diff options
Diffstat (limited to 'tools/perf/util/header.c')
| -rw-r--r-- | tools/perf/util/header.c | 4367 |
1 files changed, 2907 insertions, 1460 deletions
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index a4dafbee2511..f5cad377c99e 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1,64 +1,66 @@ -#include "util.h" +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <inttypes.h> +#include "string2.h" +#include <sys/param.h> #include <sys/types.h> #include <byteswap.h> #include <unistd.h> +#include <regex.h> #include <stdio.h> #include <stdlib.h> +#include <linux/compiler.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/bitops.h> +#include <linux/string.h> +#include <linux/stringify.h> +#include <linux/zalloc.h> +#include <sys/stat.h> #include <sys/utsname.h> +#include <linux/time64.h> +#include <dirent.h> +#ifdef HAVE_LIBBPF_SUPPORT +#include <bpf/libbpf.h> +#endif +#include <perf/cpumap.h> +#include <tools/libc_compat.h> // reallocarray +#include "dso.h" #include "evlist.h" #include "evsel.h" +#include "util/evsel_fprintf.h" #include "header.h" -#include "../perf.h" +#include "memswap.h" #include "trace-event.h" #include "session.h" #include "symbol.h" #include "debug.h" #include "cpumap.h" #include "pmu.h" +#include "pmus.h" #include "vdso.h" #include "strbuf.h" #include "build-id.h" - -static bool no_buildid_cache = false; - -static int trace_event_count; -static struct perf_trace_event_type *trace_events; - -static u32 header_argc; -static const char **header_argv; - -int perf_header__push_event(u64 id, const char *name) -{ - struct perf_trace_event_type *nevents; - - if (strlen(name) > MAX_EVENT_NAME) - pr_warning("Event %s will be truncated\n", name); - - nevents = realloc(trace_events, (trace_event_count + 1) * sizeof(*trace_events)); - if (nevents == NULL) - return -ENOMEM; - trace_events = nevents; - - memset(&trace_events[trace_event_count], 0, sizeof(struct perf_trace_event_type)); - trace_events[trace_event_count].event_id = id; - strncpy(trace_events[trace_event_count].name, name, MAX_EVENT_NAME - 1); - trace_event_count++; - return 0; -} - -char *perf_header__find_event(u64 id) -{ - int i; - for (i = 0 ; i < trace_event_count; i++) { - if (trace_events[i].event_id == id) - return trace_events[i].name; - } - return NULL; -} +#include "data.h" +#include <api/fs/fs.h> +#include <api/io_dir.h> +#include "asm/bug.h" +#include "tool.h" +#include "time-utils.h" +#include "units.h" +#include "util/util.h" // perf_exe() +#include "cputopo.h" +#include "bpf-event.h" +#include "bpf-utils.h" +#include "clockid.h" + +#include <linux/ctype.h> +#include <internal/lib.h> + +#ifdef HAVE_LIBTRACEEVENT +#include <event-parse.h> +#endif /* * magic2 = "PERFILE2" @@ -75,6 +77,8 @@ static const u64 __perf_magic2_sw = 0x50455246494c4532ULL; #define PERF_MAGIC __perf_magic2 +const char perf_version_string[] = PERF_VERSION; + struct perf_file_attr { struct perf_event_attr attr; struct perf_file_section ids; @@ -82,12 +86,12 @@ struct perf_file_attr { void perf_header__set_feat(struct perf_header *header, int feat) { - set_bit(feat, header->adds_features); + __set_bit(feat, header->adds_features); } void perf_header__clear_feat(struct perf_header *header, int feat) { - clear_bit(feat, header->adds_features); + __clear_bit(feat, header->adds_features); } bool perf_header__has_feat(const struct perf_header *header, int feat) @@ -95,418 +99,248 @@ bool perf_header__has_feat(const struct perf_header *header, int feat) return test_bit(feat, header->adds_features); } -static int do_write(int fd, const void *buf, size_t size) +static int __do_write_fd(struct feat_fd *ff, const void *buf, size_t size) { - while (size) { - int ret = write(fd, buf, size); - - if (ret < 0) - return -errno; - - size -= ret; - buf += ret; - } + ssize_t ret = writen(ff->fd, buf, size); + if (ret != (ssize_t)size) + return ret < 0 ? (int)ret : -1; return 0; } -#define NAME_ALIGN 64 - -static int write_padded(int fd, const void *bf, size_t count, - size_t count_aligned) -{ - static const char zero_buf[NAME_ALIGN]; - int err = do_write(fd, bf, count); - - if (!err) - err = do_write(fd, zero_buf, count_aligned - count); - - return err; -} - -static int do_write_string(int fd, const char *str) -{ - u32 len, olen; - int ret; - - olen = strlen(str) + 1; - len = PERF_ALIGN(olen, NAME_ALIGN); - - /* write len, incl. \0 */ - ret = do_write(fd, &len, sizeof(len)); - if (ret < 0) - return ret; - - return write_padded(fd, str, olen, len); -} - -static char *do_read_string(int fd, struct perf_header *ph) +static int __do_write_buf(struct feat_fd *ff, const void *buf, size_t size) { - ssize_t sz, ret; - u32 len; - char *buf; - - sz = readn(fd, &len, sizeof(len)); - if (sz < (ssize_t)sizeof(len)) - return NULL; + /* struct perf_event_header::size is u16 */ + const size_t max_size = 0xffff - sizeof(struct perf_event_header); + size_t new_size = ff->size; + void *addr; - if (ph->needs_swap) - len = bswap_32(len); + if (size + ff->offset > max_size) + return -E2BIG; - buf = malloc(len); - if (!buf) - return NULL; + while (size > (new_size - ff->offset)) + new_size <<= 1; + new_size = min(max_size, new_size); - 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; + if (ff->size < new_size) { + addr = realloc(ff->buf, new_size); + if (!addr) + return -ENOMEM; + ff->buf = addr; + ff->size = new_size; } - free(buf); - return NULL; -} - -int -perf_header__set_cmdline(int argc, const char **argv) -{ - int i; - - /* - * 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; - - 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]; + memcpy(ff->buf + ff->offset, buf, size); + ff->offset += size; return 0; } -#define dsos__for_each_with_build_id(pos, head) \ - list_for_each_entry(pos, head, node) \ - if (!pos->has_build_id) \ - continue; \ - else - -static int write_buildid(char *name, size_t name_len, u8 *build_id, - pid_t pid, u16 misc, int fd) +/* Return: 0 if succeeded, -ERR if failed. */ +int do_write(struct feat_fd *ff, const void *buf, size_t size) { - 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); + if (!ff->buf) + return __do_write_fd(ff, buf, size); + return __do_write_buf(ff, buf, size); } -static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, - u16 misc, int fd) +/* Return: 0 if succeeded, -ERR if failed. */ +static int do_write_bitmap(struct feat_fd *ff, unsigned long *set, u64 size) { - struct dso *pos; - - dsos__for_each_with_build_id(pos, head) { - int err; - char *name; - size_t name_len; + u64 *p = (u64 *) set; + int i, ret; - if (!pos->hit) - continue; - - if (is_vdso_map(pos->short_name)) { - name = (char *) VDSO__MAP_NAME; - name_len = sizeof(VDSO__MAP_NAME) + 1; - } else { - name = pos->long_name; - name_len = pos->long_name_len + 1; - } + ret = do_write(ff, &size, sizeof(size)); + if (ret < 0) + return ret; - err = write_buildid(name, name_len, pos->build_id, - pid, misc, fd); - if (err) - return err; + for (i = 0; (u64) i < BITS_TO_U64(size); i++) { + ret = do_write(ff, p + i, sizeof(*p)); + if (ret < 0) + return ret; } return 0; } -static int machine__write_buildid_table(struct machine *machine, int fd) +/* Return: 0 if succeeded, -ERR if failed. */ +int write_padded(struct feat_fd *ff, const void *bf, + size_t count, size_t count_aligned) { - int err; - u16 kmisc = PERF_RECORD_MISC_KERNEL, - umisc = PERF_RECORD_MISC_USER; + static const char zero_buf[NAME_ALIGN]; + int err = do_write(ff, bf, count); - if (!machine__is_host(machine)) { - kmisc = PERF_RECORD_MISC_GUEST_KERNEL; - umisc = PERF_RECORD_MISC_GUEST_USER; - } + if (!err) + err = do_write(ff, zero_buf, count_aligned - count); - err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid, - kmisc, fd); - if (err == 0) - err = __dsos__write_buildid_table(&machine->user_dsos, - machine->pid, umisc, fd); return err; } -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->machines.host, fd); - - if (err) - return err; - - for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - err = machine__write_buildid_table(pos, fd); - if (err) - break; - } - return err; -} +#define string_size(str) \ + (PERF_ALIGN((strlen(str) + 1), NAME_ALIGN) + sizeof(u32)) -int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, - const char *name, bool is_kallsyms, bool is_vdso) +/* Return: 0 if succeeded, -ERR if failed. */ +static int do_write_string(struct feat_fd *ff, const char *str) { - const size_t size = PATH_MAX; - char *realname, *filename = zalloc(size), - *linkname = zalloc(size), *targetname; - int len, err = -1; - bool slash = is_kallsyms || is_vdso; - - 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 = 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, size - len, "/%s", sbuild_id); - - if (access(filename, F_OK)) { - if (is_kallsyms) { - if (copyfile("/proc/kallsyms", filename)) - goto out_free; - } else if (link(realname, filename) && copyfile(name, filename)) - goto out_free; - } - - len = scnprintf(linkname, size, "%s/.build-id/%.2s", - debugdir, sbuild_id); + u32 len, olen; + int ret; - if (access(linkname, X_OK) && mkdir_p(linkname, 0755)) - goto out_free; + olen = strlen(str) + 1; + len = PERF_ALIGN(olen, NAME_ALIGN); - snprintf(linkname + len, size - len, "/%s", sbuild_id + 2); - targetname = filename + strlen(debugdir) - 5; - memcpy(targetname, "../..", 5); + /* write len, incl. \0 */ + ret = do_write(ff, &len, sizeof(len)); + if (ret < 0) + return ret; - if (symlink(targetname, linkname) == 0) - err = 0; -out_free: - if (!is_kallsyms) - free(realname); - free(filename); - free(linkname); - return err; + return write_padded(ff, str, olen, len); } -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_vdso) +static int __do_read_fd(struct feat_fd *ff, void *addr, ssize_t size) { - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + ssize_t ret = readn(ff->fd, addr, size); - build_id__sprintf(build_id, build_id_size, sbuild_id); - - return build_id_cache__add_s(sbuild_id, debugdir, name, - is_kallsyms, is_vdso); + if (ret != size) + return ret < 0 ? (int)ret : -1; + return 0; } -int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) +static int __do_read_buf(struct feat_fd *ff, void *addr, ssize_t size) { - const size_t size = PATH_MAX; - char *filename = zalloc(size), - *linkname = zalloc(size); - int err = -1; - - if (filename == NULL || linkname == NULL) - goto out_free; - - snprintf(linkname, size, "%s/.build-id/%.2s/%s", - debugdir, sbuild_id, sbuild_id + 2); - - if (access(linkname, F_OK)) - goto out_free; - - if (readlink(linkname, filename, size - 1) < 0) - goto out_free; - - if (unlink(linkname)) - goto out_free; + if (size > (ssize_t)ff->size - ff->offset) + return -1; - /* - * Since the link is relative, we must make it absolute: - */ - snprintf(linkname, size, "%s/.build-id/%.2s/%s", - debugdir, sbuild_id, filename); + memcpy(addr, ff->buf + ff->offset, size); + ff->offset += size; - if (unlink(linkname)) - goto out_free; + return 0; - err = 0; -out_free: - free(filename); - free(linkname); - return err; } -static int dso__cache_build_id(struct dso *dso, const char *debugdir) +static int __do_read(struct feat_fd *ff, void *addr, ssize_t size) { - bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; - bool is_vdso = is_vdso_map(dso->short_name); - - return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), - dso->long_name, debugdir, - is_kallsyms, is_vdso); + if (!ff->buf) + return __do_read_fd(ff, addr, size); + return __do_read_buf(ff, addr, size); } -static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) +static int do_read_u32(struct feat_fd *ff, u32 *addr) { - struct dso *pos; - int err = 0; + int ret; - dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, debugdir)) - err = -1; + ret = __do_read(ff, addr, sizeof(*addr)); + if (ret) + return ret; - return err; + if (ff->ph->needs_swap) + *addr = bswap_32(*addr); + return 0; } -static int machine__cache_build_ids(struct machine *machine, const char *debugdir) +static int do_read_u64(struct feat_fd *ff, u64 *addr) { - int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir); - return ret; + int ret; + + ret = __do_read(ff, addr, sizeof(*addr)); + if (ret) + return ret; + + if (ff->ph->needs_swap) + *addr = bswap_64(*addr); + return 0; } -static int perf_session__cache_build_ids(struct perf_session *session) +static char *do_read_string(struct feat_fd *ff) { - struct rb_node *nd; - int ret; - char debugdir[PATH_MAX]; - - snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); + u32 len; + char *buf; - if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) - return -1; + if (do_read_u32(ff, &len)) + return NULL; - ret = machine__cache_build_ids(&session->machines.host, debugdir); + buf = malloc(len); + if (!buf) + return NULL; - 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); + if (!__do_read(ff, buf, len)) { + /* + * strings are padded by zeroes + * thus the actual strlen of buf + * may be less than len + */ + return buf; } - return ret ? -1 : 0; -} -static bool machine__read_build_ids(struct machine *machine, bool with_hits) -{ - bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits); - ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits); - return ret; + free(buf); + return NULL; } -static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits) +/* Return: 0 if succeeded, -ERR if failed. */ +static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize) { - struct rb_node *nd; - bool ret = machine__read_build_ids(&session->machines.host, with_hits); + unsigned long *set; + u64 size, *p; + int i, ret; + + ret = do_read_u64(ff, &size); + if (ret) + return ret; + + set = bitmap_zalloc(size); + if (!set) + return -ENOMEM; - 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); + p = (u64 *) set; + + for (i = 0; (u64) i < BITS_TO_U64(size); i++) { + ret = do_read_u64(ff, p + i); + if (ret < 0) { + free(set); + return ret; + } } - return ret; + *pset = set; + *psize = size; + return 0; } -static int write_tracing_data(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist) +#ifdef HAVE_LIBTRACEEVENT +static int write_tracing_data(struct feat_fd *ff, + struct evlist *evlist) { - return read_tracing_data(fd, &evlist->entries); -} + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + return read_tracing_data(ff->fd, &evlist->core.entries); +} +#endif -static int write_build_id(int fd, struct perf_header *h, - struct perf_evlist *evlist __maybe_unused) +static int write_build_id(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) { struct perf_session *session; int err; - session = container_of(h, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); if (!perf_session__read_build_ids(session, true)) return -1; - err = dsos__write_buildid_table(h, fd); + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + + err = perf_session__write_buildid_table(session, ff); if (err < 0) { pr_debug("failed to write buildid table\n"); return err; } - if (!no_buildid_cache) - perf_session__cache_build_ids(session); return 0; } -static int write_hostname(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_hostname(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -515,11 +349,11 @@ static int write_hostname(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return -1; - return do_write_string(fd, uts.nodename); + return do_write_string(ff, uts.nodename); } -static int write_osrelease(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_osrelease(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -528,11 +362,11 @@ static int write_osrelease(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return -1; - return do_write_string(fd, uts.release); + return do_write_string(ff, uts.release); } -static int write_arch(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_arch(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -541,25 +375,21 @@ static int write_arch(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return -1; - return do_write_string(fd, uts.machine); + return do_write_string(ff, uts.machine); } -static int write_version(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_version(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) { - return do_write_string(fd, perf_version_string); + return do_write_string(ff, perf_version_string); } -static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int __write_cpudesc(struct feat_fd *ff, const char *cpuinfo_proc) { -#ifndef CPUINFO_PROC -#define CPUINFO_PROC NULL -#endif FILE *file; char *buf = NULL; char *s, *p; - const char *search = CPUINFO_PROC; + const char *search = cpuinfo_proc; size_t len = 0; int ret = -1; @@ -576,8 +406,10 @@ static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, break; } - if (ret) + if (ret) { + ret = -1; goto done; + } s = buf; @@ -593,34 +425,64 @@ static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, while (*p) { if (isspace(*p)) { char *r = p + 1; - char *q = r; + char *q = skip_spaces(r); *p = ' '; - while (*q && isspace(*q)) - q++; if (q != (p+1)) while ((*r++ = *q++)); } p++; } - ret = do_write_string(fd, s); + ret = do_write_string(ff, s); done: free(buf); fclose(file); return ret; } -static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_cpudesc(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ +#if defined(__powerpc__) || defined(__hppa__) || defined(__sparc__) +#define CPUINFO_PROC { "cpu", } +#elif defined(__s390__) +#define CPUINFO_PROC { "vendor_id", } +#elif defined(__sh__) +#define CPUINFO_PROC { "cpu type", } +#elif defined(__alpha__) || defined(__mips__) +#define CPUINFO_PROC { "cpu model", } +#elif defined(__arm__) +#define CPUINFO_PROC { "model name", "Processor", } +#elif defined(__arc__) +#define CPUINFO_PROC { "Processor", } +#elif defined(__xtensa__) +#define CPUINFO_PROC { "core ID", } +#elif defined(__loongarch__) +#define CPUINFO_PROC { "Model Name", } +#else +#define CPUINFO_PROC { "model name", } +#endif + const char *cpuinfo_procs[] = CPUINFO_PROC; +#undef CPUINFO_PROC + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) { + int ret; + ret = __write_cpudesc(ff, cpuinfo_procs[i]); + if (ret >= 0) + return ret; + } + return -1; +} + + +static int write_nrcpus(struct feat_fd *ff, + struct 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); + nrc = cpu__max_present_cpu().cpu; nr = sysconf(_SC_NPROCESSORS_ONLN); if (nr < 0) @@ -628,40 +490,39 @@ static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, nra = (u32)(nr & UINT_MAX); - ret = do_write(fd, &nrc, sizeof(nrc)); + ret = do_write(ff, &nrc, sizeof(nrc)); if (ret < 0) return ret; - return do_write(fd, &nra, sizeof(nra)); + return do_write(ff, &nra, sizeof(nra)); } -static int write_event_desc(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist) +static int write_event_desc(struct feat_fd *ff, + struct evlist *evlist) { - struct perf_evsel *evsel; + struct evsel *evsel; u32 nre, nri, sz; int ret; - nre = evlist->nr_entries; + nre = evlist->core.nr_entries; /* * write number of events */ - ret = do_write(fd, &nre, sizeof(nre)); + ret = do_write(ff, &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)); + sz = (u32)sizeof(evsel->core.attr); + ret = do_write(ff, &sz, sizeof(sz)); if (ret < 0) return ret; - list_for_each_entry(evsel, &evlist->entries, node) { - - ret = do_write(fd, &evsel->attr, sz); + evlist__for_each_entry(evlist, evsel) { + ret = do_write(ff, &evsel->core.attr, sz); if (ret < 0) return ret; /* @@ -671,234 +532,132 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused, * copy into an nri to be independent of the * type of ids, */ - nri = evsel->ids; - ret = do_write(fd, &nri, sizeof(nri)); + nri = evsel->core.ids; + ret = do_write(ff, &nri, sizeof(nri)); if (ret < 0) return ret; /* * write event string as passed on cmdline */ - ret = do_write_string(fd, perf_evsel__name(evsel)); + ret = do_write_string(ff, evsel__name(evsel)); if (ret < 0) return ret; /* * write unique ids for this event */ - ret = do_write(fd, evsel->id, evsel->ids * sizeof(u64)); + ret = do_write(ff, evsel->core.id, evsel->core.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) +static int write_cmdline(struct feat_fd *ff, + struct 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; + struct perf_env *env = &ff->ph->env; + char pbuf[MAXPATHLEN], *buf; + int i, ret, n; - /* readlink() does not add null termination */ - buf[ret] = '\0'; + /* actual path to perf binary */ + buf = perf_exe(pbuf, MAXPATHLEN); /* account for binary path */ - n = header_argc + 1; + n = env->nr_cmdline + 1; - ret = do_write(fd, &n, sizeof(n)); + ret = do_write(ff, &n, sizeof(n)); if (ret < 0) return ret; - ret = do_write_string(fd, buf); + ret = do_write_string(ff, buf); if (ret < 0) return ret; - for (i = 0 ; i < header_argc; i++) { - ret = do_write_string(fd, header_argv[i]); + for (i = 0 ; i < env->nr_cmdline; i++) { + ret = do_write_string(ff, env->cmdline_argv[i]); if (ret < 0) return ret; } return 0; } -#define CORE_SIB_FMT \ - "/sys/devices/system/cpu/cpu%d/topology/core_siblings_list" -#define THRD_SIB_FMT \ - "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list" -struct cpu_topo { - u32 core_sib; - u32 thread_sib; - char **core_siblings; - char **thread_siblings; -}; - -static int build_cpu_topo(struct cpu_topo *tp, int cpu) +static int write_cpu_topology(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) { - FILE *fp; - char filename[MAXPATHLEN]; - char *buf = NULL, *p; - size_t len = 0; - u32 i = 0; - int ret = -1; + struct perf_env *env = &ff->ph->env; + struct cpu_topology *tp; + u32 i; + int ret, j; - sprintf(filename, CORE_SIB_FMT, cpu); - fp = fopen(filename, "r"); - if (!fp) + tp = cpu_topology__new(); + if (!tp) return -1; - if (getline(&buf, &len, fp) <= 0) + ret = do_write(ff, &tp->package_cpus_lists, sizeof(tp->package_cpus_lists)); + if (ret < 0) goto done; - fclose(fp); - - p = strchr(buf, '\n'); - if (p) - *p = '\0'; - - for (i = 0; i < tp->core_sib; i++) { - if (!strcmp(buf, tp->core_siblings[i])) - break; - } - if (i == tp->core_sib) { - tp->core_siblings[i] = buf; - tp->core_sib++; - buf = NULL; - len = 0; + for (i = 0; i < tp->package_cpus_lists; i++) { + ret = do_write_string(ff, tp->package_cpus_list[i]); + if (ret < 0) + goto done; } - - sprintf(filename, THRD_SIB_FMT, cpu); - fp = fopen(filename, "r"); - if (!fp) - goto done; - - if (getline(&buf, &len, fp) <= 0) + ret = do_write(ff, &tp->core_cpus_lists, sizeof(tp->core_cpus_lists)); + if (ret < 0) goto done; - p = strchr(buf, '\n'); - if (p) - *p = '\0'; - - for (i = 0; i < tp->thread_sib; i++) { - if (!strcmp(buf, tp->thread_siblings[i])) + for (i = 0; i < tp->core_cpus_lists; i++) { + ret = do_write_string(ff, tp->core_cpus_list[i]); + if (ret < 0) break; } - if (i == tp->thread_sib) { - tp->thread_siblings[i] = buf; - tp->thread_sib++; - buf = NULL; - } - ret = 0; -done: - if(fp) - fclose(fp); - free(buf); - return ret; -} -static void free_cpu_topo(struct cpu_topo *tp) -{ - u32 i; - - if (!tp) - return; - - for (i = 0 ; i < tp->core_sib; i++) - free(tp->core_siblings[i]); - - for (i = 0 ; i < tp->thread_sib; i++) - free(tp->thread_siblings[i]); - - free(tp); -} - -static struct cpu_topo *build_cpu_topology(void) -{ - struct cpu_topo *tp; - void *addr; - u32 nr, i; - size_t sz; - long ncpus; - int ret = -1; - - ncpus = sysconf(_SC_NPROCESSORS_CONF); - if (ncpus < 0) - return NULL; - - nr = (u32)(ncpus & UINT_MAX); - - sz = nr * sizeof(char *); - - addr = calloc(1, sizeof(*tp) + 2 * sz); - if (!addr) - return NULL; - - tp = addr; - - addr += sizeof(*tp); - tp->core_siblings = addr; - addr += sz; - tp->thread_siblings = addr; + ret = perf_env__read_cpu_topology_map(env); + if (ret < 0) + goto done; - for (i = 0; i < nr; i++) { - ret = build_cpu_topo(tp, i); + for (j = 0; j < env->nr_cpus_avail; j++) { + ret = do_write(ff, &env->cpu[j].core_id, + sizeof(env->cpu[j].core_id)); if (ret < 0) - break; - } - if (ret) { - free_cpu_topo(tp); - tp = NULL; + return ret; + ret = do_write(ff, &env->cpu[j].socket_id, + sizeof(env->cpu[j].socket_id)); + if (ret < 0) + return ret; } - return tp; -} - -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; + if (!tp->die_cpus_lists) + goto done; - ret = do_write(fd, &tp->core_sib, sizeof(tp->core_sib)); + ret = do_write(ff, &tp->die_cpus_lists, sizeof(tp->die_cpus_lists)); if (ret < 0) goto done; - for (i = 0; i < tp->core_sib; i++) { - ret = do_write_string(fd, tp->core_siblings[i]); + for (i = 0; i < tp->die_cpus_lists; i++) { + ret = do_write_string(ff, tp->die_cpus_list[i]); if (ret < 0) goto done; } - ret = do_write(fd, &tp->thread_sib, sizeof(tp->thread_sib)); - if (ret < 0) - goto done; - for (i = 0; i < tp->thread_sib; i++) { - ret = do_write_string(fd, tp->thread_siblings[i]); + for (j = 0; j < env->nr_cpus_avail; j++) { + ret = do_write(ff, &env->cpu[j].die_id, + sizeof(env->cpu[j].die_id)); if (ret < 0) - break; + return ret; } + done: - free_cpu_topo(tp); + cpu_topology__delete(tp); return ret; } -static int write_total_mem(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_total_mem(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) { char *buf = NULL; FILE *fp; @@ -918,119 +677,53 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused, if (!ret) { n = sscanf(buf, "%*s %"PRIu64, &mem); if (n == 1) - ret = do_write(fd, &mem, sizeof(mem)); - } + ret = do_write(ff, &mem, sizeof(mem)); + } else + ret = -1; free(buf); fclose(fp); return ret; } -static int write_topo_node(int fd, int node) +static int write_numa_topology(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) { - char str[MAXPATHLEN]; - char field[32]; - char *buf = NULL, *p; - size_t len = 0; - FILE *fp; - u64 mem_total, mem_free, mem; - int ret = -1; - - sprintf(str, "/sys/devices/system/node/node%d/meminfo", node); - fp = fopen(str, "r"); - if (!fp) - return -1; - - while (getline(&buf, &len, fp) > 0) { - /* skip over invalid lines */ - if (!strchr(buf, ':')) - continue; - if (sscanf(buf, "%*s %*d %s %"PRIu64, field, &mem) != 2) - goto done; - if (!strcmp(field, "MemTotal:")) - mem_total = mem; - if (!strcmp(field, "MemFree:")) - mem_free = mem; - } - - fclose(fp); - 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; + struct numa_topology *tp; int ret = -1; + u32 i; - fp = fopen("/sys/devices/system/node/online", "r"); - if (!fp) - return -1; + tp = numa_topology__new(); + if (!tp) + return -ENOMEM; - if (getline(&buf, &len, fp) <= 0) - goto done; + ret = do_write(ff, &tp->nr, sizeof(u32)); + if (ret < 0) + goto err; - c = strchr(buf, '\n'); - if (c) - *c = '\0'; + for (i = 0; i < tp->nr; i++) { + struct numa_topology_node *n = &tp->nodes[i]; - node_map = cpu_map__new(buf); - if (!node_map) - goto done; + ret = do_write(ff, &n->node, sizeof(u32)); + if (ret < 0) + goto err; - nr = (u32)node_map->nr; + ret = do_write(ff, &n->mem_total, sizeof(u64)); + if (ret) + goto err; - ret = do_write(fd, &nr, sizeof(nr)); - if (ret < 0) - goto done; + ret = do_write(ff, &n->mem_free, sizeof(u64)); + if (ret) + goto err; - 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); + ret = do_write_string(ff, n->cpus); if (ret < 0) - break; + goto err; } -done: - free(buf); - fclose(fp); - free(node_map); + + ret = 0; + +err: + numa_topology__delete(tp); return ret; } @@ -1046,39 +739,34 @@ done: * }; */ -static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_pmu_mappings(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) { struct perf_pmu *pmu = NULL; - off_t offset = lseek(fd, 0, SEEK_CUR); - __u32 pmu_num = 0; + u32 pmu_num = 0; int ret; - /* write real pmu_num later */ - ret = do_write(fd, &pmu_num, sizeof(pmu_num)); + /* + * Do a first pass to count number of pmu to avoid lseek so this + * works in pipe mode as well. + */ + while ((pmu = perf_pmus__scan(pmu))) + pmu_num++; + + ret = do_write(ff, &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)); + while ((pmu = perf_pmus__scan(pmu))) { + ret = do_write(ff, &pmu->type, sizeof(pmu->type)); if (ret < 0) return ret; - ret = do_write_string(fd, pmu->name); + ret = do_write_string(ff, 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; - } - return 0; } @@ -1094,33 +782,32 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, * }[nr_groups]; * }; */ -static int write_group_desc(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist) +static int write_group_desc(struct feat_fd *ff, + struct evlist *evlist) { - u32 nr_groups = evlist->nr_groups; - struct perf_evsel *evsel; + u32 nr_groups = evlist__nr_groups(evlist); + struct evsel *evsel; int ret; - ret = do_write(fd, &nr_groups, sizeof(nr_groups)); + ret = do_write(ff, &nr_groups, sizeof(nr_groups)); if (ret < 0) return ret; - list_for_each_entry(evsel, &evlist->entries, node) { - if (perf_evsel__is_group_leader(evsel) && - evsel->nr_members > 1) { + evlist__for_each_entry(evlist, evsel) { + if (evsel__is_group_leader(evsel) && evsel->core.nr_members > 1) { const char *name = evsel->group_name ?: "{anon_group}"; - u32 leader_idx = evsel->idx; - u32 nr_members = evsel->nr_members; + u32 leader_idx = evsel->core.idx; + u32 nr_members = evsel->core.nr_members; - ret = do_write_string(fd, name); + ret = do_write_string(ff, name); if (ret < 0) return ret; - ret = do_write(fd, &leader_idx, sizeof(leader_idx)); + ret = do_write(ff, &leader_idx, sizeof(leader_idx)); if (ret < 0) return ret; - ret = do_write(fd, &nr_members, sizeof(nr_members)); + ret = do_write(ff, &nr_members, sizeof(nr_members)); if (ret < 0) return ret; } @@ -1129,94 +816,868 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused, } /* + * Return the CPU id as a raw string. + * + * Each architecture should provide a more precise id string that + * can be use to match the architecture's "mapfile". + */ +char * __weak get_cpuid_str(struct perf_cpu cpu __maybe_unused) +{ + return NULL; +} + +char *get_cpuid_allow_env_override(struct perf_cpu cpu) +{ + char *cpuid; + static bool printed; + + cpuid = getenv("PERF_CPUID"); + if (cpuid) + cpuid = strdup(cpuid); + if (!cpuid) + cpuid = get_cpuid_str(cpu); + if (!cpuid) + return NULL; + + if (!printed) { + pr_debug("Using CPUID %s\n", cpuid); + printed = true; + } + return cpuid; +} + +/* Return zero when the cpuid from the mapfile.csv matches the + * cpuid string generated on this platform. + * Otherwise return non-zero. + */ +int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) +{ + regex_t re; + regmatch_t pmatch[1]; + int match; + + if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) { + /* Warn unable to generate match particular string. */ + pr_info("Invalid regular expression %s\n", mapcpuid); + return 1; + } + + match = !regexec(&re, cpuid, 1, pmatch, 0); + regfree(&re); + if (match) { + size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so); + + /* Verify the entire string matched. */ + if (match_len == strlen(cpuid)) + return 0; + } + return 1; +} + +/* * default get_cpuid(): nothing gets recorded - * actual implementation must be in arch/$(ARCH)/util/header.c + * actual implementation must be in arch/$(SRCARCH)/util/header.c */ -int __attribute__ ((weak)) get_cpuid(char *buffer __maybe_unused, - size_t sz __maybe_unused) +int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused, + struct perf_cpu cpu __maybe_unused) { - return -1; + return ENOSYS; /* Not implemented */ } -static int write_cpuid(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_cpuid(struct feat_fd *ff, struct evlist *evlist) { + struct perf_cpu cpu = perf_cpu_map__min(evlist->core.all_cpus); char buffer[64]; int ret; - ret = get_cpuid(buffer, sizeof(buffer)); - if (!ret) - goto write_it; + ret = get_cpuid(buffer, sizeof(buffer), cpu); + if (ret) + return -1; - return -1; -write_it: - return do_write_string(fd, buffer); + return do_write_string(ff, buffer); } -static int write_branch_stack(int fd __maybe_unused, - struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_branch_stack(struct feat_fd *ff __maybe_unused, + struct evlist *evlist __maybe_unused) { return 0; } -static void print_hostname(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static int write_auxtrace(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct perf_session *session; + int err; + + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + + session = container_of(ff->ph, struct perf_session, header); + + err = auxtrace_index__write(ff->fd, &session->auxtrace_index); + if (err < 0) + pr_err("Failed to write auxtrace index\n"); + return err; +} + +static int write_clockid(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + return do_write(ff, &ff->ph->env.clock.clockid_res_ns, + sizeof(ff->ph->env.clock.clockid_res_ns)); +} + +static int write_clock_data(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + u64 *data64; + u32 data32; + int ret; + + /* version */ + data32 = 1; + + ret = do_write(ff, &data32, sizeof(data32)); + if (ret < 0) + return ret; + + /* clockid */ + data32 = ff->ph->env.clock.clockid; + + ret = do_write(ff, &data32, sizeof(data32)); + if (ret < 0) + return ret; + + /* TOD ref time */ + data64 = &ff->ph->env.clock.tod_ns; + + ret = do_write(ff, data64, sizeof(*data64)); + if (ret < 0) + return ret; + + /* clockid ref time */ + data64 = &ff->ph->env.clock.clockid_ns; + + return do_write(ff, data64, sizeof(*data64)); +} + +static int write_hybrid_topology(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct hybrid_topology *tp; + int ret; + u32 i; + + tp = hybrid_topology__new(); + if (!tp) + return -ENOENT; + + ret = do_write(ff, &tp->nr, sizeof(u32)); + if (ret < 0) + goto err; + + for (i = 0; i < tp->nr; i++) { + struct hybrid_topology_node *n = &tp->nodes[i]; + + ret = do_write_string(ff, n->pmu_name); + if (ret < 0) + goto err; + + ret = do_write_string(ff, n->cpus); + if (ret < 0) + goto err; + } + + ret = 0; + +err: + hybrid_topology__delete(tp); + return ret; +} + +static int write_dir_format(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct perf_session *session; + struct perf_data *data; + + session = container_of(ff->ph, struct perf_session, header); + data = session->data; + + if (WARN_ON(!perf_data__is_dir(data))) + return -1; + + return do_write(ff, &data->dir.version, sizeof(data->dir.version)); +} + +#ifdef HAVE_LIBBPF_SUPPORT +static int write_bpf_prog_info(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct rb_root *root; + struct rb_node *next; + int ret = 0; + + down_read(&env->bpf_progs.lock); + + ret = do_write(ff, &env->bpf_progs.infos_cnt, + sizeof(env->bpf_progs.infos_cnt)); + if (ret < 0 || env->bpf_progs.infos_cnt == 0) + goto out; + + root = &env->bpf_progs.infos; + next = rb_first(root); + while (next) { + struct bpf_prog_info_node *node; + size_t len; + + node = rb_entry(next, struct bpf_prog_info_node, rb_node); + next = rb_next(&node->rb_node); + len = sizeof(struct perf_bpil) + + node->info_linear->data_len; + + /* before writing to file, translate address to offset */ + bpil_addr_to_offs(node->info_linear); + ret = do_write(ff, node->info_linear, len); + /* + * translate back to address even when do_write() fails, + * so that this function never changes the data. + */ + bpil_offs_to_addr(node->info_linear); + if (ret < 0) + goto out; + } +out: + up_read(&env->bpf_progs.lock); + return ret; +} + +static int write_bpf_btf(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) { - fprintf(fp, "# hostname : %s\n", ph->env.hostname); + struct perf_env *env = &ff->ph->env; + struct rb_root *root; + struct rb_node *next; + int ret = 0; + + down_read(&env->bpf_progs.lock); + + ret = do_write(ff, &env->bpf_progs.btfs_cnt, + sizeof(env->bpf_progs.btfs_cnt)); + + if (ret < 0 || env->bpf_progs.btfs_cnt == 0) + goto out; + + root = &env->bpf_progs.btfs; + next = rb_first(root); + while (next) { + struct btf_node *node; + + node = rb_entry(next, struct btf_node, rb_node); + next = rb_next(&node->rb_node); + ret = do_write(ff, &node->id, + sizeof(u32) * 2 + node->data_size); + if (ret < 0) + goto out; + } +out: + up_read(&env->bpf_progs.lock); + return ret; } +#endif // HAVE_LIBBPF_SUPPORT -static void print_osrelease(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static int cpu_cache_level__sort(const void *a, const void *b) { - fprintf(fp, "# os release : %s\n", ph->env.os_release); + struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a; + struct cpu_cache_level *cache_b = (struct cpu_cache_level *)b; + + return cache_a->level - cache_b->level; } -static void print_arch(struct perf_header *ph, int fd __maybe_unused, FILE *fp) +static bool cpu_cache_level__cmp(struct cpu_cache_level *a, struct cpu_cache_level *b) { - fprintf(fp, "# arch : %s\n", ph->env.arch); + if (a->level != b->level) + return false; + + if (a->line_size != b->line_size) + return false; + + if (a->sets != b->sets) + return false; + + if (a->ways != b->ways) + return false; + + if (strcmp(a->type, b->type)) + return false; + + if (strcmp(a->size, b->size)) + return false; + + if (strcmp(a->map, b->map)) + return false; + + return true; } -static void print_cpudesc(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 level) { - fprintf(fp, "# cpudesc : %s\n", ph->env.cpu_desc); + char path[PATH_MAX], file[PATH_MAX]; + struct stat st; + size_t len; + + scnprintf(path, PATH_MAX, "devices/system/cpu/cpu%d/cache/index%d/", cpu, level); + scnprintf(file, PATH_MAX, "%s/%s", sysfs__mountpoint(), path); + + if (stat(file, &st)) + return 1; + + scnprintf(file, PATH_MAX, "%s/level", path); + if (sysfs__read_int(file, (int *) &cache->level)) + return -1; + + scnprintf(file, PATH_MAX, "%s/coherency_line_size", path); + if (sysfs__read_int(file, (int *) &cache->line_size)) + return -1; + + scnprintf(file, PATH_MAX, "%s/number_of_sets", path); + if (sysfs__read_int(file, (int *) &cache->sets)) + return -1; + + scnprintf(file, PATH_MAX, "%s/ways_of_associativity", path); + if (sysfs__read_int(file, (int *) &cache->ways)) + return -1; + + scnprintf(file, PATH_MAX, "%s/type", path); + if (sysfs__read_str(file, &cache->type, &len)) + return -1; + + cache->type[len] = 0; + cache->type = strim(cache->type); + + scnprintf(file, PATH_MAX, "%s/size", path); + if (sysfs__read_str(file, &cache->size, &len)) { + zfree(&cache->type); + return -1; + } + + cache->size[len] = 0; + cache->size = strim(cache->size); + + scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path); + if (sysfs__read_str(file, &cache->map, &len)) { + zfree(&cache->size); + zfree(&cache->type); + return -1; + } + + cache->map[len] = 0; + cache->map = strim(cache->map); + return 0; } -static void print_nrcpus(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c) { - fprintf(fp, "# nrcpus online : %u\n", ph->env.nr_cpus_online); - fprintf(fp, "# nrcpus avail : %u\n", ph->env.nr_cpus_avail); + fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map); } -static void print_version(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +/* + * Build caches levels for a particular CPU from the data in + * /sys/devices/system/cpu/cpu<cpu>/cache/ + * The cache level data is stored in caches[] from index at + * *cntp. + */ +int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp) +{ + u16 level; + + for (level = 0; level < MAX_CACHE_LVL; level++) { + struct cpu_cache_level c; + int err; + u32 i; + + err = cpu_cache_level__read(&c, cpu, level); + if (err < 0) + return err; + + if (err == 1) + break; + + for (i = 0; i < *cntp; i++) { + if (cpu_cache_level__cmp(&c, &caches[i])) + break; + } + + if (i == *cntp) { + caches[*cntp] = c; + *cntp = *cntp + 1; + } else + cpu_cache_level__free(&c); + } + + return 0; +} + +static int build_caches(struct cpu_cache_level caches[], u32 *cntp) { - fprintf(fp, "# perf version : %s\n", ph->env.version); + u32 nr, cpu, cnt = 0; + + nr = cpu__max_cpu().cpu; + + for (cpu = 0; cpu < nr; cpu++) { + int ret = build_caches_for_cpu(cpu, caches, &cnt); + + if (ret) + return ret; + } + *cntp = cnt; + return 0; } -static void print_cmdline(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static int write_cache(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + u32 max_caches = cpu__max_cpu().cpu * MAX_CACHE_LVL; + struct cpu_cache_level caches[max_caches]; + u32 cnt = 0, i, version = 1; + int ret; + + ret = build_caches(caches, &cnt); + if (ret) + goto out; + + qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort); + + ret = do_write(ff, &version, sizeof(u32)); + if (ret < 0) + goto out; + + ret = do_write(ff, &cnt, sizeof(u32)); + if (ret < 0) + goto out; + + for (i = 0; i < cnt; i++) { + struct cpu_cache_level *c = &caches[i]; + + #define _W(v) \ + ret = do_write(ff, &c->v, sizeof(u32)); \ + if (ret < 0) \ + goto out; + + _W(level) + _W(line_size) + _W(sets) + _W(ways) + #undef _W + + #define _W(v) \ + ret = do_write_string(ff, (const char *) c->v); \ + if (ret < 0) \ + goto out; + + _W(type) + _W(size) + _W(map) + #undef _W + } + +out: + for (i = 0; i < cnt; i++) + cpu_cache_level__free(&caches[i]); + return ret; +} + +static int write_stat(struct feat_fd *ff __maybe_unused, + struct evlist *evlist __maybe_unused) +{ + return 0; +} + +static int write_sample_time(struct feat_fd *ff, + struct evlist *evlist) +{ + int ret; + + ret = do_write(ff, &evlist->first_sample_time, + sizeof(evlist->first_sample_time)); + if (ret < 0) + return ret; + + return do_write(ff, &evlist->last_sample_time, + sizeof(evlist->last_sample_time)); +} + + +static int memory_node__read(struct memory_node *n, unsigned long idx) +{ + unsigned int phys, size = 0; + char path[PATH_MAX]; + struct io_dirent64 *ent; + struct io_dir dir; + +#define for_each_memory(mem, dir) \ + while ((ent = io_dir__readdir(&dir)) != NULL) \ + if (strcmp(ent->d_name, ".") && \ + strcmp(ent->d_name, "..") && \ + sscanf(ent->d_name, "memory%u", &mem) == 1) + + scnprintf(path, PATH_MAX, + "%s/devices/system/node/node%lu", + sysfs__mountpoint(), idx); + + io_dir__init(&dir, open(path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (dir.dirfd < 0) { + pr_warning("failed: can't open memory sysfs data '%s'\n", path); + return -1; + } + + for_each_memory(phys, dir) { + size = max(phys, size); + } + + size++; + + n->set = bitmap_zalloc(size); + if (!n->set) { + close(dir.dirfd); + return -ENOMEM; + } + + n->node = idx; + n->size = size; + + io_dir__rewinddir(&dir); + + for_each_memory(phys, dir) { + __set_bit(phys, n->set); + } + + close(dir.dirfd); + return 0; +} + +static void memory_node__delete_nodes(struct memory_node *nodesp, u64 cnt) +{ + for (u64 i = 0; i < cnt; i++) + bitmap_free(nodesp[i].set); + + free(nodesp); +} + +static int memory_node__sort(const void *a, const void *b) +{ + const struct memory_node *na = a; + const struct memory_node *nb = b; + + return na->node - nb->node; +} + +static int build_mem_topology(struct memory_node **nodesp, u64 *cntp) +{ + char path[PATH_MAX]; + struct io_dirent64 *ent; + struct io_dir dir; + int ret = 0; + size_t cnt = 0, size = 0; + struct memory_node *nodes = NULL; + + scnprintf(path, PATH_MAX, "%s/devices/system/node/", + sysfs__mountpoint()); + + io_dir__init(&dir, open(path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (dir.dirfd < 0) { + pr_debug2("%s: couldn't read %s, does this arch have topology information?\n", + __func__, path); + return -1; + } + + while (!ret && (ent = io_dir__readdir(&dir))) { + unsigned int idx; + int r; + + if (!strcmp(ent->d_name, ".") || + !strcmp(ent->d_name, "..")) + continue; + + r = sscanf(ent->d_name, "node%u", &idx); + if (r != 1) + continue; + + if (cnt >= size) { + struct memory_node *new_nodes = + reallocarray(nodes, cnt + 4, sizeof(*nodes)); + + if (!new_nodes) { + pr_err("Failed to write MEM_TOPOLOGY, size %zd nodes\n", size); + ret = -ENOMEM; + goto out; + } + nodes = new_nodes; + size += 4; + } + ret = memory_node__read(&nodes[cnt], idx); + if (!ret) + cnt += 1; + } +out: + close(dir.dirfd); + if (!ret) { + *cntp = cnt; + *nodesp = nodes; + qsort(nodes, cnt, sizeof(nodes[0]), memory_node__sort); + } else + memory_node__delete_nodes(nodes, cnt); + + return ret; +} + +/* + * The MEM_TOPOLOGY holds physical memory map for every + * node in system. The format of data is as follows: + * + * 0 - version | for future changes + * 8 - block_size_bytes | /sys/devices/system/memory/block_size_bytes + * 16 - count | number of nodes + * + * For each node we store map of physical indexes for + * each node: + * + * 32 - node id | node index + * 40 - size | size of bitmap + * 48 - bitmap | bitmap of memory indexes that belongs to node + */ +static int write_mem_topology(struct feat_fd *ff __maybe_unused, + struct evlist *evlist __maybe_unused) +{ + struct memory_node *nodes = NULL; + u64 bsize, version = 1, i, nr = 0; + int ret; + + ret = sysfs__read_xll("devices/system/memory/block_size_bytes", + (unsigned long long *) &bsize); + if (ret) + return ret; + + ret = build_mem_topology(&nodes, &nr); + if (ret) + return ret; + + ret = do_write(ff, &version, sizeof(version)); + if (ret < 0) + goto out; + + ret = do_write(ff, &bsize, sizeof(bsize)); + if (ret < 0) + goto out; + + ret = do_write(ff, &nr, sizeof(nr)); + if (ret < 0) + goto out; + + for (i = 0; i < nr; i++) { + struct memory_node *n = &nodes[i]; + + #define _W(v) \ + ret = do_write(ff, &n->v, sizeof(n->v)); \ + if (ret < 0) \ + goto out; + + _W(node) + _W(size) + + #undef _W + + ret = do_write_bitmap(ff, n->set, n->size); + if (ret < 0) + goto out; + } + +out: + memory_node__delete_nodes(nodes, nr); + return ret; +} + +static int write_compressed(struct feat_fd *ff __maybe_unused, + struct evlist *evlist __maybe_unused) +{ + int ret; + + ret = do_write(ff, &(ff->ph->env.comp_ver), sizeof(ff->ph->env.comp_ver)); + if (ret) + return ret; + + ret = do_write(ff, &(ff->ph->env.comp_type), sizeof(ff->ph->env.comp_type)); + if (ret) + return ret; + + ret = do_write(ff, &(ff->ph->env.comp_level), sizeof(ff->ph->env.comp_level)); + if (ret) + return ret; + + ret = do_write(ff, &(ff->ph->env.comp_ratio), sizeof(ff->ph->env.comp_ratio)); + if (ret) + return ret; + + return do_write(ff, &(ff->ph->env.comp_mmap_len), sizeof(ff->ph->env.comp_mmap_len)); +} + +static int __write_pmu_caps(struct feat_fd *ff, struct perf_pmu *pmu, + bool write_pmu) +{ + struct perf_pmu_caps *caps = NULL; + int ret; + + ret = do_write(ff, &pmu->nr_caps, sizeof(pmu->nr_caps)); + if (ret < 0) + return ret; + + list_for_each_entry(caps, &pmu->caps, list) { + ret = do_write_string(ff, caps->name); + if (ret < 0) + return ret; + + ret = do_write_string(ff, caps->value); + if (ret < 0) + return ret; + } + + if (write_pmu) { + ret = do_write_string(ff, pmu->name); + if (ret < 0) + return ret; + } + + return ret; +} + +static int write_cpu_pmu_caps(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct perf_pmu *cpu_pmu = perf_pmus__find_core_pmu(); + int ret; + + if (!cpu_pmu) + return -ENOENT; + + ret = perf_pmu__caps_parse(cpu_pmu); + if (ret < 0) + return ret; + + return __write_pmu_caps(ff, cpu_pmu, false); +} + +static int write_pmu_caps(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct perf_pmu *pmu = NULL; + int nr_pmu = 0; + int ret; + + while ((pmu = perf_pmus__scan(pmu))) { + if (!strcmp(pmu->name, "cpu")) { + /* + * The "cpu" PMU is special and covered by + * HEADER_CPU_PMU_CAPS. Note, core PMUs are + * counted/written here for ARM, s390 and Intel hybrid. + */ + continue; + } + if (perf_pmu__caps_parse(pmu) <= 0) + continue; + nr_pmu++; + } + + ret = do_write(ff, &nr_pmu, sizeof(nr_pmu)); + if (ret < 0) + return ret; + + if (!nr_pmu) + return 0; + + /* + * Note older perf tools assume core PMUs come first, this is a property + * of perf_pmus__scan. + */ + pmu = NULL; + while ((pmu = perf_pmus__scan(pmu))) { + if (!strcmp(pmu->name, "cpu")) { + /* Skip as above. */ + continue; + } + if (perf_pmu__caps_parse(pmu) <= 0) + continue; + ret = __write_pmu_caps(ff, pmu, true); + if (ret < 0) + return ret; + } + return 0; +} + +static void print_hostname(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname); +} + +static void print_osrelease(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# os release : %s\n", ff->ph->env.os_release); +} + +static void print_arch(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# arch : %s\n", ff->ph->env.arch); +} + +static void print_cpudesc(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# cpudesc : %s\n", ff->ph->env.cpu_desc); +} + +static void print_nrcpus(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# nrcpus online : %u\n", ff->ph->env.nr_cpus_online); + fprintf(fp, "# nrcpus avail : %u\n", ff->ph->env.nr_cpus_avail); +} + +static void print_version(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# perf version : %s\n", ff->ph->env.version); +} + +static void print_cmdline(struct feat_fd *ff, FILE *fp) { int nr, i; - char *str; - nr = ph->env.nr_cmdline; - str = ph->env.cmdline; + nr = ff->ph->env.nr_cmdline; fprintf(fp, "# cmdline : "); for (i = 0; i < nr; i++) { - fprintf(fp, "%s ", str); - str += strlen(str) + 1; + char *argv_i = strdup(ff->ph->env.cmdline_argv[i]); + if (!argv_i) { + fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]); + } else { + char *mem = argv_i; + do { + char *quote = strchr(argv_i, '\''); + if (!quote) + break; + *quote++ = '\0'; + fprintf(fp, "%s\\\'", argv_i); + argv_i = quote; + } while (1); + fprintf(fp, "%s ", argv_i); + free(mem); + } } fputc('\n', fp); } -static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_cpu_topology(struct feat_fd *ff, FILE *fp) { + struct perf_header *ph = ff->ph; + int cpu_nr = ph->env.nr_cpus_avail; int nr, i; char *str; @@ -1224,10 +1685,20 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused, str = ph->env.sibling_cores; for (i = 0; i < nr; i++) { - fprintf(fp, "# sibling cores : %s\n", str); + fprintf(fp, "# sibling sockets : %s\n", str); str += strlen(str) + 1; } + if (ph->env.nr_sibling_dies) { + nr = ph->env.nr_sibling_dies; + str = ph->env.sibling_dies; + + for (i = 0; i < nr; i++) { + fprintf(fp, "# sibling dies : %s\n", str); + str += strlen(str) + 1; + } + } + nr = ph->env.nr_sibling_threads; str = ph->env.sibling_threads; @@ -1235,90 +1706,262 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused, fprintf(fp, "# sibling threads : %s\n", str); str += strlen(str) + 1; } + + if (ph->env.nr_sibling_dies) { + if (ph->env.cpu != NULL) { + for (i = 0; i < cpu_nr; i++) + fprintf(fp, "# CPU %d: Core ID %d, " + "Die ID %d, Socket ID %d\n", + i, ph->env.cpu[i].core_id, + ph->env.cpu[i].die_id, + ph->env.cpu[i].socket_id); + } else + fprintf(fp, "# Core ID, Die ID and Socket ID " + "information is not available\n"); + } else { + if (ph->env.cpu != NULL) { + for (i = 0; i < cpu_nr; i++) + fprintf(fp, "# CPU %d: Core ID %d, " + "Socket ID %d\n", + i, ph->env.cpu[i].core_id, + ph->env.cpu[i].socket_id); + } else + fprintf(fp, "# Core ID and Socket ID " + "information is not available\n"); + } +} + +static void print_clockid(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# clockid frequency: %"PRIu64" MHz\n", + ff->ph->env.clock.clockid_res_ns * 1000); +} + +static void print_clock_data(struct feat_fd *ff, FILE *fp) +{ + struct timespec clockid_ns; + char tstr[64], date[64]; + struct timeval tod_ns; + clockid_t clockid; + struct tm ltime; + u64 ref; + + if (!ff->ph->env.clock.enabled) { + fprintf(fp, "# reference time disabled\n"); + return; + } + + /* Compute TOD time. */ + ref = ff->ph->env.clock.tod_ns; + tod_ns.tv_sec = ref / NSEC_PER_SEC; + ref -= tod_ns.tv_sec * NSEC_PER_SEC; + tod_ns.tv_usec = ref / NSEC_PER_USEC; + + /* Compute clockid time. */ + ref = ff->ph->env.clock.clockid_ns; + clockid_ns.tv_sec = ref / NSEC_PER_SEC; + ref -= clockid_ns.tv_sec * NSEC_PER_SEC; + clockid_ns.tv_nsec = ref; + + clockid = ff->ph->env.clock.clockid; + + if (localtime_r(&tod_ns.tv_sec, <ime) == NULL) + snprintf(tstr, sizeof(tstr), "<error>"); + else { + strftime(date, sizeof(date), "%F %T", <ime); + scnprintf(tstr, sizeof(tstr), "%s.%06d", + date, (int) tod_ns.tv_usec); + } + + fprintf(fp, "# clockid: %s (%u)\n", clockid_name(clockid), clockid); + fprintf(fp, "# reference time: %s = %ld.%06d (TOD) = %ld.%09ld (%s)\n", + tstr, (long) tod_ns.tv_sec, (int) tod_ns.tv_usec, + (long) clockid_ns.tv_sec, clockid_ns.tv_nsec, + clockid_name(clockid)); +} + +static void print_hybrid_topology(struct feat_fd *ff, FILE *fp) +{ + int i; + struct hybrid_node *n; + + fprintf(fp, "# hybrid cpu system:\n"); + for (i = 0; i < ff->ph->env.nr_hybrid_nodes; i++) { + n = &ff->ph->env.hybrid_nodes[i]; + fprintf(fp, "# %s cpu list : %s\n", n->pmu_name, n->cpus); + } +} + +static void print_dir_format(struct feat_fd *ff, FILE *fp) +{ + struct perf_session *session; + struct perf_data *data; + + session = container_of(ff->ph, struct perf_session, header); + data = session->data; + + fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version); +} + +#ifdef HAVE_LIBBPF_SUPPORT +static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) +{ + struct perf_env *env = &ff->ph->env; + struct rb_root *root; + struct rb_node *next; + + down_read(&env->bpf_progs.lock); + + root = &env->bpf_progs.infos; + next = rb_first(root); + + if (!next) + printf("# bpf_prog_info empty\n"); + + while (next) { + struct bpf_prog_info_node *node; + + node = rb_entry(next, struct bpf_prog_info_node, rb_node); + next = rb_next(&node->rb_node); + + __bpf_event__print_bpf_prog_info(&node->info_linear->info, + env, fp); + } + + up_read(&env->bpf_progs.lock); +} + +static void print_bpf_btf(struct feat_fd *ff, FILE *fp) +{ + struct perf_env *env = &ff->ph->env; + struct rb_root *root; + struct rb_node *next; + + down_read(&env->bpf_progs.lock); + + root = &env->bpf_progs.btfs; + next = rb_first(root); + + if (!next) + printf("# btf info empty\n"); + + while (next) { + struct btf_node *node; + + node = rb_entry(next, struct btf_node, rb_node); + next = rb_next(&node->rb_node); + fprintf(fp, "# btf info of id %u\n", node->id); + } + + up_read(&env->bpf_progs.lock); } +#endif // HAVE_LIBBPF_SUPPORT -static void free_event_desc(struct perf_evsel *events) +static void free_event_desc(struct evsel *events) { - struct perf_evsel *evsel; + struct evsel *evsel; if (!events) return; - for (evsel = events; evsel->attr.size; evsel++) { - if (evsel->name) - free(evsel->name); - if (evsel->id) - free(evsel->id); + for (evsel = events; evsel->core.attr.size; evsel++) { + zfree(&evsel->name); + zfree(&evsel->core.id); } free(events); } -static struct perf_evsel * -read_event_desc(struct perf_header *ph, int fd) +static bool perf_attr_check(struct perf_event_attr *attr) { - struct perf_evsel *evsel, *events = NULL; + if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3) { + pr_warning("Reserved bits are set unexpectedly. " + "Please update perf tool.\n"); + return false; + } + + if (attr->sample_type & ~(PERF_SAMPLE_MAX-1)) { + pr_warning("Unknown sample type (0x%llx) is detected. " + "Please update perf tool.\n", + attr->sample_type); + return false; + } + + if (attr->read_format & ~(PERF_FORMAT_MAX-1)) { + pr_warning("Unknown read format (0x%llx) is detected. " + "Please update perf tool.\n", + attr->read_format); + return false; + } + + if ((attr->sample_type & PERF_SAMPLE_BRANCH_STACK) && + (attr->branch_sample_type & ~(PERF_SAMPLE_BRANCH_MAX-1))) { + pr_warning("Unknown branch sample type (0x%llx) is detected. " + "Please update perf tool.\n", + attr->branch_sample_type); + + return false; + } + + return true; +} + +static struct evsel *read_event_desc(struct feat_fd *ff) +{ + struct 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)) + if (do_read_u32(ff, &nre)) goto error; - if (ph->needs_swap) - nre = bswap_32(nre); - - ret = readn(fd, &sz, sizeof(sz)); - if (ret != (ssize_t)sizeof(sz)) + if (do_read_u32(ff, &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: */ + /* the last event terminates with evsel->core.attr.size == 0: */ events = calloc(nre + 1, sizeof(*events)); if (!events) goto error; - msz = sizeof(evsel->attr); + msz = sizeof(evsel->core.attr); if (sz < msz) msz = sz; for (i = 0, evsel = events; i < nre; evsel++, i++) { - evsel->idx = i; + evsel->core.idx = i; /* * must read entire on-file attr struct to * sync up with layout. */ - ret = readn(fd, buf, sz); - if (ret != (ssize_t)sz) + if (__do_read(ff, buf, sz)) goto error; - if (ph->needs_swap) + if (ff->ph->needs_swap) perf_event__attr_swap(buf); - memcpy(&evsel->attr, buf, msz); + memcpy(&evsel->core.attr, buf, msz); + + if (!perf_attr_check(&evsel->core.attr)) + goto error; - ret = readn(fd, &nr, sizeof(nr)); - if (ret != (ssize_t)sizeof(nr)) + if (do_read_u32(ff, &nr)) goto error; - if (ph->needs_swap) { - nr = bswap_32(nr); + if (ff->ph->needs_swap) evsel->needs_swap = true; - } - evsel->name = do_read_string(fd, ph); + evsel->name = do_read_string(ff); + if (!evsel->name) + goto error; if (!nr) continue; @@ -1326,63 +1969,52 @@ read_event_desc(struct perf_header *ph, int fd) id = calloc(nr, sizeof(*id)); if (!id) goto error; - evsel->ids = nr; - evsel->id = id; + evsel->core.ids = nr; + evsel->core.id = id; for (j = 0 ; j < nr; j++) { - ret = readn(fd, id, sizeof(*id)); - if (ret != (ssize_t)sizeof(*id)) + if (do_read_u64(ff, id)) goto error; - if (ph->needs_swap) - *id = bswap_64(*id); id++; } } out: - if (buf) - free(buf); + free(buf); return events; error: - if (events) - free_event_desc(events); + free_event_desc(events); events = NULL; goto out; } -static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) +static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val, + void *priv __maybe_unused) { - struct perf_evsel *evsel, *events = read_event_desc(ph, fd); + return fprintf(fp, ", %s = %s", name, val); +} + +static void print_event_desc(struct feat_fd *ff, FILE *fp) +{ + struct evsel *evsel, *events; u32 j; u64 *id; + if (ff->events) + events = ff->events; + else + events = read_event_desc(ff); + if (!events) { fprintf(fp, "# event desc: not available or unable to read\n"); return; } - for (evsel = events; evsel->attr.size; evsel++) { + for (evsel = events; evsel->core.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); - - if (evsel->ids) { + if (evsel->core.ids) { fprintf(fp, ", id = {"); - for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) { + for (j = 0, id = evsel->core.id; j < evsel->core.ids; j++, id++) { if (j) fputc(',', fp); fprintf(fp, " %"PRIu64, *id); @@ -1390,85 +2022,135 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) fprintf(fp, " }"); } + perf_event_attr__fprintf(fp, &evsel->core.attr, __desc_attr__fprintf, NULL); + fputc('\n', fp); } free_event_desc(events); + ff->events = NULL; } -static void print_total_mem(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_total_mem(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# total memory : %Lu kB\n", ph->env.total_mem); + fprintf(fp, "# total memory : %llu kB\n", ff->ph->env.total_mem); } -static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_numa_topology(struct feat_fd *ff, FILE *fp) { - u32 nr, c, i; - char *str, *tmp; - uint64_t mem_total, mem_free; + int i; + struct numa_node *n; - /* nr nodes */ - nr = ph->env.nr_numa_nodes; - str = ph->env.numa_nodes; + for (i = 0; i < ff->ph->env.nr_numa_nodes; i++) { + n = &ff->ph->env.numa_nodes[i]; - for (i = 0; i < nr; i++) { - /* node number */ - c = strtoul(str, &tmp, 0); - if (*tmp != ':') - goto error; + fprintf(fp, "# node%u meminfo : total = %"PRIu64" kB," + " free = %"PRIu64" kB\n", + n->node, n->mem_total, n->mem_free); - str = tmp + 1; - mem_total = strtoull(str, &tmp, 0); - if (*tmp != ':') - goto error; + fprintf(fp, "# node%u cpu list : ", n->node); + cpu_map__fprintf(n->map, fp); + } +} - str = tmp + 1; - mem_free = strtoull(str, &tmp, 0); - if (*tmp != ':') - goto error; +static void print_cpuid(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# cpuid : %s\n", ff->ph->env.cpuid); +} - fprintf(fp, "# node%u meminfo : total = %"PRIu64" kB," - " free = %"PRIu64" kB\n", - c, mem_total, mem_free); +static void print_branch_stack(struct feat_fd *ff __maybe_unused, FILE *fp) +{ + fprintf(fp, "# contains samples with branch stack\n"); +} - str = tmp + 1; - fprintf(fp, "# node%u cpu list : %s\n", c, str); +static void print_auxtrace(struct feat_fd *ff __maybe_unused, FILE *fp) +{ + fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n"); +} - str += strlen(str) + 1; +static void print_stat(struct feat_fd *ff __maybe_unused, FILE *fp) +{ + fprintf(fp, "# contains stat data\n"); +} + +static void print_cache(struct feat_fd *ff, FILE *fp __maybe_unused) +{ + int i; + + fprintf(fp, "# CPU cache info:\n"); + for (i = 0; i < ff->ph->env.caches_cnt; i++) { + fprintf(fp, "# "); + cpu_cache_level__fprintf(fp, &ff->ph->env.caches[i]); } - return; -error: - fprintf(fp, "# numa topology : not available\n"); } -static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp) +static void print_compressed(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# cpuid : %s\n", ph->env.cpuid); + fprintf(fp, "# compressed : %s, level = %d, ratio = %d\n", + ff->ph->env.comp_type == PERF_COMP_ZSTD ? "Zstd" : "Unknown", + ff->ph->env.comp_level, ff->ph->env.comp_ratio); } -static void print_branch_stack(struct perf_header *ph __maybe_unused, - int fd __maybe_unused, FILE *fp) +static void __print_pmu_caps(FILE *fp, int nr_caps, char **caps, char *pmu_name) { - fprintf(fp, "# contains samples with branch stack\n"); + const char *delimiter = ""; + int i; + + if (!nr_caps) { + fprintf(fp, "# %s pmu capabilities: not available\n", pmu_name); + return; + } + + fprintf(fp, "# %s pmu capabilities: ", pmu_name); + for (i = 0; i < nr_caps; i++) { + fprintf(fp, "%s%s", delimiter, caps[i]); + delimiter = ", "; + } + + fprintf(fp, "\n"); +} + +static void print_cpu_pmu_caps(struct feat_fd *ff, FILE *fp) +{ + __print_pmu_caps(fp, ff->ph->env.nr_cpu_pmu_caps, + ff->ph->env.cpu_pmu_caps, (char *)"cpu"); +} + +static void print_pmu_caps(struct feat_fd *ff, FILE *fp) +{ + struct perf_env *env = &ff->ph->env; + struct pmu_caps *pmu_caps; + + for (int i = 0; i < env->nr_pmus_with_caps; i++) { + pmu_caps = &env->pmu_caps[i]; + __print_pmu_caps(fp, pmu_caps->nr_caps, pmu_caps->caps, + pmu_caps->pmu_name); + } + + if (strcmp(perf_env__arch(env), "x86") == 0 && + perf_env__has_pmu_mapping(env, "ibs_op")) { + char *max_precise = perf_env__find_pmu_cap(env, "cpu", "max_precise"); + + if (max_precise != NULL && atoi(max_precise) == 0) + fprintf(fp, "# AMD systems uses ibs_op// PMU for some precise events, e.g.: cycles:p, see the 'perf list' man page for further details.\n"); + } } -static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_pmu_mappings(struct feat_fd *ff, FILE *fp) { + struct perf_env *env = &ff->ph->env; const char *delimiter = "# pmu mappings: "; char *str, *tmp; u32 pmu_num; u32 type; - pmu_num = ph->env.nr_pmu_mappings; + pmu_num = env->nr_pmu_mappings; if (!pmu_num) { fprintf(fp, "# pmu mappings: not available\n"); return; } - str = ph->env.pmu_mappings; + str = env->pmu_mappings; while (pmu_num) { type = strtoul(str, &tmp, 0); @@ -1491,24 +2173,21 @@ error: fprintf(fp, "# pmu mappings: unable to read\n"); } -static void print_group_desc(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_group_desc(struct feat_fd *ff, FILE *fp) { struct perf_session *session; - struct perf_evsel *evsel; + struct evsel *evsel; u32 nr = 0; - session = container_of(ph, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); - list_for_each_entry(evsel, &session->evlist->entries, node) { - if (perf_evsel__is_group_leader(evsel) && - evsel->nr_members > 1) { - fprintf(fp, "# group: %s{%s", evsel->group_name ?: "", - perf_evsel__name(evsel)); + evlist__for_each_entry(session->evlist, evsel) { + if (evsel__is_group_leader(evsel) && evsel->core.nr_members > 1) { + fprintf(fp, "# group: %s{%s", evsel->group_name ?: "", evsel__name(evsel)); - nr = evsel->nr_members - 1; + nr = evsel->core.nr_members - 1; } else if (nr) { - fprintf(fp, ",%s", perf_evsel__name(evsel)); + fprintf(fp, ",%s", evsel__name(evsel)); if (--nr == 0) fprintf(fp, "}\n"); @@ -1516,54 +2195,116 @@ static void print_group_desc(struct perf_header *ph, int fd __maybe_unused, } } -static int __event_process_build_id(struct build_id_event *bev, +static void print_sample_time(struct feat_fd *ff, FILE *fp) +{ + struct perf_session *session; + char time_buf[32]; + double d; + + session = container_of(ff->ph, struct perf_session, header); + + timestamp__scnprintf_usec(session->evlist->first_sample_time, + time_buf, sizeof(time_buf)); + fprintf(fp, "# time of first sample : %s\n", time_buf); + + timestamp__scnprintf_usec(session->evlist->last_sample_time, + time_buf, sizeof(time_buf)); + fprintf(fp, "# time of last sample : %s\n", time_buf); + + d = (double)(session->evlist->last_sample_time - + session->evlist->first_sample_time) / NSEC_PER_MSEC; + + fprintf(fp, "# sample duration : %10.3f ms\n", d); +} + +static void memory_node__fprintf(struct memory_node *n, + unsigned long long bsize, FILE *fp) +{ + char buf_map[100], buf_size[50]; + unsigned long long size; + + size = bsize * bitmap_weight(n->set, n->size); + unit_number__scnprintf(buf_size, 50, size); + + bitmap_scnprintf(n->set, n->size, buf_map, 100); + fprintf(fp, "# %3" PRIu64 " [%s]: %s\n", n->node, buf_size, buf_map); +} + +static void print_mem_topology(struct feat_fd *ff, FILE *fp) +{ + struct perf_env *env = &ff->ph->env; + struct memory_node *nodes; + int i, nr; + + nodes = env->memory_nodes; + nr = env->nr_memory_nodes; + + fprintf(fp, "# memory nodes (nr %d, block size 0x%llx):\n", + nr, env->memory_bsize); + + for (i = 0; i < nr; i++) { + memory_node__fprintf(&nodes[i], env->memory_bsize, fp); + } +} + +static int __event_process_build_id(struct perf_record_header_build_id *bev, char *filename, struct perf_session *session) { int err = -1; - struct list_head *head; struct machine *machine; - u16 misc; + u16 cpumode; struct dso *dso; - enum dso_kernel_type dso_type; + enum dso_space_type dso_space; machine = perf_session__findnew_machine(session, bev->pid); if (!machine) goto out; - misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + cpumode = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - switch (misc) { + switch (cpumode) { case PERF_RECORD_MISC_KERNEL: - dso_type = DSO_TYPE_KERNEL; - head = &machine->kernel_dsos; + dso_space = DSO_SPACE__KERNEL; break; case PERF_RECORD_MISC_GUEST_KERNEL: - dso_type = DSO_TYPE_GUEST_KERNEL; - head = &machine->kernel_dsos; + dso_space = DSO_SPACE__KERNEL_GUEST; break; case PERF_RECORD_MISC_USER: case PERF_RECORD_MISC_GUEST_USER: - dso_type = DSO_TYPE_USER; - head = &machine->user_dsos; + dso_space = DSO_SPACE__USER; break; default: goto out; } - dso = __dsos__findnew(head, filename); + dso = machine__findnew_dso(machine, filename); if (dso != NULL) { - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + char sbuild_id[SBUILD_ID_SIZE]; + struct build_id bid; + size_t size = BUILD_ID_SIZE; + + if (bev->header.misc & PERF_RECORD_MISC_BUILD_ID_SIZE) + size = bev->size; - dso__set_build_id(dso, &bev->build_id); + build_id__init(&bid, bev->data, size); + dso__set_build_id(dso, &bid); + dso__set_header_build_id(dso, true); - if (filename[0] == '[') - dso->kernel = dso_type; + if (dso_space != DSO_SPACE__USER) { + struct kmod_path m = { .name = NULL, }; - build_id__sprintf(dso->build_id, sizeof(dso->build_id), - sbuild_id); - pr_debug("build id event received for %s: %s\n", - dso->long_name, sbuild_id); + if (!kmod_path__parse_name(&m, filename) && m.kmod) + dso__set_module_info(dso, &m, machine); + + dso__set_kernel(dso, dso_space); + free(m.name); + } + + build_id__snprintf(dso__bid(dso), sbuild_id, sizeof(sbuild_id)); + pr_debug("build id event received for %s: %s [%zu]\n", + dso__long_name(dso), sbuild_id, size); + dso__put(dso); } err = 0; @@ -1580,7 +2321,7 @@ static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, u8 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))]; char filename[0]; } old_bev; - struct build_id_event bev; + struct perf_record_header_build_id bev; char filename[PATH_MAX]; u64 limit = offset + size; @@ -1621,7 +2362,7 @@ 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; + struct perf_record_header_build_id bev; char filename[PATH_MAX]; u64 limit = offset + size, orig_offset = offset; int err = -1; @@ -1643,7 +2384,7 @@ static int perf_header__read_build_ids(struct perf_header *header, * * "perf: 'perf kvm' tool for monitoring guest performance from host" * - * Added a field to struct build_id_event that broke the file + * Added a field to struct perf_record_header_build_id that broke the file * format. * * Since the kernel build-id is the first entry, process the @@ -1666,139 +2407,89 @@ out: return err; } -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; +/* Macro for features that simply need to read and store a string. */ +#define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \ +static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \ +{\ + free(ff->ph->env.__feat_env); \ + ff->ph->env.__feat_env = do_read_string(ff); \ + return ff->ph->env.__feat_env ? 0 : -ENOMEM; \ } -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; -} +FEAT_PROCESS_STR_FUN(hostname, hostname); +FEAT_PROCESS_STR_FUN(osrelease, os_release); +FEAT_PROCESS_STR_FUN(version, version); +FEAT_PROCESS_STR_FUN(arch, arch); +FEAT_PROCESS_STR_FUN(cpudesc, cpu_desc); +FEAT_PROCESS_STR_FUN(cpuid, cpuid); -static int process_osrelease(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +#ifdef HAVE_LIBTRACEEVENT +static int process_tracing_data(struct feat_fd *ff, void *data) { - ph->env.os_release = do_read_string(fd, ph); - return ph->env.os_release ? 0 : -ENOMEM; -} + ssize_t ret = trace_report(ff->fd, data, false); -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; + return ret < 0 ? -1 : 0; } +#endif -static int process_arch(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_build_id(struct feat_fd *ff, void *data __maybe_unused) { - ph->env.arch = do_read_string(fd, ph); - return ph->env.arch ? 0 : -ENOMEM; + if (perf_header__read_build_ids(ff->ph, ff->fd, ff->offset, ff->size)) + pr_debug("Failed to read buildids, continuing...\n"); + return 0; } -static int process_nrcpus(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_nrcpus(struct feat_fd *ff, void *data __maybe_unused) { - size_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; + struct perf_env *env = &ff->ph->env; + int ret; + u32 nr_cpus_avail, nr_cpus_online; - if (ph->needs_swap) - nr = bswap_32(nr); + ret = do_read_u32(ff, &nr_cpus_avail); + if (ret) + return ret; - ph->env.nr_cpus_avail = nr; + ret = do_read_u32(ff, &nr_cpus_online); + if (ret) + return ret; + env->nr_cpus_avail = (int)nr_cpus_avail; + env->nr_cpus_online = (int)nr_cpus_online; 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) +static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused) { - uint64_t mem; - size_t ret; + struct perf_env *env = &ff->ph->env; + u64 total_mem; + int ret; - ret = readn(fd, &mem, sizeof(mem)); - if (ret != sizeof(mem)) + ret = do_read_u64(ff, &total_mem); + if (ret) return -1; - - if (ph->needs_swap) - mem = bswap_64(mem); - - ph->env.total_mem = mem; + env->total_mem = (unsigned long long)total_mem; return 0; } -static struct perf_evsel * -perf_evlist__find_by_index(struct perf_evlist *evlist, int idx) +static struct evsel *evlist__find_by_index(struct evlist *evlist, int idx) { - struct perf_evsel *evsel; + struct evsel *evsel; - list_for_each_entry(evsel, &evlist->entries, node) { - if (evsel->idx == idx) + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.idx == idx) return evsel; } return NULL; } -static void -perf_evlist__set_event_name(struct perf_evlist *evlist, - struct perf_evsel *event) +static void evlist__set_event_name(struct evlist *evlist, struct evsel *event) { - struct perf_evsel *evsel; + struct evsel *evsel; if (!event->name) return; - evsel = perf_evlist__find_by_index(evlist, event->idx); + evsel = evlist__find_by_index(evlist, event->core.idx); if (!evsel) return; @@ -1809,220 +2500,278 @@ perf_evlist__set_event_name(struct perf_evlist *evlist, } static int -process_event_desc(struct perf_file_section *section __maybe_unused, - struct perf_header *header, int fd, - void *data __maybe_unused) +process_event_desc(struct feat_fd *ff, void *data __maybe_unused) { struct perf_session *session; - struct perf_evsel *evsel, *events = read_event_desc(header, fd); + struct evsel *evsel, *events = read_event_desc(ff); 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); + session = container_of(ff->ph, struct perf_session, header); - free_event_desc(events); + if (session->data->is_pipe) { + /* Save events for reading later by print_event_desc, + * since they can't be read again in pipe mode. */ + ff->events = events; + } + + for (evsel = events; evsel->core.attr.size; evsel++) + evlist__set_event_name(session->evlist, evsel); + + if (!session->data->is_pipe) + 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) +static int process_cmdline(struct feat_fd *ff, void *data __maybe_unused) { - size_t ret; - char *str; - u32 nr, i; - struct strbuf sb; + struct perf_env *env = &ff->ph->env; + char *str, *cmdline = NULL, **argv = NULL; + u32 nr, i, len = 0; - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) return -1; - if (ph->needs_swap) - nr = bswap_32(nr); + env->nr_cmdline = nr; + + cmdline = zalloc(ff->size + nr + 1); + if (!cmdline) + return -1; - ph->env.nr_cmdline = nr; - strbuf_init(&sb, 128); + argv = zalloc(sizeof(char *) * (nr + 1)); + if (!argv) + goto error; for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; - /* include a NULL character at the end */ - strbuf_add(&sb, str, strlen(str) + 1); + argv[i] = cmdline + len; + memcpy(argv[i], str, strlen(str) + 1); + len += strlen(str) + 1; free(str); } - ph->env.cmdline = strbuf_detach(&sb, NULL); + env->cmdline = cmdline; + env->cmdline_argv = (const char **) argv; return 0; error: - strbuf_release(&sb); + free(argv); + free(cmdline); return -1; } -static int process_cpu_topology(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) { - size_t ret; u32 nr, i; - char *str; + char *str = NULL; struct strbuf sb; + struct perf_env *env = &ff->ph->env; + int cpu_nr = env->nr_cpus_avail; + u64 size = 0; - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + env->cpu = calloc(cpu_nr, sizeof(*env->cpu)); + if (!env->cpu) return -1; - if (ph->needs_swap) - nr = bswap_32(nr); + if (do_read_u32(ff, &nr)) + goto free_cpu; - ph->env.nr_sibling_cores = nr; - strbuf_init(&sb, 128); + env->nr_sibling_cores = nr; + size += sizeof(u32); + if (strbuf_init(&sb, 128) < 0) + goto free_cpu; for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; /* include a NULL character at the end */ - strbuf_add(&sb, str, strlen(str) + 1); - free(str); + if (strbuf_add(&sb, str, strlen(str) + 1) < 0) + goto error; + size += string_size(str); + zfree(&str); } - ph->env.sibling_cores = strbuf_detach(&sb, NULL); + env->sibling_cores = strbuf_detach(&sb, NULL); - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) return -1; - if (ph->needs_swap) - nr = bswap_32(nr); + env->nr_sibling_threads = nr; + size += sizeof(u32); + + for (i = 0; i < nr; i++) { + str = do_read_string(ff); + if (!str) + goto error; - ph->env.nr_sibling_threads = nr; + /* include a NULL character at the end */ + if (strbuf_add(&sb, str, strlen(str) + 1) < 0) + goto error; + size += string_size(str); + zfree(&str); + } + env->sibling_threads = strbuf_detach(&sb, NULL); + + /* + * The header may be from old perf, + * which doesn't include core id and socket id information. + */ + if (ff->size <= size) { + zfree(&env->cpu); + return 0; + } + + for (i = 0; i < (u32)cpu_nr; i++) { + if (do_read_u32(ff, &nr)) + goto free_cpu; + + env->cpu[i].core_id = nr; + size += sizeof(u32); + + if (do_read_u32(ff, &nr)) + goto free_cpu; + + env->cpu[i].socket_id = nr; + size += sizeof(u32); + } + + /* + * The header may be from old perf, + * which doesn't include die information. + */ + if (ff->size <= size) + return 0; + + if (do_read_u32(ff, &nr)) + return -1; + + env->nr_sibling_dies = nr; + size += sizeof(u32); for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; /* include a NULL character at the end */ - strbuf_add(&sb, str, strlen(str) + 1); - free(str); + if (strbuf_add(&sb, str, strlen(str) + 1) < 0) + goto error; + size += string_size(str); + zfree(&str); + } + env->sibling_dies = strbuf_detach(&sb, NULL); + + for (i = 0; i < (u32)cpu_nr; i++) { + if (do_read_u32(ff, &nr)) + goto free_cpu; + + env->cpu[i].die_id = nr; } - ph->env.sibling_threads = strbuf_detach(&sb, NULL); + return 0; error: strbuf_release(&sb); + zfree(&str); +free_cpu: + zfree(&env->cpu); return -1; } -static int process_numa_topology(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused) { - size_t ret; - u32 nr, node, i; + struct perf_env *env = &ff->ph->env; + struct numa_node *nodes, *n; + u32 nr, 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); + if (do_read_u32(ff, &nr)) + return -1; - ph->env.nr_numa_nodes = nr; - strbuf_init(&sb, 256); + nodes = zalloc(sizeof(*nodes) * nr); + if (!nodes) + return -ENOMEM; for (i = 0; i < nr; i++) { + n = &nodes[i]; + /* node number */ - ret = readn(fd, &node, sizeof(node)); - if (ret != sizeof(node)) + if (do_read_u32(ff, &n->node)) goto error; - ret = readn(fd, &mem_total, sizeof(u64)); - if (ret != sizeof(u64)) + if (do_read_u64(ff, &n->mem_total)) goto error; - ret = readn(fd, &mem_free, sizeof(u64)); - if (ret != sizeof(u64)) + if (do_read_u64(ff, &n->mem_free)) 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); + str = do_read_string(ff); if (!str) goto error; - /* include a NULL character at the end */ - strbuf_add(&sb, str, strlen(str) + 1); + n->map = perf_cpu_map__new(str); free(str); + if (!n->map) + goto error; } - ph->env.numa_nodes = strbuf_detach(&sb, NULL); + env->nr_numa_nodes = nr; + env->numa_nodes = nodes; return 0; error: - strbuf_release(&sb); + free(nodes); return -1; } -static int process_pmu_mappings(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_pmu_mappings(struct feat_fd *ff, void *data __maybe_unused) { - size_t ret; + struct perf_env *env = &ff->ph->env; char *name; u32 pmu_num; u32 type; struct strbuf sb; - ret = readn(fd, &pmu_num, sizeof(pmu_num)); - if (ret != sizeof(pmu_num)) + if (do_read_u32(ff, &pmu_num)) return -1; - 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); + env->nr_pmu_mappings = pmu_num; + if (strbuf_init(&sb, 128) < 0) + return -1; while (pmu_num) { - if (readn(fd, &type, sizeof(type)) != sizeof(type)) + if (do_read_u32(ff, &type)) goto error; - if (ph->needs_swap) - type = bswap_32(type); - name = do_read_string(fd, ph); + name = do_read_string(ff); if (!name) goto error; - strbuf_addf(&sb, "%u:%s", type, name); + if (strbuf_addf(&sb, "%u:%s", type, name) < 0) + goto error; /* include a NULL character at the end */ - strbuf_add(&sb, "", 1); + if (strbuf_add(&sb, "", 1) < 0) + goto error; + + if (!strcmp(name, "msr")) + env->msr_pmu_type = type; free(name); pmu_num--; } - ph->env.pmu_mappings = strbuf_detach(&sb, NULL); + /* AMD may set it by evlist__has_amd_ibs() from perf_session__new() */ + free(env->pmu_mappings); + env->pmu_mappings = strbuf_detach(&sb, NULL); return 0; error: @@ -2030,27 +2779,23 @@ error: return -1; } -static int process_group_desc(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; size_t ret = -1; u32 i, nr, nr_groups; struct perf_session *session; - struct perf_evsel *evsel, *leader = NULL; + struct 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)) + if (do_read_u32(ff, &nr_groups)) return -1; - if (ph->needs_swap) - nr_groups = bswap_32(nr_groups); - - ph->env.nr_groups = nr_groups; + env->nr_groups = nr_groups; if (!nr_groups) { pr_debug("group desc not available\n"); return 0; @@ -2061,36 +2806,32 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused, return -1; for (i = 0; i < nr_groups; i++) { - desc[i].name = do_read_string(fd, ph); + desc[i].name = do_read_string(ff); if (!desc[i].name) goto out_free; - if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32)) + if (do_read_u32(ff, &desc[i].leader_idx)) goto out_free; - if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32)) + if (do_read_u32(ff, &desc[i].nr_members)) 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); - } } /* * Rebuild group relationship based on the group_desc */ - session = container_of(ph, struct perf_session, header); - session->evlist->nr_groups = nr_groups; + session = container_of(ff->ph, struct perf_session, header); i = nr = 0; - list_for_each_entry(evsel, &session->evlist->entries, node) { - if (evsel->idx == (int) desc[i].leader_idx) { - evsel->leader = evsel; + evlist__for_each_entry(session->evlist, evsel) { + if (i < nr_groups && evsel->core.idx == (int) desc[i].leader_idx) { + evsel__set_leader(evsel, evsel); /* {anon_group} is a dummy name */ - if (strcmp(desc[i].name, "{anon_group}")) + if (strcmp(desc[i].name, "{anon_group}")) { evsel->group_name = desc[i].name; - evsel->nr_members = desc[i].nr_members; + desc[i].name = NULL; + } + evsel->core.nr_members = desc[i].nr_members; if (i >= nr_groups || nr > 0) { pr_debug("invalid group desc\n"); @@ -2098,11 +2839,11 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused, } leader = evsel; - nr = evsel->nr_members - 1; + nr = evsel->core.nr_members - 1; i++; } else if (nr) { /* This is a group member */ - evsel->leader = leader; + evsel__set_leader(evsel, leader); nr--; } @@ -2115,53 +2856,603 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused, ret = 0; out_free: - while ((int) --i >= 0) - free(desc[i].name); + for (i = 0; i < nr_groups; i++) + zfree(&desc[i].name); free(desc); return ret; } -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; -}; +static int process_auxtrace(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_session *session; + int err; + + session = container_of(ff->ph, struct perf_session, header); + + err = auxtrace_index__process(ff->fd, ff->size, session, + ff->ph->needs_swap); + if (err < 0) + pr_err("Failed to process auxtrace index\n"); + return err; +} + +static int process_cache(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct cpu_cache_level *caches; + u32 cnt, i, version; + + if (do_read_u32(ff, &version)) + return -1; + + if (version != 1) + return -1; + + if (do_read_u32(ff, &cnt)) + return -1; + + caches = zalloc(sizeof(*caches) * cnt); + if (!caches) + return -1; + + for (i = 0; i < cnt; i++) { + struct cpu_cache_level *c = &caches[i]; + + #define _R(v) \ + if (do_read_u32(ff, &c->v)) \ + goto out_free_caches; \ + + _R(level) + _R(line_size) + _R(sets) + _R(ways) + #undef _R + + #define _R(v) \ + c->v = do_read_string(ff); \ + if (!c->v) \ + goto out_free_caches; \ + + _R(type) + _R(size) + _R(map) + #undef _R + } + + env->caches = caches; + env->caches_cnt = cnt; + return 0; +out_free_caches: + for (i = 0; i < cnt; i++) { + free(caches[i].type); + free(caches[i].size); + free(caches[i].map); + } + free(caches); + return -1; +} + +static int process_sample_time(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_session *session; + u64 first_sample_time, last_sample_time; + int ret; + + session = container_of(ff->ph, struct perf_session, header); + + ret = do_read_u64(ff, &first_sample_time); + if (ret) + return -1; + + ret = do_read_u64(ff, &last_sample_time); + if (ret) + return -1; + + session->evlist->first_sample_time = first_sample_time; + session->evlist->last_sample_time = last_sample_time; + return 0; +} + +static int process_mem_topology(struct feat_fd *ff, + void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct memory_node *nodes; + u64 version, i, nr, bsize; + int ret = -1; + + if (do_read_u64(ff, &version)) + return -1; + + if (version != 1) + return -1; + + if (do_read_u64(ff, &bsize)) + return -1; + + if (do_read_u64(ff, &nr)) + return -1; + + nodes = zalloc(sizeof(*nodes) * nr); + if (!nodes) + return -1; + + for (i = 0; i < nr; i++) { + struct memory_node n; + + #define _R(v) \ + if (do_read_u64(ff, &n.v)) \ + goto out; \ + + _R(node) + _R(size) + + #undef _R + + if (do_read_bitmap(ff, &n.set, &n.size)) + goto out; + + nodes[i] = n; + } + + env->memory_bsize = bsize; + env->memory_nodes = nodes; + env->nr_memory_nodes = nr; + ret = 0; + +out: + if (ret) + free(nodes); + return ret; +} + +static int process_clockid(struct feat_fd *ff, + void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + + if (do_read_u64(ff, &env->clock.clockid_res_ns)) + return -1; + + return 0; +} + +static int process_clock_data(struct feat_fd *ff, + void *_data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + u32 data32; + u64 data64; + + /* version */ + if (do_read_u32(ff, &data32)) + return -1; + + if (data32 != 1) + return -1; + + /* clockid */ + if (do_read_u32(ff, &data32)) + return -1; + + env->clock.clockid = data32; + + /* TOD ref time */ + if (do_read_u64(ff, &data64)) + return -1; + + env->clock.tod_ns = data64; + + /* clockid ref time */ + if (do_read_u64(ff, &data64)) + return -1; + + env->clock.clockid_ns = data64; + env->clock.enabled = true; + return 0; +} + +static int process_hybrid_topology(struct feat_fd *ff, + void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct hybrid_node *nodes, *n; + u32 nr, i; + + /* nr nodes */ + if (do_read_u32(ff, &nr)) + return -1; + + nodes = zalloc(sizeof(*nodes) * nr); + if (!nodes) + return -ENOMEM; + + for (i = 0; i < nr; i++) { + n = &nodes[i]; + + n->pmu_name = do_read_string(ff); + if (!n->pmu_name) + goto error; + + n->cpus = do_read_string(ff); + if (!n->cpus) + goto error; + } + + env->nr_hybrid_nodes = nr; + env->hybrid_nodes = nodes; + return 0; + +error: + for (i = 0; i < nr; i++) { + free(nodes[i].pmu_name); + free(nodes[i].cpus); + } + + free(nodes); + return -1; +} + +static int process_dir_format(struct feat_fd *ff, + void *_data __maybe_unused) +{ + struct perf_session *session; + struct perf_data *data; + + session = container_of(ff->ph, struct perf_session, header); + data = session->data; + + if (WARN_ON(!perf_data__is_dir(data))) + return -1; + + return do_read_u64(ff, &data->dir.version); +} + +#ifdef HAVE_LIBBPF_SUPPORT +static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) +{ + struct bpf_prog_info_node *info_node; + struct perf_env *env = &ff->ph->env; + struct perf_bpil *info_linear; + u32 count, i; + int err = -1; + + if (ff->ph->needs_swap) { + pr_warning("interpreting bpf_prog_info from systems with endianness is not yet supported\n"); + return 0; + } + + if (do_read_u32(ff, &count)) + return -1; + + down_write(&env->bpf_progs.lock); + + for (i = 0; i < count; ++i) { + u32 info_len, data_len; + + info_linear = NULL; + info_node = NULL; + if (do_read_u32(ff, &info_len)) + goto out; + if (do_read_u32(ff, &data_len)) + goto out; + + if (info_len > sizeof(struct bpf_prog_info)) { + pr_warning("detected invalid bpf_prog_info\n"); + goto out; + } + + info_linear = malloc(sizeof(struct perf_bpil) + + data_len); + if (!info_linear) + goto out; + info_linear->info_len = sizeof(struct bpf_prog_info); + info_linear->data_len = data_len; + if (do_read_u64(ff, (u64 *)(&info_linear->arrays))) + goto out; + if (__do_read(ff, &info_linear->info, info_len)) + goto out; + if (info_len < sizeof(struct bpf_prog_info)) + memset(((void *)(&info_linear->info)) + info_len, 0, + sizeof(struct bpf_prog_info) - info_len); + + if (__do_read(ff, info_linear->data, data_len)) + goto out; + + info_node = malloc(sizeof(struct bpf_prog_info_node)); + if (!info_node) + goto out; + + /* after reading from file, translate offset to address */ + bpil_offs_to_addr(info_linear); + info_node->info_linear = info_linear; + info_node->metadata = NULL; + if (!__perf_env__insert_bpf_prog_info(env, info_node)) { + free(info_linear); + free(info_node); + } + } + + up_write(&env->bpf_progs.lock); + return 0; +out: + free(info_linear); + free(info_node); + up_write(&env->bpf_progs.lock); + return err; +} + +static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct btf_node *node = NULL; + u32 count, i; + int err = -1; + + if (ff->ph->needs_swap) { + pr_warning("interpreting btf from systems with endianness is not yet supported\n"); + return 0; + } + + if (do_read_u32(ff, &count)) + return -1; + + down_write(&env->bpf_progs.lock); + + for (i = 0; i < count; ++i) { + u32 id, data_size; + + if (do_read_u32(ff, &id)) + goto out; + if (do_read_u32(ff, &data_size)) + goto out; + + node = malloc(sizeof(struct btf_node) + data_size); + if (!node) + goto out; + + node->id = id; + node->data_size = data_size; + + if (__do_read(ff, node->data, data_size)) + goto out; + + if (!__perf_env__insert_btf(env, node)) + free(node); + node = NULL; + } + + err = 0; +out: + up_write(&env->bpf_progs.lock); + free(node); + return err; +} +#endif // HAVE_LIBBPF_SUPPORT + +static int process_compressed(struct feat_fd *ff, + void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + + if (do_read_u32(ff, &(env->comp_ver))) + return -1; + + if (do_read_u32(ff, &(env->comp_type))) + return -1; + + if (do_read_u32(ff, &(env->comp_level))) + return -1; + + if (do_read_u32(ff, &(env->comp_ratio))) + return -1; + + if (do_read_u32(ff, &(env->comp_mmap_len))) + return -1; + + return 0; +} + +static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps, + char ***caps, unsigned int *max_branches, + unsigned int *br_cntr_nr, + unsigned int *br_cntr_width) +{ + char *name, *value, *ptr; + u32 nr_pmu_caps, i; + + *nr_caps = 0; + *caps = NULL; + + if (do_read_u32(ff, &nr_pmu_caps)) + return -1; + + if (!nr_pmu_caps) + return 0; + + *caps = zalloc(sizeof(char *) * nr_pmu_caps); + if (!*caps) + return -1; + + for (i = 0; i < nr_pmu_caps; i++) { + name = do_read_string(ff); + if (!name) + goto error; + + value = do_read_string(ff); + if (!value) + goto free_name; + + if (asprintf(&ptr, "%s=%s", name, value) < 0) + goto free_value; + + (*caps)[i] = ptr; + + if (!strcmp(name, "branches")) + *max_branches = atoi(value); -#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 } + if (!strcmp(name, "branch_counter_nr")) + *br_cntr_nr = atoi(value); + + if (!strcmp(name, "branch_counter_width")) + *br_cntr_width = atoi(value); + + free(value); + free(name); + } + *nr_caps = nr_pmu_caps; + return 0; + +free_value: + free(value); +free_name: + free(name); +error: + for (; i > 0; i--) + free((*caps)[i - 1]); + free(*caps); + *caps = NULL; + *nr_caps = 0; + return -1; +} + +static int process_cpu_pmu_caps(struct feat_fd *ff, + void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + int ret = __process_pmu_caps(ff, &env->nr_cpu_pmu_caps, + &env->cpu_pmu_caps, + &env->max_branches, + &env->br_cntr_nr, + &env->br_cntr_width); + + if (!ret && !env->cpu_pmu_caps) + pr_debug("cpu pmu capabilities not available\n"); + return ret; +} + +static int process_pmu_caps(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct pmu_caps *pmu_caps; + u32 nr_pmu, i; + int ret; + int j; + + if (do_read_u32(ff, &nr_pmu)) + return -1; + + if (!nr_pmu) { + pr_debug("pmu capabilities not available\n"); + return 0; + } + + pmu_caps = zalloc(sizeof(*pmu_caps) * nr_pmu); + if (!pmu_caps) + return -ENOMEM; + + for (i = 0; i < nr_pmu; i++) { + ret = __process_pmu_caps(ff, &pmu_caps[i].nr_caps, + &pmu_caps[i].caps, + &pmu_caps[i].max_branches, + &pmu_caps[i].br_cntr_nr, + &pmu_caps[i].br_cntr_width); + if (ret) + goto err; + + pmu_caps[i].pmu_name = do_read_string(ff); + if (!pmu_caps[i].pmu_name) { + ret = -1; + goto err; + } + if (!pmu_caps[i].nr_caps) { + pr_debug("%s pmu capabilities not available\n", + pmu_caps[i].pmu_name); + } + } + + env->nr_pmus_with_caps = nr_pmu; + env->pmu_caps = pmu_caps; + return 0; + +err: + for (i = 0; i < nr_pmu; i++) { + for (j = 0; j < pmu_caps[i].nr_caps; j++) + free(pmu_caps[i].caps[j]); + free(pmu_caps[i].caps); + free(pmu_caps[i].pmu_name); + } + + free(pmu_caps); + return ret; +} + +#define FEAT_OPR(n, func, __full_only) \ + [HEADER_##n] = { \ + .name = __stringify(n), \ + .write = write_##func, \ + .print = print_##func, \ + .full_only = __full_only, \ + .process = process_##func, \ + .synthesize = true \ + } + +#define FEAT_OPN(n, func, __full_only) \ + [HEADER_##n] = { \ + .name = __stringify(n), \ + .write = write_##func, \ + .print = print_##func, \ + .full_only = __full_only, \ + .process = process_##func \ + } /* 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), +#define process_branch_stack NULL +#define process_stat NULL + +// Only used in util/synthetic-events.c +const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE]; + +const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = { +#ifdef HAVE_LIBTRACEEVENT + FEAT_OPN(TRACING_DATA, tracing_data, false), +#endif + FEAT_OPN(BUILD_ID, build_id, false), + FEAT_OPR(HOSTNAME, hostname, false), + FEAT_OPR(OSRELEASE, osrelease, false), + FEAT_OPR(VERSION, version, false), + FEAT_OPR(ARCH, arch, false), + FEAT_OPR(NRCPUS, nrcpus, false), + FEAT_OPR(CPUDESC, cpudesc, false), + FEAT_OPR(CPUID, cpuid, false), + FEAT_OPR(TOTAL_MEM, total_mem, false), + FEAT_OPR(EVENT_DESC, event_desc, false), + FEAT_OPR(CMDLINE, cmdline, false), + FEAT_OPR(CPU_TOPOLOGY, cpu_topology, true), + FEAT_OPR(NUMA_TOPOLOGY, numa_topology, true), + FEAT_OPN(BRANCH_STACK, branch_stack, false), + FEAT_OPR(PMU_MAPPINGS, pmu_mappings, false), + FEAT_OPR(GROUP_DESC, group_desc, false), + FEAT_OPN(AUXTRACE, auxtrace, false), + FEAT_OPN(STAT, stat, false), + FEAT_OPN(CACHE, cache, true), + FEAT_OPR(SAMPLE_TIME, sample_time, false), + FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), + FEAT_OPR(CLOCKID, clockid, false), + FEAT_OPN(DIR_FORMAT, dir_format, false), +#ifdef HAVE_LIBBPF_SUPPORT + FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, false), + FEAT_OPR(BPF_BTF, bpf_btf, false), +#endif + FEAT_OPR(COMPRESSED, compressed, false), + FEAT_OPR(CPU_PMU_CAPS, cpu_pmu_caps, false), + FEAT_OPR(CLOCK_DATA, clock_data, false), + FEAT_OPN(HYBRID_TOPOLOGY, hybrid_topology, true), + FEAT_OPR(PMU_CAPS, pmu_caps, false), }; struct header_print_data { @@ -2174,6 +3465,7 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section, int feat, int fd, void *data) { struct header_print_data *hd = data; + struct feat_fd ff; if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { pr_debug("Failed to lseek to %" PRIu64 " offset for feature " @@ -2187,8 +3479,13 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section, if (!feat_ops[feat].print) return 0; + ff = (struct feat_fd) { + .fd = fd, + .ph = ph, + }; + if (!feat_ops[feat].full_only || hd->full) - feat_ops[feat].print(ph, fd, hd->fp); + feat_ops[feat].print(&ff, hd->fp); else fprintf(hd->fp, "# %s info available, use -I to display\n", feat_ops[feat].name); @@ -2200,47 +3497,111 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) { struct header_print_data hd; struct perf_header *header = &session->header; - int fd = session->fd; + int fd = perf_data__fd(session->data); + struct stat st; + time_t stctime; + int ret, bit; + hd.fp = fp; hd.full = full; + ret = fstat(fd, &st); + if (ret == -1) + return -1; + + stctime = st.st_mtime; + fprintf(fp, "# captured on : %s", ctime(&stctime)); + + fprintf(fp, "# header version : %u\n", header->version); + fprintf(fp, "# data offset : %" PRIu64 "\n", header->data_offset); + fprintf(fp, "# data size : %" PRIu64 "\n", header->data_size); + fprintf(fp, "# feat offset : %" PRIu64 "\n", header->feat_offset); + perf_header__process_sections(header, fd, &hd, perf_file_section__fprintf_info); + + if (session->data->is_pipe) + return 0; + + fprintf(fp, "# missing features: "); + for_each_clear_bit(bit, header->adds_features, HEADER_LAST_FEATURE) { + if (bit) + fprintf(fp, "%s ", feat_ops[bit].name); + } + + fprintf(fp, "\n"); return 0; } -static int do_write_feat(int fd, struct perf_header *h, int type, +struct header_fw { + struct feat_writer fw; + struct feat_fd *ff; +}; + +static int feat_writer_cb(struct feat_writer *fw, void *buf, size_t sz) +{ + struct header_fw *h = container_of(fw, struct header_fw, fw); + + return do_write(h->ff, buf, sz); +} + +static int do_write_feat(struct feat_fd *ff, int type, struct perf_file_section **p, - struct perf_evlist *evlist) + struct evlist *evlist, + struct feat_copier *fc) { int err; int ret = 0; - if (perf_header__has_feat(h, type)) { + if (perf_header__has_feat(ff->ph, type)) { if (!feat_ops[type].write) return -1; - (*p)->offset = lseek(fd, 0, SEEK_CUR); + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + + (*p)->offset = lseek(ff->fd, 0, SEEK_CUR); - err = feat_ops[type].write(fd, h, evlist); + /* + * Hook to let perf inject copy features sections from the input + * file. + */ + if (fc && fc->copy) { + struct header_fw h = { + .fw.write = feat_writer_cb, + .ff = ff, + }; + + /* ->copy() returns 0 if the feature was not copied */ + err = fc->copy(fc, type, &h.fw); + } else { + err = 0; + } + if (!err) + err = feat_ops[type].write(ff, evlist); if (err < 0) { - pr_debug("failed to write feature %d\n", type); + pr_debug("failed to write feature %s\n", feat_ops[type].name); /* undo anything written */ - lseek(fd, (*p)->offset, SEEK_SET); + lseek(ff->fd, (*p)->offset, SEEK_SET); return -1; } - (*p)->size = lseek(fd, 0, SEEK_CUR) - (*p)->offset; + (*p)->size = lseek(ff->fd, 0, SEEK_CUR) - (*p)->offset; (*p)++; } return ret; } static int perf_header__adds_write(struct perf_header *header, - struct perf_evlist *evlist, int fd) + struct evlist *evlist, int fd, + struct feat_copier *fc) { int nr_sections; + struct feat_fd ff = { + .fd = fd, + .ph = header, + }; struct perf_file_section *feat_sec, *p; int sec_size; u64 sec_start; @@ -2257,22 +3618,23 @@ static int perf_header__adds_write(struct perf_header *header, sec_size = sizeof(*feat_sec) * nr_sections; - sec_start = header->data_offset + header->data_size; + sec_start = header->feat_offset; lseek(fd, sec_start + sec_size, SEEK_SET); for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { - if (do_write_feat(fd, header, feat, &p, evlist)) + if (do_write_feat(&ff, feat, &p, evlist, fc)) perf_header__clear_feat(header, feat); } lseek(fd, sec_start, SEEK_SET); /* * may write more than needed due to dropped feature, but - * this is okay, reader will skip the mising entries + * this is okay, reader will skip the missing entries */ - err = do_write(fd, feat_sec, sec_size); + err = do_write(&ff, feat_sec, sec_size); if (err < 0) pr_debug("failed to write feature section\n"); + free(ff.buf); /* TODO: added to silence clang-tidy. */ free(feat_sec); return err; } @@ -2280,6 +3642,9 @@ static int perf_header__adds_write(struct perf_header *header, int perf_header__write_pipe(int fd) { struct perf_pipe_file_header f_header; + struct feat_fd ff = { + .fd = fd, + }; int err; f_header = (struct perf_pipe_file_header){ @@ -2287,100 +3652,166 @@ int perf_header__write_pipe(int fd) .size = sizeof(f_header), }; - err = do_write(fd, &f_header, sizeof(f_header)); + err = do_write(&ff, &f_header, sizeof(f_header)); if (err < 0) { pr_debug("failed to write perf pipe header\n"); return err; } - + free(ff.buf); return 0; } -int perf_session__write_header(struct perf_session *session, - struct perf_evlist *evlist, - int fd, bool at_exit) +static int perf_session__do_write_header(struct perf_session *session, + struct evlist *evlist, + int fd, bool at_exit, + struct feat_copier *fc, + bool write_attrs_after_data) { struct perf_file_header f_header; - struct perf_file_attr f_attr; struct perf_header *header = &session->header; - struct perf_evsel *evsel; + struct evsel *evsel; + struct feat_fd ff = { + .ph = header, + .fd = fd, + }; + u64 attr_offset = sizeof(f_header), attr_size = 0; int err; - lseek(fd, sizeof(f_header), SEEK_SET); - - list_for_each_entry(evsel, &evlist->entries, node) { - 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 (write_attrs_after_data && at_exit) { + /* + * Write features at the end of the file first so that + * attributes may come after them. + */ + if (!header->data_offset && header->data_size) { + pr_err("File contains data but offset unknown\n"); + err = -1; + goto err_out; } + header->feat_offset = header->data_offset + header->data_size; + err = perf_header__adds_write(header, evlist, fd, fc); + if (err < 0) + goto err_out; + attr_offset = lseek(fd, 0, SEEK_CUR); + } else { + lseek(fd, attr_offset, SEEK_SET); } - header->attr_offset = lseek(fd, 0, SEEK_CUR); - - list_for_each_entry(evsel, &evlist->entries, node) { - f_attr = (struct perf_file_attr){ - .attr = evsel->attr, - .ids = { - .offset = evsel->id_offset, - .size = evsel->ids * sizeof(u64), + evlist__for_each_entry(session->evlist, evsel) { + evsel->id_offset = attr_offset; + /* Avoid writing at the end of the file until the session is exiting. */ + if (!write_attrs_after_data || at_exit) { + err = do_write(&ff, evsel->core.id, evsel->core.ids * sizeof(u64)); + if (err < 0) { + pr_debug("failed to write perf header\n"); + goto err_out; } - }; - err = do_write(fd, &f_attr, sizeof(f_attr)); - if (err < 0) { - pr_debug("failed to write perf header attribute\n"); - return err; } + attr_offset += evsel->core.ids * sizeof(u64); } - header->event_offset = lseek(fd, 0, SEEK_CUR); - header->event_size = trace_event_count * sizeof(struct perf_trace_event_type); - if (trace_events) { - err = do_write(fd, trace_events, header->event_size); - if (err < 0) { - pr_debug("failed to write perf header events\n"); - return err; + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.attr.size < sizeof(evsel->core.attr)) { + /* + * We are likely in "perf inject" and have read + * from an older file. Update attr size so that + * reader gets the right offset to the ids. + */ + evsel->core.attr.size = sizeof(evsel->core.attr); + } + /* Avoid writing at the end of the file until the session is exiting. */ + if (!write_attrs_after_data || at_exit) { + struct perf_file_attr f_attr = { + .attr = evsel->core.attr, + .ids = { + .offset = evsel->id_offset, + .size = evsel->core.ids * sizeof(u64), + } + }; + err = do_write(&ff, &f_attr, sizeof(f_attr)); + if (err < 0) { + pr_debug("failed to write perf header attribute\n"); + goto err_out; + } } + attr_size += sizeof(struct perf_file_attr); } - header->data_offset = lseek(fd, 0, SEEK_CUR); + if (!header->data_offset) { + if (write_attrs_after_data) + header->data_offset = sizeof(f_header); + else + header->data_offset = attr_offset + attr_size; + } + header->feat_offset = header->data_offset + header->data_size; - if (at_exit) { - err = perf_header__adds_write(header, evlist, fd); + if (!write_attrs_after_data && at_exit) { + /* Write features now feat_offset is known. */ + err = perf_header__adds_write(header, evlist, fd, fc); if (err < 0) - return err; + goto err_out; } f_header = (struct perf_file_header){ .magic = PERF_MAGIC, .size = sizeof(f_header), - .attr_size = sizeof(f_attr), + .attr_size = sizeof(struct perf_file_attr), .attrs = { - .offset = header->attr_offset, - .size = evlist->nr_entries * sizeof(f_attr), + .offset = attr_offset, + .size = attr_size, }, .data = { .offset = header->data_offset, .size = header->data_size, }, - .event_types = { - .offset = header->event_offset, - .size = header->event_size, - }, + /* event_types is ignored, store zeros */ }; memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features)); lseek(fd, 0, SEEK_SET); - err = do_write(fd, &f_header, sizeof(f_header)); + err = do_write(&ff, &f_header, sizeof(f_header)); if (err < 0) { pr_debug("failed to write perf header\n"); - return err; + goto err_out; + } else { + lseek(fd, 0, SEEK_END); + err = 0; } - lseek(fd, header->data_offset + header->data_size, SEEK_SET); +err_out: + free(ff.buf); + return err; +} - return 0; +int perf_session__write_header(struct perf_session *session, + struct evlist *evlist, + int fd, bool at_exit) +{ + return perf_session__do_write_header(session, evlist, fd, at_exit, /*fc=*/NULL, + /*write_attrs_after_data=*/false); +} + +size_t perf_session__data_offset(const struct evlist *evlist) +{ + struct evsel *evsel; + size_t data_offset; + + data_offset = sizeof(struct perf_file_header); + evlist__for_each_entry(evlist, evsel) { + data_offset += evsel->core.ids * sizeof(u64); + } + data_offset += evlist->core.nr_entries * sizeof(struct perf_file_attr); + + return data_offset; +} + +int perf_session__inject_header(struct perf_session *session, + struct evlist *evlist, + int fd, + struct feat_copier *fc, + bool write_attrs_after_data) +{ + return perf_session__do_write_header(session, evlist, fd, true, fc, + write_attrs_after_data); } static int perf_header__getbuffer64(struct perf_header *header, @@ -2417,7 +3848,7 @@ int perf_header__process_sections(struct perf_header *header, int fd, sec_size = sizeof(*feat_sec) * nr_sections; - lseek(fd, header->data_offset + header->data_size, SEEK_SET); + lseek(fd, header->feat_offset, SEEK_SET); err = perf_header__getbuffer64(header, fd, feat_sec, sec_size); if (err < 0) @@ -2439,6 +3870,7 @@ static const int attr_file_abi_sizes[] = { [1] = PERF_ATTR_SIZE_VER1, [2] = PERF_ATTR_SIZE_VER2, [3] = PERF_ATTR_SIZE_VER3, + [4] = PERF_ATTR_SIZE_VER4, 0, }; @@ -2480,11 +3912,11 @@ static const size_t attr_pipe_abi_sizes[] = { }; /* - * In the legacy pipe format, there is an implicit assumption that endiannesss + * In the legacy pipe format, there is an implicit assumption that endianness * 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. + * different endianness and perf_event ABI revisions in the perf tool itself. */ static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph) { @@ -2523,6 +3955,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, /* check for legacy format */ ret = memcmp(&magic, __perf_magic1, sizeof(magic)); if (ret == 0) { + ph->version = PERF_HEADER_VERSION_1; pr_debug("legacy perf.data format\n"); if (is_pipe) return try_all_pipe_abis(hdr_sz, ph); @@ -2534,6 +3967,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, * - unique number to identify actual perf.data files * - encode endianness of file */ + ph->version = PERF_HEADER_VERSION_2; /* check magic number with one endianness */ if (magic == __perf_magic2) @@ -2551,7 +3985,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, int perf_file_header__read(struct perf_file_header *header, struct perf_header *ph, int fd) { - int ret; + ssize_t ret; lseek(fd, 0, SEEK_SET); @@ -2570,6 +4004,24 @@ int perf_file_header__read(struct perf_file_header *header, adds_features)); } + if (header->size > header->attrs.offset) { + pr_err("Perf file header corrupt: header overlaps attrs\n"); + return -1; + } + + if (header->size > header->data.offset) { + pr_err("Perf file header corrupt: header overlaps data\n"); + return -1; + } + + if ((header->attrs.offset <= header->data.offset && + header->attrs.offset + header->attrs.size > header->data.offset) || + (header->attrs.offset > header->data.offset && + header->data.offset + header->data.size > header->attrs.offset)) { + pr_err("Perf file header corrupt: Attributes and data overlap\n"); + return -1; + } + if (header->size != sizeof(*header)) { /* Support the previous format */ if (header->size == offsetof(typeof(*header), adds_features)) @@ -2607,17 +4059,16 @@ int perf_file_header__read(struct perf_file_header *header, if (!test_bit(HEADER_HOSTNAME, header->adds_features)) { bitmap_zero(header->adds_features, HEADER_FEAT_BITS); - set_bit(HEADER_BUILD_ID, header->adds_features); + __set_bit(HEADER_BUILD_ID, header->adds_features); } } memcpy(&ph->adds_features, &header->adds_features, sizeof(ph->adds_features)); - ph->event_offset = header->event_types.offset; - ph->event_size = header->event_types.size; ph->data_offset = header->data.offset; ph->data_size = header->data.size; + ph->feat_offset = header->data.offset + header->data.size; return 0; } @@ -2625,6 +4076,13 @@ static int perf_file_section__process(struct perf_file_section *section, struct perf_header *ph, int feat, int fd, void *data) { + struct feat_fd fdd = { + .fd = fd, + .ph = ph, + .size = section->size, + .offset = section->offset, + }; + 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); @@ -2639,16 +4097,16 @@ static int perf_file_section__process(struct perf_file_section *section, if (!feat_ops[feat].process) return 0; - return feat_ops[feat].process(section, ph, fd, data); + return feat_ops[feat].process(&fdd, data); } static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, - struct perf_header *ph, int fd, - bool repipe) + struct perf_header *ph, + struct perf_data *data) { - int ret; + ssize_t ret; - ret = readn(fd, header, sizeof(*header)); + ret = perf_data__read(data, header, sizeof(*header)); if (ret <= 0) return -1; @@ -2660,26 +4118,20 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, if (ph->needs_swap) header->size = bswap_64(header->size); - if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0) - return -1; - return 0; } -static int perf_header__read_pipe(struct perf_session *session, int fd) +static int perf_header__read_pipe(struct perf_session *session) { struct perf_header *header = &session->header; struct perf_pipe_file_header f_header; - if (perf_file_header__read_pipe(&f_header, header, fd, - session->repipe) < 0) { + if (perf_file_header__read_pipe(&f_header, header, session->data) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; } - session->fd = fd; - - return 0; + return f_header.size == sizeof(f_header) ? 0 : -1; } static int read_attr(int fd, struct perf_header *ph, @@ -2688,7 +4140,7 @@ static int read_attr(int fd, struct perf_header *ph, struct perf_event_attr *attr = &f_attr->attr; size_t sz, left; size_t our_sz = sizeof(f_attr->attr); - int ret; + ssize_t ret; memset(f_attr, 0, sizeof(*f_attr)); @@ -2728,10 +4180,10 @@ static int read_attr(int fd, struct perf_header *ph, return ret <= 0 ? -1 : 0; } -static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, - struct pevent *pevent) +#ifdef HAVE_LIBTRACEEVENT +static int evsel__prepare_tracepoint_event(struct evsel *evsel, struct tep_handle *pevent) { - struct event_format *event; + struct tep_event *event; char bf[128]; /* already prepared */ @@ -2743,9 +4195,11 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, return -1; } - event = pevent_find_event(pevent, evsel->attr.config); - if (event == NULL) + event = tep_find_event(pevent, evsel->core.attr.config); + if (event == NULL) { + pr_debug("cannot find event format for %d\n", (int)evsel->core.attr.config); return -1; + } if (!evsel->name) { snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name); @@ -2758,53 +4212,92 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, return 0; } -static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, - struct pevent *pevent) +static int evlist__prepare_tracepoint_events(struct evlist *evlist, struct tep_handle *pevent) { - struct perf_evsel *pos; + struct evsel *pos; - list_for_each_entry(pos, &evlist->entries, node) { - if (pos->attr.type == PERF_TYPE_TRACEPOINT && - perf_evsel__prepare_tracepoint_event(pos, pevent)) + evlist__for_each_entry(evlist, pos) { + if (pos->core.attr.type == PERF_TYPE_TRACEPOINT && + evsel__prepare_tracepoint_event(pos, pevent)) return -1; } return 0; } +#endif -int perf_session__read_header(struct perf_session *session, int fd) +int perf_session__read_header(struct perf_session *session) { + struct perf_data *data = session->data; 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 nr_attrs, nr_ids, i, j, err; + int fd = perf_data__fd(data); - session->evlist = perf_evlist__new(); + session->evlist = evlist__new(); if (session->evlist == NULL) return -ENOMEM; - if (session->fd_pipe) - return perf_header__read_pipe(session, fd); + session->evlist->session = session; + session->machines.host.env = &header->env; + + /* + * We can read 'pipe' data event from regular file, + * check for the pipe header regardless of source. + */ + err = perf_header__read_pipe(session); + if (!err || perf_data__is_pipe(data)) { + data->is_pipe = true; + return err; + } if (perf_file_header__read(&f_header, header, fd) < 0) return -EINVAL; + if (header->needs_swap && data->in_place_update) { + pr_err("In-place update not supported when byte-swapping is required\n"); + 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", + data->file.path); + } + + if (f_header.attr_size == 0) { + pr_err("ERROR: The %s file's attr size field is 0 which is unexpected.\n" + "Was the 'perf record' command properly terminated?\n", + data->file.path); + return -EINVAL; + } + 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; + struct evsel *evsel; off_t tmp; if (read_attr(fd, header, &f_attr) < 0) goto out_errno; - if (header->needs_swap) + if (header->needs_swap) { + f_attr.ids.size = bswap_64(f_attr.ids.size); + f_attr.ids.offset = bswap_64(f_attr.ids.offset); perf_event__attr_swap(&f_attr.attr); + } tmp = lseek(fd, 0, SEEK_CUR); - evsel = perf_evsel__new(&f_attr.attr, i); + evsel = evsel__new(&f_attr.attr); if (evsel == NULL) goto out_delete_evlist; @@ -2812,9 +4305,9 @@ int perf_session__read_header(struct perf_session *session, int fd) 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(). + * entry gets purged too at evlist__delete(). */ - perf_evlist__add(session->evlist, evsel); + evlist__add(session->evlist, evsel); nr_ids = f_attr.ids.size / sizeof(u64); /* @@ -2822,7 +4315,7 @@ int perf_session__read_header(struct perf_session *session, int fd) * for allocating the perf_sample_id table we fake 1 cpu and * hattr->ids threads. */ - if (perf_evsel__alloc_id(evsel, 1, nr_ids)) + if (perf_evsel__alloc_id(&evsel->core, 1, nr_ids)) goto out_delete_evlist; lseek(fd, f_attr.ids.offset, SEEK_SET); @@ -2831,260 +4324,247 @@ int perf_session__read_header(struct perf_session *session, int fd) 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); + perf_evlist__id_add(&session->evlist->core, &evsel->core, 0, j, f_id); } lseek(fd, tmp, SEEK_SET); } - symbol_conf.nr_events = nr_attrs; - - if (f_header.event_types.size) { - lseek(fd, f_header.event_types.offset, SEEK_SET); - trace_events = malloc(f_header.event_types.size); - if (trace_events == NULL) - return -ENOMEM; - if (perf_header__getbuffer64(header, fd, trace_events, - f_header.event_types.size)) - goto out_errno; - trace_event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); - } - - perf_header__process_sections(header, fd, &session->pevent, +#ifdef HAVE_LIBTRACEEVENT + perf_header__process_sections(header, fd, &session->tevent, perf_file_section__process); - lseek(fd, header->data_offset, SEEK_SET); - - if (perf_evlist__prepare_tracepoint_events(session->evlist, - session->pevent)) + if (evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent)) goto out_delete_evlist; +#else + perf_header__process_sections(header, fd, NULL, perf_file_section__process); +#endif return 0; out_errno: return -errno; out_delete_evlist: - perf_evlist__delete(session->evlist); + evlist__delete(session->evlist); session->evlist = NULL; return -ENOMEM; } -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__process_feature(struct perf_session *session, + union perf_event *event) { - union perf_event *ev; - size_t size; - int err; - - size = sizeof(struct perf_event_attr); - size = PERF_ALIGN(size, sizeof(u64)); - size += sizeof(struct perf_event_header); - size += ids * sizeof(u64); + struct feat_fd ff = { .fd = 0 }; + struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event; + int type = fe->header.type; + u64 feat = fe->feat_id; + int ret = 0; + bool print = dump_trace; - ev = malloc(size); + if (type < 0 || type >= PERF_RECORD_HEADER_MAX) { + pr_warning("invalid record type %d in pipe-mode\n", type); + return 0; + } + if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) { + pr_warning("invalid record type %d in pipe-mode\n", type); + return -1; + } - if (ev == NULL) - return -ENOMEM; + ff.buf = (void *)fe->data; + ff.size = event->header.size - sizeof(*fe); + ff.ph = &session->header; - ev->attr.attr = *attr; - memcpy(ev->attr.id, id, ids * sizeof(u64)); + if (feat_ops[feat].process && feat_ops[feat].process(&ff, NULL)) { + ret = -1; + goto out; + } - ev->attr.header.type = PERF_RECORD_HEADER_ATTR; - ev->attr.header.size = (u16)size; + if (session->tool->show_feat_hdr) { + if (!feat_ops[feat].full_only || + session->tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) { + print = true; + } else { + fprintf(stdout, "# %s info available, use -I to display\n", + feat_ops[feat].name); + } + } - if (ev->attr.header.size == size) - err = process(tool, ev, NULL, NULL); - else - err = -E2BIG; + if (dump_trace) + printf(", "); - free(ev); + if (print) { + if (feat_ops[feat].print) + feat_ops[feat].print(&ff, stdout); + else + printf("# %s", feat_ops[feat].name); + } - return err; +out: + free_event_desc(ff.events); + return ret; } -int perf_event__synthesize_attrs(struct perf_tool *tool, - struct perf_session *session, - perf_event__handler_t process) +size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) { - struct perf_evsel *evsel; - int err = 0; + struct perf_record_event_update *ev = &event->event_update; + struct perf_cpu_map *map; + size_t ret; - list_for_each_entry(evsel, &session->evlist->entries, node) { - err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids, - evsel->id, process); - if (err) { - pr_debug("failed to create perf header attribute\n"); - return err; - } + ret = fprintf(fp, "\n... id: %" PRI_lu64 "\n", ev->id); + + switch (ev->type) { + case PERF_EVENT_UPDATE__SCALE: + ret += fprintf(fp, "... scale: %f\n", ev->scale.scale); + break; + case PERF_EVENT_UPDATE__UNIT: + ret += fprintf(fp, "... unit: %s\n", ev->unit); + break; + case PERF_EVENT_UPDATE__NAME: + ret += fprintf(fp, "... name: %s\n", ev->name); + break; + case PERF_EVENT_UPDATE__CPUS: + ret += fprintf(fp, "... "); + + map = cpu_map__new_data(&ev->cpus.cpus); + if (map) { + ret += cpu_map__fprintf(map, fp); + perf_cpu_map__put(map); + } else + ret += fprintf(fp, "failed to get cpus\n"); + break; + default: + ret += fprintf(fp, "... unknown type\n"); + break; } - return err; + return ret; } -int perf_event__process_attr(union perf_event *event, - struct perf_evlist **pevlist) +size_t perf_event__fprintf_attr(union perf_event *event, FILE *fp) { - u32 i, ids, n_ids; - struct perf_evsel *evsel; - struct perf_evlist *evlist = *pevlist; + return perf_event_attr__fprintf(fp, &event->attr.attr, __desc_attr__fprintf, NULL); +} + +int perf_event__process_attr(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct evlist **pevlist) +{ + u32 i, n_ids; + u64 *ids; + struct evsel *evsel; + struct evlist *evlist = *pevlist; + + if (dump_trace) + perf_event__fprintf_attr(event, stdout); if (evlist == NULL) { - *pevlist = evlist = perf_evlist__new(); + *pevlist = evlist = evlist__new(); if (evlist == NULL) return -ENOMEM; } - evsel = perf_evsel__new(&event->attr.attr, evlist->nr_entries); + evsel = evsel__new(&event->attr.attr); if (evsel == NULL) return -ENOMEM; - perf_evlist__add(evlist, evsel); + evlist__add(evlist, evsel); - ids = event->header.size; - ids -= (void *)&event->attr.id - (void *)event; - n_ids = ids / sizeof(u64); + n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size; + n_ids = n_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)) + if (perf_evsel__alloc_id(&evsel->core, 1, n_ids)) return -ENOMEM; + ids = perf_record_header_attr_id(event); for (i = 0; i < n_ids; i++) { - perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]); + perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]); } - symbol_conf.nr_events = evlist->nr_entries; - return 0; } -int perf_event__synthesize_event_type(struct perf_tool *tool, - u64 event_id, char *name, - perf_event__handler_t process, - struct machine *machine) +int perf_event__process_event_update(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct evlist **pevlist) { - union perf_event ev; - size_t size = 0; - int err = 0; - - memset(&ev, 0, sizeof(ev)); - - ev.event_type.event_type.event_id = event_id; - memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME); - strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1); + struct perf_record_event_update *ev = &event->event_update; + struct evlist *evlist; + struct evsel *evsel; + struct perf_cpu_map *map; - ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE; - size = strlen(ev.event_type.event_type.name); - size = PERF_ALIGN(size, sizeof(u64)); - ev.event_type.header.size = sizeof(ev.event_type) - - (sizeof(ev.event_type.event_type.name) - size); + if (dump_trace) + perf_event__fprintf_event_update(event, stdout); - err = process(tool, &ev, NULL, machine); - - return err; -} + if (!pevlist || *pevlist == NULL) + return -EINVAL; -int perf_event__synthesize_event_types(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) -{ - struct perf_trace_event_type *type; - int i, err = 0; + evlist = *pevlist; - for (i = 0; i < trace_event_count; i++) { - type = &trace_events[i]; + evsel = evlist__id2evsel(evlist, ev->id); + if (evsel == NULL) + return -EINVAL; - err = perf_event__synthesize_event_type(tool, type->event_id, - type->name, process, - machine); - if (err) { - pr_debug("failed to create perf header event type\n"); - return err; - } + switch (ev->type) { + case PERF_EVENT_UPDATE__UNIT: + free((char *)evsel->unit); + evsel->unit = strdup(ev->unit); + break; + case PERF_EVENT_UPDATE__NAME: + free(evsel->name); + evsel->name = strdup(ev->name); + break; + case PERF_EVENT_UPDATE__SCALE: + evsel->scale = ev->scale.scale; + break; + case PERF_EVENT_UPDATE__CPUS: + map = cpu_map__new_data(&ev->cpus.cpus); + if (map) { + perf_cpu_map__put(evsel->core.pmu_cpus); + evsel->core.pmu_cpus = map; + } else + pr_err("failed to get event_update cpus\n"); + default: + break; } - return err; -} - -int perf_event__process_event_type(struct perf_tool *tool __maybe_unused, - union perf_event *event) -{ - if (perf_header__push_event(event->event_type.event_type.event_id, - event->event_type.event_type.name) < 0) - return -ENOMEM; - return 0; } -int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, - struct perf_evlist *evlist, - perf_event__handler_t process) +#ifdef HAVE_LIBTRACEEVENT +int perf_event__process_tracing_data(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, + union perf_event *event) { - union perf_event ev; - struct tracing_data *tdata; - ssize_t size = 0, aligned_size = 0, padding; - 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 = 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(tool, &ev, NULL, NULL); + ssize_t size_read, padding, size = event->tracing_data.size; + int fd = perf_data__fd(session->data); + char buf[BUFSIZ]; /* - * The put function will copy all the tracing data - * stored in temp file to the pipe. + * The pipe fd is already in proper place and in any case + * we can't move it, and we'd screw the case where we read + * 'pipe' data from regular file. The trace_report reads + * data from 'fd' so we need to set it directly behind the + * event, where the tracing data starts. */ - tracing_data_put(tdata); + if (!perf_data__is_pipe(session->data)) { + off_t offset = lseek(fd, 0, SEEK_CUR); - write_padded(fd, NULL, 0, padding); - - return aligned_size; -} - -int perf_event__process_tracing_data(union perf_event *event, - struct perf_session *session) -{ - ssize_t size_read, padding, size = event->tracing_data.size; - off_t offset = lseek(session->fd, 0, SEEK_CUR); - char buf[BUFSIZ]; - - /* setup for reading amidst mmap */ - lseek(session->fd, offset + sizeof(struct tracing_data_event), - SEEK_SET); + /* setup for reading amidst mmap */ + lseek(fd, offset + sizeof(struct perf_record_header_tracing_data), + SEEK_SET); + } - size_read = trace_report(session->fd, &session->pevent, - session->repipe); + size_read = trace_report(fd, &session->tevent, session->trace_event_repipe); padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read; - if (readn(session->fd, buf, padding) < 0) { + if (readn(fd, buf, padding) < 0) { pr_err("%s: reading input file", __func__); return -1; } - if (session->repipe) { + if (session->trace_event_repipe) { int retw = write(STDOUT_FILENO, buf, padding); if (retw <= 0 || retw != padding) { pr_err("%s: repiping tracing data padding", __func__); @@ -3097,51 +4577,18 @@ int perf_event__process_tracing_data(union perf_event *event, return -1; } - perf_evlist__prepare_tracepoint_events(session->evlist, - session->pevent); + evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent); return size_read + padding; } +#endif -int perf_event__synthesize_build_id(struct perf_tool *tool, - struct dso *pos, u16 misc, - perf_event__handler_t process, - struct machine *machine) -{ - union perf_event ev; - size_t len; - int err = 0; - - if (!pos->hit) - return err; - - memset(&ev, 0, sizeof(ev)); - - len = pos->long_name_len + 1; - 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; - ev.build_id.pid = machine->pid; - ev.build_id.header.size = sizeof(ev.build_id) + len; - memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len); - - err = process(tool, &ev, NULL, machine); - - return err; -} - -int perf_event__process_build_id(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session) +int perf_event__process_build_id(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, + union perf_event *event) { __event_process_build_id(&event->build_id, event->build_id.filename, session); return 0; } - -void disable_buildid_cache(void) -{ - no_buildid_cache = true; -} |