pf->sp_die, DW_AT_frame_base, &fb_attr); ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1); if (ret <= 0 || nops == 0) { pf->fb_ops = NULL; @@ -1008,7 +668,7 @@ static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf) Dwarf_Frame *frame; if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 || dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) { - pr_warning("Failed to get CFA on 0x%jx\n", + pr_warning("Failed to get call frame on 0x%jx\n", (uintmax_t)pf->addr); return -ENOENT; } @@ -1016,7 +676,7 @@ static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf) } /* Call finder's callback handler */ - ret = pf->callback(sp_die, pf); + ret = pf->callback(sc_die, pf); /* *pf->fb_ops will be cached in libdw. Don't free it. */ pf->fb_ops = NULL; @@ -1024,195 +684,210 @@ static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf) return ret; } -/* Find probe point from its line number */ -static int find_probe_point_by_line(struct probe_finder *pf) -{ - Dwarf_Lines *lines; - Dwarf_Line *line; - size_t nlines, i; - Dwarf_Addr addr; - int lineno; - int ret = 0; +struct find_scope_param { + const char *function; + const char *file; + int line; + int diff; + Dwarf_Die *die_mem; + bool found; +}; - if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) { - pr_warning("No source lines found in this CU.\n"); - return -ENOENT; +static int find_best_scope_cb(Dwarf_Die *fn_die, void *data) +{ + struct find_scope_param *fsp = data; + const char *file; + int lno; + + /* Skip if declared file name does not match */ + if (fsp->file) { + file = dwarf_decl_file(fn_die); + if (!file || strcmp(fsp->file, file) != 0) + return 0; + } + /* If the function name is given, that's what user expects */ + if (fsp->function) { + if (die_compare_name(fn_die, fsp->function)) { + memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die)); + fsp->found = true; + return 1; + } + } else { + /* With the line number, find the nearest declared DIE */ + dwarf_decl_line(fn_die, &lno); + if (lno < fsp->line && fsp->diff > fsp->line - lno) { + /* Keep a candidate and continue */ + fsp->diff = fsp->line - lno; + memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die)); + fsp->found = true; + } } + return 0; +} - for (i = 0; i < nlines && ret == 0; i++) { - line = dwarf_onesrcline(lines, i); - if (dwarf_lineno(line, &lineno) != 0 || - lineno != pf->lno) - continue; +/* Find an appropriate scope fits to given conditions */ +static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem) +{ + struct find_scope_param fsp = { + .function = pf->pev->point.function, + .file = pf->fname, + .line = pf->lno, + .diff = INT_MAX, + .die_mem = die_mem, + .found = false, + }; + + cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, &fsp); + + return fsp.found ? die_mem : NULL; +} - /* TODO: Get fileno from line, but how? */ - if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0) - continue; +static int probe_point_line_walker(const char *fname, int lineno, + Dwarf_Addr addr, void *data) +{ + struct probe_finder *pf = data; + Dwarf_Die *sc_die, die_mem; + int ret; - if (dwarf_lineaddr(line, &addr) != 0) { - pr_warning("Failed to get the address of the line.\n"); - return -ENOENT; - } - pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n", - (int)i, lineno, (uintmax_t)addr); - pf->addr = addr; + if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0) + return 0; - ret = call_probe_finder(NULL, pf); - /* Continuing, because target line might be inlined. */ + pf->addr = addr; + sc_die = find_best_scope(pf, &die_mem); + if (!sc_die) { + pr_warning("Failed to find scope of probe point.\n"); + return -ENOENT; } - return ret; + + ret = call_probe_finder(sc_die, pf); + + /* Continue if no error, because the line will be in inline function */ + return ret < 0 ? ret : 0; +} + +/* Find probe point from its line number */ +static int find_probe_point_by_line(struct probe_finder *pf) +{ + return die_walk_lines(&pf->cu_die, probe_point_line_walker, pf); } /* Find lines which match lazy pattern */ -static int find_lazy_match_lines(struct list_head *head, +static int find_lazy_match_lines(struct intlist *list, const char *fname, const char *pat) { - char *fbuf, *p1, *p2; - int fd, line, nlines = -1; - struct stat st; - - fd = open(fname, O_RDONLY); - if (fd < 0) { - pr_warning("Failed to open %s: %s\n", fname, strerror(-fd)); + FILE *fp; + char *line = NULL; + size_t line_len; + ssize_t len; + int count = 0, linenum = 1; + + fp = fopen(fname, "r"); + if (!fp) { + pr_warning("Failed to open %s: %s\n", fname, strerror(errno)); return -errno; } - if (fstat(fd, &st) < 0) { - pr_warning("Failed to get the size of %s: %s\n", - fname, strerror(errno)); - nlines = -errno; - goto out_close; - } + while ((len = getline(&line, &line_len, fp)) > 0) { - nlines = -ENOMEM; - fbuf = malloc(st.st_size + 2); - if (fbuf == NULL) - goto out_close; - if (read(fd, fbuf, st.st_size) < 0) { - pr_warning("Failed to read %s: %s\n", fname, strerror(errno)); - nlines = -errno; - goto out_free_fbuf; - } - fbuf[st.st_size] = '\n'; /* Dummy line */ - fbuf[st.st_size + 1] = '\0'; - p1 = fbuf; - line = 1; - nlines = 0; - while ((p2 = strchr(p1, '\n')) != NULL) { - *p2 = '\0'; - if (strlazymatch(p1, pat)) { - line_list__add_line(head, line); - nlines++; + if (line[len - 1] == '\n') + line[len - 1] = '\0'; + + if (strlazymatch(line, pat)) { + intlist__add(list, linenum); + count++; } - line++; - p1 = p2 + 1; + linenum++; } -out_free_fbuf: - free(fbuf); -out_close: - close(fd); - return nlines; + + if (ferror(fp)) + count = -errno; + free(line); + fclose(fp); + + if (count == 0) + pr_debug("No matched lines found in %s.\n", fname); + return count; } -/* Find probe points from lazy pattern */ -static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) +static int probe_point_lazy_walker(const char *fname, int lineno, + Dwarf_Addr addr, void *data) { - Dwarf_Lines *lines; - Dwarf_Line *line; - size_t nlines, i; - Dwarf_Addr addr; - Dwarf_Die die_mem; - int lineno; - int ret = 0; + struct probe_finder *pf = data; + Dwarf_Die *sc_die, die_mem; + int ret; - if (list_empty(&pf->lcache)) { - /* Matching lazy line pattern */ - ret = find_lazy_match_lines(&pf->lcache, pf->fname, - pf->pev->point.lazy_line); - if (ret == 0) { - pr_debug("No matched lines found in %s.\n", pf->fname); - return 0; - } else if (ret < 0) - return ret; - } + if (!intlist__has_entry(pf->lcache, lineno) || + strtailcmp(fname, pf->fname) != 0) + return 0; - if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) { - pr_warning("No source lines found in this CU.\n"); + pr_debug("Probe line found: line:%d addr:0x%llx\n", + lineno, (unsigned long long)addr); + pf->addr = addr; + pf->lno = lineno; + sc_die = find_best_scope(pf, &die_mem); + if (!sc_die) { + pr_warning("Failed to find scope of probe point.\n"); return -ENOENT; } - for (i = 0; i < nlines && ret >= 0; i++) { - line = dwarf_onesrcline(lines, i); + ret = call_probe_finder(sc_die, pf); - if (dwarf_lineno(line, &lineno) != 0 || - !line_list__has_line(&pf->lcache, lineno)) - continue; - - /* TODO: Get fileno from line, but how? */ - if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0) - continue; - - if (dwarf_lineaddr(line, &addr) != 0) { - pr_debug("Failed to get the address of line %d.\n", - lineno); - continue; - } - if (sp_die) { - /* Address filtering 1: does sp_die include addr? */ - if (!dwarf_haspc(sp_die, addr)) - continue; - /* Address filtering 2: No child include addr? */ - if (die_find_inlinefunc(sp_die, addr, &die_mem)) - continue; - } + /* + * Continue if no error, because the lazy pattern will match + * to other lines + */ + return ret < 0 ? ret : 0; +} - pr_debug("Probe line found: line[%d]:%d addr:0x%llx\n", - (int)i, lineno, (unsigned long long)addr); - pf->addr = addr; +/* Find probe points from lazy pattern */ +static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) +{ + int ret = 0; - ret = call_probe_finder(sp_die, pf); - /* Continuing, because target line might be inlined. */ + if (intlist__empty(pf->lcache)) { + /* Matching lazy line pattern */ + ret = find_lazy_match_lines(pf->lcache, pf->fname, + pf->pev->point.lazy_line); + if (ret <= 0) + return ret; } - /* TODO: deallocate lines, but how? */ - return ret; -} -/* Callback parameter with return value */ -struct dwarf_callback_param { - void *data; - int retval; -}; + return die_walk_lines(sp_die, probe_point_lazy_walker, pf); +} static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) { - struct dwarf_callback_param *param = data; - struct probe_finder *pf = param->data; + struct probe_finder *pf = data; struct perf_probe_point *pp = &pf->pev->point; Dwarf_Addr addr; + int ret; if (pp->lazy_line) - param->retval = find_probe_point_lazy(in_die, pf); + ret = find_probe_point_lazy(in_die, pf); else { /* Get probe address */ if (dwarf_entrypc(in_die, &addr) != 0) { - pr_warning("Failed to get entry pc of %s.\n", + pr_warning("Failed to get entry address of %s.\n", dwarf_diename(in_die)); - param->retval = -ENOENT; - return DWARF_CB_ABORT; + return -ENOENT; } pf->addr = addr; pf->addr += pp->offset; pr_debug("found inline addr: 0x%jx\n", (uintmax_t)pf->addr); - param->retval = call_probe_finder(in_die, pf); - if (param->retval < 0) - return DWARF_CB_ABORT; + ret = call_probe_finder(in_die, pf); } - return DWARF_CB_OK; + return ret; } +/* Callback parameter with return value for libdw */ +struct dwarf_callback_param { + void *data; + int retval; +}; + /* Search function from function name */ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) { @@ -1221,10 +896,14 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) struct perf_probe_point *pp = &pf->pev->point; /* Check tag and diename */ - if (dwarf_tag(sp_die) != DW_TAG_subprogram || + if (!die_is_func_def(sp_die) || !die_compare_name(sp_die, pp->function)) return DWARF_CB_OK; + /* Check declared file */ + if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die))) + return DWARF_CB_OK; + pf->fname = dwarf_decl_file(sp_die); if (pp->line) { /* Function relative line */ dwarf_decl_line(sp_die, &pf->lno); @@ -1236,8 +915,8 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) param->retval = find_probe_point_lazy(sp_die, pf); else { if (dwarf_entrypc(sp_die, &pf->addr) != 0) { - pr_warning("Failed to get entry pc of %s.\n", - dwarf_diename(sp_die)); + pr_warning("Failed to get entry address of " + "%s.\n", dwarf_diename(sp_die)); param->retval = -ENOENT; return DWARF_CB_ABORT; } @@ -1245,14 +924,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) /* TODO: Check the address in this function */ param->retval = call_probe_finder(sp_die, pf); } - } else { - struct dwarf_callback_param _param = {.data = (void *)pf, - .retval = 0}; + } else /* Inlined function: search instances */ - dwarf_func_inline_instances(sp_die, probe_point_inline_cb, - &_param); - param->retval = _param.retval; - } + param->retval = die_walk_instances(sp_die, + probe_point_inline_cb, (void *)pf); return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */ } @@ -1265,37 +940,84 @@ static int find_probe_point_by_func(struct probe_finder *pf) return _param.retval; } +struct pubname_callback_param { + char *function; + char *file; + Dwarf_Die *cu_die; + Dwarf_Die *sp_die; + int found; +}; + +static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data) +{ + struct pubname_callback_param *param = data; + + if (dwarf_offdie(dbg, gl->die_offset, param->sp_die)) { + if (dwarf_tag(param->sp_die) != DW_TAG_subprogram) + return DWARF_CB_OK; + + if (die_compare_name(param->sp_die, param->function)) { + if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die)) + return DWARF_CB_OK; + + if (param->file && + strtailcmp(param->file, dwarf_decl_file(param->sp_die))) + return DWARF_CB_OK; + + param->found = 1; + return DWARF_CB_ABORT; + } + } + + return DWARF_CB_OK; +} + /* Find probe points from debuginfo */ -static int find_probes(int fd, struct probe_finder *pf) +static int debuginfo__find_probes(struct debuginfo *dbg, + struct probe_finder *pf) { struct perf_probe_point *pp = &pf->pev->point; Dwarf_Off off, noff; size_t cuhl; Dwarf_Die *diep; - Dwarf *dbg = NULL; - Dwfl *dwfl; - Dwarf_Addr bias; /* Currently ignored */ int ret = 0; - dbg = dwfl_init_offline_dwarf(fd, &dwfl, &bias); - if (!dbg) { - pr_warning("No dwarf info found in the vmlinux - " - "please rebuild with CONFIG_DEBUG_INFO=y.\n"); - return -EBADF; - } - #if _ELFUTILS_PREREQ(0, 142) /* Get the call frame information from this dwarf */ - pf->cfi = dwarf_getcfi(dbg); + pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg)); #endif off = 0; - line_list__init(&pf->lcache); + pf->lcache = intlist__new(NULL); + if (!pf->lcache) + return -ENOMEM; + + /* Fastpath: lookup by function name from .debug_pubnames section */ + if (pp->function) { + struct pubname_callback_param pubname_param = { + .function = pp->function, + .file = pp->file, + .cu_die = &pf->cu_die, + .sp_die = &pf->sp_die, + .found = 0, + }; + struct dwarf_callback_param probe_param = { + .data = pf, + }; + + dwarf_getpubnames(dbg->dbg, pubname_search_cb, + &pubname_param, 0); + if (pubname_param.found) { + ret = probe_point_search_cb(&pf->sp_die, &probe_param); + if (ret) + goto found; + } + } + /* Loop on CUs (Compilation Unit) */ - while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) && - ret >= 0) { + while (!dwarf_nextcu(dbg->dbg, off, &noff, &cuhl, NULL, NULL, NULL)) { /* Get the DIE(Debugging Information Entry) of this CU */ - diep = dwarf_offdie(dbg, off + cuhl, &pf->cu_die); + diep = dwarf_offdie(dbg->dbg, off + cuhl, &pf->cu_die); if (!diep) continue; @@ -1314,22 +1036,93 @@ static int find_probes(int fd, struct probe_finder *pf) pf->lno = pp->line; ret = find_probe_point_by_line(pf); } + if (ret < 0) + break; } off = noff; } - line_list__free(&pf->lcache); - if (dwfl) - dwfl_end(dwfl); + +found: + intlist__delete(pf->lcache); + pf->lcache = NULL; 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 *sp_die, struct probe_finder *pf) +static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) { struct trace_event_finder *tf = container_of(pf, struct trace_event_finder, pf); struct probe_trace_event *tev; + struct perf_probe_arg *args; int ret, i; /* Check number of tevs */ @@ -1340,37 +1133,54 @@ static int add_probe_trace_event(Dwarf_Die *sp_die, struct probe_finder *pf) } tev = &tf->tevs[tf->ntevs++]; - ret = convert_to_trace_point(sp_die, pf->addr, pf->pev->point.retprobe, - &tev->point); + /* Trace point should be converted from subprogram DIE */ + ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr, + pf->pev->point.retprobe, &tev->point); if (ret < 0) return ret; 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]; - ret = find_variable(sp_die, pf); + /* 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 find_probe_trace_events(int fd, struct perf_probe_event *pev, - struct probe_trace_event **tevs, int max_tevs) +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 */ @@ -1381,10 +1191,9 @@ int find_probe_trace_events(int fd, struct perf_probe_event *pev, tf.tevs = *tevs; tf.ntevs = 0; - ret = find_probes(fd, &tf.pf); + ret = debuginfo__find_probes(dbg, &tf.pf); if (ret < 0) { - free(*tevs); - *tevs = NULL; + zfree(tevs); return ret; } @@ -1407,7 +1216,8 @@ 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); @@ -1423,13 +1233,13 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data) } /* Add a found vars into available variables list */ -static int add_available_vars(Dwarf_Die *sp_die, struct probe_finder *pf) +static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) { struct available_var_finder *af = container_of(pf, struct available_var_finder, pf); struct variable_list *vl; - Dwarf_Die die_mem, *scopes = NULL; - int ret, nscopes; + Dwarf_Die die_mem; + int ret; /* Check number of tevs */ if (af->nvls == af->max_vls) { @@ -1438,8 +1248,9 @@ static int add_available_vars(Dwarf_Die *sp_die, struct probe_finder *pf) } vl = &af->vls[af->nvls++]; - ret = convert_to_trace_point(sp_die, pf->addr, pf->pev->point.retprobe, - &vl->point); + /* Trace point should be converted from subprogram DIE */ + ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr, + pf->pev->point.retprobe, &vl->point); if (ret < 0) return ret; @@ -1451,19 +1262,14 @@ static int add_available_vars(Dwarf_Die *sp_die, struct probe_finder *pf) if (vl->vars == NULL) return -ENOMEM; af->child = true; - die_find_child(sp_die, collect_variables_cb, (void *)af, &die_mem); + die_find_child(sc_die, collect_variables_cb, (void *)af, &die_mem); /* Find external variables */ if (!af->externs) goto out; /* Don't need to search child DIE for externs. */ af->child = false; - nscopes = dwarf_getscopes_die(sp_die, &scopes); - while (nscopes-- > 1) - die_find_child(&scopes[nscopes], collect_variables_cb, - (void *)af, &die_mem); - if (scopes) - free(scopes); + die_find_child(&pf->cu_die, collect_variables_cb, (void *)af, &die_mem); out: if (strlist__empty(vl->vars)) { @@ -1474,13 +1280,19 @@ out: return ret; } -/* Find available variables at given probe point */ -int find_available_vars_at(int fd, struct perf_probe_event *pev, - struct variable_list **vls, int max_vls, - bool externs) +/* + * Find available variables at given probe point + * Return the number of found probe points. Return 0 if there is no + * matched probe point. Return <0 if an error occurs. + */ +int debuginfo__find_available_vars_at(struct debuginfo *dbg, + struct perf_probe_event *pev, + struct variable_list **vls, + 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; @@ -1492,17 +1304,14 @@ int find_available_vars_at(int fd, struct perf_probe_event *pev, af.vls = *vls; af.nvls = 0; - ret = find_probes(fd, &af.pf); + ret = debuginfo__find_probes(dbg, &af.pf); if (ret < 0) { /* Free vlist for error */ while (af.nvls--) { - if (af.vls[af.nvls].point.symbol) - free(af.vls[af.nvls].point.symbol); - if (af.vls[af.nvls].vars) - strlist__delete(af.vls[af.nvls].vars); + zfree(&af.vls[af.nvls].point.symbol); + strlist__delete(af.vls[af.nvls].vars); } - free(af.vls); - *vls = NULL; + zfree(vls); return ret; } @@ -1510,97 +1319,110 @@ int find_available_vars_at(int fd, struct perf_probe_event *pev, } /* Reverse search */ -int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt) +int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, + struct perf_probe_point *ppt) { Dwarf_Die cudie, spdie, indie; - Dwarf *dbg = NULL; - Dwfl *dwfl = NULL; - Dwarf_Line *line; - Dwarf_Addr laddr, eaddr, bias = 0; - const char *tmp; - int lineno, ret = 0; - bool found = false; - - /* Open the live linux kernel */ - dbg = dwfl_init_live_kernel_dwarf(addr, &dwfl, &bias); - if (!dbg) { - pr_warning("No dwarf info found in the vmlinux - " - "please rebuild with CONFIG_DEBUG_INFO=y.\n"); - ret = -EINVAL; - goto end; - } + 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 += bias; + addr += dbg->bias; + /* Find cu die */ - if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr - bias, &cudie)) { - pr_warning("No CU DIE is found at %lx\n", addr); + 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; goto end; } - /* Find a corresponding line */ - line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr); - if (line) { - if (dwarf_lineaddr(line, &laddr) == 0 && - (Dwarf_Addr)addr == laddr && - dwarf_lineno(line, &lineno) == 0) { - tmp = dwarf_linesrc(line, NULL, NULL); - if (tmp) { - ppt->line = lineno; - ppt->file = strdup(tmp); - if (ppt->file == NULL) { - ret = -ENOMEM; - goto end; - } - found = true; - } + /* Find a corresponding line (filename and lineno) */ + cu_find_lineinfo(&cudie, addr, &fname, &lineno); + /* Don't care whether it failed or not */ + + /* Find a corresponding function (name, baseline and baseaddr) */ + if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) { + /* Get function entry information */ + func = basefunc = dwarf_diename(&spdie); + if (!func || + dwarf_entrypc(&spdie, &baseaddr) != 0 || + dwarf_decl_line(&spdie, &baseline) != 0) { + lineno = 0; + goto post; } - } - /* Find a corresponding function */ - if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) { - tmp = dwarf_diename(&spdie); - if (!tmp || dwarf_entrypc(&spdie, &eaddr) != 0) - goto end; + fname = dwarf_decl_file(&spdie); + if (addr == (unsigned long)baseaddr) { + /* Function entry - Relative line number is 0 */ + lineno = baseline; + goto post; + } - if (ppt->line) { - if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr, + /* Track down the inline functions step by step */ + while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr, &indie)) { - /* addr in an inline function */ - tmp = dwarf_diename(&indie); - if (!tmp) - goto end; - ret = dwarf_decl_line(&indie, &lineno); + /* There is an inline function */ + if (dwarf_entrypc(&indie, &_addr) == 0 && + _addr == addr) { + /* + * addr is at an inline function entry. + * In this case, lineno should be the call-site + * line number. (overwrite lineinfo) + */ + lineno = die_get_call_lineno(&indie); + fname = die_get_call_file(&indie); + break; } else { - if (eaddr == addr) { /* Function entry */ - lineno = ppt->line; - ret = 0; - } else - ret = dwarf_decl_line(&spdie, &lineno); - } - if (ret == 0) { - /* Make a relative line number */ - ppt->line -= lineno; - goto found; + /* + * addr is in an inline function body. + * Since lineno points one of the lines + * of the inline function, baseline should + * be the entry line of the inline function. + */ + tmp = dwarf_diename(&indie); + if (!tmp || + dwarf_decl_line(&indie, &baseline) != 0) + break; + func = tmp; + spdie = indie; } } - /* We don't have a line number, let's use offset */ - ppt->offset = addr - (unsigned long)eaddr; -found: - ppt->function = strdup(tmp); + /* 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 (basefunc) { + ppt->offset = addr - (unsigned long)baseaddr; + func = basefunc; + } + + /* Duplicate strings */ + if (func) { + ppt->function = strdup(func); if (ppt->function == NULL) { ret = -ENOMEM; goto end; } - found = true; } - + if (fname) { + ppt->file = strdup(fname); + if (ppt->file == NULL) { + zfree(&ppt->function); + ret = -ENOMEM; + goto end; + } + } end: - if (dwfl) - dwfl_end(dwfl); - if (ret >= 0) - ret = found ? 1 : 0; + if (ret == 0 && (fname || func)) + ret = 1; /* Found a point */ return ret; } @@ -1614,127 +1436,71 @@ static int line_range_add_line(const char *src, unsigned int lineno, if (lr->path == NULL) return -ENOMEM; } - return line_list__add_line(&lr->line_list, lineno); + return intlist__add(lr->line_list, lineno); } -/* Search function declaration lines */ -static int line_range_funcdecl_cb(Dwarf_Die *sp_die, void *data) +static int line_range_walk_cb(const char *fname, int lineno, + Dwarf_Addr addr __maybe_unused, + void *data) { - struct dwarf_callback_param *param = data; - struct line_finder *lf = param->data; - const char *src; - int lineno; - - src = dwarf_decl_file(sp_die); - if (src && strtailcmp(src, lf->fname) != 0) - return DWARF_CB_OK; + struct line_finder *lf = data; + int err; - if (dwarf_decl_line(sp_die, &lineno) != 0 || + if ((strtailcmp(fname, lf->fname) != 0) || (lf->lno_s > lineno || lf->lno_e < lineno)) - return DWARF_CB_OK; + return 0; - param->retval = line_range_add_line(src, lineno, lf->lr); - if (param->retval < 0) - return DWARF_CB_ABORT; - return DWARF_CB_OK; -} + err = line_range_add_line(fname, lineno, lf->lr); + if (err < 0 && err != -EEXIST) + return err; -static int find_line_range_func_decl_lines(struct line_finder *lf) -{ - struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0}; - dwarf_getfuncs(&lf->cu_die, line_range_funcdecl_cb, ¶m, 0); - return param.retval; + return 0; } /* Find line range from its line number */ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) { - Dwarf_Lines *lines; - Dwarf_Line *line; - size_t nlines, i; - Dwarf_Addr addr; - int lineno, ret = 0; - const char *src; - Dwarf_Die die_mem; - - line_list__init(&lf->lr->line_list); - if (dwarf_getsrclines(&lf->cu_die, &lines, &nlines) != 0) { - pr_warning("No source lines found in this CU.\n"); - return -ENOENT; - } - - /* Search probable lines on lines list */ - for (i = 0; i < nlines; i++) { - line = dwarf_onesrcline(lines, i); - if (dwarf_lineno(line, &lineno) != 0 || - (lf->lno_s > lineno || lf->lno_e < lineno)) - continue; - - if (sp_die) { - /* Address filtering 1: does sp_die include addr? */ - if (dwarf_lineaddr(line, &addr) != 0 || - !dwarf_haspc(sp_die, addr)) - continue; - - /* Address filtering 2: No child include addr? */ - if (die_find_inlinefunc(sp_die, addr, &die_mem)) - continue; - } - - /* TODO: Get fileno from line, but how? */ - src = dwarf_linesrc(line, NULL, NULL); - if (strtailcmp(src, lf->fname) != 0) - continue; - - ret = line_range_add_line(src, lineno, lf->lr); - if (ret < 0) - return ret; - } + int ret; - /* - * Dwarf lines doesn't include function declarations. We have to - * check functions list or given function. - */ - if (sp_die) { - src = dwarf_decl_file(sp_die); - if (src && dwarf_decl_line(sp_die, &lineno) == 0 && - (lf->lno_s <= lineno && lf->lno_e >= lineno)) - ret = line_range_add_line(src, lineno, lf->lr); - } else - ret = find_line_range_func_decl_lines(lf); + ret = die_walk_lines(sp_die ?: &lf->cu_die, line_range_walk_cb, lf); /* Update status */ if (ret >= 0) - if (!list_empty(&lf->lr->line_list)) + if (!intlist__empty(lf->lr->line_list)) ret = lf->found = 1; else ret = 0; /* Lines are not found */ else { - free(lf->lr->path); - lf->lr->path = NULL; + zfree(&lf->lr->path); } return ret; } static int line_range_inline_cb(Dwarf_Die *in_die, void *data) { - struct dwarf_callback_param *param = data; + int ret = find_line_range_by_line(in_die, data); - param->retval = find_line_range_by_line(in_die, param->data); - return DWARF_CB_ABORT; /* No need to find other instances */ + /* + * We have to check all instances of inlined function, because + * some execution paths can be optimized out depends on the + * function argument of instances. However, if an error occurs, + * it should be handled by the caller. + */ + return ret < 0 ? ret : 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; struct line_finder *lf = param->data; struct line_range *lr = lf->lr; - pr_debug("find (%llx) %s\n", - (unsigned long long)dwarf_dieoffset(sp_die), - dwarf_diename(sp_die)); - if (dwarf_tag(sp_die) == DW_TAG_subprogram && + /* Check declared file */ + if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die))) + return DWARF_CB_OK; + + 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); @@ -1748,15 +1514,10 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) pr_debug("New line range: %d to %d\n", lf->lno_s, lf->lno_e); lr->start = lf->lno_s; lr->end = lf->lno_e; - if (dwarf_func_inline(sp_die)) { - struct dwarf_callback_param _param; - _param.data = (void *)lf; - _param.retval = 0; - dwarf_func_inline_instances(sp_die, - line_range_inline_cb, - &_param); - param->retval = _param.retval; - } else + if (dwarf_func_inline(sp_die)) + param->retval = die_walk_instances(sp_die, + line_range_inline_cb, lf); + else param->retval = find_line_range_by_line(sp_die, lf); return DWARF_CB_ABORT; } @@ -1770,32 +1531,40 @@ static int find_line_range_by_func(struct line_finder *lf) return param.retval; } -int find_line_range(int fd, 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; Dwarf_Off off = 0, noff; size_t cuhl; Dwarf_Die *diep; - Dwarf *dbg = NULL; - Dwfl *dwfl; - Dwarf_Addr bias; /* Currently ignored */ const char *comp_dir; - dbg = dwfl_init_offline_dwarf(fd, &dwfl, &bias); - if (!dbg) { - pr_warning("No dwarf info found in the vmlinux - " - "please rebuild with CONFIG_DEBUG_INFO=y.\n"); - return -EBADF; + /* Fastpath: lookup by function name from .debug_pubnames section */ + if (lr->function) { + struct pubname_callback_param pubname_param = { + .function = lr->function, .file = lr->file, + .cu_die = &lf.cu_die, .sp_die = &lf.sp_die, .found = 0}; + struct dwarf_callback_param line_range_param = { + .data = (void *)&lf, .retval = 0}; + + dwarf_getpubnames(dbg->dbg, pubname_search_cb, + &pubname_param, 0); + if (pubname_param.found) { + line_range_search_cb(&lf.sp_die, &line_range_param); + if (lf.found) + goto found; + } } /* Loop on CUs (Compilation Unit) */ while (!lf.found && ret >= 0) { - if (dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0) + 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(dbg, off + cuhl, &lf.cu_die); + diep = dwarf_offdie(dbg->dbg, off + cuhl, &lf.cu_die); if (!diep) continue; @@ -1817,6 +1586,7 @@ int find_line_range(int fd, struct line_range *lr) off = noff; } +found: /* Store comp_dir */ if (lf.found) { comp_dir = cu_get_comp_dir(&lf.cu_die); @@ -1828,7 +1598,6 @@ int find_line_range(int fd, struct line_range *lr) } pr_debug("path: %s\n", lr->path); - dwfl_end(dwfl); return (ret < 0) ? ret : lf.found; } diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index bba69d45569..92590b2c7e1 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -3,11 +3,12 @@ #include <stdbool.h> #include "util.h" +#include "intlist.h" #include "probe-event.h" -#define MAX_PATH_LEN 256 #define MAX_PROBE_BUFFER 1024 #define MAX_PROBES 128 +#define MAX_PROBE_ARGS 128 static inline int is_c_varname(const char *name) { @@ -15,41 +16,58 @@ 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" + +/* TODO: export debuginfo data structure even if no dwarf support */ + +/* debug information structure */ +struct debuginfo { + Dwarf *dbg; + Dwfl_Module *mod; + Dwfl *dwfl; + Dwarf_Addr bias; +}; + +/* This also tries to open distro debuginfo */ +extern struct debuginfo *debuginfo__new(const char *path); +extern void debuginfo__delete(struct debuginfo *dbg); + /* Find probe_trace_events specified by perf_probe_event from debuginfo */ -extern int find_probe_trace_events(int fd, struct perf_probe_event *pev, - struct probe_trace_event **tevs, - int max_tevs); +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 find_perf_probe_point(unsigned long addr, - struct perf_probe_point *ppt); +extern int debuginfo__find_probe_point(struct debuginfo *dbg, + unsigned long addr, + struct perf_probe_point *ppt); /* Find a line range */ -extern int find_line_range(int fd, struct line_range *lr); +extern int debuginfo__find_line_range(struct debuginfo *dbg, + struct line_range *lr); /* Find available variables */ -extern int find_available_vars_at(int fd, struct perf_probe_event *pev, - struct variable_list **vls, int max_points, - bool externs); - -#include <dwarf.h> -#include <libdw.h> -#include <libdwfl.h> -#include <version.h> +extern int debuginfo__find_available_vars_at(struct debuginfo *dbg, + struct perf_probe_event *pev, + struct variable_list **vls, + int max_points, bool externs); struct probe_finder { struct perf_probe_event *pev; /* Target probe event */ /* Callback when a probe point is found */ - int (*callback)(Dwarf_Die *sp_die, struct probe_finder *pf); + int (*callback)(Dwarf_Die *sc_die, struct probe_finder *pf); /* For function searching */ int lno; /* Line number */ Dwarf_Addr addr; /* Address */ const char *fname; /* Real file name */ Dwarf_Die cu_die; /* Current CU */ - struct list_head lcache; /* Line cache for lazy match */ + Dwarf_Die sp_die; + struct intlist *lcache; /* Line cache for lazy match */ /* For variable searching */ #if _ELFUTILS_PREREQ(0, 142) @@ -62,6 +80,7 @@ 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 */ @@ -69,6 +88,7 @@ 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 */ @@ -83,9 +103,10 @@ struct line_finder { int lno_s; /* Start line number */ int lno_e; /* End line number */ Dwarf_Die cu_die; /* Current CU */ + Dwarf_Die sp_die; int found; }; -#endif /* DWARF_SUPPORT */ +#endif /* HAVE_DWARF_SUPPORT */ #endif /*_PROBE_FINDER_H */ diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c index 13d36faf64e..daa17aeb6c6 100644 --- a/tools/perf/util/pstack.c +++ b/tools/perf/util/pstack.c @@ -17,59 +17,59 @@ struct pstack { struct pstack *pstack__new(unsigned short max_nr_entries) { - struct pstack *self = zalloc((sizeof(*self) + - max_nr_entries * sizeof(void *))); - if (self != NULL) - self->max_nr_entries = max_nr_entries; - return self; + struct pstack *pstack = zalloc((sizeof(*pstack) + + max_nr_entries * sizeof(void *))); + if (pstack != NULL) + pstack->max_nr_entries = max_nr_entries; + return pstack; } -void pstack__delete(struct pstack *self) +void pstack__delete(struct pstack *pstack) { - free(self); + free(pstack); } -bool pstack__empty(const struct pstack *self) +bool pstack__empty(const struct pstack *pstack) { - return self->top == 0; + return pstack->top == 0; } -void pstack__remove(struct pstack *self, void *key) +void pstack__remove(struct pstack *pstack, void *key) { - unsigned short i = self->top, last_index = self->top - 1; + unsigned short i = pstack->top, last_index = pstack->top - 1; while (i-- != 0) { - if (self->entries[i] == key) { + if (pstack->entries[i] == key) { if (i < last_index) - memmove(self->entries + i, - self->entries + i + 1, + memmove(pstack->entries + i, + pstack->entries + i + 1, (last_index - i) * sizeof(void *)); - --self->top; + --pstack->top; return; } } pr_err("%s: %p not on the pstack!\n", __func__, key); } -void pstack__push(struct pstack *self, void *key) +void pstack__push(struct pstack *pstack, void *key) { - if (self->top == self->max_nr_entries) { - pr_err("%s: top=%d, overflow!\n", __func__, self->top); + if (pstack->top == pstack->max_nr_entries) { + pr_err("%s: top=%d, overflow!\n", __func__, pstack->top); return; } - self->entries[self->top++] = key; + pstack->entries[pstack->top++] = key; } -void *pstack__pop(struct pstack *self) +void *pstack__pop(struct pstack *pstack) { void *ret; - if (self->top == 0) { + if (pstack->top == 0) { pr_err("%s: underflow!\n", __func__); return NULL; } - ret = self->entries[--self->top]; - self->entries[self->top] = NULL; + ret = pstack->entries[--pstack->top]; + pstack->entries[pstack->top] = NULL; return ret; } diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h index 4cedea59f51..c3cb6584d52 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 new file mode 100644 index 00000000000..16a475a7d49 --- /dev/null +++ b/tools/perf/util/python-ext-sources @@ -0,0 +1,22 @@ +# +# List of files needed by perf python extension +# +# Each source file must be placed on its own line so that it can be +# processed by Makefile and util/setup.py accordingly. +# + +util/python.c +util/ctype.c +util/evlist.c +util/evsel.c +util/cpumap.c +util/hweight.c +util/thread_map.c +util/util.c +util/xyarray.c +util/cgroup.c +util/rblist.c +util/strlist.c +../lib/api/fs/fs.c +util/trace-event.c +../../lib/rbtree.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c new file mode 100644 index 00000000000..122669c18ff --- /dev/null +++ b/tools/perf/util/python.c @@ -0,0 +1,1074 @@ +#include <Python.h> +#include <structmember.h> +#include <inttypes.h> +#include <poll.h> +#include "evlist.h" +#include "evsel.h" +#include "event.h" +#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 + +PyMODINIT_FUNC initperf(void); + +#define member_def(type, member, ptype, help) \ + { #member, ptype, \ + offsetof(struct pyrf_event, event) + offsetof(struct type, member), \ + 0, help } + +#define sample_member_def(name, member, ptype, help) \ + { #name, ptype, \ + offsetof(struct pyrf_event, sample) + offsetof(struct perf_sample, member), \ + 0, help } + +struct pyrf_event { + PyObject_HEAD + struct perf_sample sample; + union perf_event event; +}; + +#define sample_members \ + sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"), \ + sample_member_def(sample_pid, pid, T_INT, "event pid"), \ + sample_member_def(sample_tid, tid, T_INT, "event tid"), \ + sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"), \ + sample_member_def(sample_addr, addr, T_ULONGLONG, "event addr"), \ + sample_member_def(sample_id, id, T_ULONGLONG, "event id"), \ + sample_member_def(sample_stream_id, stream_id, T_ULONGLONG, "event stream id"), \ + sample_member_def(sample_period, period, T_ULONGLONG, "event period"), \ + sample_member_def(sample_cpu, cpu, T_UINT, "event cpu"), + +static char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object."); + +static PyMemberDef pyrf_mmap_event__members[] = { + sample_members + member_def(perf_event_header, type, T_UINT, "event type"), + member_def(mmap_event, pid, T_UINT, "event pid"), + member_def(mmap_event, tid, T_UINT, "event tid"), + member_def(mmap_event, start, T_ULONGLONG, "start of the map"), + member_def(mmap_event, len, T_ULONGLONG, "map length"), + member_def(mmap_event, pgoff, T_ULONGLONG, "page offset"), + member_def(mmap_event, filename, T_STRING_INPLACE, "backing store"), + { .name = NULL, }, +}; + +static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent) +{ + PyObject *ret; + char *s; + + if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRIx64 ", " + "length: %#" PRIx64 ", offset: %#" PRIx64 ", " + "filename: %s }", + pevent->event.mmap.pid, pevent->event.mmap.tid, + pevent->event.mmap.start, pevent->event.mmap.len, + pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) { + ret = PyErr_NoMemory(); + } else { + ret = PyString_FromString(s); + free(s); + } + return ret; +} + +static PyTypeObject pyrf_mmap_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.mmap_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_mmap_event__doc, + .tp_members = pyrf_mmap_event__members, + .tp_repr = (reprfunc)pyrf_mmap_event__repr, +}; + +static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object."); + +static PyMemberDef pyrf_task_event__members[] = { + sample_members + member_def(perf_event_header, type, T_UINT, "event type"), + member_def(fork_event, pid, T_UINT, "event pid"), + member_def(fork_event, ppid, T_UINT, "event ppid"), + member_def(fork_event, tid, T_UINT, "event tid"), + member_def(fork_event, ptid, T_UINT, "event ptid"), + member_def(fork_event, time, T_ULONGLONG, "timestamp"), + { .name = NULL, }, +}; + +static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent) +{ + return PyString_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, " + "ptid: %u, time: %" PRIu64 "}", + pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit", + pevent->event.fork.pid, + pevent->event.fork.ppid, + pevent->event.fork.tid, + pevent->event.fork.ptid, + pevent->event.fork.time); +} + +static PyTypeObject pyrf_task_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.task_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_task_event__doc, + .tp_members = pyrf_task_event__members, + .tp_repr = (reprfunc)pyrf_task_event__repr, +}; + +static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object."); + +static PyMemberDef pyrf_comm_event__members[] = { + sample_members + member_def(perf_event_header, type, T_UINT, "event type"), + member_def(comm_event, pid, T_UINT, "event pid"), + member_def(comm_event, tid, T_UINT, "event tid"), + member_def(comm_event, comm, T_STRING_INPLACE, "process name"), + { .name = NULL, }, +}; + +static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent) +{ + return PyString_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }", + pevent->event.comm.pid, + pevent->event.comm.tid, + pevent->event.comm.comm); +} + +static PyTypeObject pyrf_comm_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.comm_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_comm_event__doc, + .tp_members = pyrf_comm_event__members, + .tp_repr = (reprfunc)pyrf_comm_event__repr, +}; + +static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object."); + +static PyMemberDef pyrf_throttle_event__members[] = { + sample_members + member_def(perf_event_header, type, T_UINT, "event type"), + member_def(throttle_event, time, T_ULONGLONG, "timestamp"), + member_def(throttle_event, id, T_ULONGLONG, "event id"), + member_def(throttle_event, stream_id, T_ULONGLONG, "event stream id"), + { .name = NULL, }, +}; + +static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent) +{ + struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1); + + return PyString_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64 + ", stream_id: %" PRIu64 " }", + pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un", + te->time, te->id, te->stream_id); +} + +static PyTypeObject pyrf_throttle_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.throttle_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_throttle_event__doc, + .tp_members = pyrf_throttle_event__members, + .tp_repr = (reprfunc)pyrf_throttle_event__repr, +}; + +static char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object."); + +static PyMemberDef pyrf_lost_event__members[] = { + sample_members + member_def(lost_event, id, T_ULONGLONG, "event id"), + member_def(lost_event, lost, T_ULONGLONG, "number of lost events"), + { .name = NULL, }, +}; + +static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent) +{ + PyObject *ret; + char *s; + + if (asprintf(&s, "{ type: lost, id: %#" PRIx64 ", " + "lost: %#" PRIx64 " }", + pevent->event.lost.id, pevent->event.lost.lost) < 0) { + ret = PyErr_NoMemory(); + } else { + ret = PyString_FromString(s); + free(s); + } + return ret; +} + +static PyTypeObject pyrf_lost_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.lost_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_lost_event__doc, + .tp_members = pyrf_lost_event__members, + .tp_repr = (reprfunc)pyrf_lost_event__repr, +}; + +static char pyrf_read_event__doc[] = PyDoc_STR("perf read event object."); + +static PyMemberDef pyrf_read_event__members[] = { + sample_members + member_def(read_event, pid, T_UINT, "event pid"), + member_def(read_event, tid, T_UINT, "event tid"), + { .name = NULL, }, +}; + +static PyObject *pyrf_read_event__repr(struct pyrf_event *pevent) +{ + return PyString_FromFormat("{ type: read, pid: %u, tid: %u }", + pevent->event.read.pid, + pevent->event.read.tid); + /* + * FIXME: return the array of read values, + * making this method useful ;-) + */ +} + +static PyTypeObject pyrf_read_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.read_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_read_event__doc, + .tp_members = pyrf_read_event__members, + .tp_repr = (reprfunc)pyrf_read_event__repr, +}; + +static char pyrf_sample_event__doc[] = PyDoc_STR("perf sample event object."); + +static PyMemberDef pyrf_sample_event__members[] = { + sample_members + member_def(perf_event_header, type, T_UINT, "event type"), + { .name = NULL, }, +}; + +static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent) +{ + PyObject *ret; + char *s; + + if (asprintf(&s, "{ type: sample }") < 0) { + ret = PyErr_NoMemory(); + } else { + ret = PyString_FromString(s); + free(s); + } + return ret; +} + +static PyTypeObject pyrf_sample_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.sample_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_sample_event__doc, + .tp_members = pyrf_sample_event__members, + .tp_repr = (reprfunc)pyrf_sample_event__repr, +}; + +static int pyrf_event__setup_types(void) +{ + int err; + pyrf_mmap_event__type.tp_new = + pyrf_task_event__type.tp_new = + pyrf_comm_event__type.tp_new = + pyrf_lost_event__type.tp_new = + pyrf_read_event__type.tp_new = + pyrf_sample_event__type.tp_new = + pyrf_throttle_event__type.tp_new = PyType_GenericNew; + err = PyType_Ready(&pyrf_mmap_event__type); + if (err < 0) + goto out; + err = PyType_Ready(&pyrf_lost_event__type); + if (err < 0) + goto out; + err = PyType_Ready(&pyrf_task_event__type); + if (err < 0) + goto out; + err = PyType_Ready(&pyrf_comm_event__type); + if (err < 0) + goto out; + err = PyType_Ready(&pyrf_throttle_event__type); + if (err < 0) + goto out; + err = PyType_Ready(&pyrf_read_event__type); + if (err < 0) + goto out; + err = PyType_Ready(&pyrf_sample_event__type); + if (err < 0) + goto out; +out: + return err; +} + +static PyTypeObject *pyrf_event__type[] = { + [PERF_RECORD_MMAP] = &pyrf_mmap_event__type, + [PERF_RECORD_LOST] = &pyrf_lost_event__type, + [PERF_RECORD_COMM] = &pyrf_comm_event__type, + [PERF_RECORD_EXIT] = &pyrf_task_event__type, + [PERF_RECORD_THROTTLE] = &pyrf_throttle_event__type, + [PERF_RECORD_UNTHROTTLE] = &pyrf_throttle_event__type, + [PERF_RECORD_FORK] = &pyrf_task_event__type, + [PERF_RECORD_READ] = &pyrf_read_event__type, + [PERF_RECORD_SAMPLE] = &pyrf_sample_event__type, +}; + +static PyObject *pyrf_event__new(union perf_event *event) +{ + struct pyrf_event *pevent; + PyTypeObject *ptype; + + if (event->header.type < PERF_RECORD_MMAP || + event->header.type > PERF_RECORD_SAMPLE) + return NULL; + + ptype = pyrf_event__type[event->header.type]; + pevent = PyObject_New(struct pyrf_event, ptype); + if (pevent != NULL) + memcpy(&pevent->event, event, event->header.size); + return (PyObject *)pevent; +} + +struct pyrf_cpu_map { + PyObject_HEAD + + struct cpu_map *cpus; +}; + +static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus, + PyObject *args, PyObject *kwargs) +{ + static char *kwlist[] = { "cpustr", NULL }; + char *cpustr = NULL; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|s", + kwlist, &cpustr)) + return -1; + + pcpus->cpus = cpu_map__new(cpustr); + if (pcpus->cpus == NULL) + return -1; + return 0; +} + +static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus) +{ + cpu_map__delete(pcpus->cpus); + pcpus->ob_type->tp_free((PyObject*)pcpus); +} + +static Py_ssize_t pyrf_cpu_map__length(PyObject *obj) +{ + struct pyrf_cpu_map *pcpus = (void *)obj; + + return pcpus->cpus->nr; +} + +static PyObject *pyrf_cpu_map__item(PyObject *obj, Py_ssize_t i) +{ + struct pyrf_cpu_map *pcpus = (void *)obj; + + if (i >= pcpus->cpus->nr) + return NULL; + + return Py_BuildValue("i", pcpus->cpus->map[i]); +} + +static PySequenceMethods pyrf_cpu_map__sequence_methods = { + .sq_length = pyrf_cpu_map__length, + .sq_item = pyrf_cpu_map__item, +}; + +static char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object."); + +static PyTypeObject pyrf_cpu_map__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.cpu_map", + .tp_basicsize = sizeof(struct pyrf_cpu_map), + .tp_dealloc = (destructor)pyrf_cpu_map__delete, + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_cpu_map__doc, + .tp_as_sequence = &pyrf_cpu_map__sequence_methods, + .tp_init = (initproc)pyrf_cpu_map__init, +}; + +static int pyrf_cpu_map__setup_types(void) +{ + pyrf_cpu_map__type.tp_new = PyType_GenericNew; + return PyType_Ready(&pyrf_cpu_map__type); +} + +struct pyrf_thread_map { + PyObject_HEAD + + struct thread_map *threads; +}; + +static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads, + PyObject *args, PyObject *kwargs) +{ + static char *kwlist[] = { "pid", "tid", "uid", NULL }; + int pid = -1, tid = -1, uid = UINT_MAX; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iii", + kwlist, &pid, &tid, &uid)) + return -1; + + pthreads->threads = thread_map__new(pid, tid, uid); + if (pthreads->threads == NULL) + return -1; + return 0; +} + +static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads) +{ + thread_map__delete(pthreads->threads); + pthreads->ob_type->tp_free((PyObject*)pthreads); +} + +static Py_ssize_t pyrf_thread_map__length(PyObject *obj) +{ + struct pyrf_thread_map *pthreads = (void *)obj; + + return pthreads->threads->nr; +} + +static PyObject *pyrf_thread_map__item(PyObject *obj, Py_ssize_t i) +{ + struct pyrf_thread_map *pthreads = (void *)obj; + + if (i >= pthreads->threads->nr) + return NULL; + + return Py_BuildValue("i", pthreads->threads->map[i]); +} + +static PySequenceMethods pyrf_thread_map__sequence_methods = { + .sq_length = pyrf_thread_map__length, + .sq_item = pyrf_thread_map__item, +}; + +static char pyrf_thread_map__doc[] = PyDoc_STR("thread map object."); + +static PyTypeObject pyrf_thread_map__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.thread_map", + .tp_basicsize = sizeof(struct pyrf_thread_map), + .tp_dealloc = (destructor)pyrf_thread_map__delete, + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_thread_map__doc, + .tp_as_sequence = &pyrf_thread_map__sequence_methods, + .tp_init = (initproc)pyrf_thread_map__init, +}; + +static int pyrf_thread_map__setup_types(void) +{ + pyrf_thread_map__type.tp_new = PyType_GenericNew; + return PyType_Ready(&pyrf_thread_map__type); +} + +struct pyrf_evsel { + PyObject_HEAD + + struct perf_evsel evsel; +}; + +static int pyrf_evsel__init(struct pyrf_evsel *pevsel, + PyObject *args, PyObject *kwargs) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .sample_type = PERF_SAMPLE_PERIOD | PERF_SAMPLE_TID, + }; + static char *kwlist[] = { + "type", + "config", + "sample_freq", + "sample_period", + "sample_type", + "read_format", + "disabled", + "inherit", + "pinned", + "exclusive", + "exclude_user", + "exclude_kernel", + "exclude_hv", + "exclude_idle", + "mmap", + "comm", + "freq", + "inherit_stat", + "enable_on_exec", + "task", + "watermark", + "precise_ip", + "mmap_data", + "sample_id_all", + "wakeup_events", + "bp_type", + "bp_addr", + "bp_len", + NULL + }; + u64 sample_period = 0; + u32 disabled = 0, + inherit = 0, + pinned = 0, + exclusive = 0, + exclude_user = 0, + exclude_kernel = 0, + exclude_hv = 0, + exclude_idle = 0, + mmap = 0, + comm = 0, + freq = 1, + inherit_stat = 0, + enable_on_exec = 0, + task = 0, + watermark = 0, + precise_ip = 0, + mmap_data = 0, + sample_id_all = 1; + int idx = 0; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, + "|iKiKKiiiiiiiiiiiiiiiiiiiiiKK", kwlist, + &attr.type, &attr.config, &attr.sample_freq, + &sample_period, &attr.sample_type, + &attr.read_format, &disabled, &inherit, + &pinned, &exclusive, &exclude_user, + &exclude_kernel, &exclude_hv, &exclude_idle, + &mmap, &comm, &freq, &inherit_stat, + &enable_on_exec, &task, &watermark, + &precise_ip, &mmap_data, &sample_id_all, + &attr.wakeup_events, &attr.bp_type, + &attr.bp_addr, &attr.bp_len, &idx)) + return -1; + + /* union... */ + if (sample_period != 0) { + if (attr.sample_freq != 0) + return -1; /* FIXME: throw right exception */ + attr.sample_period = sample_period; + } + + /* Bitfields */ + attr.disabled = disabled; + attr.inherit = inherit; + attr.pinned = pinned; + attr.exclusive = exclusive; + attr.exclude_user = exclude_user; + attr.exclude_kernel = exclude_kernel; + attr.exclude_hv = exclude_hv; + attr.exclude_idle = exclude_idle; + attr.mmap = mmap; + attr.comm = comm; + attr.freq = freq; + attr.inherit_stat = inherit_stat; + attr.enable_on_exec = enable_on_exec; + attr.task = task; + attr.watermark = watermark; + attr.precise_ip = precise_ip; + attr.mmap_data = mmap_data; + attr.sample_id_all = sample_id_all; + + perf_evsel__init(&pevsel->evsel, &attr, idx); + return 0; +} + +static void pyrf_evsel__delete(struct pyrf_evsel *pevsel) +{ + perf_evsel__exit(&pevsel->evsel); + pevsel->ob_type->tp_free((PyObject*)pevsel); +} + +static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, + PyObject *args, PyObject *kwargs) +{ + struct perf_evsel *evsel = &pevsel->evsel; + struct cpu_map *cpus = NULL; + struct thread_map *threads = NULL; + PyObject *pcpus = NULL, *pthreads = NULL; + int group = 0, inherit = 0; + static char *kwlist[] = { "cpus", "threads", "group", "inherit", NULL }; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, + &pcpus, &pthreads, &group, &inherit)) + return NULL; + + if (pthreads != NULL) + threads = ((struct pyrf_thread_map *)pthreads)->threads; + + if (pcpus != NULL) + cpus = ((struct pyrf_cpu_map *)pcpus)->cpus; + + evsel->attr.inherit = inherit; + /* + * This will group just the fds for this single evsel, to group + * multiple events, use evlist.open(). + */ + if (perf_evsel__open(evsel, cpus, threads) < 0) { + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + + Py_INCREF(Py_None); + return Py_None; +} + +static PyMethodDef pyrf_evsel__methods[] = { + { + .ml_name = "open", + .ml_meth = (PyCFunction)pyrf_evsel__open, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("open the event selector file descriptor table.") + }, + { .ml_name = NULL, } +}; + +static char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object."); + +static PyTypeObject pyrf_evsel__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.evsel", + .tp_basicsize = sizeof(struct pyrf_evsel), + .tp_dealloc = (destructor)pyrf_evsel__delete, + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_evsel__doc, + .tp_methods = pyrf_evsel__methods, + .tp_init = (initproc)pyrf_evsel__init, +}; + +static int pyrf_evsel__setup_types(void) +{ + pyrf_evsel__type.tp_new = PyType_GenericNew; + return PyType_Ready(&pyrf_evsel__type); +} + +struct pyrf_evlist { + PyObject_HEAD + + struct perf_evlist evlist; +}; + +static int pyrf_evlist__init(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs __maybe_unused) +{ + PyObject *pcpus = NULL, *pthreads = NULL; + struct cpu_map *cpus; + struct thread_map *threads; + + if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads)) + return -1; + + threads = ((struct pyrf_thread_map *)pthreads)->threads; + cpus = ((struct pyrf_cpu_map *)pcpus)->cpus; + perf_evlist__init(&pevlist->evlist, cpus, threads); + return 0; +} + +static void pyrf_evlist__delete(struct pyrf_evlist *pevlist) +{ + perf_evlist__exit(&pevlist->evlist); + pevlist->ob_type->tp_free((PyObject*)pevlist); +} + +static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs) +{ + struct perf_evlist *evlist = &pevlist->evlist; + static char *kwlist[] = { "pages", "overwrite", NULL }; + int pages = 128, overwrite = false; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii", kwlist, + &pages, &overwrite)) + return NULL; + + if (perf_evlist__mmap(evlist, pages, overwrite) < 0) { + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + + Py_INCREF(Py_None); + return Py_None; +} + +static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs) +{ + struct perf_evlist *evlist = &pevlist->evlist; + static char *kwlist[] = { "timeout", NULL }; + int timeout = -1, n; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout)) + return NULL; + + n = poll(evlist->pollfd, evlist->nr_fds, timeout); + if (n < 0) { + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + + return Py_BuildValue("i", n); +} + +static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, + PyObject *args __maybe_unused, + PyObject *kwargs __maybe_unused) +{ + struct perf_evlist *evlist = &pevlist->evlist; + PyObject *list = PyList_New(0); + int i; + + for (i = 0; i < evlist->nr_fds; ++i) { + PyObject *file; + FILE *fp = fdopen(evlist->pollfd[i].fd, "r"); + + if (fp == NULL) + goto free_list; + + file = PyFile_FromFile(fp, "perf", "r", NULL); + if (file == NULL) + goto free_list; + + if (PyList_Append(list, file) != 0) { + Py_DECREF(file); + goto free_list; + } + + Py_DECREF(file); + } + + return list; +free_list: + return PyErr_NoMemory(); +} + + +static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist, + PyObject *args, + PyObject *kwargs __maybe_unused) +{ + struct perf_evlist *evlist = &pevlist->evlist; + PyObject *pevsel; + struct perf_evsel *evsel; + + if (!PyArg_ParseTuple(args, "O", &pevsel)) + return NULL; + + Py_INCREF(pevsel); + evsel = &((struct pyrf_evsel *)pevsel)->evsel; + evsel->idx = evlist->nr_entries; + perf_evlist__add(evlist, evsel); + + return Py_BuildValue("i", evlist->nr_entries); +} + +static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs) +{ + struct perf_evlist *evlist = &pevlist->evlist; + union perf_event *event; + int sample_id_all = 1, cpu; + static char *kwlist[] = { "cpu", "sample_id_all", NULL }; + int err; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist, + &cpu, &sample_id_all)) + return NULL; + + event = perf_evlist__mmap_read(evlist, cpu); + if (event != NULL) { + 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(); + + err = perf_evlist__parse_sample(evlist, event, &pevent->sample); + if (err) + return PyErr_Format(PyExc_OSError, + "perf: can't parse sample, err=%d", err); + return pyevent; + } + + Py_INCREF(Py_None); + return Py_None; +} + +static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs) +{ + struct perf_evlist *evlist = &pevlist->evlist; + int group = 0; + static char *kwlist[] = { "group", NULL }; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, &group)) + return NULL; + + if (group) + perf_evlist__set_leader(evlist); + + if (perf_evlist__open(evlist) < 0) { + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + + Py_INCREF(Py_None); + return Py_None; +} + +static PyMethodDef pyrf_evlist__methods[] = { + { + .ml_name = "mmap", + .ml_meth = (PyCFunction)pyrf_evlist__mmap, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("mmap the file descriptor table.") + }, + { + .ml_name = "open", + .ml_meth = (PyCFunction)pyrf_evlist__open, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("open the file descriptors.") + }, + { + .ml_name = "poll", + .ml_meth = (PyCFunction)pyrf_evlist__poll, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("poll the file descriptor table.") + }, + { + .ml_name = "get_pollfd", + .ml_meth = (PyCFunction)pyrf_evlist__get_pollfd, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("get the poll file descriptor table.") + }, + { + .ml_name = "add", + .ml_meth = (PyCFunction)pyrf_evlist__add, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("adds an event selector to the list.") + }, + { + .ml_name = "read_on_cpu", + .ml_meth = (PyCFunction)pyrf_evlist__read_on_cpu, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("reads an event.") + }, + { .ml_name = NULL, } +}; + +static Py_ssize_t pyrf_evlist__length(PyObject *obj) +{ + struct pyrf_evlist *pevlist = (void *)obj; + + return pevlist->evlist.nr_entries; +} + +static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i) +{ + struct pyrf_evlist *pevlist = (void *)obj; + struct perf_evsel *pos; + + if (i >= pevlist->evlist.nr_entries) + return NULL; + + evlist__for_each(&pevlist->evlist, pos) { + if (i-- == 0) + break; + } + + return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel)); +} + +static PySequenceMethods pyrf_evlist__sequence_methods = { + .sq_length = pyrf_evlist__length, + .sq_item = pyrf_evlist__item, +}; + +static char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object."); + +static PyTypeObject pyrf_evlist__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.evlist", + .tp_basicsize = sizeof(struct pyrf_evlist), + .tp_dealloc = (destructor)pyrf_evlist__delete, + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_as_sequence = &pyrf_evlist__sequence_methods, + .tp_doc = pyrf_evlist__doc, + .tp_methods = pyrf_evlist__methods, + .tp_init = (initproc)pyrf_evlist__init, +}; + +static int pyrf_evlist__setup_types(void) +{ + pyrf_evlist__type.tp_new = PyType_GenericNew; + return PyType_Ready(&pyrf_evlist__type); +} + +static struct { + const char *name; + int value; +} perf__constants[] = { + { "TYPE_HARDWARE", PERF_TYPE_HARDWARE }, + { "TYPE_SOFTWARE", PERF_TYPE_SOFTWARE }, + { "TYPE_TRACEPOINT", PERF_TYPE_TRACEPOINT }, + { "TYPE_HW_CACHE", PERF_TYPE_HW_CACHE }, + { "TYPE_RAW", PERF_TYPE_RAW }, + { "TYPE_BREAKPOINT", PERF_TYPE_BREAKPOINT }, + + { "COUNT_HW_CPU_CYCLES", PERF_COUNT_HW_CPU_CYCLES }, + { "COUNT_HW_INSTRUCTIONS", PERF_COUNT_HW_INSTRUCTIONS }, + { "COUNT_HW_CACHE_REFERENCES", PERF_COUNT_HW_CACHE_REFERENCES }, + { "COUNT_HW_CACHE_MISSES", PERF_COUNT_HW_CACHE_MISSES }, + { "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + { "COUNT_HW_BRANCH_MISSES", PERF_COUNT_HW_BRANCH_MISSES }, + { "COUNT_HW_BUS_CYCLES", PERF_COUNT_HW_BUS_CYCLES }, + { "COUNT_HW_CACHE_L1D", PERF_COUNT_HW_CACHE_L1D }, + { "COUNT_HW_CACHE_L1I", PERF_COUNT_HW_CACHE_L1I }, + { "COUNT_HW_CACHE_LL", PERF_COUNT_HW_CACHE_LL }, + { "COUNT_HW_CACHE_DTLB", PERF_COUNT_HW_CACHE_DTLB }, + { "COUNT_HW_CACHE_ITLB", PERF_COUNT_HW_CACHE_ITLB }, + { "COUNT_HW_CACHE_BPU", PERF_COUNT_HW_CACHE_BPU }, + { "COUNT_HW_CACHE_OP_READ", PERF_COUNT_HW_CACHE_OP_READ }, + { "COUNT_HW_CACHE_OP_WRITE", PERF_COUNT_HW_CACHE_OP_WRITE }, + { "COUNT_HW_CACHE_OP_PREFETCH", PERF_COUNT_HW_CACHE_OP_PREFETCH }, + { "COUNT_HW_CACHE_RESULT_ACCESS", PERF_COUNT_HW_CACHE_RESULT_ACCESS }, + { "COUNT_HW_CACHE_RESULT_MISS", PERF_COUNT_HW_CACHE_RESULT_MISS }, + + { "COUNT_HW_STALLED_CYCLES_FRONTEND", PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + { "COUNT_HW_STALLED_CYCLES_BACKEND", PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, + + { "COUNT_SW_CPU_CLOCK", PERF_COUNT_SW_CPU_CLOCK }, + { "COUNT_SW_TASK_CLOCK", PERF_COUNT_SW_TASK_CLOCK }, + { "COUNT_SW_PAGE_FAULTS", PERF_COUNT_SW_PAGE_FAULTS }, + { "COUNT_SW_CONTEXT_SWITCHES", PERF_COUNT_SW_CONTEXT_SWITCHES }, + { "COUNT_SW_CPU_MIGRATIONS", PERF_COUNT_SW_CPU_MIGRATIONS }, + { "COUNT_SW_PAGE_FAULTS_MIN", PERF_COUNT_SW_PAGE_FAULTS_MIN }, + { "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 }, + { "SAMPLE_TIME", PERF_SAMPLE_TIME }, + { "SAMPLE_ADDR", PERF_SAMPLE_ADDR }, + { "SAMPLE_READ", PERF_SAMPLE_READ }, + { "SAMPLE_CALLCHAIN", PERF_SAMPLE_CALLCHAIN }, + { "SAMPLE_ID", PERF_SAMPLE_ID }, + { "SAMPLE_CPU", PERF_SAMPLE_CPU }, + { "SAMPLE_PERIOD", PERF_SAMPLE_PERIOD }, + { "SAMPLE_STREAM_ID", PERF_SAMPLE_STREAM_ID }, + { "SAMPLE_RAW", PERF_SAMPLE_RAW }, + + { "FORMAT_TOTAL_TIME_ENABLED", PERF_FORMAT_TOTAL_TIME_ENABLED }, + { "FORMAT_TOTAL_TIME_RUNNING", PERF_FORMAT_TOTAL_TIME_RUNNING }, + { "FORMAT_ID", PERF_FORMAT_ID }, + { "FORMAT_GROUP", PERF_FORMAT_GROUP }, + + { "RECORD_MMAP", PERF_RECORD_MMAP }, + { "RECORD_LOST", PERF_RECORD_LOST }, + { "RECORD_COMM", PERF_RECORD_COMM }, + { "RECORD_EXIT", PERF_RECORD_EXIT }, + { "RECORD_THROTTLE", PERF_RECORD_THROTTLE }, + { "RECORD_UNTHROTTLE", PERF_RECORD_UNTHROTTLE }, + { "RECORD_FORK", PERF_RECORD_FORK }, + { "RECORD_READ", PERF_RECORD_READ }, + { "RECORD_SAMPLE", PERF_RECORD_SAMPLE }, + { .name = NULL, }, +}; + +static PyMethodDef perf__methods[] = { + { .ml_name = NULL, } +}; + +PyMODINIT_FUNC initperf(void) +{ + PyObject *obj; + int i; + PyObject *dict, *module = Py_InitModule("perf", perf__methods); + + if (module == NULL || + pyrf_event__setup_types() < 0 || + pyrf_evlist__setup_types() < 0 || + pyrf_evsel__setup_types() < 0 || + pyrf_thread_map__setup_types() < 0 || + 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); + PyModule_AddObject(module, "evlist", (PyObject*)&pyrf_evlist__type); + + Py_INCREF(&pyrf_evsel__type); + PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type); + + Py_INCREF(&pyrf_thread_map__type); + PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type); + + Py_INCREF(&pyrf_cpu_map__type); + PyModule_AddObject(module, "cpu_map", (PyObject*)&pyrf_cpu_map__type); + + dict = PyModule_GetDict(module); + if (dict == NULL) + goto error; + + for (i = 0; perf__constants[i].name != NULL; i++) { + obj = PyInt_FromLong(perf__constants[i].value); + if (obj == NULL) + goto error; + PyDict_SetItemString(dict, perf__constants[i].name, obj); + Py_DECREF(obj); + } + +error: + if (PyErr_Occurred()) + PyErr_SetString(PyExc_ImportError, "perf: Init failed!"); +} + +/* + * Dummy, to avoid dragging all the test_attr infrastructure in the python + * binding. + */ +void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, + int fd, int group_fd, unsigned long flags) +{ +} diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c new file mode 100644 index 00000000000..0dfe27d9945 --- /dev/null +++ b/tools/perf/util/rblist.c @@ -0,0 +1,128 @@ +/* + * Based on strlist.c by: + * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Licensed under the GPLv2. + */ + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> + +#include "rblist.h" + +int rblist__add_node(struct rblist *rblist, const void *new_entry) +{ + struct rb_node **p = &rblist->entries.rb_node; + struct rb_node *parent = NULL, *new_node; + + while (*p != NULL) { + int rc; + + parent = *p; + + rc = rblist->node_cmp(parent, new_entry); + if (rc > 0) + p = &(*p)->rb_left; + else if (rc < 0) + p = &(*p)->rb_right; + else + return -EEXIST; + } + + new_node = rblist->node_new(rblist, new_entry); + if (new_node == NULL) + return -ENOMEM; + + rb_link_node(new_node, parent, p); + rb_insert_color(new_node, &rblist->entries); + ++rblist->nr_entries; + + return 0; +} + +void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node) +{ + rb_erase(rb_node, &rblist->entries); + --rblist->nr_entries; + rblist->node_delete(rblist, rb_node); +} + +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, *new_node = NULL; + + while (*p != NULL) { + int rc; + + parent = *p; + + rc = rblist->node_cmp(parent, entry); + if (rc > 0) + p = &(*p)->rb_left; + else if (rc < 0) + p = &(*p)->rb_right; + else + return parent; + } + + 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) +{ + if (rblist != NULL) { + rblist->entries = RB_ROOT; + rblist->nr_entries = 0; + } + + return; +} + +void rblist__delete(struct rblist *rblist) +{ + if (rblist != NULL) { + struct rb_node *pos, *next = rb_first(&rblist->entries); + + while (next) { + pos = next; + next = rb_next(pos); + rblist__remove_node(rblist, pos); + } + free(rblist); + } +} + +struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx) +{ + struct rb_node *node; + + for (node = rb_first(&rblist->entries); node; node = rb_next(node)) { + if (!idx--) + return node; + } + + return NULL; +} diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h new file mode 100644 index 00000000000..ff9913b994c --- /dev/null +++ b/tools/perf/util/rblist.h @@ -0,0 +1,48 @@ +#ifndef __PERF_RBLIST_H +#define __PERF_RBLIST_H + +#include <linux/rbtree.h> +#include <stdbool.h> + +/* + * create node structs of the form: + * struct my_node { + * struct rb_node rb_node; + * ... my data ... + * }; + * + * create list structs of the form: + * struct mylist { + * struct rblist rblist; + * ... my data ... + * }; + */ + +struct rblist { + struct rb_root entries; + unsigned int nr_entries; + + int (*node_cmp)(struct rb_node *rbn, const void *entry); + struct rb_node *(*node_new)(struct rblist *rlist, const void *new_entry); + void (*node_delete)(struct rblist *rblist, struct rb_node *rb_node); +}; + +void rblist__init(struct rblist *rblist); +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) +{ + return rblist->nr_entries == 0; +} + +static inline unsigned int rblist__nr_entries(const struct rblist *rblist) +{ + return rblist->nr_entries; +} + +#endif /* __PERF_RBLIST_H */ diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c new file mode 100644 index 00000000000..049e0a09ccd --- /dev/null +++ b/tools/perf/util/record.c @@ -0,0 +1,215 @@ +#include "evlist.h" +#include "evsel.h" +#include "cpumap.h" +#include "parse-events.h" +#include <api/fs/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 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; + + evlist__for_each(evlist, evsel) + perf_evsel__config(evsel, opts); + + if (evlist->nr_entries > 1) { + struct perf_evsel *first = perf_evlist__first(evlist); + + evlist__for_each(evlist, evsel) { + if (evsel->attr.sample_type == first->attr.sample_type) + continue; + use_sample_identifier = perf_can_sample_identifier(); + break; + } + evlist__for_each(evlist, evsel) + 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 record_opts__config_freq(struct 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 record_opts__config(struct record_opts *opts) +{ + return record_opts__config_freq(opts); +} + +bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) +{ + struct perf_evlist *temp_evlist; + struct perf_evsel *evsel; + int err, fd, cpu; + bool ret = false; + + temp_evlist = perf_evlist__new(); + if (!temp_evlist) + return false; + + err = parse_events(temp_evlist, str); + if (err) + goto out_delete; + + evsel = perf_evlist__last(temp_evlist); + + if (!evlist || cpu_map__empty(evlist->cpus)) { + struct cpu_map *cpus = cpu_map__new(NULL); + + cpu = cpus ? cpus->map[0] : 0; + cpu_map__delete(cpus); + } else { + cpu = evlist->cpus->map[0]; + } + + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + if (fd >= 0) { + close(fd); + ret = true; + } + +out_delete: + perf_evlist__delete(temp_evlist); + return ret; +} diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index b059dc50cc2..af7da565a75 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -1,5 +1,5 @@ /* - * trace-event-perl. Feed perf trace events to an embedded Perl interpreter. + * trace-event-perl. Feed perf script events to an embedded Perl interpreter. * * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com> * @@ -25,13 +25,16 @@ #include <ctype.h> #include <errno.h> -#include "../../perf.h" #include "../util.h" -#include "../trace-event.h" - #include <EXTERN.h> #include <perl.h> +#include "../../perf.h" +#include "../thread.h" +#include "../event.h" +#include "../trace-event.h" +#include "../evsel.h" + void boot_Perf__Trace__Context(pTHX_ CV *cv); void boot_DynaLoader(pTHX_ CV *cv); typedef PerlInterpreter * INTERP; @@ -53,7 +56,7 @@ INTERP my_perl; #define FTRACE_MAX_EVENT \ ((1 << (sizeof(unsigned short) * 8)) - 1) -struct event *events[FTRACE_MAX_EVENT]; +struct event_format *events[FTRACE_MAX_EVENT]; extern struct scripting_context *scripting_context; @@ -178,7 +181,7 @@ static void define_flag_field(const char *ev_name, LEAVE; } -static void define_event_symbols(struct event *event, +static void define_event_symbols(struct event_format *event, const char *ev_name, struct print_arg *args) { @@ -191,8 +194,7 @@ static void define_event_symbols(struct event *event, zero_flag_atom = 0; break; case PRINT_FIELD: - if (cur_field_name) - free(cur_field_name); + free(cur_field_name); cur_field_name = strdup(args->field.name); break; case PRINT_FLAGS: @@ -206,7 +208,14 @@ static void define_event_symbols(struct event *event, define_symbolic_values(args->symbol.symbols, ev_name, cur_field_name); break; + case PRINT_HEX: + define_event_symbols(event, ev_name, args->hex.field); + define_event_symbols(event, ev_name, args->hex.size); + break; + case PRINT_BSTRING: + case PRINT_DYNAMIC_ARRAY: case PRINT_STRING: + case PRINT_BITMASK: break; case PRINT_TYPE: define_event_symbols(event, ev_name, args->typecast.item); @@ -217,7 +226,9 @@ static void define_event_symbols(struct event *event, define_event_symbols(event, ev_name, args->op.left); define_event_symbols(event, ev_name, args->op.right); break; + case PRINT_FUNC: default: + pr_err("Unsupported print arg type\n"); /* we should warn... */ return; } @@ -226,15 +237,16 @@ static void define_event_symbols(struct event *event, define_event_symbols(event, ev_name, args->next); } -static inline struct event *find_cache_event(int type) +static inline struct event_format *find_cache_event(struct perf_evsel *evsel) { static char ev_name[256]; - struct event *event; + struct event_format *event; + int type = evsel->attr.config; if (events[type]) return events[type]; - events[type] = event = trace_find_event(type); + events[type] = event = evsel->tp_format; if (!event) return NULL; @@ -245,27 +257,31 @@ static inline struct event *find_cache_event(int type) return event; } -static void perl_process_event(int cpu, void *data, - int size __unused, - unsigned long long nsecs, char *comm) +static void perl_process_tracepoint(struct perf_sample *sample, + struct perf_evsel *evsel, + struct thread *thread) { struct format_field *field; static char handler[256]; unsigned long long val; unsigned long s, ns; - struct event *event; - int type; + struct event_format *event; int pid; + int cpu = sample->cpu; + void *data = sample->raw_data; + unsigned long long nsecs = sample->time; + const char *comm = thread__comm_str(thread); dSP; - type = trace_parse_common_type(data); + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + return; - event = find_cache_event(type); + event = find_cache_event(evsel); if (!event) - die("ug! no event found for type %d", type); + die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); - pid = trace_parse_common_pid(data); + pid = raw_field_value(event, "common_pid", data); sprintf(handler, "%s::%s", event->system, event->name); @@ -273,6 +289,7 @@ static void perl_process_event(int cpu, void *data, ns = nsecs - s * NSECS_PER_SEC; scripting_context->event_data = data; + scripting_context->pevent = evsel->tp_format->pevent; ENTER; SAVETMPS; @@ -298,7 +315,8 @@ static void perl_process_event(int cpu, void *data, offset = field->offset; XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0))); } else { /* FIELD_IS_NUMERIC */ - val = read_size(data + field->offset, field->size); + val = read_size(event, data + field->offset, + field->size); if (field->flags & FIELD_IS_SIGNED) { XPUSHs(sv_2mortal(newSViv(val))); } else { @@ -326,6 +344,40 @@ static void perl_process_event(int cpu, void *data, LEAVE; } +static void perl_process_event_generic(union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel) +{ + dSP; + + if (!get_cv("process_event", 0)) + return; + + ENTER; + SAVETMPS; + PUSHMARK(SP); + XPUSHs(sv_2mortal(newSVpvn((const char *)event, event->header.size))); + XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->attr, sizeof(evsel->attr)))); + XPUSHs(sv_2mortal(newSVpvn((const char *)sample, sizeof(*sample)))); + XPUSHs(sv_2mortal(newSVpvn((const char *)sample->raw_data, sample->raw_size))); + PUTBACK; + call_pv("process_event", G_SCALAR); + SPAGAIN; + PUTBACK; + FREETMPS; + LEAVE; +} + +static void perl_process_event(union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct thread *thread, + struct addr_location *al __maybe_unused) +{ + perl_process_tracepoint(sample, evsel, thread); + perl_process_event_generic(event, sample, evsel); +} + static void run_start_sub(void) { dSP; /* access to Perl stack */ @@ -396,9 +448,9 @@ static int perl_stop_script(void) return 0; } -static int perl_generate_script(const char *outfile) +static int perl_generate_script(struct pevent *pevent, const char *outfile) { - struct event *event = NULL; + struct event_format *event = NULL; struct format_field *f; char fname[PATH_MAX]; int not_first, count; @@ -411,8 +463,8 @@ static int perl_generate_script(const char *outfile) return -1; } - fprintf(ofp, "# perf trace event handlers, " - "generated by perf trace -g perl\n"); + fprintf(ofp, "# perf script event handlers, " + "generated by perf script -g perl\n"); fprintf(ofp, "# Licensed under the terms of the GNU GPL" " License version 2\n\n"); @@ -443,7 +495,7 @@ static int perl_generate_script(const char *outfile) fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n"); fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n"); - while ((event = trace_find_next_event(event))) { + while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); fprintf(ofp, "\tmy ("); @@ -547,7 +599,28 @@ static int perl_generate_script(const char *outfile) fprintf(ofp, "sub print_header\n{\n" "\tmy ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_;\n\n" "\tprintf(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \",\n\t " - "$event_name, $cpu, $secs, $nsecs, $pid, $comm);\n}"); + "$event_name, $cpu, $secs, $nsecs, $pid, $comm);\n}\n"); + + fprintf(ofp, + "\n# Packed byte string args of process_event():\n" + "#\n" + "# $event:\tunion perf_event\tutil/event.h\n" + "# $attr:\tstruct perf_event_attr\tlinux/perf_event.h\n" + "# $sample:\tstruct perf_sample\tutil/event.h\n" + "# $raw_data:\tperf_sample->raw_data\tutil/event.h\n" + "\n" + "sub process_event\n" + "{\n" + "\tmy ($event, $attr, $sample, $raw_data) = @_;\n" + "\n" + "\tmy @event\t= unpack(\"LSS\", $event);\n" + "\tmy @attr\t= unpack(\"LLQQQQQLLQQ\", $attr);\n" + "\tmy @sample\t= unpack(\"QLLQQQQQLL\", $sample);\n" + "\tmy @raw_data\t= unpack(\"C*\", $raw_data);\n" + "\n" + "\tuse Data::Dumper;\n" + "\tprint Dumper \\@event, \\@attr, \\@sample, \\@raw_data;\n" + "}\n"); fclose(ofp); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 33a63252374..1c419321f70 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -24,11 +24,13 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <ctype.h> #include <errno.h> #include "../../perf.h" +#include "../evsel.h" #include "../util.h" +#include "../event.h" +#include "../thread.h" #include "../trace-event.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -36,7 +38,7 @@ PyMODINIT_FUNC initperf_trace_context(void); #define FTRACE_MAX_EVENT \ ((1 << (sizeof(unsigned short) * 8)) - 1) -struct event *events[FTRACE_MAX_EVENT]; +struct event_format *events[FTRACE_MAX_EVENT]; #define MAX_FIELDS 64 #define N_COMMON_FIELDS 7 @@ -54,6 +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, @@ -135,7 +148,7 @@ static void define_field(enum print_arg_type field_type, Py_DECREF(t); } -static void define_event_symbols(struct event *event, +static void define_event_symbols(struct event_format *event, const char *ev_name, struct print_arg *args) { @@ -148,8 +161,7 @@ static void define_event_symbols(struct event *event, zero_flag_atom = 0; break; case PRINT_FIELD: - if (cur_field_name) - free(cur_field_name); + free(cur_field_name); cur_field_name = strdup(args->field.name); break; case PRINT_FLAGS: @@ -165,6 +177,10 @@ static void define_event_symbols(struct event *event, define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name, cur_field_name); break; + case PRINT_HEX: + define_event_symbols(event, ev_name, args->hex.field); + define_event_symbols(event, ev_name, args->hex.size); + break; case PRINT_STRING: break; case PRINT_TYPE: @@ -177,6 +193,11 @@ static void define_event_symbols(struct event *event, define_event_symbols(event, ev_name, args->op.right); break; default: + /* gcc warns for these? */ + case PRINT_BSTRING: + case PRINT_DYNAMIC_ARRAY: + case PRINT_FUNC: + case PRINT_BITMASK: /* we should warn... */ return; } @@ -185,15 +206,21 @@ static void define_event_symbols(struct event *event, define_event_symbols(event, ev_name, args->next); } -static inline struct event *find_cache_event(int type) +static inline struct event_format *find_cache_event(struct perf_evsel *evsel) { static char ev_name[256]; - struct event *event; - + struct event_format *event; + int type = evsel->attr.config; + + /* + * XXX: Do we really need to cache this since now we have evsel->tp_format + * cached already? Need to re-read this "cache" routine that as well calls + * define_event_symbols() :-\ + */ if (events[type]) return events[type]; - events[type] = event = trace_find_event(type); + events[type] = event = evsel->tp_format; if (!event) return NULL; @@ -204,31 +231,33 @@ static inline struct event *find_cache_event(int type) return event; } -static void python_process_event(int cpu, void *data, - int size __unused, - unsigned long long nsecs, char *comm) +static void python_process_tracepoint(struct perf_sample *sample, + struct perf_evsel *evsel, + struct thread *thread, + struct addr_location *al) { PyObject *handler, *retval, *context, *t, *obj, *dict = NULL; static char handler_name[256]; struct format_field *field; unsigned long long val; unsigned long s, ns; - struct event *event; + struct event_format *event; unsigned n = 0; - int type; int pid; + int cpu = sample->cpu; + void *data = sample->raw_data; + unsigned long long nsecs = sample->time; + const char *comm = thread__comm_str(thread); t = PyTuple_New(MAX_FIELDS); if (!t) Py_FatalError("couldn't create Python tuple"); - type = trace_parse_common_type(data); - - event = find_cache_event(type); + event = find_cache_event(evsel); if (!event) - die("ug! no event found for type %d", type); + die("ug! no event found for type %d", (int)evsel->attr.config); - pid = trace_parse_common_pid(data); + pid = raw_field_value(event, "common_pid", data); sprintf(handler_name, "%s__%s", event->system, event->name); @@ -244,12 +273,12 @@ static void python_process_event(int cpu, void *data, ns = nsecs - s * NSECS_PER_SEC; scripting_context->event_data = data; + scripting_context->pevent = evsel->tp_format->pevent; context = PyCObject_FromVoidPtr(scripting_context, NULL); PyTuple_SetItem(t, n++, PyString_FromString(handler_name)); - PyTuple_SetItem(t, n++, - PyCObject_FromVoidPtr(scripting_context, NULL)); + PyTuple_SetItem(t, n++, context); if (handler) { PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); @@ -258,11 +287,11 @@ static void python_process_event(int cpu, void *data, 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) { @@ -274,7 +303,8 @@ static void python_process_event(int cpu, void *data, offset = field->offset; obj = PyString_FromString((char *)data + offset); } else { /* FIELD_IS_NUMERIC */ - val = read_size(data + field->offset, field->size); + val = read_size(event, data + field->offset, + field->size); if (field->flags & FIELD_IS_SIGNED) { if ((long long)val >= LONG_MIN && (long long)val <= LONG_MAX) @@ -291,7 +321,7 @@ static void python_process_event(int cpu, void *data, 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) @@ -318,6 +348,79 @@ static void python_process_event(int cpu, void *data, Py_DECREF(t); } +static void python_process_general_event(struct perf_sample *sample, + struct perf_evsel *evsel, + struct thread *thread, + struct addr_location *al) +{ + PyObject *handler, *retval, *t, *dict; + static char handler_name[64]; + unsigned n = 0; + + /* + * Use the MAX_FIELDS to make the function expandable, though + * currently there is only one item for the tuple. + */ + t = PyTuple_New(MAX_FIELDS); + if (!t) + Py_FatalError("couldn't create Python tuple"); + + dict = PyDict_New(); + if (!dict) + Py_FatalError("couldn't create Python dictionary"); + + snprintf(handler_name, sizeof(handler_name), "%s", "process_event"); + + handler = PyDict_GetItemString(main_dict, handler_name); + if (!handler || !PyCallable_Check(handler)) + goto exit; + + pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); + pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( + (const char *)&evsel->attr, sizeof(evsel->attr))); + pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize( + (const char *)sample, sizeof(*sample))); + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( + (const char *)sample->raw_data, sample->raw_size)); + pydict_set_item_string_decref(dict, "comm", + PyString_FromString(thread__comm_str(thread))); + if (al->map) { + pydict_set_item_string_decref(dict, "dso", + PyString_FromString(al->map->dso->name)); + } + if (al->sym) { + pydict_set_item_string_decref(dict, "symbol", + PyString_FromString(al->sym->name)); + } + + PyTuple_SetItem(t, n++, dict); + if (_PyTuple_Resize(&t, n) == -1) + Py_FatalError("error resizing Python tuple"); + + retval = PyObject_CallObject(handler, t); + if (retval == NULL) + handler_call_die(handler_name); +exit: + Py_DECREF(dict); + Py_DECREF(t); +} + +static void python_process_event(union perf_event *event __maybe_unused, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct thread *thread, + struct addr_location *al) +{ + switch (evsel->attr.type) { + case PERF_TYPE_TRACEPOINT: + python_process_tracepoint(sample, evsel, thread, al); + break; + /* Reserve for future process_hw/sw/raw APIs */ + default: + python_process_general_event(sample, evsel, thread, al); + } +} + static int run_start_sub(void) { PyObject *handler, *retval; @@ -428,9 +531,9 @@ out: return err; } -static int python_generate_script(const char *outfile) +static int python_generate_script(struct pevent *pevent, const char *outfile) { - struct event *event = NULL; + struct event_format *event = NULL; struct format_field *f; char fname[PATH_MAX]; int not_first, count; @@ -442,8 +545,8 @@ static int python_generate_script(const char *outfile) fprintf(stderr, "couldn't open %s\n", fname); return -1; } - fprintf(ofp, "# perf trace event handlers, " - "generated by perf trace -g python\n"); + fprintf(ofp, "# perf script event handlers, " + "generated by perf script -g python\n"); fprintf(ofp, "# Licensed under the terms of the GNU GPL" " License version 2\n\n"); @@ -477,7 +580,7 @@ static int python_generate_script(const char *outfile) fprintf(ofp, "def trace_end():\n"); fprintf(ofp, "\tprint \"in trace_end\"\n\n"); - while ((event = trace_find_next_event(event))) { + while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "def %s__%s(", event->system, event->name); fprintf(ofp, "event_name, "); fprintf(ofp, "context, "); @@ -520,6 +623,7 @@ static int python_generate_script(const char *outfile) fprintf(ofp, "%s=", f->name); if (f->flags & FIELD_IS_STRING || f->flags & FIELD_IS_FLAG || + f->flags & FIELD_IS_ARRAY || f->flags & FIELD_IS_SYMBOLIC) fprintf(ofp, "%%s"); else if (f->flags & FIELD_IS_SIGNED) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index fa9d652c2dc..64a186edc7b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,419 +1,531 @@ -#define _FILE_OFFSET_BITS 64 - #include <linux/kernel.h> +#include <traceevent/event-parse.h> #include <byteswap.h> #include <unistd.h> #include <sys/types.h> #include <sys/mman.h> +#include "evlist.h" +#include "evsel.h" #include "session.h" +#include "tool.h" #include "sort.h" #include "util.h" +#include "cpumap.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; - - if (!strcmp(self->filename, "-")) { - self->fd_pipe = true; - self->fd = STDIN_FILENO; - - if (perf_header__read(self, self->fd) < 0) - pr_err("incompatible file format"); - - return 0; - } - - self->fd = open(self->filename, O_RDONLY); - if (self->fd < 0) { - int err = errno; + struct perf_data_file *file = session->file; - 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 (perf_session__read_header(session) < 0) { + pr_err("incompatible file format (rerun with -v to learn more)"); + return -1; } - if (fstat(self->fd, &input_stat) < 0) - goto out_close; + if (perf_data_file__is_pipe(file)) + return 0; - 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 (!perf_evlist__valid_sample_type(session->evlist)) { + pr_err("non matching sample_type"); + return -1; } - if (!input_stat.st_size) { - pr_info("zero-sized file (%s), nothing to do!\n", - self->filename); - goto out_close; + if (!perf_evlist__valid_sample_id_all(session->evlist)) { + pr_err("non matching sample_id_all"); + return -1; } - if (perf_header__read(self, self->fd) < 0) { - pr_err("incompatible file format"); - goto out_close; + if (!perf_evlist__valid_read_format(session->evlist)) { + pr_err("non matching read_format"); + return -1; } - self->size = input_stat.st_size; return 0; - -out_close: - close(self->fd); - self->fd = -1; - return -1; } -void perf_session__update_sample_type(struct perf_session *self) +void perf_session__set_id_hdr_size(struct perf_session *session) { - self->sample_type = perf_header__sample_type(&self->header); + u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist); + + 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->host_machine); + 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) { - machine__destroy_kernel_maps(&self->host_machine); - machines__destroy_guest_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_session *perf_session__new(struct perf_data_file *file, + bool repipe, struct perf_tool *tool) { - size_t len = filename ? strlen(filename) + 1 : 0; - struct perf_session *self = zalloc(sizeof(*self) + len); + struct perf_session *session = zalloc(sizeof(*session)); - if (self == NULL) + if (!session) goto out; - if (perf_header__init(&self->header) < 0) - goto out_free; - - memcpy(self->filename, filename, len); - self->threads = RB_ROOT; - INIT_LIST_HEAD(&self->dead_threads); - self->hists_tree = RB_ROOT; - self->last_match = NULL; - self->mmap_window = 32; - self->machines = RB_ROOT; - self->repipe = repipe; - INIT_LIST_HEAD(&self->ordered_samples.samples_head); - machine__init(&self->host_machine, "", HOST_KERNEL_ID); - - if (mode == O_RDONLY) { - if (perf_session__open(self, force) < 0) + 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 (file) { + if (perf_data_file__open(file)) goto out_delete; - } 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 event__process_mmap(). + * 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; } - perf_session__update_sample_type(self); -out: - return self; -out_free: - free(self); - return NULL; -out_delete: - perf_session__delete(self); + if (tool && tool->ordering_requires_timestamps && + 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; + } + + return session; + + out_close: + perf_data_file__close(file); + out_delete: + perf_session__delete(session); + out: return NULL; } -static void perf_session__delete_dead_threads(struct perf_session *self) +static void perf_session__delete_dead_threads(struct perf_session *session) { - struct thread *n, *t; - - list_for_each_entry_safe(t, n, &self->dead_threads, node) { - list_del(&t->node); - thread__delete(t); - } + machine__delete_dead_threads(&session->machines.host); } -static void perf_session__delete_threads(struct perf_session *self) +static void perf_session__delete_threads(struct perf_session *session) { - struct rb_node *nd = rb_first(&self->threads); - - while (nd) { - struct thread *t = rb_entry(nd, struct thread, rb_node); - - rb_erase(&t->rb_node, &self->threads); - nd = rb_next(nd); - thread__delete(t); - } + machine__delete_threads(&session->machines.host); } -void perf_session__delete(struct perf_session *self) +static void perf_session_env__delete(struct perf_session_env *env) { - perf_header__exit(&self->header); - perf_session__destroy_kernel_maps(self); - perf_session__delete_dead_threads(self); - perf_session__delete_threads(self); - machine__exit(&self->host_machine); - close(self->fd); - free(self); + zfree(&env->hostname); + zfree(&env->os_release); + zfree(&env->version); + zfree(&env->arch); + zfree(&env->cpu_desc); + zfree(&env->cpuid); + + zfree(&env->cmdline); + zfree(&env->sibling_cores); + zfree(&env->sibling_threads); + zfree(&env->numa_nodes); + zfree(&env->pmu_mappings); } -void perf_session__remove_thread(struct perf_session *self, struct thread *th) +void perf_session__delete(struct perf_session *session) { - self->last_match = NULL; - rb_erase(&th->rb_node, &self->threads); - /* - * We may have references to this thread, for instance in some hist_entry - * instances, so just move them to a separate list. - */ - list_add_tail(&th->node, &self->dead_threads); + 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 bool symbol__match_parent_regex(struct symbol *sym) +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) { - if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0)) - return 1; - + dump_printf(": unhandled!\n"); return 0; } -struct map_symbol *perf_session__resolve_callchain(struct perf_session *self, - struct thread *thread, - struct ip_callchain *chain, - struct symbol **parent) +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) { - u8 cpumode = PERF_RECORD_MISC_USER; - unsigned int i; - struct map_symbol *syms = calloc(chain->nr, sizeof(*syms)); - - if (!syms) - return NULL; - - for (i = 0; i < chain->nr; i++) { - u64 ip = chain->ips[i]; - struct addr_location al; - - if (ip >= PERF_CONTEXT_MAX) { - switch (ip) { - case PERF_CONTEXT_HV: - cpumode = PERF_RECORD_MISC_HYPERVISOR; break; - case PERF_CONTEXT_KERNEL: - cpumode = PERF_RECORD_MISC_KERNEL; break; - case PERF_CONTEXT_USER: - cpumode = PERF_RECORD_MISC_USER; break; - default: - break; - } - continue; - } - - al.filtered = false; - thread__find_addr_location(thread, self, cpumode, - MAP__FUNCTION, thread->pid, ip, &al, NULL); - if (al.sym != NULL) { - if (sort__has_parent && !*parent && - symbol__match_parent_regex(al.sym)) - *parent = al.sym; - if (!symbol_conf.use_callchain) - break; - syms[i].map = al.map; - syms[i].sym = al.sym; - } - } + dump_printf(": unhandled!\n"); + return 0; +} - return syms; +static int process_event_sample_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct machine *machine __maybe_unused) +{ + dump_printf(": unhandled!\n"); + return 0; } -static int process_event_stub(event_t *event __used, - struct perf_session *session __used) +static int process_event_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) { dump_printf(": unhandled!\n"); return 0; } -static int process_finished_round_stub(event_t *event __used, - struct perf_session *session __used, - struct perf_event_ops *ops __used) +static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *perf_session + __maybe_unused) { dump_printf(": unhandled!\n"); return 0; } -static int process_finished_round(event_t *event, - struct perf_session *session, - struct perf_event_ops *ops); - -static void perf_event_ops__fill_defaults(struct perf_event_ops *handler) -{ - if (handler->sample == NULL) - handler->sample = process_event_stub; - if (handler->mmap == NULL) - handler->mmap = process_event_stub; - if (handler->comm == NULL) - handler->comm = process_event_stub; - if (handler->fork == NULL) - handler->fork = process_event_stub; - if (handler->exit == NULL) - handler->exit = process_event_stub; - if (handler->lost == NULL) - handler->lost = process_event_stub; - if (handler->read == NULL) - handler->read = process_event_stub; - if (handler->throttle == NULL) - handler->throttle = process_event_stub; - if (handler->unthrottle == NULL) - handler->unthrottle = process_event_stub; - if (handler->attr == NULL) - handler->attr = process_event_stub; - if (handler->event_type == NULL) - handler->event_type = process_event_stub; - if (handler->tracing_data == NULL) - handler->tracing_data = process_event_stub; - if (handler->build_id == NULL) - handler->build_id = process_event_stub; - if (handler->finished_round == NULL) { - if (handler->ordered_samples) - handler->finished_round = process_finished_round; +static int process_finished_round(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session); + +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) + tool->fork = process_event_stub; + if (tool->exit == NULL) + tool->exit = process_event_stub; + if (tool->lost == NULL) + tool->lost = perf_event__process_lost; + if (tool->read == NULL) + tool->read = process_event_sample_stub; + if (tool->throttle == NULL) + tool->throttle = process_event_stub; + if (tool->unthrottle == NULL) + tool->unthrottle = process_event_stub; + if (tool->attr == NULL) + tool->attr = process_event_synth_attr_stub; + if (tool->tracing_data == NULL) + tool->tracing_data = process_event_synth_tracing_data_stub; + if (tool->build_id == NULL) + tool->build_id = process_finished_round_stub; + if (tool->finished_round == NULL) { + if (tool->ordered_samples) + tool->finished_round = process_finished_round; else - handler->finished_round = process_finished_round_stub; + tool->finished_round = process_finished_round_stub; } } + +static void swap_sample_id_all(union perf_event *event, void *data) +{ + void *end = (void *) event + event->header.size; + int size = end - data; + + BUG_ON(size % sizeof(u64)); + mem_bswap_64(data, size); +} -void mem_bswap_64(void *src, int byte_size) +static void perf_event__all64_swap(union perf_event *event, + bool sample_id_all __maybe_unused) { - u64 *m = src; + struct perf_event_header *hdr = &event->header; + mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr)); +} + +static void perf_event__comm_swap(union perf_event *event, bool sample_id_all) +{ + event->comm.pid = bswap_32(event->comm.pid); + event->comm.tid = bswap_32(event->comm.tid); - while (byte_size > 0) { - *m = bswap_64(*m); - byte_size -= sizeof(u64); - ++m; + if (sample_id_all) { + void *data = &event->comm.comm; + + data += PERF_ALIGN(strlen(data) + 1, sizeof(u64)); + swap_sample_id_all(event, data); } } -static void event__all64_swap(event_t *self) +static void perf_event__mmap_swap(union perf_event *event, + bool sample_id_all) { - struct perf_event_header *hdr = &self->header; - mem_bswap_64(hdr + 1, self->header.size - sizeof(*hdr)); + event->mmap.pid = bswap_32(event->mmap.pid); + event->mmap.tid = bswap_32(event->mmap.tid); + event->mmap.start = bswap_64(event->mmap.start); + event->mmap.len = bswap_64(event->mmap.len); + event->mmap.pgoff = bswap_64(event->mmap.pgoff); + + if (sample_id_all) { + void *data = &event->mmap.filename; + + data += PERF_ALIGN(strlen(data) + 1, sizeof(u64)); + swap_sample_id_all(event, data); + } } -static void event__comm_swap(event_t *self) +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) { - self->comm.pid = bswap_32(self->comm.pid); - self->comm.tid = bswap_32(self->comm.tid); + event->fork.pid = bswap_32(event->fork.pid); + event->fork.tid = bswap_32(event->fork.tid); + event->fork.ppid = bswap_32(event->fork.ppid); + event->fork.ptid = bswap_32(event->fork.ptid); + event->fork.time = bswap_64(event->fork.time); + + if (sample_id_all) + swap_sample_id_all(event, &event->fork + 1); } -static void event__mmap_swap(event_t *self) +static void perf_event__read_swap(union perf_event *event, bool sample_id_all) { - self->mmap.pid = bswap_32(self->mmap.pid); - self->mmap.tid = bswap_32(self->mmap.tid); - self->mmap.start = bswap_64(self->mmap.start); - self->mmap.len = bswap_64(self->mmap.len); - self->mmap.pgoff = bswap_64(self->mmap.pgoff); + event->read.pid = bswap_32(event->read.pid); + event->read.tid = bswap_32(event->read.tid); + event->read.value = bswap_64(event->read.value); + event->read.time_enabled = bswap_64(event->read.time_enabled); + event->read.time_running = bswap_64(event->read.time_running); + event->read.id = bswap_64(event->read.id); + + if (sample_id_all) + swap_sample_id_all(event, &event->read + 1); } -static void event__task_swap(event_t *self) +static void perf_event__throttle_swap(union perf_event *event, + bool sample_id_all) { - self->fork.pid = bswap_32(self->fork.pid); - self->fork.tid = bswap_32(self->fork.tid); - self->fork.ppid = bswap_32(self->fork.ppid); - self->fork.ptid = bswap_32(self->fork.ptid); - self->fork.time = bswap_64(self->fork.time); + 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 void event__read_swap(event_t *self) +static u8 revbyte(u8 b) { - self->read.pid = bswap_32(self->read.pid); - self->read.tid = bswap_32(self->read.tid); - self->read.value = bswap_64(self->read.value); - self->read.time_enabled = bswap_64(self->read.time_enabled); - self->read.time_running = bswap_64(self->read.time_running); - self->read.id = bswap_64(self->read.id); + int rev = (b >> 4) | ((b & 0xf) << 4); + rev = ((rev & 0xcc) >> 2) | ((rev & 0x33) << 2); + rev = ((rev & 0xaa) >> 1) | ((rev & 0x55) << 1); + return (u8) rev; } -static void event__attr_swap(event_t *self) +/* + * XXX this is hack in attempt to carry flags bitfield + * throught endian village. ABI says: + * + * Bit-fields are allocated from right to left (least to most significant) + * on little-endian implementations and from left to right (most to least + * significant) on big-endian implementations. + * + * The above seems to be byte specific, so we need to reverse each + * byte of the bitfield. 'Internet' also says this might be implementation + * specific and we probably need proper fix and carry perf_event_attr + * bitfield flags in separate data file FEAT_ section. Thought this seems + * to work for now. + */ +static void swap_bitfield(u8 *p, unsigned len) { - size_t size; + unsigned i; - self->attr.attr.type = bswap_32(self->attr.attr.type); - self->attr.attr.size = bswap_32(self->attr.attr.size); - self->attr.attr.config = bswap_64(self->attr.attr.config); - self->attr.attr.sample_period = bswap_64(self->attr.attr.sample_period); - self->attr.attr.sample_type = bswap_64(self->attr.attr.sample_type); - self->attr.attr.read_format = bswap_64(self->attr.attr.read_format); - self->attr.attr.wakeup_events = bswap_32(self->attr.attr.wakeup_events); - self->attr.attr.bp_type = bswap_32(self->attr.attr.bp_type); - self->attr.attr.bp_addr = bswap_64(self->attr.attr.bp_addr); - self->attr.attr.bp_len = bswap_64(self->attr.attr.bp_len); + for (i = 0; i < len; i++) { + *p = revbyte(*p); + p++; + } +} - size = self->header.size; - size -= (void *)&self->attr.id - (void *)self; - mem_bswap_64(self->attr.id, size); +/* exported for swapping attributes in file header */ +void perf_event__attr_swap(struct perf_event_attr *attr) +{ + attr->type = bswap_32(attr->type); + attr->size = bswap_32(attr->size); + attr->config = bswap_64(attr->config); + attr->sample_period = bswap_64(attr->sample_period); + attr->sample_type = bswap_64(attr->sample_type); + attr->read_format = bswap_64(attr->read_format); + attr->wakeup_events = bswap_32(attr->wakeup_events); + 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)); } -static void event__event_type_swap(event_t *self) +static void perf_event__hdr_attr_swap(union perf_event *event, + bool sample_id_all __maybe_unused) { - self->event_type.event_type.event_id = - bswap_64(self->event_type.event_type.event_id); + size_t size; + + perf_event__attr_swap(&event->attr.attr); + + size = event->header.size; + size -= (void *)&event->attr.id - (void *)event; + mem_bswap_64(event->attr.id, size); } -static void event__tracing_data_swap(event_t *self) +static void perf_event__event_type_swap(union perf_event *event, + bool sample_id_all __maybe_unused) { - self->tracing_data.size = bswap_32(self->tracing_data.size); + event->event_type.event_type.event_id = + bswap_64(event->event_type.event_type.event_id); } -typedef void (*event__swap_op)(event_t *self); +static void perf_event__tracing_data_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + event->tracing_data.size = bswap_32(event->tracing_data.size); +} -static event__swap_op event__swap_ops[] = { - [PERF_RECORD_MMAP] = event__mmap_swap, - [PERF_RECORD_COMM] = event__comm_swap, - [PERF_RECORD_FORK] = event__task_swap, - [PERF_RECORD_EXIT] = event__task_swap, - [PERF_RECORD_LOST] = event__all64_swap, - [PERF_RECORD_READ] = event__read_swap, - [PERF_RECORD_SAMPLE] = event__all64_swap, - [PERF_RECORD_HEADER_ATTR] = event__attr_swap, - [PERF_RECORD_HEADER_EVENT_TYPE] = event__event_type_swap, - [PERF_RECORD_HEADER_TRACING_DATA] = event__tracing_data_swap, - [PERF_RECORD_HEADER_BUILD_ID] = NULL, - [PERF_RECORD_HEADER_MAX] = NULL, +typedef void (*perf_event__swap_op)(union perf_event *event, + bool sample_id_all); + +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, + [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap, + [PERF_RECORD_HEADER_BUILD_ID] = NULL, + [PERF_RECORD_HEADER_MAX] = NULL, }; struct sample_queue { u64 timestamp; - struct sample_event *event; + u64 file_offset; + union perf_event *event; struct list_head list; }; -static void flush_sample_queue(struct perf_session *s, - struct perf_event_ops *ops) +static void perf_session_free_sample_buffers(struct perf_session *session) +{ + struct ordered_samples *os = &session->ordered_samples; + + while (!list_empty(&os->to_free)) { + struct sample_queue *sq; + + sq = list_entry(os->to_free.next, struct sample_queue, list); + list_del(&sq->list); + free(sq); + } +} + +static int perf_session_deliver_event(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, + u64 file_offset); + +static int flush_sample_queue(struct perf_session *s, + struct perf_tool *tool) { - struct list_head *head = &s->ordered_samples.samples_head; - u64 limit = s->ordered_samples.next_flush; + struct ordered_samples *os = &s->ordered_samples; + struct list_head *head = &os->samples; struct sample_queue *tmp, *iter; + struct perf_sample sample; + u64 limit = os->next_flush; + u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL; + bool show_progress = limit == ULLONG_MAX; + struct ui_progress prog; + int ret; + + if (!tool->ordered_samples || !limit) + return 0; - if (!ops->ordered_samples || !limit) - return; + 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) - return; + break; + + ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample); + if (ret) + pr_err("Can't parse sample, err = %d\n", ret); + else { + ret = perf_session_deliver_event(s, iter->event, &sample, tool, + iter->file_offset); + if (ret) + return ret; + } - if (iter == s->ordered_samples.last_inserted) - s->ordered_samples.last_inserted = NULL; + os->last_flush = iter->timestamp; + list_del(&iter->list); + list_add(&iter->list, &os->sample_cache); - ops->sample((event_t *)iter->event, s); + if (show_progress) + ui_progress__update(&prog, 1); + } - s->ordered_samples.last_flush = iter->timestamp; - list_del(&iter->list); - free(iter->event); - free(iter); + if (list_empty(head)) { + os->last_sample = NULL; + } else if (last_ts <= limit) { + os->last_sample = + list_entry(head->prev, struct sample_queue, list); } + + os->nr_samples = 0; + + return 0; } /* @@ -455,200 +567,530 @@ static void flush_sample_queue(struct perf_session *s, * Flush every events below timestamp 7 * etc... */ -static int process_finished_round(event_t *event __used, - struct perf_session *session, - struct perf_event_ops *ops) +static int process_finished_round(struct perf_tool *tool, + union perf_event *event __maybe_unused, + struct perf_session *session) { - flush_sample_queue(session, ops); - session->ordered_samples.next_flush = session->ordered_samples.max_timestamp; + int ret = flush_sample_queue(session, tool); + if (!ret) + session->ordered_samples.next_flush = session->ordered_samples.max_timestamp; - return 0; + return ret; } -static void __queue_sample_end(struct sample_queue *new, struct list_head *head) +/* The queue is ordered by time */ +static void __queue_event(struct sample_queue *new, struct perf_session *s) { - struct sample_queue *iter; + struct ordered_samples *os = &s->ordered_samples; + struct sample_queue *sample = os->last_sample; + u64 timestamp = new->timestamp; + struct list_head *p; - list_for_each_entry_reverse(iter, head, list) { - if (iter->timestamp < new->timestamp) { - list_add(&new->list, &iter->list); - return; - } + ++os->nr_samples; + os->last_sample = new; + + if (!sample) { + list_add(&new->list, &os->samples); + os->max_timestamp = timestamp; + return; } - list_add(&new->list, head); + /* + * last_sample might point to some random place in the list as it's + * the last queued event. We expect that the new event is close to + * this. + */ + if (sample->timestamp <= timestamp) { + while (sample->timestamp <= timestamp) { + p = sample->list.next; + if (p == &os->samples) { + list_add_tail(&new->list, &os->samples); + os->max_timestamp = timestamp; + return; + } + sample = list_entry(p, struct sample_queue, list); + } + list_add_tail(&new->list, &sample->list); + } else { + while (sample->timestamp > timestamp) { + p = sample->list.prev; + if (p == &os->samples) { + list_add(&new->list, &os->samples); + return; + } + sample = list_entry(p, struct sample_queue, list); + } + list_add(&new->list, &sample->list); + } } -static void __queue_sample_before(struct sample_queue *new, - struct sample_queue *iter, - struct list_head *head) +#define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct sample_queue)) + +int perf_session_queue_event(struct perf_session *s, union perf_event *event, + struct perf_sample *sample, u64 file_offset) { - list_for_each_entry_continue_reverse(iter, head, list) { - if (iter->timestamp < new->timestamp) { - list_add(&new->list, &iter->list); - return; - } + struct ordered_samples *os = &s->ordered_samples; + struct list_head *sc = &os->sample_cache; + u64 timestamp = sample->time; + struct sample_queue *new; + + if (!timestamp || timestamp == ~0ULL) + return -ETIME; + + if (timestamp < s->ordered_samples.last_flush) { + printf("Warning: Timestamp below last timeslice flush\n"); + return -EINVAL; + } + + if (!list_empty(sc)) { + new = list_entry(sc->next, struct sample_queue, list); + list_del(&new->list); + } else if (os->sample_buffer) { + new = os->sample_buffer + os->sample_buffer_idx; + if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER) + os->sample_buffer = NULL; + } else { + os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new)); + if (!os->sample_buffer) + return -ENOMEM; + list_add(&os->sample_buffer->list, &os->to_free); + os->sample_buffer_idx = 2; + new = os->sample_buffer + 1; } - list_add(&new->list, head); + new->timestamp = timestamp; + new->file_offset = file_offset; + new->event = event; + + __queue_event(new, s); + + return 0; } -static void __queue_sample_after(struct sample_queue *new, - struct sample_queue *iter, - struct list_head *head) +static void callchain__printf(struct perf_sample *sample) { - list_for_each_entry_continue(iter, head, list) { - if (iter->timestamp > new->timestamp) { - list_add_tail(&new->list, &iter->list); - return; - } + unsigned int i; + + printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr); + + for (i = 0; i < sample->callchain->nr; i++) + printf("..... %2d: %016" PRIx64 "\n", + i, sample->callchain->ips[i]); +} + +static void branch_stack__printf(struct perf_sample *sample) +{ + uint64_t i; + + printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr); + + for (i = 0; i < sample->branch_stack->nr; i++) + printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n", + i, sample->branch_stack->entries[i].from, + sample->branch_stack->entries[i].to); +} + +static void regs_dump__printf(u64 mask, u64 *regs) +{ + unsigned rid, i = 0; + + for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) { + u64 val = regs[i++]; + + printf(".... %-5s 0x%" PRIx64 "\n", + perf_reg_name(rid), val); } - list_add_tail(&new->list, head); } -/* The queue is ordered by time */ -static void __queue_sample_event(struct sample_queue *new, - struct perf_session *s) +static void regs_user__printf(struct perf_sample *sample) +{ + struct regs_dump *user_regs = &sample->user_regs; + + if (user_regs->regs) { + u64 mask = user_regs->mask; + printf("... user regs: mask 0x%" PRIx64 "\n", mask); + regs_dump__printf(mask, user_regs->regs); + } +} + +static void stack_user__printf(struct stack_dump *dump) { - struct sample_queue *last_inserted = s->ordered_samples.last_inserted; - struct list_head *head = &s->ordered_samples.samples_head; + printf("... ustack: size %" PRIu64 ", offset 0x%x\n", + dump->size, dump->offset); +} +static void perf_session__print_tstamp(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample) +{ + u64 sample_type = __perf_evlist__combined_sample_type(session->evlist); - if (!last_inserted) { - __queue_sample_end(new, head); + if (event->header.type != PERF_RECORD_SAMPLE && + !perf_evlist__sample_id_all(session->evlist)) { + fputs("-1 -1 ", stdout); return; } - /* - * Most of the time the current event has a timestamp - * very close to the last event inserted, unless we just switched - * to another event buffer. Having a sorting based on a list and - * on the last inserted event that is close to the current one is - * probably more efficient than an rbtree based sorting. - */ - if (last_inserted->timestamp >= new->timestamp) - __queue_sample_before(new, last_inserted, head); - else - __queue_sample_after(new, last_inserted, head); + if ((sample_type & PERF_SAMPLE_CPU)) + printf("%u ", sample->cpu); + + if (sample_type & PERF_SAMPLE_TIME) + printf("%" PRIu64 " ", sample->time); } -static int queue_sample_event(event_t *event, struct sample_data *data, - struct perf_session *s) +static void sample_read__printf(struct perf_sample *sample, u64 read_format) { - u64 timestamp = data->time; - struct sample_queue *new; + printf("... sample_read:\n"); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + printf("...... time enabled %016" PRIx64 "\n", + sample->read.time_enabled); - if (timestamp < s->ordered_samples.last_flush) { - printf("Warning: Timestamp below last timeslice flush\n"); - return -EINVAL; - } + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + printf("...... time running %016" PRIx64 "\n", + sample->read.time_running); - new = malloc(sizeof(*new)); - if (!new) - return -ENOMEM; + if (read_format & PERF_FORMAT_GROUP) { + u64 i; - new->timestamp = timestamp; + printf(".... group nr %" PRIu64 "\n", sample->read.group.nr); - new->event = malloc(event->header.size); - if (!new->event) { - free(new); - return -ENOMEM; - } + for (i = 0; i < sample->read.group.nr; i++) { + struct sample_read_value *value; - memcpy(new->event, event, event->header.size); + 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); +} - __queue_sample_event(new, s); - s->ordered_samples.last_inserted = new; +static void dump_event(struct perf_session *session, union perf_event *event, + u64 file_offset, struct perf_sample *sample) +{ + if (!dump_trace) + return; - if (new->timestamp > s->ordered_samples.max_timestamp) - s->ordered_samples.max_timestamp = new->timestamp; + printf("\n%#" PRIx64 " [%#x]: event: %d\n", + file_offset, event->header.size, event->header.type); - return 0; + trace_event(event); + + if (sample) + perf_session__print_tstamp(session, event, sample); + + printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset, + event->header.size, perf_event__name(event->header.type)); } -static int perf_session__process_sample(event_t *event, struct perf_session *s, - struct perf_event_ops *ops) +static void dump_sample(struct perf_evsel *evsel, union perf_event *event, + struct perf_sample *sample) { - struct sample_data data; + u64 sample_type; - if (!ops->ordered_samples) - return ops->sample(event, s); + if (!dump_trace) + return; - bzero(&data, sizeof(struct sample_data)); - event__parse_sample(event, s->sample_type, &data); + printf("(IP, 0x%x): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n", + event->header.misc, sample->pid, sample->tid, sample->ip, + sample->period, sample->addr); - queue_sample_event(event, &data, s); + sample_type = evsel->attr.sample_type; - return 0; + if (sample_type & PERF_SAMPLE_CALLCHAIN) + callchain__printf(sample); + + if (sample_type & PERF_SAMPLE_BRANCH_STACK) + branch_stack__printf(sample); + + if (sample_type & PERF_SAMPLE_REGS_USER) + regs_user__printf(sample); + + if (sample_type & PERF_SAMPLE_STACK_USER) + stack_user__printf(&sample->user_stack); + + if (sample_type & PERF_SAMPLE_WEIGHT) + printf("... weight: %" PRIu64 "\n", sample->weight); + + 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 int perf_session__process_event(struct perf_session *self, - event_t *event, - struct perf_event_ops *ops, - u64 offset, u64 head) +static struct machine * + perf_session__find_machine_for_cpumode(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample) { - trace_event(event); + const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct machine *machine; + + if (perf_guest && + ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) || + (cpumode == PERF_RECORD_MISC_GUEST_USER))) { + u32 pid; + + if (event->header.type == PERF_RECORD_MMAP + || event->header.type == PERF_RECORD_MMAP2) + pid = event->mmap.pid; + else + pid = sample->pid; + + machine = perf_session__find_machine(session, pid); + if (!machine) + machine = perf_session__findnew_machine(session, + DEFAULT_GUEST_KERNEL_ID); + return 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; +} - if (event->header.type < PERF_RECORD_HEADER_MAX) { - dump_printf("%#Lx [%#x]: PERF_RECORD_%s", - offset + head, event->header.size, - event__name[event->header.type]); - hists__inc_nr_events(&self->hists, event->header.type); +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, + struct perf_tool *tool, + u64 file_offset) +{ + struct perf_evsel *evsel; + struct machine *machine; + + dump_event(session, event, file_offset, sample); + + evsel = perf_evlist__id2evsel(session->evlist, sample->id); + if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) { + /* + * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here + * because the tools right now may apply filters, discarding + * some of the samples. For consistency, in the future we + * should have something like nr_filtered_samples and remove + * the sample->period from total_sample_period, etc, KISS for + * now tho. + * + * Also testing against NULL allows us to handle files without + * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the + * future probably it'll be a good idea to restrict event + * processing via perf_session to files with both set. + */ + hists__inc_nr_events(&evsel->hists, event->header.type); } - if (self->header.needs_swap && event__swap_ops[event->header.type]) - event__swap_ops[event->header.type](event); + machine = perf_session__find_machine_for_cpumode(session, event, + sample); switch (event->header.type) { case PERF_RECORD_SAMPLE: - return perf_session__process_sample(event, self, ops); + dump_sample(evsel, event, sample); + if (evsel == NULL) { + ++session->stats.nr_unknown_id; + return 0; + } + if (machine == NULL) { + ++session->stats.nr_unprocessable_samples; + return 0; + } + return perf_session__deliver_sample(session, tool, event, + sample, evsel, machine); case PERF_RECORD_MMAP: - return ops->mmap(event, self); + return tool->mmap(tool, event, sample, machine); + case PERF_RECORD_MMAP2: + return tool->mmap2(tool, event, sample, machine); case PERF_RECORD_COMM: - return ops->comm(event, self); + return tool->comm(tool, event, sample, machine); case PERF_RECORD_FORK: - return ops->fork(event, self); + return tool->fork(tool, event, sample, machine); case PERF_RECORD_EXIT: - return ops->exit(event, self); + return tool->exit(tool, event, sample, machine); case PERF_RECORD_LOST: - return ops->lost(event, self); + if (tool->lost == perf_event__process_lost) + session->stats.total_lost += event->lost.lost; + return tool->lost(tool, event, sample, machine); case PERF_RECORD_READ: - return ops->read(event, self); + return tool->read(tool, event, sample, evsel, machine); case PERF_RECORD_THROTTLE: - return ops->throttle(event, self); + return tool->throttle(tool, event, sample, machine); case PERF_RECORD_UNTHROTTLE: - return ops->unthrottle(event, self); + return tool->unthrottle(tool, event, sample, machine); + default: + ++session->stats.nr_unknown_events; + return -1; + } +} + +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); + + /* These events are processed right away */ + switch (event->header.type) { case PERF_RECORD_HEADER_ATTR: - return ops->attr(event, self); + 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 ops->event_type(event, self); + /* + * Depreceated, but we need to handle it for sake + * of old data files create in pipe mode. + */ + return 0; case PERF_RECORD_HEADER_TRACING_DATA: /* setup for reading amidst mmap */ - lseek(self->fd, offset + head, SEEK_SET); - return ops->tracing_data(event, self); + lseek(fd, file_offset, SEEK_SET); + return tool->tracing_data(tool, event, session); case PERF_RECORD_HEADER_BUILD_ID: - return ops->build_id(event, self); + return tool->build_id(tool, event, session); case PERF_RECORD_FINISHED_ROUND: - return ops->finished_round(event, self, ops); + return tool->finished_round(tool, event, session); default: - ++self->hists.stats.nr_unknown_events; - return -1; + return -EINVAL; + } +} + +static void event_swap(union perf_event *event, bool sample_id_all) +{ + perf_event__swap_op swap; + + swap = perf_event__swap_ops[event->header.type]; + if (swap) + swap(event, sample_id_all); +} + +static int perf_session__process_event(struct perf_session *session, + union perf_event *event, + struct perf_tool *tool, + u64 file_offset) +{ + struct perf_sample sample; + int ret; + + if (session->header.needs_swap) + event_swap(event, perf_evlist__sample_id_all(session->evlist)); + + if (event->header.type >= PERF_RECORD_HEADER_MAX) + return -EINVAL; + + events_stats__inc(&session->stats, event->header.type); + + if (event->header.type >= PERF_RECORD_USER_TYPE_START) + return perf_session__process_user_event(session, event, tool, file_offset); + + /* + * For all kernel events we get the sample data + */ + ret = perf_evlist__parse_sample(session->evlist, event, &sample); + if (ret) + return ret; + + if (tool->ordered_samples) { + ret = perf_session_queue_event(session, event, &sample, + file_offset); + if (ret != -ETIME) + return ret; } + + return perf_session_deliver_event(session, event, &sample, tool, + file_offset); +} + +void perf_event_header__bswap(struct perf_event_header *hdr) +{ + hdr->type = bswap_32(hdr->type); + hdr->misc = bswap_16(hdr->misc); + hdr->size = bswap_16(hdr->size); } -void perf_event_header__bswap(struct perf_event_header *self) +struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) { - self->type = bswap_32(self->type); - self->misc = bswap_16(self->misc); - self->size = bswap_16(self->size); + 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; } @@ -656,41 +1098,71 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se return thread; } -int do_read(int fd, void *buf, size_t size) +static void perf_session__warn_about_errors(const struct perf_session *session, + const struct perf_tool *tool) { - void *buf_start = buf; - - while (size) { - int ret = read(fd, buf, size); + if (tool->lost == perf_event__process_lost && + session->stats.nr_events[PERF_RECORD_LOST] != 0) { + ui__warning("Processed %d events and lost %d chunks!\n\n" + "Check IO/CPU overload!\n\n", + session->stats.nr_events[0], + session->stats.nr_events[PERF_RECORD_LOST]); + } - if (ret <= 0) - return ret; + if (session->stats.nr_unknown_events != 0) { + ui__warning("Found %u unknown events!\n\n" + "Is this an older tool processing a perf.data " + "file generated by a more recent tool?\n\n" + "If that is not the case, consider " + "reporting to linux-kernel@vger.kernel.org.\n\n", + session->stats.nr_unknown_events); + } - size -= ret; - buf += ret; + if (session->stats.nr_unknown_id != 0) { + ui__warning("%u samples with id not present in the header\n", + session->stats.nr_unknown_id); } - return buf - buf_start; + if (session->stats.nr_invalid_chains != 0) { + ui__warning("Found invalid callchains!\n\n" + "%u out of %u events were discarded for this reason.\n\n" + "Consider reporting to linux-kernel@vger.kernel.org.\n\n", + session->stats.nr_invalid_chains, + session->stats.nr_events[PERF_RECORD_SAMPLE]); + } + + if (session->stats.nr_unprocessable_samples != 0) { + ui__warning("%u unprocessable samples recorded.\n" + "Do you have a KVM guest running and not using 'perf kvm'?\n", + session->stats.nr_unprocessable_samples); + } } -#define session_done() (*(volatile int *)(&session_done)) volatile int session_done; -static int __perf_session__process_pipe_events(struct perf_session *self, - struct perf_event_ops *ops) +static int __perf_session__process_pipe_events(struct perf_session *session, + struct perf_tool *tool) { - event_t event; - uint32_t size; + int fd = perf_data_file__fd(session->file); + union perf_event *event; + uint32_t size, cur_size = 0; + void *buf = NULL; int skip = 0; u64 head; - int err; + ssize_t err; void *p; - perf_event_ops__fill_defaults(ops); + perf_tool__fill_defaults(tool); head = 0; + cur_size = sizeof(union perf_event); + + buf = malloc(cur_size); + if (!buf) + return -errno; more: - err = do_read(self->fd, &event, sizeof(struct perf_event_header)); + event = buf; + err = readn(fd, event, sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) goto done; @@ -699,19 +1171,30 @@ more: goto out_err; } - if (self->header.needs_swap) - perf_event_header__bswap(&event.header); + if (session->header.needs_swap) + perf_event_header__bswap(&event->header); - size = event.header.size; - if (size == 0) - size = 8; + size = event->header.size; + if (size < sizeof(struct perf_event_header)) { + pr_err("bad event header size\n"); + goto out_err; + } - p = &event; + if (size > cur_size) { + void *new = realloc(buf, size); + if (!new) { + pr_err("failed to allocate memory to read event\n"); + goto out_err; + } + buf = new; + cur_size = size; + event = buf; + } + p = event; p += sizeof(struct perf_event_header); if (size - sizeof(struct perf_event_header)) { - err = do_read(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"); @@ -723,170 +1206,202 @@ more: } } - if (size == 0 || - (skip = perf_session__process_event(self, &event, ops, - 0, head)) < 0) { - dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n", - head, event.header.size, event.header.type); - /* - * assume we lost track of the stream, check alignment, and - * increment a single u64 in the hope to catch on again 'soon'. - */ - if (unlikely(head & 7)) - head &= ~7ULL; - - size = 8; + 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; + goto out_err; } head += size; - dump_printf("\n%#Lx [%#x]: event: %d\n", - head, event.header.size, event.header.type); - if (skip > 0) head += skip; 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(session, tool); + perf_session_free_sample_buffers(session); return err; } -int __perf_session__process_events(struct perf_session *self, +static union perf_event * +fetch_mmaped_event(struct perf_session *session, + u64 head, size_t mmap_size, char *buf) +{ + union perf_event *event; + + /* + * Ensure we have enough space remaining to read + * the size of the event in the headers. + */ + if (head + sizeof(event->header) > mmap_size) + return NULL; + + event = (union perf_event *)(buf + head); + + if (session->header.needs_swap) + perf_event_header__bswap(&event->header); + + 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; +} + +/* + * On 64bit we can mmap the data file in one go. No need for tiny mmap + * slices. On 32bit we use 32MB. + */ +#if BITS_PER_LONG == 64 +#define MMAP_SIZE ULLONG_MAX +#define NUM_MMAPS 1 +#else +#define MMAP_SIZE (32 * 1024 * 1024ULL) +#define NUM_MMAPS 128 +#endif + +int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, - u64 file_size, struct perf_event_ops *ops) + u64 file_size, struct perf_tool *tool) { - int err, mmap_prot, mmap_flags; - u64 head, shift; - u64 offset = 0; - size_t page_size; - event_t *event; + 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; - char *buf; - struct ui_progress *progress = ui_progress__new("Processing events...", - self->size); - if (progress == NULL) - return -1; + struct ui_progress prog; + + perf_tool__fill_defaults(tool); - perf_event_ops__fill_defaults(ops); + page_offset = page_size * (data_offset / page_size); + file_offset = page_offset; + head = data_offset - page_offset; - page_size = sysconf(_SC_PAGESIZE); + if (data_size && (data_offset + data_size < file_size)) + file_size = data_offset + data_size; - head = data_offset; - shift = page_size * (head / page_size); - offset += shift; - head -= shift; + ui_progress__init(&prog, file_size, "Processing events..."); + + mmap_size = MMAP_SIZE; + if (mmap_size > file_size) + mmap_size = file_size; + + memset(mmaps, 0, sizeof(mmaps)); mmap_prot = PROT_READ; mmap_flags = MAP_SHARED; - if (self->header.needs_swap) { + if (session->header.needs_swap) { mmap_prot |= PROT_WRITE; mmap_flags = MAP_PRIVATE; } remap: - buf = mmap(NULL, page_size * self->mmap_window, mmap_prot, - mmap_flags, self->fd, offset); + buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd, + file_offset); if (buf == MAP_FAILED) { pr_err("failed to mmap file\n"); err = -errno; goto out_err; } + mmaps[map_idx] = buf; + map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1); + file_pos = file_offset + head; more: - event = (event_t *)(buf + head); - ui_progress__update(progress, offset); - - if (self->header.needs_swap) - perf_event_header__bswap(&event->header); - size = event->header.size; - if (size == 0) - size = 8; - - if (head + event->header.size >= page_size * self->mmap_window) { - int munmap_ret; - - shift = page_size * (head / page_size); - - munmap_ret = munmap(buf, page_size * self->mmap_window); - assert(munmap_ret == 0); + event = fetch_mmaped_event(session, head, mmap_size, buf); + if (!event) { + if (mmaps[map_idx]) { + munmap(mmaps[map_idx], mmap_size); + mmaps[map_idx] = NULL; + } - offset += shift; - head -= shift; + page_offset = page_size * (head / page_size); + file_offset += page_offset; + head -= page_offset; goto remap; } size = event->header.size; - dump_printf("\n%#Lx [%#x]: event: %d\n", - offset + head, event->header.size, event->header.type); - - if (size == 0 || - perf_session__process_event(self, event, ops, offset, head) < 0) { - dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n", - offset + head, event->header.size, - event->header.type); - /* - * assume we lost track of the stream, check alignment, and - * increment a single u64 in the hope to catch on again 'soon'. - */ - if (unlikely(head & 7)) - head &= ~7ULL; - - size = 8; + 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, + event->header.type); + err = -EINVAL; + goto out_err; } head += size; + file_pos += size; - if (offset + head >= data_offset + data_size) - goto done; + ui_progress__update(&prog, size); + + if (session_done()) + goto out; - if (offset + head < file_size) + if (file_pos < file_size) goto more; -done: - err = 0; + +out: /* do the final flush for ordered samples */ - self->ordered_samples.next_flush = ULLONG_MAX; - flush_sample_queue(self, ops); + session->ordered_samples.next_flush = ULLONG_MAX; + err = flush_sample_queue(session, tool); out_err: - ui_progress__delete(progress); + ui_progress__finish(); + perf_session__warn_about_errors(session, tool); + perf_session_free_sample_buffers(session); return err; } -int perf_session__process_events(struct perf_session *self, - struct perf_event_ops *ops) +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, ops); + 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, ops); + err = __perf_session__process_pipe_events(session, tool); return err; } -bool perf_session__has_traces(struct perf_session *self, const char *msg) +bool perf_session__has_traces(struct perf_session *session, const char *msg) { - if (!(self->sample_type & PERF_SAMPLE_RAW)) { - pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg); - return false; + struct perf_evsel *evsel; + + evlist__for_each(session->evlist, evsel) { + 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 perf_session__set_kallsyms_ref_reloc_sym(struct map **maps, - const char *symbol_name, - u64 addr) +int maps__set_kallsyms_ref_reloc_sym(struct map **maps, + const char *symbol_name, u64 addr) { char *bracket; enum map_type i; @@ -916,16 +1431,243 @@ int perf_session__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(&session->machines, 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(&session->machines, fp, skip, parm); +} + +size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) +{ + struct perf_evsel *pos; + size_t ret = fprintf(fp, "Aggregated stats:\n"); + + ret += events_stats__fprintf(&session->stats, fp); + + evlist__for_each(session->evlist, pos) { + ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); + ret += events_stats__fprintf(&pos->hists.stats, fp); + } + + return ret; +} + +size_t perf_session__fprintf(struct perf_session *session, FILE *fp) +{ + /* + * FIXME: Here we have to actually print all the machines in this + * session, not just the host... + */ + return machine__fprintf(&session->machines.host, fp); +} + +struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, + unsigned int type) +{ + struct perf_evsel *pos; + + evlist__for_each(session->evlist, pos) { + if (pos->attr.type == type) + return pos; + } + return NULL; +} + +void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample, + struct addr_location *al, + unsigned int print_opts, unsigned int stack_depth) +{ + struct callchain_cursor_node *node; + 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; + int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE; + char s = print_oneline ? ' ' : '\t'; + + if (symbol_conf.use_callchain && sample->callchain) { + struct addr_location node_al; + + if (machine__resolve_callchain(al->machine, evsel, al->thread, + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { + if (verbose) + error("Failed to resolve callchain. Skipping\n"); + return; + } + callchain_cursor_commit(&callchain_cursor); + + if (print_symoffset) + node_al = *al; + + while (stack_depth) { + u64 addr = 0; + + node = callchain_cursor_current(&callchain_cursor); + if (!node) + break; + + if (node->sym && node->sym->ignore) + goto next; + + if (print_ip) + printf("%c%16" PRIx64, s, node->ip); + + if (node->map) + addr = node->map->map_ip(node->map, node->ip); + + if (print_sym) { + printf(" "); + if (print_symoffset) { + node_al.addr = addr; + node_al.map = node->map; + symbol__fprintf_symname_offs(node->sym, &node_al, stdout); + } else + symbol__fprintf_symname(node->sym, stdout); + } + + if (print_dso) { + printf(" ("); + map__fprintf_dsoname(node->map, stdout); + printf(")"); + } + + if (print_srcline) + map__fprintf_srcline(node->map, addr, "\n ", + stdout); + + if (!print_oneline) + printf("\n"); + + stack_depth--; +next: + callchain_cursor_advance(&callchain_cursor); + } + + } else { + if (al->sym && al->sym->ignore) + return; + + if (print_ip) + printf("%16" PRIx64, sample->ip); + + if (print_sym) { + printf(" "); + if (print_symoffset) + symbol__fprintf_symname_offs(al->sym, al, + stdout); + else + symbol__fprintf_symname(al->sym, stdout); + } + + if (print_dso) { + printf(" ("); + map__fprintf_dsoname(al->map, stdout); + printf(")"); + } + + if (print_srcline) + map__fprintf_srcline(al->map, al->addr, "\n ", stdout); + } +} + +int perf_session__cpu_bitmap(struct perf_session *session, + const char *cpu_list, unsigned long *cpu_bitmap) { - return __dsos__fprintf(&self->host_machine.kernel_dsos, fp) + - __dsos__fprintf(&self->host_machine.user_dsos, fp) + - machines__fprintf_dsos(&self->machines, fp); + int i, err = -1; + struct cpu_map *map; + + for (i = 0; i < PERF_TYPE_MAX; ++i) { + struct perf_evsel *evsel; + + evsel = perf_session__find_first_evtype(session, i); + if (!evsel) + continue; + + if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) { + pr_err("File does not contain CPU events. " + "Remove -c option to proceed.\n"); + return -1; + } + } + + map = cpu_map__new(cpu_list); + if (map == NULL) { + pr_err("Invalid cpu_list\n"); + return -1; + } + + for (i = 0; i < map->nr; i++) { + int cpu = map->map[i]; + + if (cpu >= MAX_NR_CPUS) { + pr_err("Requested CPU %d too large. " + "Consider raising MAX_NR_CPUS\n", cpu); + goto out_delete_map; + } + + set_bit(cpu, cpu_bitmap); + } + + err = 0; + +out_delete_map: + cpu_map__delete(map); + return err; } -size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp, - bool with_hits) +void perf_session__fprintf_info(struct perf_session *session, FILE *fp, + bool full) { - size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits); - return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits); + struct stat st; + int fd, ret; + + if (session == NULL || fp == NULL) + return; + + fd = perf_data_file__fd(session->file); + + ret = fstat(fd, &st); + if (ret == -1) + return; + + fprintf(fp, "# ========\n"); + fprintf(fp, "# captured on: %s", ctime(&st.st_ctime)); + perf_header__fprintf_info(session, fp, full); + fprintf(fp, "# ========\n#\n"); +} + + +int __perf_session__set_tracepoints_handlers(struct perf_session *session, + const struct perf_evsel_str_handler *assocs, + size_t nr_assocs) +{ + struct perf_evsel *evsel; + size_t i; + int err; + + for (i = 0; i < nr_assocs; i++) { + /* + * 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) + continue; + + err = -EEXIST; + if (evsel->handler != NULL) + goto out; + evsel->handler = assocs[i].handler; + } + + err = 0; +out: + return err; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 9fa0fc2a863..3140f8ae614 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -1,13 +1,16 @@ #ifndef __PERF_SESSION_H #define __PERF_SESSION_H +#include "trace-event.h" #include "hist.h" #include "event.h" #include "header.h" +#include "machine.h" #include "symbol.h" #include "thread.h" +#include "data.h" #include <linux/rbtree.h> -#include "../../../include/linux/perf_event.h" +#include <linux/perf_event.h> struct sample_queue; struct ip_callchain; @@ -17,129 +20,110 @@ struct ordered_samples { u64 last_flush; u64 next_flush; u64 max_timestamp; - struct list_head samples_head; - struct sample_queue *last_inserted; + struct list_head samples; + struct list_head sample_cache; + struct list_head to_free; + struct sample_queue *sample_buffer; + struct sample_queue *last_sample; + int sample_buffer_idx; + unsigned int nr_samples; }; struct perf_session { struct perf_header header; - unsigned long size; - unsigned long mmap_window; - struct rb_root threads; - struct list_head dead_threads; - struct thread *last_match; - struct machine host_machine; - struct rb_root machines; - struct rb_root hists_tree; - /* - * FIXME: should point to the first entry in hists_tree and - * be a hists instance. Right now its only 'report' - * that is using ->hists_tree while all the rest use - * ->hists. - */ - struct hists hists; - u64 sample_type; - int fd; - bool fd_pipe; + struct machines machines; + struct perf_evlist *evlist; + struct trace_event tevent; + struct events_stats stats; bool repipe; - int cwdlen; - char *cwd; struct ordered_samples ordered_samples; - char filename[0]; + struct perf_data_file *file; }; -struct perf_event_ops; - -typedef int (*event_op)(event_t *self, struct perf_session *session); -typedef int (*event_op2)(event_t *self, struct perf_session *session, - struct perf_event_ops *ops); - -struct perf_event_ops { - event_op sample, - mmap, - comm, - fork, - exit, - lost, - read, - throttle, - unthrottle, - attr, - event_type, - tracing_data, - build_id; - event_op2 finished_round; - bool ordered_samples; -}; +#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) +#define PRINT_IP_OPT_SRCLINE (1<<5) + +struct perf_tool; -struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe); -void perf_session__delete(struct perf_session *self); +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_event_ops *ops); -int perf_session__process_events(struct perf_session *self, - struct perf_event_ops *event_ops); + struct perf_tool *tool); +int perf_session__process_events(struct perf_session *session, + struct perf_tool *tool); -struct map_symbol *perf_session__resolve_callchain(struct perf_session *self, - struct thread *thread, - struct ip_callchain *chain, - struct symbol **parent); +int perf_session_queue_event(struct perf_session *s, union perf_event *event, + struct perf_sample *sample, u64 file_offset); -bool perf_session__has_traces(struct perf_session *self, const char *msg); +void perf_tool__fill_defaults(struct perf_tool *tool); -int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps, - const char *symbol_name, - u64 addr); +int perf_session__resolve_callchain(struct perf_session *session, + struct perf_evsel *evsel, + struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent); -void mem_bswap_64(void *src, int byte_size); +bool perf_session__has_traces(struct perf_session *session, const char *msg); -int perf_session__create_kernel_maps(struct perf_session *self); +void perf_event__attr_swap(struct perf_event_attr *attr); -int do_read(int fd, void *buf, size_t size); -void perf_session__update_sample_type(struct perf_session *self); -void perf_session__remove_thread(struct perf_session *self, struct thread *th); +int perf_session__create_kernel_maps(struct perf_session *session); -static inline -struct machine *perf_session__find_host_machine(struct perf_session *self) -{ - return &self->host_machine; -} +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) { - if (pid == HOST_KERNEL_ID) - return &self->host_machine; - 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) { - if (pid == HOST_KERNEL_ID) - return &self->host_machine; - return machines__findnew(&self->machines, pid); + return machines__findnew(&session->machines, pid); } -static inline -void perf_session__process_machines(struct perf_session *self, - machine__process_t process) -{ - process(&self->host_machine, self); - return machines__process(&self->machines, process, self); -} +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 *self, - FILE *fp, bool with_hits); +size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp, + bool (fn)(struct dso *dso, int parm), int parm); -static inline -size_t perf_session__fprintf_nr_events(struct perf_session *self, FILE *fp) -{ - return hists__fprintf_nr_events(&self->hists, fp); -} +size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); + +struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, + unsigned int type); + +void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample, + struct addr_location *al, + 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); + +void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full); + +struct perf_evsel_str_handler; + +int __perf_session__set_tracepoints_handlers(struct perf_session *session, + const struct perf_evsel_str_handler *assocs, + size_t nr_assocs); + +#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/setup.py b/tools/perf/util/setup.py new file mode 100644 index 00000000000..d0aee4b9dfd --- /dev/null +++ b/tools/perf/util/setup.py @@ -0,0 +1,48 @@ +#!/usr/bin/python2 + +from distutils.core import setup, Extension +from os import getenv + +from distutils.command.build_ext import build_ext as _build_ext +from distutils.command.install_lib import install_lib as _install_lib + +class build_ext(_build_ext): + def finalize_options(self): + _build_ext.finalize_options(self) + self.build_lib = build_lib + self.build_temp = build_tmp + +class install_lib(_install_lib): + def finalize_options(self): + _install_lib.finalize_options(self) + self.build_dir = build_lib + + +cflags = getenv('CFLAGS', '').split() +# switch off several checks (need to be at the end of cflags list) +cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ] + +build_lib = getenv('PYTHON_EXTBUILD_LIB') +build_tmp = getenv('PYTHON_EXTBUILD_TMP') +libtraceevent = getenv('LIBTRACEEVENT') +libapikfs = getenv('LIBAPIKFS') + +ext_sources = [f.strip() for f in file('util/python-ext-sources') + if len(f.strip()) > 0 and f[0] != '#'] + +perf = Extension('perf', + sources = ext_sources, + include_dirs = ['util/include'], + extra_compile_args = cflags, + extra_objects = [libtraceevent, libapikfs], + ) + +setup(name='perf', + version='0.1', + description='Interface with the Linux profiling infrastructure', + author='Arnaldo Carvalho de Melo', + author_email='acme@redhat.com', + license='GPLv2', + url='http://perf.wiki.kernel.org', + ext_modules=[perf], + cmdclass={'build_ext': build_ext, 'install_lib': install_lib}) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index b62a553cc67..1ec57dd8228 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,32 +1,78 @@ +#include <sys/mman.h> #include "sort.h" #include "hist.h" +#include "comm.h" +#include "symbol.h" +#include "evsel.h" regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; const char default_sort_order[] = "comm,dso,symbol"; -const char *sort_order = default_sort_order; +const char default_branch_sort_order[] = "comm,dso_from,symbol_from,dso_to,symbol_to"; +const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; +const char default_top_sort_order[] = "dso,symbol"; +const char default_diff_sort_order[] = "dso,symbol"; +const char *sort_order; +const char *field_order; +regex_t ignore_callees_regex; +int have_ignore_callees = 0; int sort__need_collapse = 0; int sort__has_parent = 0; +int sort__has_sym = 0; +int sort__has_dso = 0; +enum sort_mode sort__mode = SORT_MODE__NORMAL; -enum sort_type sort__first_dimension; -char * field_sep; +static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) +{ + int n; + va_list ap; -LIST_HEAD(hist_entry__sort_list); + va_start(ap, fmt); + n = vsnprintf(bf, size, fmt, ap); + if (symbol_conf.field_sep && n > 0) { + char *sep = bf; -static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width); -static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width); -static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width); -static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width); -static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width); -static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width); + while (1) { + sep = strchr(sep, *symbol_conf.field_sep); + if (sep == NULL) + break; + *sep = '.'; + } + } + va_end(ap); + + if (n >= (int)size) + return size - 1; + return n; +} + +static int64_t cmp_null(const void *l, const void *r) +{ + if (!l && !r) + return 0; + else if (!l) + return -1; + else + return 1; +} + +/* --sort pid */ + +static int64_t +sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->tid - left->thread->tid; +} + +static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + const char *comm = thread__comm_str(he->thread); + return repsep_snprintf(bf, size, "%*s:%5d", width - 6, + comm ?: "", he->thread->tid); +} struct sort_entry sort_thread = { .se_header = "Command: Pid", @@ -35,14 +81,89 @@ struct sort_entry sort_thread = { .se_width_idx = HISTC_THREAD, }; +/* --sort comm */ + +static int64_t +sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) +{ + /* 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) +{ + /* Compare the addr that should be unique among comm */ + return comm__str(right->comm) - comm__str(left->comm); +} + +static int64_t +sort__comm_sort(struct hist_entry *left, struct hist_entry *right) +{ + return strcmp(comm__str(right->comm), comm__str(left->comm)); +} + +static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm)); +} + struct sort_entry sort_comm = { .se_header = "Command", .se_cmp = sort__comm_cmp, .se_collapse = sort__comm_collapse, + .se_sort = sort__comm_sort, .se_snprintf = hist_entry__comm_snprintf, .se_width_idx = HISTC_COMM, }; +/* --sort dso */ + +static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) +{ + struct dso *dso_l = map_l ? map_l->dso : NULL; + struct dso *dso_r = map_r ? map_r->dso : NULL; + const char *dso_name_l, *dso_name_r; + + if (!dso_l || !dso_r) + return cmp_null(dso_r, dso_l); + + if (verbose) { + dso_name_l = dso_l->long_name; + dso_name_r = dso_r->long_name; + } else { + dso_name_l = dso_l->short_name; + dso_name_r = dso_r->short_name; + } + + return strcmp(dso_name_l, dso_name_r); +} + +static int64_t +sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return _sort__dso_cmp(right->ms.map, left->ms.map); +} + +static int _hist_entry__dso_snprintf(struct map *map, char *bf, + size_t size, unsigned int width) +{ + if (map && map->dso) { + const char *dso_name = !verbose ? map->dso->short_name : + map->dso->long_name; + return repsep_snprintf(bf, size, "%-*s", width, dso_name); + } + + return repsep_snprintf(bf, size, "%-*s", width, "[unknown]"); +} + +static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__dso_snprintf(he->ms.map, bf, size, width); +} + struct sort_entry sort_dso = { .se_header = "Shared Object", .se_cmp = sort__dso_cmp, @@ -50,20 +171,192 @@ struct sort_entry sort_dso = { .se_width_idx = HISTC_DSO, }; +/* --sort symbol */ + +static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip) +{ + return (int64_t)(right_ip - left_ip); +} + +static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r) +{ + u64 ip_l, ip_r; + + if (!sym_l || !sym_r) + return cmp_null(sym_l, sym_r); + + if (sym_l == sym_r) + return 0; + + ip_l = sym_l->start; + ip_r = sym_r->start; + + return (int64_t)(ip_r - ip_l); +} + +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 _sort__addr_cmp(left->ip, right->ip); + + /* + * comparing symbol address alone is not enough since it's a + * relative address within a dso. + */ + if (!sort__has_dso) { + ret = sort__dso_cmp(left, right); + if (ret != 0) + return ret; + } + + return _sort__sym_cmp(left->ms.sym, right->ms.sym); +} + +static int64_t +sort__sym_sort(struct hist_entry *left, struct hist_entry *right) +{ + if (!left->ms.sym || !right->ms.sym) + return cmp_null(left->ms.sym, right->ms.sym); + + return strcmp(right->ms.sym->name, left->ms.sym->name); +} + +static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, + u64 ip, char level, char *bf, size_t size, + unsigned int width) +{ + size_t ret = 0; + + if (verbose) { + char o = map ? dso__symtab_origin(map->dso) : '!'; + ret += repsep_snprintf(bf, size, "%-#*llx %c ", + BITS_PER_LONG / 4 + 2, ip, o); + } + + ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level); + if (sym && map) { + if (map->type == MAP__VARIABLE) { + ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name); + ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx", + ip - map->unmap_ip(map, sym->start)); + ret += repsep_snprintf(bf + ret, size - ret, "%-*s", + width - ret, ""); + } else { + ret += repsep_snprintf(bf + ret, size - ret, "%-*s", + width - ret, + sym->name); + } + } else { + size_t len = BITS_PER_LONG / 4; + ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", + len, ip); + ret += repsep_snprintf(bf + ret, size - ret, "%-*s", + width - ret, ""); + } + + return ret; +} + +static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__sym_snprintf(he->ms.map, he->ms.sym, he->ip, + he->level, bf, size, width); +} + struct sort_entry sort_sym = { .se_header = "Symbol", .se_cmp = sort__sym_cmp, + .se_sort = sort__sym_sort, .se_snprintf = hist_entry__sym_snprintf, .se_width_idx = HISTC_SYMBOL, }; +/* --sort srcline */ + +static int64_t +sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) +{ + 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(right->srcline, left->srcline); +} + +static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, + size_t size, + unsigned int width __maybe_unused) +{ + return repsep_snprintf(bf, size, "%s", he->srcline); +} + +struct sort_entry sort_srcline = { + .se_header = "Source:Line", + .se_cmp = sort__srcline_cmp, + .se_snprintf = hist_entry__srcline_snprintf, + .se_width_idx = HISTC_SRCLINE, +}; + +/* --sort parent */ + +static int64_t +sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct symbol *sym_l = left->parent; + struct symbol *sym_r = right->parent; + + if (!sym_l || !sym_r) + return cmp_null(sym_l, sym_r); + + return strcmp(sym_r->name, sym_l->name); +} + +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, + he->parent ? he->parent->name : "[other]"); +} + struct sort_entry sort_parent = { .se_header = "Parent symbol", .se_cmp = sort__parent_cmp, .se_snprintf = hist_entry__parent_snprintf, .se_width_idx = HISTC_PARENT, }; - + +/* --sort cpu */ + +static int64_t +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 *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%*d", width, he->cpu); +} + struct sort_entry sort_cpu = { .se_header = "CPU", .se_cmp = sort__cpu_cmp, @@ -71,217 +364,996 @@ struct sort_entry sort_cpu = { .se_width_idx = HISTC_CPU, }; -struct sort_dimension { - const char *name; - struct sort_entry *entry; - int taken; +/* sort keys for branch stacks */ + +static int64_t +sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return _sort__dso_cmp(left->branch_info->from.map, + right->branch_info->from.map); +} + +static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__dso_snprintf(he->branch_info->from.map, + bf, size, width); +} + +static int64_t +sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return _sort__dso_cmp(left->branch_info->to.map, + right->branch_info->to.map); +} + +static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__dso_snprintf(he->branch_info->to.map, + bf, size, width); +} + +static int64_t +sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct addr_map_symbol *from_l = &left->branch_info->from; + struct addr_map_symbol *from_r = &right->branch_info->from; + + if (!from_l->sym && !from_r->sym) + return _sort__addr_cmp(from_l->addr, from_r->addr); + + return _sort__sym_cmp(from_l->sym, from_r->sym); +} + +static int64_t +sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct addr_map_symbol *to_l = &left->branch_info->to; + struct addr_map_symbol *to_r = &right->branch_info->to; + + if (!to_l->sym && !to_r->sym) + return _sort__addr_cmp(to_l->addr, to_r->addr); + + return _sort__sym_cmp(to_l->sym, to_r->sym); +} + +static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + struct addr_map_symbol *from = &he->branch_info->from; + return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, + he->level, bf, size, width); + +} + +static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + struct addr_map_symbol *to = &he->branch_info->to; + return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, + he->level, bf, size, width); + +} + +struct sort_entry sort_dso_from = { + .se_header = "Source Shared Object", + .se_cmp = sort__dso_from_cmp, + .se_snprintf = hist_entry__dso_from_snprintf, + .se_width_idx = HISTC_DSO_FROM, +}; + +struct sort_entry sort_dso_to = { + .se_header = "Target Shared Object", + .se_cmp = sort__dso_to_cmp, + .se_snprintf = hist_entry__dso_to_snprintf, + .se_width_idx = HISTC_DSO_TO, +}; + +struct sort_entry sort_sym_from = { + .se_header = "Source Symbol", + .se_cmp = sort__sym_from_cmp, + .se_snprintf = hist_entry__sym_from_snprintf, + .se_width_idx = HISTC_SYMBOL_FROM, }; -static struct sort_dimension sort_dimensions[] = { - { .name = "pid", .entry = &sort_thread, }, - { .name = "comm", .entry = &sort_comm, }, - { .name = "dso", .entry = &sort_dso, }, - { .name = "symbol", .entry = &sort_sym, }, - { .name = "parent", .entry = &sort_parent, }, - { .name = "cpu", .entry = &sort_cpu, }, +struct sort_entry sort_sym_to = { + .se_header = "Target Symbol", + .se_cmp = sort__sym_to_cmp, + .se_snprintf = hist_entry__sym_to_snprintf, + .se_width_idx = HISTC_SYMBOL_TO, }; -int64_t cmp_null(void *l, void *r) +static int64_t +sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right) { - if (!l && !r) - return 0; - else if (!l) - return -1; + const unsigned char mp = left->branch_info->flags.mispred != + right->branch_info->flags.mispred; + const unsigned char p = left->branch_info->flags.predicted != + right->branch_info->flags.predicted; + + return mp || p; +} + +static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width){ + static const char *out = "N/A"; + + if (he->branch_info->flags.predicted) + out = "N"; + else if (he->branch_info->flags.mispred) + out = "Y"; + + return repsep_snprintf(bf, size, "%-*s", width, out); +} + +/* --sort daddr_sym */ +static int64_t +sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right) +{ + uint64_t l = 0, r = 0; + + if (left->mem_info) + l = left->mem_info->daddr.addr; + if (right->mem_info) + r = right->mem_info->daddr.addr; + + return (int64_t)(r - l); +} + +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 (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, he->level, bf, size, + width); +} + +static int64_t +sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct map *map_l = NULL; + struct map *map_r = NULL; + + if (left->mem_info) + map_l = left->mem_info->daddr.map; + if (right->mem_info) + map_r = right->mem_info->daddr.map; + + return _sort__dso_cmp(map_l, map_r); +} + +static int hist_entry__dso_daddr_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + struct map *map = NULL; + + if (he->mem_info) + map = he->mem_info->daddr.map; + + return _hist_entry__dso_snprintf(map, bf, size, width); +} + +static int64_t +sort__locked_cmp(struct hist_entry *left, struct hist_entry *right) +{ + union perf_mem_data_src data_src_l; + union perf_mem_data_src data_src_r; + + if (left->mem_info) + data_src_l = left->mem_info->data_src; else - return 1; + data_src_l.mem_lock = PERF_MEM_LOCK_NA; + + if (right->mem_info) + data_src_r = right->mem_info->data_src; + else + data_src_r.mem_lock = PERF_MEM_LOCK_NA; + + return (int64_t)(data_src_r.mem_lock - data_src_l.mem_lock); } -/* --sort pid */ +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; -int64_t -sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) + if (he->mem_info) + mask = he->mem_info->data_src.mem_lock; + + if (mask & PERF_MEM_LOCK_NA) + out = "N/A"; + else if (mask & PERF_MEM_LOCK_LOCKED) + out = "Yes"; + else + out = "No"; + + return repsep_snprintf(bf, size, "%-*s", width, out); +} + +static int64_t +sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right) { - return right->thread->pid - left->thread->pid; + union perf_mem_data_src data_src_l; + union perf_mem_data_src data_src_r; + + if (left->mem_info) + data_src_l = left->mem_info->data_src; + else + data_src_l.mem_dtlb = PERF_MEM_TLB_NA; + + if (right->mem_info) + data_src_r = right->mem_info->data_src; + else + data_src_r.mem_dtlb = PERF_MEM_TLB_NA; + + return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb); } -static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) +static const char * const tlb_access[] = { + "N/A", + "HIT", + "MISS", + "L1", + "L2", + "Walker", + "Fault", +}; +#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *)) + +static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) { - int n; - va_list ap; + char out[64]; + size_t sz = sizeof(out) - 1; /* -1 for null termination */ + size_t l = 0, i; + u64 m = PERF_MEM_TLB_NA; + u64 hit, miss; - va_start(ap, fmt); - n = vsnprintf(bf, size, fmt, ap); - if (field_sep && n > 0) { - char *sep = bf; + out[0] = '\0'; - while (1) { - sep = strchr(sep, *field_sep); - if (sep == NULL) - break; - *sep = '.'; + if (he->mem_info) + m = he->mem_info->data_src.mem_dtlb; + + hit = m & PERF_MEM_TLB_HIT; + miss = m & PERF_MEM_TLB_MISS; + + /* already taken care of */ + m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS); + + for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) { + if (!(m & 0x1)) + continue; + if (l) { + strcat(out, " or "); + l += 4; } + strncat(out, tlb_access[i], sz - l); + l += strlen(tlb_access[i]); } - va_end(ap); - return n; + if (*out == '\0') + strcpy(out, "N/A"); + if (hit) + strncat(out, " hit", sz - l); + if (miss) + strncat(out, " miss", sz - l); + + return repsep_snprintf(bf, size, "%-*s", width, out); } -static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width) +static int64_t +sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right) { - return repsep_snprintf(bf, size, "%*s:%5d", width, - self->thread->comm ?: "", self->thread->pid); + union perf_mem_data_src data_src_l; + union perf_mem_data_src data_src_r; + + if (left->mem_info) + data_src_l = left->mem_info->data_src; + else + data_src_l.mem_lvl = PERF_MEM_LVL_NA; + + if (right->mem_info) + data_src_r = right->mem_info->data_src; + else + data_src_r.mem_lvl = PERF_MEM_LVL_NA; + + return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl); } -static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width) +static const char * const mem_lvl[] = { + "N/A", + "HIT", + "MISS", + "L1", + "LFB", + "L2", + "L3", + "Local RAM", + "Remote RAM (1 hop)", + "Remote RAM (2 hops)", + "Remote Cache (1 hop)", + "Remote Cache (2 hops)", + "I/O", + "Uncached", +}; +#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *)) + +static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*s", width, self->thread->comm); + char out[64]; + size_t sz = sizeof(out) - 1; /* -1 for null termination */ + size_t i, l = 0; + u64 m = PERF_MEM_LVL_NA; + u64 hit, miss; + + if (he->mem_info) + m = he->mem_info->data_src.mem_lvl; + + out[0] = '\0'; + + hit = m & PERF_MEM_LVL_HIT; + miss = m & PERF_MEM_LVL_MISS; + + /* already taken care of */ + m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); + + for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) { + if (!(m & 0x1)) + continue; + if (l) { + strcat(out, " or "); + l += 4; + } + strncat(out, mem_lvl[i], sz - l); + l += strlen(mem_lvl[i]); + } + if (*out == '\0') + strcpy(out, "N/A"); + if (hit) + strncat(out, " hit", sz - l); + if (miss) + strncat(out, " miss", sz - l); + + return repsep_snprintf(bf, size, "%-*s", width, out); } -/* --sort dso */ +static int64_t +sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right) +{ + union perf_mem_data_src data_src_l; + union perf_mem_data_src data_src_r; -int64_t -sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) + if (left->mem_info) + data_src_l = left->mem_info->data_src; + else + data_src_l.mem_snoop = PERF_MEM_SNOOP_NA; + + if (right->mem_info) + data_src_r = right->mem_info->data_src; + else + data_src_r.mem_snoop = PERF_MEM_SNOOP_NA; + + return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop); +} + +static const char * const snoop_access[] = { + "N/A", + "None", + "Miss", + "Hit", + "HitM", +}; +#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *)) + +static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) { - struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL; - struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL; - const char *dso_name_l, *dso_name_r; + char out[64]; + size_t sz = sizeof(out) - 1; /* -1 for null termination */ + size_t i, l = 0; + u64 m = PERF_MEM_SNOOP_NA; - if (!dso_l || !dso_r) - return cmp_null(dso_l, dso_r); + out[0] = '\0'; - if (verbose) { - dso_name_l = dso_l->long_name; - dso_name_r = dso_r->long_name; - } else { - dso_name_l = dso_l->short_name; - dso_name_r = dso_r->short_name; + 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)) + continue; + if (l) { + strcat(out, " or "); + l += 4; + } + strncat(out, snoop_access[i], sz - l); + l += strlen(snoop_access[i]); } - return strcmp(dso_name_l, dso_name_r); + if (*out == '\0') + strcpy(out, "N/A"); + + return repsep_snprintf(bf, size, "%-*s", width, out); } -static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width) +static inline u64 cl_address(u64 address) { - if (self->ms.map && self->ms.map->dso) { - const char *dso_name = !verbose ? self->ms.map->dso->short_name : - self->ms.map->dso->long_name; - return repsep_snprintf(bf, size, "%-*s", width, dso_name); + /* return the cacheline of the address */ + return (address & ~(cacheline_size - 1)); +} + +static int64_t +sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) +{ + u64 l, r; + struct map *l_map, *r_map; + + if (!left->mem_info) return -1; + if (!right->mem_info) return 1; + + /* group event types together */ + if (left->cpumode > right->cpumode) return -1; + if (left->cpumode < right->cpumode) return 1; + + l_map = left->mem_info->daddr.map; + r_map = right->mem_info->daddr.map; + + /* if both are NULL, jump to sort on al_addr instead */ + if (!l_map && !r_map) + goto addr; + + if (!l_map) return -1; + if (!r_map) return 1; + + if (l_map->maj > r_map->maj) return -1; + if (l_map->maj < r_map->maj) return 1; + + if (l_map->min > r_map->min) return -1; + if (l_map->min < r_map->min) return 1; + + if (l_map->ino > r_map->ino) return -1; + if (l_map->ino < r_map->ino) return 1; + + if (l_map->ino_generation > r_map->ino_generation) return -1; + if (l_map->ino_generation < r_map->ino_generation) return 1; + + /* + * Addresses with no major/minor numbers are assumed to be + * anonymous in userspace. Sort those on pid then address. + * + * The kernel and non-zero major/minor mapped areas are + * assumed to be unity mapped. Sort those on address. + */ + + if ((left->cpumode != PERF_RECORD_MISC_KERNEL) && + (!(l_map->flags & MAP_SHARED)) && + !l_map->maj && !l_map->min && !l_map->ino && + !l_map->ino_generation) { + /* userspace anonymous */ + + if (left->thread->pid_ > right->thread->pid_) return -1; + if (left->thread->pid_ < right->thread->pid_) return 1; } - return repsep_snprintf(bf, size, "%*Lx", width, self->ip); +addr: + /* al_addr does all the right addr - start + offset calculations */ + l = cl_address(left->mem_info->daddr.al_addr); + r = cl_address(right->mem_info->daddr.al_addr); + + if (l > r) return -1; + if (l < r) return 1; + + return 0; } -/* --sort symbol */ +static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ -int64_t -sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) + uint64_t addr = 0; + struct map *map = NULL; + struct symbol *sym = NULL; + char level = he->level; + + if (he->mem_info) { + addr = cl_address(he->mem_info->daddr.al_addr); + map = he->mem_info->daddr.map; + sym = he->mem_info->daddr.sym; + + /* print [s] for shared data mmaps */ + if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && + map && (map->type == MAP__VARIABLE) && + (map->flags & MAP_SHARED) && + (map->maj || map->min || map->ino || + map->ino_generation)) + level = 's'; + else if (!map) + level = 'X'; + } + return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size, + width); +} + +struct sort_entry sort_mispredict = { + .se_header = "Branch Mispredicted", + .se_cmp = sort__mispredict_cmp, + .se_snprintf = hist_entry__mispredict_snprintf, + .se_width_idx = HISTC_MISPREDICT, +}; + +static u64 he_weight(struct hist_entry *he) { - u64 ip_l, ip_r; + return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0; +} - if (left->ms.sym == right->ms.sym) - return 0; +static int64_t +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 *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he)); +} - ip_l = left->ms.sym ? left->ms.sym->start : left->ip; - ip_r = right->ms.sym ? right->ms.sym->start : right->ip; +struct sort_entry sort_local_weight = { + .se_header = "Local Weight", + .se_cmp = sort__local_weight_cmp, + .se_snprintf = hist_entry__local_weight_snprintf, + .se_width_idx = HISTC_LOCAL_WEIGHT, +}; - return (int64_t)(ip_r - ip_l); +static int64_t +sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->stat.weight - right->stat.weight; } -static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width __used) +static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) { - size_t ret = 0; + return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight); +} - if (verbose) { - char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!'; - ret += repsep_snprintf(bf, size, "%*Lx %c ", - BITS_PER_LONG / 4, self->ip, o); +struct sort_entry sort_global_weight = { + .se_header = "Weight", + .se_cmp = sort__global_weight_cmp, + .se_snprintf = hist_entry__global_weight_snprintf, + .se_width_idx = HISTC_GLOBAL_WEIGHT, +}; + +struct sort_entry sort_mem_daddr_sym = { + .se_header = "Data Symbol", + .se_cmp = sort__daddr_cmp, + .se_snprintf = hist_entry__daddr_snprintf, + .se_width_idx = HISTC_MEM_DADDR_SYMBOL, +}; + +struct sort_entry sort_mem_daddr_dso = { + .se_header = "Data Object", + .se_cmp = sort__dso_daddr_cmp, + .se_snprintf = hist_entry__dso_daddr_snprintf, + .se_width_idx = HISTC_MEM_DADDR_SYMBOL, +}; + +struct sort_entry sort_mem_locked = { + .se_header = "Locked", + .se_cmp = sort__locked_cmp, + .se_snprintf = hist_entry__locked_snprintf, + .se_width_idx = HISTC_MEM_LOCKED, +}; + +struct sort_entry sort_mem_tlb = { + .se_header = "TLB access", + .se_cmp = sort__tlb_cmp, + .se_snprintf = hist_entry__tlb_snprintf, + .se_width_idx = HISTC_MEM_TLB, +}; + +struct sort_entry sort_mem_lvl = { + .se_header = "Memory access", + .se_cmp = sort__lvl_cmp, + .se_snprintf = hist_entry__lvl_snprintf, + .se_width_idx = HISTC_MEM_LVL, +}; + +struct sort_entry sort_mem_snoop = { + .se_header = "Snoop", + .se_cmp = sort__snoop_cmp, + .se_snprintf = hist_entry__snoop_snprintf, + .se_width_idx = HISTC_MEM_SNOOP, +}; + +struct sort_entry sort_mem_dcacheline = { + .se_header = "Data Cacheline", + .se_cmp = sort__dcacheline_cmp, + .se_snprintf = hist_entry__dcacheline_snprintf, + .se_width_idx = HISTC_MEM_DCACHELINE, +}; + +static int64_t +sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) +{ + 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; +} - ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level); - if (self->ms.sym) - ret += repsep_snprintf(bf + ret, size - ret, "%s", - self->ms.sym->name); - else - ret += repsep_snprintf(bf + ret, size - ret, "%*Lx", - BITS_PER_LONG / 4, self->ip); +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 ret; + return repsep_snprintf(bf, size, "%-*s", width, buf); } -/* --sort comm */ +struct sort_entry sort_transaction = { + .se_header = "Transaction ", + .se_cmp = sort__transaction_cmp, + .se_snprintf = hist_entry__transaction_snprintf, + .se_width_idx = HISTC_TRANSACTION, +}; -int64_t -sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) +struct sort_dimension { + const char *name; + struct sort_entry *entry; + int taken; +}; + +#define DIM(d, n, func) [d] = { .name = n, .entry = &(func) } + +static struct sort_dimension common_sort_dimensions[] = { + DIM(SORT_PID, "pid", sort_thread), + DIM(SORT_COMM, "comm", sort_comm), + DIM(SORT_DSO, "dso", sort_dso), + DIM(SORT_SYM, "symbol", sort_sym), + 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 + +#define DIM(d, n, func) [d - __SORT_BRANCH_STACK] = { .name = n, .entry = &(func) } + +static struct sort_dimension bstack_sort_dimensions[] = { + DIM(SORT_DSO_FROM, "dso_from", sort_dso_from), + DIM(SORT_DSO_TO, "dso_to", sort_dso_to), + 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 + +#define DIM(d, n, func) [d - __SORT_MEMORY_MODE] = { .name = n, .entry = &(func) } + +static struct sort_dimension memory_sort_dimensions[] = { + 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), + DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb), + DIM(SORT_MEM_LVL, "mem", sort_mem_lvl), + DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop), + DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline), +}; + +#undef DIM + +struct hpp_dimension { + const char *name; + struct perf_hpp_fmt *fmt; + int taken; +}; + +#define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], } + +static struct hpp_dimension hpp_sort_dimensions[] = { + DIM(PERF_HPP__OVERHEAD, "overhead"), + DIM(PERF_HPP__OVERHEAD_SYS, "overhead_sys"), + DIM(PERF_HPP__OVERHEAD_US, "overhead_us"), + DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"), + DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"), + DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"), + DIM(PERF_HPP__SAMPLES, "sample"), + DIM(PERF_HPP__PERIOD, "period"), +}; + +#undef DIM + +struct hpp_sort_entry { + struct perf_hpp_fmt hpp; + struct sort_entry *se; +}; + +bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) { - return right->thread->pid - left->thread->pid; + struct hpp_sort_entry *hse_a; + struct hpp_sort_entry *hse_b; + + if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b)) + return false; + + hse_a = container_of(a, struct hpp_sort_entry, hpp); + hse_b = container_of(b, struct hpp_sort_entry, hpp); + + return hse_a->se == hse_b->se; } -int64_t -sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) +void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) { - char *comm_l = left->thread->comm; - char *comm_r = right->thread->comm; + struct hpp_sort_entry *hse; - if (!comm_l || !comm_r) - return cmp_null(comm_l, comm_r); + if (!perf_hpp__is_sort_entry(fmt)) + return; - return strcmp(comm_l, comm_r); + hse = container_of(fmt, struct hpp_sort_entry, hpp); + hists__new_col_len(hists, hse->se->se_width_idx, + strlen(hse->se->se_header)); } -/* --sort parent */ +static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel) +{ + struct hpp_sort_entry *hse; + size_t len; -int64_t -sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) + hse = container_of(fmt, struct hpp_sort_entry, hpp); + len = hists__col_len(&evsel->hists, hse->se->se_width_idx); + + return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header); +} + +static int __sort__hpp_width(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused, + struct perf_evsel *evsel) { - struct symbol *sym_l = left->parent; - struct symbol *sym_r = right->parent; + struct hpp_sort_entry *hse; - if (!sym_l || !sym_r) - return cmp_null(sym_l, sym_r); + hse = container_of(fmt, struct hpp_sort_entry, hpp); - return strcmp(sym_l->name, sym_r->name); + return hists__col_len(&evsel->hists, hse->se->se_width_idx); } -static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width) +static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) { - return repsep_snprintf(bf, size, "%-*s", width, - self->parent ? self->parent->name : "[other]"); + struct hpp_sort_entry *hse; + size_t len; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + len = hists__col_len(he->hists, hse->se->se_width_idx); + + return hse->se->se_snprintf(he, hpp->buf, hpp->size, len); } -/* --sort cpu */ +static struct hpp_sort_entry * +__sort_dimension__alloc_hpp(struct sort_dimension *sd) +{ + struct hpp_sort_entry *hse; -int64_t -sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right) + hse = malloc(sizeof(*hse)); + if (hse == NULL) { + pr_err("Memory allocation failed\n"); + return NULL; + } + + hse->se = sd->entry; + hse->hpp.header = __sort__hpp_header; + hse->hpp.width = __sort__hpp_width; + hse->hpp.entry = __sort__hpp_entry; + hse->hpp.color = NULL; + + hse->hpp.cmp = sd->entry->se_cmp; + hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp; + hse->hpp.sort = sd->entry->se_sort ? : hse->hpp.collapse; + + INIT_LIST_HEAD(&hse->hpp.list); + INIT_LIST_HEAD(&hse->hpp.sort_list); + hse->hpp.elide = false; + + return hse; +} + +bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format) { - return right->cpu - left->cpu; + return format->header == __sort__hpp_header; } -static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width) +static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd) { - return repsep_snprintf(bf, size, "%-*d", width, self->cpu); + struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd); + + if (hse == NULL) + return -1; + + perf_hpp__register_sort_field(&hse->hpp); + return 0; +} + +static int __sort_dimension__add_hpp_output(struct sort_dimension *sd) +{ + struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd); + + if (hse == NULL) + return -1; + + perf_hpp__column_register(&hse->hpp); + return 0; +} + +static int __sort_dimension__add(struct sort_dimension *sd) +{ + if (sd->taken) + return 0; + + if (__sort_dimension__add_hpp_sort(sd) < 0) + return -1; + + if (sd->entry->se_collapse) + sort__need_collapse = 1; + + sd->taken = 1; + + return 0; +} + +static int __hpp_dimension__add(struct hpp_dimension *hd) +{ + if (!hd->taken) { + hd->taken = 1; + + perf_hpp__register_sort_field(hd->fmt); + } + return 0; +} + +static int __sort_dimension__add_output(struct sort_dimension *sd) +{ + if (sd->taken) + return 0; + + if (__sort_dimension__add_hpp_output(sd) < 0) + return -1; + + sd->taken = 1; + return 0; +} + +static int __hpp_dimension__add_output(struct hpp_dimension *hd) +{ + if (!hd->taken) { + hd->taken = 1; + + perf_hpp__column_register(hd->fmt); + } + return 0; } int sort_dimension__add(const char *tok) { unsigned int i; - for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { - struct sort_dimension *sd = &sort_dimensions[i]; - - if (sd->taken) - continue; + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) { + struct sort_dimension *sd = &common_sort_dimensions[i]; if (strncasecmp(tok, sd->name, strlen(tok))) continue; - if (sd->entry->se_collapse) - sort__need_collapse = 1; - if (sd->entry == &sort_parent) { int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED); if (ret) { @@ -292,54 +1364,343 @@ int sort_dimension__add(const char *tok) return -EINVAL; } sort__has_parent = 1; + } else if (sd->entry == &sort_sym) { + sort__has_sym = 1; + } else if (sd->entry == &sort_dso) { + sort__has_dso = 1; } - if (list_empty(&hist_entry__sort_list)) { - if (!strcmp(sd->name, "pid")) - sort__first_dimension = SORT_PID; - else if (!strcmp(sd->name, "comm")) - sort__first_dimension = SORT_COMM; - else if (!strcmp(sd->name, "dso")) - sort__first_dimension = SORT_DSO; - else if (!strcmp(sd->name, "symbol")) - sort__first_dimension = SORT_SYM; - else if (!strcmp(sd->name, "parent")) - sort__first_dimension = SORT_PARENT; - else if (!strcmp(sd->name, "cpu")) - sort__first_dimension = SORT_CPU; - } + return __sort_dimension__add(sd); + } + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { + struct hpp_dimension *hd = &hpp_sort_dimensions[i]; + + if (strncasecmp(tok, hd->name, strlen(tok))) + continue; - list_add_tail(&sd->entry->list, &hist_entry__sort_list); - sd->taken = 1; + return __hpp_dimension__add(hd); + } + + for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { + struct sort_dimension *sd = &bstack_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + if (sort__mode != SORT_MODE__BRANCH) + return -EINVAL; + + if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to) + sort__has_sym = 1; + + __sort_dimension__add(sd); + return 0; + } + + for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) { + struct sort_dimension *sd = &memory_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + if (sort__mode != SORT_MODE__MEMORY) + return -EINVAL; + + if (sd->entry == &sort_mem_daddr_sym) + sort__has_sym = 1; + + __sort_dimension__add(sd); return 0; } return -ESRCH; } -void setup_sorting(const char * const usagestr[], const struct option *opts) +static const char *get_default_sort_order(void) +{ + const char *default_sort_orders[] = { + default_sort_order, + default_branch_sort_order, + default_mem_sort_order, + default_top_sort_order, + default_diff_sort_order, + }; + + BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); + + return default_sort_orders[sort__mode]; +} + +static int __setup_sorting(void) { - char *tmp, *tok, *str = strdup(sort_order); + char *tmp, *tok, *str; + const char *sort_keys = sort_order; + int ret = 0; + + if (sort_keys == NULL) { + if (field_order) { + /* + * If user specified field order but no sort order, + * we'll honor it and not add default sort orders. + */ + return 0; + } + + sort_keys = get_default_sort_order(); + } + + str = strdup(sort_keys); + if (str == NULL) { + error("Not enough memory to setup sort keys"); + return -ENOMEM; + } for (tok = strtok_r(str, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - if (sort_dimension__add(tok) < 0) { + ret = sort_dimension__add(tok); + if (ret == -EINVAL) { + error("Invalid --sort key: `%s'", tok); + break; + } else if (ret == -ESRCH) { error("Unknown --sort key: `%s'", tok); - usage_with_options(usagestr, opts); + break; } } free(str); + return ret; +} + +void perf_hpp__set_elide(int idx, bool elide) +{ + struct perf_hpp_fmt *fmt; + struct hpp_sort_entry *hse; + + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + if (hse->se->se_width_idx == idx) { + fmt->elide = elide; + break; + } + } } -void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list, - const char *list_name, FILE *fp) +static bool __get_elide(struct strlist *list, const char *list_name, FILE *fp) { if (list && strlist__nr_entries(list) == 1) { if (fp != NULL) fprintf(fp, "# %s: %s\n", list_name, strlist__entry(list, 0)->s); - self->elide = true; + return true; + } + return false; +} + +static bool get_elide(int idx, FILE *output) +{ + switch (idx) { + case HISTC_SYMBOL: + return __get_elide(symbol_conf.sym_list, "symbol", output); + case HISTC_DSO: + return __get_elide(symbol_conf.dso_list, "dso", output); + case HISTC_COMM: + return __get_elide(symbol_conf.comm_list, "comm", output); + default: + break; + } + + if (sort__mode != SORT_MODE__BRANCH) + return false; + + switch (idx) { + case HISTC_SYMBOL_FROM: + return __get_elide(symbol_conf.sym_from_list, "sym_from", output); + case HISTC_SYMBOL_TO: + return __get_elide(symbol_conf.sym_to_list, "sym_to", output); + case HISTC_DSO_FROM: + return __get_elide(symbol_conf.dso_from_list, "dso_from", output); + case HISTC_DSO_TO: + return __get_elide(symbol_conf.dso_to_list, "dso_to", output); + default: + break; + } + + return false; +} + +void sort__setup_elide(FILE *output) +{ + struct perf_hpp_fmt *fmt; + struct hpp_sort_entry *hse; + + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + fmt->elide = get_elide(hse->se->se_width_idx, output); } + + /* + * It makes no sense to elide all of sort entries. + * Just revert them to show up again. + */ + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + if (!fmt->elide) + return; + } + + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + fmt->elide = false; + } +} + +static int output_field_add(char *tok) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) { + struct sort_dimension *sd = &common_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + return __sort_dimension__add_output(sd); + } + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { + struct hpp_dimension *hd = &hpp_sort_dimensions[i]; + + if (strncasecmp(tok, hd->name, strlen(tok))) + continue; + + return __hpp_dimension__add_output(hd); + } + + for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { + struct sort_dimension *sd = &bstack_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + return __sort_dimension__add_output(sd); + } + + for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) { + struct sort_dimension *sd = &memory_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + return __sort_dimension__add_output(sd); + } + + return -ESRCH; +} + +static void reset_dimensions(void) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) + common_sort_dimensions[i].taken = 0; + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) + hpp_sort_dimensions[i].taken = 0; + + for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) + bstack_sort_dimensions[i].taken = 0; + + for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) + memory_sort_dimensions[i].taken = 0; +} + +static int __setup_output_field(void) +{ + char *tmp, *tok, *str; + int ret = 0; + + if (field_order == NULL) + return 0; + + reset_dimensions(); + + str = strdup(field_order); + if (str == NULL) { + error("Not enough memory to setup output fields"); + return -ENOMEM; + } + + for (tok = strtok_r(str, ", ", &tmp); + tok; tok = strtok_r(NULL, ", ", &tmp)) { + ret = output_field_add(tok); + if (ret == -EINVAL) { + error("Invalid --fields key: `%s'", tok); + break; + } else if (ret == -ESRCH) { + error("Unknown --fields key: `%s'", tok); + break; + } + } + + free(str); + return ret; +} + +int setup_sorting(void) +{ + int err; + + err = __setup_sorting(); + if (err < 0) + return err; + + if (parent_pattern != default_parent_pattern) { + err = sort_dimension__add("parent"); + if (err < 0) + return err; + } + + reset_dimensions(); + + /* + * perf diff doesn't use default hpp output fields. + */ + if (sort__mode != SORT_MODE__DIFF) + perf_hpp__init(); + + err = __setup_output_field(); + if (err < 0) + return err; + + /* copy sort keys to output fields */ + perf_hpp__setup_output_field(); + /* and then copy output fields to sort keys */ + perf_hpp__append_sort_keys(); + + return 0; +} + +void reset_output_field(void) +{ + sort__need_collapse = 0; + sort__has_parent = 0; + sort__has_sym = 0; + sort__has_dso = 0; + + field_order = NULL; + sort_order = NULL; + + reset_dimensions(); + perf_hpp__reset_output_field(); } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 0b91053a7d1..041f0c9cea2 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -20,24 +20,54 @@ #include "parse-options.h" #include "parse-events.h" - +#include "hist.h" #include "thread.h" -#include "sort.h" extern regex_t parent_regex; extern const char *sort_order; +extern const char *field_order; extern const char default_parent_pattern[]; extern const char *parent_pattern; extern const char default_sort_order[]; +extern regex_t ignore_callees_regex; +extern int have_ignore_callees; extern int sort__need_collapse; extern int sort__has_parent; -extern char *field_sep; +extern int sort__has_sym; +extern enum sort_mode sort__mode; extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; extern struct sort_entry sort_sym; extern struct sort_entry sort_parent; +extern struct sort_entry sort_dso_from; +extern struct sort_entry sort_dso_to; +extern struct sort_entry sort_sym_from; +extern struct sort_entry sort_sym_to; extern enum sort_type sort__first_dimension; +struct he_stat { + u64 period; + u64 period_sys; + u64 period_us; + u64 period_guest_sys; + u64 period_guest_us; + u64 weight; + u32 nr_events; +}; + +struct hist_entry_diff { + bool computed; + + /* PERF_HPP__DELTA */ + double period_ratio_delta; + + /* PERF_HPP__RATIO */ + double period_ratio; + + /* HISTC_WEIGHTED_DIFF */ + s64 wdiff; +}; + /** * struct hist_entry - histogram entry * @@ -45,17 +75,26 @@ extern enum sort_type sort__first_dimension; * @nr_rows - rows expanded in callchain, recalculated on folding/unfolding */ struct hist_entry { + struct rb_node rb_node_in; struct rb_node rb_node; - u64 period; - u64 period_sys; - u64 period_us; - u64 period_guest_sys; - u64 period_guest_us; + union { + struct list_head node; + struct list_head head; + } pairs; + struct he_stat stat; + struct he_stat *stat_acc; struct map_symbol ms; struct thread *thread; + struct comm *comm; u64 ip; + u64 transaction; s32 cpu; - u32 nr_events; + u8 cpumode; + + 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; @@ -63,23 +102,91 @@ struct hist_entry { bool init_have_children; char level; + bool used; u8 filtered; + char *srcline; struct symbol *parent; - union { - unsigned long position; - struct hist_entry *pair; - struct rb_root sorted_chain; - }; - struct callchain_root callchain[0]; + unsigned long position; + struct rb_root sorted_chain; + struct branch_info *branch_info; + struct hists *hists; + struct mem_info *mem_info; + struct callchain_root callchain[0]; /* must be last member */ +}; + +static inline bool hist_entry__has_pairs(struct hist_entry *he) +{ + return !list_empty(&he->pairs.node); +} + +static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he) +{ + if (hist_entry__has_pairs(he)) + return list_entry(he->pairs.node.next, struct hist_entry, pairs.node); + return NULL; +} + +static inline void hist_entry__add_pair(struct hist_entry *pair, + struct hist_entry *he) +{ + list_add_tail(&pair->pairs.node, &he->pairs.head); +} + +static inline float hist_entry__get_percent_limit(struct hist_entry *he) +{ + u64 period = he->stat.period; + u64 total_period = hists__total_period(he->hists); + + if (unlikely(total_period == 0)) + return 0; + + if (symbol_conf.cumulate_callchain) + period = he->stat_acc->period; + + return period * 100.0 / total_period; +} + + +enum sort_mode { + SORT_MODE__NORMAL, + SORT_MODE__BRANCH, + SORT_MODE__MEMORY, + SORT_MODE__TOP, + SORT_MODE__DIFF, }; enum sort_type { + /* common sort keys */ SORT_PID, SORT_COMM, SORT_DSO, SORT_SYM, SORT_PARENT, SORT_CPU, + SORT_SRCLINE, + SORT_LOCAL_WEIGHT, + SORT_GLOBAL_WEIGHT, + SORT_TRANSACTION, + + /* branch stack specific sort keys */ + __SORT_BRANCH_STACK, + SORT_DSO_FROM = __SORT_BRANCH_STACK, + SORT_DSO_TO, + SORT_SYM_FROM, + SORT_SYM_TO, + SORT_MISPREDICT, + SORT_ABORT, + SORT_IN_TX, + + /* memory mode specific sort keys */ + __SORT_MEMORY_MODE, + SORT_MEM_DADDR_SYMBOL = __SORT_MEMORY_MODE, + SORT_MEM_DADDR_DSO, + SORT_MEM_LOCKED, + SORT_MEM_TLB, + SORT_MEM_LVL, + SORT_MEM_SNOOP, + SORT_MEM_DCACHELINE, }; /* @@ -93,32 +200,22 @@ 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, + int64_t (*se_sort)(struct hist_entry *, struct hist_entry *); + int (*se_snprintf)(struct hist_entry *he, char *bf, size_t size, unsigned int width); u8 se_width_idx; - bool elide; }; extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; -void setup_sorting(const char * const usagestr[], const struct option *opts); - -extern size_t sort__thread_print(FILE *, struct hist_entry *, unsigned int); -extern size_t sort__comm_print(FILE *, struct hist_entry *, unsigned int); -extern size_t sort__dso_print(FILE *, struct hist_entry *, unsigned int); -extern size_t sort__sym_print(FILE *, struct hist_entry *, unsigned int __used); -extern int64_t cmp_null(void *, void *); -extern int64_t sort__thread_cmp(struct hist_entry *, struct hist_entry *); -extern int64_t sort__comm_cmp(struct hist_entry *, struct hist_entry *); -extern int64_t sort__comm_collapse(struct hist_entry *, struct hist_entry *); -extern int64_t sort__dso_cmp(struct hist_entry *, struct hist_entry *); -extern int64_t sort__sym_cmp(struct hist_entry *, struct hist_entry *); -extern int64_t sort__parent_cmp(struct hist_entry *, struct hist_entry *); -int64_t sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right); -extern size_t sort__parent_print(FILE *, struct hist_entry *, unsigned int); +int setup_sorting(void); +int setup_output_field(void); +void reset_output_field(void); extern int sort_dimension__add(const char *); -void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list, - const char *list_name, FILE *fp); +void sort__setup_elide(FILE *fp); +void perf_hpp__set_elide(int idx, bool elide); + +int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); #endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c new file mode 100644 index 00000000000..f3e4bc5fe5d --- /dev/null +++ b/tools/perf/util/srcline.c @@ -0,0 +1,299 @@ +#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) { + zfree((char **)&a2l->input); + free(a2l); + } + bfd_close(abfd); + return NULL; +} + +static void addr2line_cleanup(struct a2l_data *a2l) +{ + if (a2l->abfd) + bfd_close(a2l->abfd); + zfree((char **)&a2l->input); + zfree(&a2l->syms); + free(a2l); +} + +static int addr2line(const char *dso_name, unsigned long addr, + char **file, unsigned int *line, struct dso *dso) +{ + int ret = 0; + struct a2l_data *a2l = dso->a2l; + + if (!a2l) { + dso->a2l = addr2line_init(dso_name); + a2l = dso->a2l; + } + + if (a2l == NULL) { + pr_warning("addr2line_init failed for %s\n", dso_name); + return 0; + } + + a2l->addr = addr; + a2l->found = false; + + 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; + } + + return ret; +} + +void dso__free_a2l(struct dso *dso) +{ + struct a2l_data *a2l = dso->a2l; + + if (!a2l) + return; + + addr2line_cleanup(a2l); + + dso->a2l = NULL; +} + +#else /* HAVE_LIBBFD_SUPPORT */ + +static int addr2line(const char *dso_name, unsigned long addr, + char **file, unsigned int *line_nr, + struct dso *dso __maybe_unused) +{ + 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; +} + +void dso__free_a2l(struct dso *dso __maybe_unused) +{ +} + +#endif /* HAVE_LIBBFD_SUPPORT */ + +/* + * Number of addr2line failures (without success) before disabling it for that + * dso. + */ +#define A2L_FAIL_LIMIT 123 + +char *get_srcline(struct dso *dso, unsigned long addr) +{ + char *file = NULL; + unsigned line = 0; + char *srcline; + const char *dso_name; + + if (!dso->has_srcline) + return SRCLINE_UNKNOWN; + + if (dso->symsrc_filename) + dso_name = dso->symsrc_filename; + else + dso_name = dso->long_name; + + if (dso_name[0] == '[') + goto out; + + if (!strncmp(dso_name, "/tmp/perf-", 10)) + goto out; + + if (!addr2line(dso_name, addr, &file, &line, dso)) + goto out; + + if (asprintf(&srcline, "%s:%u", file, line) < 0) { + free(file); + goto out; + } + + dso->a2l_fails = 0; + + free(file); + return srcline; + +out: + if (dso->a2l_fails && ++dso->a2l_fails > A2L_FAIL_LIMIT) { + dso->has_srcline = 0; + dso__free_a2l(dso); + } + 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 new file mode 100644 index 00000000000..6506b3dfb60 --- /dev/null +++ b/tools/perf/util/stat.c @@ -0,0 +1,63 @@ +#include <math.h> + +#include "stat.h" + +void update_stats(struct stats *stats, u64 val) +{ + double delta; + + stats->n++; + 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) +{ + return stats->mean; +} + +/* + * http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance + * + * (\Sum n_i^2) - ((\Sum n_i)^2)/n + * s^2 = ------------------------------- + * n - 1 + * + * http://en.wikipedia.org/wiki/Stddev + * + * The std dev of the mean is related to the std dev by: + * + * s + * s_mean = ------- + * sqrt(n) + * + */ +double stddev_stats(struct stats *stats) +{ + double variance, variance_mean; + + if (stats->n < 2) + return 0.0; + + variance = stats->M2 / (stats->n - 1); + variance_mean = variance / stats->n; + + return sqrt(variance_mean); +} + +double rel_stddev_stats(double stddev, double avg) +{ + double pct = 0.0; + + if (avg) + pct = 100.0 * stddev/avg; + + return pct; +} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h new file mode 100644 index 00000000000..5667fc3e39c --- /dev/null +++ b/tools/perf/util/stat.h @@ -0,0 +1,25 @@ +#ifndef __PERF_STATS_H +#define __PERF_STATS_H + +#include <linux/types.h> + +struct stats +{ + double n, mean, M2; + u64 max, min; +}; + +void update_stats(struct stats *stats, u64 val); +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/strbuf.c b/tools/perf/util/strbuf.c index 92e068517c1..4abe23550c7 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -1,4 +1,5 @@ #include "cache.h" +#include <linux/kernel.h> int prefixcmp(const char *str, const char *prefix) { @@ -27,7 +28,7 @@ void strbuf_init(struct strbuf *sb, ssize_t hint) void strbuf_release(struct strbuf *sb) { if (sb->alloc) { - free(sb->buf); + zfree(&sb->buf); strbuf_init(sb, 0); } } @@ -99,7 +100,7 @@ void strbuf_addf(struct strbuf *sb, const char *fmt, ...) len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); va_end(ap); if (len > strbuf_avail(sb)) { - die("this should not happen, your snprintf is broken"); + die("this should not happen, your vsnprintf is broken"); } } strbuf_setlen(sb, sb->len + len); diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c new file mode 100644 index 00000000000..79a757a2a15 --- /dev/null +++ b/tools/perf/util/strfilter.c @@ -0,0 +1,199 @@ +#include "util.h" +#include "string.h" +#include "strfilter.h" + +/* Operators */ +static const char *OP_and = "&"; /* Logical AND */ +static const char *OP_or = "|"; /* Logical OR */ +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 *node) +{ + if (node) { + if (node->p && !is_operator(*node->p)) + zfree((char **)&node->p); + strfilter_node__delete(node->l); + strfilter_node__delete(node->r); + free(node); + } +} + +void strfilter__delete(struct strfilter *filter) +{ + if (filter) { + strfilter_node__delete(filter->root); + free(filter); + } +} + +static const char *get_token(const char *s, const char **e) +{ + const char *p; + + while (isspace(*s)) /* Skip spaces */ + s++; + + if (*s == '\0') { + p = s; + goto end; + } + + p = s + 1; + if (!is_separator(*s)) { + /* End search */ +retry: + while (*p && !is_separator(*p) && !isspace(*p)) + p++; + /* Escape and special case: '!' is also used in glob pattern */ + if (*(p - 1) == '\\' || (*p == '!' && *(p - 1) == '[')) { + p++; + goto retry; + } + } +end: + *e = p; + return s; +} + +static struct strfilter_node *strfilter_node__alloc(const char *op, + struct strfilter_node *l, + struct strfilter_node *r) +{ + struct strfilter_node *node = zalloc(sizeof(*node)); + + if (node) { + node->p = op; + node->l = l; + node->r = r; + } + + return node; +} + +static struct strfilter_node *strfilter_node__new(const char *s, + const char **ep) +{ + struct strfilter_node root, *cur, *last_op; + const char *e; + + if (!s) + return NULL; + + memset(&root, 0, sizeof(root)); + last_op = cur = &root; + + s = get_token(s, &e); + while (*s != '\0' && *s != ')') { + switch (*s) { + case '&': /* Exchg last OP->r with AND */ + if (!cur->r || !last_op->r) + goto error; + cur = strfilter_node__alloc(OP_and, last_op->r, NULL); + if (!cur) + goto nomem; + last_op->r = cur; + last_op = cur; + break; + case '|': /* Exchg the root with OR */ + if (!cur->r || !root.r) + goto error; + cur = strfilter_node__alloc(OP_or, root.r, NULL); + if (!cur) + goto nomem; + root.r = cur; + last_op = cur; + break; + case '!': /* Add NOT as a leaf node */ + if (cur->r) + goto error; + cur->r = strfilter_node__alloc(OP_not, NULL, NULL); + if (!cur->r) + goto nomem; + cur = cur->r; + break; + case '(': /* Recursively parses inside the parenthesis */ + if (cur->r) + goto error; + cur->r = strfilter_node__new(s + 1, &s); + if (!s) + goto nomem; + if (!cur->r || *s != ')') + goto error; + e = s + 1; + break; + default: + if (cur->r) + goto error; + cur->r = strfilter_node__alloc(NULL, NULL, NULL); + if (!cur->r) + goto nomem; + cur->r->p = strndup(s, e - s); + if (!cur->r->p) + goto nomem; + } + s = get_token(e, &e); + } + if (!cur->r) + goto error; + *ep = s; + return root.r; +nomem: + s = NULL; +error: + *ep = s; + strfilter_node__delete(root.r); + return NULL; +} + +/* + * Parse filter rule and return new strfilter. + * Return NULL if fail, and *ep == NULL if memory allocation failed. + */ +struct strfilter *strfilter__new(const char *rules, const char **err) +{ + struct strfilter *filter = zalloc(sizeof(*filter)); + const char *ep = NULL; + + if (filter) + filter->root = strfilter_node__new(rules, &ep); + + if (!filter || !filter->root || *ep != '\0') { + if (err) + *err = ep; + strfilter__delete(filter); + filter = NULL; + } + + return filter; +} + +static bool strfilter_node__compare(struct strfilter_node *node, + const char *str) +{ + if (!node || !node->p) + return false; + + switch (*node->p) { + case '|': /* OR */ + return strfilter_node__compare(node->l, str) || + strfilter_node__compare(node->r, str); + case '&': /* AND */ + return strfilter_node__compare(node->l, str) && + strfilter_node__compare(node->r, str); + case '!': /* NOT */ + return !strfilter_node__compare(node->r, str); + default: + return strglobmatch(str, node->p); + } +} + +/* Return true if STR matches the filter rules */ +bool strfilter__compare(struct strfilter *filter, const char *str) +{ + if (!filter) + return false; + return strfilter_node__compare(filter->root, str); +} diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h new file mode 100644 index 00000000000..fe611f3c9e3 --- /dev/null +++ b/tools/perf/util/strfilter.h @@ -0,0 +1,48 @@ +#ifndef __PERF_STRFILTER_H +#define __PERF_STRFILTER_H +/* General purpose glob matching filter */ + +#include <linux/list.h> +#include <stdbool.h> + +/* A node of string filter */ +struct strfilter_node { + struct strfilter_node *l; /* Tree left branche (for &,|) */ + struct strfilter_node *r; /* Tree right branche (for !,&,|) */ + const char *p; /* Operator or rule */ +}; + +/* String filter */ +struct strfilter { + struct strfilter_node *root; +}; + +/** + * strfilter__new - Create a new string filter + * @rules: Filter rule, which is a combination of glob expressions. + * @err: Pointer which points an error detected on @rules + * + * Parse @rules and return new strfilter. Return NULL if an error detected. + * In that case, *@err will indicate where it is detected, and *@err is NULL + * if a memory allocation is failed. + */ +struct strfilter *strfilter__new(const char *rules, const char **err); + +/** + * strfilter__compare - compare given string and a string filter + * @filter: String filter + * @str: target string + * + * Compare @str and @filter. Return true if the str match the rule + */ +bool strfilter__compare(struct strfilter *filter, const char *str); + +/** + * strfilter__delete - delete a string filter + * @filter: String filter to delete + * + * Delete @filter. + */ +void strfilter__delete(struct strfilter *filter); + +#endif diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 0409fc7c005..2553e5b55b8 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -1,5 +1,5 @@ #include "util.h" -#include "string.h" +#include "linux/string.h" #define K 1024LL /* @@ -85,7 +85,7 @@ out: /* * Helper function for splitting a string into an argv-like array. - * originaly copied from lib/argv_split.c + * originally copied from lib/argv_split.c */ static const char *skip_sep(const char *cp) { @@ -128,7 +128,7 @@ void argv_free(char **argv) { char **p; for (p = argv; *p; p++) - free(*p); + zfree(p); free(argv); } @@ -259,7 +259,7 @@ static bool __match_glob(const char *str, const char *pat, bool ignore_space) if (!*pat) /* Tail wild card matches all */ return true; while (*str) - if (strglobmatch(str++, pat)) + if (__match_glob(str++, pat, ignore_space)) return true; } return !*str && !*pat; @@ -294,3 +294,120 @@ bool strlazymatch(const char *str, const char *pat) { return __match_glob(str, pat, true); } + +/** + * strtailcmp - Compare the tail of two strings + * @s1: 1st string to be compared + * @s2: 2nd string to be compared + * + * Return 0 if whole of either string is same as another's tail part. + */ +int strtailcmp(const char *s1, const char *s2) +{ + int i1 = strlen(s1); + int i2 = strlen(s2); + while (--i1 >= 0 && --i2 >= 0) { + if (s1[i1] != s2[i2]) + return s1[i1] - s2[i2]; + } + return 0; +} + +/** + * strxfrchar - Locate and replace character in @s + * @s: The string to be searched/changed. + * @from: Source character to be replaced. + * @to: Destination character. + * + * Return pointer to the changed string. + */ +char *strxfrchar(char *s, char from, char to) +{ + char *p = s; + + while ((p = strchr(p, from)) != NULL) + *p++ = to; + + return s; +} + +/** + * ltrim - Removes leading whitespace from @s. + * @s: The string to be stripped. + * + * Return pointer to the first non-whitespace character in @s. + */ +char *ltrim(char *s) +{ + int len = strlen(s); + + while (len && isspace(*s)) { + len--; + s++; + } + + return s; +} + +/** + * rtrim - Removes trailing whitespace from @s. + * @s: The string to be stripped. + * + * Note that the first trailing whitespace is replaced with a %NUL-terminator + * in the given string @s. Returns @s. + */ +char *rtrim(char *s) +{ + size_t size = strlen(s); + char *end; + + if (!size) + return s; + + end = s + size - 1; + while (end >= s && isspace(*end)) + end--; + *(end + 1) = '\0'; + + return s; +} + +/** + * memdup - duplicate region of memory + * @src: memory region to duplicate + * @len: memory region length + */ +void *memdup(const void *src, size_t len) +{ + void *p; + + p = malloc(len); + if (p) + memcpy(p, src, 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/strlist.c b/tools/perf/util/strlist.c index 6783a204355..71f9d102b96 100644 --- a/tools/perf/util/strlist.c +++ b/tools/perf/util/strlist.c @@ -5,71 +5,67 @@ */ #include "strlist.h" +#include "util.h" #include <errno.h> #include <stdio.h> #include <stdlib.h> #include <string.h> -static struct str_node *str_node__new(const char *s, bool dupstr) +static +struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry) { - struct str_node *self = malloc(sizeof(*self)); + const char *s = entry; + struct rb_node *rc = NULL; + struct strlist *strlist = container_of(rblist, struct strlist, rblist); + struct str_node *snode = malloc(sizeof(*snode)); - if (self != NULL) { - if (dupstr) { + if (snode != NULL) { + if (strlist->dupstr) { s = strdup(s); if (s == NULL) goto out_delete; } - self->s = s; + snode->s = s; + rc = &snode->rb_node; } - return self; + return rc; out_delete: - free(self); + free(snode); return NULL; } -static void str_node__delete(struct str_node *self, bool dupstr) +static void str_node__delete(struct str_node *snode, bool dupstr) { if (dupstr) - free((void *)self->s); - free(self); + zfree((char **)&snode->s); + free(snode); } -int strlist__add(struct strlist *self, const char *new_entry) +static +void strlist__node_delete(struct rblist *rblist, struct rb_node *rb_node) { - struct rb_node **p = &self->entries.rb_node; - struct rb_node *parent = NULL; - struct str_node *sn; - - while (*p != NULL) { - int rc; - - parent = *p; - sn = rb_entry(parent, struct str_node, rb_node); - rc = strcmp(sn->s, new_entry); - - if (rc > 0) - p = &(*p)->rb_left; - else if (rc < 0) - p = &(*p)->rb_right; - else - return -EEXIST; - } + struct strlist *slist = container_of(rblist, struct strlist, rblist); + struct str_node *snode = container_of(rb_node, struct str_node, rb_node); + + str_node__delete(snode, slist->dupstr); +} - sn = str_node__new(new_entry, self->dupstr); - if (sn == NULL) - return -ENOMEM; +static int strlist__node_cmp(struct rb_node *rb_node, const void *entry) +{ + const char *str = entry; + struct str_node *snode = container_of(rb_node, struct str_node, rb_node); - rb_link_node(&sn->rb_node, parent, p); - rb_insert_color(&sn->rb_node, &self->entries); - ++self->nr_entries; + return strcmp(snode->s, str); +} - return 0; +int strlist__add(struct strlist *slist, const char *new_entry) +{ + return rblist__add_node(&slist->rblist, new_entry); } -int strlist__load(struct strlist *self, const char *filename) +int strlist__load(struct strlist *slist, const char *filename) { char entry[1024]; int err; @@ -85,7 +81,7 @@ int strlist__load(struct strlist *self, const char *filename) continue; entry[len - 1] = '\0'; - err = strlist__add(self, entry); + err = strlist__add(slist, entry); if (err != 0) goto out; } @@ -96,105 +92,82 @@ out: return err; } -void strlist__remove(struct strlist *self, struct str_node *sn) +void strlist__remove(struct strlist *slist, struct str_node *snode) { - rb_erase(&sn->rb_node, &self->entries); - str_node__delete(sn, self->dupstr); + rblist__remove_node(&slist->rblist, &snode->rb_node); } -struct str_node *strlist__find(struct strlist *self, const char *entry) +struct str_node *strlist__find(struct strlist *slist, const char *entry) { - struct rb_node **p = &self->entries.rb_node; - struct rb_node *parent = NULL; - - while (*p != NULL) { - struct str_node *sn; - int rc; - - parent = *p; - sn = rb_entry(parent, struct str_node, rb_node); - rc = strcmp(sn->s, entry); - - if (rc > 0) - p = &(*p)->rb_left; - else if (rc < 0) - p = &(*p)->rb_right; - else - return sn; - } + struct str_node *snode = NULL; + struct rb_node *rb_node = rblist__find(&slist->rblist, entry); - return NULL; + if (rb_node) + snode = container_of(rb_node, struct str_node, rb_node); + + return snode; } -static int strlist__parse_list_entry(struct strlist *self, const char *s) +static int strlist__parse_list_entry(struct strlist *slist, const char *s) { if (strncmp(s, "file://", 7) == 0) - return strlist__load(self, s + 7); + return strlist__load(slist, s + 7); - return strlist__add(self, s); + return strlist__add(slist, s); } -int strlist__parse_list(struct strlist *self, const char *s) +int strlist__parse_list(struct strlist *slist, const char *s) { char *sep; int err; while ((sep = strchr(s, ',')) != NULL) { *sep = '\0'; - err = strlist__parse_list_entry(self, s); + err = strlist__parse_list_entry(slist, s); *sep = ','; if (err != 0) return err; s = sep + 1; } - return *s ? strlist__parse_list_entry(self, s) : 0; + return *s ? strlist__parse_list_entry(slist, s) : 0; } -struct strlist *strlist__new(bool dupstr, const char *slist) +struct strlist *strlist__new(bool dupstr, const char *list) { - struct strlist *self = malloc(sizeof(*self)); + struct strlist *slist = malloc(sizeof(*slist)); + + if (slist != NULL) { + rblist__init(&slist->rblist); + slist->rblist.node_cmp = strlist__node_cmp; + slist->rblist.node_new = strlist__node_new; + slist->rblist.node_delete = strlist__node_delete; - if (self != NULL) { - self->entries = RB_ROOT; - self->dupstr = dupstr; - self->nr_entries = 0; - if (slist && strlist__parse_list(self, slist) != 0) + slist->dupstr = dupstr; + if (list && strlist__parse_list(slist, list) != 0) goto out_error; } - return self; + return slist; out_error: - free(self); + free(slist); return NULL; } -void strlist__delete(struct strlist *self) +void strlist__delete(struct strlist *slist) { - if (self != NULL) { - struct str_node *pos; - struct rb_node *next = rb_first(&self->entries); - - while (next) { - pos = rb_entry(next, struct str_node, rb_node); - next = rb_next(&pos->rb_node); - strlist__remove(self, pos); - } - self->entries = RB_ROOT; - free(self); - } + if (slist != NULL) + rblist__delete(&slist->rblist); } -struct str_node *strlist__entry(const struct strlist *self, unsigned int idx) +struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx) { - struct rb_node *nd; + struct str_node *snode = NULL; + struct rb_node *rb_node; - for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { - struct str_node *pos = rb_entry(nd, struct str_node, rb_node); + rb_node = rblist__entry(&slist->rblist, idx); + if (rb_node) + snode = container_of(rb_node, struct str_node, rb_node); - if (!idx--) - return pos; - } - - return NULL; + return snode; } diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index 3ba839007d2..5c7f87069d9 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -4,46 +4,47 @@ #include <linux/rbtree.h> #include <stdbool.h> +#include "rblist.h" + struct str_node { struct rb_node rb_node; const char *s; }; struct strlist { - struct rb_root entries; - unsigned int nr_entries; + struct rblist rblist; bool dupstr; }; struct strlist *strlist__new(bool dupstr, const char *slist); -void strlist__delete(struct strlist *self); +void strlist__delete(struct strlist *slist); -void strlist__remove(struct strlist *self, struct str_node *sn); -int strlist__load(struct strlist *self, const char *filename); -int strlist__add(struct strlist *self, const char *str); +void strlist__remove(struct strlist *slist, struct str_node *sn); +int strlist__load(struct strlist *slist, const char *filename); +int strlist__add(struct strlist *slist, const char *str); -struct str_node *strlist__entry(const struct strlist *self, unsigned int idx); -struct str_node *strlist__find(struct strlist *self, const char *entry); +struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx); +struct str_node *strlist__find(struct strlist *slist, const char *entry); -static inline bool strlist__has_entry(struct strlist *self, const char *entry) +static inline bool strlist__has_entry(struct strlist *slist, const char *entry) { - return strlist__find(self, entry) != NULL; + return strlist__find(slist, entry) != NULL; } -static inline bool strlist__empty(const struct strlist *self) +static inline bool strlist__empty(const struct strlist *slist) { - return self->nr_entries == 0; + return rblist__empty(&slist->rblist); } -static inline unsigned int strlist__nr_entries(const struct strlist *self) +static inline unsigned int strlist__nr_entries(const struct strlist *slist) { - return self->nr_entries; + return rblist__nr_entries(&slist->rblist); } /* For strlist iteration */ -static inline struct str_node *strlist__first(struct strlist *self) +static inline struct str_node *strlist__first(struct strlist *slist) { - struct rb_node *rn = rb_first(&self->entries); + struct rb_node *rn = rb_first(&slist->rblist.entries); return rn ? rb_entry(rn, struct str_node, rb_node) : NULL; } static inline struct str_node *strlist__next(struct str_node *sn) @@ -58,21 +59,21 @@ static inline struct str_node *strlist__next(struct str_node *sn) /** * strlist_for_each - iterate over a strlist * @pos: the &struct str_node to use as a loop cursor. - * @self: the &struct strlist for loop. + * @slist: the &struct strlist for loop. */ -#define strlist__for_each(pos, self) \ - for (pos = strlist__first(self); pos; pos = strlist__next(pos)) +#define strlist__for_each(pos, slist) \ + for (pos = strlist__first(slist); pos; pos = strlist__next(pos)) /** * strlist_for_each_safe - iterate over a strlist safe against removal of * str_node * @pos: the &struct str_node to use as a loop cursor. * @n: another &struct str_node to use as temporary storage. - * @self: the &struct strlist for loop. + * @slist: the &struct strlist for loop. */ -#define strlist__for_each_safe(pos, n, self) \ - for (pos = strlist__first(self), n = strlist__next(pos); pos;\ +#define strlist__for_each_safe(pos, n, slist) \ + for (pos = strlist__first(slist), n = strlist__next(pos); pos;\ pos = n, n = strlist__next(n)) -int strlist__parse_list(struct strlist *self, const char *s); +int strlist__parse_list(struct strlist *slist, const char *s); #endif /* __PERF_STRLIST_H */ diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index b3637db025a..6a0a13d07a2 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -12,12 +12,17 @@ * of the License. */ +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <string.h> +#include <linux/bitmap.h> +#include "perf.h" #include "svghelper.h" +#include "util.h" +#include "cpumap.h" static u64 first_time, last_time; static u64 turbo_frequency, max_freq; @@ -27,6 +32,8 @@ static u64 turbo_frequency, max_freq; #define SLOT_HEIGHT 25.0 int svg_page_width = 1000; +u64 svg_highlight; +const char *svg_highlight_name; #define MIN_TEXT_SIZE 0.01 @@ -38,16 +45,21 @@ static double cpu2slot(int cpu) return 2 * cpu + 1; } +static int *topology_map; + static double cpu2y(int cpu) { - return cpu2slot(cpu) * SLOT_MULT; + if (topology_map) + return cpu2slot(topology_map[cpu]) * SLOT_MULT; + else + return cpu2slot(cpu) * SLOT_MULT; } -static double time2pixels(u64 time) +static double time2pixels(u64 __time) { double X; - X = 1.0 * svg_page_width * (time - first_time) / (last_time - first_time); + X = 1.0 * svg_page_width * (__time - first_time) / (last_time - first_time); return X; } @@ -94,7 +106,8 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end) total_height = (1 + rows + cpu2slot(cpus)) * SLOT_MULT; fprintf(svgfile, "<?xml version=\"1.0\" standalone=\"no\"?> \n"); - fprintf(svgfile, "<svg width=\"%i\" height=\"%llu\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height); + fprintf(svgfile, "<!DOCTYPE svg SYSTEM \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n"); + fprintf(svgfile, "<svg width=\"%i\" height=\"%" PRIu64 "\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height); fprintf(svgfile, "<defs>\n <style type=\"text/css\">\n <![CDATA[\n"); @@ -102,6 +115,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end) fprintf(svgfile, " rect.process { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.sample { fill:rgb( 0, 0,255); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); + fprintf(svgfile, " rect.sample_hi{ fill:rgb(255,128, 0); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.blocked { fill:rgb(255, 0, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.waiting { fill:rgb(224,214, 0); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); fprintf(svgfile, " rect.WAITING { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0; stroke:rgb( 0, 0, 0); } \n"); @@ -127,14 +141,42 @@ void svg_box(int Yslot, u64 start, u64 end, const char *type) time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type); } -void svg_sample(int Yslot, int cpu, u64 start, u64 end) +static char *time_to_string(u64 duration); +void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) +{ + if (!svgfile) + return; + + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<title>#%d blocked %s</title>\n", cpu, + time_to_string(end - start)); + if (backtrace) + fprintf(svgfile, "<desc>Blocked on:\n%s</desc>\n", backtrace); + svg_box(Yslot, start, end, "blocked"); + fprintf(svgfile, "</g>\n"); +} + +void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) { double text_size; + const char *type; + if (!svgfile) return; - fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"sample\"/>\n", - time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT); + if (svg_highlight && end - start > svg_highlight) + type = "sample_hi"; + else + type = "sample"; + fprintf(svgfile, "<g>\n"); + + fprintf(svgfile, "<title>#%d running %s</title>\n", + cpu, time_to_string(end - start)); + if (backtrace) + fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace); + fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n", + time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, + type); text_size = (time2pixels(end)-time2pixels(start)); if (cpu > 9) @@ -147,6 +189,7 @@ void svg_sample(int Yslot, int cpu, u64 start, u64 end) fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n", time2pixels(start), Yslot * SLOT_MULT + SLOT_HEIGHT - 1, text_size, cpu + 1); + fprintf(svgfile, "</g>\n"); } static char *time_to_string(u64 duration) @@ -167,7 +210,7 @@ static char *time_to_string(u64 duration) return text; } -void svg_waiting(int Yslot, u64 start, u64 end) +void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) { char *text; const char *style; @@ -191,6 +234,9 @@ void svg_waiting(int Yslot, u64 start, u64 end) font_size = round_text_size(font_size); fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT); + fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start)); + if (backtrace) + fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace); fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style); if (font_size > MIN_TEXT_SIZE) @@ -241,28 +287,42 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq) max_freq = __max_freq; turbo_frequency = __turbo_freq; + fprintf(svgfile, "<g>\n"); + fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n", time2pixels(first_time), time2pixels(last_time)-time2pixels(first_time), cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT); - sprintf(cpu_string, "CPU %i", (int)cpu+1); + sprintf(cpu_string, "CPU %i", (int)cpu); fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n", 10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string); fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n", 10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model()); + + fprintf(svgfile, "</g>\n"); } -void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name) +void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace) { double width; + const char *type; if (!svgfile) return; + if (svg_highlight && end - start >= svg_highlight) + type = "sample_hi"; + else if (svg_highlight_name && strstr(name, svg_highlight_name)) + type = "sample_hi"; + else + type = "sample"; fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu)); + fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start)); + if (backtrace) + fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace); fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n", time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type); width = time2pixels(end)-time2pixels(start); @@ -287,6 +347,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type) return; + fprintf(svgfile, "<g>\n"); + if (type > 6) type = 6; sprintf(style, "c%i", type); @@ -305,6 +367,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type) if (width > MIN_TEXT_SIZE) fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n", time2pixels(start), cpu2y(cpu)+width, width, type); + + fprintf(svgfile, "</g>\n"); } static char *HzToHuman(unsigned long hz) @@ -338,6 +402,8 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq) if (!svgfile) return; + fprintf(svgfile, "<g>\n"); + if (max_freq) height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT); height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height; @@ -346,10 +412,11 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq) fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n", time2pixels(start), height+0.9, HzToHuman(freq)); + fprintf(svgfile, "</g>\n"); } -void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2) +void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace) { double height; @@ -357,6 +424,15 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc return; + fprintf(svgfile, "<g>\n"); + + fprintf(svgfile, "<title>%s wakes up %s</title>\n", + desc1 ? desc1 : "?", + desc2 ? desc2 : "?"); + + if (backtrace) + fprintf(svgfile, "<desc>%s</desc>\n", backtrace); + if (row1 < row2) { if (row1) { fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", @@ -394,9 +470,11 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc if (row1) fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", time2pixels(start), height); + + fprintf(svgfile, "</g>\n"); } -void svg_wakeline(u64 start, int row1, int row2) +void svg_wakeline(u64 start, int row1, int row2, const char *backtrace) { double height; @@ -404,6 +482,11 @@ void svg_wakeline(u64 start, int row1, int row2) return; + fprintf(svgfile, "<g>\n"); + + if (backtrace) + fprintf(svgfile, "<desc>%s</desc>\n", backtrace); + if (row1 < row2) fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n", time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row2 * SLOT_MULT); @@ -416,17 +499,28 @@ void svg_wakeline(u64 start, int row1, int row2) height += SLOT_HEIGHT; fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n", time2pixels(start), height); + + fprintf(svgfile, "</g>\n"); } -void svg_interrupt(u64 start, int row) +void svg_interrupt(u64 start, int row, const char *backtrace) { if (!svgfile) return; + fprintf(svgfile, "<g>\n"); + + fprintf(svgfile, "<title>Wakeup from interrupt</title>\n"); + + if (backtrace) + fprintf(svgfile, "<desc>%s</desc>\n", backtrace); + fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", time2pixels(start), row * SLOT_MULT); fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n", time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT); + + fprintf(svgfile, "</g>\n"); } void svg_text(int Yslot, u64 start, const char *text) @@ -454,13 +548,15 @@ void svg_legenda(void) if (!svgfile) return; + fprintf(svgfile, "<g>\n"); svg_legenda_box(0, "Running", "sample"); - svg_legenda_box(100, "Idle","rect.c1"); - svg_legenda_box(200, "Deeper Idle", "rect.c3"); - svg_legenda_box(350, "Deepest Idle", "rect.c6"); + svg_legenda_box(100, "Idle","c1"); + svg_legenda_box(200, "Deeper Idle", "c3"); + svg_legenda_box(350, "Deepest Idle", "c6"); svg_legenda_box(550, "Sleeping", "process2"); svg_legenda_box(650, "Waiting for cpu", "waiting"); svg_legenda_box(800, "Blocked on IO", "blocked"); + fprintf(svgfile, "</g>\n"); } void svg_time_grid(void) @@ -483,7 +579,7 @@ void svg_time_grid(void) color = 128; } - fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%llu\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n", + fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n", time2pixels(i), SLOT_MULT/2, time2pixels(i), total_height, color, color, color, thickness); i += 10000000; @@ -498,3 +594,123 @@ void svg_close(void) svgfile = NULL; } } + +#define cpumask_bits(maskp) ((maskp)->bits) +typedef struct { DECLARE_BITMAP(bits, MAX_NR_CPUS); } cpumask_t; + +struct topology { + cpumask_t *sib_core; + int sib_core_nr; + cpumask_t *sib_thr; + int sib_thr_nr; +}; + +static void scan_thread_topology(int *map, struct topology *t, int cpu, int *pos) +{ + int i; + int thr; + + for (i = 0; i < t->sib_thr_nr; i++) { + if (!test_bit(cpu, cpumask_bits(&t->sib_thr[i]))) + continue; + + for_each_set_bit(thr, + cpumask_bits(&t->sib_thr[i]), + MAX_NR_CPUS) + if (map[thr] == -1) + map[thr] = (*pos)++; + } +} + +static void scan_core_topology(int *map, struct topology *t) +{ + int pos = 0; + int i; + int cpu; + + for (i = 0; i < t->sib_core_nr; i++) + for_each_set_bit(cpu, + cpumask_bits(&t->sib_core[i]), + MAX_NR_CPUS) + scan_thread_topology(map, t, cpu, &pos); +} + +static int str_to_bitmap(char *s, cpumask_t *b) +{ + int i; + int ret = 0; + struct cpu_map *m; + int c; + + m = cpu_map__new(s); + if (!m) + return -1; + + for (i = 0; i < m->nr; i++) { + c = m->map[i]; + if (c >= MAX_NR_CPUS) { + ret = -1; + break; + } + + set_bit(c, cpumask_bits(b)); + } + + cpu_map__delete(m); + + return ret; +} + +int svg_build_topology_map(char *sib_core, int sib_core_nr, + char *sib_thr, int sib_thr_nr) +{ + int i; + struct topology t; + + t.sib_core_nr = sib_core_nr; + t.sib_thr_nr = sib_thr_nr; + t.sib_core = calloc(sib_core_nr, sizeof(cpumask_t)); + t.sib_thr = calloc(sib_thr_nr, sizeof(cpumask_t)); + + if (!t.sib_core || !t.sib_thr) { + fprintf(stderr, "topology: no memory\n"); + goto exit; + } + + for (i = 0; i < sib_core_nr; i++) { + if (str_to_bitmap(sib_core, &t.sib_core[i])) { + fprintf(stderr, "topology: can't parse siblings map\n"); + goto exit; + } + + sib_core += strlen(sib_core) + 1; + } + + for (i = 0; i < sib_thr_nr; i++) { + if (str_to_bitmap(sib_thr, &t.sib_thr[i])) { + fprintf(stderr, "topology: can't parse siblings map\n"); + goto exit; + } + + sib_thr += strlen(sib_thr) + 1; + } + + topology_map = malloc(sizeof(int) * MAX_NR_CPUS); + if (!topology_map) { + fprintf(stderr, "topology: no memory\n"); + goto exit; + } + + for (i = 0; i < MAX_NR_CPUS; i++) + topology_map[i] = -1; + + scan_core_topology(topology_map, &t); + + return 0; + +exit: + zfree(&t.sib_core); + zfree(&t.sib_thr); + + return -1; +} diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h index e0781989cc3..e3aff5332e3 100644 --- a/tools/perf/util/svghelper.h +++ b/tools/perf/util/svghelper.h @@ -1,28 +1,33 @@ #ifndef __PERF_SVGHELPER_H #define __PERF_SVGHELPER_H -#include "types.h" +#include <linux/types.h> extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end); extern void svg_box(int Yslot, u64 start, u64 end, const char *type); -extern void svg_sample(int Yslot, int cpu, u64 start, u64 end); -extern void svg_waiting(int Yslot, u64 start, u64 end); +extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace); +extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace); +extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace); extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency); -extern void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name); +extern void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace); extern void svg_cstate(int cpu, u64 start, u64 end, int type); extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq); extern void svg_time_grid(void); extern void svg_legenda(void); -extern void svg_wakeline(u64 start, int row1, int row2); -extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2); -extern void svg_interrupt(u64 start, int row); +extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace); +extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace); +extern void svg_interrupt(u64 start, int row, const char *backtrace); extern void svg_text(int Yslot, u64 start, const char *text); extern void svg_close(void); +extern int svg_build_topology_map(char *sib_core, int sib_core_nr, + char *sib_thr, int sib_thr_nr); extern int svg_page_width; +extern u64 svg_highlight; +extern const char *svg_highlight_name; #endif /* __PERF_SVGHELPER_H */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c new file mode 100644 index 00000000000..6864661a79d --- /dev/null +++ b/tools/perf/util/symbol-elf.c @@ -0,0 +1,1625 @@ +#include <fcntl.h> +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <unistd.h> +#include <inttypes.h> + +#include "symbol.h" +#include "vdso.h" +#include <symbol/kallsyms.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 + +/** + * elf_symtab__for_each_symbol - iterate thru all the symbols + * + * @syms: struct elf_symtab instance to iterate + * @idx: uint32_t idx + * @sym: GElf_Sym iterator + */ +#define elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) \ + for (idx = 0, gelf_getsym(syms, idx, &sym);\ + idx < nr_syms; \ + idx++, gelf_getsym(syms, idx, &sym)) + +static inline uint8_t elf_sym__type(const GElf_Sym *sym) +{ + return GELF_ST_TYPE(sym->st_info); +} + +static inline int elf_sym__is_function(const GElf_Sym *sym) +{ + return elf_sym__type(sym) == STT_FUNC && + sym->st_name != 0 && + sym->st_shndx != SHN_UNDEF; +} + +static inline bool elf_sym__is_object(const GElf_Sym *sym) +{ + return elf_sym__type(sym) == STT_OBJECT && + sym->st_name != 0 && + sym->st_shndx != SHN_UNDEF; +} + +static inline int elf_sym__is_label(const GElf_Sym *sym) +{ + return elf_sym__type(sym) == STT_NOTYPE && + sym->st_name != 0 && + sym->st_shndx != SHN_UNDEF && + sym->st_shndx != SHN_ABS; +} + +static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type) +{ + switch (type) { + case MAP__FUNCTION: + return elf_sym__is_function(sym); + case MAP__VARIABLE: + return elf_sym__is_object(sym); + default: + return false; + } +} + +static inline const char *elf_sym__name(const GElf_Sym *sym, + const Elf_Data *symstrs) +{ + return symstrs->d_buf + sym->st_name; +} + +static inline const char *elf_sec__name(const GElf_Shdr *shdr, + const Elf_Data *secstrs) +{ + return secstrs->d_buf + shdr->sh_name; +} + +static inline int elf_sec__is_text(const GElf_Shdr *shdr, + const Elf_Data *secstrs) +{ + return strstr(elf_sec__name(shdr, secstrs), "text") != NULL; +} + +static inline bool elf_sec__is_data(const GElf_Shdr *shdr, + const Elf_Data *secstrs) +{ + return strstr(elf_sec__name(shdr, secstrs), "data") != NULL; +} + +static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs, + enum map_type type) +{ + switch (type) { + case MAP__FUNCTION: + return elf_sec__is_text(shdr, secstrs); + case MAP__VARIABLE: + return elf_sec__is_data(shdr, secstrs); + default: + return false; + } +} + +static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr) +{ + Elf_Scn *sec = NULL; + GElf_Shdr shdr; + size_t cnt = 1; + + while ((sec = elf_nextscn(elf, sec)) != NULL) { + gelf_getshdr(sec, &shdr); + + if ((addr >= shdr.sh_addr) && + (addr < (shdr.sh_addr + shdr.sh_size))) + return cnt; + + ++cnt; + } + + return -1; +} + +Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, + GElf_Shdr *shp, const char *name, size_t *idx) +{ + Elf_Scn *sec = NULL; + size_t cnt = 1; + + /* Elf is corrupted/truncated, avoid calling elf_strptr. */ + if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) + return NULL; + + while ((sec = elf_nextscn(elf, sec)) != NULL) { + char *str; + + gelf_getshdr(sec, shp); + str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name); + if (str && !strcmp(name, str)) { + if (idx) + *idx = cnt; + return sec; + } + ++cnt; + } + + return NULL; +} + +#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ + for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \ + idx < nr_entries; \ + ++idx, pos = gelf_getrel(reldata, idx, &pos_mem)) + +#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \ + for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \ + idx < nr_entries; \ + ++idx, pos = gelf_getrela(reldata, idx, &pos_mem)) + +/* + * We need to check if we have a .dynsym, so that we can handle the + * .plt, synthesizing its symbols, that aren't on the symtabs (be it + * .dynsym or .symtab). + * And always look at the original dso, not at debuginfo packages, that + * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS). + */ +int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map, + symbol_filter_t filter) +{ + uint32_t nr_rel_entries, idx; + GElf_Sym sym; + u64 plt_offset; + GElf_Shdr shdr_plt; + struct symbol *f; + GElf_Shdr shdr_rel_plt, shdr_dynsym; + Elf_Data *reldata, *syms, *symstrs; + Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym; + size_t dynsym_idx; + GElf_Ehdr ehdr; + char sympltname[1024]; + Elf *elf; + int nr = 0, symidx, err = 0; + + if (!ss->dynsym) + return 0; + + elf = ss->elf; + ehdr = ss->ehdr; + + scn_dynsym = ss->dynsym; + shdr_dynsym = ss->dynshdr; + dynsym_idx = ss->dynsym_idx; + + if (scn_dynsym == NULL) + goto out_elf_end; + + scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt, + ".rela.plt", NULL); + if (scn_plt_rel == NULL) { + scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt, + ".rel.plt", NULL); + if (scn_plt_rel == NULL) + goto out_elf_end; + } + + err = -1; + + if (shdr_rel_plt.sh_link != dynsym_idx) + goto out_elf_end; + + if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL) + goto out_elf_end; + + /* + * Fetch the relocation section to find the idxes to the GOT + * and the symbols in the .dynsym they refer to. + */ + reldata = elf_getdata(scn_plt_rel, NULL); + if (reldata == NULL) + goto out_elf_end; + + syms = elf_getdata(scn_dynsym, NULL); + if (syms == NULL) + goto out_elf_end; + + scn_symstrs = elf_getscn(elf, shdr_dynsym.sh_link); + if (scn_symstrs == NULL) + goto out_elf_end; + + symstrs = elf_getdata(scn_symstrs, NULL); + if (symstrs == NULL) + goto out_elf_end; + + if (symstrs->d_size == 0) + goto out_elf_end; + + nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize; + plt_offset = shdr_plt.sh_offset; + + if (shdr_rel_plt.sh_type == SHT_RELA) { + GElf_Rela pos_mem, *pos; + + elf_section__for_each_rela(reldata, pos, pos_mem, idx, + nr_rel_entries) { + symidx = GELF_R_SYM(pos->r_info); + plt_offset += shdr_plt.sh_entsize; + gelf_getsym(syms, symidx, &sym); + snprintf(sympltname, sizeof(sympltname), + "%s@plt", elf_sym__name(&sym, symstrs)); + + f = symbol__new(plt_offset, shdr_plt.sh_entsize, + STB_GLOBAL, sympltname); + if (!f) + goto out_elf_end; + + if (filter && filter(map, f)) + symbol__delete(f); + else { + symbols__insert(&dso->symbols[map->type], f); + ++nr; + } + } + } else if (shdr_rel_plt.sh_type == SHT_REL) { + GElf_Rel pos_mem, *pos; + elf_section__for_each_rel(reldata, pos, pos_mem, idx, + nr_rel_entries) { + symidx = GELF_R_SYM(pos->r_info); + plt_offset += shdr_plt.sh_entsize; + gelf_getsym(syms, symidx, &sym); + snprintf(sympltname, sizeof(sympltname), + "%s@plt", elf_sym__name(&sym, symstrs)); + + f = symbol__new(plt_offset, shdr_plt.sh_entsize, + STB_GLOBAL, sympltname); + if (!f) + goto out_elf_end; + + if (filter && filter(map, f)) + symbol__delete(f); + else { + symbols__insert(&dso->symbols[map->type], f); + ++nr; + } + } + } + + err = 0; +out_elf_end: + if (err == 0) + return nr; + pr_debug("%s: problems reading %s PLT info.\n", + __func__, dso->long_name); + return 0; +} + +/* + * Align offset to 4 bytes as needed for note name and descriptor data. + */ +#define NOTE_ALIGN(n) (((n) + 3) & -4U) + +static int elf_read_build_id(Elf *elf, void *bf, size_t size) +{ + int err = -1; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *data; + Elf_Scn *sec; + Elf_Kind ek; + void *ptr; + + if (size < BUILD_ID_SIZE) + goto out; + + ek = elf_kind(elf); + if (ek != ELF_K_ELF) + goto out; + + if (gelf_getehdr(elf, &ehdr) == NULL) { + pr_err("%s: cannot get elf header.\n", __func__); + goto out; + } + + /* + * Check following sections for notes: + * '.note.gnu.build-id' + * '.notes' + * '.note' (VDSO specific) + */ + do { + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".note.gnu.build-id", NULL); + if (sec) + break; + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".notes", NULL); + if (sec) + break; + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".note", NULL); + if (sec) + break; + + return err; + + } while (0); + + data = elf_getdata(sec, NULL); + if (data == NULL) + goto out; + + ptr = data->d_buf; + while (ptr < (data->d_buf + data->d_size)) { + GElf_Nhdr *nhdr = ptr; + size_t namesz = NOTE_ALIGN(nhdr->n_namesz), + descsz = NOTE_ALIGN(nhdr->n_descsz); + const char *name; + + ptr += sizeof(*nhdr); + name = ptr; + ptr += namesz; + if (nhdr->n_type == NT_GNU_BUILD_ID && + nhdr->n_namesz == sizeof("GNU")) { + if (memcmp(name, "GNU", sizeof("GNU")) == 0) { + size_t sz = min(size, descsz); + memcpy(bf, ptr, sz); + memset(bf + sz, 0, size - sz); + err = descsz; + break; + } + } + ptr += descsz; + } + +out: + return err; +} + +int filename__read_build_id(const char *filename, void *bf, size_t size) +{ + int fd, err = -1; + Elf *elf; + + if (size < BUILD_ID_SIZE) + goto out; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); + goto out_close; + } + + err = elf_read_build_id(elf, bf, size); + + elf_end(elf); +out_close: + close(fd); +out: + return err; +} + +int sysfs__read_build_id(const char *filename, void *build_id, size_t size) +{ + int fd, err = -1; + + if (size < BUILD_ID_SIZE) + goto out; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out; + + while (1) { + char bf[BUFSIZ]; + GElf_Nhdr nhdr; + size_t namesz, descsz; + + if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr)) + break; + + namesz = NOTE_ALIGN(nhdr.n_namesz); + descsz = NOTE_ALIGN(nhdr.n_descsz); + if (nhdr.n_type == NT_GNU_BUILD_ID && + nhdr.n_namesz == sizeof("GNU")) { + if (read(fd, bf, namesz) != (ssize_t)namesz) + break; + if (memcmp(bf, "GNU", sizeof("GNU")) == 0) { + size_t sz = min(descsz, size); + if (read(fd, build_id, sz) == (ssize_t)sz) { + memset(build_id + sz, 0, size - sz); + err = 0; + break; + } + } else if (read(fd, bf, descsz) != (ssize_t)descsz) + break; + } else { + int n = namesz + descsz; + if (read(fd, bf, n) != n) + break; + } + } + close(fd); +out: + return err; +} + +int filename__read_debuglink(const char *filename, char *debuglink, + size_t size) +{ + int fd, err = -1; + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *data; + Elf_Scn *sec; + Elf_Kind ek; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); + goto out_close; + } + + ek = elf_kind(elf); + if (ek != ELF_K_ELF) + goto out_elf_end; + + if (gelf_getehdr(elf, &ehdr) == NULL) { + pr_err("%s: cannot get elf header.\n", __func__); + goto out_elf_end; + } + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".gnu_debuglink", NULL); + if (sec == NULL) + goto out_elf_end; + + data = elf_getdata(sec, NULL); + if (data == NULL) + goto out_elf_end; + + /* the start of this section is a zero-terminated string */ + strncpy(debuglink, data->d_buf, size); + + err = 0; + +out_elf_end: + elf_end(elf); +out_close: + close(fd); +out: + return err; +} + +static int dso__swap_init(struct dso *dso, unsigned char eidata) +{ + static unsigned int const endian = 1; + + dso->needs_swap = DSO_SWAP__NO; + + switch (eidata) { + case ELFDATA2LSB: + /* We are big endian, DSO is little endian. */ + if (*(unsigned char const *)&endian != 1) + dso->needs_swap = DSO_SWAP__YES; + break; + + case ELFDATA2MSB: + /* We are little endian, DSO is big endian. */ + if (*(unsigned char const *)&endian != 0) + dso->needs_swap = DSO_SWAP__YES; + break; + + default: + pr_err("unrecognized DSO data encoding %d\n", eidata); + return -EINVAL; + } + + return 0; +} + +bool symsrc__possibly_runtime(struct symsrc *ss) +{ + return ss->dynsym || ss->opdsec; +} + +bool symsrc__has_symtab(struct symsrc *ss) +{ + return ss->symtab != NULL; +} + +void symsrc__destroy(struct symsrc *ss) +{ + zfree(&ss->name); + elf_end(ss->elf); + close(ss->fd); +} + +int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, + enum dso_binary_type type) +{ + int err = -1; + GElf_Ehdr ehdr; + Elf *elf; + int fd; + + fd = open(name, O_RDONLY); + if (fd < 0) + return -1; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + pr_debug("%s: cannot read %s ELF file.\n", __func__, name); + goto out_close; + } + + if (gelf_getehdr(elf, &ehdr) == NULL) { + pr_debug("%s: cannot get elf header.\n", __func__); + goto out_elf_end; + } + + if (dso__swap_init(dso, ehdr.e_ident[EI_DATA])) + goto out_elf_end; + + /* Always reject images with a mismatched build-id: */ + if (dso->has_build_id) { + u8 build_id[BUILD_ID_SIZE]; + + if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) + goto out_elf_end; + + if (!dso__build_id_equal(dso, build_id)) + goto out_elf_end; + } + + ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab", + NULL); + if (ss->symshdr.sh_type != SHT_SYMTAB) + ss->symtab = NULL; + + ss->dynsym_idx = 0; + ss->dynsym = elf_section_by_name(elf, &ehdr, &ss->dynshdr, ".dynsym", + &ss->dynsym_idx); + if (ss->dynshdr.sh_type != SHT_DYNSYM) + ss->dynsym = NULL; + + ss->opdidx = 0; + ss->opdsec = elf_section_by_name(elf, &ehdr, &ss->opdshdr, ".opd", + &ss->opdidx); + if (ss->opdshdr.sh_type != SHT_PROGBITS) + ss->opdsec = NULL; + + if (dso->kernel == DSO_TYPE_USER) { + GElf_Shdr shdr; + ss->adjust_symbols = (ehdr.e_type == ET_EXEC || + ehdr.e_type == ET_REL || + is_vdso_map(dso->short_name) || + elf_section_by_name(elf, &ehdr, &shdr, + ".gnu.prelink_undo", + NULL) != NULL); + } else { + ss->adjust_symbols = ehdr.e_type == ET_EXEC || + ehdr.e_type == ET_REL; + } + + ss->name = strdup(name); + if (!ss->name) + goto out_elf_end; + + ss->elf = elf; + ss->fd = fd; + ss->ehdr = ehdr; + ss->type = type; + + return 0; + +out_elf_end: + elf_end(elf); +out_close: + close(fd); + 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) +{ + struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL; + struct map *curr_map = map; + struct dso *curr_dso = dso; + Elf_Data *symstrs, *secstrs; + uint32_t nr_syms; + int err = -1; + uint32_t idx; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *syms, *opddata = NULL; + GElf_Sym sym; + 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; + syms_ss->symshdr = syms_ss->dynshdr; + } + + elf = syms_ss->elf; + ehdr = syms_ss->ehdr; + sec = syms_ss->symtab; + shdr = syms_ss->symshdr; + + if (runtime_ss->opdsec) + opddata = elf_rawdata(runtime_ss->opdsec, NULL); + + syms = elf_getdata(sec, NULL); + if (syms == NULL) + goto out_elf_end; + + sec = elf_getscn(elf, shdr.sh_link); + if (sec == NULL) + goto out_elf_end; + + symstrs = elf_getdata(sec, NULL); + if (symstrs == NULL) + goto out_elf_end; + + sec_strndx = elf_getscn(elf, ehdr.e_shstrndx); + if (sec_strndx == NULL) + goto out_elf_end; + + secstrs = elf_getdata(sec_strndx, NULL); + if (secstrs == NULL) + goto out_elf_end; + + nr_syms = shdr.sh_size / shdr.sh_entsize; + + memset(&sym, 0, sizeof(sym)); + + /* + * 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; + map->reloc = kmap->ref_reloc_sym->addr - + kmap->ref_reloc_sym->unrelocated_addr; + 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); + char *demangled = NULL; + int is_label = elf_sym__is_label(&sym); + const char *section_name; + bool used_opd = false; + + if (!is_label && !elf_sym__is_a(&sym, map->type)) + continue; + + /* Reject ARM ELF "mapping symbols": these aren't unique and + * don't identify functions, so will confuse the profile + * output: */ + if (ehdr.e_machine == EM_ARM) { + if (!strcmp(elf_name, "$a") || + !strcmp(elf_name, "$d") || + !strcmp(elf_name, "$t")) + continue; + } + + if (runtime_ss->opdsec && sym.st_shndx == runtime_ss->opdidx) { + u32 offset = sym.st_value - syms_ss->opdshdr.sh_addr; + u64 *opd = opddata->d_buf + offset; + sym.st_value = DSO__SWAP(dso, u64, *opd); + sym.st_shndx = elf_addr_to_index(runtime_ss->elf, + sym.st_value); + used_opd = true; + } + /* + * When loading symbols in a data mapping, ABS symbols (which + * has a value of SHN_ABS in its st_shndx) failed at + * elf_getscn(). And it marks the loading as a failure so + * already loaded symbols cannot be fixed up. + * + * I'm not sure what should be done. Just ignore them for now. + * - Namhyung Kim + */ + if (sym.st_shndx == SHN_ABS) + continue; + + sec = elf_getscn(runtime_ss->elf, sym.st_shndx); + if (!sec) + goto out_elf_end; + + gelf_getshdr(sec, &shdr); + + if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type)) + continue; + + section_name = elf_sec__name(&shdr, secstrs); + + /* On ARM, symbols for thumb functions have 1 added to + * the symbol address as a flag - remove it */ + if ((ehdr.e_machine == EM_ARM) && + (map->type == MAP__FUNCTION) && + (sym.st_value & 1)) + --sym.st_value; + + 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); + + curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name); + if (curr_map == NULL) { + u64 start = sym.st_value; + + if (kmodule) + start += map->start + shdr.sh_offset; + + curr_dso = dso__new(dso_name); + if (curr_dso == NULL) + goto out_elf_end; + curr_dso->kernel = dso->kernel; + curr_dso->long_name = dso->long_name; + curr_dso->long_name_len = dso->long_name_len; + curr_map = map__new2(start, curr_dso, + map->type); + if (curr_map == NULL) { + dso__delete(curr_dso); + goto out_elf_end; + } + 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); + dso__set_loaded(curr_dso, map->type); + } else + curr_dso = curr_map->dso; + + goto new_symbol; + } + + if ((used_opd && runtime_ss->adjust_symbols) + || (!used_opd && syms_ss->adjust_symbols)) { + pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " " + "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__, + (u64)sym.st_value, (u64)shdr.sh_addr, + (u64)shdr.sh_offset); + sym.st_value -= shdr.sh_addr - shdr.sh_offset; + } +new_symbol: + /* + * We need to figure out if the object was created from C++ sources + * DWARF DW_compile_unit has this, but we don't always have access + * to it... + */ + if (symbol_conf.demangle) { + demangled = bfd_demangle(NULL, elf_name, + DMGL_PARAMS | DMGL_ANSI); + if (demangled != NULL) + elf_name = demangled; + } + f = symbol__new(sym.st_value, sym.st_size, + GELF_ST_BIND(sym.st_info), elf_name); + free(demangled); + if (!f) + goto out_elf_end; + + if (filter && filter(curr_map, f)) + symbol__delete(f); + else { + symbols__insert(&curr_dso->symbols[curr_map->type], f); + nr++; + } + } + + /* + * For misannotated, zeroed, ASM function sizes. + */ + if (nr > 0) { + symbols__fixup_duplicate(&dso->symbols[map->type]); + symbols__fixup_end(&dso->symbols[map->type]); + if (kmap) { + /* + * We need to fixup this here too because we create new + * maps here, for things like vsyscall sections. + */ + __map_groups__fixup_end(kmap->kmaps, map->type); + } + } + err = nr; +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 new file mode 100644 index 00000000000..bd15f490d04 --- /dev/null +++ b/tools/perf/util/symbol-minimal.c @@ -0,0 +1,330 @@ +#include "symbol.h" +#include "util.h" + +#include <stdio.h> +#include <fcntl.h> +#include <string.h> +#include <byteswap.h> +#include <sys/stat.h> + + +static bool check_need_swap(int file_endian) +{ + const int data = 1; + u8 *check = (u8 *)&data; + int host_endian; + + if (check[0] == 1) + host_endian = ELFDATA2LSB; + else + host_endian = ELFDATA2MSB; + + return host_endian != file_endian; +} + +#define NOTE_ALIGN(sz) (((sz) + 3) & ~3) + +#define NT_GNU_BUILD_ID 3 + +static int read_build_id(void *note_data, size_t note_len, void *bf, + size_t size, bool need_swap) +{ + struct { + u32 n_namesz; + u32 n_descsz; + u32 n_type; + } *nhdr; + void *ptr; + + ptr = note_data; + while (ptr < (note_data + note_len)) { + const char *name; + size_t namesz, descsz; + + nhdr = ptr; + if (need_swap) { + nhdr->n_namesz = bswap_32(nhdr->n_namesz); + nhdr->n_descsz = bswap_32(nhdr->n_descsz); + nhdr->n_type = bswap_32(nhdr->n_type); + } + + namesz = NOTE_ALIGN(nhdr->n_namesz); + descsz = NOTE_ALIGN(nhdr->n_descsz); + + ptr += sizeof(*nhdr); + name = ptr; + ptr += namesz; + if (nhdr->n_type == NT_GNU_BUILD_ID && + nhdr->n_namesz == sizeof("GNU")) { + if (memcmp(name, "GNU", sizeof("GNU")) == 0) { + size_t sz = min(size, descsz); + memcpy(bf, ptr, sz); + memset(bf + sz, 0, size - sz); + return 0; + } + } + ptr += descsz; + } + + return -1; +} + +int filename__read_debuglink(const char *filename __maybe_unused, + char *debuglink __maybe_unused, + size_t size __maybe_unused) +{ + return -1; +} + +/* + * Just try PT_NOTE header otherwise fails + */ +int filename__read_build_id(const char *filename, void *bf, size_t size) +{ + FILE *fp; + int ret = -1; + bool need_swap = false; + u8 e_ident[EI_NIDENT]; + size_t buf_size; + void *buf; + int i; + + fp = fopen(filename, "r"); + if (fp == NULL) + return -1; + + if (fread(e_ident, sizeof(e_ident), 1, fp) != 1) + goto out; + + if (memcmp(e_ident, ELFMAG, SELFMAG) || + e_ident[EI_VERSION] != EV_CURRENT) + goto out; + + need_swap = check_need_swap(e_ident[EI_DATA]); + + /* for simplicity */ + fseek(fp, 0, SEEK_SET); + + if (e_ident[EI_CLASS] == ELFCLASS32) { + Elf32_Ehdr ehdr; + Elf32_Phdr *phdr; + + if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) + goto out; + + if (need_swap) { + ehdr.e_phoff = bswap_32(ehdr.e_phoff); + ehdr.e_phentsize = bswap_16(ehdr.e_phentsize); + ehdr.e_phnum = bswap_16(ehdr.e_phnum); + } + + buf_size = ehdr.e_phentsize * ehdr.e_phnum; + buf = malloc(buf_size); + if (buf == NULL) + goto out; + + fseek(fp, ehdr.e_phoff, SEEK_SET); + if (fread(buf, buf_size, 1, fp) != 1) + goto out_free; + + for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { + void *tmp; + + if (need_swap) { + phdr->p_type = bswap_32(phdr->p_type); + phdr->p_offset = bswap_32(phdr->p_offset); + phdr->p_filesz = bswap_32(phdr->p_filesz); + } + + if (phdr->p_type != PT_NOTE) + continue; + + buf_size = phdr->p_filesz; + tmp = realloc(buf, buf_size); + if (tmp == NULL) + goto out_free; + + buf = tmp; + fseek(fp, phdr->p_offset, SEEK_SET); + if (fread(buf, buf_size, 1, fp) != 1) + goto out_free; + + ret = read_build_id(buf, buf_size, bf, size, need_swap); + if (ret == 0) + ret = size; + break; + } + } else { + Elf64_Ehdr ehdr; + Elf64_Phdr *phdr; + + if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) + goto out; + + if (need_swap) { + ehdr.e_phoff = bswap_64(ehdr.e_phoff); + ehdr.e_phentsize = bswap_16(ehdr.e_phentsize); + ehdr.e_phnum = bswap_16(ehdr.e_phnum); + } + + buf_size = ehdr.e_phentsize * ehdr.e_phnum; + buf = malloc(buf_size); + if (buf == NULL) + goto out; + + fseek(fp, ehdr.e_phoff, SEEK_SET); + if (fread(buf, buf_size, 1, fp) != 1) + goto out_free; + + for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { + void *tmp; + + if (need_swap) { + phdr->p_type = bswap_32(phdr->p_type); + phdr->p_offset = bswap_64(phdr->p_offset); + phdr->p_filesz = bswap_64(phdr->p_filesz); + } + + if (phdr->p_type != PT_NOTE) + continue; + + buf_size = phdr->p_filesz; + tmp = realloc(buf, buf_size); + if (tmp == NULL) + goto out_free; + + buf = tmp; + fseek(fp, phdr->p_offset, SEEK_SET); + if (fread(buf, buf_size, 1, fp) != 1) + goto out_free; + + ret = read_build_id(buf, buf_size, bf, size, need_swap); + if (ret == 0) + ret = size; + break; + } + } +out_free: + free(buf); +out: + fclose(fp); + return ret; +} + +int sysfs__read_build_id(const char *filename, void *build_id, size_t size) +{ + int fd; + int ret = -1; + struct stat stbuf; + size_t buf_size; + void *buf; + + fd = open(filename, O_RDONLY); + if (fd < 0) + return -1; + + if (fstat(fd, &stbuf) < 0) + goto out; + + buf_size = stbuf.st_size; + buf = malloc(buf_size); + if (buf == NULL) + goto out; + + if (read(fd, buf, buf_size) != (ssize_t) buf_size) + goto out_free; + + ret = read_build_id(buf, buf_size, build_id, size, false); +out_free: + free(buf); +out: + close(fd); + return ret; +} + +int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused, + const char *name, + enum dso_binary_type type) +{ + int fd = open(name, O_RDONLY); + if (fd < 0) + return -1; + + ss->name = strdup(name); + if (!ss->name) + goto out_close; + + ss->fd = fd; + ss->type = type; + + return 0; +out_close: + close(fd); + return -1; +} + +bool symsrc__possibly_runtime(struct symsrc *ss __maybe_unused) +{ + /* Assume all sym sources could be a runtime image. */ + return true; +} + +bool symsrc__has_symtab(struct symsrc *ss __maybe_unused) +{ + return false; +} + +void symsrc__destroy(struct symsrc *ss) +{ + zfree(&ss->name); + close(ss->fd); +} + +int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused, + struct symsrc *ss __maybe_unused, + struct map *map __maybe_unused, + symbol_filter_t filter __maybe_unused) +{ + return 0; +} + +int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, + struct symsrc *ss, + struct symsrc *runtime_ss __maybe_unused, + symbol_filter_t filter __maybe_unused, + int kmodule __maybe_unused) +{ + unsigned char *build_id[BUILD_ID_SIZE]; + + if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) { + dso__set_build_id(dso, build_id); + return 1; + } + 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 b39f499e575..7b9096f29cd 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1,8 +1,5 @@ -#define _GNU_SOURCE -#include <ctype.h> #include <dirent.h> #include <errno.h> -#include <libgen.h> #include <stdlib.h> #include <stdio.h> #include <string.h> @@ -11,76 +8,169 @@ #include <sys/param.h> #include <fcntl.h> #include <unistd.h> +#include <inttypes.h> #include "build-id.h" +#include "util.h" #include "debug.h" +#include "machine.h" #include "symbol.h" #include "strlist.h" -#include <libelf.h> -#include <gelf.h> #include <elf.h> #include <limits.h> +#include <symbol/kallsyms.h> #include <sys/utsname.h> -#ifndef NT_GNU_BUILD_ID -#define NT_GNU_BUILD_ID 3 -#endif - -static bool dso__build_id_equal(const struct dso *self, u8 *build_id); -static int elf_read_build_id(Elf *elf, void *bf, size_t size); -static void dsos__add(struct list_head *head, struct dso *dso); -static struct map *map__new2(u64 start, struct dso *dso, enum map_type type); -static int dso__load_kernel_sym(struct dso *self, struct map *map, +static int dso__load_kernel_sym(struct dso *dso, struct map *map, symbol_filter_t filter); -static int dso__load_guest_kernel_sym(struct dso *self, struct map *map, +static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, symbol_filter_t filter); -static int vmlinux_path__nr_entries; -static char **vmlinux_path; +int vmlinux_path__nr_entries; +char **vmlinux_path; struct symbol_conf symbol_conf = { - .exclude_other = true, - .use_modules = true, - .try_vmlinux_path = true, + .use_modules = true, + .try_vmlinux_path = true, + .annotate_src = true, + .demangle = true, + .cumulate_callchain = true, + .symfs = "", }; -int dso__name_len(const struct dso *self) -{ - if (verbose) - return self->long_name_len; +static enum dso_binary_type binary_type_symtab[] = { + DSO_BINARY_TYPE__KALLSYMS, + DSO_BINARY_TYPE__GUEST_KALLSYMS, + DSO_BINARY_TYPE__JAVA_JIT, + DSO_BINARY_TYPE__DEBUGLINK, + DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + 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, +}; - return self->short_name_len; -} +#define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab) -bool dso__loaded(const struct dso *self, enum map_type type) +bool symbol_type__is_a(char symbol_type, enum map_type map_type) { - return self->loaded & (1 << type); + symbol_type = toupper(symbol_type); + + switch (map_type) { + case MAP__FUNCTION: + return symbol_type == 'T' || symbol_type == 'W'; + case MAP__VARIABLE: + return symbol_type == 'D'; + default: + return false; + } } -bool dso__sorted_by_name(const struct dso *self, enum map_type type) +static int prefix_underscores_count(const char *str) { - return self->sorted_by_name & (1 << type); + const char *tail = str; + + while (*tail == '_') + tail++; + + return tail - str; } -static void dso__set_sorted_by_name(struct dso *self, enum map_type type) +#define SYMBOL_A 0 +#define SYMBOL_B 1 + +static int choose_best_symbol(struct symbol *syma, struct symbol *symb) { - self->sorted_by_name |= (1 << type); + s64 a; + s64 b; + size_t na, nb; + + /* Prefer a symbol with non zero length */ + a = syma->end - syma->start; + b = symb->end - symb->start; + if ((b == 0) && (a > 0)) + return SYMBOL_A; + else if ((a == 0) && (b > 0)) + return SYMBOL_B; + + /* Prefer a non weak symbol over a weak one */ + a = syma->binding == STB_WEAK; + b = symb->binding == STB_WEAK; + if (b && !a) + return SYMBOL_A; + if (a && !b) + return SYMBOL_B; + + /* Prefer a global symbol over a non global one */ + a = syma->binding == STB_GLOBAL; + b = symb->binding == STB_GLOBAL; + if (a && !b) + return SYMBOL_A; + if (b && !a) + return SYMBOL_B; + + /* Prefer a symbol with less underscores */ + a = prefix_underscores_count(syma->name); + b = prefix_underscores_count(symb->name); + if (b > a) + return SYMBOL_A; + else if (a > b) + return SYMBOL_B; + + /* Choose the symbol with the longest name */ + na = strlen(syma->name); + nb = strlen(symb->name); + if (na > nb) + return SYMBOL_A; + 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; } -bool symbol_type__is_a(char symbol_type, enum map_type map_type) +void symbols__fixup_duplicate(struct rb_root *symbols) { - switch (map_type) { - case MAP__FUNCTION: - return symbol_type == 'T' || symbol_type == 'W'; - case MAP__VARIABLE: - return symbol_type == 'D' || symbol_type == 'd'; - default: - return false; + struct rb_node *nd; + struct symbol *curr, *next; + + nd = rb_first(symbols); + + while (nd) { + curr = rb_entry(nd, struct symbol, rb_node); +again: + nd = rb_next(&curr->rb_node); + next = rb_entry(nd, struct symbol, rb_node); + + if (!nd) + break; + + if (curr->start != next->start) + continue; + + if (choose_best_symbol(curr, next) == SYMBOL_A) { + rb_erase(&next->rb_node, symbols); + symbol__delete(next); + goto again; + } else { + nd = rb_next(&curr->rb_node); + rb_erase(&curr->rb_node, symbols); + symbol__delete(curr); + } } } -static void symbols__fixup_end(struct rb_root *self) +void symbols__fixup_end(struct rb_root *symbols) { - struct rb_node *nd, *prevnd = rb_first(self); + struct rb_node *nd, *prevnd = rb_first(symbols); struct symbol *curr, *prev; if (prevnd == NULL) @@ -92,7 +182,7 @@ static void symbols__fixup_end(struct rb_root *self) prev = curr; curr = rb_entry(nd, struct symbol, rb_node); - if (prev->end == prev->start) + if (prev->end == prev->start && prev->end != curr->start) prev->end = curr->start - 1; } @@ -101,10 +191,10 @@ static void symbols__fixup_end(struct rb_root *self) curr->end = roundup(curr->start, 4096); } -static void __map_groups__fixup_end(struct map_groups *self, enum map_type type) +void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) { struct map *prev, *curr; - struct rb_node *nd, *prevnd = rb_first(&self->maps[type]); + struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]); if (prevnd == NULL) return; @@ -121,132 +211,87 @@ static void __map_groups__fixup_end(struct map_groups *self, enum map_type type) * We still haven't the actual symbols, so guess the * last map final address. */ - curr->end = ~0UL; + curr->end = ~0ULL; } -static void map_groups__fixup_end(struct map_groups *self) -{ - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - __map_groups__fixup_end(self, i); -} - -static struct symbol *symbol__new(u64 start, u64 len, u8 binding, - const char *name) +struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) { size_t namelen = strlen(name) + 1; - struct symbol *self = calloc(1, (symbol_conf.priv_size + - sizeof(*self) + namelen)); - if (self == NULL) + struct symbol *sym = calloc(1, (symbol_conf.priv_size + + sizeof(*sym) + namelen)); + if (sym == NULL) return NULL; if (symbol_conf.priv_size) - self = ((void *)self) + symbol_conf.priv_size; + sym = ((void *)sym) + symbol_conf.priv_size; - self->start = start; - self->end = len ? start + len - 1 : start; - self->binding = binding; - self->namelen = namelen - 1; + sym->start = start; + sym->end = len ? start + len - 1 : start; + sym->binding = binding; + sym->namelen = namelen - 1; - pr_debug4("%s: %s %#Lx-%#Lx\n", __func__, name, start, self->end); + pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n", + __func__, name, start, sym->end); + memcpy(sym->name, name, namelen); - memcpy(self->name, name, namelen); - - return self; + return sym; } -void symbol__delete(struct symbol *self) +void symbol__delete(struct symbol *sym) { - free(((void *)self) - symbol_conf.priv_size); + free(((void *)sym) - symbol_conf.priv_size); } -static size_t symbol__fprintf(struct symbol *self, FILE *fp) +size_t symbol__fprintf(struct symbol *sym, FILE *fp) { - return fprintf(fp, " %llx-%llx %c %s\n", - self->start, self->end, - self->binding == STB_GLOBAL ? 'g' : - self->binding == STB_LOCAL ? 'l' : 'w', - self->name); -} - -void dso__set_long_name(struct dso *self, char *name) -{ - if (name == NULL) - return; - self->long_name = name; - self->long_name_len = strlen(name); + return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n", + sym->start, sym->end, + sym->binding == STB_GLOBAL ? 'g' : + sym->binding == STB_LOCAL ? 'l' : 'w', + sym->name); } -static void dso__set_short_name(struct dso *self, const char *name) +size_t symbol__fprintf_symname_offs(const struct symbol *sym, + const struct addr_location *al, FILE *fp) { - if (name == NULL) - return; - self->short_name = name; - self->short_name_len = strlen(name); -} + unsigned long offset; + size_t length; -static void dso__set_basename(struct dso *self) -{ - dso__set_short_name(self, basename(self->long_name)); + if (sym && sym->name) { + length = fprintf(fp, "%s", sym->name); + if (al) { + 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; + } else + return fprintf(fp, "[unknown]"); } -struct dso *dso__new(const char *name) +size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) { - struct dso *self = calloc(1, sizeof(*self) + strlen(name) + 1); - - if (self != NULL) { - int i; - strcpy(self->name, name); - dso__set_long_name(self, self->name); - dso__set_short_name(self, self->name); - for (i = 0; i < MAP__NR_TYPES; ++i) - self->symbols[i] = self->symbol_names[i] = RB_ROOT; - self->slen_calculated = 0; - self->origin = DSO__ORIG_NOT_FOUND; - self->loaded = 0; - self->sorted_by_name = 0; - self->has_build_id = 0; - self->kernel = DSO_TYPE_USER; - INIT_LIST_HEAD(&self->node); - } - - return self; + return symbol__fprintf_symname_offs(sym, NULL, fp); } -static void symbols__delete(struct rb_root *self) +void symbols__delete(struct rb_root *symbols) { struct symbol *pos; - struct rb_node *next = rb_first(self); + struct rb_node *next = rb_first(symbols); while (next) { pos = rb_entry(next, struct symbol, rb_node); next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, self); + rb_erase(&pos->rb_node, symbols); symbol__delete(pos); } } -void dso__delete(struct dso *self) +void symbols__insert(struct rb_root *symbols, struct symbol *sym) { - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - symbols__delete(&self->symbols[i]); - if (self->sname_alloc) - free((char *)self->short_name); - if (self->lname_alloc) - free(self->long_name); - free(self); -} - -void dso__set_build_id(struct dso *self, void *build_id) -{ - memcpy(self->build_id, build_id, sizeof(self->build_id)); - self->has_build_id = 1; -} - -static void symbols__insert(struct rb_root *self, struct symbol *sym) -{ - struct rb_node **p = &self->rb_node; + struct rb_node **p = &symbols->rb_node; struct rb_node *parent = NULL; const u64 ip = sym->start; struct symbol *s; @@ -260,17 +305,17 @@ static void symbols__insert(struct rb_root *self, struct symbol *sym) p = &(*p)->rb_right; } rb_link_node(&sym->rb_node, parent, p); - rb_insert_color(&sym->rb_node, self); + rb_insert_color(&sym->rb_node, symbols); } -static struct symbol *symbols__find(struct rb_root *self, u64 ip) +static struct symbol *symbols__find(struct rb_root *symbols, u64 ip) { struct rb_node *n; - if (self == NULL) + if (symbols == NULL) return NULL; - n = self->rb_node; + n = symbols->rb_node; while (n) { struct symbol *s = rb_entry(n, struct symbol, rb_node); @@ -286,16 +331,28 @@ static struct symbol *symbols__find(struct rb_root *self, 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; }; -static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym) +static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym) { - struct rb_node **p = &self->rb_node; + struct rb_node **p = &symbols->rb_node; struct rb_node *parent = NULL; - struct symbol_name_rb_node *symn = ((void *)sym) - sizeof(*parent), *s; + struct symbol_name_rb_node *symn, *s; + + symn = container_of(sym, struct symbol_name_rb_node, sym); while (*p != NULL) { parent = *p; @@ -306,27 +363,29 @@ static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym) p = &(*p)->rb_right; } rb_link_node(&symn->rb_node, parent, p); - rb_insert_color(&symn->rb_node, self); + rb_insert_color(&symn->rb_node, symbols); } -static void symbols__sort_by_name(struct rb_root *self, struct rb_root *source) +static void symbols__sort_by_name(struct rb_root *symbols, + struct rb_root *source) { struct rb_node *nd; for (nd = rb_first(source); nd; nd = rb_next(nd)) { struct symbol *pos = rb_entry(nd, struct symbol, rb_node); - symbols__insert_by_name(self, pos); + symbols__insert_by_name(symbols, pos); } } -static struct symbol *symbols__find_by_name(struct rb_root *self, const char *name) +static struct symbol *symbols__find_by_name(struct rb_root *symbols, + const char *name) { struct rb_node *n; - if (self == NULL) + if (symbols == NULL) return NULL; - n = self->rb_node; + n = symbols->rb_node; while (n) { struct symbol_name_rb_node *s; @@ -346,55 +405,38 @@ static struct symbol *symbols__find_by_name(struct rb_root *self, const char *na return NULL; } -struct symbol *dso__find_symbol(struct dso *self, +struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr) { - return symbols__find(&self->symbols[type], addr); + return symbols__find(&dso->symbols[type], addr); } -struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type, - const char *name) +static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) { - return symbols__find_by_name(&self->symbol_names[type], name); + return symbols__first(&dso->symbols[type]); } -void dso__sort_by_name(struct dso *self, enum map_type type) -{ - dso__set_sorted_by_name(self, type); - return symbols__sort_by_name(&self->symbol_names[type], - &self->symbols[type]); -} - -int build_id__sprintf(const u8 *self, int len, char *bf) +struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, + const char *name) { - char *bid = bf; - const u8 *raw = self; - int i; - - for (i = 0; i < len; ++i) { - sprintf(bid, "%02x", *raw); - ++raw; - bid += 2; - } - - return raw - self; + return symbols__find_by_name(&dso->symbol_names[type], name); } -size_t dso__fprintf_buildid(struct dso *self, FILE *fp) +void dso__sort_by_name(struct dso *dso, enum map_type type) { - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - - build_id__sprintf(self->build_id, sizeof(self->build_id), sbuild_id); - return fprintf(fp, "%s", sbuild_id); + dso__set_sorted_by_name(dso, type); + return symbols__sort_by_name(&dso->symbol_names[type], + &dso->symbols[type]); } -size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp) +size_t dso__fprintf_symbols_by_name(struct dso *dso, + enum map_type type, FILE *fp) { size_t ret = 0; struct rb_node *nd; struct symbol_name_rb_node *pos; - for (nd = rb_first(&self->symbol_names[type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) { pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); fprintf(fp, "%s\n", pos->sym.name); } @@ -402,69 +444,62 @@ size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE * return ret; } -size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp) -{ - struct rb_node *nd; - size_t ret = fprintf(fp, "dso: %s (", self->short_name); - - if (self->short_name != self->long_name) - ret += fprintf(fp, "%s, ", self->long_name); - ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type], - self->loaded ? "" : "NOT "); - ret += dso__fprintf_buildid(self, fp); - ret += fprintf(fp, ")\n"); - for (nd = rb_first(&self->symbols[type]); nd; nd = rb_next(nd)) { - struct symbol *pos = rb_entry(nd, struct symbol, rb_node); - ret += symbol__fprintf(pos, fp); - } - - return ret; -} - -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)) { char *line = NULL; size_t n; + FILE *file; int err = 0; - FILE *file = fopen(filename, "r"); + file = fopen(filename, "r"); if (file == NULL) - goto out_failure; + return -1; - while (!feof(file)) { + while (1) { + char name[PATH_MAX]; u64 start; - int line_len, len; - char symbol_type; - char *symbol_name; + char *sep; + ssize_t line_len; line_len = getline(&line, &n, file); - if (line_len < 0 || !line) - break; + if (line_len < 0) { + if (feof(file)) + break; + err = -1; + goto out; + } + + if (!line) { + err = -1; + goto out; + } line[--line_len] = '\0'; /* \n */ - len = hex2u64(line, &start); + sep = strrchr(line, 'x'); + if (sep == NULL) + continue; - len++; - if (len + 2 >= line_len) + hex2u64(sep + 1, &start); + + sep = strchr(line, ' '); + if (sep == NULL) continue; - symbol_type = toupper(line[len]); - symbol_name = line + len + 2; + *sep = '\0'; + + scnprintf(name, sizeof(name), "[%s]", line); - err = process_symbol(arg, symbol_name, symbol_type, start); + err = process_module(arg, name, start); if (err) break; } - +out: free(line); fclose(file); return err; - -out_failure: - return -1; } struct process_kallsyms_args { @@ -472,12 +507,34 @@ struct process_kallsyms_args { struct dso *dso; }; -static u8 kallsyms2elf_type(char type) -{ - if (type == 'W') - return STB_WEAK; +bool symbol__is_idle(struct symbol *sym) +{ + const char * const idle_symbols[] = { + "cpu_idle", + "intel_idle", + "default_idle", + "native_safe_halt", + "enter_idle", + "exit_idle", + "mwait_idle", + "mwait_idle_with_hints", + "poll_idle", + "ppc64_runlatch_off", + "pseries_dedicated_idle_sleep", + NULL + }; + + int i; + + if (!sym) + return false; + + for (i = 0; idle_symbols[i]; i++) { + if (!strcmp(idle_symbols[i], sym->name)) + return true; + } - return isupper(type) ? STB_GLOBAL : STB_LOCAL; + return false; } static int map__process_kallsym_symbol(void *arg, const char *name, @@ -491,10 +548,11 @@ static int map__process_kallsym_symbol(void *arg, const char *name, return 0; /* - * Will fix up the end later, when we have all symbols sorted. + * module symbols are not sorted so we add all + * symbols, setting length to 0, and rely on + * symbols__fixup_end() to fix it up. */ sym = symbol__new(start, 0, kallsyms2elf_type(type), name); - if (sym == NULL) return -ENOMEM; /* @@ -511,27 +569,74 @@ static int map__process_kallsym_symbol(void *arg, const char *name, * so that we can in the next step set the symbol ->end address and then * call kernel_maps__split_kallsyms. */ -static int dso__load_all_kallsyms(struct dso *self, const char *filename, +static int dso__load_all_kallsyms(struct dso *dso, const char *filename, struct map *map) { - struct process_kallsyms_args args = { .map = map, .dso = self, }; + struct process_kallsyms_args args = { .map = map, .dso = dso, }; 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 * the original ELF section names vmlinux have. */ -static int dso__split_kallsyms(struct dso *self, struct map *map, +static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta, symbol_filter_t filter) { struct map_groups *kmaps = map__kmap(map)->kmaps; struct machine *machine = kmaps->machine; struct map *curr_map = map; struct symbol *pos; - int count = 0; - struct rb_root *root = &self->symbols[map->type]; + int count = 0, moved = 0; + struct rb_root *root = &dso->symbols[map->type]; struct rb_node *next = rb_first(root); int kernel_range = 0; @@ -550,7 +655,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, if (strcmp(curr_map->dso->short_name, module)) { if (curr_map != map && - self->kernel == DSO_TYPE_GUEST_KERNEL && + dso->kernel == DSO_TYPE_GUEST_KERNEL && machine__is_default_guest(machine)) { /* * We assume all symbols of a module are @@ -586,9 +691,20 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, pos->end = curr_map->map_ip(curr_map, pos->end); } else if (curr_map != map) { char dso_name[PATH_MAX]; - struct dso *dso; + struct dso *ndso; - if (self->kernel == DSO_TYPE_GUEST_KERNEL) + if (delta) { + /* Kernel was relocated at boot time */ + pos->start -= delta; + pos->end -= delta; + } + + if (count == 0) { + curr_map = map; + goto filter_symbol; + } + + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) snprintf(dso_name, sizeof(dso_name), "[guest.kernel].%d", kernel_range++); @@ -597,23 +713,27 @@ static int dso__split_kallsyms(struct dso *self, struct map *map, "[kernel].%d", kernel_range++); - dso = dso__new(dso_name); - if (dso == NULL) + ndso = dso__new(dso_name); + if (ndso == NULL) return -1; - dso->kernel = self->kernel; + ndso->kernel = dso->kernel; - curr_map = map__new2(pos->start, dso, map->type); + curr_map = map__new2(pos->start, ndso, map->type); if (curr_map == NULL) { - dso__delete(dso); + dso__delete(ndso); return -1; } curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; map_groups__insert(kmaps, curr_map); ++kernel_range; + } else if (delta) { + /* Kernel was relocated at boot time */ + pos->start -= delta; + pos->end -= delta; } - +filter_symbol: if (filter && filter(curr_map, pos)) { discard_symbol: rb_erase(&pos->rb_node, root); symbol__delete(pos); @@ -621,913 +741,695 @@ discard_symbol: rb_erase(&pos->rb_node, root); if (curr_map != map) { rb_erase(&pos->rb_node, root); symbols__insert(&curr_map->dso->symbols[curr_map->type], pos); - } - count++; + ++moved; + } else + ++count; } } if (curr_map != map && - self->kernel == DSO_TYPE_GUEST_KERNEL && + dso->kernel == DSO_TYPE_GUEST_KERNEL && machine__is_default_guest(kmaps->machine)) { dso__set_loaded(curr_map->dso, curr_map->type); } - return count; + return count + moved; } -int dso__load_kallsyms(struct dso *self, const char *filename, - struct map *map, symbol_filter_t filter) +bool symbol__restricted_filename(const char *filename, + const char *restricted_filename) { - if (dso__load_all_kallsyms(self, filename, map) < 0) - return -1; + bool restricted = false; - symbols__fixup_end(&self->symbols[map->type]); - if (self->kernel == DSO_TYPE_GUEST_KERNEL) - self->origin = DSO__ORIG_GUEST_KERNEL; - else - self->origin = DSO__ORIG_KERNEL; + if (symbol_conf.kptr_restrict) { + char *r = realpath(filename, NULL); + + if (r != NULL) { + restricted = strcmp(r, restricted_filename) == 0; + free(r); + return restricted; + } + } - return dso__split_kallsyms(self, map, filter); + return restricted; } -static int dso__load_perf_map(struct dso *self, struct map *map, - symbol_filter_t filter) -{ - char *line = NULL; - size_t n; - FILE *file; - int nr_syms = 0; +struct module_info { + struct rb_node rb_node; + char *name; + u64 start; +}; - file = fopen(self->long_name, "r"); - if (file == NULL) - goto out_failure; +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 (!feof(file)) { - u64 start, size; - struct symbol *sym; - int line_len, len; + 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); +} - line_len = getline(&line, &n, file); - if (line_len < 0) - break; +static void delete_modules(struct rb_root *modules) +{ + struct module_info *mi; + struct rb_node *next = rb_first(modules); - if (!line) - goto out_failure; + while (next) { + mi = rb_entry(next, struct module_info, rb_node); + next = rb_next(&mi->rb_node); + rb_erase(&mi->rb_node, modules); + zfree(&mi->name); + free(mi); + } +} - line[--line_len] = '\0'; /* \n */ +static struct module_info *find_module(const char *name, + struct rb_root *modules) +{ + struct rb_node *n = modules->rb_node; - len = hex2u64(line, &start); + while (n) { + struct module_info *m; + int cmp; - len++; - if (len + 2 >= line_len) - continue; + 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; + } - len += hex2u64(line + len, &size); + return NULL; +} - len++; - if (len + 2 >= line_len) - continue; +static int __read_proc_modules(void *arg, const char *name, u64 start) +{ + struct rb_root *modules = arg; + struct module_info *mi; - sym = symbol__new(start, size, STB_GLOBAL, line + len); + mi = zalloc(sizeof(struct module_info)); + if (!mi) + return -ENOMEM; - if (sym == NULL) - goto out_delete_line; + mi->name = strdup(name); + mi->start = start; - if (filter && filter(map, sym)) - symbol__delete(sym); - else { - symbols__insert(&self->symbols[map->type], sym); - nr_syms++; - } + if (!mi->name) { + free(mi); + return -ENOMEM; } - free(line); - fclose(file); - - return nr_syms; + add_module(mi, modules); -out_delete_line: - free(line); -out_failure: - return -1; -} - -/** - * elf_symtab__for_each_symbol - iterate thru all the symbols - * - * @self: struct elf_symtab instance to iterate - * @idx: uint32_t idx - * @sym: GElf_Sym iterator - */ -#define elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) \ - for (idx = 0, gelf_getsym(syms, idx, &sym);\ - idx < nr_syms; \ - idx++, gelf_getsym(syms, idx, &sym)) - -static inline uint8_t elf_sym__type(const GElf_Sym *sym) -{ - return GELF_ST_TYPE(sym->st_info); -} - -static inline int elf_sym__is_function(const GElf_Sym *sym) -{ - return elf_sym__type(sym) == STT_FUNC && - sym->st_name != 0 && - sym->st_shndx != SHN_UNDEF; + return 0; } -static inline bool elf_sym__is_object(const GElf_Sym *sym) +static int read_proc_modules(const char *filename, struct rb_root *modules) { - return elf_sym__type(sym) == STT_OBJECT && - sym->st_name != 0 && - sym->st_shndx != SHN_UNDEF; -} + if (symbol__restricted_filename(filename, "/proc/modules")) + return -1; -static inline int elf_sym__is_label(const GElf_Sym *sym) -{ - return elf_sym__type(sym) == STT_NOTYPE && - sym->st_name != 0 && - sym->st_shndx != SHN_UNDEF && - sym->st_shndx != SHN_ABS; -} + if (modules__parse(filename, modules, __read_proc_modules)) { + delete_modules(modules); + return -1; + } -static inline const char *elf_sec__name(const GElf_Shdr *shdr, - const Elf_Data *secstrs) -{ - return secstrs->d_buf + shdr->sh_name; + return 0; } -static inline int elf_sec__is_text(const GElf_Shdr *shdr, - const Elf_Data *secstrs) +int compare_proc_modules(const char *from, const char *to) { - return strstr(elf_sec__name(shdr, secstrs), "text") != NULL; -} + 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; -static inline bool elf_sec__is_data(const GElf_Shdr *shdr, - const Elf_Data *secstrs) -{ - return strstr(elf_sec__name(shdr, secstrs), "data") != NULL; -} + if (read_proc_modules(from, &from_modules)) + return -1; -static inline const char *elf_sym__name(const GElf_Sym *sym, - const Elf_Data *symstrs) -{ - return symstrs->d_buf + sym->st_name; -} + if (read_proc_modules(to, &to_modules)) + goto out_delete_from; -static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, - GElf_Shdr *shp, const char *name, - size_t *idx) -{ - Elf_Scn *sec = NULL; - size_t cnt = 1; + from_node = rb_first(&from_modules); + to_node = rb_first(&to_modules); + while (from_node) { + if (!to_node) + break; - while ((sec = elf_nextscn(elf, sec)) != NULL) { - char *str; + from_m = rb_entry(from_node, struct module_info, rb_node); + to_m = rb_entry(to_node, struct module_info, rb_node); - gelf_getshdr(sec, shp); - str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name); - if (!strcmp(name, str)) { - if (idx) - *idx = cnt; + if (from_m->start != to_m->start || + strcmp(from_m->name, to_m->name)) break; - } - ++cnt; + + from_node = rb_next(from_node); + to_node = rb_next(to_node); } - return sec; -} + if (!from_node && !to_node) + ret = 0; -#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ - for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \ - idx < nr_entries; \ - ++idx, pos = gelf_getrel(reldata, idx, &pos_mem)) + delete_modules(&to_modules); +out_delete_from: + delete_modules(&from_modules); -#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \ - for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \ - idx < nr_entries; \ - ++idx, pos = gelf_getrela(reldata, idx, &pos_mem)) + return ret; +} -/* - * We need to check if we have a .dynsym, so that we can handle the - * .plt, synthesizing its symbols, that aren't on the symtabs (be it - * .dynsym or .symtab). - * And always look at the original dso, not at debuginfo packages, that - * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS). - */ -static int dso__synthesize_plt_symbols(struct dso *self, struct map *map, - symbol_filter_t filter) +static int do_validate_kcore_modules(const char *filename, struct map *map, + struct map_groups *kmaps) { - uint32_t nr_rel_entries, idx; - GElf_Sym sym; - u64 plt_offset; - GElf_Shdr shdr_plt; - struct symbol *f; - GElf_Shdr shdr_rel_plt, shdr_dynsym; - Elf_Data *reldata, *syms, *symstrs; - Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym; - size_t dynsym_idx; - GElf_Ehdr ehdr; - char sympltname[1024]; - Elf *elf; - int nr = 0, symidx, fd, err = 0; - - fd = open(self->long_name, O_RDONLY); - if (fd < 0) - goto out; - - elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) - goto out_close; - - if (gelf_getehdr(elf, &ehdr) == NULL) - goto out_elf_end; - - scn_dynsym = elf_section_by_name(elf, &ehdr, &shdr_dynsym, - ".dynsym", &dynsym_idx); - if (scn_dynsym == NULL) - goto out_elf_end; - - scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt, - ".rela.plt", NULL); - if (scn_plt_rel == NULL) { - scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt, - ".rel.plt", NULL); - if (scn_plt_rel == NULL) - goto out_elf_end; - } - - err = -1; + struct rb_root modules = RB_ROOT; + struct map *old_map; + int err; - if (shdr_rel_plt.sh_link != dynsym_idx) - goto out_elf_end; + err = read_proc_modules(filename, &modules); + if (err) + return err; - if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL) - goto out_elf_end; + old_map = map_groups__first(kmaps, map->type); + while (old_map) { + struct map *next = map_groups__next(old_map); + struct module_info *mi; - /* - * Fetch the relocation section to find the idxes to the GOT - * and the symbols in the .dynsym they refer to. - */ - reldata = elf_getdata(scn_plt_rel, NULL); - if (reldata == NULL) - goto out_elf_end; - - syms = elf_getdata(scn_dynsym, NULL); - if (syms == NULL) - goto out_elf_end; - - scn_symstrs = elf_getscn(elf, shdr_dynsym.sh_link); - if (scn_symstrs == NULL) - goto out_elf_end; - - symstrs = elf_getdata(scn_symstrs, NULL); - if (symstrs == NULL) - goto out_elf_end; - - nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize; - plt_offset = shdr_plt.sh_offset; - - if (shdr_rel_plt.sh_type == SHT_RELA) { - GElf_Rela pos_mem, *pos; - - elf_section__for_each_rela(reldata, pos, pos_mem, idx, - nr_rel_entries) { - symidx = GELF_R_SYM(pos->r_info); - plt_offset += shdr_plt.sh_entsize; - gelf_getsym(syms, symidx, &sym); - snprintf(sympltname, sizeof(sympltname), - "%s@plt", elf_sym__name(&sym, symstrs)); - - f = symbol__new(plt_offset, shdr_plt.sh_entsize, - STB_GLOBAL, sympltname); - if (!f) - goto out_elf_end; - - if (filter && filter(map, f)) - symbol__delete(f); - else { - symbols__insert(&self->symbols[map->type], f); - ++nr; - } - } - } else if (shdr_rel_plt.sh_type == SHT_REL) { - GElf_Rel pos_mem, *pos; - elf_section__for_each_rel(reldata, pos, pos_mem, idx, - nr_rel_entries) { - symidx = GELF_R_SYM(pos->r_info); - plt_offset += shdr_plt.sh_entsize; - gelf_getsym(syms, symidx, &sym); - snprintf(sympltname, sizeof(sympltname), - "%s@plt", elf_sym__name(&sym, symstrs)); - - f = symbol__new(plt_offset, shdr_plt.sh_entsize, - STB_GLOBAL, sympltname); - if (!f) - goto out_elf_end; - - if (filter && filter(map, f)) - symbol__delete(f); - else { - symbols__insert(&self->symbols[map->type], f); - ++nr; - } + if (old_map == map || old_map->start == map->start) { + /* The kernel map */ + old_map = next; + continue; } - } - err = 0; -out_elf_end: - elf_end(elf); -out_close: - close(fd); + /* 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; + } - if (err == 0) - return nr; + old_map = next; + } out: - pr_debug("%s: problems reading %s PLT info.\n", - __func__, self->long_name); - return 0; + delete_modules(&modules); + return err; } -static bool elf_sym__is_a(GElf_Sym *self, enum map_type type) +/* + * 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) { - switch (type) { - case MAP__FUNCTION: - return elf_sym__is_function(self); - case MAP__VARIABLE: - return elf_sym__is_object(self); - default: - return false; - } -} + char *name; -static bool elf_sec__is_a(GElf_Shdr *self, Elf_Data *secstrs, enum map_type type) -{ - switch (type) { - case MAP__FUNCTION: - return elf_sec__is_text(self, secstrs); - case MAP__VARIABLE: - return elf_sec__is_data(self, secstrs); - default: + strcpy(filename, kallsyms_filename); + name = strrchr(filename, '/'); + if (!name) return false; - } -} - -static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr) -{ - Elf_Scn *sec = NULL; - GElf_Shdr shdr; - size_t cnt = 1; - - while ((sec = elf_nextscn(elf, sec)) != NULL) { - gelf_getshdr(sec, &shdr); - if ((addr >= shdr.sh_addr) && - (addr < (shdr.sh_addr + shdr.sh_size))) - return cnt; + name += 1; - ++cnt; + if (!strcmp(name, "kallsyms")) { + strcpy(name, base_name); + return true; } - return -1; + return false; } -static int dso__load_sym(struct dso *self, struct map *map, const char *name, - int fd, symbol_filter_t filter, int kmodule, - int want_symtab) +static int validate_kcore_modules(const char *kallsyms_filename, + struct map *map) { - struct kmap *kmap = self->kernel ? map__kmap(map) : NULL; - struct map *curr_map = map; - struct dso *curr_dso = self; - Elf_Data *symstrs, *secstrs; - uint32_t nr_syms; - int err = -1; - uint32_t idx; - GElf_Ehdr ehdr; - GElf_Shdr shdr, opdshdr; - Elf_Data *syms, *opddata = NULL; - GElf_Sym sym; - Elf_Scn *sec, *sec_strndx, *opdsec; - Elf *elf; - int nr = 0; - size_t opdidx = 0; - - elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) { - pr_debug("%s: cannot read %s ELF file.\n", __func__, name); - goto out_close; - } + struct map_groups *kmaps = map__kmap(map)->kmaps; + char modules_filename[PATH_MAX]; - if (gelf_getehdr(elf, &ehdr) == NULL) { - pr_debug("%s: cannot get elf header.\n", __func__); - goto out_elf_end; - } + if (!filename_from_kallsyms_filename(modules_filename, "modules", + kallsyms_filename)) + return -EINVAL; - /* Always reject images with a mismatched build-id: */ - if (self->has_build_id) { - u8 build_id[BUILD_ID_SIZE]; + if (do_validate_kcore_modules(modules_filename, map, kmaps)) + return -EINVAL; - if (elf_read_build_id(elf, build_id, - BUILD_ID_SIZE) != BUILD_ID_SIZE) - goto out_elf_end; + return 0; +} - if (!dso__build_id_equal(self, build_id)) - goto out_elf_end; - } +static int validate_kcore_addresses(const char *kallsyms_filename, + struct map *map) +{ + struct kmap *kmap = map__kmap(map); - sec = elf_section_by_name(elf, &ehdr, &shdr, ".symtab", NULL); - if (sec == NULL) { - if (want_symtab) - goto out_elf_end; + if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) { + u64 start; - sec = elf_section_by_name(elf, &ehdr, &shdr, ".dynsym", NULL); - if (sec == NULL) - goto out_elf_end; + start = kallsyms__get_function_start(kallsyms_filename, + kmap->ref_reloc_sym->name); + if (start != kmap->ref_reloc_sym->addr) + return -EINVAL; } - opdsec = elf_section_by_name(elf, &ehdr, &opdshdr, ".opd", &opdidx); - if (opdsec) - opddata = elf_rawdata(opdsec, NULL); - - syms = elf_getdata(sec, NULL); - if (syms == NULL) - goto out_elf_end; - - sec = elf_getscn(elf, shdr.sh_link); - if (sec == NULL) - goto out_elf_end; - - symstrs = elf_getdata(sec, NULL); - if (symstrs == NULL) - goto out_elf_end; - - sec_strndx = elf_getscn(elf, ehdr.e_shstrndx); - if (sec_strndx == NULL) - goto out_elf_end; - - secstrs = elf_getdata(sec_strndx, NULL); - if (secstrs == NULL) - goto out_elf_end; - - nr_syms = shdr.sh_size / shdr.sh_entsize; - - memset(&sym, 0, sizeof(sym)); - if (self->kernel == DSO_TYPE_USER) { - self->adjust_symbols = (ehdr.e_type == ET_EXEC || - elf_section_by_name(elf, &ehdr, &shdr, - ".gnu.prelink_undo", - NULL) != NULL); - } else self->adjust_symbols = 0; + return validate_kcore_modules(kallsyms_filename, map); +} - elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) { - struct symbol *f; - const char *elf_name = elf_sym__name(&sym, symstrs); - char *demangled = NULL; - int is_label = elf_sym__is_label(&sym); - const char *section_name; +struct kcore_mapfn_data { + struct dso *dso; + enum map_type type; + struct list_head maps; +}; - 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; +static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) +{ + struct kcore_mapfn_data *md = data; + struct map *map; - if (!is_label && !elf_sym__is_a(&sym, map->type)) - continue; + map = map__new2(start, md->dso, md->type); + if (map == NULL) + return -ENOMEM; - /* Reject ARM ELF "mapping symbols": these aren't unique and - * don't identify functions, so will confuse the profile - * output: */ - if (ehdr.e_machine == EM_ARM) { - if (!strcmp(elf_name, "$a") || - !strcmp(elf_name, "$d") || - !strcmp(elf_name, "$t")) - continue; - } + map->end = map->start + len; + map->pgoff = pgoff; - if (opdsec && sym.st_shndx == opdidx) { - u32 offset = sym.st_value - opdshdr.sh_addr; - u64 *opd = opddata->d_buf + offset; - sym.st_value = *opd; - sym.st_shndx = elf_addr_to_index(elf, sym.st_value); - } + list_add(&map->node, &md->maps); - sec = elf_getscn(elf, sym.st_shndx); - if (!sec) - goto out_elf_end; + return 0; +} - gelf_getshdr(sec, &shdr); +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; - if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type)) - continue; + /* This function requires that the map is the kernel map */ + if (map != machine->vmlinux_maps[map->type]) + return -EINVAL; - section_name = elf_sec__name(&shdr, secstrs); + if (!filename_from_kallsyms_filename(kcore_filename, "kcore", + kallsyms_filename)) + return -EINVAL; - if (self->kernel != DSO_TYPE_USER || kmodule) { - char dso_name[PATH_MAX]; + /* Modules and kernel must be present at their original addresses */ + if (validate_kcore_addresses(kallsyms_filename, map)) + return -EINVAL; - if (strcmp(section_name, - (curr_dso->short_name + - self->short_name_len)) == 0) - goto new_symbol; + md.dso = dso; + md.type = map->type; + INIT_LIST_HEAD(&md.maps); - if (strcmp(section_name, ".text") == 0) { - curr_map = map; - curr_dso = self; - goto new_symbol; - } + fd = open(kcore_filename, O_RDONLY); + if (fd < 0) + return -EINVAL; - snprintf(dso_name, sizeof(dso_name), - "%s%s", self->short_name, section_name); + /* 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; - curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name); - if (curr_map == NULL) { - u64 start = sym.st_value; + if (list_empty(&md.maps)) { + err = -EINVAL; + goto out_err; + } - if (kmodule) - start += map->start + shdr.sh_offset; + /* Remove old maps */ + old_map = map_groups__first(kmaps, map->type); + while (old_map) { + struct map *next = map_groups__next(old_map); - curr_dso = dso__new(dso_name); - if (curr_dso == NULL) - goto out_elf_end; - curr_dso->kernel = self->kernel; - curr_map = map__new2(start, curr_dso, - map->type); - if (curr_map == NULL) { - dso__delete(curr_dso); - goto out_elf_end; - } - curr_map->map_ip = identity__map_ip; - curr_map->unmap_ip = identity__map_ip; - curr_dso->origin = self->origin; - map_groups__insert(kmap->kmaps, curr_map); - dsos__add(&self->node, curr_dso); - dso__set_loaded(curr_dso, map->type); - } else - curr_dso = curr_map->dso; + if (old_map != map) + map_groups__remove(kmaps, old_map); + old_map = next; + } - goto new_symbol; + /* 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 (curr_dso->adjust_symbols) { - pr_debug4("%s: adjusting symbol: st_value: %#Lx " - "sh_addr: %#Lx sh_offset: %#Lx\n", __func__, - (u64)sym.st_value, (u64)shdr.sh_addr, - (u64)shdr.sh_offset); - sym.st_value -= shdr.sh_addr - shdr.sh_offset; - } - /* - * We need to figure out if the object was created from C++ sources - * DWARF DW_compile_unit has this, but we don't always have access - * to it... - */ - demangled = bfd_demangle(NULL, elf_name, DMGL_PARAMS | DMGL_ANSI); - if (demangled != NULL) - elf_name = demangled; -new_symbol: - f = symbol__new(sym.st_value, sym.st_size, - GELF_ST_BIND(sym.st_info), elf_name); - free(demangled); - if (!f) - goto out_elf_end; - - if (filter && filter(curr_map, f)) - symbol__delete(f); - else { - symbols__insert(&curr_dso->symbols[curr_map->type], f); - nr++; + 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); } } /* - * For misannotated, zeroed, ASM function sizes. + * Set the data type and long name so that kcore can be read via + * dso__data_read_addr(). */ - if (nr > 0) { - symbols__fixup_end(&self->symbols[map->type]); - if (kmap) { - /* - * We need to fixup this here too because we create new - * maps here, for things like vsyscall sections. - */ - __map_groups__fixup_end(kmap->kmaps, map->type); - } - } - err = nr; -out_elf_end: - elf_end(elf); -out_close: - return err; -} + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + dso->binary_type = DSO_BINARY_TYPE__GUEST_KCORE; + else + dso->binary_type = DSO_BINARY_TYPE__KCORE; + dso__set_long_name(dso, strdup(kcore_filename), true); -static bool dso__build_id_equal(const struct dso *self, u8 *build_id) -{ - return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0; -} + close(fd); -bool __dsos__read_build_ids(struct list_head *head, bool with_hits) -{ - bool have_build_id = false; - struct dso *pos; + 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); - list_for_each_entry(pos, head, node) { - if (with_hits && !pos->hit) - continue; - if (pos->has_build_id) { - have_build_id = true; - continue; - } - if (filename__read_build_id(pos->long_name, pos->build_id, - sizeof(pos->build_id)) > 0) { - have_build_id = true; - pos->has_build_id = true; - } - } + return 0; - return have_build_id; +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; } /* - * Align offset to 4 bytes as needed for note name and descriptor data. + * If the kernel is relocated at boot time, kallsyms won't match. Compute the + * delta based on the relocation reference symbol. */ -#define NOTE_ALIGN(n) (((n) + 3) & -4U) - -static int elf_read_build_id(Elf *elf, void *bf, size_t size) +static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) { - int err = -1; - GElf_Ehdr ehdr; - GElf_Shdr shdr; - Elf_Data *data; - Elf_Scn *sec; - Elf_Kind ek; - void *ptr; - - if (size < BUILD_ID_SIZE) - goto out; - - ek = elf_kind(elf); - if (ek != ELF_K_ELF) - goto out; - - if (gelf_getehdr(elf, &ehdr) == NULL) { - pr_err("%s: cannot get elf header.\n", __func__); - goto out; - } + struct kmap *kmap = map__kmap(map); + u64 addr; - sec = elf_section_by_name(elf, &ehdr, &shdr, - ".note.gnu.build-id", NULL); - if (sec == NULL) { - sec = elf_section_by_name(elf, &ehdr, &shdr, - ".notes", NULL); - if (sec == NULL) - goto out; - } + if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name) + return 0; - data = elf_getdata(sec, NULL); - if (data == NULL) - goto out; - - ptr = data->d_buf; - while (ptr < (data->d_buf + data->d_size)) { - GElf_Nhdr *nhdr = ptr; - int namesz = NOTE_ALIGN(nhdr->n_namesz), - descsz = NOTE_ALIGN(nhdr->n_descsz); - const char *name; - - ptr += sizeof(*nhdr); - name = ptr; - ptr += namesz; - if (nhdr->n_type == NT_GNU_BUILD_ID && - nhdr->n_namesz == sizeof("GNU")) { - if (memcmp(name, "GNU", sizeof("GNU")) == 0) { - memcpy(bf, ptr, BUILD_ID_SIZE); - err = BUILD_ID_SIZE; - break; - } - } - ptr += descsz; - } + addr = kallsyms__get_function_start(filename, + kmap->ref_reloc_sym->name); + if (!addr) + return -1; -out: - return err; + *delta = addr - kmap->ref_reloc_sym->addr; + return 0; } -int filename__read_build_id(const char *filename, void *bf, size_t size) +int dso__load_kallsyms(struct dso *dso, const char *filename, + struct map *map, symbol_filter_t filter) { - int fd, err = -1; - Elf *elf; + u64 delta = 0; - if (size < BUILD_ID_SIZE) - goto out; + if (symbol__restricted_filename(filename, "/proc/kallsyms")) + return -1; - fd = open(filename, O_RDONLY); - if (fd < 0) - goto out; + if (dso__load_all_kallsyms(dso, filename, map) < 0) + return -1; - elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) { - pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); - goto out_close; - } + if (kallsyms__delta(map, filename, &delta)) + return -1; - err = elf_read_build_id(elf, bf, size); + symbols__fixup_duplicate(&dso->symbols[map->type]); + symbols__fixup_end(&dso->symbols[map->type]); - elf_end(elf); -out_close: - close(fd); -out: - return err; + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS; + else + dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; + + if (!dso__load_kcore(dso, map, filename)) + return dso__split_kallsyms_for_kcore(dso, map, filter); + else + return dso__split_kallsyms(dso, map, delta, filter); } -int sysfs__read_build_id(const char *filename, void *build_id, size_t size) +static int dso__load_perf_map(struct dso *dso, struct map *map, + symbol_filter_t filter) { - int fd, err = -1; - - if (size < BUILD_ID_SIZE) - goto out; + char *line = NULL; + size_t n; + FILE *file; + int nr_syms = 0; - fd = open(filename, O_RDONLY); - if (fd < 0) - goto out; + file = fopen(dso->long_name, "r"); + if (file == NULL) + goto out_failure; - while (1) { - char bf[BUFSIZ]; - GElf_Nhdr nhdr; - int namesz, descsz; + while (!feof(file)) { + u64 start, size; + struct symbol *sym; + int line_len, len; - if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr)) + line_len = getline(&line, &n, file); + if (line_len < 0) break; - namesz = NOTE_ALIGN(nhdr.n_namesz); - descsz = NOTE_ALIGN(nhdr.n_descsz); - if (nhdr.n_type == NT_GNU_BUILD_ID && - nhdr.n_namesz == sizeof("GNU")) { - if (read(fd, bf, namesz) != namesz) - break; - if (memcmp(bf, "GNU", sizeof("GNU")) == 0) { - if (read(fd, build_id, - BUILD_ID_SIZE) == BUILD_ID_SIZE) { - err = 0; - break; - } - } else if (read(fd, bf, descsz) != descsz) - break; - } else { - int n = namesz + descsz; - if (read(fd, bf, n) != n) - break; + if (!line) + goto out_failure; + + line[--line_len] = '\0'; /* \n */ + + len = hex2u64(line, &start); + + len++; + if (len + 2 >= line_len) + continue; + + len += hex2u64(line + len, &size); + + len++; + if (len + 2 >= line_len) + continue; + + sym = symbol__new(start, size, STB_GLOBAL, line + len); + + if (sym == NULL) + goto out_delete_line; + + if (filter && filter(map, sym)) + symbol__delete(sym); + else { + symbols__insert(&dso->symbols[map->type], sym); + nr_syms++; } } - close(fd); -out: - return err; + + free(line); + fclose(file); + + return nr_syms; + +out_delete_line: + free(line); +out_failure: + return -1; } -char dso__symtab_origin(const struct dso *self) +static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, + enum dso_binary_type type) { - static const char origin[] = { - [DSO__ORIG_KERNEL] = 'k', - [DSO__ORIG_JAVA_JIT] = 'j', - [DSO__ORIG_BUILD_ID_CACHE] = 'B', - [DSO__ORIG_FEDORA] = 'f', - [DSO__ORIG_UBUNTU] = 'u', - [DSO__ORIG_BUILDID] = 'b', - [DSO__ORIG_DSO] = 'd', - [DSO__ORIG_KMODULE] = 'K', - [DSO__ORIG_GUEST_KERNEL] = 'g', - [DSO__ORIG_GUEST_KMODULE] = 'G', - }; + switch (type) { + case DSO_BINARY_TYPE__JAVA_JIT: + case DSO_BINARY_TYPE__DEBUGLINK: + case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: + case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + return !kmod && dso->kernel == DSO_TYPE_USER; + + case DSO_BINARY_TYPE__KALLSYMS: + case DSO_BINARY_TYPE__VMLINUX: + case DSO_BINARY_TYPE__KCORE: + return dso->kernel == DSO_TYPE_KERNEL; + + case DSO_BINARY_TYPE__GUEST_KALLSYMS: + case DSO_BINARY_TYPE__GUEST_VMLINUX: + case DSO_BINARY_TYPE__GUEST_KCORE: + return dso->kernel == DSO_TYPE_GUEST_KERNEL; + + case DSO_BINARY_TYPE__GUEST_KMODULE: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + /* + * kernel modules know their symtab type - it's set when + * creating a module dso in machine__new_module(). + */ + return kmod && dso->symtab_type == type; - if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND) - return '!'; - return origin[self->origin]; + case DSO_BINARY_TYPE__BUILD_ID_CACHE: + return true; + + case DSO_BINARY_TYPE__NOT_FOUND: + default: + return false; + } } -int dso__load(struct dso *self, struct map *map, symbol_filter_t filter) +int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) { - int size = PATH_MAX; char *name; int ret = -1; - int fd; + u_int i; struct machine *machine; - const char *root_dir; - int want_symtab; + char *root_dir = (char *) ""; + int ss_pos = 0; + struct symsrc ss_[2]; + struct symsrc *syms_ss = NULL, *runtime_ss = NULL; + bool kmod; - dso__set_loaded(self, map->type); + dso__set_loaded(dso, map->type); - if (self->kernel == DSO_TYPE_KERNEL) - return dso__load_kernel_sym(self, map, filter); - else if (self->kernel == DSO_TYPE_GUEST_KERNEL) - return dso__load_guest_kernel_sym(self, map, filter); + if (dso->kernel == DSO_TYPE_KERNEL) + return dso__load_kernel_sym(dso, map, filter); + else if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + return dso__load_guest_kernel_sym(dso, map, filter); if (map->groups && map->groups->machine) machine = map->groups->machine; else machine = NULL; - name = malloc(size); - if (!name) - return -1; + dso->adjust_symbols = 0; + + if (strncmp(dso->name, "/tmp/perf-", 10) == 0) { + struct stat st; - self->adjust_symbols = 0; + if (lstat(dso->name, &st) < 0) + return -1; - if (strncmp(self->name, "/tmp/perf-", 10) == 0) { - ret = dso__load_perf_map(self, map, filter); - self->origin = ret > 0 ? DSO__ORIG_JAVA_JIT : - DSO__ORIG_NOT_FOUND; + if (st.st_uid && (st.st_uid != geteuid())) { + pr_warning("File %s not owned by current user or root, " + "ignoring it.\n", dso->name); + return -1; + } + + ret = dso__load_perf_map(dso, map, filter); + dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT : + DSO_BINARY_TYPE__NOT_FOUND; return ret; } - /* Iterate over candidate debug images. - * On the first pass, only load images if they have a full symtab. - * Failing that, do a second pass where we accept .dynsym also + if (machine) + root_dir = machine->root_dir; + + name = malloc(PATH_MAX); + if (!name) + return -1; + + kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; + + /* + * Iterate over candidate debug images. + * Keep track of "interesting" ones (those which have a symtab, dynsym, + * and/or opd section) for processing. */ - for (self->origin = DSO__ORIG_BUILD_ID_CACHE, want_symtab = 1; - self->origin != DSO__ORIG_NOT_FOUND; - self->origin++) { - switch (self->origin) { - case DSO__ORIG_BUILD_ID_CACHE: - if (dso__build_id_filename(self, name, size) == NULL) - continue; - break; - case DSO__ORIG_FEDORA: - snprintf(name, size, "/usr/lib/debug%s.debug", - self->long_name); - break; - case DSO__ORIG_UBUNTU: - snprintf(name, size, "/usr/lib/debug%s", - self->long_name); - break; - case DSO__ORIG_BUILDID: { - char build_id_hex[BUILD_ID_SIZE * 2 + 1]; - - if (!self->has_build_id) - continue; - - build_id__sprintf(self->build_id, - sizeof(self->build_id), - build_id_hex); - snprintf(name, size, - "/usr/lib/debug/.build-id/%.2s/%s.debug", - build_id_hex, build_id_hex + 2); - } - break; - case DSO__ORIG_DSO: - snprintf(name, size, "%s", self->long_name); - break; - case DSO__ORIG_GUEST_KMODULE: - if (map->groups && map->groups->machine) - root_dir = map->groups->machine->root_dir; - else - root_dir = ""; - snprintf(name, size, "%s%s", root_dir, self->long_name); - break; + for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) { + struct symsrc *ss = &ss_[ss_pos]; + bool next_slot = false; - default: - /* - * If we wanted a full symtab but no image had one, - * relax our requirements and repeat the search. - */ - if (want_symtab) { - want_symtab = 0; - self->origin = DSO__ORIG_BUILD_ID_CACHE; - } else - continue; - } + enum dso_binary_type symtab_type = binary_type_symtab[i]; - /* Name is now the name of the next image to try */ - fd = open(name, O_RDONLY); - if (fd < 0) + if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type)) continue; - ret = dso__load_sym(self, map, name, fd, filter, 0, - want_symtab); - close(fd); + if (dso__read_binary_type_filename(dso, symtab_type, + root_dir, name, PATH_MAX)) + continue; - /* - * Some people seem to have debuginfo files _WITHOUT_ debug - * info!?!? - */ - if (!ret) + /* Name is now the name of the next image to try */ + if (symsrc__init(ss, dso, name, symtab_type) < 0) continue; - if (ret > 0) { - int nr_plt = dso__synthesize_plt_symbols(self, map, filter); - if (nr_plt > 0) - ret += nr_plt; - break; + if (!syms_ss && symsrc__has_symtab(ss)) { + syms_ss = ss; + next_slot = true; + if (!dso->symsrc_filename) + dso->symsrc_filename = strdup(name); + } + + if (!runtime_ss && symsrc__possibly_runtime(ss)) { + runtime_ss = ss; + next_slot = true; + } + + if (next_slot) { + ss_pos++; + + if (syms_ss && runtime_ss) + break; + } else { + symsrc__destroy(ss); } + + } + + if (!runtime_ss && !syms_ss) + goto out_free; + + if (runtime_ss && !syms_ss) { + syms_ss = runtime_ss; } + /* We'll have to hope for the best */ + if (!runtime_ss && syms_ss) + runtime_ss = syms_ss; + + if (syms_ss) + ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod); + else + ret = -1; + + if (ret > 0) { + int nr_plt; + + nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map, filter); + if (nr_plt > 0) + ret += nr_plt; + } + + for (; ss_pos > 0; ss_pos--) + symsrc__destroy(&ss_[ss_pos - 1]); +out_free: free(name); - if (ret < 0 && strstr(self->name, " (deleted)") != NULL) + if (ret < 0 && strstr(dso->name, " (deleted)") != NULL) return 0; return ret; } -struct map *map_groups__find_by_name(struct map_groups *self, +struct map *map_groups__find_by_name(struct map_groups *mg, enum map_type type, const char *name) { struct rb_node *nd; - for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) { struct map *map = rb_entry(nd, struct map, rb_node); if (map->dso && strcmp(map->dso->short_name, name) == 0) @@ -1537,299 +1439,184 @@ struct map *map_groups__find_by_name(struct map_groups *self, return NULL; } -static int dso__kernel_module_get_build_id(struct dso *self, - const char *root_dir) +int dso__load_vmlinux(struct dso *dso, struct map *map, + const char *vmlinux, bool vmlinux_allocated, + symbol_filter_t filter) { - char filename[PATH_MAX]; - /* - * kernel module short names are of the form "[module]" and - * we need just "module" here. - */ - const char *name = self->short_name + 1; - - snprintf(filename, sizeof(filename), - "%s/sys/module/%.*s/notes/.note.gnu.build-id", - root_dir, (int)strlen(name) - 1, name); - - if (sysfs__read_build_id(filename, self->build_id, - sizeof(self->build_id)) == 0) - self->has_build_id = true; + int err = -1; + struct symsrc ss; + char symfs_vmlinux[PATH_MAX]; + enum dso_binary_type symtab_type; - return 0; -} + if (vmlinux[0] == '/') + snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux); + else + snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s", + symbol_conf.symfs, vmlinux); -static int map_groups__set_modules_path_dir(struct map_groups *self, - const char *dir_name) -{ - struct dirent *dent; - DIR *dir = opendir(dir_name); - int ret = 0; + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX; + else + symtab_type = DSO_BINARY_TYPE__VMLINUX; - if (!dir) { - pr_debug("%s: cannot open %s dir\n", __func__, dir_name); + if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type)) return -1; - } - - while ((dent = readdir(dir)) != NULL) { - char path[PATH_MAX]; - struct stat st; - /*sshfs might return bad dent->d_type, so we have to stat*/ - sprintf(path, "%s/%s", dir_name, dent->d_name); - if (stat(path, &st)) - continue; + err = dso__load_sym(dso, map, &ss, &ss, filter, 0); + symsrc__destroy(&ss); - if (S_ISDIR(st.st_mode)) { - if (!strcmp(dent->d_name, ".") || - !strcmp(dent->d_name, "..")) - continue; - - snprintf(path, sizeof(path), "%s/%s", - dir_name, dent->d_name); - ret = map_groups__set_modules_path_dir(self, path); - if (ret < 0) - goto out; - } else { - char *dot = strrchr(dent->d_name, '.'), - dso_name[PATH_MAX]; - struct map *map; - char *long_name; - - if (dot == NULL || strcmp(dot, ".ko")) - continue; - snprintf(dso_name, sizeof(dso_name), "[%.*s]", - (int)(dot - dent->d_name), dent->d_name); - - strxfrchar(dso_name, '-', '_'); - map = map_groups__find_by_name(self, MAP__FUNCTION, dso_name); - if (map == NULL) - continue; - - snprintf(path, sizeof(path), "%s/%s", - dir_name, dent->d_name); - - long_name = strdup(path); - if (long_name == NULL) { - ret = -1; - goto out; - } - dso__set_long_name(map->dso, long_name); - map->dso->lname_alloc = 1; - dso__kernel_module_get_build_id(map->dso, ""); - } + if (err > 0) { + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX; + else + dso->binary_type = DSO_BINARY_TYPE__VMLINUX; + dso__set_long_name(dso, vmlinux, vmlinux_allocated); + dso__set_loaded(dso, map->type); + pr_debug("Using %s for symbols\n", symfs_vmlinux); } -out: - closedir(dir); - return ret; + return err; } -static char *get_kernel_version(const char *root_dir) +int dso__load_vmlinux_path(struct dso *dso, struct map *map, + symbol_filter_t filter) { - char version[PATH_MAX]; - FILE *file; - char *name, *tmp; - const char *prefix = "Linux version "; - - sprintf(version, "%s/proc/version", root_dir); - file = fopen(version, "r"); - if (!file) - return NULL; + int i, err = 0; + char *filename; - version[0] = '\0'; - tmp = fgets(version, sizeof(version), file); - fclose(file); + pr_debug("Looking at the vmlinux_path (%d entries long)\n", + vmlinux_path__nr_entries + 1); - name = strstr(version, prefix); - if (!name) - return NULL; - name += strlen(prefix); - tmp = strchr(name, ' '); - if (tmp) - *tmp = '\0'; + filename = dso__build_id_filename(dso, NULL, 0); + if (filename != NULL) { + err = dso__load_vmlinux(dso, map, filename, true, filter); + if (err > 0) + goto out; + free(filename); + } - return strdup(name); + for (i = 0; i < vmlinux_path__nr_entries; ++i) { + err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter); + if (err > 0) + break; + } +out: + return err; } -static int machine__set_modules_path(struct machine *self) +static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz) { - char *version; - char modules_path[PATH_MAX]; + char kallsyms_filename[PATH_MAX]; + struct dirent *dent; + int ret = -1; + DIR *d; - version = get_kernel_version(self->root_dir); - if (!version) + d = opendir(dir); + if (!d) return -1; - snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel", - self->root_dir, version); - free(version); - - return map_groups__set_modules_path_dir(&self->kmaps, modules_path); -} - -/* - * Constructor variant for modules (where we know from /proc/modules where - * they are loaded) and for vmlinux, where only after we load all the - * symbols we'll know where it starts and ends. - */ -static struct map *map__new2(u64 start, struct dso *dso, enum map_type type) -{ - struct map *self = calloc(1, (sizeof(*self) + - (dso->kernel ? sizeof(struct kmap) : 0))); - if (self != NULL) { - /* - * ->end will be filled after we load all the symbols - */ - map__init(self, type, start, 0, 0, dso); + 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_addresses(kallsyms_filename, map)) { + strlcpy(dir, kallsyms_filename, dir_sz); + ret = 0; + break; + } } - return self; -} + closedir(d); -struct map *machine__new_module(struct machine *self, u64 start, - const char *filename) -{ - struct map *map; - struct dso *dso = __dsos__findnew(&self->kernel_dsos, filename); - - if (dso == NULL) - return NULL; - - map = map__new2(start, dso, MAP__FUNCTION); - if (map == NULL) - return NULL; - - if (machine__is_host(self)) - dso->origin = DSO__ORIG_KMODULE; - else - dso->origin = DSO__ORIG_GUEST_KMODULE; - map_groups__insert(&self->kmaps, map); - return map; + return ret; } -static int machine__create_modules(struct machine *self) +static char *dso__find_kallsyms(struct dso *dso, struct map *map) { - char *line = NULL; - size_t n; - FILE *file; - struct map *map; - const char *modules; + u8 host_build_id[BUILD_ID_SIZE]; + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + bool is_host = false; char path[PATH_MAX]; - if (machine__is_default_guest(self)) - modules = symbol_conf.default_guest_modules; - else { - sprintf(path, "%s/proc/modules", self->root_dir); - modules = path; + 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; } - file = fopen(modules, "r"); - if (file == NULL) - return -1; + 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); - while (!feof(file)) { - char name[PATH_MAX]; - u64 start; - char *sep; - int line_len; + build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); - line_len = getline(&line, &n, file); - if (line_len < 0) - break; + scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir, + sbuild_id); - if (!line) - goto out_failure; + /* Use /proc/kallsyms if possible */ + if (is_host) { + DIR *d; + int fd; - line[--line_len] = '\0'; /* \n */ + /* If no cached kcore go with /proc/kallsyms */ + d = opendir(path); + if (!d) + goto proc_kallsyms; + closedir(d); - sep = strrchr(line, 'x'); - if (sep == NULL) - continue; - - hex2u64(sep + 1, &start); + /* + * 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_addresses("/proc/kallsyms", map)) + goto proc_kallsyms; + } - sep = strchr(line, ' '); - if (sep == NULL) - continue; + /* Find kallsyms in build-id cache with kcore */ + if (!find_matching_kcore(map, path, sizeof(path))) + return strdup(path); - *sep = '\0'; - - snprintf(name, sizeof(name), "[%s]", line); - map = machine__new_module(self, start, name); - if (map == NULL) - goto out_delete_line; - dso__kernel_module_get_build_id(map->dso, self->root_dir); + goto proc_kallsyms; } - free(line); - fclose(file); - - return machine__set_modules_path(self); + /* Find kallsyms in build-id cache with kcore */ + if (!find_matching_kcore(map, path, sizeof(path))) + return strdup(path); -out_delete_line: - free(line); -out_failure: - return -1; -} - -static int dso__load_vmlinux(struct dso *self, struct map *map, - const char *vmlinux, symbol_filter_t filter) -{ - int err = -1, fd; - - fd = open(vmlinux, O_RDONLY); - if (fd < 0) - return -1; + scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s", + buildid_dir, sbuild_id); - dso__set_loaded(self, map->type); - err = dso__load_sym(self, map, vmlinux, fd, filter, 0, 0); - close(fd); - - if (err > 0) - pr_debug("Using %s for symbols\n", vmlinux); - - return err; -} - -int dso__load_vmlinux_path(struct dso *self, struct map *map, - symbol_filter_t filter) -{ - int i, err = 0; - char *filename; - - pr_debug("Looking at the vmlinux_path (%d entries long)\n", - vmlinux_path__nr_entries + 1); - - filename = dso__build_id_filename(self, NULL, 0); - if (filename != NULL) { - err = dso__load_vmlinux(self, map, filename, filter); - if (err > 0) { - dso__set_long_name(self, filename); - goto out; - } - free(filename); + if (access(path, F_OK)) { + pr_err("No kallsyms or vmlinux with build-id %s was found\n", + sbuild_id); + return NULL; } - for (i = 0; i < vmlinux_path__nr_entries; ++i) { - err = dso__load_vmlinux(self, map, vmlinux_path[i], filter); - if (err > 0) { - dso__set_long_name(self, strdup(vmlinux_path[i])); - break; - } - } -out: - return err; + return strdup(path); + +proc_kallsyms: + return strdup("/proc/kallsyms"); } -static int dso__load_kernel_sym(struct dso *self, struct map *map, +static int dso__load_kernel_sym(struct dso *dso, struct map *map, symbol_filter_t filter) { int err; const char *kallsyms_filename = NULL; char *kallsyms_allocated_filename = NULL; /* - * Step 1: if the user specified a vmlinux filename, use it and only - * it, reporting errors to the user if it cannot be used. + * Step 1: if the user specified a kallsyms or vmlinux filename, use + * it and only it, reporting errors to the user if it cannot be used. * * For instance, try to analyse an ARM perf.data file _without_ a * build-id, or if the user specifies the wrong path to the right @@ -1842,79 +1629,40 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map, * validation in dso__load_vmlinux and will bail out if they don't * match. */ - if (symbol_conf.vmlinux_name != NULL) { - err = dso__load_vmlinux(self, map, - symbol_conf.vmlinux_name, filter); - if (err > 0) { - dso__set_long_name(self, - strdup(symbol_conf.vmlinux_name)); - goto out_fixup; - } - return err; + if (symbol_conf.kallsyms_name != NULL) { + kallsyms_filename = symbol_conf.kallsyms_name; + goto do_kallsyms; } - if (vmlinux_path != NULL) { - err = dso__load_vmlinux_path(self, map, filter); - if (err > 0) - goto out_fixup; + if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) { + return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, + false, filter); } - /* - * 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 (self->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(self, 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(self->build_id, sizeof(self->build_id), - sbuild_id); + if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) { + err = dso__load_vmlinux_path(dso, map, filter); + if (err > 0) + return err; + } - 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; - } + /* do not try local files if a symfs was given */ + if (symbol_conf.symfs[0] != 0) + return -1; - kallsyms_filename = kallsyms_allocated_filename; + kallsyms_allocated_filename = dso__find_kallsyms(dso, map); + if (!kallsyms_allocated_filename) + return -1; - 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(self, kallsyms_filename, map, filter); + err = dso__load_kallsyms(dso, kallsyms_filename, map, filter); if (err > 0) pr_debug("Using %s for symbols\n", kallsyms_filename); free(kallsyms_allocated_filename); - if (err > 0) { -out_fixup: - if (kallsyms_filename != NULL) - dso__set_long_name(self, strdup("[kernel.kallsyms]")); + if (err > 0 && !dso__is_kcore(dso)) { + dso__set_long_name(dso, "[kernel.kallsyms]", false); map__fixup_start(map); map__fixup_end(map); } @@ -1922,8 +1670,8 @@ out_fixup: return err; } -static int dso__load_guest_kernel_sym(struct dso *self, struct map *map, - symbol_filter_t filter) +static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, + symbol_filter_t filter) { int err; const char *kallsyms_filename = NULL; @@ -1943,9 +1691,10 @@ static int dso__load_guest_kernel_sym(struct dso *self, struct map *map, * Or use file guest_kallsyms inputted by user on commandline */ if (symbol_conf.default_guest_vmlinux_name != NULL) { - err = dso__load_vmlinux(self, map, - symbol_conf.default_guest_vmlinux_name, filter); - goto out_try_fixup; + err = dso__load_vmlinux(dso, map, + symbol_conf.default_guest_vmlinux_name, + false, filter); + return err; } kallsyms_filename = symbol_conf.default_guest_kallsyms; @@ -1956,16 +1705,12 @@ static int dso__load_guest_kernel_sym(struct dso *self, struct map *map, kallsyms_filename = path; } - err = dso__load_kallsyms(self, kallsyms_filename, map, filter); + 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(self, strdup(path)); - } + if (err > 0 && !dso__is_kcore(dso)) { + machine__mmap_name(machine, path, sizeof(path)); + dso__set_long_name(dso, strdup(path), true); map__fixup_start(map); map__fixup_end(map); } @@ -1973,234 +1718,12 @@ out_try_fixup: return err; } -static void dsos__add(struct list_head *head, struct dso *dso) -{ - list_add_tail(&dso->node, head); -} - -static struct dso *dsos__find(struct list_head *head, const char *name) -{ - struct dso *pos; - - list_for_each_entry(pos, head, node) - if (strcmp(pos->long_name, name) == 0) - return pos; - return NULL; -} - -struct dso *__dsos__findnew(struct list_head *head, const char *name) -{ - struct dso *dso = dsos__find(head, name); - - if (!dso) { - dso = dso__new(name); - if (dso != NULL) { - dsos__add(head, dso); - dso__set_basename(dso); - } - } - - return dso; -} - -size_t __dsos__fprintf(struct list_head *head, FILE *fp) -{ - struct dso *pos; - size_t ret = 0; - - list_for_each_entry(pos, head, node) { - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - ret += dso__fprintf(pos, i, fp); - } - - return ret; -} - -size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp) -{ - struct rb_node *nd; - size_t ret = 0; - - for (nd = rb_first(self); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret += __dsos__fprintf(&pos->kernel_dsos, fp); - ret += __dsos__fprintf(&pos->user_dsos, fp); - } - - return ret; -} - -static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, - bool with_hits) -{ - struct dso *pos; - size_t ret = 0; - - list_for_each_entry(pos, head, node) { - if (with_hits && !pos->hit) - continue; - ret += dso__fprintf_buildid(pos, fp); - ret += fprintf(fp, " %s\n", pos->long_name); - } - return ret; -} - -size_t machine__fprintf_dsos_buildid(struct machine *self, FILE *fp, bool with_hits) -{ - return __dsos__fprintf_buildid(&self->kernel_dsos, fp, with_hits) + - __dsos__fprintf_buildid(&self->user_dsos, fp, with_hits); -} - -size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits) -{ - struct rb_node *nd; - size_t ret = 0; - - for (nd = rb_first(self); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret += machine__fprintf_dsos_buildid(pos, fp, with_hits); - } - return ret; -} - -struct dso *dso__new_kernel(const char *name) -{ - struct dso *self = dso__new(name ?: "[kernel.kallsyms]"); - - if (self != NULL) { - dso__set_short_name(self, "[kernel]"); - self->kernel = DSO_TYPE_KERNEL; - } - - return self; -} - -static struct dso *dso__new_guest_kernel(struct machine *machine, - const char *name) -{ - char bf[PATH_MAX]; - struct dso *self = dso__new(name ?: machine__mmap_name(machine, bf, sizeof(bf))); - - if (self != NULL) { - dso__set_short_name(self, "[guest.kernel]"); - self->kernel = DSO_TYPE_GUEST_KERNEL; - } - - return self; -} - -void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine) -{ - char path[PATH_MAX]; - - if (machine__is_default_guest(machine)) - return; - sprintf(path, "%s/sys/kernel/notes", machine->root_dir); - if (sysfs__read_build_id(path, self->build_id, - sizeof(self->build_id)) == 0) - self->has_build_id = true; -} - -static struct dso *machine__create_kernel(struct machine *self) -{ - const char *vmlinux_name = NULL; - struct dso *kernel; - - if (machine__is_host(self)) { - vmlinux_name = symbol_conf.vmlinux_name; - kernel = dso__new_kernel(vmlinux_name); - } else { - if (machine__is_default_guest(self)) - vmlinux_name = symbol_conf.default_guest_vmlinux_name; - kernel = dso__new_guest_kernel(self, vmlinux_name); - } - - if (kernel != NULL) { - dso__read_running_kernel_build_id(kernel, self); - dsos__add(&self->kernel_dsos, kernel); - } - return kernel; -} - -int __machine__create_kernel_maps(struct machine *self, struct dso *kernel) -{ - enum map_type type; - - for (type = 0; type < MAP__NR_TYPES; ++type) { - struct kmap *kmap; - - self->vmlinux_maps[type] = map__new2(0, kernel, type); - if (self->vmlinux_maps[type] == NULL) - return -1; - - self->vmlinux_maps[type]->map_ip = - self->vmlinux_maps[type]->unmap_ip = identity__map_ip; - - kmap = map__kmap(self->vmlinux_maps[type]); - kmap->kmaps = &self->kmaps; - map_groups__insert(&self->kmaps, self->vmlinux_maps[type]); - } - - return 0; -} - -void machine__destroy_kernel_maps(struct machine *self) -{ - enum map_type type; - - for (type = 0; type < MAP__NR_TYPES; ++type) { - struct kmap *kmap; - - if (self->vmlinux_maps[type] == NULL) - continue; - - kmap = map__kmap(self->vmlinux_maps[type]); - map_groups__remove(&self->kmaps, self->vmlinux_maps[type]); - if (kmap->ref_reloc_sym) { - /* - * ref_reloc_sym is shared among all maps, so free just - * on one of them. - */ - if (type == MAP__FUNCTION) { - free((char *)kmap->ref_reloc_sym->name); - kmap->ref_reloc_sym->name = NULL; - free(kmap->ref_reloc_sym); - } - kmap->ref_reloc_sym = NULL; - } - - map__delete(self->vmlinux_maps[type]); - self->vmlinux_maps[type] = NULL; - } -} - -int machine__create_kernel_maps(struct machine *self) -{ - struct dso *kernel = machine__create_kernel(self); - - if (kernel == NULL || - __machine__create_kernel_maps(self, kernel) < 0) - return -1; - - if (symbol_conf.use_modules && machine__create_modules(self) < 0) - pr_debug("Problems creating module maps, continuing anyway...\n"); - /* - * Now that we have all the maps created, just set the ->end of them: - */ - map_groups__fixup_end(&self->kmaps); - return 0; -} - static void vmlinux_path__exit(void) { - while (--vmlinux_path__nr_entries >= 0) { - free(vmlinux_path[vmlinux_path__nr_entries]); - vmlinux_path[vmlinux_path__nr_entries] = NULL; - } + while (--vmlinux_path__nr_entries >= 0) + zfree(&vmlinux_path[vmlinux_path__nr_entries]); - free(vmlinux_path); - vmlinux_path = NULL; + zfree(&vmlinux_path); } static int vmlinux_path__init(void) @@ -2208,9 +1731,6 @@ static int vmlinux_path__init(void) struct utsname uts; char bf[PATH_MAX]; - if (uname(&uts) < 0) - return -1; - vmlinux_path = malloc(sizeof(char *) * 5); if (vmlinux_path == NULL) return -1; @@ -2223,6 +1743,14 @@ static int vmlinux_path__init(void) if (vmlinux_path[vmlinux_path__nr_entries] == NULL) goto out_fail; ++vmlinux_path__nr_entries; + + /* only try running kernel version if no symfs was given */ + if (symbol_conf.symfs[0] != 0) + return 0; + + if (uname(&uts) < 0) + return -1; + snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release); vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); if (vmlinux_path[vmlinux_path__nr_entries] == NULL) @@ -2247,26 +1775,7 @@ out_fail: return -1; } -size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp) -{ - int i; - size_t printed = 0; - struct dso *kdso = self->vmlinux_maps[MAP__FUNCTION]->dso; - - if (kdso->has_build_id) { - char filename[PATH_MAX]; - if (dso__build_id_filename(kdso, filename, sizeof(filename))) - printed += fprintf(fp, "[0] %s\n", filename); - } - - for (i = 0; i < vmlinux_path__nr_entries; ++i) - printed += fprintf(fp, "[%d] %s\n", - i + kdso->has_build_id, vmlinux_path[i]); - - return printed; -} - -static int setup_list(struct strlist **list, const char *list_str, +int setup_list(struct strlist **list, const char *list_str, const char *list_name) { if (list_str == NULL) @@ -2280,12 +1789,36 @@ static int setup_list(struct strlist **list, const char *list_str, return 0; } +static bool symbol__read_kptr_restrict(void) +{ + bool value = false; + + if (geteuid() != 0) { + FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r"); + if (fp != NULL) { + char line[8]; + + if (fgets(line, sizeof(line), fp) != NULL) + value = atoi(line) != 0; + + fclose(fp); + } + } + + return value; +} + int symbol__init(void) { + const char *symfs; + if (symbol_conf.initialized) return 0; - elf_version(EV_CURRENT); + symbol_conf.priv_size = PERF_ALIGN(symbol_conf.priv_size, sizeof(u64)); + + symbol__elf_init(); + if (symbol_conf.sort_by_name) symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) - sizeof(struct symbol)); @@ -2310,13 +1843,27 @@ int symbol__init(void) symbol_conf.sym_list_str, "symbol") < 0) goto out_free_comm_list; + /* + * A path to symbols of "/" is identical to "" + * reset here for simplicity. + */ + symfs = realpath(symbol_conf.symfs, NULL); + if (symfs == NULL) + symfs = symbol_conf.symfs; + if (strcmp(symfs, "/") == 0) + symbol_conf.symfs = ""; + if (symfs != symbol_conf.symfs) + free((void *)symfs); + + symbol_conf.kptr_restrict = symbol__read_kptr_restrict(); + symbol_conf.initialized = true; return 0; -out_free_dso_list: - strlist__delete(symbol_conf.dso_list); out_free_comm_list: strlist__delete(symbol_conf.comm_list); +out_free_dso_list: + strlist__delete(symbol_conf.dso_list); return -1; } @@ -2331,143 +1878,3 @@ void symbol__exit(void) symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL; symbol_conf.initialized = false; } - -int machines__create_kernel_maps(struct rb_root *self, pid_t pid) -{ - struct machine *machine = machines__findnew(self, pid); - - if (machine == NULL) - return -1; - - return machine__create_kernel_maps(machine); -} - -static int hex(char ch) -{ - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - if ((ch >= 'A') && (ch <= 'F')) - return ch - 'A' + 10; - return -1; -} - -/* - * While we find nice hex chars, build a long_val. - * Return number of chars processed. - */ -int hex2u64(const char *ptr, u64 *long_val) -{ - const char *p = ptr; - *long_val = 0; - - while (*p) { - const int hex_val = hex(*p); - - if (hex_val < 0) - break; - - *long_val = (*long_val << 4) | hex_val; - p++; - } - - return p - ptr; -} - -char *strxfrchar(char *s, char from, char to) -{ - char *p = s; - - while ((p = strchr(p, from)) != NULL) - *p++ = to; - - return s; -} - -int machines__create_guest_kernel_maps(struct rb_root *self) -{ - int ret = 0; - struct dirent **namelist = NULL; - int i, items = 0; - char path[PATH_MAX]; - pid_t pid; - - if (symbol_conf.default_guest_vmlinux_name || - symbol_conf.default_guest_modules || - symbol_conf.default_guest_kallsyms) { - machines__create_kernel_maps(self, DEFAULT_GUEST_KERNEL_ID); - } - - if (symbol_conf.guestmount) { - items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL); - if (items <= 0) - return -ENOENT; - for (i = 0; i < items; i++) { - if (!isdigit(namelist[i]->d_name[0])) { - /* Filter out . and .. */ - continue; - } - pid = atoi(namelist[i]->d_name); - sprintf(path, "%s/%s/proc/kallsyms", - symbol_conf.guestmount, - namelist[i]->d_name); - ret = access(path, R_OK); - if (ret) { - pr_debug("Can't access file %s\n", path); - goto failure; - } - machines__create_kernel_maps(self, pid); - } -failure: - free(namelist); - } - - return ret; -} - -void machines__destroy_guest_kernel_maps(struct rb_root *self) -{ - struct rb_node *next = rb_first(self); - - while (next) { - struct machine *pos = rb_entry(next, struct machine, rb_node); - - next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, self); - machine__delete(pos); - } -} - -int machine__load_kallsyms(struct machine *self, const char *filename, - enum map_type type, symbol_filter_t filter) -{ - struct map *map = self->vmlinux_maps[type]; - int ret = dso__load_kallsyms(map->dso, filename, map, filter); - - if (ret > 0) { - dso__set_loaded(map->dso, type); - /* - * Since /proc/kallsyms will have multiple sessions for the - * kernel, with modules between them, fixup the end of all - * sections. - */ - __map_groups__fixup_end(&self->kmaps, type); - } - - return ret; -} - -int machine__load_vmlinux_path(struct machine *self, enum map_type type, - symbol_filter_t filter) -{ - struct map *map = self->vmlinux_maps[type]; - int ret = dso__load_vmlinux_path(map->dso, map, filter); - - if (ret > 0) { - dso__set_loaded(map->dso, type); - map__reloc_vmlinux(map); - } - - return ret; -} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 038f2201ee0..615c752dd76 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -5,40 +5,57 @@ #include <stdbool.h> #include <stdint.h> #include "map.h" +#include "../perf.h" #include <linux/list.h> #include <linux/rbtree.h> #include <stdio.h> +#include <byteswap.h> +#include <libgen.h> +#include "build-id.h" +#include "event.h" + +#ifdef HAVE_LIBELF_SUPPORT +#include <libelf.h> +#include <gelf.h> +#endif +#include <elf.h> + +#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 __used *v, const char *c, int i) +static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i) { return cplus_demangle(c, i); } #else #ifdef NO_DEMANGLE -static inline char *bfd_demangle(void __used *v, const char __used *c, - int __used i) +static inline char *bfd_demangle(void __maybe_unused *v, + const char __maybe_unused *c, + int __maybe_unused i) { return NULL; } #else +#define PACKAGE 'perf' #include <bfd.h> #endif #endif -int hex2u64(const char *ptr, u64 *val); -char *strxfrchar(char *s, char from, char to); - /* * 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_NO_MMAP -# define PERF_ELF_C_READ_MMAP ELF_C_READ -#else +#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 +#endif + +#ifdef HAVE_LIBELF_SUPPORT +extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, + GElf_Shdr *shp, const char *name, size_t *idx); #endif #ifndef DMGL_PARAMS @@ -46,32 +63,64 @@ char *strxfrchar(char *s, char from, char to); #define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ #endif -#define BUILD_ID_SIZE 20 - +/** struct symbol - symtab entry + * + * @ignore - resolvable but tools ignore it (e.g. idle routines) + */ struct symbol { struct rb_node rb_node; u64 start; u64 end; u16 namelen; u8 binding; + bool ignore; char name[0]; }; -void symbol__delete(struct symbol *self); +void symbol__delete(struct symbol *sym); +void symbols__delete(struct rb_root *symbols); + +/* symbols__for_each_entry - iterate over symbols (rb_root) + * + * @symbols: the rb_root of symbols + * @pos: the 'struct symbol *' to use as a loop cursor + * @nd: the 'struct rb_node *' to use as a temporary storage + */ +#define symbols__for_each_entry(symbols, pos, nd) \ + for (nd = rb_first(symbols); \ + nd && (pos = rb_entry(nd, struct symbol, rb_node)); \ + nd = rb_next(nd)) + +static inline size_t symbol__size(const struct symbol *sym) +{ + return sym->end - sym->start + 1; +} struct strlist; 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, show_nr_samples, + show_total_period, use_callchain, + cumulate_callchain, exclude_other, show_cpu_utilization, - initialized; + initialized, + kptr_restrict, + annotate_asm_raw, + annotate_src, + event_group, + demangle, + filter_relative; const char *vmlinux_name, + *kallsyms_name, *source_prefix, *field_sep; const char *default_guest_vmlinux_name, @@ -84,14 +133,21 @@ struct symbol_conf { *col_width_list_str; struct strlist *dso_list, *comm_list, - *sym_list; + *sym_list, + *dso_from_list, + *dso_to_list, + *sym_from_list, + *sym_to_list; + const char *symfs; }; extern struct symbol_conf symbol_conf; +extern int vmlinux_path__nr_entries; +extern char **vmlinux_path; -static inline void *symbol__priv(struct symbol *self) +static inline void *symbol__priv(struct symbol *sym) { - return ((void *)self) - symbol_conf.priv_size; + return ((void *)sym) - symbol_conf.priv_size; } struct ref_reloc_sym { @@ -107,126 +163,135 @@ struct map_symbol { bool has_children; }; +struct addr_map_symbol { + struct map *map; + struct symbol *sym; + u64 addr; + u64 al_addr; +}; + +struct branch_info { + struct addr_map_symbol from; + struct addr_map_symbol to; + struct branch_flags flags; +}; + +struct mem_info { + struct addr_map_symbol iaddr; + struct addr_map_symbol daddr; + union perf_mem_data_src data_src; +}; + struct addr_location { + struct machine *machine; struct thread *thread; struct map *map; struct symbol *sym; u64 addr; char level; - bool filtered; + u8 filtered; u8 cpumode; s32 cpu; }; -enum dso_kernel_type { - DSO_TYPE_USER = 0, - DSO_TYPE_KERNEL, - DSO_TYPE_GUEST_KERNEL -}; - -struct dso { - struct list_head node; - struct rb_root symbols[MAP__NR_TYPES]; - struct rb_root symbol_names[MAP__NR_TYPES]; - enum dso_kernel_type kernel; - u8 adjust_symbols:1; - u8 slen_calculated:1; - u8 has_build_id:1; - u8 hit:1; - u8 annotate_warned:1; - u8 sname_alloc:1; - u8 lname_alloc:1; - unsigned char origin; - u8 sorted_by_name; - u8 loaded; - u8 build_id[BUILD_ID_SIZE]; - const char *short_name; - char *long_name; - u16 long_name_len; - u16 short_name_len; - char name[0]; -}; +struct symsrc { + char *name; + int fd; + enum dso_binary_type type; -struct dso *dso__new(const char *name); -struct dso *dso__new_kernel(const char *name); -void dso__delete(struct dso *self); +#ifdef HAVE_LIBELF_SUPPORT + Elf *elf; + GElf_Ehdr ehdr; -int dso__name_len(const struct dso *self); + Elf_Scn *opdsec; + size_t opdidx; + GElf_Shdr opdshdr; -bool dso__loaded(const struct dso *self, enum map_type type); -bool dso__sorted_by_name(const struct dso *self, enum map_type type); + Elf_Scn *symtab; + GElf_Shdr symshdr; -static inline void dso__set_loaded(struct dso *self, enum map_type type) -{ - self->loaded |= (1 << type); -} + Elf_Scn *dynsym; + size_t dynsym_idx; + GElf_Shdr dynshdr; -void dso__sort_by_name(struct dso *self, enum map_type type); - -struct dso *__dsos__findnew(struct list_head *head, const char *name); + bool adjust_symbols; +#endif +}; -int dso__load(struct dso *self, struct map *map, symbol_filter_t filter); -int dso__load_vmlinux_path(struct dso *self, struct map *map, +void symsrc__destroy(struct symsrc *ss); +int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, + enum dso_binary_type type); +bool symsrc__has_symtab(struct symsrc *ss); +bool symsrc__possibly_runtime(struct symsrc *ss); + +int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter); +int dso__load_vmlinux(struct dso *dso, struct map *map, + const char *vmlinux, bool vmlinux_allocated, + symbol_filter_t filter); +int dso__load_vmlinux_path(struct dso *dso, struct map *map, symbol_filter_t filter); -int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map, +int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, symbol_filter_t filter); -int machine__load_kallsyms(struct machine *self, const char *filename, - enum map_type type, symbol_filter_t filter); -int machine__load_vmlinux_path(struct machine *self, enum map_type type, - symbol_filter_t filter); - -size_t __dsos__fprintf(struct list_head *head, FILE *fp); - -size_t machine__fprintf_dsos_buildid(struct machine *self, FILE *fp, bool with_hits); -size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp); -size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits); - -size_t dso__fprintf_buildid(struct dso *self, FILE *fp); -size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp); -size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp); - -enum dso_origin { - DSO__ORIG_KERNEL = 0, - DSO__ORIG_GUEST_KERNEL, - DSO__ORIG_JAVA_JIT, - DSO__ORIG_BUILD_ID_CACHE, - DSO__ORIG_FEDORA, - DSO__ORIG_UBUNTU, - DSO__ORIG_BUILDID, - DSO__ORIG_DSO, - DSO__ORIG_GUEST_KMODULE, - DSO__ORIG_KMODULE, - DSO__ORIG_NOT_FOUND, -}; -char dso__symtab_origin(const struct dso *self); -void dso__set_long_name(struct dso *self, char *name); -void dso__set_build_id(struct dso *self, void *build_id); -void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine); -struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr); -struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type, +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); 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); -bool __dsos__read_build_ids(struct list_head *head, bool with_hits); -int build_id__sprintf(const u8 *self, int len, char *bf); -int kallsyms__parse(const char *filename, void *arg, - int (*process_symbol)(void *arg, const char *name, - char type, u64 start)); - -void machine__destroy_kernel_maps(struct machine *self); -int __machine__create_kernel_maps(struct machine *self, struct dso *kernel); -int machine__create_kernel_maps(struct machine *self); - -int machines__create_kernel_maps(struct rb_root *self, pid_t pid); -int machines__create_guest_kernel_maps(struct rb_root *self); -void machines__destroy_guest_kernel_maps(struct rb_root *self); +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); int symbol__init(void); void symbol__exit(void); +void symbol__elf_init(void); +struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name); +size_t symbol__fprintf_symname_offs(const struct symbol *sym, + const struct addr_location *al, FILE *fp); +size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); +size_t symbol__fprintf(struct symbol *sym, FILE *fp); bool symbol_type__is_a(char symbol_type, enum map_type map_type); +bool symbol__restricted_filename(const char *filename, + const char *restricted_filename); +bool symbol__is_idle(struct symbol *sym); + +int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, + struct symsrc *runtime_ss, symbol_filter_t filter, + int kmodule); +int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, + struct map *map, symbol_filter_t filter); + +void symbols__insert(struct rb_root *symbols, struct symbol *sym); +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); -size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp); +int setup_list(struct strlist **list, const char *list_str, + const char *list_name); #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c new file mode 100644 index 00000000000..e74c5963dc7 --- /dev/null +++ b/tools/perf/util/target.c @@ -0,0 +1,158 @@ +/* + * Helper functions for handling target threads/cpus + * + * Copyright (C) 2012, LG Electronics, Namhyung Kim <namhyung.kim@lge.com> + * + * Released under the GPL v2. + */ + +#include "target.h" +#include "debug.h" + +#include <pwd.h> +#include <string.h> + + +enum target_errno target__validate(struct target *target) +{ + enum target_errno ret = TARGET_ERRNO__SUCCESS; + + if (target->pid) + target->tid = target->pid; + + /* CPU and PID are mutually exclusive */ + if (target->tid && target->cpu_list) { + target->cpu_list = NULL; + if (ret == TARGET_ERRNO__SUCCESS) + ret = TARGET_ERRNO__PID_OVERRIDE_CPU; + } + + /* UID and PID are mutually exclusive */ + if (target->tid && target->uid_str) { + target->uid_str = NULL; + if (ret == TARGET_ERRNO__SUCCESS) + ret = TARGET_ERRNO__PID_OVERRIDE_UID; + } + + /* UID and CPU are mutually exclusive */ + if (target->uid_str && target->cpu_list) { + target->cpu_list = NULL; + if (ret == TARGET_ERRNO__SUCCESS) + ret = TARGET_ERRNO__UID_OVERRIDE_CPU; + } + + /* PID and SYSTEM are mutually exclusive */ + if (target->tid && target->system_wide) { + target->system_wide = false; + if (ret == TARGET_ERRNO__SUCCESS) + ret = TARGET_ERRNO__PID_OVERRIDE_SYSTEM; + } + + /* UID and SYSTEM are mutually exclusive */ + if (target->uid_str && target->system_wide) { + target->system_wide = false; + if (ret == TARGET_ERRNO__SUCCESS) + ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM; + } + + /* THREAD and SYSTEM/CPU are mutually exclusive */ + if (target->per_thread && (target->system_wide || target->cpu_list)) { + target->per_thread = false; + if (ret == TARGET_ERRNO__SUCCESS) + ret = TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD; + } + + return ret; +} + +enum target_errno target__parse_uid(struct target *target) +{ + struct passwd pwd, *result; + char buf[1024]; + const char *str = target->uid_str; + + target->uid = UINT_MAX; + if (str == NULL) + return TARGET_ERRNO__SUCCESS; + + /* Try user name first */ + getpwnam_r(str, &pwd, buf, sizeof(buf), &result); + + if (result == NULL) { + /* + * The user name not found. Maybe it's a UID number. + */ + char *endptr; + int uid = strtol(str, &endptr, 10); + + if (*endptr != '\0') + return TARGET_ERRNO__INVALID_UID; + + getpwuid_r(uid, &pwd, buf, sizeof(buf), &result); + + if (result == NULL) + return TARGET_ERRNO__USER_NOT_FOUND; + } + + target->uid = result->pw_uid; + return TARGET_ERRNO__SUCCESS; +} + +/* + * This must have a same ordering as the enum target_errno. + */ +static const char *target__error_str[] = { + "PID/TID switch overriding CPU", + "PID/TID switch overriding UID", + "UID switch overriding CPU", + "PID/TID switch overriding SYSTEM", + "UID switch overriding SYSTEM", + "SYSTEM/CPU switch overriding PER-THREAD", + "Invalid User: %s", + "Problems obtaining information for user %s", +}; + +int target__strerror(struct target *target, int errnum, + char *buf, size_t buflen) +{ + int idx; + const char *msg; + + BUG_ON(buflen == 0); + + if (errnum >= 0) { + const char *err = strerror_r(errnum, buf, buflen); + + if (err != buf) { + size_t len = strlen(err); + memcpy(buf, err, min(buflen - 1, len)); + *(buf + min(buflen - 1, len)) = '\0'; + } + + return 0; + } + + if (errnum < __TARGET_ERRNO__START || errnum >= __TARGET_ERRNO__END) + return -1; + + idx = errnum - __TARGET_ERRNO__START; + msg = target__error_str[idx]; + + switch (errnum) { + case TARGET_ERRNO__PID_OVERRIDE_CPU ... + TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD: + snprintf(buf, buflen, "%s", msg); + break; + + case TARGET_ERRNO__INVALID_UID: + case TARGET_ERRNO__USER_NOT_FOUND: + snprintf(buf, buflen, msg, target->uid_str); + break; + + default: + /* cannot reach here */ + break; + } + + return 0; +} diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h new file mode 100644 index 00000000000..7381b1ca404 --- /dev/null +++ b/tools/perf/util/target.h @@ -0,0 +1,79 @@ +#ifndef _PERF_TARGET_H +#define _PERF_TARGET_H + +#include <stdbool.h> +#include <sys/types.h> + +struct target { + const char *pid; + const char *tid; + const char *cpu_list; + const char *uid_str; + uid_t uid; + bool system_wide; + bool uses_mmap; + bool default_per_cpu; + bool per_thread; +}; + +enum target_errno { + TARGET_ERRNO__SUCCESS = 0, + + /* + * Choose an arbitrary negative big number not to clash with standard + * errno since SUS requires the errno has distinct positive values. + * See 'Issue 6' in the link below. + * + * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html + */ + __TARGET_ERRNO__START = -10000, + + /* for target__validate() */ + TARGET_ERRNO__PID_OVERRIDE_CPU = __TARGET_ERRNO__START, + TARGET_ERRNO__PID_OVERRIDE_UID, + TARGET_ERRNO__UID_OVERRIDE_CPU, + TARGET_ERRNO__PID_OVERRIDE_SYSTEM, + TARGET_ERRNO__UID_OVERRIDE_SYSTEM, + TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD, + + /* for target__parse_uid() */ + TARGET_ERRNO__INVALID_UID, + TARGET_ERRNO__USER_NOT_FOUND, + + __TARGET_ERRNO__END, +}; + +enum target_errno target__validate(struct target *target); +enum target_errno target__parse_uid(struct target *target); + +int target__strerror(struct target *target, int errnum, char *buf, size_t buflen); + +static inline bool target__has_task(struct target *target) +{ + return target->tid || target->pid || target->uid_str; +} + +static inline bool target__has_cpu(struct target *target) +{ + return target->system_wide || target->cpu_list; +} + +static inline bool target__none(struct target *target) +{ + return !target__has_task(target) && !target__has_cpu(target); +} + +static inline bool target__uses_dummy_map(struct target *target) +{ + bool use_dummy = false; + + if (target->default_per_cpu) + use_dummy = target->per_thread ? true : false; + else if (target__has_task(target) || + (!target__has_cpu(target) && !target->uses_mmap)) + use_dummy = true; + + return use_dummy; +} + +#endif /* _PERF_TARGET_H */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 8c72d888e44..2fde0d5e40b 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -6,175 +6,188 @@ #include "thread.h" #include "util.h" #include "debug.h" +#include "comm.h" -/* Skip "." and ".." directories */ -static int filter(const struct dirent *dir) +int thread__init_map_groups(struct thread *thread, struct machine *machine) { - if (dir->d_name[0] == '.') - return 0; - else - return 1; + struct thread *leader; + pid_t pid = thread->pid_; + + if (pid == thread->tid) { + thread->mg = map_groups__new(); + } else { + leader = machine__findnew_thread(machine, pid, pid); + if (leader) + thread->mg = map_groups__get(leader->mg); + } + + return thread->mg ? 0 : -1; } -int find_all_tid(int pid, pid_t ** all_tid) +struct thread *thread__new(pid_t pid, pid_t tid) { - char name[256]; - int items; - struct dirent **namelist = NULL; - int ret = 0; - int i; - - sprintf(name, "/proc/%d/task", pid); - items = scandir(name, &namelist, filter, NULL); - if (items <= 0) - return -ENOENT; - *all_tid = malloc(sizeof(pid_t) * items); - if (!*all_tid) { - ret = -ENOMEM; - goto failure; + char *comm_str; + struct comm *comm; + struct thread *thread = zalloc(sizeof(*thread)); + + if (thread != NULL) { + 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); } - for (i = 0; i < items; i++) - (*all_tid)[i] = atoi(namelist[i]->d_name); + return thread; - ret = items; - -failure: - for (i=0; i<items; i++) - free(namelist[i]); - free(namelist); - - return ret; +err_thread: + free(thread); + return NULL; } -static struct thread *thread__new(pid_t pid) +void thread__delete(struct thread *thread) { - struct thread *self = zalloc(sizeof(*self)); - - if (self != NULL) { - map_groups__init(&self->mg); - self->pid = pid; - self->comm = malloc(32); - if (self->comm) - snprintf(self->comm, 32, ":%d", self->pid); + struct comm *comm, *tmp; + + map_groups__put(thread->mg); + thread->mg = NULL; + list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) { + list_del(&comm->list); + comm__free(comm); } - 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) { + struct comm *new, *curr = thread__comm(thread); int err; - if (self->comm) - free(self->comm); - self->comm = strdup(comm); - err = self->comm == NULL ? -ENOMEM : 0; - if (!err) { - self->comm_set = true; - map_groups__flush(&self->mg); + /* Override latest entry if it had no specific time coverage */ + if (!curr->start) { + err = comm__override(curr, str, timestamp); + if (err) + return err; + } else { + new = comm__new(str, timestamp); + if (!new) + return -ENOMEM; + list_add(&new->list, &thread->comm_list); } - return err; -} -int thread__comm_len(struct thread *self) -{ - if (!self->comm_len) { - if (!self->comm) - return 0; - self->comm_len = strlen(self->comm); - } + thread->comm_set = true; - return self->comm_len; + return 0; } -static size_t thread__fprintf(struct thread *self, FILE *fp) +const char *thread__comm_str(const struct thread *thread) { - return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) + - map_groups__fprintf(&self->mg, verbose, fp); + const struct comm *comm = thread__comm(thread); + + if (!comm) + return NULL; + + return comm__str(comm); } -struct thread *perf_session__findnew(struct perf_session *self, pid_t pid) +/* CHECKME: it should probably better return the max comm len from its comm list */ +int thread__comm_len(struct thread *thread) { - struct rb_node **p = &self->threads.rb_node; - struct rb_node *parent = NULL; - struct thread *th; - - /* - * Font-end cache - PID lookups come in blocks, - * so most of the time we dont have to look up - * the full rbtree: - */ - if (self->last_match && self->last_match->pid == pid) - return self->last_match; - - while (*p != NULL) { - parent = *p; - th = rb_entry(parent, struct thread, rb_node); - - if (th->pid == pid) { - self->last_match = th; - return th; - } - - if (pid < th->pid) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; + if (!thread->comm_len) { + const char *comm = thread__comm_str(thread); + if (!comm) + return 0; + thread->comm_len = strlen(comm); } - th = thread__new(pid); - if (th != NULL) { - rb_link_node(&th->rb_node, parent, p); - rb_insert_color(&th->rb_node, &self->threads); - self->last_match = th; - } + return thread->comm_len; +} - return th; +size_t thread__fprintf(struct thread *thread, FILE *fp) +{ + return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) + + map_groups__fprintf(thread->mg, verbose, fp); } -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) +static int thread__clone_map_groups(struct thread *thread, + struct thread *parent) { int i; - if (parent->comm_set) { - if (self->comm) - free(self->comm); - self->comm = strdup(parent->comm); - if (!self->comm) - return -ENOMEM; - self->comm_set = true; - } + /* This is new thread, we share map groups for process. */ + if (thread->pid_ == parent->pid_) + return 0; + /* But this one is new process, copy maps. */ for (i = 0; i < MAP__NR_TYPES; ++i) - if (map_groups__clone(&self->mg, &parent->mg, i) < 0) + if (map_groups__clone(thread->mg, parent->mg, i) < 0) return -ENOMEM; + return 0; } -size_t perf_session__fprintf(struct perf_session *self, FILE *fp) +int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) { - size_t ret = 0; - struct rb_node *nd; - - for (nd = rb_first(&self->threads); nd; nd = rb_next(nd)) { - struct thread *pos = rb_entry(nd, struct thread, rb_node); + int err; - ret += thread__fprintf(pos, fp); + if (parent->comm_set) { + const char *comm = thread__comm_str(parent); + if (!comm) + return -ENOMEM; + err = thread__set_comm(thread, comm, timestamp); + if (err) + return err; + thread->comm_set = true; } - return ret; + thread->ppid = parent->tid; + return thread__clone_map_groups(thread, parent); +} + +void thread__find_cpumode_addr_location(struct thread *thread, + struct machine *machine, + enum map_type type, u64 addr, + struct addr_location *al) +{ + size_t i; + const u8 const cpumodes[] = { + PERF_RECORD_MISC_USER, + PERF_RECORD_MISC_KERNEL, + PERF_RECORD_MISC_GUEST_USER, + PERF_RECORD_MISC_GUEST_KERNEL + }; + + for (i = 0; i < ARRAY_SIZE(cpumodes); i++) { + thread__find_addr_location(thread, machine, cpumodes[i], type, + addr, al); + if (al->map) + break; + } } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 688500ff826..3c0c2724f82 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -2,48 +2,80 @@ #define __PERF_THREAD_H #include <linux/rbtree.h> +#include <linux/list.h> #include <unistd.h> +#include <sys/types.h> #include "symbol.h" +#include <strlist.h> struct thread { union { struct rb_node rb_node; struct list_head node; }; - struct map_groups mg; - pid_t pid; + struct map_groups *mg; + 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 perf_session; +struct machine; +struct comm; + +struct thread *thread__new(pid_t pid, pid_t tid); +int thread__init_map_groups(struct thread *thread, struct machine *machine); +void thread__delete(struct thread *thread); +static inline void thread__exited(struct thread *thread) +{ + thread->dead = true; +} + +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); + +void thread__find_addr_map(struct thread *thread, struct machine *machine, + u8 cpumode, enum map_type type, u64 addr, + struct addr_location *al); + +void thread__find_addr_location(struct thread *thread, struct machine *machine, + u8 cpumode, enum map_type type, u64 addr, + struct addr_location *al); -void thread__delete(struct thread *self); +void thread__find_cpumode_addr_location(struct thread *thread, + struct machine *machine, + enum map_type type, u64 addr, + struct addr_location *al); -int find_all_tid(int pid, pid_t ** all_tid); -int thread__set_comm(struct thread *self, const char *comm); -int thread__comm_len(struct thread *self); -struct thread *perf_session__findnew(struct perf_session *self, pid_t pid); -void thread__insert_map(struct thread *self, struct map *map); -int thread__fork(struct thread *self, struct thread *parent); -size_t perf_session__fprintf(struct perf_session *self, FILE *fp); +static inline void *thread__priv(struct thread *thread) +{ + return thread->priv; +} -static inline struct map *thread__find_map(struct thread *self, - enum map_type type, u64 addr) +static inline void thread__set_priv(struct thread *thread, void *p) { - return self ? map_groups__find(&self->mg, type, addr) : NULL; + thread->priv = p; } -void thread__find_addr_map(struct thread *self, - struct perf_session *session, u8 cpumode, - enum map_type type, pid_t pid, u64 addr, - struct addr_location *al); +static inline bool thread__is_filtered(struct thread *thread) +{ + if (symbol_conf.comm_list && + !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread))) { + return true; + } + + return false; +} -void thread__find_addr_location(struct thread *self, - struct perf_session *session, u8 cpumode, - enum map_type type, pid_t pid, u64 addr, - struct addr_location *al, - symbol_filter_t filter); #endif /* __PERF_THREAD_H */ diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c new file mode 100644 index 00000000000..5d321591210 --- /dev/null +++ b/tools/perf/util/thread_map.c @@ -0,0 +1,294 @@ +#include <dirent.h> +#include <limits.h> +#include <stdbool.h> +#include <stdlib.h> +#include <stdio.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include "strlist.h" +#include <string.h> +#include "thread_map.h" +#include "util.h" + +/* Skip "." and ".." directories */ +static int filter(const struct dirent *dir) +{ + if (dir->d_name[0] == '.') + return 0; + else + return 1; +} + +struct thread_map *thread_map__new_by_pid(pid_t pid) +{ + struct thread_map *threads; + char name[256]; + int items; + struct dirent **namelist = NULL; + int i; + + sprintf(name, "/proc/%d/task", pid); + items = scandir(name, &namelist, filter, NULL); + if (items <= 0) + return NULL; + + threads = malloc(sizeof(*threads) + sizeof(pid_t) * items); + if (threads != NULL) { + for (i = 0; i < items; i++) + threads->map[i] = atoi(namelist[i]->d_name); + threads->nr = items; + } + + for (i=0; i<items; i++) + zfree(&namelist[i]); + free(namelist); + + return threads; +} + +struct thread_map *thread_map__new_by_tid(pid_t tid) +{ + struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t)); + + if (threads != NULL) { + threads->map[0] = tid; + threads->nr = 1; + } + + return threads; +} + +struct thread_map *thread_map__new_by_uid(uid_t uid) +{ + DIR *proc; + int max_threads = 32, items, i; + char path[256]; + struct dirent dirent, *next, **namelist = NULL; + struct thread_map *threads = malloc(sizeof(*threads) + + max_threads * sizeof(pid_t)); + if (threads == NULL) + goto out; + + proc = opendir("/proc"); + if (proc == NULL) + goto out_free_threads; + + threads->nr = 0; + + while (!readdir_r(proc, &dirent, &next) && next) { + char *end; + bool grow = false; + struct stat st; + pid_t pid = strtol(dirent.d_name, &end, 10); + + if (*end) /* only interested in proper numerical dirents */ + continue; + + snprintf(path, sizeof(path), "/proc/%s", dirent.d_name); + + if (stat(path, &st) != 0) + continue; + + if (st.st_uid != uid) + continue; + + snprintf(path, sizeof(path), "/proc/%d/task", pid); + items = scandir(path, &namelist, filter, NULL); + if (items <= 0) + goto out_free_closedir; + + while (threads->nr + items >= max_threads) { + max_threads *= 2; + grow = true; + } + + if (grow) { + struct thread_map *tmp; + + tmp = realloc(threads, (sizeof(*threads) + + max_threads * sizeof(pid_t))); + if (tmp == NULL) + goto out_free_namelist; + + threads = tmp; + } + + for (i = 0; i < items; i++) + threads->map[threads->nr + i] = atoi(namelist[i]->d_name); + + for (i = 0; i < items; i++) + zfree(&namelist[i]); + free(namelist); + + threads->nr += items; + } + +out_closedir: + closedir(proc); +out: + return threads; + +out_free_threads: + free(threads); + return NULL; + +out_free_namelist: + for (i = 0; i < items; i++) + zfree(&namelist[i]); + free(namelist); + +out_free_closedir: + zfree(&threads); + goto out_closedir; +} + +struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid) +{ + if (pid != -1) + return thread_map__new_by_pid(pid); + + if (tid == -1 && uid != UINT_MAX) + return thread_map__new_by_uid(uid); + + return thread_map__new_by_tid(tid); +} + +static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) +{ + struct thread_map *threads = NULL, *nt; + char name[256]; + int items, total_tasks = 0; + struct dirent **namelist = NULL; + int i, j = 0; + pid_t pid, prev_pid = INT_MAX; + char *end_ptr; + struct str_node *pos; + struct strlist *slist = strlist__new(false, pid_str); + + if (!slist) + return NULL; + + strlist__for_each(pos, slist) { + pid = strtol(pos->s, &end_ptr, 10); + + if (pid == INT_MIN || pid == INT_MAX || + (*end_ptr != '\0' && *end_ptr != ',')) + goto out_free_threads; + + if (pid == prev_pid) + continue; + + sprintf(name, "/proc/%d/task", pid); + items = scandir(name, &namelist, filter, NULL); + if (items <= 0) + goto out_free_threads; + + total_tasks += items; + nt = realloc(threads, (sizeof(*threads) + + sizeof(pid_t) * total_tasks)); + if (nt == NULL) + goto out_free_namelist; + + threads = nt; + + for (i = 0; i < items; i++) { + threads->map[j++] = atoi(namelist[i]->d_name); + zfree(&namelist[i]); + } + threads->nr = total_tasks; + free(namelist); + } + +out: + strlist__delete(slist); + return threads; + +out_free_namelist: + for (i = 0; i < items; i++) + zfree(&namelist[i]); + free(namelist); + +out_free_threads: + zfree(&threads); + goto out; +} + +static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) +{ + struct thread_map *threads = NULL, *nt; + int ntasks = 0; + pid_t tid, prev_tid = INT_MAX; + char *end_ptr; + struct str_node *pos; + struct strlist *slist; + + /* perf-stat expects threads to be generated even if tid not given */ + if (!tid_str) { + threads = malloc(sizeof(*threads) + sizeof(pid_t)); + if (threads != NULL) { + threads->map[0] = -1; + threads->nr = 1; + } + return threads; + } + + slist = strlist__new(false, tid_str); + if (!slist) + return NULL; + + strlist__for_each(pos, slist) { + tid = strtol(pos->s, &end_ptr, 10); + + if (tid == INT_MIN || tid == INT_MAX || + (*end_ptr != '\0' && *end_ptr != ',')) + goto out_free_threads; + + if (tid == prev_tid) + continue; + + ntasks++; + nt = realloc(threads, sizeof(*threads) + sizeof(pid_t) * ntasks); + + if (nt == NULL) + goto out_free_threads; + + threads = nt; + threads->map[ntasks - 1] = tid; + threads->nr = ntasks; + } +out: + return threads; + +out_free_threads: + zfree(&threads); + goto out; +} + +struct thread_map *thread_map__new_str(const char *pid, const char *tid, + uid_t uid) +{ + if (pid) + return thread_map__new_by_pid_str(pid); + + if (!tid && uid != UINT_MAX) + return thread_map__new_by_uid(uid); + + return thread_map__new_by_tid_str(tid); +} + +void thread_map__delete(struct thread_map *threads) +{ + free(threads); +} + +size_t thread_map__fprintf(struct thread_map *threads, FILE *fp) +{ + int i; + size_t printed = fprintf(fp, "%d thread%s: ", + threads->nr, threads->nr > 1 ? "s" : ""); + for (i = 0; i < threads->nr; ++i) + printed += fprintf(fp, "%s%d", i ? ", " : "", threads->map[i]); + + return printed + fprintf(fp, "\n"); +} diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h new file mode 100644 index 00000000000..0cd8b310808 --- /dev/null +++ b/tools/perf/util/thread_map.h @@ -0,0 +1,29 @@ +#ifndef __PERF_THREAD_MAP_H +#define __PERF_THREAD_MAP_H + +#include <sys/types.h> +#include <stdio.h> + +struct thread_map { + int nr; + pid_t map[]; +}; + +struct thread_map *thread_map__new_by_pid(pid_t pid); +struct thread_map *thread_map__new_by_tid(pid_t tid); +struct thread_map *thread_map__new_by_uid(uid_t uid); +struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid); + +struct thread_map *thread_map__new_str(const char *pid, + const char *tid, uid_t uid); + +void thread_map__delete(struct thread_map *threads); + +size_t thread_map__fprintf(struct thread_map *threads, FILE *fp); + +static inline int thread_map__nr(struct thread_map *threads) +{ + return threads ? threads->nr : 1; +} + +#endif /* __PERF_THREAD_MAP_H */ diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h new file mode 100644 index 00000000000..4385816d3d4 --- /dev/null +++ b/tools/perf/util/tool.h @@ -0,0 +1,47 @@ +#ifndef __PERF_TOOL_H +#define __PERF_TOOL_H + +#include <stdbool.h> + +struct perf_session; +union perf_event; +struct perf_evlist; +struct perf_evsel; +struct perf_sample; +struct perf_tool; +struct machine; + +typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, struct machine *machine); + +typedef int (*event_op)(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, struct machine *machine); + +typedef int (*event_attr_op)(struct perf_tool *tool, + union perf_event *event, + struct perf_evlist **pevlist); + +typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event, + struct perf_session *session); + +struct perf_tool { + event_sample sample, + read; + event_op mmap, + mmap2, + comm, + fork, + exit, + lost, + throttle, + unthrottle; + event_attr_op attr; + event_op2 tracing_data; + event_op2 finished_round, + build_id; + bool ordered_samples; + bool ordering_requires_timestamps; +}; + +#endif /* __PERF_TOOL_H */ diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c new file mode 100644 index 00000000000..8e517def925 --- /dev/null +++ b/tools/perf/util/top.c @@ -0,0 +1,117 @@ +/* + * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Refactored from builtin-top.c, see that files for further copyright notes. + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "cpumap.h" +#include "event.h" +#include "evlist.h" +#include "evsel.h" +#include "parse-events.h" +#include "symbol.h" +#include "top.h" +#include <inttypes.h> + +#define SNPRINTF(buf, size, fmt, args...) \ +({ \ + size_t r = snprintf(buf, size, fmt, ## args); \ + r > size ? size : r; \ +}) + +size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) +{ + float samples_per_sec; + float ksamples_per_sec; + float esamples_percent; + struct record_opts *opts = &top->record_opts; + struct target *target = &opts->target; + size_t ret = 0; + + if (top->samples) { + samples_per_sec = top->samples / top->delay_secs; + ksamples_per_sec = top->kernel_samples / top->delay_secs; + esamples_percent = (100.0 * top->exact_samples) / top->samples; + } else { + samples_per_sec = ksamples_per_sec = esamples_percent = 0.0; + } + + if (!perf_guest) { + float ksamples_percent = 0.0; + + if (samples_per_sec) + ksamples_percent = (100.0 * ksamples_per_sec) / + samples_per_sec; + ret = SNPRINTF(bf, size, + " PerfTop:%8.0f irqs/sec kernel:%4.1f%%" + " exact: %4.1f%% [", samples_per_sec, + ksamples_percent, esamples_percent); + } else { + float us_samples_per_sec = top->us_samples / top->delay_secs; + float guest_kernel_samples_per_sec = top->guest_kernel_samples / top->delay_secs; + float guest_us_samples_per_sec = top->guest_us_samples / top->delay_secs; + + ret = SNPRINTF(bf, size, + " PerfTop:%8.0f irqs/sec kernel:%4.1f%% us:%4.1f%%" + " guest kernel:%4.1f%% guest us:%4.1f%%" + " exact: %4.1f%% [", samples_per_sec, + 100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec - us_samples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec - + guest_kernel_samples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec - + guest_us_samples_per_sec) / + samples_per_sec)), + esamples_percent); + } + + if (top->evlist->nr_entries == 1) { + struct perf_evsel *first = perf_evlist__first(top->evlist); + ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ", + (uint64_t)first->attr.sample_period, + opts->freq ? "Hz" : ""); + } + + ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel)); + + ret += SNPRINTF(bf + ret, size - ret, "], "); + + if (target->pid) + ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s", + target->pid); + else if (target->tid) + ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s", + target->tid); + else if (target->uid_str != NULL) + ret += SNPRINTF(bf + ret, size - ret, " (uid: %s", + target->uid_str); + else + ret += SNPRINTF(bf + ret, size - ret, " (all"); + + if (target->cpu_list) + ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", + top->evlist->cpus->nr > 1 ? "s" : "", + target->cpu_list); + else { + if (target->tid) + ret += SNPRINTF(bf + ret, size - ret, ")"); + else + ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", + top->evlist->cpus->nr, + top->evlist->cpus->nr > 1 ? "s" : ""); + } + + return ret; +} + +void perf_top__reset_sample_counters(struct perf_top *top) +{ + top->samples = top->us_samples = top->kernel_samples = + top->exact_samples = top->guest_kernel_samples = + top->guest_us_samples = 0; +} diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h new file mode 100644 index 00000000000..f92c37abb0a --- /dev/null +++ b/tools/perf/util/top.h @@ -0,0 +1,47 @@ +#ifndef __PERF_TOP_H +#define __PERF_TOP_H 1 + +#include "tool.h" +#include <linux/types.h> +#include <stddef.h> +#include <stdbool.h> +#include <termios.h> + +struct perf_evlist; +struct perf_evsel; +struct perf_session; + +struct perf_top { + struct perf_tool tool; + struct perf_evlist *evlist; + struct record_opts record_opts; + /* + * Symbols will be added here in perf_event__process_sample and will + * get out after decayed. + */ + u64 samples; + u64 kernel_samples, us_samples; + u64 exact_samples; + u64 guest_us_samples, guest_kernel_samples; + int print_entries, count_filter, delay_secs; + int max_stack; + bool hide_kernel_symbols, hide_user_symbols, zero; + bool use_tui, use_stdio; + bool kptr_restrict_warned; + bool vmlinux_warned; + bool dump_symtab; + struct hist_entry *sym_filter_entry; + struct perf_evsel *sym_evsel; + struct perf_session *session; + struct winsize winsize; + int realtime_prio; + int sym_pcnt_filter; + const char *sym_filter; + 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 b1572601286..7e6fcfe8b43 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -18,7 +18,7 @@ * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -#define _GNU_SOURCE +#include "util.h" #include <dirent.h> #include <mntent.h> #include <stdio.h> @@ -31,146 +31,20 @@ #include <pthread.h> #include <fcntl.h> #include <unistd.h> -#include <ctype.h> #include <errno.h> #include <stdbool.h> +#include <linux/list.h> #include <linux/kernel.h> #include "../perf.h" #include "trace-event.h" -#include "debugfs.h" +#include <api/fs/debugfs.h> +#include "evsel.h" #define VERSION "0.5" -#define _STR(x) #x -#define STR(x) _STR(x) -#define MAX_PATH 256 - -#define TRACE_CTRL "tracing_on" -#define TRACE "trace" -#define AVAILABLE "available_tracers" -#define CURRENT "current_tracer" -#define ITER_CTRL "trace_options" -#define MAX_LATENCY "tracing_max_latency" - -unsigned int page_size; - -static const char *output_file = "trace.info"; static int output_fd; -struct event_list { - struct event_list *next; - const char *event; -}; - -struct events { - struct events *sibling; - struct events *children; - struct events *next; - char *name; -}; - - - -static void die(const char *fmt, ...) -{ - va_list ap; - int ret = errno; - - if (errno) - perror("trace-cmd"); - else - ret = -1; - - va_start(ap, fmt); - fprintf(stderr, " "); - vfprintf(stderr, fmt, ap); - va_end(ap); - - fprintf(stderr, "\n"); - exit(ret); -} - -void *malloc_or_die(unsigned int size) -{ - void *data; - - data = malloc(size); - if (!data) - die("malloc"); - return data; -} - -static const char *find_debugfs(void) -{ - const char *path = debugfs_mount(NULL); - - if (!path) - die("Your kernel not support 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(); - - tracing = malloc_or_die(strlen(debugfs) + 9); - - 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_or_die(strlen(tracing) + strlen(name) + 2); - - sprintf(file, "%s/%s", tracing, name); - return file; -} - -static void put_tracing_file(char *file) -{ - free(file); -} - -static ssize_t calc_data_size; - -static ssize_t write_or_die(const void *buf, size_t len) -{ - int ret; - - if (calc_data_size) { - calc_data_size += len; - return len; - } - - ret = write(output_fd, buf, len); - if (ret < 0) - die("writing to '%s'", output_file); - - return ret; -} int bigendian(void) { @@ -181,106 +55,107 @@ int bigendian(void) return *ptr == 0x01020304; } -static unsigned long long copy_file_fd(int fd) +/* unfortunately, you can not stat debugfs or proc files for size */ +static int record_file(const char *file, ssize_t hdr_sz) { unsigned long long size = 0; - char buf[BUFSIZ]; - int r; - - do { - r = read(fd, buf, BUFSIZ); - if (r > 0) { - size += r; - write_or_die(buf, r); - } - } while (r > 0); - - return size; -} - -static unsigned long long copy_file(const char *file) -{ - unsigned long long size = 0; - int fd; + char buf[BUFSIZ], *sizep; + off_t hdr_pos = lseek(output_fd, 0, SEEK_CUR); + int r, fd; + int err = -EIO; fd = open(file, O_RDONLY); - if (fd < 0) - die("Can't read '%s'", file); - size = copy_file_fd(fd); - close(fd); - - return size; -} + if (fd < 0) { + pr_debug("Can't read '%s'", file); + return -errno; + } -static unsigned long get_size_fd(int fd) -{ - unsigned long long size = 0; - char buf[BUFSIZ]; - int r; + /* put in zeros for file size, then fill true size later */ + if (hdr_sz) { + if (write(output_fd, &size, hdr_sz) != hdr_sz) + goto out; + } do { r = read(fd, buf, BUFSIZ); - if (r > 0) + if (r > 0) { size += r; + if (write(output_fd, buf, r) != r) + goto out; + } } while (r > 0); - lseek(fd, 0, SEEK_SET); - - return size; -} + /* ugh, handle big-endian hdr_size == 4 */ + sizep = (char*)&size; + if (bigendian()) + sizep += sizeof(u64) - hdr_sz; -static unsigned long get_size(const char *file) -{ - unsigned long long size = 0; - int fd; + if (hdr_sz && pwrite(output_fd, sizep, hdr_sz, hdr_pos) < 0) { + pr_debug("writing file size failed\n"); + goto out; + } - fd = open(file, O_RDONLY); - if (fd < 0) - die("Can't read '%s'", file); - size = get_size_fd(fd); + err = 0; +out: close(fd); - - return size; + return err; } -static void read_header_files(void) +static int record_header_files(void) { - unsigned long long size, check_size; char *path; - int fd; + struct stat st; + int err = -EIO; path = get_tracing_file("events/header_page"); - fd = open(path, O_RDONLY); - if (fd < 0) - die("can't read '%s'", path); + if (!path) { + pr_debug("can't get tracing/events/header_page"); + return -ENOMEM; + } + + if (stat(path, &st) < 0) { + pr_debug("can't read '%s'", path); + goto out; + } - /* unfortunately, you can not stat debugfs files for size */ - size = get_size_fd(fd); + if (write(output_fd, "header_page", 12) != 12) { + pr_debug("can't write header_page\n"); + goto out; + } - write_or_die("header_page", 12); - write_or_die(&size, 8); - check_size = copy_file_fd(fd); - close(fd); + if (record_file(path, 8) < 0) { + pr_debug("can't record header_page file\n"); + goto out; + } - if (size != check_size) - die("wrong size for '%s' size=%lld read=%lld", - path, size, check_size); put_tracing_file(path); path = get_tracing_file("events/header_event"); - fd = open(path, O_RDONLY); - if (fd < 0) - die("can't read '%s'", path); + if (!path) { + pr_debug("can't get tracing/events/header_event"); + err = -ENOMEM; + goto out; + } - size = get_size_fd(fd); + if (stat(path, &st) < 0) { + pr_debug("can't read '%s'", path); + goto out; + } - write_or_die("header_event", 13); - write_or_die(&size, 8); - check_size = copy_file_fd(fd); - if (size != check_size) - die("wrong size for '%s'", path); + if (write(output_fd, "header_event", 13) != 13) { + pr_debug("can't write header_event\n"); + goto out; + } + + if (record_file(path, 8) < 0) { + pr_debug("can't record header_event file\n"); + goto out; + } + + err = 0; +out: put_tracing_file(path); - close(fd); + return err; } static bool name_in_tp_list(char *sys, struct tracepoint_path *tps) @@ -294,19 +169,21 @@ static bool name_in_tp_list(char *sys, struct tracepoint_path *tps) return false; } -static void copy_event_system(const char *sys, struct tracepoint_path *tps) +static int copy_event_system(const char *sys, struct tracepoint_path *tps) { - unsigned long long size, check_size; struct dirent *dent; struct stat st; char *format; DIR *dir; int count = 0; int ret; + int err; dir = opendir(sys); - if (!dir) - die("can't read directory '%s'", sys); + if (!dir) { + pr_debug("can't read directory '%s'", sys); + return -errno; + } while ((dent = readdir(dir))) { if (dent->d_type != DT_DIR || @@ -314,7 +191,11 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps) strcmp(dent->d_name, "..") == 0 || !name_in_tp_list(dent->d_name, tps)) continue; - format = malloc_or_die(strlen(sys) + strlen(dent->d_name) + 10); + format = malloc(strlen(sys) + strlen(dent->d_name) + 10); + if (!format) { + err = -ENOMEM; + goto out; + } sprintf(format, "%s/%s/format", sys, dent->d_name); ret = stat(format, &st); free(format); @@ -323,7 +204,11 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps) count++; } - write_or_die(&count, 4); + if (write(output_fd, &count, 4) != 4) { + err = -EIO; + pr_debug("can't write count\n"); + goto out; + } rewinddir(dir); while ((dent = readdir(dir))) { @@ -332,33 +217,45 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps) strcmp(dent->d_name, "..") == 0 || !name_in_tp_list(dent->d_name, tps)) continue; - format = malloc_or_die(strlen(sys) + strlen(dent->d_name) + 10); + format = malloc(strlen(sys) + strlen(dent->d_name) + 10); + if (!format) { + err = -ENOMEM; + goto out; + } sprintf(format, "%s/%s/format", sys, dent->d_name); ret = stat(format, &st); if (ret >= 0) { - /* unfortunately, you can not stat debugfs files for size */ - size = get_size(format); - write_or_die(&size, 8); - check_size = copy_file(format); - if (size != check_size) - die("error in size of file '%s'", format); + err = record_file(format, 8); + if (err) { + free(format); + goto out; + } } - free(format); } + err = 0; +out: closedir(dir); + return err; } -static void read_ftrace_files(struct tracepoint_path *tps) +static int record_ftrace_files(struct tracepoint_path *tps) { char *path; + int ret; path = get_tracing_file("events/ftrace"); + if (!path) { + pr_debug("can't get tracing/events/ftrace"); + return -ENOMEM; + } - copy_event_system(path, tps); + ret = copy_event_system(path, tps); put_tracing_file(path); + + return ret; } static bool system_in_tp_list(char *sys, struct tracepoint_path *tps) @@ -372,7 +269,7 @@ static bool system_in_tp_list(char *sys, struct tracepoint_path *tps) return false; } -static void read_event_files(struct tracepoint_path *tps) +static int record_event_files(struct tracepoint_path *tps) { struct dirent *dent; struct stat st; @@ -381,12 +278,20 @@ static void read_event_files(struct tracepoint_path *tps) DIR *dir; int count = 0; int ret; + int err; path = get_tracing_file("events"); + if (!path) { + pr_debug("can't get tracing/events"); + return -ENOMEM; + } dir = opendir(path); - if (!dir) - die("can't read directory '%s'", path); + if (!dir) { + err = -errno; + pr_debug("can't read directory '%s'", path); + goto out; + } while ((dent = readdir(dir))) { if (dent->d_type != DT_DIR || @@ -398,7 +303,11 @@ static void read_event_files(struct tracepoint_path *tps) count++; } - write_or_die(&count, 4); + if (write(output_fd, &count, 4) != 4) { + err = -EIO; + pr_debug("can't write count\n"); + goto out; + } rewinddir(dir); while ((dent = readdir(dir))) { @@ -408,117 +317,158 @@ static void read_event_files(struct tracepoint_path *tps) strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; - sys = malloc_or_die(strlen(path) + strlen(dent->d_name) + 2); + sys = malloc(strlen(path) + strlen(dent->d_name) + 2); + if (!sys) { + err = -ENOMEM; + goto out; + } sprintf(sys, "%s/%s", path, dent->d_name); ret = stat(sys, &st); if (ret >= 0) { - write_or_die(dent->d_name, strlen(dent->d_name) + 1); - copy_event_system(sys, tps); + ssize_t size = strlen(dent->d_name) + 1; + + if (write(output_fd, dent->d_name, size) != size || + copy_event_system(sys, tps) < 0) { + err = -EIO; + free(sys); + goto out; + } } free(sys); } - + err = 0; +out: closedir(dir); put_tracing_file(path); + + return err; } -static void read_proc_kallsyms(void) +static int record_proc_kallsyms(void) { - unsigned int size, check_size; + unsigned int size; const char *path = "/proc/kallsyms"; struct stat st; - int ret; + int ret, err = 0; ret = stat(path, &st); if (ret < 0) { /* not found */ size = 0; - write_or_die(&size, 4); - return; + if (write(output_fd, &size, 4) != 4) + err = -EIO; + return err; } - size = get_size(path); - write_or_die(&size, 4); - check_size = copy_file(path); - if (size != check_size) - die("error in size of file '%s'", path); - + return record_file(path, 4); } -static void read_ftrace_printk(void) +static int record_ftrace_printk(void) { - unsigned int size, check_size; + unsigned int size; char *path; struct stat st; - int ret; + int ret, err = 0; path = get_tracing_file("printk_formats"); + if (!path) { + pr_debug("can't get tracing/printk_formats"); + return -ENOMEM; + } + ret = stat(path, &st); if (ret < 0) { /* not found */ size = 0; - write_or_die(&size, 4); + if (write(output_fd, &size, 4) != 4) + err = -EIO; goto out; } - size = get_size(path); - write_or_die(&size, 4); - check_size = copy_file(path); - if (size != check_size) - die("error in size of file '%s'", path); + err = record_file(path, 4); + out: put_tracing_file(path); + return err; +} + +static void +put_tracepoints_path(struct tracepoint_path *tps) +{ + while (tps) { + struct tracepoint_path *t = tps; + + tps = tps->next; + zfree(&t->name); + zfree(&t->system); + free(t); + } } static struct tracepoint_path * -get_tracepoints_path(struct perf_event_attr *pattrs, int nb_events) +get_tracepoints_path(struct list_head *pattrs) { struct tracepoint_path path, *ppath = &path; - int i, nr_tracepoints = 0; + struct perf_evsel *pos; + int nr_tracepoints = 0; - for (i = 0; i < nb_events; i++) { - if (pattrs[i].type != PERF_TYPE_TRACEPOINT) + list_for_each_entry(pos, pattrs, node) { + if (pos->attr.type != PERF_TYPE_TRACEPOINT) continue; ++nr_tracepoints; - ppath->next = tracepoint_id_to_path(pattrs[i].config); - if (!ppath->next) - die("%s\n", "No memory to alloc tracepoints list"); + + 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; } return nr_tracepoints > 0 ? path.next : NULL; } -bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events) +bool have_tracepoints(struct list_head *pattrs) { - int i; + struct perf_evsel *pos; - for (i = 0; i < nb_events; i++) - if (pattrs[i].type == PERF_TYPE_TRACEPOINT) + list_for_each_entry(pos, pattrs, node) + if (pos->attr.type == PERF_TYPE_TRACEPOINT) return true; return false; } -int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events) +static int tracing_data_header(void) { - char buf[BUFSIZ]; - struct tracepoint_path *tps = get_tracepoints_path(pattrs, nb_events); - - /* - * What? No tracepoints? No sense writing anything here, bail out. - */ - if (tps == NULL) - return -1; - - output_fd = fd; + char buf[20]; + ssize_t size; + /* just guessing this is someone's birthday.. ;) */ buf[0] = 23; buf[1] = 8; buf[2] = 68; memcpy(buf + 3, "tracing", 7); - write_or_die(buf, 10); + if (write(output_fd, buf, 10) != 10) + return -1; - write_or_die(VERSION, strlen(VERSION) + 1); + size = strlen(VERSION) + 1; + if (write(output_fd, VERSION, size) != size) + return -1; /* save endian */ if (bigendian()) @@ -526,38 +476,125 @@ int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events) else buf[0] = 0; - write_or_die(buf, 1); + if (write(output_fd, buf, 1) != 1) + return -1; /* save size of long */ buf[0] = sizeof(long); - write_or_die(buf, 1); + if (write(output_fd, buf, 1) != 1) + return -1; /* save page_size */ - page_size = sysconf(_SC_PAGESIZE); - write_or_die(&page_size, 4); - - read_header_files(); - read_ftrace_files(tps); - read_event_files(tps); - read_proc_kallsyms(); - read_ftrace_printk(); + if (write(output_fd, &page_size, 4) != 4) + return -1; return 0; } -ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs, - int nb_events) +struct tracing_data *tracing_data_get(struct list_head *pattrs, + int fd, bool temp) +{ + struct tracepoint_path *tps; + struct tracing_data *tdata; + int err; + + output_fd = fd; + + tps = get_tracepoints_path(pattrs); + if (!tps) + return NULL; + + tdata = malloc(sizeof(*tdata)); + if (!tdata) + return NULL; + + tdata->temp = temp; + tdata->size = 0; + + if (temp) { + int temp_fd; + + snprintf(tdata->temp_file, sizeof(tdata->temp_file), + "/tmp/perf-XXXXXX"); + if (!mkstemp(tdata->temp_file)) { + pr_debug("Can't make temp file"); + return NULL; + } + + temp_fd = open(tdata->temp_file, O_RDWR); + if (temp_fd < 0) { + pr_debug("Can't read '%s'", tdata->temp_file); + return NULL; + } + + /* + * Set the temp file the default output, so all the + * tracing data are stored into it. + */ + output_fd = temp_fd; + } + + err = tracing_data_header(); + if (err) + goto out; + err = record_header_files(); + if (err) + goto out; + err = record_ftrace_files(tps); + if (err) + goto out; + err = record_event_files(tps); + if (err) + goto out; + err = record_proc_kallsyms(); + if (err) + goto out; + err = record_ftrace_printk(); + +out: + /* + * All tracing data are stored by now, we can restore + * the default output file in case we used temp file. + */ + if (temp) { + tdata->size = lseek(output_fd, 0, SEEK_CUR); + close(output_fd); + output_fd = fd; + } + + if (err) + zfree(&tdata); + + put_tracepoints_path(tps); + return tdata; +} + +int tracing_data_put(struct tracing_data *tdata) { - ssize_t size; int err = 0; - calc_data_size = 1; - err = read_tracing_data(fd, pattrs, nb_events); - size = calc_data_size - 1; - calc_data_size = 0; + if (tdata->temp) { + err = record_file(tdata->temp_file, 0); + unlink(tdata->temp_file); + } - if (err < 0) - return err; + free(tdata); + return err; +} + +int read_tracing_data(int fd, struct list_head *pattrs) +{ + int err; + struct tracing_data *tdata; + + /* + * We work over the real file, so we can write data + * directly, no temp file is needed. + */ + tdata = tracing_data_get(pattrs, fd, false); + if (!tdata) + return -ENOMEM; - return size; + err = tracing_data_put(tdata); + return err; } diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 73a02223c62..c36636fd825 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -17,2161 +17,211 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * The parts for function graph printing was taken and modified from the - * Linux Kernel that were written by Frederic Weisbecker. */ -#define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> #include <string.h> #include <ctype.h> #include <errno.h> -#undef _GNU_SOURCE #include "../perf.h" #include "util.h" #include "trace-event.h" -int header_page_ts_offset; -int header_page_ts_size; -int header_page_size_offset; -int header_page_size_size; -int header_page_overwrite_offset; -int header_page_overwrite_size; -int header_page_data_offset; -int header_page_data_size; - -bool latency_format; - -static char *input_buf; -static unsigned long long input_buf_ptr; -static unsigned long long input_buf_siz; - -static int cpus; -static int long_size; -static int is_flag_field; -static int is_symbolic_field; - -static struct format_field * -find_any_field(struct event *event, const char *name); - -static void init_input_buf(char *buf, unsigned long long size) -{ - input_buf = buf; - input_buf_siz = size; - input_buf_ptr = 0; -} - -struct cmdline { - char *comm; - int pid; -}; - -static struct cmdline *cmdlines; -static int cmdline_count; - -static int cmdline_cmp(const void *a, const void *b) -{ - const struct cmdline *ca = a; - const struct cmdline *cb = b; - - if (ca->pid < cb->pid) - return -1; - if (ca->pid > cb->pid) - return 1; - - return 0; -} - -void parse_cmdlines(char *file, int size __unused) +static int get_common_field(struct scripting_context *context, + int *offset, int *size, const char *type) { - struct cmdline_list { - struct cmdline_list *next; - char *comm; - int pid; - } *list = NULL, *item; - char *line; - char *next = NULL; - int i; - - line = strtok_r(file, "\n", &next); - while (line) { - item = malloc_or_die(sizeof(*item)); - sscanf(line, "%d %as", &item->pid, - (float *)(void *)&item->comm); /* workaround gcc warning */ - item->next = list; - list = item; - line = strtok_r(NULL, "\n", &next); - cmdline_count++; - } + struct pevent *pevent = context->pevent; + struct event_format *event; + struct format_field *field; - cmdlines = malloc_or_die(sizeof(*cmdlines) * cmdline_count); + if (!*size) { + if (!pevent->events) + return 0; - i = 0; - while (list) { - cmdlines[i].pid = list->pid; - cmdlines[i].comm = list->comm; - i++; - item = list; - list = list->next; - free(item); + event = pevent->events[0]; + field = pevent_find_common_field(event, type); + if (!field) + return 0; + *offset = field->offset; + *size = field->size; } - qsort(cmdlines, cmdline_count, sizeof(*cmdlines), cmdline_cmp); + return pevent_read_number(pevent, context->event_data + *offset, *size); } -static struct func_map { - unsigned long long addr; - char *func; - char *mod; -} *func_list; -static unsigned int func_count; - -static int func_cmp(const void *a, const void *b) +int common_lock_depth(struct scripting_context *context) { - const struct func_map *fa = a; - const struct func_map *fb = b; + static int offset; + static int size; + int ret; - if (fa->addr < fb->addr) + ret = get_common_field(context, &size, &offset, + "common_lock_depth"); + if (ret < 0) return -1; - if (fa->addr > fb->addr) - return 1; - return 0; + return ret; } -void parse_proc_kallsyms(char *file, unsigned int size __unused) +int common_flags(struct scripting_context *context) { - struct func_list { - struct func_list *next; - unsigned long long addr; - char *func; - char *mod; - } *list = NULL, *item; - char *line; - char *next = NULL; - char *addr_str; - char ch; + static int offset; + static int size; int ret; - int i; - - line = strtok_r(file, "\n", &next); - while (line) { - item = malloc_or_die(sizeof(*item)); - item->mod = NULL; - ret = sscanf(line, "%as %c %as\t[%as", - (float *)(void *)&addr_str, /* workaround gcc warning */ - &ch, - (float *)(void *)&item->func, - (float *)(void *)&item->mod); - item->addr = strtoull(addr_str, NULL, 16); - free(addr_str); - - /* truncate the extra ']' */ - if (item->mod) - item->mod[strlen(item->mod) - 1] = 0; + ret = get_common_field(context, &size, &offset, + "common_flags"); + if (ret < 0) + return -1; - item->next = list; - list = item; - line = strtok_r(NULL, "\n", &next); - func_count++; - } - - func_list = malloc_or_die(sizeof(*func_list) * (func_count + 1)); - - i = 0; - while (list) { - func_list[i].func = list->func; - func_list[i].addr = list->addr; - func_list[i].mod = list->mod; - i++; - item = list; - list = list->next; - free(item); - } - - qsort(func_list, func_count, sizeof(*func_list), func_cmp); - - /* - * Add a special record at the end. - */ - func_list[func_count].func = NULL; - func_list[func_count].addr = 0; - func_list[func_count].mod = NULL; + return ret; } -/* - * We are searching for a record in between, not an exact - * match. - */ -static int func_bcmp(const void *a, const void *b) +int common_pc(struct scripting_context *context) { - const struct func_map *fa = a; - const struct func_map *fb = b; - - if ((fa->addr == fb->addr) || - - (fa->addr > fb->addr && - fa->addr < (fb+1)->addr)) - return 0; + static int offset; + static int size; + int ret; - if (fa->addr < fb->addr) + ret = get_common_field(context, &size, &offset, + "common_preempt_count"); + if (ret < 0) return -1; - return 1; + return ret; } -static struct func_map *find_func(unsigned long long addr) +unsigned long long +raw_field_value(struct event_format *event, const char *name, void *data) { - struct func_map *func; - struct func_map key; + struct format_field *field; + unsigned long long val; - key.addr = addr; + field = pevent_find_any_field(event, name); + if (!field) + return 0ULL; - func = bsearch(&key, func_list, func_count, sizeof(*func_list), - func_bcmp); + pevent_read_number_field(field, data, &val); - return func; + return val; } -void print_funcs(void) +unsigned long long read_size(struct event_format *event, void *ptr, int size) { - int i; - - for (i = 0; i < (int)func_count; i++) { - printf("%016llx %s", - func_list[i].addr, - func_list[i].func); - if (func_list[i].mod) - printf(" [%s]\n", func_list[i].mod); - else - printf("\n"); - } + return pevent_read_number(event->pevent, ptr, size); } -static struct printk_map { - unsigned long long addr; - char *printk; -} *printk_list; -static unsigned int printk_count; - -static int printk_cmp(const void *a, const void *b) +void event_format__print(struct event_format *event, + int cpu, void *data, int size) { - const struct func_map *fa = a; - const struct func_map *fb = b; + struct pevent_record record; + struct trace_seq s; - if (fa->addr < fb->addr) - return -1; - if (fa->addr > fb->addr) - return 1; + memset(&record, 0, sizeof(record)); + record.cpu = cpu; + record.size = size; + record.data = data; - return 0; + trace_seq_init(&s); + pevent_event_info(&s, event, &record); + trace_seq_do_printf(&s); + trace_seq_destroy(&s); } -static struct printk_map *find_printk(unsigned long long addr) +void parse_proc_kallsyms(struct pevent *pevent, + char *file, unsigned int size __maybe_unused) { - struct printk_map *printk; - struct printk_map key; - - key.addr = addr; + unsigned long long addr; + char *func; + char *line; + char *next = NULL; + char *addr_str; + char *mod; + char *fmt = NULL; - printk = bsearch(&key, printk_list, printk_count, sizeof(*printk_list), - printk_cmp); + line = strtok_r(file, "\n", &next); + while (line) { + mod = NULL; + addr_str = strtok_r(line, " ", &fmt); + addr = strtoull(addr_str, NULL, 16); + /* skip character */ + strtok_r(NULL, " ", &fmt); + func = strtok_r(NULL, "\t", &fmt); + mod = strtok_r(NULL, "]", &fmt); + /* truncate the extra '[' */ + if (mod) + mod = mod + 1; + + pevent_register_function(pevent, func, addr, mod); - return printk; + line = strtok_r(NULL, "\n", &next); + } } -void parse_ftrace_printk(char *file, unsigned int size __unused) +void parse_ftrace_printk(struct pevent *pevent, + char *file, unsigned int size __maybe_unused) { - struct printk_list { - struct printk_list *next; - unsigned long long addr; - char *printk; - } *list = NULL, *item; + unsigned long long addr; + char *printk; char *line; char *next = NULL; char *addr_str; - int i; + char *fmt; line = strtok_r(file, "\n", &next); while (line) { - addr_str = strsep(&line, ":"); - if (!line) { - warning("error parsing print strings"); + addr_str = strtok_r(line, ":", &fmt); + if (!addr_str) { + warning("printk format with empty entry"); break; } - item = malloc_or_die(sizeof(*item)); - item->addr = strtoull(addr_str, NULL, 16); + addr = strtoull(addr_str, NULL, 16); /* fmt still has a space, skip it */ - item->printk = strdup(line+1); - item->next = list; - list = item; + printk = strdup(fmt+1); line = strtok_r(NULL, "\n", &next); - printk_count++; - } - - printk_list = malloc_or_die(sizeof(*printk_list) * printk_count + 1); - - i = 0; - while (list) { - printk_list[i].printk = list->printk; - printk_list[i].addr = list->addr; - i++; - item = list; - list = list->next; - free(item); - } - - qsort(printk_list, printk_count, sizeof(*printk_list), printk_cmp); -} - -void print_printk(void) -{ - int i; - - for (i = 0; i < (int)printk_count; i++) { - printf("%016llx %s\n", - printk_list[i].addr, - printk_list[i].printk); - } -} - -static struct event *alloc_event(void) -{ - struct event *event; - - event = malloc_or_die(sizeof(*event)); - memset(event, 0, sizeof(*event)); - - return event; -} - -enum event_type { - EVENT_ERROR, - EVENT_NONE, - EVENT_SPACE, - EVENT_NEWLINE, - EVENT_OP, - EVENT_DELIM, - EVENT_ITEM, - EVENT_DQUOTE, - EVENT_SQUOTE, -}; - -static struct event *event_list; - -static void add_event(struct event *event) -{ - event->next = event_list; - event_list = event; -} - -static int event_item_type(enum event_type type) -{ - switch (type) { - case EVENT_ITEM ... EVENT_SQUOTE: - return 1; - case EVENT_ERROR ... EVENT_DELIM: - default: - return 0; - } -} - -static void free_arg(struct print_arg *arg) -{ - if (!arg) - return; - - switch (arg->type) { - case PRINT_ATOM: - if (arg->atom.atom) - free(arg->atom.atom); - break; - case PRINT_NULL: - case PRINT_FIELD ... PRINT_OP: - default: - /* todo */ - break; - } - - free(arg); -} - -static enum event_type get_type(int ch) -{ - if (ch == '\n') - return EVENT_NEWLINE; - if (isspace(ch)) - return EVENT_SPACE; - if (isalnum(ch) || ch == '_') - return EVENT_ITEM; - if (ch == '\'') - return EVENT_SQUOTE; - if (ch == '"') - return EVENT_DQUOTE; - if (!isprint(ch)) - return EVENT_NONE; - if (ch == '(' || ch == ')' || ch == ',') - return EVENT_DELIM; - - return EVENT_OP; -} - -static int __read_char(void) -{ - if (input_buf_ptr >= input_buf_siz) - return -1; - - return input_buf[input_buf_ptr++]; -} - -static int __peek_char(void) -{ - if (input_buf_ptr >= input_buf_siz) - return -1; - - return input_buf[input_buf_ptr]; -} - -static enum event_type __read_token(char **tok) -{ - char buf[BUFSIZ]; - int ch, last_ch, quote_ch, next_ch; - int i = 0; - int tok_size = 0; - enum event_type type; - - *tok = NULL; - - - ch = __read_char(); - if (ch < 0) - return EVENT_NONE; - - type = get_type(ch); - if (type == EVENT_NONE) - return type; - - buf[i++] = ch; - - switch (type) { - case EVENT_NEWLINE: - case EVENT_DELIM: - *tok = malloc_or_die(2); - (*tok)[0] = ch; - (*tok)[1] = 0; - return type; - - case EVENT_OP: - switch (ch) { - case '-': - next_ch = __peek_char(); - if (next_ch == '>') { - buf[i++] = __read_char(); - break; - } - /* fall through */ - case '+': - case '|': - case '&': - case '>': - case '<': - last_ch = ch; - ch = __peek_char(); - if (ch != last_ch) - goto test_equal; - buf[i++] = __read_char(); - switch (last_ch) { - case '>': - case '<': - goto test_equal; - default: - break; - } - break; - case '!': - case '=': - goto test_equal; - default: /* what should we do instead? */ - break; - } - buf[i] = 0; - *tok = strdup(buf); - return type; - - test_equal: - ch = __peek_char(); - if (ch == '=') - buf[i++] = __read_char(); - break; - - case EVENT_DQUOTE: - case EVENT_SQUOTE: - /* don't keep quotes */ - i--; - quote_ch = ch; - last_ch = 0; - do { - if (i == (BUFSIZ - 1)) { - buf[i] = 0; - if (*tok) { - *tok = realloc(*tok, tok_size + BUFSIZ); - if (!*tok) - return EVENT_NONE; - strcat(*tok, buf); - } else - *tok = strdup(buf); - - if (!*tok) - return EVENT_NONE; - tok_size += BUFSIZ; - i = 0; - } - last_ch = ch; - ch = __read_char(); - buf[i++] = ch; - /* the '\' '\' will cancel itself */ - if (ch == '\\' && last_ch == '\\') - last_ch = 0; - } while (ch != quote_ch || last_ch == '\\'); - /* remove the last quote */ - i--; - goto out; - - case EVENT_ERROR ... EVENT_SPACE: - case EVENT_ITEM: - default: - break; - } - - while (get_type(__peek_char()) == type) { - if (i == (BUFSIZ - 1)) { - buf[i] = 0; - if (*tok) { - *tok = realloc(*tok, tok_size + BUFSIZ); - if (!*tok) - return EVENT_NONE; - strcat(*tok, buf); - } else - *tok = strdup(buf); - - if (!*tok) - return EVENT_NONE; - tok_size += BUFSIZ; - i = 0; - } - ch = __read_char(); - buf[i++] = ch; - } - - out: - buf[i] = 0; - if (*tok) { - *tok = realloc(*tok, tok_size + i); - if (!*tok) - return EVENT_NONE; - strcat(*tok, buf); - } else - *tok = strdup(buf); - if (!*tok) - return EVENT_NONE; - - return type; -} - -static void free_token(char *tok) -{ - if (tok) - free(tok); -} - -static enum event_type read_token(char **tok) -{ - enum event_type type; - - for (;;) { - type = __read_token(tok); - if (type != EVENT_SPACE) - return type; - - free_token(*tok); + pevent_register_print_string(pevent, printk, addr); } - - /* not reached */ - return EVENT_NONE; } -/* no newline */ -static enum event_type read_token_item(char **tok) +int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size) { - enum event_type type; - - for (;;) { - type = __read_token(tok); - if (type != EVENT_SPACE && type != EVENT_NEWLINE) - return type; - - free_token(*tok); - } - - /* not reached */ - return EVENT_NONE; + return pevent_parse_event(pevent, buf, size, "ftrace"); } -static int test_type(enum event_type type, enum event_type expect) +int parse_event_file(struct pevent *pevent, + char *buf, unsigned long size, char *sys) { - if (type != expect) { - warning("Error: expected type %d but read %d", - expect, type); - return -1; - } - return 0; + return pevent_parse_event(pevent, buf, size, sys); } -static int __test_type_token(enum event_type type, char *token, - enum event_type expect, const char *expect_tok, - bool warn) +struct event_format *trace_find_next_event(struct pevent *pevent, + struct event_format *event) { - if (type != expect) { - if (warn) - warning("Error: expected type %d but read %d", - expect, type); - return -1; - } + static int idx; - if (strcmp(token, expect_tok) != 0) { - if (warn) - warning("Error: expected '%s' but read '%s'", - expect_tok, token); - return -1; - } - return 0; -} - -static int test_type_token(enum event_type type, char *token, - enum event_type expect, const char *expect_tok) -{ - return __test_type_token(type, token, expect, expect_tok, true); -} - -static int __read_expect_type(enum event_type expect, char **tok, int newline_ok) -{ - enum event_type type; - - if (newline_ok) - type = read_token(tok); - else - type = read_token_item(tok); - return test_type(type, expect); -} - -static int read_expect_type(enum event_type expect, char **tok) -{ - return __read_expect_type(expect, tok, 1); -} - -static int __read_expected(enum event_type expect, const char *str, - int newline_ok, bool warn) -{ - enum event_type type; - char *token; - int ret; - - if (newline_ok) - type = read_token(&token); - else - type = read_token_item(&token); - - ret = __test_type_token(type, token, expect, str, warn); - - free_token(token); - - return ret; -} - -static int read_expected(enum event_type expect, const char *str) -{ - return __read_expected(expect, str, 1, true); -} - -static int read_expected_item(enum event_type expect, const char *str) -{ - return __read_expected(expect, str, 0, true); -} - -static char *event_read_name(void) -{ - char *token; - - if (read_expected(EVENT_ITEM, "name") < 0) + if (!pevent || !pevent->events) return NULL; - if (read_expected(EVENT_OP, ":") < 0) - return NULL; - - if (read_expect_type(EVENT_ITEM, &token) < 0) - goto fail; - - return token; - - fail: - free_token(token); - return NULL; -} - -static int event_read_id(void) -{ - char *token; - int id; - - if (read_expected_item(EVENT_ITEM, "ID") < 0) - return -1; - - if (read_expected(EVENT_OP, ":") < 0) - return -1; - - if (read_expect_type(EVENT_ITEM, &token) < 0) - goto fail; - - id = strtoul(token, NULL, 0); - free_token(token); - return id; - - fail: - free_token(token); - return -1; -} - -static int field_is_string(struct format_field *field) -{ - if ((field->flags & FIELD_IS_ARRAY) && - (!strstr(field->type, "char") || !strstr(field->type, "u8") || - !strstr(field->type, "s8"))) - return 1; - - return 0; -} - -static int field_is_dynamic(struct format_field *field) -{ - if (!strncmp(field->type, "__data_loc", 10)) - return 1; - - return 0; -} - -static int event_read_fields(struct event *event, struct format_field **fields) -{ - struct format_field *field = NULL; - enum event_type type; - char *token; - char *last_token; - int count = 0; - - do { - type = read_token(&token); - if (type == EVENT_NEWLINE) { - free_token(token); - return count; - } - - count++; - - if (test_type_token(type, token, EVENT_ITEM, "field")) - goto fail; - free_token(token); - - type = read_token(&token); - /* - * The ftrace fields may still use the "special" name. - * Just ignore it. - */ - if (event->flags & EVENT_FL_ISFTRACE && - type == EVENT_ITEM && strcmp(token, "special") == 0) { - free_token(token); - type = read_token(&token); - } - - if (test_type_token(type, token, EVENT_OP, ":") < 0) - return -1; - - if (read_expect_type(EVENT_ITEM, &token) < 0) - goto fail; - - last_token = token; - - field = malloc_or_die(sizeof(*field)); - memset(field, 0, sizeof(*field)); - - /* read the rest of the type */ - for (;;) { - type = read_token(&token); - if (type == EVENT_ITEM || - (type == EVENT_OP && strcmp(token, "*") == 0) || - /* - * Some of the ftrace fields are broken and have - * an illegal "." in them. - */ - (event->flags & EVENT_FL_ISFTRACE && - type == EVENT_OP && strcmp(token, ".") == 0)) { - - if (strcmp(token, "*") == 0) - field->flags |= FIELD_IS_POINTER; - - if (field->type) { - field->type = realloc(field->type, - strlen(field->type) + - strlen(last_token) + 2); - strcat(field->type, " "); - strcat(field->type, last_token); - } else - field->type = last_token; - last_token = token; - continue; - } - - break; - } - - if (!field->type) { - die("no type found"); - goto fail; - } - field->name = last_token; - - if (test_type(type, EVENT_OP)) - goto fail; - - if (strcmp(token, "[") == 0) { - enum event_type last_type = type; - char *brackets = token; - int len; - - field->flags |= FIELD_IS_ARRAY; - - type = read_token(&token); - while (strcmp(token, "]") != 0) { - if (last_type == EVENT_ITEM && - type == EVENT_ITEM) - len = 2; - else - len = 1; - last_type = type; - - brackets = realloc(brackets, - strlen(brackets) + - strlen(token) + len); - if (len == 2) - strcat(brackets, " "); - strcat(brackets, token); - free_token(token); - type = read_token(&token); - if (type == EVENT_NONE) { - die("failed to find token"); - goto fail; - } - } - - free_token(token); - - brackets = realloc(brackets, strlen(brackets) + 2); - strcat(brackets, "]"); - - /* add brackets to type */ - - type = read_token(&token); - /* - * If the next token is not an OP, then it is of - * the format: type [] item; - */ - if (type == EVENT_ITEM) { - field->type = realloc(field->type, - strlen(field->type) + - strlen(field->name) + - strlen(brackets) + 2); - strcat(field->type, " "); - strcat(field->type, field->name); - free_token(field->name); - strcat(field->type, brackets); - field->name = token; - type = read_token(&token); - } else { - field->type = realloc(field->type, - strlen(field->type) + - strlen(brackets) + 1); - strcat(field->type, brackets); - } - free(brackets); - } - - if (field_is_string(field)) { - field->flags |= FIELD_IS_STRING; - if (field_is_dynamic(field)) - field->flags |= FIELD_IS_DYNAMIC; - } - - if (test_type_token(type, token, EVENT_OP, ";")) - goto fail; - free_token(token); - - if (read_expected(EVENT_ITEM, "offset") < 0) - goto fail_expect; - - if (read_expected(EVENT_OP, ":") < 0) - goto fail_expect; - - if (read_expect_type(EVENT_ITEM, &token)) - goto fail; - field->offset = strtoul(token, NULL, 0); - free_token(token); - - if (read_expected(EVENT_OP, ";") < 0) - goto fail_expect; - - if (read_expected(EVENT_ITEM, "size") < 0) - goto fail_expect; - - if (read_expected(EVENT_OP, ":") < 0) - goto fail_expect; - - if (read_expect_type(EVENT_ITEM, &token)) - goto fail; - field->size = strtoul(token, NULL, 0); - free_token(token); - - if (read_expected(EVENT_OP, ";") < 0) - goto fail_expect; - - type = read_token(&token); - if (type != EVENT_NEWLINE) { - /* newer versions of the kernel have a "signed" type */ - if (test_type_token(type, token, EVENT_ITEM, "signed")) - goto fail; - - free_token(token); - - if (read_expected(EVENT_OP, ":") < 0) - goto fail_expect; - - if (read_expect_type(EVENT_ITEM, &token)) - goto fail; - - if (strtoul(token, NULL, 0)) - field->flags |= FIELD_IS_SIGNED; - - free_token(token); - if (read_expected(EVENT_OP, ";") < 0) - goto fail_expect; - - if (read_expect_type(EVENT_NEWLINE, &token)) - goto fail; - } - - free_token(token); - - *fields = field; - fields = &field->next; - - } while (1); - - return 0; - -fail: - free_token(token); -fail_expect: - if (field) - free(field); - return -1; -} - -static int event_read_format(struct event *event) -{ - char *token; - int ret; - - if (read_expected_item(EVENT_ITEM, "format") < 0) - return -1; - - if (read_expected(EVENT_OP, ":") < 0) - return -1; - - if (read_expect_type(EVENT_NEWLINE, &token)) - goto fail; - free_token(token); - - ret = event_read_fields(event, &event->format.common_fields); - if (ret < 0) - return ret; - event->format.nr_common = ret; - - ret = event_read_fields(event, &event->format.fields); - if (ret < 0) - return ret; - event->format.nr_fields = ret; - - return 0; - - fail: - free_token(token); - return -1; -} - -enum event_type -process_arg_token(struct event *event, struct print_arg *arg, - char **tok, enum event_type type); - -static enum event_type -process_arg(struct event *event, struct print_arg *arg, char **tok) -{ - enum event_type type; - char *token; - - type = read_token(&token); - *tok = token; - - return process_arg_token(event, arg, tok, type); -} - -static enum event_type -process_cond(struct event *event, struct print_arg *top, char **tok) -{ - struct print_arg *arg, *left, *right; - enum event_type type; - char *token = NULL; - - arg = malloc_or_die(sizeof(*arg)); - memset(arg, 0, sizeof(*arg)); - - left = malloc_or_die(sizeof(*left)); - - right = malloc_or_die(sizeof(*right)); - - arg->type = PRINT_OP; - arg->op.left = left; - arg->op.right = right; - - *tok = NULL; - type = process_arg(event, left, &token); - if (test_type_token(type, token, EVENT_OP, ":")) - goto out_free; - - arg->op.op = token; - - type = process_arg(event, right, &token); - - top->op.right = arg; - - *tok = token; - return type; - -out_free: - free_token(*tok); - free(right); - free(left); - free_arg(arg); - return EVENT_ERROR; -} - -static enum event_type -process_array(struct event *event, struct print_arg *top, char **tok) -{ - struct print_arg *arg; - enum event_type type; - char *token = NULL; - - arg = malloc_or_die(sizeof(*arg)); - memset(arg, 0, sizeof(*arg)); - - *tok = NULL; - type = process_arg(event, arg, &token); - if (test_type_token(type, token, EVENT_OP, "]")) - goto out_free; - - top->op.right = arg; - - free_token(token); - type = read_token_item(&token); - *tok = token; - - return type; - -out_free: - free_token(*tok); - free_arg(arg); - return EVENT_ERROR; -} - -static int get_op_prio(char *op) -{ - if (!op[1]) { - switch (op[0]) { - case '*': - case '/': - case '%': - return 6; - case '+': - case '-': - return 7; - /* '>>' and '<<' are 8 */ - case '<': - case '>': - return 9; - /* '==' and '!=' are 10 */ - case '&': - return 11; - case '^': - return 12; - case '|': - return 13; - case '?': - return 16; - default: - die("unknown op '%c'", op[0]); - return -1; - } - } else { - if (strcmp(op, "++") == 0 || - strcmp(op, "--") == 0) { - return 3; - } else if (strcmp(op, ">>") == 0 || - strcmp(op, "<<") == 0) { - return 8; - } else if (strcmp(op, ">=") == 0 || - strcmp(op, "<=") == 0) { - return 9; - } else if (strcmp(op, "==") == 0 || - strcmp(op, "!=") == 0) { - return 10; - } else if (strcmp(op, "&&") == 0) { - return 14; - } else if (strcmp(op, "||") == 0) { - return 15; - } else { - die("unknown op '%s'", op); - return -1; - } - } -} - -static void set_op_prio(struct print_arg *arg) -{ - - /* single ops are the greatest */ - if (!arg->op.left || arg->op.left->type == PRINT_NULL) { - arg->op.prio = 0; - return; - } - - arg->op.prio = get_op_prio(arg->op.op); -} - -static enum event_type -process_op(struct event *event, struct print_arg *arg, char **tok) -{ - struct print_arg *left, *right = NULL; - enum event_type type; - char *token; - - /* the op is passed in via tok */ - token = *tok; - - if (arg->type == PRINT_OP && !arg->op.left) { - /* handle single op */ - if (token[1]) { - die("bad op token %s", token); - return EVENT_ERROR; - } - switch (token[0]) { - case '!': - case '+': - case '-': - break; - default: - die("bad op token %s", token); - return EVENT_ERROR; - } - - /* make an empty left */ - left = malloc_or_die(sizeof(*left)); - left->type = PRINT_NULL; - arg->op.left = left; - - right = malloc_or_die(sizeof(*right)); - arg->op.right = right; - - type = process_arg(event, right, tok); - - } else if (strcmp(token, "?") == 0) { - - left = malloc_or_die(sizeof(*left)); - /* copy the top arg to the left */ - *left = *arg; - - arg->type = PRINT_OP; - arg->op.op = token; - arg->op.left = left; - arg->op.prio = 0; - - type = process_cond(event, arg, tok); - - } else if (strcmp(token, ">>") == 0 || - strcmp(token, "<<") == 0 || - strcmp(token, "&") == 0 || - strcmp(token, "|") == 0 || - strcmp(token, "&&") == 0 || - strcmp(token, "||") == 0 || - strcmp(token, "-") == 0 || - strcmp(token, "+") == 0 || - strcmp(token, "*") == 0 || - strcmp(token, "^") == 0 || - strcmp(token, "/") == 0 || - strcmp(token, "<") == 0 || - strcmp(token, ">") == 0 || - strcmp(token, "==") == 0 || - strcmp(token, "!=") == 0) { - - left = malloc_or_die(sizeof(*left)); - - /* copy the top arg to the left */ - *left = *arg; - - arg->type = PRINT_OP; - arg->op.op = token; - arg->op.left = left; - - set_op_prio(arg); - - right = malloc_or_die(sizeof(*right)); - - type = read_token_item(&token); - *tok = token; - - /* could just be a type pointer */ - if ((strcmp(arg->op.op, "*") == 0) && - type == EVENT_DELIM && (strcmp(token, ")") == 0)) { - if (left->type != PRINT_ATOM) - die("bad pointer type"); - left->atom.atom = realloc(left->atom.atom, - sizeof(left->atom.atom) + 3); - strcat(left->atom.atom, " *"); - *arg = *left; - free(arg); - - return type; - } - - type = process_arg_token(event, right, tok, type); - - arg->op.right = right; - - } else if (strcmp(token, "[") == 0) { - - left = malloc_or_die(sizeof(*left)); - *left = *arg; - - arg->type = PRINT_OP; - arg->op.op = token; - arg->op.left = left; - - arg->op.prio = 0; - type = process_array(event, arg, tok); - - } else { - warning("unknown op '%s'", token); - event->flags |= EVENT_FL_FAILED; - /* the arg is now the left side */ - return EVENT_NONE; - } - - if (type == EVENT_OP) { - int prio; - - /* higher prios need to be closer to the root */ - prio = get_op_prio(*tok); - - if (prio > arg->op.prio) - return process_op(event, arg, tok); - - return process_op(event, right, tok); - } - - return type; -} - -static enum event_type -process_entry(struct event *event __unused, struct print_arg *arg, - char **tok) -{ - enum event_type type; - char *field; - char *token; - - if (read_expected(EVENT_OP, "->") < 0) - return EVENT_ERROR; - - if (read_expect_type(EVENT_ITEM, &token) < 0) - goto fail; - field = token; - - arg->type = PRINT_FIELD; - arg->field.name = field; - - if (is_flag_field) { - arg->field.field = find_any_field(event, arg->field.name); - arg->field.field->flags |= FIELD_IS_FLAG; - is_flag_field = 0; - } else if (is_symbolic_field) { - arg->field.field = find_any_field(event, arg->field.name); - arg->field.field->flags |= FIELD_IS_SYMBOLIC; - is_symbolic_field = 0; + if (!event) { + idx = 0; + return pevent->events[0]; } - type = read_token(&token); - *tok = token; - - return type; - -fail: - free_token(token); - return EVENT_ERROR; -} - -static char *arg_eval (struct print_arg *arg); - -static long long arg_num_eval(struct print_arg *arg) -{ - long long left, right; - long long val = 0; - - switch (arg->type) { - case PRINT_ATOM: - val = strtoll(arg->atom.atom, NULL, 0); - break; - case PRINT_TYPE: - val = arg_num_eval(arg->typecast.item); - break; - case PRINT_OP: - switch (arg->op.op[0]) { - case '|': - left = arg_num_eval(arg->op.left); - right = arg_num_eval(arg->op.right); - if (arg->op.op[1]) - val = left || right; - else - val = left | right; - break; - case '&': - left = arg_num_eval(arg->op.left); - right = arg_num_eval(arg->op.right); - if (arg->op.op[1]) - val = left && right; - else - val = left & right; - break; - case '<': - left = arg_num_eval(arg->op.left); - right = arg_num_eval(arg->op.right); - switch (arg->op.op[1]) { - case 0: - val = left < right; - break; - case '<': - val = left << right; - break; - case '=': - val = left <= right; - break; - default: - die("unknown op '%s'", arg->op.op); - } - break; - case '>': - left = arg_num_eval(arg->op.left); - right = arg_num_eval(arg->op.right); - switch (arg->op.op[1]) { - case 0: - val = left > right; - break; - case '>': - val = left >> right; - break; - case '=': - val = left >= right; - break; - default: - die("unknown op '%s'", arg->op.op); - } - break; - case '=': - left = arg_num_eval(arg->op.left); - right = arg_num_eval(arg->op.right); - - if (arg->op.op[1] != '=') - die("unknown op '%s'", arg->op.op); - - val = left == right; - break; - case '!': - left = arg_num_eval(arg->op.left); - right = arg_num_eval(arg->op.right); - - switch (arg->op.op[1]) { - case '=': - val = left != right; - break; - default: - die("unknown op '%s'", arg->op.op); - } - break; - default: - die("unknown op '%s'", arg->op.op); - } - break; - - case PRINT_NULL: - case PRINT_FIELD ... PRINT_SYMBOL: - case PRINT_STRING: - default: - die("invalid eval type %d", arg->type); - + if (idx < pevent->nr_events && event == pevent->events[idx]) { + idx++; + if (idx == pevent->nr_events) + return NULL; + return pevent->events[idx]; } - return val; -} - -static char *arg_eval (struct print_arg *arg) -{ - long long val; - static char buf[20]; - - switch (arg->type) { - case PRINT_ATOM: - return arg->atom.atom; - case PRINT_TYPE: - return arg_eval(arg->typecast.item); - case PRINT_OP: - val = arg_num_eval(arg); - sprintf(buf, "%lld", val); - return buf; - case PRINT_NULL: - case PRINT_FIELD ... PRINT_SYMBOL: - case PRINT_STRING: - default: - die("invalid eval type %d", arg->type); - break; + for (idx = 1; idx < pevent->nr_events; idx++) { + if (event == pevent->events[idx - 1]) + return pevent->events[idx]; } - return NULL; } -static enum event_type -process_fields(struct event *event, struct print_flag_sym **list, char **tok) -{ - enum event_type type; - struct print_arg *arg = NULL; - struct print_flag_sym *field; - char *token = NULL; - char *value; - - do { - free_token(token); - type = read_token_item(&token); - if (test_type_token(type, token, EVENT_OP, "{")) - break; - - arg = malloc_or_die(sizeof(*arg)); - - free_token(token); - type = process_arg(event, arg, &token); - if (test_type_token(type, token, EVENT_DELIM, ",")) - goto out_free; - - field = malloc_or_die(sizeof(*field)); - memset(field, 0, sizeof(*field)); - - value = arg_eval(arg); - field->value = strdup(value); - - free_token(token); - type = process_arg(event, arg, &token); - if (test_type_token(type, token, EVENT_OP, "}")) - goto out_free; - - value = arg_eval(arg); - field->str = strdup(value); - free_arg(arg); - arg = NULL; - - *list = field; - list = &field->next; - - free_token(token); - type = read_token_item(&token); - } while (type == EVENT_DELIM && strcmp(token, ",") == 0); - - *tok = token; - return type; - -out_free: - free_arg(arg); - free_token(token); - - return EVENT_ERROR; -} - -static enum event_type -process_flags(struct event *event, struct print_arg *arg, char **tok) -{ - struct print_arg *field; - enum event_type type; - char *token; - - memset(arg, 0, sizeof(*arg)); - arg->type = PRINT_FLAGS; - - if (read_expected_item(EVENT_DELIM, "(") < 0) - return EVENT_ERROR; - - field = malloc_or_die(sizeof(*field)); - - type = process_arg(event, field, &token); - if (test_type_token(type, token, EVENT_DELIM, ",")) - goto out_free; - - arg->flags.field = field; - - type = read_token_item(&token); - if (event_item_type(type)) { - arg->flags.delim = token; - type = read_token_item(&token); - } - - if (test_type_token(type, token, EVENT_DELIM, ",")) - goto out_free; - - type = process_fields(event, &arg->flags.flags, &token); - if (test_type_token(type, token, EVENT_DELIM, ")")) - goto out_free; - - free_token(token); - type = read_token_item(tok); - return type; - -out_free: - free_token(token); - return EVENT_ERROR; -} - -static enum event_type -process_symbols(struct event *event, struct print_arg *arg, char **tok) -{ - struct print_arg *field; - enum event_type type; - char *token; - - memset(arg, 0, sizeof(*arg)); - arg->type = PRINT_SYMBOL; - - if (read_expected_item(EVENT_DELIM, "(") < 0) - return EVENT_ERROR; - - field = malloc_or_die(sizeof(*field)); - - type = process_arg(event, field, &token); - if (test_type_token(type, token, EVENT_DELIM, ",")) - goto out_free; - - arg->symbol.field = field; - - type = process_fields(event, &arg->symbol.symbols, &token); - if (test_type_token(type, token, EVENT_DELIM, ")")) - goto out_free; - - free_token(token); - type = read_token_item(tok); - return type; - -out_free: - free_token(token); - return EVENT_ERROR; -} - -static enum event_type -process_paren(struct event *event, struct print_arg *arg, char **tok) -{ - struct print_arg *item_arg; - enum event_type type; - char *token; - - type = process_arg(event, arg, &token); - - if (type == EVENT_ERROR) - return EVENT_ERROR; - - if (type == EVENT_OP) - type = process_op(event, arg, &token); - - if (type == EVENT_ERROR) - return EVENT_ERROR; - - if (test_type_token(type, token, EVENT_DELIM, ")")) { - free_token(token); - return EVENT_ERROR; - } - - free_token(token); - type = read_token_item(&token); - - /* - * If the next token is an item or another open paren, then - * this was a typecast. - */ - if (event_item_type(type) || - (type == EVENT_DELIM && strcmp(token, "(") == 0)) { - - /* make this a typecast and contine */ - - /* prevous must be an atom */ - if (arg->type != PRINT_ATOM) - die("previous needed to be PRINT_ATOM"); - - item_arg = malloc_or_die(sizeof(*item_arg)); - - arg->type = PRINT_TYPE; - arg->typecast.type = arg->atom.atom; - arg->typecast.item = item_arg; - type = process_arg_token(event, item_arg, &token, type); - - } - - *tok = token; - return type; -} - - -static enum event_type -process_str(struct event *event __unused, struct print_arg *arg, char **tok) -{ - enum event_type type; - char *token; - - if (read_expected(EVENT_DELIM, "(") < 0) - return EVENT_ERROR; - - if (read_expect_type(EVENT_ITEM, &token) < 0) - goto fail; - - arg->type = PRINT_STRING; - arg->string.string = token; - arg->string.offset = -1; - - if (read_expected(EVENT_DELIM, ")") < 0) - return EVENT_ERROR; - - type = read_token(&token); - *tok = token; - - return type; -fail: - free_token(token); - return EVENT_ERROR; -} - -enum event_type -process_arg_token(struct event *event, struct print_arg *arg, - char **tok, enum event_type type) -{ - char *token; - char *atom; - - token = *tok; - - switch (type) { - case EVENT_ITEM: - if (strcmp(token, "REC") == 0) { - free_token(token); - type = process_entry(event, arg, &token); - } else if (strcmp(token, "__print_flags") == 0) { - free_token(token); - is_flag_field = 1; - type = process_flags(event, arg, &token); - } else if (strcmp(token, "__print_symbolic") == 0) { - free_token(token); - is_symbolic_field = 1; - type = process_symbols(event, arg, &token); - } else if (strcmp(token, "__get_str") == 0) { - free_token(token); - type = process_str(event, arg, &token); - } else { - atom = token; - /* test the next token */ - type = read_token_item(&token); - - /* atoms can be more than one token long */ - while (type == EVENT_ITEM) { - atom = realloc(atom, strlen(atom) + strlen(token) + 2); - strcat(atom, " "); - strcat(atom, token); - free_token(token); - type = read_token_item(&token); - } - - /* todo, test for function */ - - arg->type = PRINT_ATOM; - arg->atom.atom = atom; - } - break; - case EVENT_DQUOTE: - case EVENT_SQUOTE: - arg->type = PRINT_ATOM; - arg->atom.atom = token; - type = read_token_item(&token); - break; - case EVENT_DELIM: - if (strcmp(token, "(") == 0) { - free_token(token); - type = process_paren(event, arg, &token); - break; - } - case EVENT_OP: - /* handle single ops */ - arg->type = PRINT_OP; - arg->op.op = token; - arg->op.left = NULL; - type = process_op(event, arg, &token); - - break; - - case EVENT_ERROR ... EVENT_NEWLINE: - default: - die("unexpected type %d", type); - } - *tok = token; - - return type; -} - -static int event_read_print_args(struct event *event, struct print_arg **list) -{ - enum event_type type = EVENT_ERROR; - struct print_arg *arg; - char *token; - int args = 0; - - do { - if (type == EVENT_NEWLINE) { - free_token(token); - type = read_token_item(&token); - continue; - } - - arg = malloc_or_die(sizeof(*arg)); - memset(arg, 0, sizeof(*arg)); - - type = process_arg(event, arg, &token); - - if (type == EVENT_ERROR) { - free_arg(arg); - return -1; - } - - *list = arg; - args++; - - if (type == EVENT_OP) { - type = process_op(event, arg, &token); - list = &arg->next; - continue; - } - - if (type == EVENT_DELIM && strcmp(token, ",") == 0) { - free_token(token); - *list = arg; - list = &arg->next; - continue; - } - break; - } while (type != EVENT_NONE); - - if (type != EVENT_NONE) - free_token(token); - - return args; -} - -static int event_read_print(struct event *event) -{ - enum event_type type; - char *token; - int ret; - - if (read_expected_item(EVENT_ITEM, "print") < 0) - return -1; - - if (read_expected(EVENT_ITEM, "fmt") < 0) - return -1; - - if (read_expected(EVENT_OP, ":") < 0) - return -1; - - if (read_expect_type(EVENT_DQUOTE, &token) < 0) - goto fail; - - concat: - event->print_fmt.format = token; - event->print_fmt.args = NULL; - - /* ok to have no arg */ - type = read_token_item(&token); - - if (type == EVENT_NONE) - return 0; - - /* Handle concatination of print lines */ - if (type == EVENT_DQUOTE) { - char *cat; - - cat = malloc_or_die(strlen(event->print_fmt.format) + - strlen(token) + 1); - strcpy(cat, event->print_fmt.format); - strcat(cat, token); - free_token(token); - free_token(event->print_fmt.format); - event->print_fmt.format = NULL; - token = cat; - goto concat; - } - - if (test_type_token(type, token, EVENT_DELIM, ",")) - goto fail; - - free_token(token); - - ret = event_read_print_args(event, &event->print_fmt.args); - if (ret < 0) - return -1; - - return ret; - - fail: - free_token(token); - return -1; -} - -static struct format_field * -find_common_field(struct event *event, const char *name) -{ - struct format_field *format; - - for (format = event->format.common_fields; - format; format = format->next) { - if (strcmp(format->name, name) == 0) - break; - } - - return format; -} - -static struct format_field * -find_field(struct event *event, const char *name) -{ - struct format_field *format; - - for (format = event->format.fields; - format; format = format->next) { - if (strcmp(format->name, name) == 0) - break; - } - - return format; -} - -static struct format_field * -find_any_field(struct event *event, const char *name) -{ - struct format_field *format; - - format = find_common_field(event, name); - if (format) - return format; - return find_field(event, name); -} - -unsigned long long read_size(void *ptr, int size) -{ - switch (size) { - case 1: - return *(unsigned char *)ptr; - case 2: - return data2host2(ptr); - case 4: - return data2host4(ptr); - case 8: - return data2host8(ptr); - default: - /* BUG! */ - return 0; - } -} - -unsigned long long -raw_field_value(struct event *event, const char *name, void *data) -{ - struct format_field *field; - - field = find_any_field(event, name); - if (!field) - return 0ULL; - - return read_size(data + field->offset, field->size); -} - -void *raw_field_ptr(struct event *event, const char *name, void *data) -{ - struct format_field *field; - - field = 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; -} - -static int get_common_info(const char *type, int *offset, int *size) -{ - struct event *event; - struct format_field *field; - - /* - * All events should have the same common elements. - * Pick any event to find where the type is; - */ - if (!event_list) - die("no event_list!"); - - event = event_list; - field = find_common_field(event, type); - if (!field) - die("field '%s' not found", type); - - *offset = field->offset; - *size = field->size; - - return 0; -} - -static int __parse_common(void *data, int *size, int *offset, - const char *name) -{ - int ret; - - if (!*size) { - ret = get_common_info(name, offset, size); - if (ret < 0) - return ret; - } - return read_size(data + *offset, *size); -} - -int trace_parse_common_type(void *data) -{ - static int type_offset; - static int type_size; - - return __parse_common(data, &type_size, &type_offset, - "common_type"); -} - -int trace_parse_common_pid(void *data) -{ - static int pid_offset; - static int pid_size; - - return __parse_common(data, &pid_size, &pid_offset, - "common_pid"); -} - -int parse_common_pc(void *data) -{ - static int pc_offset; - static int pc_size; - - return __parse_common(data, &pc_size, &pc_offset, - "common_preempt_count"); -} - -int parse_common_flags(void *data) -{ - static int flags_offset; - static int flags_size; - - return __parse_common(data, &flags_size, &flags_offset, - "common_flags"); -} - -int parse_common_lock_depth(void *data) -{ - static int ld_offset; - static int ld_size; - int ret; - - ret = __parse_common(data, &ld_size, &ld_offset, - "common_lock_depth"); - if (ret < 0) - return -1; - - return ret; -} - -struct event *trace_find_event(int id) -{ - struct event *event; - - for (event = event_list; event; event = event->next) { - if (event->id == id) - break; - } - return event; -} - -struct event *trace_find_next_event(struct event *event) -{ - if (!event) - return event_list; - - return event->next; -} - -static unsigned long long eval_num_arg(void *data, int size, - struct event *event, struct print_arg *arg) -{ - unsigned long long val = 0; - unsigned long long left, right; - struct print_arg *larg; - - switch (arg->type) { - case PRINT_NULL: - /* ?? */ - return 0; - case PRINT_ATOM: - return strtoull(arg->atom.atom, NULL, 0); - case PRINT_FIELD: - if (!arg->field.field) { - arg->field.field = find_any_field(event, arg->field.name); - if (!arg->field.field) - die("field %s not found", arg->field.name); - } - /* must be a number */ - val = read_size(data + arg->field.field->offset, - arg->field.field->size); - break; - case PRINT_FLAGS: - case PRINT_SYMBOL: - break; - case PRINT_TYPE: - return eval_num_arg(data, size, event, arg->typecast.item); - case PRINT_STRING: - return 0; - break; - case PRINT_OP: - if (strcmp(arg->op.op, "[") == 0) { - /* - * Arrays are special, since we don't want - * to read the arg as is. - */ - if (arg->op.left->type != PRINT_FIELD) - goto default_op; /* oops, all bets off */ - larg = arg->op.left; - if (!larg->field.field) { - larg->field.field = - find_any_field(event, larg->field.name); - if (!larg->field.field) - die("field %s not found", larg->field.name); - } - right = eval_num_arg(data, size, event, arg->op.right); - val = read_size(data + larg->field.field->offset + - right * long_size, long_size); - break; - } - default_op: - left = eval_num_arg(data, size, event, arg->op.left); - right = eval_num_arg(data, size, event, arg->op.right); - switch (arg->op.op[0]) { - case '|': - if (arg->op.op[1]) - val = left || right; - else - val = left | right; - break; - case '&': - if (arg->op.op[1]) - val = left && right; - else - val = left & right; - break; - case '<': - switch (arg->op.op[1]) { - case 0: - val = left < right; - break; - case '<': - val = left << right; - break; - case '=': - val = left <= right; - break; - default: - die("unknown op '%s'", arg->op.op); - } - break; - case '>': - switch (arg->op.op[1]) { - case 0: - val = left > right; - break; - case '>': - val = left >> right; - break; - case '=': - val = left >= right; - break; - default: - die("unknown op '%s'", arg->op.op); - } - break; - case '=': - if (arg->op.op[1] != '=') - die("unknown op '%s'", arg->op.op); - val = left == right; - break; - case '-': - val = left - right; - break; - case '+': - val = left + right; - break; - default: - die("unknown op '%s'", arg->op.op); - } - break; - default: /* not sure what to do there */ - return 0; - } - return val; -} - struct flag { const char *name; unsigned long long value; @@ -2211,1023 +261,3 @@ unsigned long long eval_flag(const char *flag) return 0; } - -static void print_str_arg(void *data, int size, - struct event *event, struct print_arg *arg) -{ - struct print_flag_sym *flag; - unsigned long long val, fval; - char *str; - int print; - - switch (arg->type) { - case PRINT_NULL: - /* ?? */ - return; - case PRINT_ATOM: - printf("%s", arg->atom.atom); - return; - case PRINT_FIELD: - if (!arg->field.field) { - arg->field.field = find_any_field(event, arg->field.name); - if (!arg->field.field) - die("field %s not found", arg->field.name); - } - str = malloc_or_die(arg->field.field->size + 1); - memcpy(str, data + arg->field.field->offset, - arg->field.field->size); - str[arg->field.field->size] = 0; - printf("%s", str); - free(str); - break; - case PRINT_FLAGS: - val = eval_num_arg(data, size, event, arg->flags.field); - print = 0; - for (flag = arg->flags.flags; flag; flag = flag->next) { - fval = eval_flag(flag->value); - if (!val && !fval) { - printf("%s", flag->str); - break; - } - if (fval && (val & fval) == fval) { - if (print && arg->flags.delim) - printf("%s", arg->flags.delim); - printf("%s", flag->str); - print = 1; - val &= ~fval; - } - } - break; - case PRINT_SYMBOL: - val = eval_num_arg(data, size, event, arg->symbol.field); - for (flag = arg->symbol.symbols; flag; flag = flag->next) { - fval = eval_flag(flag->value); - if (val == fval) { - printf("%s", flag->str); - break; - } - } - break; - - case PRINT_TYPE: - break; - case PRINT_STRING: { - int str_offset; - - if (arg->string.offset == -1) { - struct format_field *f; - - f = find_any_field(event, arg->string.string); - arg->string.offset = f->offset; - } - str_offset = *(int *)(data + arg->string.offset); - str_offset &= 0xffff; - printf("%s", ((char *)data) + str_offset); - break; - } - case PRINT_OP: - /* - * The only op for string should be ? : - */ - if (arg->op.op[0] != '?') - return; - val = eval_num_arg(data, size, event, arg->op.left); - if (val) - print_str_arg(data, size, event, arg->op.right->op.left); - else - print_str_arg(data, size, event, arg->op.right->op.right); - break; - default: - /* well... */ - break; - } -} - -static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struct event *event) -{ - static struct format_field *field, *ip_field; - struct print_arg *args, *arg, **next; - unsigned long long ip, val; - char *ptr; - void *bptr; - - if (!field) { - field = find_field(event, "buf"); - if (!field) - die("can't find buffer field for binary printk"); - ip_field = find_field(event, "ip"); - if (!ip_field) - die("can't find ip field for binary printk"); - } - - ip = read_size(data + ip_field->offset, ip_field->size); - - /* - * The first arg is the IP pointer. - */ - args = malloc_or_die(sizeof(*args)); - arg = args; - arg->next = NULL; - next = &arg->next; - - arg->type = PRINT_ATOM; - arg->atom.atom = malloc_or_die(32); - sprintf(arg->atom.atom, "%lld", ip); - - /* skip the first "%pf : " */ - for (ptr = fmt + 6, bptr = data + field->offset; - bptr < data + size && *ptr; ptr++) { - int ls = 0; - - if (*ptr == '%') { - process_again: - ptr++; - switch (*ptr) { - case '%': - break; - case 'l': - ls++; - goto process_again; - case 'L': - ls = 2; - goto process_again; - case '0' ... '9': - goto process_again; - case 'p': - ls = 1; - /* fall through */ - case 'd': - case 'u': - case 'x': - case 'i': - /* the pointers are always 4 bytes aligned */ - bptr = (void *)(((unsigned long)bptr + 3) & - ~3); - switch (ls) { - case 0: - case 1: - ls = long_size; - break; - case 2: - ls = 8; - default: - break; - } - val = read_size(bptr, ls); - bptr += ls; - arg = malloc_or_die(sizeof(*arg)); - arg->next = NULL; - arg->type = PRINT_ATOM; - arg->atom.atom = malloc_or_die(32); - sprintf(arg->atom.atom, "%lld", val); - *next = arg; - next = &arg->next; - break; - case 's': - arg = malloc_or_die(sizeof(*arg)); - arg->next = NULL; - arg->type = PRINT_STRING; - arg->string.string = strdup(bptr); - bptr += strlen(bptr) + 1; - *next = arg; - next = &arg->next; - default: - break; - } - } - } - - return args; -} - -static void free_args(struct print_arg *args) -{ - struct print_arg *next; - - while (args) { - next = args->next; - - if (args->type == PRINT_ATOM) - free(args->atom.atom); - else - free(args->string.string); - free(args); - args = next; - } -} - -static char *get_bprint_format(void *data, int size __unused, struct event *event) -{ - unsigned long long addr; - static struct format_field *field; - struct printk_map *printk; - char *format; - char *p; - - if (!field) { - field = find_field(event, "fmt"); - if (!field) - die("can't find format field for binary printk"); - printf("field->offset = %d size=%d\n", field->offset, field->size); - } - - addr = read_size(data + field->offset, field->size); - - printk = find_printk(addr); - if (!printk) { - format = malloc_or_die(45); - sprintf(format, "%%pf : (NO FORMAT FOUND at %llx)\n", - addr); - return format; - } - - p = printk->printk; - /* Remove any quotes. */ - if (*p == '"') - p++; - format = malloc_or_die(strlen(p) + 10); - sprintf(format, "%s : %s", "%pf", p); - /* remove ending quotes and new line since we will add one too */ - p = format + strlen(format) - 1; - if (*p == '"') - *p = 0; - - p -= 2; - if (strcmp(p, "\\n") == 0) - *p = 0; - - return format; -} - -static void pretty_print(void *data, int size, struct event *event) -{ - struct print_fmt *print_fmt = &event->print_fmt; - struct print_arg *arg = print_fmt->args; - struct print_arg *args = NULL; - const char *ptr = print_fmt->format; - unsigned long long val; - struct func_map *func; - const char *saveptr; - char *bprint_fmt = NULL; - char format[32]; - int show_func; - int len; - int ls; - - if (event->flags & EVENT_FL_ISFUNC) - ptr = " %pF <-- %pF"; - - if (event->flags & EVENT_FL_ISBPRINT) { - bprint_fmt = get_bprint_format(data, size, event); - args = make_bprint_args(bprint_fmt, data, size, event); - arg = args; - ptr = bprint_fmt; - } - - for (; *ptr; ptr++) { - ls = 0; - if (*ptr == '\\') { - ptr++; - switch (*ptr) { - case 'n': - printf("\n"); - break; - case 't': - printf("\t"); - break; - case 'r': - printf("\r"); - break; - case '\\': - printf("\\"); - break; - default: - printf("%c", *ptr); - break; - } - - } else if (*ptr == '%') { - saveptr = ptr; - show_func = 0; - cont_process: - ptr++; - switch (*ptr) { - case '%': - printf("%%"); - break; - case 'l': - ls++; - goto cont_process; - case 'L': - ls = 2; - goto cont_process; - case 'z': - case 'Z': - case '0' ... '9': - goto cont_process; - case 'p': - if (long_size == 4) - ls = 1; - else - ls = 2; - - if (*(ptr+1) == 'F' || - *(ptr+1) == 'f') { - ptr++; - show_func = *ptr; - } - - /* fall through */ - case 'd': - case 'i': - case 'x': - case 'X': - case 'u': - if (!arg) - die("no argument match"); - - len = ((unsigned long)ptr + 1) - - (unsigned long)saveptr; - - /* should never happen */ - if (len > 32) - die("bad format!"); - - memcpy(format, saveptr, len); - format[len] = 0; - - val = eval_num_arg(data, size, event, arg); - arg = arg->next; - - if (show_func) { - func = find_func(val); - if (func) { - printf("%s", func->func); - if (show_func == 'F') - printf("+0x%llx", - val - func->addr); - break; - } - } - switch (ls) { - case 0: - printf(format, (int)val); - break; - case 1: - printf(format, (long)val); - break; - case 2: - printf(format, (long long)val); - break; - default: - die("bad count (%d)", ls); - } - break; - case 's': - if (!arg) - die("no matching argument"); - - print_str_arg(data, size, event, arg); - arg = arg->next; - break; - default: - printf(">%c<", *ptr); - - } - } else - printf("%c", *ptr); - } - - if (args) { - free_args(args); - free(bprint_fmt); - } -} - -static inline int log10_cpu(int nb) -{ - if (nb / 100) - return 3; - if (nb / 10) - return 2; - return 1; -} - -static void print_lat_fmt(void *data, int size __unused) -{ - unsigned int lat_flags; - unsigned int pc; - int lock_depth; - int hardirq; - int softirq; - - lat_flags = parse_common_flags(data); - pc = parse_common_pc(data); - lock_depth = parse_common_lock_depth(data); - - hardirq = lat_flags & TRACE_FLAG_HARDIRQ; - softirq = lat_flags & TRACE_FLAG_SOFTIRQ; - - printf("%c%c%c", - (lat_flags & TRACE_FLAG_IRQS_OFF) ? 'd' : - (lat_flags & TRACE_FLAG_IRQS_NOSUPPORT) ? - 'X' : '.', - (lat_flags & TRACE_FLAG_NEED_RESCHED) ? - 'N' : '.', - (hardirq && softirq) ? 'H' : - hardirq ? 'h' : softirq ? 's' : '.'); - - if (pc) - printf("%x", pc); - else - printf("."); - - if (lock_depth < 0) - printf("."); - else - printf("%d", lock_depth); -} - -/* taken from Linux, written by Frederic Weisbecker */ -static void print_graph_cpu(int cpu) -{ - int i; - int log10_this = log10_cpu(cpu); - int log10_all = log10_cpu(cpus); - - - /* - * Start with a space character - to make it stand out - * to the right a bit when trace output is pasted into - * email: - */ - printf(" "); - - /* - * Tricky - we space the CPU field according to the max - * number of online CPUs. On a 2-cpu system it would take - * a maximum of 1 digit - on a 128 cpu system it would - * take up to 3 digits: - */ - for (i = 0; i < log10_all - log10_this; i++) - printf(" "); - - printf("%d) ", cpu); -} - -#define TRACE_GRAPH_PROCINFO_LENGTH 14 -#define TRACE_GRAPH_INDENT 2 - -static void print_graph_proc(int pid, const char *comm) -{ - /* sign + log10(MAX_INT) + '\0' */ - char pid_str[11]; - int spaces = 0; - int len; - int i; - - sprintf(pid_str, "%d", pid); - - /* 1 stands for the "-" character */ - len = strlen(comm) + strlen(pid_str) + 1; - - if (len < TRACE_GRAPH_PROCINFO_LENGTH) - spaces = TRACE_GRAPH_PROCINFO_LENGTH - len; - - /* First spaces to align center */ - for (i = 0; i < spaces / 2; i++) - printf(" "); - - printf("%s-%s", comm, pid_str); - - /* Last spaces to align center */ - for (i = 0; i < spaces - (spaces / 2); i++) - printf(" "); -} - -static struct record * -get_return_for_leaf(int cpu, int cur_pid, unsigned long long cur_func, - struct record *next) -{ - struct format_field *field; - struct event *event; - unsigned long val; - int type; - int pid; - - type = trace_parse_common_type(next->data); - event = trace_find_event(type); - if (!event) - return NULL; - - if (!(event->flags & EVENT_FL_ISFUNCRET)) - return NULL; - - pid = trace_parse_common_pid(next->data); - field = find_field(event, "func"); - if (!field) - die("function return does not have field func"); - - val = read_size(next->data + field->offset, field->size); - - if (cur_pid != pid || cur_func != val) - return NULL; - - /* this is a leaf, now advance the iterator */ - return trace_read_data(cpu); -} - -/* Signal a overhead of time execution to the output */ -static void print_graph_overhead(unsigned long long duration) -{ - /* Non nested entry or return */ - if (duration == ~0ULL) - return (void)printf(" "); - - /* Duration exceeded 100 msecs */ - if (duration > 100000ULL) - return (void)printf("! "); - - /* Duration exceeded 10 msecs */ - if (duration > 10000ULL) - return (void)printf("+ "); - - printf(" "); -} - -static void print_graph_duration(unsigned long long duration) -{ - unsigned long usecs = duration / 1000; - unsigned long nsecs_rem = duration % 1000; - /* log10(ULONG_MAX) + '\0' */ - char msecs_str[21]; - char nsecs_str[5]; - int len; - int i; - - sprintf(msecs_str, "%lu", usecs); - - /* Print msecs */ - len = printf("%lu", usecs); - - /* Print nsecs (we don't want to exceed 7 numbers) */ - if (len < 7) { - snprintf(nsecs_str, 8 - len, "%03lu", nsecs_rem); - len += printf(".%s", nsecs_str); - } - - printf(" us "); - - /* Print remaining spaces to fit the row's width */ - for (i = len; i < 7; i++) - printf(" "); - - printf("| "); -} - -static void -print_graph_entry_leaf(struct event *event, void *data, struct record *ret_rec) -{ - unsigned long long rettime, calltime; - unsigned long long duration, depth; - unsigned long long val; - struct format_field *field; - struct func_map *func; - struct event *ret_event; - int type; - int i; - - type = trace_parse_common_type(ret_rec->data); - ret_event = trace_find_event(type); - - field = find_field(ret_event, "rettime"); - if (!field) - die("can't find rettime in return graph"); - rettime = read_size(ret_rec->data + field->offset, field->size); - - field = find_field(ret_event, "calltime"); - if (!field) - die("can't find rettime in return graph"); - calltime = read_size(ret_rec->data + field->offset, field->size); - - duration = rettime - calltime; - - /* Overhead */ - print_graph_overhead(duration); - - /* Duration */ - print_graph_duration(duration); - - field = find_field(event, "depth"); - if (!field) - die("can't find depth in entry graph"); - depth = read_size(data + field->offset, field->size); - - /* Function */ - for (i = 0; i < (int)(depth * TRACE_GRAPH_INDENT); i++) - printf(" "); - - field = find_field(event, "func"); - if (!field) - die("can't find func in entry graph"); - val = read_size(data + field->offset, field->size); - func = find_func(val); - - if (func) - printf("%s();", func->func); - else - printf("%llx();", val); -} - -static void print_graph_nested(struct event *event, void *data) -{ - struct format_field *field; - unsigned long long depth; - unsigned long long val; - struct func_map *func; - int i; - - /* No overhead */ - print_graph_overhead(-1); - - /* No time */ - printf(" | "); - - field = find_field(event, "depth"); - if (!field) - die("can't find depth in entry graph"); - depth = read_size(data + field->offset, field->size); - - /* Function */ - for (i = 0; i < (int)(depth * TRACE_GRAPH_INDENT); i++) - printf(" "); - - field = find_field(event, "func"); - if (!field) - die("can't find func in entry graph"); - val = read_size(data + field->offset, field->size); - func = find_func(val); - - if (func) - printf("%s() {", func->func); - else - printf("%llx() {", val); -} - -static void -pretty_print_func_ent(void *data, int size, struct event *event, - int cpu, int pid, const char *comm, - unsigned long secs, unsigned long usecs) -{ - struct format_field *field; - struct record *rec; - void *copy_data; - unsigned long val; - - printf("%5lu.%06lu | ", secs, usecs); - - print_graph_cpu(cpu); - print_graph_proc(pid, comm); - - printf(" | "); - - if (latency_format) { - print_lat_fmt(data, size); - printf(" | "); - } - - field = find_field(event, "func"); - if (!field) - die("function entry does not have func field"); - - val = read_size(data + field->offset, field->size); - - /* - * peek_data may unmap the data pointer. Copy it first. - */ - copy_data = malloc_or_die(size); - memcpy(copy_data, data, size); - data = copy_data; - - rec = trace_peek_data(cpu); - if (rec) { - rec = get_return_for_leaf(cpu, pid, val, rec); - if (rec) { - print_graph_entry_leaf(event, data, rec); - goto out_free; - } - } - print_graph_nested(event, data); -out_free: - free(data); -} - -static void -pretty_print_func_ret(void *data, int size __unused, struct event *event, - int cpu, int pid, const char *comm, - unsigned long secs, unsigned long usecs) -{ - unsigned long long rettime, calltime; - unsigned long long duration, depth; - struct format_field *field; - int i; - - printf("%5lu.%06lu | ", secs, usecs); - - print_graph_cpu(cpu); - print_graph_proc(pid, comm); - - printf(" | "); - - if (latency_format) { - print_lat_fmt(data, size); - printf(" | "); - } - - field = find_field(event, "rettime"); - if (!field) - die("can't find rettime in return graph"); - rettime = read_size(data + field->offset, field->size); - - field = find_field(event, "calltime"); - if (!field) - die("can't find calltime in return graph"); - calltime = read_size(data + field->offset, field->size); - - duration = rettime - calltime; - - /* Overhead */ - print_graph_overhead(duration); - - /* Duration */ - print_graph_duration(duration); - - field = find_field(event, "depth"); - if (!field) - die("can't find depth in entry graph"); - depth = read_size(data + field->offset, field->size); - - /* Function */ - for (i = 0; i < (int)(depth * TRACE_GRAPH_INDENT); i++) - printf(" "); - - printf("}"); -} - -static void -pretty_print_func_graph(void *data, int size, struct event *event, - int cpu, int pid, const char *comm, - unsigned long secs, unsigned long usecs) -{ - if (event->flags & EVENT_FL_ISFUNCENT) - pretty_print_func_ent(data, size, event, - cpu, pid, comm, secs, usecs); - else if (event->flags & EVENT_FL_ISFUNCRET) - pretty_print_func_ret(data, size, event, - cpu, pid, comm, secs, usecs); - printf("\n"); -} - -void print_event(int cpu, void *data, int size, unsigned long long nsecs, - char *comm) -{ - struct event *event; - unsigned long secs; - unsigned long usecs; - int type; - int pid; - - secs = nsecs / NSECS_PER_SEC; - nsecs -= secs * NSECS_PER_SEC; - usecs = nsecs / NSECS_PER_USEC; - - type = trace_parse_common_type(data); - - event = trace_find_event(type); - if (!event) { - warning("ug! no event found for type %d", type); - return; - } - - pid = trace_parse_common_pid(data); - - if (event->flags & (EVENT_FL_ISFUNCENT | EVENT_FL_ISFUNCRET)) - return pretty_print_func_graph(data, size, event, cpu, - pid, comm, secs, usecs); - - if (latency_format) { - printf("%8.8s-%-5d %3d", - comm, pid, cpu); - print_lat_fmt(data, size); - } else - printf("%16s-%-5d [%03d]", comm, pid, cpu); - - printf(" %5lu.%06lu: %s: ", secs, usecs, event->name); - - if (event->flags & EVENT_FL_FAILED) { - printf("EVENT '%s' FAILED TO PARSE\n", - event->name); - return; - } - - pretty_print(data, size, event); - printf("\n"); -} - -static void print_fields(struct print_flag_sym *field) -{ - printf("{ %s, %s }", field->value, field->str); - if (field->next) { - printf(", "); - print_fields(field->next); - } -} - -static void print_args(struct print_arg *args) -{ - int print_paren = 1; - - switch (args->type) { - case PRINT_NULL: - printf("null"); - break; - case PRINT_ATOM: - printf("%s", args->atom.atom); - break; - case PRINT_FIELD: - printf("REC->%s", args->field.name); - break; - case PRINT_FLAGS: - printf("__print_flags("); - print_args(args->flags.field); - printf(", %s, ", args->flags.delim); - print_fields(args->flags.flags); - printf(")"); - break; - case PRINT_SYMBOL: - printf("__print_symbolic("); - print_args(args->symbol.field); - printf(", "); - print_fields(args->symbol.symbols); - printf(")"); - break; - case PRINT_STRING: - printf("__get_str(%s)", args->string.string); - break; - case PRINT_TYPE: - printf("(%s)", args->typecast.type); - print_args(args->typecast.item); - break; - case PRINT_OP: - if (strcmp(args->op.op, ":") == 0) - print_paren = 0; - if (print_paren) - printf("("); - print_args(args->op.left); - printf(" %s ", args->op.op); - print_args(args->op.right); - if (print_paren) - printf(")"); - break; - default: - /* we should warn... */ - return; - } - if (args->next) { - printf("\n"); - print_args(args->next); - } -} - -int parse_ftrace_file(char *buf, unsigned long size) -{ - struct format_field *field; - struct print_arg *arg, **list; - struct event *event; - int ret; - - init_input_buf(buf, size); - - event = alloc_event(); - if (!event) - return -ENOMEM; - - event->flags |= EVENT_FL_ISFTRACE; - - event->name = event_read_name(); - if (!event->name) - die("failed to read ftrace event name"); - - if (strcmp(event->name, "function") == 0) - event->flags |= EVENT_FL_ISFUNC; - - else if (strcmp(event->name, "funcgraph_entry") == 0) - event->flags |= EVENT_FL_ISFUNCENT; - - else if (strcmp(event->name, "funcgraph_exit") == 0) - event->flags |= EVENT_FL_ISFUNCRET; - - else if (strcmp(event->name, "bprint") == 0) - event->flags |= EVENT_FL_ISBPRINT; - - event->id = event_read_id(); - if (event->id < 0) - die("failed to read ftrace event id"); - - add_event(event); - - ret = event_read_format(event); - if (ret < 0) - die("failed to read ftrace event format"); - - ret = event_read_print(event); - if (ret < 0) - die("failed to read ftrace event print fmt"); - - /* New ftrace handles args */ - if (ret > 0) - return 0; - /* - * The arguments for ftrace files are parsed by the fields. - * Set up the fields as their arguments. - */ - list = &event->print_fmt.args; - for (field = event->format.fields; field; field = field->next) { - arg = malloc_or_die(sizeof(*arg)); - memset(arg, 0, sizeof(*arg)); - *list = arg; - list = &arg->next; - arg->type = PRINT_FIELD; - arg->field.name = field->name; - arg->field.field = field; - } - return 0; -} - -int parse_event_file(char *buf, unsigned long size, char *sys) -{ - struct event *event; - int ret; - - init_input_buf(buf, size); - - event = alloc_event(); - if (!event) - return -ENOMEM; - - event->name = event_read_name(); - if (!event->name) - die("failed to read event name"); - - event->id = event_read_id(); - if (event->id < 0) - die("failed to read event id"); - - ret = event_read_format(event); - if (ret < 0) { - warning("failed to read event format for %s", event->name); - goto event_failed; - } - - ret = event_read_print(event); - if (ret < 0) { - warning("failed to read event print fmt for %s", event->name); - goto event_failed; - } - - event->system = strdup(sys); - -#define PRINT_ARGS 0 - if (PRINT_ARGS && event->print_fmt.args) - print_args(event->print_fmt.args); - - add_event(event); - return 0; - - event_failed: - event->flags |= EVENT_FL_FAILED; - /* still add it even if it failed */ - add_event(event); - return -1; -} - -void parse_set_info(int nr_cpus, int long_sz) -{ - cpus = nr_cpus; - long_size = long_sz; -} - -int common_pc(struct scripting_context *context) -{ - return parse_common_pc(context->event_data); -} - -int common_flags(struct scripting_context *context) -{ - return parse_common_flags(context->event_data); -} - -int common_lock_depth(struct scripting_context *context) -{ - return parse_common_lock_depth(context->event_data); -} diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index f55cc3a765a..e113e180c48 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -18,8 +18,6 @@ * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -#define _FILE_OFFSET_BITS 64 - #include <dirent.h> #include <stdio.h> #include <stdlib.h> @@ -33,7 +31,6 @@ #include <pthread.h> #include <fcntl.h> #include <unistd.h> -#include <ctype.h> #include <errno.h> #include "../perf.h" @@ -42,18 +39,10 @@ static int input_fd; -static int read_page; - -int file_bigendian; -int host_bigendian; -static int long_size; - -static unsigned long page_size; - -static ssize_t calc_data_size; +static ssize_t trace_data_size; static bool repipe; -static int do_read(int fd, void *buf, int size) +static int __do_read(int fd, void *buf, int size) { int rsize = size; @@ -66,8 +55,10 @@ static int do_read(int fd, void *buf, int size) if (repipe) { int retw = write(STDOUT_FILENO, buf, ret); - if (retw <= 0 || retw != ret) - die("repiping input file"); + if (retw <= 0 || retw != ret) { + pr_debug("repiping input file"); + return -1; + } } size -= ret; @@ -77,17 +68,18 @@ static int do_read(int fd, void *buf, int size) return rsize; } -static int read_or_die(void *data, int size) +static int do_read(void *data, int size) { int r; - r = do_read(input_fd, data, size); - if (r <= 0) - die("reading input file (size expected=%d received=%d)", - size, r); + r = __do_read(input_fd, data, size); + if (r <= 0) { + pr_debug("reading input file (size expected=%d received=%d)", + size, r); + return -1; + } - if (calc_data_size) - calc_data_size += r; + trace_data_size += r; return r; } @@ -100,25 +92,27 @@ static void skip(int size) while (size) { r = size > BUFSIZ ? BUFSIZ : size; - read_or_die(buf, r); + do_read(buf, r); size -= r; }; } -static unsigned int read4(void) +static unsigned int read4(struct pevent *pevent) { unsigned int data; - read_or_die(&data, 4); - return __data2host4(data); + if (do_read(&data, 4) < 0) + return 0; + return __data2host4(pevent, data); } -static unsigned long long read8(void) +static unsigned long long read8(struct pevent *pevent) { unsigned long long data; - read_or_die(&data, 8); - return __data2host8(data); + if (do_read(&data, 8) < 0) + return 0; + return __data2host8(pevent, data); } static char *read_string(void) @@ -131,17 +125,23 @@ static char *read_string(void) for (;;) { r = read(input_fd, &c, 1); - if (r < 0) - die("reading input file"); + if (r < 0) { + pr_debug("reading input file"); + goto out; + } - if (!r) - die("no data"); + if (!r) { + pr_debug("no data"); + goto out; + } if (repipe) { int retw = write(STDOUT_FILENO, &c, 1); - if (retw <= 0 || retw != r) - die("repiping input file string"); + if (retw <= 0 || retw != r) { + pr_debug("repiping input file string"); + goto out; + } } buf[size++] = c; @@ -150,335 +150,200 @@ static char *read_string(void) break; } - if (calc_data_size) - calc_data_size += size; - - str = malloc_or_die(size); - memcpy(str, buf, size); + trace_data_size += size; + str = malloc(size); + if (str) + memcpy(str, buf, size); +out: return str; } -static void read_proc_kallsyms(void) +static int read_proc_kallsyms(struct pevent *pevent) { unsigned int size; char *buf; - size = read4(); + size = read4(pevent); if (!size) - return; + return 0; + + buf = malloc(size + 1); + if (buf == NULL) + return -1; - buf = malloc_or_die(size + 1); - read_or_die(buf, size); + if (do_read(buf, size) < 0) { + free(buf); + return -1; + } buf[size] = '\0'; - parse_proc_kallsyms(buf, size); + parse_proc_kallsyms(pevent, buf, size); free(buf); + return 0; } -static void read_ftrace_printk(void) +static int read_ftrace_printk(struct pevent *pevent) { unsigned int size; char *buf; - size = read4(); + /* it can have 0 size */ + size = read4(pevent); if (!size) - return; + return 0; + + buf = malloc(size); + if (buf == NULL) + return -1; - buf = malloc_or_die(size); - read_or_die(buf, size); + if (do_read(buf, size) < 0) { + free(buf); + return -1; + } - parse_ftrace_printk(buf, size); + parse_ftrace_printk(pevent, buf, size); free(buf); + return 0; } -static void read_header_files(void) +static int read_header_files(struct pevent *pevent) { unsigned long long size; - char *header_event; + char *header_page; char buf[BUFSIZ]; + int ret = 0; - read_or_die(buf, 12); + if (do_read(buf, 12) < 0) + return -1; - if (memcmp(buf, "header_page", 12) != 0) - die("did not read header page"); + if (memcmp(buf, "header_page", 12) != 0) { + pr_debug("did not read header page"); + return -1; + } - size = read8(); - skip(size); + size = read8(pevent); + + header_page = malloc(size); + if (header_page == NULL) + return -1; - /* - * The size field in the page is of type long, - * use that instead, since it represents the kernel. - */ - long_size = header_page_size_size; + 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); - read_or_die(buf, 13); - if (memcmp(buf, "header_event", 13) != 0) - die("did not read header event"); + if (do_read(buf, 13) < 0) + return -1; - size = read8(); - header_event = malloc_or_die(size); - read_or_die(header_event, size); - free(header_event); + if (memcmp(buf, "header_event", 13) != 0) { + pr_debug("did not read header event"); + return -1; + } + + size = read8(pevent); + skip(size); + + return ret; } -static void read_ftrace_file(unsigned long long size) +static int read_ftrace_file(struct pevent *pevent, unsigned long long size) { char *buf; - buf = malloc_or_die(size); - read_or_die(buf, size); - parse_ftrace_file(buf, size); + buf = malloc(size); + if (buf == NULL) + return -1; + + if (do_read(buf, size) < 0) { + free(buf); + return -1; + } + + parse_ftrace_file(pevent, buf, size); free(buf); + return 0; } -static void read_event_file(char *sys, unsigned long long size) +static int read_event_file(struct pevent *pevent, char *sys, + unsigned long long size) { char *buf; - buf = malloc_or_die(size); - read_or_die(buf, size); - parse_event_file(buf, size, sys); + buf = malloc(size); + if (buf == NULL) + return -1; + + if (do_read(buf, size) < 0) { + free(buf); + return -1; + } + + parse_event_file(pevent, buf, size, sys); free(buf); + return 0; } -static void read_ftrace_files(void) +static int read_ftrace_files(struct pevent *pevent) { unsigned long long size; int count; int i; + int ret; - count = read4(); + count = read4(pevent); for (i = 0; i < count; i++) { - size = read8(); - read_ftrace_file(size); + size = read8(pevent); + ret = read_ftrace_file(pevent, size); + if (ret) + return ret; } + return 0; } -static void read_event_files(void) +static int read_event_files(struct pevent *pevent) { unsigned long long size; char *sys; int systems; int count; int i,x; + int ret; - systems = read4(); + systems = read4(pevent); for (i = 0; i < systems; i++) { sys = read_string(); + if (sys == NULL) + return -1; - count = read4(); - for (x=0; x < count; x++) { - size = read8(); - read_event_file(sys, size); - } - } -} - -struct cpu_data { - unsigned long long offset; - unsigned long long size; - unsigned long long timestamp; - struct record *next; - char *page; - int cpu; - int index; - int page_size; -}; - -static struct cpu_data *cpu_data; - -static void update_cpu_data_index(int cpu) -{ - cpu_data[cpu].offset += page_size; - cpu_data[cpu].size -= page_size; - cpu_data[cpu].index = 0; -} - -static void get_next_page(int cpu) -{ - off_t save_seek; - off_t ret; - - if (!cpu_data[cpu].page) - return; - - if (read_page) { - if (cpu_data[cpu].size <= page_size) { - free(cpu_data[cpu].page); - cpu_data[cpu].page = NULL; - return; - } - - update_cpu_data_index(cpu); - - /* other parts of the code may expect the pointer to not move */ - save_seek = lseek(input_fd, 0, SEEK_CUR); - - ret = lseek(input_fd, cpu_data[cpu].offset, SEEK_SET); - if (ret == (off_t)-1) - die("failed to lseek"); - ret = read(input_fd, cpu_data[cpu].page, page_size); - if (ret < 0) - die("failed to read page"); - - /* reset the file pointer back */ - lseek(input_fd, save_seek, SEEK_SET); - - return; - } - - munmap(cpu_data[cpu].page, page_size); - cpu_data[cpu].page = NULL; - - if (cpu_data[cpu].size <= page_size) - return; - - update_cpu_data_index(cpu); - - cpu_data[cpu].page = mmap(NULL, page_size, PROT_READ, MAP_PRIVATE, - input_fd, cpu_data[cpu].offset); - if (cpu_data[cpu].page == MAP_FAILED) - die("failed to mmap cpu %d at offset 0x%llx", - cpu, cpu_data[cpu].offset); -} - -static unsigned int type_len4host(unsigned int type_len_ts) -{ - if (file_bigendian) - return (type_len_ts >> 27) & ((1 << 5) - 1); - else - return type_len_ts & ((1 << 5) - 1); -} - -static unsigned int ts4host(unsigned int type_len_ts) -{ - if (file_bigendian) - return type_len_ts & ((1 << 27) - 1); - else - return type_len_ts >> 5; -} - -static int calc_index(void *ptr, int cpu) -{ - return (unsigned long)ptr - (unsigned long)cpu_data[cpu].page; -} + count = read4(pevent); -struct record *trace_peek_data(int cpu) -{ - struct record *data; - void *page = cpu_data[cpu].page; - int idx = cpu_data[cpu].index; - void *ptr = page + idx; - unsigned long long extend; - unsigned int type_len_ts; - unsigned int type_len; - unsigned int delta; - unsigned int length = 0; - - if (cpu_data[cpu].next) - return cpu_data[cpu].next; - - if (!page) - return NULL; - - if (!idx) { - /* FIXME: handle header page */ - if (header_page_ts_size != 8) - die("expected a long long type for timestamp"); - cpu_data[cpu].timestamp = data2host8(ptr); - ptr += 8; - switch (header_page_size_size) { - case 4: - cpu_data[cpu].page_size = data2host4(ptr); - ptr += 4; - break; - case 8: - cpu_data[cpu].page_size = data2host8(ptr); - ptr += 8; - break; - default: - die("bad long size"); + for (x=0; x < count; x++) { + size = read8(pevent); + ret = read_event_file(pevent, sys, size); + if (ret) + return ret; } - ptr = cpu_data[cpu].page + header_page_data_offset; } - -read_again: - idx = calc_index(ptr, cpu); - - if (idx >= cpu_data[cpu].page_size) { - get_next_page(cpu); - return trace_peek_data(cpu); - } - - type_len_ts = data2host4(ptr); - ptr += 4; - - type_len = type_len4host(type_len_ts); - delta = ts4host(type_len_ts); - - switch (type_len) { - case RINGBUF_TYPE_PADDING: - if (!delta) - die("error, hit unexpected end of page"); - length = data2host4(ptr); - ptr += 4; - length *= 4; - ptr += length; - goto read_again; - - case RINGBUF_TYPE_TIME_EXTEND: - extend = data2host4(ptr); - ptr += 4; - extend <<= TS_SHIFT; - extend += delta; - cpu_data[cpu].timestamp += extend; - goto read_again; - - case RINGBUF_TYPE_TIME_STAMP: - ptr += 12; - break; - case 0: - length = data2host4(ptr); - ptr += 4; - die("here! length=%d", length); - break; - default: - length = type_len * 4; - break; - } - - cpu_data[cpu].timestamp += delta; - - data = malloc_or_die(sizeof(*data)); - memset(data, 0, sizeof(*data)); - - data->ts = cpu_data[cpu].timestamp; - data->size = length; - data->data = ptr; - ptr += length; - - cpu_data[cpu].index = calc_index(ptr, cpu); - cpu_data[cpu].next = data; - - return data; -} - -struct record *trace_read_data(int cpu) -{ - struct record *data; - - data = trace_peek_data(cpu); - cpu_data[cpu].next = NULL; - - return data; + return 0; } -ssize_t trace_report(int fd, bool __repipe) +ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) { char buf[BUFSIZ]; char test[] = { 23, 8, 68 }; @@ -486,54 +351,94 @@ ssize_t trace_report(int fd, bool __repipe) int show_version = 0; int show_funcs = 0; int show_printk = 0; - ssize_t size; + ssize_t size = -1; + int file_bigendian; + int host_bigendian; + int file_long_size; + int file_page_size; + struct pevent *pevent = NULL; + int err; - calc_data_size = 1; repipe = __repipe; - input_fd = fd; - read_or_die(buf, 3); - if (memcmp(buf, test, 3) != 0) - die("no trace data in the file"); + if (do_read(buf, 3) < 0) + return -1; + if (memcmp(buf, test, 3) != 0) { + pr_debug("no trace data in the file"); + return -1; + } - read_or_die(buf, 7); - if (memcmp(buf, "tracing", 7) != 0) - die("not a trace file (missing 'tracing' tag)"); + if (do_read(buf, 7) < 0) + return -1; + if (memcmp(buf, "tracing", 7) != 0) { + pr_debug("not a trace file (missing 'tracing' tag)"); + return -1; + } version = read_string(); + if (version == NULL) + return -1; if (show_version) printf("version = %s\n", version); free(version); - read_or_die(buf, 1); + if (do_read(buf, 1) < 0) + return -1; file_bigendian = buf[0]; host_bigendian = bigendian(); - read_or_die(buf, 1); - long_size = buf[0]; - - page_size = read4(); - - read_header_files(); - - read_ftrace_files(); - read_event_files(); - read_proc_kallsyms(); - read_ftrace_printk(); + if (trace_event__init(tevent)) { + pr_debug("trace_event__init failed"); + goto out; + } - size = calc_data_size - 1; - calc_data_size = 0; + pevent = tevent->pevent; + + pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); + pevent_set_file_bigendian(pevent, file_bigendian); + pevent_set_host_bigendian(pevent, host_bigendian); + + if (do_read(buf, 1) < 0) + goto out; + file_long_size = buf[0]; + + 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; + err = read_ftrace_files(pevent); + if (err) + goto out; + err = read_event_files(pevent); + if (err) + goto out; + err = read_proc_kallsyms(pevent); + if (err) + goto out; + err = read_ftrace_printk(pevent); + if (err) + goto out; + + size = trace_data_size; repipe = false; if (show_funcs) { - print_funcs(); - return size; - } - if (show_printk) { - print_printk(); - return size; + pevent_print_funcs(pevent); + } else if (show_printk) { + pevent_print_printk(pevent); } + pevent = NULL; + +out: + if (pevent) + trace_event__cleanup(tevent); return size; } diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index f7af2fca965..57aaccc1692 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -22,7 +22,6 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <ctype.h> #include <errno.h> #include "../perf.h" @@ -36,11 +35,11 @@ static int stop_script_unsupported(void) return 0; } -static void process_event_unsupported(int cpu __unused, - void *data __unused, - int size __unused, - unsigned long long nsecs __unused, - char *comm __unused) +static void process_event_unsupported(union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct thread *thread __maybe_unused, + struct addr_location *al __maybe_unused) { } @@ -53,16 +52,19 @@ static void print_python_unsupported_msg(void) "\n etc.\n"); } -static int python_start_script_unsupported(const char *script __unused, - int argc __unused, - const char **argv __unused) +static int python_start_script_unsupported(const char *script __maybe_unused, + int argc __maybe_unused, + const char **argv __maybe_unused) { print_python_unsupported_msg(); return -1; } -static int python_generate_script_unsupported(const char *outfile __unused) +static int python_generate_script_unsupported(struct pevent *pevent + __maybe_unused, + const char *outfile + __maybe_unused) { print_python_unsupported_msg(); @@ -114,16 +116,18 @@ static void print_perl_unsupported_msg(void) "\n etc.\n"); } -static int perl_start_script_unsupported(const char *script __unused, - int argc __unused, - const char **argv __unused) +static int perl_start_script_unsupported(const char *script __maybe_unused, + int argc __maybe_unused, + const char **argv __maybe_unused) { print_perl_unsupported_msg(); return -1; } -static int perl_generate_script_unsupported(const char *outfile __unused) +static int perl_generate_script_unsupported(struct pevent *pevent + __maybe_unused, + const char *outfile __maybe_unused) { print_perl_unsupported_msg(); diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c new file mode 100644 index 00000000000..6322d37164c --- /dev/null +++ b/tools/perf/util/trace-event.c @@ -0,0 +1,82 @@ + +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <errno.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <linux/kernel.h> +#include <traceevent/event-parse.h> +#include "trace-event.h" +#include "util.h" + +/* + * global trace_event object used by trace_event__tp_format + * + * TODO There's no cleanup call for this. Add some sort of + * __exit function support and call trace_event__cleanup + * there. + */ +static struct trace_event tevent; + +int trace_event__init(struct trace_event *t) +{ + struct pevent *pevent = pevent_alloc(); + + if (pevent) { + t->plugin_list = traceevent_load_plugins(pevent); + t->pevent = pevent; + } + + return pevent ? 0 : -1; +} + +void trace_event__cleanup(struct trace_event *t) +{ + traceevent_unload_plugins(t->plugin_list, t->pevent); + pevent_free(t->pevent); +} + +static struct event_format* +tp_format(const char *sys, const char *name) +{ + struct pevent *pevent = tevent.pevent; + struct event_format *event = NULL; + char path[PATH_MAX]; + size_t size; + char *data; + + scnprintf(path, PATH_MAX, "%s/%s/%s/format", + tracing_events_path, sys, name); + + if (filename__read_str(path, &data, &size)) + return NULL; + + pevent_parse_format(pevent, &event, data, size, sys); + + free(data); + return event; +} + +struct event_format* +trace_event__tp_format(const char *sys, const char *name) +{ + static bool initialized; + + if (!initialized) { + int be = traceevent_host_bigendian(); + struct pevent *pevent; + + if (trace_event__init(&tevent)) + return NULL; + + pevent = tevent.pevent; + pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); + pevent_set_file_bigendian(pevent, be); + pevent_set_host_bigendian(pevent, be); + initialized = true; + } + + return tp_format(sys, name); +} diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index b3e86b1e444..7b6d6868832 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -1,287 +1,76 @@ -#ifndef __PERF_TRACE_EVENTS_H -#define __PERF_TRACE_EVENTS_H +#ifndef _PERF_UTIL_TRACE_EVENT_H +#define _PERF_UTIL_TRACE_EVENT_H -#include <stdbool.h> +#include <traceevent/event-parse.h> #include "parse-events.h" -#define __unused __attribute__((unused)) +struct machine; +struct perf_sample; +union perf_event; +struct perf_tool; +struct thread; +struct plugin_list; - -#ifndef PAGE_MASK -#define PAGE_MASK (page_size - 1) -#endif - -enum { - RINGBUF_TYPE_PADDING = 29, - RINGBUF_TYPE_TIME_EXTEND = 30, - RINGBUF_TYPE_TIME_STAMP = 31, -}; - -#ifndef TS_SHIFT -#define TS_SHIFT 27 -#endif - -#define NSECS_PER_SEC 1000000000ULL -#define NSECS_PER_USEC 1000ULL - -enum format_flags { - FIELD_IS_ARRAY = 1, - FIELD_IS_POINTER = 2, - FIELD_IS_SIGNED = 4, - FIELD_IS_STRING = 8, - FIELD_IS_DYNAMIC = 16, - FIELD_IS_FLAG = 32, - FIELD_IS_SYMBOLIC = 64, -}; - -struct format_field { - struct format_field *next; - char *type; - char *name; - int offset; - int size; - unsigned long flags; +struct trace_event { + struct pevent *pevent; + struct plugin_list *plugin_list; }; -struct format { - int nr_common; - int nr_fields; - struct format_field *common_fields; - struct format_field *fields; -}; - -struct print_arg_atom { - char *atom; -}; - -struct print_arg_string { - char *string; - int offset; -}; - -struct print_arg_field { - char *name; - struct format_field *field; -}; - -struct print_flag_sym { - struct print_flag_sym *next; - char *value; - char *str; -}; - -struct print_arg_typecast { - char *type; - struct print_arg *item; -}; - -struct print_arg_flags { - struct print_arg *field; - char *delim; - struct print_flag_sym *flags; -}; - -struct print_arg_symbol { - struct print_arg *field; - struct print_flag_sym *symbols; -}; - -struct print_arg; - -struct print_arg_op { - char *op; - int prio; - struct print_arg *left; - struct print_arg *right; -}; - -struct print_arg_func { - char *name; - struct print_arg *args; -}; - -enum print_arg_type { - PRINT_NULL, - PRINT_ATOM, - PRINT_FIELD, - PRINT_FLAGS, - PRINT_SYMBOL, - PRINT_TYPE, - PRINT_STRING, - PRINT_OP, -}; - -struct print_arg { - struct print_arg *next; - enum print_arg_type type; - union { - struct print_arg_atom atom; - struct print_arg_field field; - struct print_arg_typecast typecast; - struct print_arg_flags flags; - struct print_arg_symbol symbol; - struct print_arg_func func; - struct print_arg_string string; - struct print_arg_op op; - }; -}; - -struct print_fmt { - char *format; - struct print_arg *args; -}; - -struct event { - struct event *next; - char *name; - int id; - int flags; - struct format format; - struct print_fmt print_fmt; - char *system; -}; - -enum { - EVENT_FL_ISFTRACE = 0x01, - EVENT_FL_ISPRINT = 0x02, - EVENT_FL_ISBPRINT = 0x04, - EVENT_FL_ISFUNC = 0x08, - EVENT_FL_ISFUNCENT = 0x10, - EVENT_FL_ISFUNCRET = 0x20, - - EVENT_FL_FAILED = 0x80000000 -}; - -struct record { - unsigned long long ts; - int size; - void *data; -}; - -struct record *trace_peek_data(int cpu); -struct record *trace_read_data(int cpu); - -void parse_set_info(int nr_cpus, int long_sz); - -ssize_t trace_report(int fd, bool repipe); - -void *malloc_or_die(unsigned int size); - -void parse_cmdlines(char *file, int size); -void parse_proc_kallsyms(char *file, unsigned int size); -void parse_ftrace_printk(char *file, unsigned int size); - -void print_funcs(void); -void print_printk(void); - -int parse_ftrace_file(char *buf, unsigned long size); -int parse_event_file(char *buf, unsigned long size, char *sys); -void print_event(int cpu, void *data, int size, unsigned long long nsecs, - char *comm); - -extern int file_bigendian; -extern int host_bigendian; +int trace_event__init(struct trace_event *t); +void trace_event__cleanup(struct trace_event *t); +struct event_format* +trace_event__tp_format(const char *sys, const char *name); int bigendian(void); -static inline unsigned short __data2host2(unsigned short data) -{ - unsigned short swap; - - if (host_bigendian == file_bigendian) - return data; - - swap = ((data & 0xffULL) << 8) | - ((data & (0xffULL << 8)) >> 8); - - return swap; -} - -static inline unsigned int __data2host4(unsigned int data) -{ - unsigned int swap; - - if (host_bigendian == file_bigendian) - return data; +void event_format__print(struct event_format *event, + int cpu, void *data, int size); - swap = ((data & 0xffULL) << 24) | - ((data & (0xffULL << 8)) << 8) | - ((data & (0xffULL << 16)) >> 8) | - ((data & (0xffULL << 24)) >> 24); +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); - return swap; -} +unsigned long long +raw_field_value(struct event_format *event, const char *name, void *data); -static inline unsigned long long __data2host8(unsigned long long data) -{ - unsigned long long swap; +void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size); +void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size); - if (host_bigendian == file_bigendian) - return data; +ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe); - swap = ((data & 0xffULL) << 56) | - ((data & (0xffULL << 8)) << 40) | - ((data & (0xffULL << 16)) << 24) | - ((data & (0xffULL << 24)) << 8) | - ((data & (0xffULL << 32)) >> 8) | - ((data & (0xffULL << 40)) >> 24) | - ((data & (0xffULL << 48)) >> 40) | - ((data & (0xffULL << 56)) >> 56); +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); - return swap; -} +int read_tracing_data(int fd, struct list_head *pattrs); -#define data2host2(ptr) __data2host2(*(unsigned short *)ptr) -#define data2host4(ptr) __data2host4(*(unsigned int *)ptr) -#define data2host8(ptr) ({ \ - unsigned long long __val; \ - \ - memcpy(&__val, (ptr), sizeof(unsigned long long)); \ - __data2host8(__val); \ -}) +struct tracing_data { + /* size is only valid if temp is 'true' */ + ssize_t size; + bool temp; + char temp_file[50]; +}; -extern int header_page_ts_offset; -extern int header_page_ts_size; -extern int header_page_size_offset; -extern int header_page_size_size; -extern int header_page_data_offset; -extern int header_page_data_size; +struct tracing_data *tracing_data_get(struct list_head *pattrs, + int fd, bool temp); +int tracing_data_put(struct tracing_data *tdata); -extern bool latency_format; -int trace_parse_common_type(void *data); -int trace_parse_common_pid(void *data); -int parse_common_pc(void *data); -int parse_common_flags(void *data); -int parse_common_lock_depth(void *data); -struct event *trace_find_event(int id); -struct event *trace_find_next_event(struct event *event); -unsigned long long read_size(void *ptr, int size); -unsigned long long -raw_field_value(struct event *event, const char *name, void *data); -void *raw_field_ptr(struct event *event, const char *name, void *data); -unsigned long long eval_flag(const char *flag); - -int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events); -ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs, - int nb_events); +struct addr_location; -/* taken from kernel/trace/trace.h */ -enum trace_flag_type { - TRACE_FLAG_IRQS_OFF = 0x01, - TRACE_FLAG_IRQS_NOSUPPORT = 0x02, - TRACE_FLAG_NEED_RESCHED = 0x04, - TRACE_FLAG_HARDIRQ = 0x08, - TRACE_FLAG_SOFTIRQ = 0x10, -}; +struct perf_session; struct scripting_ops { const char *name; int (*start_script) (const char *script, int argc, const char **argv); int (*stop_script) (void); - void (*process_event) (int cpu, void *data, int size, - unsigned long long nsecs, char *comm); - int (*generate_script) (const char *outfile); + void (*process_event) (union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct thread *thread, + struct addr_location *al); + int (*generate_script) (struct pevent *pevent, const char *outfile); }; int script_spec_register(const char *spec, struct scripting_ops *ops); @@ -290,6 +79,7 @@ void setup_perl_scripting(void); void setup_python_scripting(void); struct scripting_context { + struct pevent *pevent; void *event_data; }; @@ -297,4 +87,4 @@ int common_pc(struct scripting_context *context); int common_flags(struct scripting_context *context); int common_lock_depth(struct scripting_context *context); -#endif /* __PERF_TRACE_EVENTS_H */ +#endif /* _PERF_UTIL_TRACE_EVENT_H */ diff --git a/tools/perf/util/types.h b/tools/perf/util/types.h deleted file mode 100644 index 7d6b8331f89..00000000000 --- a/tools/perf/util/types.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef __PERF_TYPES_H -#define __PERF_TYPES_H - -/* - * We define u64 as unsigned long long for every architecture - * so that we can print it with %Lx without getting warnings. - */ -typedef unsigned long long u64; -typedef signed long long s64; -typedef unsigned int u32; -typedef signed int s32; -typedef unsigned short u16; -typedef signed short s16; -typedef unsigned char u8; -typedef signed char s8; - -#endif /* __PERF_TYPES_H */ diff --git a/tools/perf/util/ui/browser.c b/tools/perf/util/ui/browser.c deleted file mode 100644 index 8bc010edca2..00000000000 --- a/tools/perf/util/ui/browser.c +++ /dev/null @@ -1,337 +0,0 @@ -#include "libslang.h" -#include <linux/compiler.h> -#include <linux/list.h> -#include <linux/rbtree.h> -#include <stdlib.h> -#include <sys/ttydefaults.h> -#include "browser.h" -#include "helpline.h" -#include "../color.h" -#include "../util.h" -#include <stdio.h> - -static int ui_browser__percent_color(double percent, bool current) -{ - if (current) - return HE_COLORSET_SELECTED; - if (percent >= MIN_RED) - return HE_COLORSET_TOP; - if (percent >= MIN_GREEN) - return HE_COLORSET_MEDIUM; - return HE_COLORSET_NORMAL; -} - -void ui_browser__set_color(struct ui_browser *self __used, int color) -{ - SLsmg_set_color(color); -} - -void ui_browser__set_percent_color(struct ui_browser *self, - double percent, bool current) -{ - int color = ui_browser__percent_color(percent, current); - ui_browser__set_color(self, color); -} - -void ui_browser__gotorc(struct ui_browser *self, int y, int x) -{ - SLsmg_gotorc(self->y + y, self->x + x); -} - -void ui_browser__list_head_seek(struct ui_browser *self, off_t offset, int whence) -{ - struct list_head *head = self->entries; - struct list_head *pos; - - switch (whence) { - case SEEK_SET: - pos = head->next; - break; - case SEEK_CUR: - pos = self->top; - break; - case SEEK_END: - pos = head->prev; - break; - default: - return; - } - - if (offset > 0) { - while (offset-- != 0) - pos = pos->next; - } else { - while (offset++ != 0) - pos = pos->prev; - } - - self->top = pos; -} - -void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence) -{ - struct rb_root *root = self->entries; - struct rb_node *nd; - - switch (whence) { - case SEEK_SET: - nd = rb_first(root); - break; - case SEEK_CUR: - nd = self->top; - break; - case SEEK_END: - nd = rb_last(root); - break; - default: - return; - } - - if (offset > 0) { - while (offset-- != 0) - nd = rb_next(nd); - } else { - while (offset++ != 0) - nd = rb_prev(nd); - } - - self->top = nd; -} - -unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self) -{ - struct rb_node *nd; - int row = 0; - - if (self->top == NULL) - self->top = rb_first(self->entries); - - nd = self->top; - - while (nd != NULL) { - ui_browser__gotorc(self, row, 0); - self->write(self, nd, row); - if (++row == self->height) - break; - nd = rb_next(nd); - } - - return row; -} - -bool ui_browser__is_current_entry(struct ui_browser *self, unsigned row) -{ - return self->top_idx + row == self->index; -} - -void ui_browser__refresh_dimensions(struct ui_browser *self) -{ - int cols, rows; - newtGetScreenSize(&cols, &rows); - - self->width = cols - 1; - self->height = rows - 2; - self->y = 1; - self->x = 0; -} - -void ui_browser__reset_index(struct ui_browser *self) -{ - self->index = self->top_idx = 0; - self->seek(self, 0, SEEK_SET); -} - -void ui_browser__add_exit_key(struct ui_browser *self, int key) -{ - newtFormAddHotKey(self->form, key); -} - -void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]) -{ - int i = 0; - - while (keys[i] && i < 64) { - ui_browser__add_exit_key(self, keys[i]); - ++i; - } -} - -int ui_browser__show(struct ui_browser *self, const char *title, - const char *helpline, ...) -{ - va_list ap; - int keys[] = { NEWT_KEY_UP, NEWT_KEY_DOWN, NEWT_KEY_PGUP, - NEWT_KEY_PGDN, NEWT_KEY_HOME, NEWT_KEY_END, ' ', - NEWT_KEY_LEFT, NEWT_KEY_ESCAPE, 'q', CTRL('c'), 0 }; - - if (self->form != NULL) - newtFormDestroy(self->form); - - ui_browser__refresh_dimensions(self); - self->form = newtForm(NULL, NULL, 0); - if (self->form == NULL) - return -1; - - self->sb = newtVerticalScrollbar(self->width, 1, self->height, - HE_COLORSET_NORMAL, - HE_COLORSET_SELECTED); - if (self->sb == NULL) - return -1; - - SLsmg_gotorc(0, 0); - ui_browser__set_color(self, NEWT_COLORSET_ROOT); - slsmg_write_nstring(title, self->width); - - ui_browser__add_exit_keys(self, keys); - newtFormAddComponent(self->form, self->sb); - - va_start(ap, helpline); - ui_helpline__vpush(helpline, ap); - va_end(ap); - return 0; -} - -void ui_browser__hide(struct ui_browser *self) -{ - newtFormDestroy(self->form); - self->form = NULL; - ui_helpline__pop(); -} - -int ui_browser__refresh(struct ui_browser *self) -{ - int row; - - newtScrollbarSet(self->sb, self->index, self->nr_entries - 1); - row = self->refresh(self); - ui_browser__set_color(self, HE_COLORSET_NORMAL); - SLsmg_fill_region(self->y + row, self->x, - self->height - row, self->width, ' '); - - return 0; -} - -int ui_browser__run(struct ui_browser *self) -{ - struct newtExitStruct es; - - if (ui_browser__refresh(self) < 0) - return -1; - - while (1) { - off_t offset; - - newtFormRun(self->form, &es); - - if (es.reason != NEWT_EXIT_HOTKEY) - break; - switch (es.u.key) { - case NEWT_KEY_DOWN: - if (self->index == self->nr_entries - 1) - break; - ++self->index; - if (self->index == self->top_idx + self->height) { - ++self->top_idx; - self->seek(self, +1, SEEK_CUR); - } - break; - case NEWT_KEY_UP: - if (self->index == 0) - break; - --self->index; - if (self->index < self->top_idx) { - --self->top_idx; - self->seek(self, -1, SEEK_CUR); - } - break; - case NEWT_KEY_PGDN: - case ' ': - if (self->top_idx + self->height > self->nr_entries - 1) - break; - - offset = self->height; - if (self->index + offset > self->nr_entries - 1) - offset = self->nr_entries - 1 - self->index; - self->index += offset; - self->top_idx += offset; - self->seek(self, +offset, SEEK_CUR); - break; - case NEWT_KEY_PGUP: - if (self->top_idx == 0) - break; - - if (self->top_idx < self->height) - offset = self->top_idx; - else - offset = self->height; - - self->index -= offset; - self->top_idx -= offset; - self->seek(self, -offset, SEEK_CUR); - break; - case NEWT_KEY_HOME: - ui_browser__reset_index(self); - break; - case NEWT_KEY_END: - offset = self->height - 1; - if (offset >= self->nr_entries) - offset = self->nr_entries - 1; - - self->index = self->nr_entries - 1; - self->top_idx = self->index - offset; - self->seek(self, -offset, SEEK_END); - break; - default: - return es.u.key; - } - if (ui_browser__refresh(self) < 0) - return -1; - } - return -1; -} - -unsigned int ui_browser__list_head_refresh(struct ui_browser *self) -{ - struct list_head *pos; - struct list_head *head = self->entries; - int row = 0; - - if (self->top == NULL || self->top == self->entries) - self->top = head->next; - - pos = self->top; - - list_for_each_from(pos, head) { - ui_browser__gotorc(self, row, 0); - self->write(self, pos, row); - if (++row == self->height) - break; - } - - return row; -} - -static struct newtPercentTreeColors { - const char *topColorFg, *topColorBg; - const char *mediumColorFg, *mediumColorBg; - const char *normalColorFg, *normalColorBg; - const char *selColorFg, *selColorBg; - const char *codeColorFg, *codeColorBg; -} defaultPercentTreeColors = { - "red", "lightgray", - "green", "lightgray", - "black", "lightgray", - "lightgray", "magenta", - "blue", "lightgray", -}; - -void ui_browser__init(void) -{ - struct newtPercentTreeColors *c = &defaultPercentTreeColors; - - sltt_set_color(HE_COLORSET_TOP, NULL, c->topColorFg, c->topColorBg); - sltt_set_color(HE_COLORSET_MEDIUM, NULL, c->mediumColorFg, c->mediumColorBg); - sltt_set_color(HE_COLORSET_NORMAL, NULL, c->normalColorFg, c->normalColorBg); - sltt_set_color(HE_COLORSET_SELECTED, NULL, c->selColorFg, c->selColorBg); - sltt_set_color(HE_COLORSET_CODE, NULL, c->codeColorFg, c->codeColorBg); -} diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h deleted file mode 100644 index 0dc7e4da36f..00000000000 --- a/tools/perf/util/ui/browser.h +++ /dev/null @@ -1,51 +0,0 @@ -#ifndef _PERF_UI_BROWSER_H_ -#define _PERF_UI_BROWSER_H_ 1 - -#include <stdbool.h> -#include <newt.h> -#include <sys/types.h> -#include "../types.h" - -#define HE_COLORSET_TOP 50 -#define HE_COLORSET_MEDIUM 51 -#define HE_COLORSET_NORMAL 52 -#define HE_COLORSET_SELECTED 53 -#define HE_COLORSET_CODE 54 - -struct ui_browser { - newtComponent form, sb; - u64 index, top_idx; - void *top, *entries; - u16 y, x, width, height; - void *priv; - unsigned int (*refresh)(struct ui_browser *self); - void (*write)(struct ui_browser *self, void *entry, int row); - void (*seek)(struct ui_browser *self, off_t offset, int whence); - u32 nr_entries; -}; - - -void ui_browser__set_color(struct ui_browser *self, int color); -void ui_browser__set_percent_color(struct ui_browser *self, - double percent, bool current); -bool ui_browser__is_current_entry(struct ui_browser *self, unsigned row); -void ui_browser__refresh_dimensions(struct ui_browser *self); -void ui_browser__reset_index(struct ui_browser *self); - -void ui_browser__gotorc(struct ui_browser *self, int y, int x); -void ui_browser__add_exit_key(struct ui_browser *self, int key); -void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]); -int ui_browser__show(struct ui_browser *self, const char *title, - const char *helpline, ...); -void ui_browser__hide(struct ui_browser *self); -int ui_browser__refresh(struct ui_browser *self); -int ui_browser__run(struct ui_browser *self); - -void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence); -unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self); - -void ui_browser__list_head_seek(struct ui_browser *self, off_t offset, int whence); -unsigned int ui_browser__list_head_refresh(struct ui_browser *self); - -void ui_browser__init(void); -#endif /* _PERF_UI_BROWSER_H_ */ diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c deleted file mode 100644 index 82b78f99251..00000000000 --- a/tools/perf/util/ui/browsers/annotate.c +++ /dev/null @@ -1,237 +0,0 @@ -#include "../browser.h" -#include "../helpline.h" -#include "../libslang.h" -#include "../../hist.h" -#include "../../sort.h" -#include "../../symbol.h" - -static void ui__error_window(const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - newtWinMessagev((char *)"Error", (char *)"Ok", (char *)fmt, ap); - va_end(ap); -} - -struct annotate_browser { - struct ui_browser b; - struct rb_root entries; - struct rb_node *curr_hot; -}; - -struct objdump_line_rb_node { - struct rb_node rb_node; - double percent; - u32 idx; -}; - -static inline -struct objdump_line_rb_node *objdump_line__rb(struct objdump_line *self) -{ - return (struct objdump_line_rb_node *)(self + 1); -} - -static void annotate_browser__write(struct ui_browser *self, void *entry, int row) -{ - struct objdump_line *ol = rb_entry(entry, struct objdump_line, node); - bool current_entry = ui_browser__is_current_entry(self, row); - int width = self->width; - - if (ol->offset != -1) { - struct objdump_line_rb_node *olrb = objdump_line__rb(ol); - ui_browser__set_percent_color(self, olrb->percent, current_entry); - slsmg_printf(" %7.2f ", olrb->percent); - if (!current_entry) - ui_browser__set_color(self, HE_COLORSET_CODE); - } else { - ui_browser__set_percent_color(self, 0, current_entry); - slsmg_write_nstring(" ", 9); - } - - SLsmg_write_char(':'); - slsmg_write_nstring(" ", 8); - if (!*ol->line) - slsmg_write_nstring(" ", width - 18); - else - slsmg_write_nstring(ol->line, width - 18); -} - -static double objdump_line__calc_percent(struct objdump_line *self, - struct list_head *head, - struct symbol *sym) -{ - double percent = 0.0; - - if (self->offset != -1) { - int len = sym->end - sym->start; - unsigned int hits = 0; - struct sym_priv *priv = symbol__priv(sym); - struct sym_ext *sym_ext = priv->ext; - struct sym_hist *h = priv->hist; - s64 offset = self->offset; - struct objdump_line *next = objdump__get_next_ip_line(head, self); - - - while (offset < (s64)len && - (next == NULL || offset < next->offset)) { - if (sym_ext) { - percent += sym_ext[offset].percent; - } else - hits += h->ip[offset]; - - ++offset; - } - - if (sym_ext == NULL && h->sum) - percent = 100.0 * hits / h->sum; - } - - return percent; -} - -static void objdump__insert_line(struct rb_root *self, - struct objdump_line_rb_node *line) -{ - struct rb_node **p = &self->rb_node; - struct rb_node *parent = NULL; - struct objdump_line_rb_node *l; - - while (*p != NULL) { - parent = *p; - l = rb_entry(parent, struct objdump_line_rb_node, rb_node); - if (line->percent < l->percent) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - rb_link_node(&line->rb_node, parent, p); - rb_insert_color(&line->rb_node, self); -} - -static void annotate_browser__set_top(struct annotate_browser *self, - struct rb_node *nd) -{ - struct objdump_line_rb_node *rbpos; - struct objdump_line *pos; - unsigned back; - - ui_browser__refresh_dimensions(&self->b); - back = self->b.height / 2; - rbpos = rb_entry(nd, struct objdump_line_rb_node, rb_node); - pos = ((struct objdump_line *)rbpos) - 1; - self->b.top_idx = self->b.index = rbpos->idx; - - while (self->b.top_idx != 0 && back != 0) { - pos = list_entry(pos->node.prev, struct objdump_line, node); - - --self->b.top_idx; - --back; - } - - self->b.top = pos; - self->curr_hot = nd; -} - -static int annotate_browser__run(struct annotate_browser *self) -{ - struct rb_node *nd; - struct hist_entry *he = self->b.priv; - int key; - - if (ui_browser__show(&self->b, he->ms.sym->name, - "<-, -> or ESC: exit, TAB/shift+TAB: cycle thru samples") < 0) - return -1; - /* - * To allow builtin-annotate to cycle thru multiple symbols by - * examining the exit key for this function. - */ - ui_browser__add_exit_key(&self->b, NEWT_KEY_RIGHT); - - nd = self->curr_hot; - if (nd) { - int tabs[] = { NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0 }; - ui_browser__add_exit_keys(&self->b, tabs); - } - - while (1) { - key = ui_browser__run(&self->b); - - switch (key) { - case NEWT_KEY_TAB: - nd = rb_prev(nd); - if (nd == NULL) - nd = rb_last(&self->entries); - annotate_browser__set_top(self, nd); - break; - case NEWT_KEY_UNTAB: - nd = rb_next(nd); - if (nd == NULL) - nd = rb_first(&self->entries); - annotate_browser__set_top(self, nd); - break; - default: - goto out; - } - } -out: - ui_browser__hide(&self->b); - return key; -} - -int hist_entry__tui_annotate(struct hist_entry *self) -{ - struct objdump_line *pos, *n; - struct objdump_line_rb_node *rbpos; - LIST_HEAD(head); - struct annotate_browser browser = { - .b = { - .entries = &head, - .refresh = ui_browser__list_head_refresh, - .seek = ui_browser__list_head_seek, - .write = annotate_browser__write, - .priv = self, - }, - }; - int ret; - - if (self->ms.sym == NULL) - return -1; - - if (self->ms.map->dso->annotate_warned) - return -1; - - if (hist_entry__annotate(self, &head, sizeof(*rbpos)) < 0) { - ui__error_window(ui_helpline__last_msg); - return -1; - } - - ui_helpline__push("Press <- or ESC to exit"); - - list_for_each_entry(pos, &head, node) { - size_t line_len = strlen(pos->line); - if (browser.b.width < line_len) - browser.b.width = line_len; - rbpos = objdump_line__rb(pos); - rbpos->idx = browser.b.nr_entries++; - rbpos->percent = objdump_line__calc_percent(pos, &head, self->ms.sym); - if (rbpos->percent < 0.01) - continue; - objdump__insert_line(&browser.entries, rbpos); - } - - /* - * Position the browser at the hottest line. - */ - browser.curr_hot = rb_last(&browser.entries); - if (browser.curr_hot) - annotate_browser__set_top(&browser, browser.curr_hot); - - browser.b.width += 18; /* Percentage */ - ret = annotate_browser__run(&browser); - list_for_each_entry_safe(pos, n, &head, node) { - list_del(&pos->node); - objdump_line__free(pos); - } - return ret; -} diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c deleted file mode 100644 index ebda8c3fde9..00000000000 --- a/tools/perf/util/ui/browsers/hists.c +++ /dev/null @@ -1,1013 +0,0 @@ -#define _GNU_SOURCE -#include <stdio.h> -#undef _GNU_SOURCE -#include "../libslang.h" -#include <stdlib.h> -#include <string.h> -#include <newt.h> -#include <linux/rbtree.h> - -#include "../../hist.h" -#include "../../pstack.h" -#include "../../sort.h" -#include "../../util.h" - -#include "../browser.h" -#include "../helpline.h" -#include "../util.h" -#include "map.h" - -struct hist_browser { - struct ui_browser b; - struct hists *hists; - struct hist_entry *he_selection; - struct map_symbol *selection; -}; - -static void hist_browser__refresh_dimensions(struct hist_browser *self) -{ - /* 3 == +/- toggle symbol before actual hist_entry rendering */ - self->b.width = 3 + (hists__sort_list_width(self->hists) + - sizeof("[k]")); -} - -static void hist_browser__reset(struct hist_browser *self) -{ - self->b.nr_entries = self->hists->nr_entries; - hist_browser__refresh_dimensions(self); - ui_browser__reset_index(&self->b); -} - -static char tree__folded_sign(bool unfolded) -{ - return unfolded ? '-' : '+'; -} - -static char map_symbol__folded(const struct map_symbol *self) -{ - return self->has_children ? tree__folded_sign(self->unfolded) : ' '; -} - -static char hist_entry__folded(const struct hist_entry *self) -{ - return map_symbol__folded(&self->ms); -} - -static char callchain_list__folded(const struct callchain_list *self) -{ - return map_symbol__folded(&self->ms); -} - -static void map_symbol__set_folding(struct map_symbol *self, bool unfold) -{ - self->unfolded = unfold ? self->has_children : false; -} - -static int callchain_node__count_rows_rb_tree(struct callchain_node *self) -{ - int n = 0; - struct rb_node *nd; - - for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) { - struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node); - struct callchain_list *chain; - char folded_sign = ' '; /* No children */ - - list_for_each_entry(chain, &child->val, list) { - ++n; - /* We need this because we may not have children */ - folded_sign = callchain_list__folded(chain); - if (folded_sign == '+') - break; - } - - if (folded_sign == '-') /* Have children and they're unfolded */ - n += callchain_node__count_rows_rb_tree(child); - } - - return n; -} - -static int callchain_node__count_rows(struct callchain_node *node) -{ - struct callchain_list *chain; - bool unfolded = false; - int n = 0; - - list_for_each_entry(chain, &node->val, list) { - ++n; - unfolded = chain->ms.unfolded; - } - - if (unfolded) - n += callchain_node__count_rows_rb_tree(node); - - return n; -} - -static int callchain__count_rows(struct rb_root *chain) -{ - struct rb_node *nd; - int n = 0; - - for (nd = rb_first(chain); nd; nd = rb_next(nd)) { - struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); - n += callchain_node__count_rows(node); - } - - return n; -} - -static bool map_symbol__toggle_fold(struct map_symbol *self) -{ - if (!self->has_children) - return false; - - self->unfolded = !self->unfolded; - return true; -} - -static void callchain_node__init_have_children_rb_tree(struct callchain_node *self) -{ - struct rb_node *nd = rb_first(&self->rb_root); - - for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) { - struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node); - struct callchain_list *chain; - bool first = true; - - list_for_each_entry(chain, &child->val, list) { - if (first) { - first = false; - chain->ms.has_children = chain->list.next != &child->val || - !RB_EMPTY_ROOT(&child->rb_root); - } else - chain->ms.has_children = chain->list.next == &child->val && - !RB_EMPTY_ROOT(&child->rb_root); - } - - callchain_node__init_have_children_rb_tree(child); - } -} - -static void callchain_node__init_have_children(struct callchain_node *self) -{ - struct callchain_list *chain; - - list_for_each_entry(chain, &self->val, list) - chain->ms.has_children = !RB_EMPTY_ROOT(&self->rb_root); - - callchain_node__init_have_children_rb_tree(self); -} - -static void callchain__init_have_children(struct rb_root *self) -{ - struct rb_node *nd; - - for (nd = rb_first(self); nd; nd = rb_next(nd)) { - struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); - callchain_node__init_have_children(node); - } -} - -static void hist_entry__init_have_children(struct hist_entry *self) -{ - if (!self->init_have_children) { - self->ms.has_children = !RB_EMPTY_ROOT(&self->sorted_chain); - callchain__init_have_children(&self->sorted_chain); - self->init_have_children = true; - } -} - -static bool hist_browser__toggle_fold(struct hist_browser *self) -{ - if (map_symbol__toggle_fold(self->selection)) { - struct hist_entry *he = self->he_selection; - - hist_entry__init_have_children(he); - self->hists->nr_entries -= he->nr_rows; - - if (he->ms.unfolded) - he->nr_rows = callchain__count_rows(&he->sorted_chain); - else - he->nr_rows = 0; - self->hists->nr_entries += he->nr_rows; - self->b.nr_entries = self->hists->nr_entries; - - return true; - } - - /* If it doesn't have children, no toggling performed */ - return false; -} - -static int callchain_node__set_folding_rb_tree(struct callchain_node *self, bool unfold) -{ - int n = 0; - struct rb_node *nd; - - for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) { - struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node); - struct callchain_list *chain; - bool has_children = false; - - list_for_each_entry(chain, &child->val, list) { - ++n; - map_symbol__set_folding(&chain->ms, unfold); - has_children = chain->ms.has_children; - } - - if (has_children) - n += callchain_node__set_folding_rb_tree(child, unfold); - } - - return n; -} - -static int callchain_node__set_folding(struct callchain_node *node, bool unfold) -{ - struct callchain_list *chain; - bool has_children = false; - int n = 0; - - list_for_each_entry(chain, &node->val, list) { - ++n; - map_symbol__set_folding(&chain->ms, unfold); - has_children = chain->ms.has_children; - } - - if (has_children) - n += callchain_node__set_folding_rb_tree(node, unfold); - - return n; -} - -static int callchain__set_folding(struct rb_root *chain, bool unfold) -{ - struct rb_node *nd; - int n = 0; - - for (nd = rb_first(chain); nd; nd = rb_next(nd)) { - struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); - n += callchain_node__set_folding(node, unfold); - } - - return n; -} - -static void hist_entry__set_folding(struct hist_entry *self, bool unfold) -{ - hist_entry__init_have_children(self); - map_symbol__set_folding(&self->ms, unfold); - - if (self->ms.has_children) { - int n = callchain__set_folding(&self->sorted_chain, unfold); - self->nr_rows = unfold ? n : 0; - } else - self->nr_rows = 0; -} - -static void hists__set_folding(struct hists *self, bool unfold) -{ - struct rb_node *nd; - - self->nr_entries = 0; - - for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { - struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); - hist_entry__set_folding(he, unfold); - self->nr_entries += 1 + he->nr_rows; - } -} - -static void hist_browser__set_folding(struct hist_browser *self, bool unfold) -{ - hists__set_folding(self->hists, unfold); - self->b.nr_entries = self->hists->nr_entries; - /* Go to the start, we may be way after valid entries after a collapse */ - ui_browser__reset_index(&self->b); -} - -static int hist_browser__run(struct hist_browser *self, const char *title) -{ - int key; - int exit_keys[] = { 'a', '?', 'h', 'C', 'd', 'D', 'E', 't', - NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT, 0, }; - - self->b.entries = &self->hists->entries; - self->b.nr_entries = self->hists->nr_entries; - - hist_browser__refresh_dimensions(self); - - if (ui_browser__show(&self->b, title, - "Press '?' for help on key bindings") < 0) - return -1; - - ui_browser__add_exit_keys(&self->b, exit_keys); - - while (1) { - key = ui_browser__run(&self->b); - - switch (key) { - case 'D': { /* Debug */ - static int seq; - struct hist_entry *h = rb_entry(self->b.top, - struct hist_entry, rb_node); - ui_helpline__pop(); - ui_helpline__fpush("%d: nr_ent=(%d,%d), height=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", - seq++, self->b.nr_entries, - self->hists->nr_entries, - self->b.height, - self->b.index, - self->b.top_idx, - h->row_offset, h->nr_rows); - } - break; - case 'C': - /* Collapse the whole world. */ - hist_browser__set_folding(self, false); - break; - case 'E': - /* Expand the whole world. */ - hist_browser__set_folding(self, true); - break; - case NEWT_KEY_ENTER: - if (hist_browser__toggle_fold(self)) - break; - /* fall thru */ - default: - goto out; - } - } -out: - ui_browser__hide(&self->b); - return key; -} - -static char *callchain_list__sym_name(struct callchain_list *self, - char *bf, size_t bfsize) -{ - if (self->ms.sym) - return self->ms.sym->name; - - snprintf(bf, bfsize, "%#Lx", self->ip); - return bf; -} - -#define LEVEL_OFFSET_STEP 3 - -static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self, - struct callchain_node *chain_node, - u64 total, int level, - unsigned short row, - off_t *row_offset, - bool *is_current_entry) -{ - struct rb_node *node; - int first_row = row, width, offset = level * LEVEL_OFFSET_STEP; - u64 new_total, remaining; - - if (callchain_param.mode == CHAIN_GRAPH_REL) - new_total = chain_node->children_hit; - else - new_total = total; - - remaining = new_total; - node = rb_first(&chain_node->rb_root); - while (node) { - struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); - struct rb_node *next = rb_next(node); - u64 cumul = cumul_hits(child); - struct callchain_list *chain; - char folded_sign = ' '; - int first = true; - int extra_offset = 0; - - remaining -= cumul; - - list_for_each_entry(chain, &child->val, list) { - char ipstr[BITS_PER_LONG / 4 + 1], *alloc_str; - const char *str; - int color; - bool was_first = first; - - if (first) - first = false; - else - extra_offset = LEVEL_OFFSET_STEP; - - folded_sign = callchain_list__folded(chain); - if (*row_offset != 0) { - --*row_offset; - goto do_next; - } - - alloc_str = NULL; - str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); - if (was_first) { - double percent = cumul * 100.0 / new_total; - - if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0) - str = "Not enough memory!"; - else - str = alloc_str; - } - - color = HE_COLORSET_NORMAL; - width = self->b.width - (offset + extra_offset + 2); - if (ui_browser__is_current_entry(&self->b, row)) { - self->selection = &chain->ms; - color = HE_COLORSET_SELECTED; - *is_current_entry = true; - } - - ui_browser__set_color(&self->b, color); - ui_browser__gotorc(&self->b, row, 0); - slsmg_write_nstring(" ", offset + extra_offset); - slsmg_printf("%c ", folded_sign); - slsmg_write_nstring(str, width); - free(alloc_str); - - if (++row == self->b.height) - goto out; -do_next: - if (folded_sign == '+') - break; - } - - if (folded_sign == '-') { - const int new_level = level + (extra_offset ? 2 : 1); - row += hist_browser__show_callchain_node_rb_tree(self, child, new_total, - new_level, row, row_offset, - is_current_entry); - } - if (row == self->b.height) - goto out; - node = next; - } -out: - return row - first_row; -} - -static int hist_browser__show_callchain_node(struct hist_browser *self, - struct callchain_node *node, - int level, unsigned short row, - off_t *row_offset, - bool *is_current_entry) -{ - struct callchain_list *chain; - int first_row = row, - offset = level * LEVEL_OFFSET_STEP, - width = self->b.width - offset; - char folded_sign = ' '; - - list_for_each_entry(chain, &node->val, list) { - char ipstr[BITS_PER_LONG / 4 + 1], *s; - int color; - - folded_sign = callchain_list__folded(chain); - - if (*row_offset != 0) { - --*row_offset; - continue; - } - - color = HE_COLORSET_NORMAL; - if (ui_browser__is_current_entry(&self->b, row)) { - self->selection = &chain->ms; - color = HE_COLORSET_SELECTED; - *is_current_entry = true; - } - - s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); - ui_browser__gotorc(&self->b, row, 0); - ui_browser__set_color(&self->b, color); - slsmg_write_nstring(" ", offset); - slsmg_printf("%c ", folded_sign); - slsmg_write_nstring(s, width - 2); - - if (++row == self->b.height) - goto out; - } - - if (folded_sign == '-') - row += hist_browser__show_callchain_node_rb_tree(self, node, - self->hists->stats.total_period, - level + 1, row, - row_offset, - is_current_entry); -out: - return row - first_row; -} - -static int hist_browser__show_callchain(struct hist_browser *self, - struct rb_root *chain, - int level, unsigned short row, - off_t *row_offset, - bool *is_current_entry) -{ - struct rb_node *nd; - int first_row = row; - - for (nd = rb_first(chain); nd; nd = rb_next(nd)) { - struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); - - row += hist_browser__show_callchain_node(self, node, level, - row, row_offset, - is_current_entry); - if (row == self->b.height) - break; - } - - return row - first_row; -} - -static int hist_browser__show_entry(struct hist_browser *self, - struct hist_entry *entry, - unsigned short row) -{ - char s[256]; - double percent; - int printed = 0; - int color, width = self->b.width; - char folded_sign = ' '; - bool current_entry = ui_browser__is_current_entry(&self->b, row); - off_t row_offset = entry->row_offset; - - if (current_entry) { - self->he_selection = entry; - self->selection = &entry->ms; - } - - if (symbol_conf.use_callchain) { - hist_entry__init_have_children(entry); - folded_sign = hist_entry__folded(entry); - } - - if (row_offset == 0) { - hist_entry__snprintf(entry, s, sizeof(s), self->hists, NULL, false, - 0, false, self->hists->stats.total_period); - percent = (entry->period * 100.0) / self->hists->stats.total_period; - - color = HE_COLORSET_SELECTED; - if (!current_entry) { - if (percent >= MIN_RED) - color = HE_COLORSET_TOP; - else if (percent >= MIN_GREEN) - color = HE_COLORSET_MEDIUM; - else - color = HE_COLORSET_NORMAL; - } - - ui_browser__set_color(&self->b, color); - ui_browser__gotorc(&self->b, row, 0); - if (symbol_conf.use_callchain) { - slsmg_printf("%c ", folded_sign); - width -= 2; - } - slsmg_write_nstring(s, width); - ++row; - ++printed; - } else - --row_offset; - - if (folded_sign == '-' && row != self->b.height) { - printed += hist_browser__show_callchain(self, &entry->sorted_chain, - 1, row, &row_offset, - ¤t_entry); - if (current_entry) - self->he_selection = entry; - } - - return printed; -} - -static unsigned int hist_browser__refresh(struct ui_browser *self) -{ - unsigned row = 0; - struct rb_node *nd; - struct hist_browser *hb = container_of(self, struct hist_browser, b); - - if (self->top == NULL) - self->top = rb_first(&hb->hists->entries); - - for (nd = self->top; nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - - if (h->filtered) - continue; - - row += hist_browser__show_entry(hb, h, row); - if (row == self->height) - break; - } - - return row; -} - -static struct rb_node *hists__filter_entries(struct rb_node *nd) -{ - while (nd != NULL) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - if (!h->filtered) - return nd; - - nd = rb_next(nd); - } - - return NULL; -} - -static struct rb_node *hists__filter_prev_entries(struct rb_node *nd) -{ - while (nd != NULL) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - if (!h->filtered) - return nd; - - nd = rb_prev(nd); - } - - return NULL; -} - -static void ui_browser__hists_seek(struct ui_browser *self, - off_t offset, int whence) -{ - struct hist_entry *h; - struct rb_node *nd; - bool first = true; - - switch (whence) { - case SEEK_SET: - nd = hists__filter_entries(rb_first(self->entries)); - break; - case SEEK_CUR: - nd = self->top; - goto do_offset; - case SEEK_END: - nd = hists__filter_prev_entries(rb_last(self->entries)); - first = false; - break; - default: - return; - } - - /* - * Moves not relative to the first visible entry invalidates its - * row_offset: - */ - h = rb_entry(self->top, struct hist_entry, rb_node); - h->row_offset = 0; - - /* - * Here we have to check if nd is expanded (+), if it is we can't go - * the next top level hist_entry, instead we must compute an offset of - * what _not_ to show and not change the first visible entry. - * - * This offset increments when we are going from top to bottom and - * decreases when we're going from bottom to top. - * - * As we don't have backpointers to the top level in the callchains - * structure, we need to always print the whole hist_entry callchain, - * skipping the first ones that are before the first visible entry - * and stop when we printed enough lines to fill the screen. - */ -do_offset: - if (offset > 0) { - do { - h = rb_entry(nd, struct hist_entry, rb_node); - if (h->ms.unfolded) { - u16 remaining = h->nr_rows - h->row_offset; - if (offset > remaining) { - offset -= remaining; - h->row_offset = 0; - } else { - h->row_offset += offset; - offset = 0; - self->top = nd; - break; - } - } - nd = hists__filter_entries(rb_next(nd)); - if (nd == NULL) - break; - --offset; - self->top = nd; - } while (offset != 0); - } else if (offset < 0) { - while (1) { - h = rb_entry(nd, struct hist_entry, rb_node); - if (h->ms.unfolded) { - if (first) { - if (-offset > h->row_offset) { - offset += h->row_offset; - h->row_offset = 0; - } else { - h->row_offset += offset; - offset = 0; - self->top = nd; - break; - } - } else { - if (-offset > h->nr_rows) { - offset += h->nr_rows; - h->row_offset = 0; - } else { - h->row_offset = h->nr_rows + offset; - offset = 0; - self->top = nd; - break; - } - } - } - - nd = hists__filter_prev_entries(rb_prev(nd)); - if (nd == NULL) - break; - ++offset; - self->top = nd; - if (offset == 0) { - /* - * Last unfiltered hist_entry, check if it is - * unfolded, if it is then we should have - * row_offset at its last entry. - */ - h = rb_entry(nd, struct hist_entry, rb_node); - if (h->ms.unfolded) - h->row_offset = h->nr_rows; - break; - } - first = false; - } - } else { - self->top = nd; - h = rb_entry(nd, struct hist_entry, rb_node); - h->row_offset = 0; - } -} - -static struct hist_browser *hist_browser__new(struct hists *hists) -{ - struct hist_browser *self = zalloc(sizeof(*self)); - - if (self) { - self->hists = hists; - self->b.refresh = hist_browser__refresh; - self->b.seek = ui_browser__hists_seek; - } - - return self; -} - -static void hist_browser__delete(struct hist_browser *self) -{ - free(self); -} - -static struct hist_entry *hist_browser__selected_entry(struct hist_browser *self) -{ - return self->he_selection; -} - -static struct thread *hist_browser__selected_thread(struct hist_browser *self) -{ - return self->he_selection->thread; -} - -static int hists__browser_title(struct hists *self, char *bf, size_t size, - const char *ev_name, const struct dso *dso, - const struct thread *thread) -{ - char unit; - int printed; - unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE]; - - nr_events = convert_unit(nr_events, &unit); - printed = snprintf(bf, size, "Events: %lu%c %s", nr_events, unit, ev_name); - - if (thread) - printed += snprintf(bf + printed, size - printed, - ", Thread: %s(%d)", - (thread->comm_set ? thread->comm : ""), - thread->pid); - if (dso) - printed += snprintf(bf + printed, size - printed, - ", DSO: %s", dso->short_name); - return printed; -} - -int hists__browse(struct hists *self, const char *helpline, const char *ev_name) -{ - struct hist_browser *browser = hist_browser__new(self); - struct pstack *fstack; - const struct thread *thread_filter = NULL; - const struct dso *dso_filter = NULL; - char msg[160]; - int key = -1; - - if (browser == NULL) - return -1; - - fstack = pstack__new(2); - if (fstack == NULL) - goto out; - - ui_helpline__push(helpline); - - hists__browser_title(self, msg, sizeof(msg), ev_name, - dso_filter, thread_filter); - while (1) { - const struct thread *thread; - const struct dso *dso; - char *options[16]; - int nr_options = 0, choice = 0, i, - annotate = -2, zoom_dso = -2, zoom_thread = -2, - browse_map = -2; - - key = hist_browser__run(browser, msg); - - thread = hist_browser__selected_thread(browser); - dso = browser->selection->map ? browser->selection->map->dso : NULL; - - switch (key) { - case NEWT_KEY_TAB: - case NEWT_KEY_UNTAB: - /* - * Exit the browser, let hists__browser_tree - * go to the next or previous - */ - goto out_free_stack; - case 'a': - if (browser->selection->map == NULL && - browser->selection->map->dso->annotate_warned) - continue; - goto do_annotate; - case 'd': - goto zoom_dso; - case 't': - goto zoom_thread; - case NEWT_KEY_F1: - case 'h': - case '?': - ui__help_window("-> Zoom into DSO/Threads & Annotate current symbol\n" - "<- Zoom out\n" - "a Annotate current symbol\n" - "h/?/F1 Show this window\n" - "C Collapse all callchains\n" - "E Expand all callchains\n" - "d Zoom into current DSO\n" - "t Zoom into current Thread\n" - "q/CTRL+C Exit browser"); - continue; - case NEWT_KEY_ENTER: - case NEWT_KEY_RIGHT: - /* menu */ - break; - case NEWT_KEY_LEFT: { - const void *top; - - if (pstack__empty(fstack)) - continue; - top = pstack__pop(fstack); - if (top == &dso_filter) - goto zoom_out_dso; - if (top == &thread_filter) - goto zoom_out_thread; - continue; - } - case NEWT_KEY_ESCAPE: - if (!ui__dialog_yesno("Do you really want to exit?")) - continue; - /* Fall thru */ - default: - goto out_free_stack; - } - - if (browser->selection->sym != NULL && - !browser->selection->map->dso->annotate_warned && - asprintf(&options[nr_options], "Annotate %s", - browser->selection->sym->name) > 0) - annotate = nr_options++; - - if (thread != NULL && - asprintf(&options[nr_options], "Zoom %s %s(%d) thread", - (thread_filter ? "out of" : "into"), - (thread->comm_set ? thread->comm : ""), - thread->pid) > 0) - zoom_thread = nr_options++; - - if (dso != NULL && - asprintf(&options[nr_options], "Zoom %s %s DSO", - (dso_filter ? "out of" : "into"), - (dso->kernel ? "the Kernel" : dso->short_name)) > 0) - zoom_dso = nr_options++; - - if (browser->selection->map != NULL && - asprintf(&options[nr_options], "Browse map details") > 0) - browse_map = nr_options++; - - options[nr_options++] = (char *)"Exit"; - - choice = ui__popup_menu(nr_options, options); - - for (i = 0; i < nr_options - 1; ++i) - free(options[i]); - - if (choice == nr_options - 1) - break; - - if (choice == -1) - continue; - - if (choice == annotate) { - struct hist_entry *he; -do_annotate: - if (browser->selection->map->dso->origin == DSO__ORIG_KERNEL) { - browser->selection->map->dso->annotate_warned = 1; - ui_helpline__puts("No vmlinux file found, can't " - "annotate with just a " - "kallsyms file"); - continue; - } - - he = hist_browser__selected_entry(browser); - if (he == NULL) - continue; - - hist_entry__tui_annotate(he); - } else if (choice == browse_map) - map__browse(browser->selection->map); - else if (choice == zoom_dso) { -zoom_dso: - if (dso_filter) { - pstack__remove(fstack, &dso_filter); -zoom_out_dso: - ui_helpline__pop(); - dso_filter = NULL; - } else { - if (dso == NULL) - continue; - ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"", - dso->kernel ? "the Kernel" : dso->short_name); - dso_filter = dso; - pstack__push(fstack, &dso_filter); - } - hists__filter_by_dso(self, dso_filter); - hists__browser_title(self, msg, sizeof(msg), ev_name, - dso_filter, thread_filter); - hist_browser__reset(browser); - } else if (choice == zoom_thread) { -zoom_thread: - if (thread_filter) { - pstack__remove(fstack, &thread_filter); -zoom_out_thread: - ui_helpline__pop(); - thread_filter = NULL; - } else { - ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"", - thread->comm_set ? thread->comm : "", - thread->pid); - thread_filter = thread; - pstack__push(fstack, &thread_filter); - } - hists__filter_by_thread(self, thread_filter); - hists__browser_title(self, msg, sizeof(msg), ev_name, - dso_filter, thread_filter); - hist_browser__reset(browser); - } - } -out_free_stack: - pstack__delete(fstack); -out: - hist_browser__delete(browser); - return key; -} - -int hists__tui_browse_tree(struct rb_root *self, const char *help) -{ - struct rb_node *first = rb_first(self), *nd = first, *next; - int key = 0; - - while (nd) { - struct hists *hists = rb_entry(nd, struct hists, rb_node); - const char *ev_name = __event_name(hists->type, hists->config); - - key = hists__browse(hists, help, ev_name); - switch (key) { - case NEWT_KEY_TAB: - next = rb_next(nd); - if (next) - nd = next; - break; - case NEWT_KEY_UNTAB: - if (nd == first) - continue; - nd = rb_prev(nd); - default: - return key; - } - } - - return key; -} diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c deleted file mode 100644 index e35437dfa5b..00000000000 --- a/tools/perf/util/ui/browsers/map.c +++ /dev/null @@ -1,155 +0,0 @@ -#include "../libslang.h" -#include <elf.h> -#include <sys/ttydefaults.h> -#include <ctype.h> -#include <string.h> -#include <linux/bitops.h> -#include "../../debug.h" -#include "../../symbol.h" -#include "../browser.h" -#include "../helpline.h" -#include "map.h" - -static int ui_entry__read(const char *title, char *bf, size_t size, int width) -{ - struct newtExitStruct es; - newtComponent form, entry; - const char *result; - int err = -1; - - newtCenteredWindow(width, 1, title); - form = newtForm(NULL, NULL, 0); - if (form == NULL) - return -1; - - entry = newtEntry(0, 0, "0x", width, &result, NEWT_FLAG_SCROLL); - if (entry == NULL) - goto out_free_form; - - newtFormAddComponent(form, entry); - newtFormAddHotKey(form, NEWT_KEY_ENTER); - newtFormAddHotKey(form, NEWT_KEY_ESCAPE); - newtFormAddHotKey(form, NEWT_KEY_LEFT); - newtFormAddHotKey(form, CTRL('c')); - newtFormRun(form, &es); - - if (result != NULL) { - strncpy(bf, result, size); - err = 0; - } -out_free_form: - newtPopWindow(); - newtFormDestroy(form); - return 0; -} - -struct map_browser { - struct ui_browser b; - struct map *map; - u8 addrlen; -}; - -static void map_browser__write(struct ui_browser *self, void *nd, int row) -{ - struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - struct map_browser *mb = container_of(self, struct map_browser, b); - bool current_entry = ui_browser__is_current_entry(self, row); - int width; - - ui_browser__set_percent_color(self, 0, current_entry); - slsmg_printf("%*llx %*llx %c ", - mb->addrlen, sym->start, mb->addrlen, sym->end, - sym->binding == STB_GLOBAL ? 'g' : - sym->binding == STB_LOCAL ? 'l' : 'w'); - width = self->width - ((mb->addrlen * 2) + 4); - if (width > 0) - slsmg_write_nstring(sym->name, width); -} - -/* FIXME uber-kludgy, see comment on cmd_report... */ -static u32 *symbol__browser_index(struct symbol *self) -{ - return ((void *)self) - sizeof(struct rb_node) - sizeof(u32); -} - -static int map_browser__search(struct map_browser *self) -{ - char target[512]; - struct symbol *sym; - int err = ui_entry__read("Search by name/addr", target, sizeof(target), 40); - - if (err) - return err; - - if (target[0] == '0' && tolower(target[1]) == 'x') { - u64 addr = strtoull(target, NULL, 16); - sym = map__find_symbol(self->map, addr, NULL); - } else - sym = map__find_symbol_by_name(self->map, target, NULL); - - if (sym != NULL) { - u32 *idx = symbol__browser_index(sym); - - self->b.top = &sym->rb_node; - self->b.index = self->b.top_idx = *idx; - } else - ui_helpline__fpush("%s not found!", target); - - return 0; -} - -static int map_browser__run(struct map_browser *self) -{ - int key; - - if (ui_browser__show(&self->b, self->map->dso->long_name, - "Press <- or ESC to exit, %s / to search", - verbose ? "" : "restart with -v to use") < 0) - return -1; - - if (verbose) - ui_browser__add_exit_key(&self->b, '/'); - - while (1) { - key = ui_browser__run(&self->b); - - if (verbose && key == '/') - map_browser__search(self); - else - break; - } - - ui_browser__hide(&self->b); - return key; -} - -int map__browse(struct map *self) -{ - struct map_browser mb = { - .b = { - .entries = &self->dso->symbols[self->type], - .refresh = ui_browser__rb_tree_refresh, - .seek = ui_browser__rb_tree_seek, - .write = map_browser__write, - }, - .map = self, - }; - struct rb_node *nd; - char tmp[BITS_PER_LONG / 4]; - u64 maxaddr = 0; - - for (nd = rb_first(mb.b.entries); nd; nd = rb_next(nd)) { - struct symbol *pos = rb_entry(nd, struct symbol, rb_node); - - if (maxaddr < pos->end) - maxaddr = pos->end; - if (verbose) { - u32 *idx = symbol__browser_index(pos); - *idx = mb.b.nr_entries; - } - ++mb.b.nr_entries; - } - - mb.addrlen = snprintf(tmp, sizeof(tmp), "%llx", maxaddr); - return map_browser__run(&mb); -} diff --git a/tools/perf/util/ui/browsers/map.h b/tools/perf/util/ui/browsers/map.h deleted file mode 100644 index df8581a43e1..00000000000 --- a/tools/perf/util/ui/browsers/map.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _PERF_UI_MAP_BROWSER_H_ -#define _PERF_UI_MAP_BROWSER_H_ 1 -struct map; - -int map__browse(struct map *self); -#endif /* _PERF_UI_MAP_BROWSER_H_ */ diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/util/ui/helpline.c deleted file mode 100644 index 8d79daa4458..00000000000 --- a/tools/perf/util/ui/helpline.c +++ /dev/null @@ -1,69 +0,0 @@ -#define _GNU_SOURCE -#include <stdio.h> -#include <stdlib.h> -#include <newt.h> - -#include "../debug.h" -#include "helpline.h" - -void ui_helpline__pop(void) -{ - newtPopHelpLine(); -} - -void ui_helpline__push(const char *msg) -{ - newtPushHelpLine(msg); -} - -void ui_helpline__vpush(const char *fmt, va_list ap) -{ - char *s; - - if (vasprintf(&s, fmt, ap) < 0) - vfprintf(stderr, fmt, ap); - else { - ui_helpline__push(s); - free(s); - } -} - -void ui_helpline__fpush(const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - ui_helpline__vpush(fmt, ap); - va_end(ap); -} - -void ui_helpline__puts(const char *msg) -{ - ui_helpline__pop(); - ui_helpline__push(msg); -} - -void ui_helpline__init(void) -{ - ui_helpline__puts(" "); -} - -char ui_helpline__last_msg[1024]; - -int ui_helpline__show_help(const char *format, va_list ap) -{ - int ret; - static int backlog; - - ret = vsnprintf(ui_helpline__last_msg + backlog, - sizeof(ui_helpline__last_msg) - backlog, format, ap); - backlog += ret; - - if (ui_helpline__last_msg[backlog - 1] == '\n') { - ui_helpline__puts(ui_helpline__last_msg); - newtRefresh(); - backlog = 0; - } - - return ret; -} diff --git a/tools/perf/util/ui/helpline.h b/tools/perf/util/ui/helpline.h deleted file mode 100644 index ab6028d0c40..00000000000 --- a/tools/perf/util/ui/helpline.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _PERF_UI_HELPLINE_H_ -#define _PERF_UI_HELPLINE_H_ 1 - -void ui_helpline__init(void); -void ui_helpline__pop(void); -void ui_helpline__push(const char *msg); -void ui_helpline__vpush(const char *fmt, va_list ap); -void ui_helpline__fpush(const char *fmt, ...); -void ui_helpline__puts(const char *msg); - -#endif /* _PERF_UI_HELPLINE_H_ */ diff --git a/tools/perf/util/ui/libslang.h b/tools/perf/util/ui/libslang.h deleted file mode 100644 index 5623da8e808..00000000000 --- a/tools/perf/util/ui/libslang.h +++ /dev/null @@ -1,27 +0,0 @@ -#ifndef _PERF_UI_SLANG_H_ -#define _PERF_UI_SLANG_H_ 1 -/* - * slang versions <= 2.0.6 have a "#if HAVE_LONG_LONG" that breaks - * the build if it isn't defined. Use the equivalent one that glibc - * has on features.h. - */ -#include <features.h> -#ifndef HAVE_LONG_LONG -#define HAVE_LONG_LONG __GLIBC_HAVE_LONG_LONG -#endif -#include <slang.h> - -#if SLANG_VERSION < 20104 -#define slsmg_printf(msg, args...) \ - SLsmg_printf((char *)msg, ##args) -#define slsmg_write_nstring(msg, len) \ - SLsmg_write_nstring((char *)msg, len) -#define sltt_set_color(obj, name, fg, bg) \ - SLtt_set_color(obj,(char *)name, (char *)fg, (char *)bg) -#else -#define slsmg_printf SLsmg_printf -#define slsmg_write_nstring SLsmg_write_nstring -#define sltt_set_color SLtt_set_color -#endif - -#endif /* _PERF_UI_SLANG_H_ */ diff --git a/tools/perf/util/ui/progress.c b/tools/perf/util/ui/progress.c deleted file mode 100644 index d7fc399d36b..00000000000 --- a/tools/perf/util/ui/progress.c +++ /dev/null @@ -1,60 +0,0 @@ -#include <stdlib.h> -#include <newt.h> -#include "../cache.h" -#include "progress.h" - -struct ui_progress { - newtComponent form, scale; -}; - -struct ui_progress *ui_progress__new(const char *title, u64 total) -{ - struct ui_progress *self = malloc(sizeof(*self)); - - if (self != NULL) { - int cols; - - if (use_browser <= 0) - return self; - newtGetScreenSize(&cols, NULL); - cols -= 4; - newtCenteredWindow(cols, 1, title); - self->form = newtForm(NULL, NULL, 0); - if (self->form == NULL) - goto out_free_self; - self->scale = newtScale(0, 0, cols, total); - if (self->scale == NULL) - goto out_free_form; - newtFormAddComponent(self->form, self->scale); - newtRefresh(); - } - - return self; - -out_free_form: - newtFormDestroy(self->form); -out_free_self: - free(self); - return NULL; -} - -void ui_progress__update(struct ui_progress *self, u64 curr) -{ - /* - * FIXME: We should have a per UI backend way of showing progress, - * stdio will just show a percentage as NN%, etc. - */ - if (use_browser <= 0) - return; - newtScaleSet(self->scale, curr); - newtRefresh(); -} - -void ui_progress__delete(struct ui_progress *self) -{ - if (use_browser > 0) { - newtFormDestroy(self->form); - newtPopWindow(); - } - free(self); -} diff --git a/tools/perf/util/ui/progress.h b/tools/perf/util/ui/progress.h deleted file mode 100644 index a3820a0beb5..00000000000 --- a/tools/perf/util/ui/progress.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _PERF_UI_PROGRESS_H_ -#define _PERF_UI_PROGRESS_H_ 1 - -struct ui_progress; - -struct ui_progress *ui_progress__new(const char *title, u64 total); -void ui_progress__delete(struct ui_progress *self); - -void ui_progress__update(struct ui_progress *self, u64 curr); - -#endif diff --git a/tools/perf/util/ui/setup.c b/tools/perf/util/ui/setup.c deleted file mode 100644 index 662085032eb..00000000000 --- a/tools/perf/util/ui/setup.c +++ /dev/null @@ -1,42 +0,0 @@ -#include <newt.h> -#include <signal.h> -#include <stdbool.h> - -#include "../cache.h" -#include "../debug.h" -#include "browser.h" -#include "helpline.h" - -static void newt_suspend(void *d __used) -{ - newtSuspend(); - raise(SIGTSTP); - newtResume(); -} - -void setup_browser(void) -{ - if (!isatty(1) || !use_browser || dump_trace) { - use_browser = 0; - setup_pager(); - return; - } - - use_browser = 1; - newtInit(); - newtCls(); - newtSetSuspendCallback(newt_suspend, NULL); - ui_helpline__init(); - ui_browser__init(); -} - -void exit_browser(bool wait_for_ok) -{ - if (use_browser > 0) { - if (wait_for_ok) { - char title[] = "Fatal Error", ok[] = "Ok"; - newtWinMessage(title, ok, ui_helpline__last_msg); - } - newtFinished(); - } -} diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c deleted file mode 100644 index 056c69521a3..00000000000 --- a/tools/perf/util/ui/util.c +++ /dev/null @@ -1,113 +0,0 @@ -#include <newt.h> -#include <signal.h> -#include <stdio.h> -#include <stdbool.h> -#include <string.h> -#include <sys/ttydefaults.h> - -#include "../cache.h" -#include "../debug.h" -#include "browser.h" -#include "helpline.h" -#include "util.h" - -static void newt_form__set_exit_keys(newtComponent self) -{ - newtFormAddHotKey(self, NEWT_KEY_LEFT); - newtFormAddHotKey(self, NEWT_KEY_ESCAPE); - newtFormAddHotKey(self, 'Q'); - newtFormAddHotKey(self, 'q'); - newtFormAddHotKey(self, CTRL('c')); -} - -static newtComponent newt_form__new(void) -{ - newtComponent self = newtForm(NULL, NULL, 0); - if (self) - newt_form__set_exit_keys(self); - return self; -} - -int ui__popup_menu(int argc, char * const argv[]) -{ - struct newtExitStruct es; - int i, rc = -1, max_len = 5; - newtComponent listbox, form = newt_form__new(); - - if (form == NULL) - return -1; - - listbox = newtListbox(0, 0, argc, NEWT_FLAG_RETURNEXIT); - if (listbox == NULL) - goto out_destroy_form; - - newtFormAddComponent(form, listbox); - - for (i = 0; i < argc; ++i) { - int len = strlen(argv[i]); - if (len > max_len) - max_len = len; - if (newtListboxAddEntry(listbox, argv[i], (void *)(long)i)) - goto out_destroy_form; - } - - newtCenteredWindow(max_len, argc, NULL); - newtFormRun(form, &es); - rc = newtListboxGetCurrent(listbox) - NULL; - if (es.reason == NEWT_EXIT_HOTKEY) - rc = -1; - newtPopWindow(); -out_destroy_form: - newtFormDestroy(form); - return rc; -} - -int ui__help_window(const char *text) -{ - struct newtExitStruct es; - newtComponent tb, form = newt_form__new(); - int rc = -1; - int max_len = 0, nr_lines = 0; - const char *t; - - if (form == NULL) - return -1; - - t = text; - while (1) { - const char *sep = strchr(t, '\n'); - int len; - - if (sep == NULL) - sep = strchr(t, '\0'); - len = sep - t; - if (max_len < len) - max_len = len; - ++nr_lines; - if (*sep == '\0') - break; - t = sep + 1; - } - - tb = newtTextbox(0, 0, max_len, nr_lines, 0); - if (tb == NULL) - goto out_destroy_form; - - newtTextboxSetText(tb, text); - newtFormAddComponent(form, tb); - newtCenteredWindow(max_len, nr_lines, NULL); - newtFormRun(form, &es); - newtPopWindow(); - rc = 0; -out_destroy_form: - newtFormDestroy(form); - return rc; -} - -static const char yes[] = "Yes", no[] = "No"; - -bool ui__dialog_yesno(const char *msg) -{ - /* newtWinChoice should really be accepting const char pointers... */ - return newtWinChoice(NULL, (char *)yes, (char *)no, (char *)msg) == 1; -} diff --git a/tools/perf/util/ui/util.h b/tools/perf/util/ui/util.h deleted file mode 100644 index afcbc1d9953..00000000000 --- a/tools/perf/util/ui/util.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef _PERF_UI_UTIL_H_ -#define _PERF_UI_UTIL_H_ 1 - -#include <stdbool.h> - -int ui__popup_menu(int argc, char * const argv[]); -int ui__help_window(const char *text); -bool ui__dialog_yesno(const char *msg); - -#endif /* _PERF_UI_UTIL_H_ */ diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c new file mode 100644 index 00000000000..5ec80a575b5 --- /dev/null +++ b/tools/perf/util/unwind-libdw.c @@ -0,0 +1,210 @@ +#include <linux/compiler.h> +#include <elfutils/libdw.h> +#include <elfutils/libdwfl.h> +#include <inttypes.h> +#include <errno.h> +#include "unwind.h" +#include "unwind-libdw.h" +#include "machine.h" +#include "thread.h" +#include <linux/types.h> +#include "event.h" +#include "perf_regs.h" + +static char *debuginfo_path; + +static const Dwfl_Callbacks offline_callbacks = { + .find_debuginfo = dwfl_standard_find_debuginfo, + .debuginfo_path = &debuginfo_path, + .section_address = dwfl_offline_section_address, +}; + +static int __report_module(struct addr_location *al, u64 ip, + struct unwind_info *ui) +{ + Dwfl_Module *mod; + struct dso *dso = NULL; + + thread__find_addr_location(ui->thread, ui->machine, + PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, al); + + if (al->map) + dso = al->map->dso; + + if (!dso) + return 0; + + mod = dwfl_addrmodule(ui->dwfl, ip); + if (!mod) + mod = dwfl_report_elf(ui->dwfl, dso->short_name, + dso->long_name, -1, al->map->start, + false); + + return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1; +} + +static int report_module(u64 ip, struct unwind_info *ui) +{ + struct addr_location al; + + return __report_module(&al, ip, ui); +} + +static int entry(u64 ip, struct unwind_info *ui) + +{ + struct unwind_entry e; + struct addr_location al; + + if (__report_module(&al, ip, ui)) + return -1; + + e.ip = ip; + e.map = al.map; + e.sym = al.sym; + + pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", + al.sym ? al.sym->name : "''", + ip, + al.map ? al.map->map_ip(al.map, ip) : (u64) 0); + + return ui->cb(&e, ui->arg); +} + +static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp) +{ + /* We want only single thread to be processed. */ + if (*thread_argp != NULL) + return 0; + + *thread_argp = arg; + return dwfl_pid(dwfl); +} + +static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, + Dwarf_Word *data) +{ + struct addr_location al; + ssize_t size; + + thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + MAP__FUNCTION, addr, &al); + if (!al.map) { + pr_debug("unwind: no map for %lx\n", (unsigned long)addr); + return -1; + } + + if (!al.map->dso) + return -1; + + size = dso__data_read_addr(al.map->dso, al.map, ui->machine, + addr, (u8 *) data, sizeof(*data)); + + return !(size == sizeof(*data)); +} + +static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result, + void *arg) +{ + struct unwind_info *ui = arg; + struct stack_dump *stack = &ui->sample->user_stack; + u64 start, end; + int offset; + int ret; + + ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP); + if (ret) + return false; + + end = start + stack->size; + + /* Check overflow. */ + if (addr + sizeof(Dwarf_Word) < addr) + return false; + + if (addr < start || addr + sizeof(Dwarf_Word) > end) { + ret = access_dso_mem(ui, addr, result); + if (ret) { + pr_debug("unwind: access_mem 0x%" PRIx64 " not inside range" + " 0x%" PRIx64 "-0x%" PRIx64 "\n", + addr, start, end); + return false; + } + return true; + } + + offset = addr - start; + *result = *(Dwarf_Word *)&stack->data[offset]; + pr_debug("unwind: access_mem addr 0x%" PRIx64 ", val %lx, offset %d\n", + addr, (unsigned long)*result, offset); + return true; +} + +static const Dwfl_Thread_Callbacks callbacks = { + .next_thread = next_thread, + .memory_read = memory_read, + .set_initial_registers = libdw__arch_set_initial_registers, +}; + +static int +frame_callback(Dwfl_Frame *state, void *arg) +{ + struct unwind_info *ui = arg; + Dwarf_Addr pc; + + if (!dwfl_frame_pc(state, &pc, NULL)) { + pr_err("%s", dwfl_errmsg(-1)); + return DWARF_CB_ABORT; + } + + return entry(pc, ui) || !(--ui->max_stack) ? + DWARF_CB_ABORT : DWARF_CB_OK; +} + +int unwind__get_entries(unwind_entry_cb_t cb, void *arg, + struct machine *machine, struct thread *thread, + struct perf_sample *data, + int max_stack) +{ + struct unwind_info ui = { + .sample = data, + .thread = thread, + .machine = machine, + .cb = cb, + .arg = arg, + .max_stack = max_stack, + }; + Dwarf_Word ip; + int err = -EINVAL; + + if (!data->user_regs.regs) + return -EINVAL; + + ui.dwfl = dwfl_begin(&offline_callbacks); + if (!ui.dwfl) + goto out; + + err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP); + if (err) + goto out; + + err = report_module(ip, &ui); + if (err) + goto out; + + if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui)) + goto out; + + err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui); + + if (err && !ui.max_stack) + err = 0; + + out: + if (err) + pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1)); + + dwfl_end(ui.dwfl); + return 0; +} diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h new file mode 100644 index 00000000000..417a1426f3a --- /dev/null +++ b/tools/perf/util/unwind-libdw.h @@ -0,0 +1,21 @@ +#ifndef __PERF_UNWIND_LIBDW_H +#define __PERF_UNWIND_LIBDW_H + +#include <elfutils/libdwfl.h> +#include "event.h" +#include "thread.h" +#include "unwind.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg); + +struct unwind_info { + Dwfl *dwfl; + struct perf_sample *sample; + struct machine *machine; + struct thread *thread; + unwind_entry_cb_t cb; + void *arg; + int max_stack; +}; + +#endif /* __PERF_UNWIND_LIBDW_H */ diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c new file mode 100644 index 00000000000..25578b98f5c --- /dev/null +++ b/tools/perf/util/unwind-libunwind.c @@ -0,0 +1,579 @@ +/* + * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps. + * + * Lots of this code have been borrowed or heavily inspired from parts of + * the libunwind 0.99 code which are (amongst other contributors I may have + * forgotten): + * + * Copyright (C) 2002-2007 Hewlett-Packard Co + * Contributed by David Mosberger-Tang <davidm@hpl.hp.com> + * + * And the bugs have been added by: + * + * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com> + * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com> + * + */ + +#include <elf.h> +#include <gelf.h> +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> +#include <linux/list.h> +#include <libunwind.h> +#include <libunwind-ptrace.h> +#include "thread.h" +#include "session.h" +#include "perf_regs.h" +#include "unwind.h" +#include "symbol.h" +#include "util.h" + +extern int +UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, + unw_word_t ip, + unw_dyn_info_t *di, + unw_proc_info_t *pi, + int need_unwind_info, void *arg); + +#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) + +extern int +UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, + unw_word_t ip, + unw_word_t segbase, + const char *obj_name, unw_word_t start, + unw_word_t end); + +#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame) + +#define DW_EH_PE_FORMAT_MASK 0x0f /* format of the encoded value */ +#define DW_EH_PE_APPL_MASK 0x70 /* how the value is to be applied */ + +/* Pointer-encoding formats: */ +#define DW_EH_PE_omit 0xff +#define DW_EH_PE_ptr 0x00 /* pointer-sized unsigned value */ +#define DW_EH_PE_udata4 0x03 /* unsigned 32-bit value */ +#define DW_EH_PE_udata8 0x04 /* unsigned 64-bit value */ +#define DW_EH_PE_sdata4 0x0b /* signed 32-bit value */ +#define DW_EH_PE_sdata8 0x0c /* signed 64-bit value */ + +/* Pointer-encoding application: */ +#define DW_EH_PE_absptr 0x00 /* absolute value */ +#define DW_EH_PE_pcrel 0x10 /* rel. to addr. of encoded value */ + +/* + * The following are not documented by LSB v1.3, yet they are used by + * GCC, presumably they aren't documented by LSB since they aren't + * used on Linux: + */ +#define DW_EH_PE_funcrel 0x40 /* start-of-procedure-relative */ +#define DW_EH_PE_aligned 0x50 /* aligned pointer */ + +/* Flags intentionaly not handled, since they're not needed: + * #define DW_EH_PE_indirect 0x80 + * #define DW_EH_PE_uleb128 0x01 + * #define DW_EH_PE_udata2 0x02 + * #define DW_EH_PE_sleb128 0x09 + * #define DW_EH_PE_sdata2 0x0a + * #define DW_EH_PE_textrel 0x20 + * #define DW_EH_PE_datarel 0x30 + */ + +struct unwind_info { + struct perf_sample *sample; + struct machine *machine; + struct thread *thread; +}; + +#define dw_read(ptr, type, end) ({ \ + type *__p = (type *) ptr; \ + type __v; \ + if ((__p + 1) > (type *) end) \ + return -EINVAL; \ + __v = *__p++; \ + ptr = (typeof(ptr)) __p; \ + __v; \ + }) + +static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val, + u8 encoding) +{ + u8 *cur = *p; + *val = 0; + + switch (encoding) { + case DW_EH_PE_omit: + *val = 0; + goto out; + case DW_EH_PE_ptr: + *val = dw_read(cur, unsigned long, end); + goto out; + default: + break; + } + + switch (encoding & DW_EH_PE_APPL_MASK) { + case DW_EH_PE_absptr: + break; + case DW_EH_PE_pcrel: + *val = (unsigned long) cur; + break; + default: + return -EINVAL; + } + + if ((encoding & 0x07) == 0x00) + encoding |= DW_EH_PE_udata4; + + switch (encoding & DW_EH_PE_FORMAT_MASK) { + case DW_EH_PE_sdata4: + *val += dw_read(cur, s32, end); + break; + case DW_EH_PE_udata4: + *val += dw_read(cur, u32, end); + break; + case DW_EH_PE_sdata8: + *val += dw_read(cur, s64, end); + break; + case DW_EH_PE_udata8: + *val += dw_read(cur, u64, end); + break; + default: + return -EINVAL; + } + + out: + *p = cur; + return 0; +} + +#define dw_read_encoded_value(ptr, end, enc) ({ \ + u64 __v; \ + if (__dw_read_encoded_value(&ptr, end, &__v, enc)) { \ + return -EINVAL; \ + } \ + __v; \ + }) + +static u64 elf_section_offset(int fd, const char *name) +{ + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + u64 offset = 0; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + return 0; + + do { + if (gelf_getehdr(elf, &ehdr) == NULL) + break; + + if (!elf_section_by_name(elf, &ehdr, &shdr, name, NULL)) + break; + + offset = shdr.sh_offset; + } while (0); + + elf_end(elf); + return offset; +} + +struct table_entry { + u32 start_ip_offset; + u32 fde_offset; +}; + +struct eh_frame_hdr { + unsigned char version; + unsigned char eh_frame_ptr_enc; + unsigned char fde_count_enc; + unsigned char table_enc; + + /* + * The rest of the header is variable-length and consists of the + * following members: + * + * encoded_t eh_frame_ptr; + * encoded_t fde_count; + */ + + /* A single encoded pointer should not be more than 8 bytes. */ + u64 enc[2]; + + /* + * struct { + * encoded_t start_ip; + * encoded_t fde_addr; + * } binary_search_table[fde_count]; + */ + char data[0]; +} __packed; + +static int unwind_spec_ehframe(struct dso *dso, struct machine *machine, + u64 offset, u64 *table_data, u64 *segbase, + u64 *fde_count) +{ + struct eh_frame_hdr hdr; + u8 *enc = (u8 *) &hdr.enc; + u8 *end = (u8 *) &hdr.data; + ssize_t r; + + r = dso__data_read_offset(dso, machine, offset, + (u8 *) &hdr, sizeof(hdr)); + if (r != sizeof(hdr)) + return -EINVAL; + + /* We dont need eh_frame_ptr, just skip it. */ + dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc); + + *fde_count = dw_read_encoded_value(enc, end, hdr.fde_count_enc); + *segbase = offset; + *table_data = (enc - (u8 *) &hdr) + offset; + return 0; +} + +static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, + u64 *table_data, u64 *segbase, + u64 *fde_count) +{ + int ret = -EINVAL, fd; + u64 offset; + + fd = dso__data_fd(dso, machine); + if (fd < 0) + return -EINVAL; + + /* Check the .eh_frame section for unwinding info */ + offset = elf_section_offset(fd, ".eh_frame_hdr"); + + if (offset) + ret = unwind_spec_ehframe(dso, machine, offset, + table_data, segbase, + fde_count); + + return ret; +} + +#ifndef NO_LIBUNWIND_DEBUG_FRAME +static int read_unwind_spec_debug_frame(struct dso *dso, + struct machine *machine, u64 *offset) +{ + int fd = dso__data_fd(dso, machine); + + if (fd < 0) + return -EINVAL; + + /* Check the .debug_frame section for unwinding info */ + *offset = elf_section_offset(fd, ".debug_frame"); + + if (*offset) + return 0; + + return -EINVAL; +} +#endif + +static struct map *find_map(unw_word_t ip, struct unwind_info *ui) +{ + struct addr_location al; + + thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, &al); + return al.map; +} + +static int +find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, + int need_unwind_info, void *arg) +{ + struct unwind_info *ui = arg; + struct map *map; + unw_dyn_info_t di; + u64 table_data, segbase, fde_count; + + map = find_map(ip, ui); + if (!map || !map->dso) + return -EINVAL; + + pr_debug("unwind: find_proc_info dso %s\n", map->dso->name); + + /* Check the .eh_frame section for unwinding info */ + if (!read_unwind_spec_eh_frame(map->dso, ui->machine, + &table_data, &segbase, &fde_count)) { + memset(&di, 0, sizeof(di)); + di.format = UNW_INFO_FORMAT_REMOTE_TABLE; + di.start_ip = map->start; + di.end_ip = map->end; + di.u.rti.segbase = map->start + segbase; + di.u.rti.table_data = map->start + table_data; + di.u.rti.table_len = fde_count * sizeof(struct table_entry) + / sizeof(unw_word_t); + return dwarf_search_unwind_table(as, ip, &di, pi, + need_unwind_info, arg); + } + +#ifndef NO_LIBUNWIND_DEBUG_FRAME + /* Check the .debug_frame section for unwinding info */ + if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) { + memset(&di, 0, sizeof(di)); + if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name, + map->start, map->end)) + return dwarf_search_unwind_table(as, ip, &di, pi, + need_unwind_info, arg); + } +#endif + + return -EINVAL; +} + +static int access_fpreg(unw_addr_space_t __maybe_unused as, + unw_regnum_t __maybe_unused num, + unw_fpreg_t __maybe_unused *val, + int __maybe_unused __write, + void __maybe_unused *arg) +{ + pr_err("unwind: access_fpreg unsupported\n"); + return -UNW_EINVAL; +} + +static int get_dyn_info_list_addr(unw_addr_space_t __maybe_unused as, + unw_word_t __maybe_unused *dil_addr, + void __maybe_unused *arg) +{ + return -UNW_ENOINFO; +} + +static int resume(unw_addr_space_t __maybe_unused as, + unw_cursor_t __maybe_unused *cu, + void __maybe_unused *arg) +{ + pr_err("unwind: resume unsupported\n"); + return -UNW_EINVAL; +} + +static int +get_proc_name(unw_addr_space_t __maybe_unused as, + unw_word_t __maybe_unused addr, + char __maybe_unused *bufp, size_t __maybe_unused buf_len, + unw_word_t __maybe_unused *offp, void __maybe_unused *arg) +{ + pr_err("unwind: get_proc_name unsupported\n"); + return -UNW_EINVAL; +} + +static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, + unw_word_t *data) +{ + struct addr_location al; + ssize_t size; + + thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + MAP__FUNCTION, addr, &al); + if (!al.map) { + pr_debug("unwind: no map for %lx\n", (unsigned long)addr); + return -1; + } + + if (!al.map->dso) + return -1; + + size = dso__data_read_addr(al.map->dso, al.map, ui->machine, + addr, (u8 *) data, sizeof(*data)); + + return !(size == sizeof(*data)); +} + +static int access_mem(unw_addr_space_t __maybe_unused as, + unw_word_t addr, unw_word_t *valp, + int __write, void *arg) +{ + struct unwind_info *ui = arg; + struct stack_dump *stack = &ui->sample->user_stack; + u64 start, end; + int offset; + int ret; + + /* Don't support write, probably not needed. */ + if (__write || !stack || !ui->sample->user_regs.regs) { + *valp = 0; + return 0; + } + + ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP); + if (ret) + return ret; + + end = start + stack->size; + + /* Check overflow. */ + if (addr + sizeof(unw_word_t) < addr) + return -EINVAL; + + if (addr < start || addr + sizeof(unw_word_t) >= end) { + ret = access_dso_mem(ui, addr, valp); + if (ret) { + pr_debug("unwind: access_mem %p not inside range" + " 0x%" PRIx64 "-0x%" PRIx64 "\n", + (void *) addr, start, end); + *valp = 0; + return ret; + } + return 0; + } + + offset = addr - start; + *valp = *(unw_word_t *)&stack->data[offset]; + pr_debug("unwind: access_mem addr %p val %lx, offset %d\n", + (void *) addr, (unsigned long)*valp, offset); + return 0; +} + +static int access_reg(unw_addr_space_t __maybe_unused as, + unw_regnum_t regnum, unw_word_t *valp, + int __write, void *arg) +{ + struct unwind_info *ui = arg; + int id, ret; + u64 val; + + /* Don't support write, I suspect we don't need it. */ + if (__write) { + pr_err("unwind: access_reg w %d\n", regnum); + return 0; + } + + if (!ui->sample->user_regs.regs) { + *valp = 0; + return 0; + } + + id = libunwind__arch_reg_id(regnum); + if (id < 0) + return -EINVAL; + + ret = perf_reg_value(&val, &ui->sample->user_regs, id); + if (ret) { + pr_err("unwind: can't read reg %d\n", regnum); + return ret; + } + + *valp = (unw_word_t) val; + pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp); + return 0; +} + +static void put_unwind_info(unw_addr_space_t __maybe_unused as, + unw_proc_info_t *pi __maybe_unused, + void *arg __maybe_unused) +{ + pr_debug("unwind: put_unwind_info called\n"); +} + +static int entry(u64 ip, struct thread *thread, struct machine *machine, + unwind_entry_cb_t cb, void *arg) +{ + struct unwind_entry e; + struct addr_location al; + + thread__find_addr_location(thread, machine, + PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, &al); + + e.ip = ip; + e.map = al.map; + e.sym = al.sym; + + pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", + al.sym ? al.sym->name : "''", + ip, + al.map ? al.map->map_ip(al.map, ip) : (u64) 0); + + return cb(&e, arg); +} + +static void display_error(int err) +{ + switch (err) { + case UNW_EINVAL: + pr_err("unwind: Only supports local.\n"); + break; + case UNW_EUNSPEC: + pr_err("unwind: Unspecified error.\n"); + break; + case UNW_EBADREG: + pr_err("unwind: Register unavailable.\n"); + break; + default: + break; + } +} + +static unw_accessors_t accessors = { + .find_proc_info = find_proc_info, + .put_unwind_info = put_unwind_info, + .get_dyn_info_list_addr = get_dyn_info_list_addr, + .access_mem = access_mem, + .access_reg = access_reg, + .access_fpreg = access_fpreg, + .resume = resume, + .get_proc_name = get_proc_name, +}; + +static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, + void *arg, int max_stack) +{ + unw_addr_space_t addr_space; + unw_cursor_t c; + int ret; + + addr_space = unw_create_addr_space(&accessors, 0); + if (!addr_space) { + pr_err("unwind: Can't create unwind address space.\n"); + return -ENOMEM; + } + + ret = unw_init_remote(&c, addr_space, ui); + if (ret) + display_error(ret); + + while (!ret && (unw_step(&c) > 0) && max_stack--) { + unw_word_t ip; + + unw_get_reg(&c, UNW_REG_IP, &ip); + ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0; + } + + unw_destroy_addr_space(addr_space); + return ret; +} + +int unwind__get_entries(unwind_entry_cb_t cb, void *arg, + struct machine *machine, struct thread *thread, + struct perf_sample *data, int max_stack) +{ + u64 ip; + struct unwind_info ui = { + .sample = data, + .thread = thread, + .machine = machine, + }; + int ret; + + if (!data->user_regs.regs) + return -EINVAL; + + ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP); + if (ret) + return ret; + + ret = entry(ip, thread, machine, cb, arg); + if (ret) + return -ENOMEM; + + return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0; +} diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h new file mode 100644 index 00000000000..f03061260b4 --- /dev/null +++ b/tools/perf/util/unwind.h @@ -0,0 +1,37 @@ +#ifndef __UNWIND_H +#define __UNWIND_H + +#include <linux/types.h> +#include "event.h" +#include "symbol.h" + +struct unwind_entry { + struct map *map; + struct symbol *sym; + u64 ip; +}; + +typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); + +#ifdef HAVE_DWARF_UNWIND_SUPPORT +int unwind__get_entries(unwind_entry_cb_t cb, void *arg, + struct machine *machine, + struct thread *thread, + struct perf_sample *data, int max_stack); +/* libunwind specific */ +#ifdef HAVE_LIBUNWIND_SUPPORT +int libunwind__arch_reg_id(int regnum); +#endif +#else +static inline int +unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, + void *arg __maybe_unused, + struct machine *machine __maybe_unused, + struct thread *thread __maybe_unused, + struct perf_sample *data __maybe_unused, + int max_stack __maybe_unused) +{ + return 0; +} +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ +#endif /* __UNWIND_H */ diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index e16bf9a707e..4007aca8e0c 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -1,9 +1,13 @@ /* - * GIT - The information manager from hell + * usage.c + * + * Various reporting routines. + * Originally copied from GIT source. * * Copyright (C) Linus Torvalds, 2005 */ #include "util.h" +#include "debug.h" static void report(const char *prefix, const char *err, va_list params) { diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 214265674dd..95aefa78bb0 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,5 +1,40 @@ +#include "../perf.h" #include "util.h" +#include <api/fs/fs.h> #include <sys/mman.h> +#ifdef HAVE_BACKTRACE_SUPPORT +#include <execinfo.h> +#endif +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <limits.h> +#include <byteswap.h> +#include <linux/kernel.h> + +/* + * XXX We need to find a better place for these things... + */ +unsigned int page_size; +int cacheline_size; + +bool test_attr__enabled; + +bool perf_host = true; +bool perf_guest = false; + +char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events"; + +void event_attr_init(struct perf_event_attr *attr) +{ + if (!perf_host) + attr->exclude_host = 1; + if (!perf_guest) + attr->exclude_guest = 1; + /* to capture ABI version */ + attr->size = sizeof(*attr); +} int mkdir_p(char *path, mode_t mode) { @@ -27,17 +62,20 @@ 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; @@ -54,7 +92,7 @@ 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; @@ -65,13 +103,13 @@ 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; @@ -93,6 +131,11 @@ 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 = ' '; @@ -114,3 +157,386 @@ unsigned long convert_unit(unsigned long value, char *unit) return value; } + +static ssize_t ion(bool is_read, int fd, void *buf, size_t n) +{ + void *buf_start = buf; + size_t left = n; + + while (left) { + ssize_t ret = is_read ? read(fd, buf, left) : + write(fd, buf, left); + + if (ret < 0 && errno == EINTR) + continue; + if (ret <= 0) + return ret; + + left -= ret; + buf += ret; + } + + BUG_ON((size_t)(buf - buf_start) != n); + return n; +} + +/* + * Read exactly 'n' bytes or return an error. + */ +ssize_t readn(int fd, void *buf, size_t n) +{ + return ion(true, fd, buf, n); +} + +/* + * Write exactly 'n' bytes or return an error. + */ +ssize_t writen(int fd, void *buf, size_t n) +{ + return ion(false, fd, buf, n); +} + +size_t hex_width(u64 v) +{ + size_t n = 1; + + while ((v >>= 4)) + ++n; + + return n; +} + +static int hex(char ch) +{ + if ((ch >= '0') && (ch <= '9')) + return ch - '0'; + if ((ch >= 'a') && (ch <= 'f')) + return ch - 'a' + 10; + if ((ch >= 'A') && (ch <= 'F')) + return ch - 'A' + 10; + return -1; +} + +/* + * While we find nice hex chars, build a long_val. + * Return number of chars processed. + */ +int hex2u64(const char *ptr, u64 *long_val) +{ + const char *p = ptr; + *long_val = 0; + + while (*p) { + const int hex_val = hex(*p); + + if (hex_val < 0) + break; + + *long_val = (*long_val << 4) | hex_val; + p++; + } + + return p - ptr; +} + +/* Obtain a backtrace and print it to stdout. */ +#ifdef HAVE_BACKTRACE_SUPPORT +void dump_stack(void) +{ + void *array[16]; + size_t size = backtrace(array, ARRAY_SIZE(array)); + char **strings = backtrace_symbols(array, size); + size_t i; + + printf("Obtained %zd stack frames.\n", size); + + for (i = 0; i < size; i++) + printf("%s\n", strings[i]); + + free(strings); +} +#else +void dump_stack(void) {} +#endif + +void get_term_dimensions(struct winsize *ws) +{ + char *s = getenv("LINES"); + + if (s != NULL) { + ws->ws_row = atoi(s); + s = getenv("COLUMNS"); + if (s != NULL) { + ws->ws_col = atoi(s); + if (ws->ws_row && ws->ws_col) + return; + } + } +#ifdef TIOCGWINSZ + if (ioctl(1, TIOCGWINSZ, ws) == 0 && + ws->ws_row && ws->ws_col) + return; +#endif + ws->ws_row = 25; + ws->ws_col = 80; +} + +static void set_tracing_events_path(const char *mountpoint) +{ + snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s", + mountpoint, "tracing/events"); +} + +const char *perf_debugfs_mount(const char *mountpoint) +{ + const char *mnt; + + mnt = debugfs_mount(mountpoint); + if (!mnt) + return NULL; + + set_tracing_events_path(mnt); + + return mnt; +} + +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; +} + +int filename__read_str(const char *filename, char **buf, size_t *sizep) +{ + size_t size = 0, alloc_size = 0; + void *bf = NULL, *nbf; + int fd, n, err = 0; + + fd = open(filename, O_RDONLY); + if (fd < 0) + return -errno; + + do { + if (size == alloc_size) { + alloc_size += BUFSIZ; + nbf = realloc(bf, alloc_size); + if (!nbf) { + err = -ENOMEM; + break; + } + + bf = nbf; + } + + n = read(fd, bf + size, alloc_size - size); + if (n < 0) { + if (size) { + pr_warning("read failed %d: %s\n", + errno, strerror(errno)); + err = 0; + } else + err = -errno; + + break; + } + + size += n; + } while (n > 0); + + if (!err) { + *sizep = size; + *buf = bf; + } else + free(bf); + + close(fd); + return err; +} + +const char *get_filename_for_perf_kvm(void) +{ + const char *filename; + + if (perf_host && !perf_guest) + filename = strdup("perf.data.host"); + else if (!perf_host && perf_guest) + filename = strdup("perf.data.guest"); + else + filename = strdup("perf.data.kvm"); + + return filename; +} + +int perf_event_paranoid(void) +{ + char path[PATH_MAX]; + const char *procfs = procfs__mountpoint(); + int value; + + if (!procfs) + return INT_MAX; + + scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs); + + if (filename__read_int(path, &value)) + return INT_MAX; + + return value; +} + +void mem_bswap_32(void *src, int byte_size) +{ + u32 *m = src; + while (byte_size > 0) { + *m = bswap_32(*m); + byte_size -= sizeof(u32); + ++m; + } +} + +void mem_bswap_64(void *src, int byte_size) +{ + u64 *m = src; + + while (byte_size > 0) { + *m = bswap_64(*m); + byte_size -= sizeof(u64); + ++m; + } +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 7562707ddd1..66864364ccb 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -1,8 +1,6 @@ #ifndef GIT_COMPAT_UTIL_H #define GIT_COMPAT_UTIL_H -#define _FILE_OFFSET_BITS 64 - #ifndef FLEX_ARRAY /* * See if our compiler is known to support flexible array members. @@ -40,7 +38,6 @@ #define decimal_length(x) ((int)(sizeof(x) * 2.56 + 0.5) + 1) #define _ALL_SOURCE 1 -#define _GNU_SOURCE 1 #define _BSD_SOURCE 1 #define HAS_BOOL @@ -70,26 +67,23 @@ #include <sys/poll.h> #include <sys/socket.h> #include <sys/ioctl.h> -#ifndef NO_SYS_SELECT_H -#include <sys/select.h> -#endif -#include <netinet/in.h> -#include <netinet/tcp.h> -#include <arpa/inet.h> -#include <netdb.h> -#include <pwd.h> #include <inttypes.h> -#include "../../../include/linux/magic.h" -#include "types.h" +#include <linux/magic.h> +#include <linux/types.h> #include <sys/ttydefaults.h> - -#ifndef NO_ICONV -#include <iconv.h> -#endif +#include <api/fs/debugfs.h> +#include <termios.h> +#include <linux/bitops.h> extern const char *graph_line; extern const char *graph_dotted_line; 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). @@ -135,6 +129,8 @@ extern char buildid_dir[]; #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))); @@ -190,6 +186,8 @@ static inline void *zalloc(size_t size) return calloc(1, size); } +#define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) + static inline int has_extension(const char *filename, const char *ext) { size_t len = strlen(filename); @@ -206,9 +204,17 @@ static inline int has_extension(const char *filename, const char *ext) #undef isalpha #undef isprint #undef isalnum +#undef islower +#undef isupper #undef tolower #undef toupper +#ifndef NSEC_PER_MSEC +#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 @@ -226,6 +232,8 @@ extern unsigned char sane_ctype[256]; #define isalpha(x) sane_istest(x,GIT_ALPHA) #define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) #define isprint(x) sane_istest(x,GIT_PRINT) +#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20)) +#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20)) #define tolower(x) sane_case((unsigned char)(x), 0x20) #define toupper(x) sane_case((unsigned char)(x), 0) @@ -236,37 +244,90 @@ static inline int sane_case(int x, int high) return x; } -#ifndef DIR_HAS_BSD_GROUP_SEMANTICS -# define FORCE_DIR_SET_GID S_ISGID -#else -# define FORCE_DIR_SET_GID 0 -#endif - -#ifdef NO_NSEC -#undef USE_NSEC -#define ST_CTIME_NSEC(st) 0 -#define ST_MTIME_NSEC(st) 0 -#else -#ifdef USE_ST_TIMESPEC -#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctimespec.tv_nsec)) -#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtimespec.tv_nsec)) -#else -#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctim.tv_nsec)) -#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtim.tv_nsec)) -#endif -#endif - 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); void argv_free(char **argv); bool strglobmatch(const char *str, const char *pat); bool strlazymatch(const char *str, const char *pat); +int strtailcmp(const char *s1, const char *s2); +char *strxfrchar(char *s, char from, char to); unsigned long convert_unit(unsigned long value, char *unit); +ssize_t readn(int fd, void *buf, size_t n); +ssize_t writen(int fd, void *buf, size_t n); + +struct perf_event_attr; + +void event_attr_init(struct perf_event_attr *attr); #define _STR(x) #x #define STR(x) _STR(x) +/* + * Determine whether some value is a power of two, where zero is + * *not* considered a power of two. + */ + +static inline __attribute__((const)) +bool is_power_of_2(unsigned long n) +{ + return (n != 0 && ((n & (n - 1)) == 0)); +} + +static inline unsigned next_pow2(unsigned x) +{ + if (!x) + return 1; + return 1ULL << (32 - __builtin_clz(x - 1)); +} + +static inline unsigned long next_pow2_l(unsigned long x) +{ +#if BITS_PER_LONG == 64 + if (x <= (1UL << 31)) + return next_pow2(x); + return (unsigned long)next_pow2(x >> 32) << 32; +#else + return next_pow2(x); #endif +} + +size_t hex_width(u64 v); +int hex2u64(const char *ptr, u64 *val); + +char *ltrim(char *s); +char *rtrim(char *s); + +void dump_stack(void); + +extern unsigned int page_size; +extern int cacheline_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); +int filename__read_str(const char *filename, char **buf, size_t *sizep); +int perf_event_paranoid(void); + +void mem_bswap_64(void *src, int byte_size); +void mem_bswap_32(void *src, int byte_size); + +const char *get_filename_for_perf_kvm(void); +#endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index cfa55d686e3..0fb3c1fcd3e 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -31,13 +31,14 @@ void perf_read_values_destroy(struct perf_read_values *values) return; for (i = 0; i < values->threads; i++) - free(values->value[i]); - free(values->pid); - free(values->tid); - free(values->counterrawid); + zfree(&values->value[i]); + zfree(&values->value); + zfree(&values->pid); + zfree(&values->tid); + zfree(&values->counterrawid); for (i = 0; i < values->counters; i++) - free(values->countername[i]); - free(values->countername); + zfree(&values->countername[i]); + zfree(&values->countername); } static void perf_read_values__enlarge_threads(struct perf_read_values *values) @@ -150,7 +151,7 @@ static void perf_read_values__display_pretty(FILE *fp, if (width > tidwidth) tidwidth = width; for (j = 0; j < values->counters; j++) { - width = snprintf(NULL, 0, "%Lu", values->value[i][j]); + width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]); if (width > counterwidth[j]) counterwidth[j] = width; } @@ -165,7 +166,7 @@ static void perf_read_values__display_pretty(FILE *fp, fprintf(fp, " %*d %*d", pidwidth, values->pid[i], tidwidth, values->tid[i]); for (j = 0; j < values->counters; j++) - fprintf(fp, " %*Lu", + fprintf(fp, " %*" PRIu64, counterwidth[j], values->value[i][j]); fprintf(fp, "\n"); } @@ -196,13 +197,13 @@ static void perf_read_values__display_raw(FILE *fp, width = strlen(values->countername[j]); if (width > namewidth) namewidth = width; - width = snprintf(NULL, 0, "%llx", values->counterrawid[j]); + width = snprintf(NULL, 0, "%" PRIx64, values->counterrawid[j]); if (width > rawwidth) rawwidth = width; } for (i = 0; i < values->threads; i++) { for (j = 0; j < values->counters; j++) { - width = snprintf(NULL, 0, "%Lu", values->value[i][j]); + width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]); if (width > countwidth) countwidth = width; } @@ -214,7 +215,7 @@ static void perf_read_values__display_raw(FILE *fp, countwidth, "Count"); for (i = 0; i < values->threads; i++) for (j = 0; j < values->counters; j++) - fprintf(fp, " %*d %*d %*s %*llx %*Lu\n", + fprintf(fp, " %*d %*d %*s %*" PRIx64 " %*" PRIu64, pidwidth, values->pid[i], tidwidth, values->tid[i], namewidth, values->countername[j], diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h index 2fa967e1a88..b21a80c6cf8 100644 --- a/tools/perf/util/values.h +++ b/tools/perf/util/values.h @@ -1,7 +1,7 @@ #ifndef __PERF_VALUES_H #define __PERF_VALUES_H -#include "types.h" +#include <linux/types.h> struct perf_read_values { int threads; diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c new file mode 100644 index 00000000000..0ddb3b8a89e --- /dev/null +++ b/tools/perf/util/vdso.c @@ -0,0 +1,111 @@ + +#include <unistd.h> +#include <stdio.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <stdlib.h> +#include <linux/kernel.h> + +#include "vdso.h" +#include "util.h" +#include "symbol.h" +#include "linux/string.h" + +static bool vdso_found; +static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX"; + +static int find_vdso_map(void **start, void **end) +{ + FILE *maps; + char line[128]; + int found = 0; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) { + pr_err("vdso: cannot open maps\n"); + return -1; + } + + while (!found && fgets(line, sizeof(line), maps)) { + int m = -1; + + /* We care only about private r-x mappings. */ + if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n", + start, end, &m)) + continue; + if (m < 0) + continue; + + if (!strncmp(&line[m], VDSO__MAP_NAME, + sizeof(VDSO__MAP_NAME) - 1)) + found = 1; + } + + fclose(maps); + return !found; +} + +static char *get_file(void) +{ + char *vdso = NULL; + char *buf = NULL; + void *start, *end; + size_t size; + int fd; + + if (vdso_found) + return vdso_file; + + if (find_vdso_map(&start, &end)) + return NULL; + + size = end - start; + + buf = memdup(start, size); + if (!buf) + return NULL; + + fd = mkstemp(vdso_file); + if (fd < 0) + goto out; + + if (size == (size_t) write(fd, buf, size)) + vdso = vdso_file; + + close(fd); + + out: + free(buf); + + vdso_found = (vdso != NULL); + return vdso; +} + +void vdso__exit(void) +{ + if (vdso_found) + unlink(vdso_file); +} + +struct dso *vdso__dso_findnew(struct list_head *head) +{ + struct dso *dso = dsos__find(head, VDSO__MAP_NAME, true); + + if (!dso) { + char *file; + + file = get_file(); + if (!file) + return NULL; + + dso = dso__new(VDSO__MAP_NAME); + if (dso != NULL) { + dsos__add(head, dso); + dso__set_long_name(dso, file, false); + } + } + + return dso; +} diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h new file mode 100644 index 00000000000..0f76e7caf6f --- /dev/null +++ b/tools/perf/util/vdso.h @@ -0,0 +1,18 @@ +#ifndef __PERF_VDSO__ +#define __PERF_VDSO__ + +#include <linux/types.h> +#include <string.h> +#include <stdbool.h> + +#define VDSO__MAP_NAME "[vdso]" + +static inline bool is_vdso_map(const char *filename) +{ + return !strcmp(filename, VDSO__MAP_NAME); +} + +struct dso *vdso__dso_findnew(struct list_head *head); +void vdso__exit(void); + +#endif /* __PERF_VDSO__ */ diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c index 73e900edb5a..19f15b65070 100644 --- a/tools/perf/util/wrapper.c +++ b/tools/perf/util/wrapper.c @@ -7,7 +7,8 @@ * There's no pack memory to release - but stay close to the Git * version so wrap this away: */ -static inline void release_pack_memory(size_t size __used, int flag __used) +static inline void release_pack_memory(size_t size __maybe_unused, + int flag __maybe_unused) { } diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c new file mode 100644 index 00000000000..22afbf6c536 --- /dev/null +++ b/tools/perf/util/xyarray.c @@ -0,0 +1,20 @@ +#include "xyarray.h" +#include "util.h" + +struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size) +{ + size_t row_size = ylen * entry_size; + struct xyarray *xy = zalloc(sizeof(*xy) + xlen * row_size); + + if (xy != NULL) { + xy->entry_size = entry_size; + xy->row_size = row_size; + } + + return xy; +} + +void xyarray__delete(struct xyarray *xy) +{ + free(xy); +} diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h new file mode 100644 index 00000000000..c488a07275d --- /dev/null +++ b/tools/perf/util/xyarray.h @@ -0,0 +1,20 @@ +#ifndef _PERF_XYARRAY_H_ +#define _PERF_XYARRAY_H_ 1 + +#include <sys/types.h> + +struct xyarray { + size_t row_size; + size_t entry_size; + char contents[]; +}; + +struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size); +void xyarray__delete(struct xyarray *xy); + +static inline void *xyarray__entry(struct xyarray *xy, int x, int y) +{ + return &xy->contents[x * xy->row_size + y * xy->entry_size]; +} + +#endif /* _PERF_XYARRAY_H_ */ |