From 3a2c4d55e32ad65efebdb6de44eef3bfa08bb49d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 2 Sep 2026 15:31:14 -0700 Subject: treewide: refresh kmalloc_obj() conversions This is another run of the Coccinelle script for converting kmalloc() family of allocations to kmalloc_obj() via the existing rules in scripts/coccinelle/api/kmalloc_objs.cocci This catches both the set of kmalloc() uses added since the first kmalloc_obj() conversions in v7.0 and adds a large group missed in the first pass due to Coccinelle not interacting well with the cleanup.h scoped_...() family of macros[1]. I worked around this with spatch's "--macro-file" argument to a file with all the scoped_...() macros mapped to Coccinelle's YACFE_ITERATOR[2] as that was the closest viable control flow indicator I could find. Build tested allmodconfig on x86, arm64, arm, loongarch, mips, powerpc, riscv, and s390 with no new warnings. Link: https://lore.kernel.org/lkml/202609021314.8A9C0B8@keescook/ [1] Link: https://github.com/coccinelle/coccinelle/blob/master/standard.h [2] Signed-off-by: Kees Cook --- tools/perf/util/header.c | 5801 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 5801 insertions(+) create mode 100644 tools/perf/util/header.c (limited to 'tools/perf/util/header.c') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c new file mode 100644 index 000000000..7db7da090 --- /dev/null +++ b/tools/perf/util/header.c @@ -0,0 +1,5801 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include "string2.h" +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#ifdef HAVE_LIBBPF_SUPPORT +#include +#endif +#include +#include // reallocarray + +#include "dso.h" +#include "evlist.h" +#include "evsel.h" +#include "util/evsel_fprintf.h" +#include "header.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" +#include "data.h" +#include +#include +#include "asm/bug.h" +#include "tool.h" +#include "../perf.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 "cacheline.h" + +#include +#include + +#ifdef HAVE_LIBTRACEEVENT +#include +#endif + +/* + * nr_ids * sizeof(struct perf_sample_id) must not overflow + * size_t on 32-bit; the struct is ~104 bytes (32-bit) or + * ~184 bytes (64-bit), so 1<<24 (16M) keeps the product + * under 2 GB on 32-bit. + * + * This is a per-attribute cap only — the total across all + * attributes is not capped because legitimate high-core-count + * workloads (e.g. 5000 tracepoints × 4096 CPUs) can exceed + * a single-attribute limit. + */ +#define MAX_IDS_PER_ATTR (1 << 24) +/* + * Cap nr_attrs to prevent resource exhaustion from crafted + * files. 65536 is well beyond any real workload (perf stat + * typically uses < 100 events) but prevents u64-to-int + * truncation on the attr count. + */ +#define MAX_NR_ATTRS (1 << 16) +#define MAX_BPF_DATA_LEN (256 * 1024 * 1024) +#define MAX_BPF_PROGS 131072 +#define MAX_CACHE_ENTRIES 32768 +#define MAX_GROUP_DESC 32768 +#define MAX_NUMA_NODES 4096 +#define MAX_PMU_CAPS 512 +#define MAX_PMU_MAPPINGS 4096 +#define MAX_SCHED_DOMAINS 64 + +/* + * magic2 = "PERFILE2" + * must be a numerical value to let the endianness + * determine the memory layout. That way we are able + * to detect endianness when reading the perf.data file + * back. + * + * we check for legacy (PERFFILE) format. + */ +static const char *__perf_magic1 = "PERFFILE"; +static const u64 __perf_magic2 = 0x32454c4946524550ULL; +static const u64 __perf_magic2_sw = 0x50455246494c4532ULL; + +#define PERF_MAGIC __perf_magic2 +#define DNAME_LEN 16 + +const char perf_version_string[] = PERF_VERSION; + +struct perf_file_attr { + struct perf_event_attr attr; + struct perf_file_section ids; +}; + +void perf_header__set_feat(struct perf_header *header, int feat) +{ + __set_bit(feat, header->adds_features); +} + +void perf_header__clear_feat(struct perf_header *header, int feat) +{ + __clear_bit(feat, header->adds_features); +} + +bool perf_header__has_feat(const struct perf_header *header, int feat) +{ + return test_bit(feat, header->adds_features); +} + +static int __do_write_fd(struct feat_fd *ff, const void *buf, size_t size) +{ + ssize_t ret = writen(ff->fd, buf, size); + + if (ret != (ssize_t)size) + return ret < 0 ? (int)ret : -1; + return 0; +} + +static int __do_write_buf(struct feat_fd *ff, const void *buf, size_t size) +{ + /* 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 (size + ff->offset > max_size) + return -E2BIG; + + while (size > (new_size - ff->offset)) + new_size <<= 1; + new_size = min(max_size, new_size); + + if (ff->size < new_size) { + addr = realloc(ff->buf, new_size); + if (!addr) + return -ENOMEM; + ff->buf = addr; + ff->size = new_size; + } + + memcpy(ff->buf + ff->offset, buf, size); + ff->offset += size; + + return 0; +} + +/* Return: 0 if succeeded, -ERR if failed. */ +int do_write(struct feat_fd *ff, const void *buf, size_t size) +{ + if (!ff->buf) + return __do_write_fd(ff, buf, size); + return __do_write_buf(ff, buf, size); +} + +/* Return: 0 if succeeded, -ERR if failed. */ +static int do_write_bitmap(struct feat_fd *ff, unsigned long *set, u64 size) +{ + size_t byte_size = BITS_TO_LONGS(size) * sizeof(unsigned long); + int i, ret; + + ret = do_write(ff, &size, sizeof(size)); + if (ret < 0) + return ret; + + /* + * The on-disk format uses u64 elements, but the in-memory bitmap + * uses unsigned long, which is only 4 bytes on 32-bit architectures. + * Copy with bounded size so the last element doesn't read past the + * bitmap allocation when BITS_TO_LONGS(size) is odd. + */ + for (i = 0; (u64) i < BITS_TO_U64(size); i++) { + u64 val = 0; + size_t off = i * sizeof(val); + + memcpy(&val, (char *)set + off, min(sizeof(val), byte_size - off)); + ret = do_write(ff, &val, sizeof(val)); + if (ret < 0) + return ret; + } + + return 0; +} + +/* Return: 0 if succeeded, -ERR if failed. */ +int write_padded(struct feat_fd *ff, const void *bf, + size_t count, size_t count_aligned) +{ + static const char zero_buf[NAME_ALIGN]; + int err = do_write(ff, bf, count); + + if (!err) + err = do_write(ff, zero_buf, count_aligned - count); + + return err; +} + +#define string_size(str) \ + (PERF_ALIGN((strlen(str) + 1), NAME_ALIGN) + sizeof(u32)) + +/* Return: 0 if succeeded, -ERR if failed. */ +static int do_write_string(struct feat_fd *ff, 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(ff, &len, sizeof(len)); + if (ret < 0) + return ret; + + return write_padded(ff, str, olen, len); +} + +static int __do_read_fd(struct feat_fd *ff, void *addr, ssize_t size) +{ + ssize_t ret = readn(ff->fd, addr, size); + + if (ret != size) + return ret < 0 ? (int)ret : -1; + ff->offset += size; + return 0; +} + +static int __do_read_buf(struct feat_fd *ff, void *addr, ssize_t size) +{ + memcpy(addr, ff->buf + ff->offset, size); + ff->offset += size; + + return 0; +} + +static int __do_read(struct feat_fd *ff, void *addr, ssize_t size) +{ + /* + * Reject negative sizes, which on 32-bit can occur when a + * u32 >= 0x80000000 is passed as ssize_t. The cast to + * ssize_t is safe because perf_header__process_sections() + * validates that each section fits within the file size + * before any feature callback reaches here, and only + * feature sections (metadata like build IDs, topology, etc.) + * use this path — these cannot legitimately approach 2GB. + */ + if (size < 0 || size > (ssize_t)ff->size - ff->offset) + return -1; + + if (!ff->buf) + return __do_read_fd(ff, addr, size); + return __do_read_buf(ff, addr, size); +} + +static int do_read_u32(struct feat_fd *ff, u32 *addr) +{ + int ret; + + ret = __do_read(ff, addr, sizeof(*addr)); + if (ret) + return ret; + + if (ff->ph->needs_swap) + *addr = bswap_32(*addr); + return 0; +} + +static int do_read_u64(struct feat_fd *ff, u64 *addr) +{ + 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 char *do_read_string(struct feat_fd *ff) +{ + u32 len; + char *buf; + + if (do_read_u32(ff, &len)) + return NULL; + + /* At least the null terminator. */ + if (len < 1 || len > ff->size - ff->offset) { + pr_debug("do_read_string: invalid length %u (remaining %zu)\n", + len, (size_t)(ff->size - ff->offset)); + return NULL; + } + + buf = malloc(len); + if (!buf) + return NULL; + + if (!__do_read(ff, buf, len)) { + /* + * do_write_string() writes len including the null + * terminator, padded to NAME_ALIGN. Ensure the + * string is always null-terminated even if the file + * data has been tampered with. + */ + buf[len - 1] = '\0'; + return buf; + } + + free(buf); + return NULL; +} + +/* Return: 0 if succeeded, -ERR if failed. */ +static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize) +{ + unsigned long *set; + u64 size, *p; + int i, ret; + + ret = do_read_u64(ff, &size); + if (ret) + return ret; + + /* Bitmap APIs use int for nbits; reject u64 values that truncate. */ + if (size > INT_MAX || + BITS_TO_U64(size) > (ff->size - ff->offset) / sizeof(u64)) { + pr_debug("do_read_bitmap: size %" PRIu64 " exceeds section bounds\n", size); + return -1; + } + + /* + * bitmap_zalloc() allocates in unsigned long units, which are only + * 4 bytes on 32-bit architectures. The read loop below casts the + * buffer to u64 * and writes 8-byte elements, so allocate in u64 + * units to ensure the buffer is large enough. + */ + set = calloc(BITS_TO_U64(size), sizeof(u64)); + if (!set) + return -ENOMEM; + + 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; + } + } + + *pset = set; + *psize = size; + return 0; +} + +static int write_tracing_data(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + +#ifdef HAVE_LIBTRACEEVENT + return read_tracing_data(ff->fd, &evlist__core(evlist)->entries); +#else + pr_err("ERROR: Trying to write tracing data without libtraceevent support.\n"); + return -1; +#endif +} + +static int write_build_id(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct perf_session *session; + int err; + + session = container_of(ff->ph, struct perf_session, header); + + if (!perf_session__read_build_ids(session, true)) + return -1; + + 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; + } + + return 0; +} + +static int write_hostname(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct utsname uts; + int ret; + + ret = uname(&uts); + if (ret < 0) + return -1; + + return do_write_string(ff, uts.nodename); +} + +static int write_osrelease(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct utsname uts; + const char *release = NULL; + + if (evlist__session(evlist)) + release = perf_env__os_release(perf_session__env(evlist__session(evlist))); + + if (!release) { + int ret = uname(&uts); + + if (ret < 0) + return -1; + release = uts.release; + } + return do_write_string(ff, release); +} + +static int write_arch(struct feat_fd *ff, struct evlist *evlist) +{ + struct utsname uts; + const char *arch = NULL; + + if (evlist__session(evlist)) + arch = perf_env__arch(perf_session__env(evlist__session(evlist))); + + if (!arch) { + int ret = uname(&uts); + + if (ret < 0) + return -1; + arch = uts.machine; + } + return do_write_string(ff, arch); +} + +static int write_e_machine(struct feat_fd *ff, struct evlist *evlist) +{ + /* e_machine expanded from 16 to 32-bits for alignment. */ + uint32_t e_flags; + uint32_t e_machine = perf_session__e_machine(evlist__session(evlist), &e_flags); + int ret; + + ret = do_write(ff, &e_machine, sizeof(e_machine)); + if (ret) + return ret; + + return do_write(ff, &e_flags, sizeof(e_flags)); +} + +static int write_version(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + return do_write_string(ff, perf_version_string); +} + +static int __write_cpudesc(struct feat_fd *ff, const char *cpuinfo_proc) +{ + FILE *file; + char *buf = NULL; + char *s, *p; + const char *search = cpuinfo_proc; + size_t len = 0; + int ret = -1; + + if (!search) + return -1; + + file = fopen("/proc/cpuinfo", "r"); + if (!file) + return -1; + + while (getline(&buf, &len, file) > 0) { + ret = strncmp(buf, search, strlen(search)); + if (!ret) + break; + } + + if (ret) { + ret = -1; + goto done; + } + + s = buf; + + p = strchr(buf, ':'); + if (p && *(p+1) == ' ' && *(p+2)) + s = p + 2; + p = strchr(s, '\n'); + if (p) + *p = '\0'; + + /* squash extra space characters (branding string) */ + p = s; + while (*p) { + if (isspace(*p)) { + char *r = p + 1; + char *q = skip_spaces(r); + *p = ' '; + if (q != (p+1)) + while ((*r++ = *q++)); + } + p++; + } + ret = do_write_string(ff, s); +done: + free(buf); + fclose(file); + return ret; +} + +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; + + nrc = cpu__max_present_cpu().cpu; + + nr = sysconf(_SC_NPROCESSORS_ONLN); + if (nr < 0) + return -1; + + nra = (u32)(nr & UINT_MAX); + + ret = do_write(ff, &nrc, sizeof(nrc)); + if (ret < 0) + return ret; + + return do_write(ff, &nra, sizeof(nra)); +} + +static int write_event_desc(struct feat_fd *ff, + struct evlist *evlist) +{ + struct evsel *evsel; + u32 nre, nri, sz; + int ret; + + nre = evlist__nr_entries(evlist); + + /* + * write number of events + */ + ret = do_write(ff, &nre, sizeof(nre)); + if (ret < 0) + return ret; + + /* + * size of perf_event_attr struct + */ + sz = (u32)sizeof(evsel->core.attr); + ret = do_write(ff, &sz, sizeof(sz)); + if (ret < 0) + return ret; + + evlist__for_each_entry(evlist, evsel) { + ret = do_write(ff, &evsel->core.attr, sz); + if (ret < 0) + return ret; + /* + * write number of unique id per event + * there is one id per instance of an event + * + * copy into an nri to be independent of the + * type of ids, + */ + nri = evsel->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(ff, evsel__name(evsel)); + if (ret < 0) + return ret; + /* + * write unique ids for this event + */ + ret = do_write(ff, evsel->core.id, evsel->core.ids * sizeof(u64)); + if (ret < 0) + return ret; + } + return 0; +} + +static int write_cmdline(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + char pbuf[MAXPATHLEN], *buf; + int i, ret, n; + + /* actual path to perf binary */ + buf = perf_exe(pbuf, MAXPATHLEN); + + /* account for binary path */ + n = env->nr_cmdline + 1; + + ret = do_write(ff, &n, sizeof(n)); + if (ret < 0) + return ret; + + ret = do_write_string(ff, buf); + if (ret < 0) + return ret; + + for (i = 0 ; i < env->nr_cmdline; i++) { + ret = do_write_string(ff, env->cmdline_argv[i]); + if (ret < 0) + return ret; + } + return 0; +} + + +static int write_cpu_topology(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct cpu_topology *tp; + u32 i; + int ret, j; + + tp = cpu_topology__new(); + if (!tp) + return -1; + + ret = do_write(ff, &tp->package_cpus_lists, sizeof(tp->package_cpus_lists)); + if (ret < 0) + goto done; + + for (i = 0; i < tp->package_cpus_lists; i++) { + ret = do_write_string(ff, tp->package_cpus_list[i]); + if (ret < 0) + goto done; + } + ret = do_write(ff, &tp->core_cpus_lists, sizeof(tp->core_cpus_lists)); + if (ret < 0) + goto done; + + for (i = 0; i < tp->core_cpus_lists; i++) { + ret = do_write_string(ff, tp->core_cpus_list[i]); + if (ret < 0) + break; + } + + ret = perf_env__read_cpu_topology_map(env); + if (ret < 0) + goto done; + + 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) + return ret; + ret = do_write(ff, &env->cpu[j].socket_id, + sizeof(env->cpu[j].socket_id)); + if (ret < 0) + return ret; + } + + if (!tp->die_cpus_lists) + goto done; + + ret = do_write(ff, &tp->die_cpus_lists, sizeof(tp->die_cpus_lists)); + if (ret < 0) + goto done; + + for (i = 0; i < tp->die_cpus_lists; i++) { + ret = do_write_string(ff, tp->die_cpus_list[i]); + if (ret < 0) + goto done; + } + + 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) + return ret; + } + +done: + cpu_topology__delete(tp); + return ret; +} + + + +static int write_total_mem(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + char *buf = NULL; + FILE *fp; + size_t len = 0; + int ret = -1, n; + uint64_t mem; + + fp = fopen("/proc/meminfo", "r"); + if (!fp) + return -1; + + while (getline(&buf, &len, fp) > 0) { + ret = strncmp(buf, "MemTotal:", 9); + if (!ret) + break; + } + if (!ret) { + n = sscanf(buf, "%*s %"PRIu64, &mem); + if (n == 1) + ret = do_write(ff, &mem, sizeof(mem)); + } else + ret = -1; + free(buf); + fclose(fp); + return ret; +} + +static int write_numa_topology(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct numa_topology *tp; + int ret = -1; + u32 i; + + tp = numa_topology__new(); + if (!tp) + return -ENOMEM; + + ret = do_write(ff, &tp->nr, sizeof(u32)); + if (ret < 0) + goto err; + + for (i = 0; i < tp->nr; i++) { + struct numa_topology_node *n = &tp->nodes[i]; + + ret = do_write(ff, &n->node, sizeof(u32)); + if (ret < 0) + goto err; + + ret = do_write(ff, &n->mem_total, sizeof(u64)); + if (ret) + goto err; + + ret = do_write(ff, &n->mem_free, sizeof(u64)); + if (ret) + goto err; + + ret = do_write_string(ff, n->cpus); + if (ret < 0) + goto err; + } + + ret = 0; + +err: + numa_topology__delete(tp); + return ret; +} + +/* + * File format: + * + * struct pmu_mappings { + * u32 pmu_num; + * struct pmu_map { + * u32 type; + * char name[]; + * }[pmu_num]; + * }; + */ + +static int write_pmu_mappings(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + struct perf_pmu *pmu = NULL; + u32 pmu_num = 0; + int ret; + + /* + * 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_pmus__scan(pmu))) { + ret = do_write(ff, &pmu->type, sizeof(pmu->type)); + if (ret < 0) + return ret; + + ret = do_write_string(ff, pmu->name); + if (ret < 0) + return ret; + } + + return 0; +} + +/* + * File format: + * + * struct group_descs { + * u32 nr_groups; + * struct group_desc { + * char name[]; + * u32 leader_idx; + * u32 nr_members; + * }[nr_groups]; + * }; + */ +static int write_group_desc(struct feat_fd *ff, + struct evlist *evlist) +{ + u32 nr_groups = evlist__nr_groups(evlist); + struct evsel *evsel; + int ret; + + ret = do_write(ff, &nr_groups, sizeof(nr_groups)); + if (ret < 0) + return ret; + + 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->core.idx; + u32 nr_members = evsel->core.nr_members; + + ret = do_write_string(ff, name); + if (ret < 0) + return ret; + + ret = do_write(ff, &leader_idx, sizeof(leader_idx)); + if (ret < 0) + return ret; + + ret = do_write(ff, &nr_members, sizeof(nr_members)); + if (ret < 0) + return ret; + } + } + return 0; +} + +/* + * 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/$(SRCARCH)/util/header.c + */ +int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused, + struct perf_cpu cpu __maybe_unused) +{ + return ENOSYS; /* Not implemented */ +} + +static int write_cpuid(struct feat_fd *ff, struct evlist *evlist) +{ + struct perf_cpu cpu = perf_cpu_map__min(evlist__core(evlist)->all_cpus); + char buffer[64]; + int ret; + + ret = get_cpuid(buffer, sizeof(buffer), cpu); + if (ret) + return -1; + + return do_write_string(ff, buffer); +} + +static int write_branch_stack(struct feat_fd *ff __maybe_unused, + struct evlist *evlist __maybe_unused) +{ + return 0; +} + +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)); +} + +static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused, + struct evlist *evlist __maybe_unused) +{ +#ifdef HAVE_LIBBPF_SUPPORT + struct perf_env *env = &ff->ph->env; + struct rb_root *root; + struct rb_node *next; + int ret = 0; + + /* write lock: bpil_addr_to_offs() temporarily mutates info_linear */ + down_write(&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_write(&env->bpf_progs.lock); + return ret; +#else + pr_err("ERROR: Trying to write bpf_prog_info without libbpf support.\n"); + return -1; +#endif // HAVE_LIBBPF_SUPPORT +} + +static int write_bpf_btf(struct feat_fd *ff __maybe_unused, + struct evlist *evlist __maybe_unused) +{ +#ifdef HAVE_LIBBPF_SUPPORT + 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; +#else + pr_err("ERROR: Trying to write btf data without libbpf support.\n"); + return -1; +#endif // HAVE_LIBBPF_SUPPORT +} + +static int cpu_cache_level__sort(const void *a, const void *b) +{ + 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 bool cpu_cache_level__cmp(struct cpu_cache_level *a, struct cpu_cache_level *b) +{ + 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 int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 level) +{ + 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 cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c) +{ + fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map); +} + +/* + * Build caches levels for a particular CPU from the data in + * /sys/devices/system/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) +{ + 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 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_cln_size(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + int cln_size = cacheline_size(); + + if (!cln_size) + cln_size = DEFAULT_CACHELINE_SIZE; + + ff->ph->env.cln_size = cln_size; + + return do_write(ff, &cln_size, sizeof(cln_size)); +} + +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; + u64 data = evlist__first_sample_time(evlist); + + ret = do_write(ff, &data, sizeof(data)); + if (ret < 0) + return ret; + + data = evlist__last_sample_time(evlist); + return do_write(ff, &data, sizeof(data)); +} + + +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; +} + +struct cpu_domain_map **build_cpu_domain_map(u32 *schedstat_version, u32 *max_sched_domains, u32 nr) +{ + char dname[DNAME_LEN], cpumask[MAX_NR_CPUS]; + struct domain_info *domain_info; + struct cpu_domain_map **cd_map; + char cpulist[MAX_NR_CPUS]; + char *line = NULL; + u32 cpu, domain; + u32 dcount = 0; + size_t len; + FILE *fp; + + fp = fopen("/proc/schedstat", "r"); + if (!fp) { + pr_err("Failed to open /proc/schedstat\n"); + return NULL; + } + + cd_map = zalloc(sizeof(*cd_map) * nr); + if (!cd_map) + goto out; + + while (getline(&line, &len, fp) > 0) { + int retval; + + if (strncmp(line, "version", 7) == 0) { + retval = sscanf(line, "version %d\n", schedstat_version); + if (retval != 1) + continue; + + } else if (strncmp(line, "cpu", 3) == 0) { + retval = sscanf(line, "cpu%u %*s", &cpu); + if (retval == 1) { + cd_map[cpu] = zalloc(sizeof(*cd_map[cpu])); + if (!cd_map[cpu]) + goto out_free_line; + cd_map[cpu]->cpu = cpu; + } else + continue; + + dcount = 0; + } else if (strncmp(line, "domain", 6) == 0) { + struct domain_info **temp_domains; + + dcount++; + temp_domains = realloc(cd_map[cpu]->domains, dcount * sizeof(domain_info)); + if (!temp_domains) + goto out_free_line; + else + cd_map[cpu]->domains = temp_domains; + + domain_info = zalloc(sizeof(*domain_info)); + if (!domain_info) + goto out_free_line; + + cd_map[cpu]->domains[dcount - 1] = domain_info; + + if (*schedstat_version >= 17) { + retval = sscanf(line, "domain%u %s %s %*s", &domain, dname, + cpumask); + if (retval != 3) + continue; + + domain_info->dname = strdup(dname); + if (!domain_info->dname) + goto out_free_line; + } else { + retval = sscanf(line, "domain%u %s %*s", &domain, cpumask); + if (retval != 2) + continue; + } + + domain_info->domain = domain; + if (domain > *max_sched_domains) + *max_sched_domains = domain; + + domain_info->cpumask = strdup(cpumask); + if (!domain_info->cpumask) + goto out_free_line; + + cpumask_to_cpulist(cpumask, cpulist); + domain_info->cpulist = strdup(cpulist); + if (!domain_info->cpulist) + goto out_free_line; + + cd_map[cpu]->nr_domains = dcount; + } + } + +out_free_line: + free(line); +out: + fclose(fp); + return cd_map; +} + +static int write_cpu_domain_info(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + u32 max_sched_domains = 0, schedstat_version = 0; + struct cpu_domain_map **cd_map; + u32 i, j, nr, ret; + + nr = cpu__max_present_cpu().cpu; + + cd_map = build_cpu_domain_map(&schedstat_version, &max_sched_domains, nr); + if (!cd_map) + return -1; + + ret = do_write(ff, &schedstat_version, sizeof(u32)); + if (ret < 0) + goto out; + + max_sched_domains += 1; + ret = do_write(ff, &max_sched_domains, sizeof(u32)); + if (ret < 0) + goto out; + + for (i = 0; i < nr; i++) { + if (!cd_map[i]) + continue; + + ret = do_write(ff, &cd_map[i]->cpu, sizeof(u32)); + if (ret < 0) + goto out; + + ret = do_write(ff, &cd_map[i]->nr_domains, sizeof(u32)); + if (ret < 0) + goto out; + + for (j = 0; j < cd_map[i]->nr_domains; j++) { + ret = do_write(ff, &cd_map[i]->domains[j]->domain, sizeof(u32)); + if (ret < 0) + goto out; + if (schedstat_version >= 17) { + ret = do_write_string(ff, cd_map[i]->domains[j]->dname); + if (ret < 0) + goto out; + } + + ret = do_write_string(ff, cd_map[i]->domains[j]->cpumask); + if (ret < 0) + goto out; + + ret = do_write_string(ff, cd_map[i]->domains[j]->cpulist); + if (ret < 0) + goto out; + } + } + +out: + free_cpu_domain_info(cd_map, schedstat_version, nr); + return ret; +} + +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_e_machine(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# e_machine : %u\n", ff->ph->env.e_machine); + fprintf(fp, "# e_flags : %u\n", ff->ph->env.e_flags); +} + +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; + + nr = ff->ph->env.nr_cmdline; + + fprintf(fp, "# cmdline : "); + + for (i = 0; i < nr; i++) { + 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 feat_fd *ff, FILE *fp) +{ + struct perf_header *ph = ff->ph; + int cpu_nr = ph->env.nr_cpus_avail; + int nr, i; + char *str; + + nr = ph->env.nr_sibling_cores; + str = ph->env.sibling_cores; + + for (i = 0; i < nr; i++) { + fprintf(fp, "# sibling 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; + + for (i = 0; i < nr; i++) { + 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), ""); + 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); +} + +static void print_bpf_prog_info(struct feat_fd *ff __maybe_unused, FILE *fp) +{ +#ifdef HAVE_LIBBPF_SUPPORT + 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) + fprintf(fp, "# 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, env, fp); + } + + up_read(&env->bpf_progs.lock); +#else + fprintf(fp, "# bpf_prog_info missing, no libbpf support\n"); +#endif // HAVE_LIBBPF_SUPPORT +} + +static void print_bpf_btf(struct feat_fd *ff __maybe_unused, FILE *fp) +{ +#ifdef HAVE_LIBBPF_SUPPORT + 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); +#else + fprintf(fp, "# bpf btf data missing, no libbpf support\n"); +#endif // HAVE_LIBBPF_SUPPORT +} + +static void free_event_desc(struct evsel *events) +{ + struct evsel *evsel; + + if (!events) + return; + + for (evsel = events; evsel->core.attr.size; evsel++) { + zfree(&evsel->name); + zfree(&evsel->core.id); + } + + free(events); +} + +static bool perf_attr_check(struct perf_event_attr *attr) +{ + 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; + size_t msz; + + /* number of events */ + if (do_read_u32(ff, &nre)) + goto error; + + /* Size of each of the nre attributes. */ + if (do_read_u32(ff, &sz)) + goto error; + + /* + * Require at least one event with an attr no smaller than the + * first published struct, and reject sz values where + * sz + sizeof(u32) would overflow size_t (possible on 32-bit) + * or nre == UINT32_MAX where nre + 1 wraps to 0 in the calloc. + * + * The minimum section footprint per event is sz bytes for the + * attr plus a u32 for the id count, check that nre events fit. + */ + if (!nre || sz < PERF_ATTR_SIZE_VER0 || + sz > ff->size || (size_t)sz > SIZE_MAX - sizeof(u32) || + nre == UINT32_MAX || + nre > (ff->size - ff->offset) / (sz + sizeof(u32))) { + pr_err("Invalid HEADER_EVENT_DESC: nre=%u sz=%u (min %d)\n", + nre, sz, PERF_ATTR_SIZE_VER0); + goto error; + } + + /* buffer to hold on file attr struct */ + buf = malloc(sz); + if (!buf) + goto error; + + /* the last event terminates with evsel->core.attr.size == 0: */ + events = calloc(nre + 1, sizeof(*events)); + if (!events) + goto error; + + msz = sizeof(evsel->core.attr); + if (sz < msz) + msz = sz; + + for (i = 0, evsel = events; i < nre; evsel++, i++) { + struct perf_event_attr *attr = buf; + u32 attr_size; + + evsel->core.idx = i; + + /* + * must read entire on-file attr struct to + * sync up with layout. + */ + if (__do_read(ff, buf, sz)) + goto error; + + /* Reject before attr_swap to prevent OOB via bswap_safe() */ + attr_size = ff->ph->needs_swap ? bswap_32(attr->size) : attr->size; + /* ABI0: size == 0 means the producer didn't set it */ + if (!attr_size) { + attr_size = PERF_ATTR_SIZE_VER0; + /* + * Write back so free_event_desc() doesn't + * treat this event as the end-of-array sentinel + * (it iterates while attr.size != 0). + * + * Only for native — the swap path must NOT + * write native-endian VER0 here because + * perf_event__attr_swap() would re-swap it + * to 0x40000000, defeating bswap_safe() bounds. + * perf_event__attr_swap() has its own ABI0 + * fallback that sets VER0 after swapping. + */ + if (!ff->ph->needs_swap) + attr->size = attr_size; + } + if (attr_size < PERF_ATTR_SIZE_VER0 || attr_size > sz) { + pr_err("Event %d attr.size (%u) invalid (min: %d, max: %u)\n", + i, attr_size, PERF_ATTR_SIZE_VER0, sz); + goto error; + } + + if (ff->ph->needs_swap) + perf_event__attr_swap(buf); + + memcpy(&evsel->core.attr, buf, msz); + + if (!perf_attr_check(&evsel->core.attr)) + goto error; + + if (do_read_u32(ff, &nr)) + goto error; + + if (ff->ph->needs_swap) + evsel->needs_swap = true; + + evsel->name = do_read_string(ff); + if (!evsel->name) + goto error; + + if (!nr) + continue; + + /* Prevent oversized allocation from crafted nr */ + if (nr > (ff->size - ff->offset) / sizeof(*id)) { + pr_err("Event %d: id count %u exceeds remaining section\n", i, nr); + goto error; + } + + id = calloc(nr, sizeof(*id)); + if (!id) + goto error; + evsel->core.ids = nr; + evsel->core.id = id; + + for (j = 0 ; j < nr; j++) { + if (do_read_u64(ff, id)) + goto error; + id++; + } + } +out: + free(buf); + return events; +error: + free_event_desc(events); + events = NULL; + goto out; +} + +static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val, + void *priv __maybe_unused) +{ + 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->core.attr.size; evsel++) { + fprintf(fp, "# event : name = %s, ", evsel->name); + + if (evsel->core.ids) { + fprintf(fp, ", id = {"); + for (j = 0, id = evsel->core.id; j < evsel->core.ids; j++, id++) { + if (j) + fputc(',', fp); + fprintf(fp, " %"PRIu64, *id); + } + 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 feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# total memory : %llu kB\n", ff->ph->env.total_mem); +} + +static void print_numa_topology(struct feat_fd *ff, FILE *fp) +{ + int i; + struct numa_node *n; + + for (i = 0; i < ff->ph->env.nr_numa_nodes; i++) { + n = &ff->ph->env.numa_nodes[i]; + + fprintf(fp, "# node%u meminfo : total = %"PRIu64" kB," + " free = %"PRIu64" kB\n", + n->node, n->mem_total, n->mem_free); + + fprintf(fp, "# node%u cpu list : ", n->node); + cpu_map__fprintf(n->map, fp); + } +} + +static void print_cpuid(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# cpuid : %s\n", ff->ph->env.cpuid); +} + +static void print_branch_stack(struct feat_fd *ff __maybe_unused, FILE *fp) +{ + fprintf(fp, "# contains samples with branch stack\n"); +} + +static void print_auxtrace(struct feat_fd *ff __maybe_unused, FILE *fp) +{ + fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n"); +} + +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]); + } +} + +static void print_cln_size(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# cacheline size: %u\n", ff->ph->env.cln_size); +} + +static void print_compressed(struct feat_fd *ff, FILE *fp) +{ + 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_pmu_caps(FILE *fp, int nr_caps, char **caps, char *pmu_name) +{ + 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; + uint16_t e_machine = perf_env__e_machine(env, /*e_flags=*/NULL); + + for (int i = 0; i < env->nr_pmus_with_caps; i++) { + struct pmu_caps *pmu_caps = &env->pmu_caps[i]; + + __print_pmu_caps(fp, pmu_caps->nr_caps, pmu_caps->caps, + pmu_caps->pmu_name); + } + + if ((e_machine == EM_X86_64 || e_machine == EM_386) && + 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 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 = env->nr_pmu_mappings; + if (!pmu_num) { + fprintf(fp, "# pmu mappings: not available\n"); + return; + } + + str = env->pmu_mappings; + + while (pmu_num) { + type = strtoul(str, &tmp, 0); + if (*tmp != ':') + goto error; + + str = tmp + 1; + fprintf(fp, "%s%s = %" PRIu32, delimiter, str, type); + + delimiter = ", "; + str += strlen(str) + 1; + pmu_num--; + } + + fprintf(fp, "\n"); + + if (!pmu_num) + return; +error: + fprintf(fp, "# pmu mappings: unable to read\n"); +} + +static void print_group_desc(struct feat_fd *ff, FILE *fp) +{ + struct perf_session *session; + struct evsel *evsel; + u32 nr = 0; + + session = container_of(ff->ph, struct perf_session, header); + + 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->core.nr_members - 1; + } else if (nr) { + fprintf(fp, ",%s", evsel__name(evsel)); + + if (--nr == 0) + fprintf(fp, "}\n"); + } + } +} + +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(evlist__first_sample_time(session->evlist), + time_buf, sizeof(time_buf)); + fprintf(fp, "# time of first sample : %s\n", time_buf); + + timestamp__scnprintf_usec(evlist__last_sample_time(session->evlist), + time_buf, sizeof(time_buf)); + fprintf(fp, "# time of last sample : %s\n", time_buf); + + d = (double)(evlist__last_sample_time(session->evlist) - + evlist__first_sample_time(session->evlist)) / 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 void print_cpu_domain_info(struct feat_fd *ff, FILE *fp) +{ + struct cpu_domain_map **cd_map = ff->ph->env.cpu_domain; + u32 nr = ff->ph->env.nr_cpus_avail; + struct domain_info *d_info; + u32 i, j; + + fprintf(fp, "# schedstat version : %u\n", ff->ph->env.schedstat_version); + fprintf(fp, "# Maximum sched domains : %u\n", ff->ph->env.max_sched_domains); + + for (i = 0; i < nr; i++) { + if (!cd_map[i]) + continue; + + fprintf(fp, "# cpu : %u\n", cd_map[i]->cpu); + fprintf(fp, "# nr_domains : %u\n", cd_map[i]->nr_domains); + + for (j = 0; j < cd_map[i]->nr_domains; j++) { + d_info = cd_map[i]->domains[j]; + if (!d_info) + continue; + + fprintf(fp, "# Domain : %u\n", d_info->domain); + + if (ff->ph->env.schedstat_version >= 17) + fprintf(fp, "# Domain name : %s\n", d_info->dname); + + fprintf(fp, "# Domain cpu map : %s\n", d_info->cpumask); + fprintf(fp, "# Domain cpu list : %s\n", d_info->cpulist); + } + } +} + +static int __event_process_build_id(struct perf_record_header_build_id *bev, + char *filename, + struct perf_session *session) +{ + int err = -1; + struct machine *machine; + u16 cpumode; + struct dso *dso; + enum dso_space_type dso_space; + + machine = perf_session__findnew_machine(session, bev->pid); + if (!machine) + goto out; + + cpumode = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + switch (cpumode) { + case PERF_RECORD_MISC_KERNEL: + dso_space = DSO_SPACE__KERNEL; + break; + case PERF_RECORD_MISC_GUEST_KERNEL: + dso_space = DSO_SPACE__KERNEL_GUEST; + break; + case PERF_RECORD_MISC_USER: + case PERF_RECORD_MISC_GUEST_USER: + dso_space = DSO_SPACE__USER; + break; + default: + goto out; + } + + dso = machine__findnew_dso(machine, filename); + if (dso != NULL) { + 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; + + build_id__init(&bid, bev->data, size); + dso__set_build_id(dso, &bid); + dso__set_header_build_id(dso, true); + + if (dso_space != DSO_SPACE__USER) { + struct kmod_path m = { .name = NULL, }; + + 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; +out: + return err; +} + +static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, + int input, u64 offset, u64 size) +{ + struct perf_session *session = container_of(header, struct perf_session, header); + struct { + struct perf_event_header header; + u8 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))]; + char filename[0]; + } old_bev; + struct perf_record_header_build_id bev; + char filename[PATH_MAX]; + u64 limit; + + /* Prevent offset + size from wrapping past ULLONG_MAX */ + if (size > ULLONG_MAX - offset) + return -1; + + limit = offset + size; + + while (offset < limit) { + ssize_t len; + + if (readn(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev)) + return -1; + + if (header->needs_swap) + perf_event_header__bswap(&old_bev.header); + + /* size == 0 loops forever; size > remaining reads past section */ + if (old_bev.header.size == 0 || old_bev.header.size > limit - offset) + return -1; + + len = old_bev.header.size - sizeof(old_bev); + if (len < 0 || len >= PATH_MAX) { + pr_warning("invalid build_id filename length %zd\n", len); + return -1; + } + + if (readn(input, filename, len) != len) + return -1; + /* + * The file data may lack a null terminator, which could + * indicate a corrupt or crafted perf.data file. Ensure + * filename is always a valid C string before passing it + * to functions like machine__findnew_dso(). + */ + filename[len] = '\0'; + + bev.header = old_bev.header; + + /* + * As the pid is the missing value, we need to fill + * it properly. The header.misc value give us nice hint. + */ + bev.pid = HOST_KERNEL_ID; + if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER || + bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL) + bev.pid = DEFAULT_GUEST_KERNEL_ID; + + memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id)); + __event_process_build_id(&bev, filename, session); + + offset += bev.header.size; + } + + return 0; +} + +static int perf_header__read_build_ids(struct perf_header *header, + int input, u64 offset, u64 size) +{ + struct perf_session *session = container_of(header, struct perf_session, header); + struct perf_record_header_build_id bev; + char filename[PATH_MAX]; + u64 limit, orig_offset = offset; + int err = -1; + + /* Prevent offset + size from wrapping past ULLONG_MAX */ + if (size > ULLONG_MAX - offset) + return -1; + + limit = offset + size; + + while (offset < limit) { + ssize_t len; + + if (readn(input, &bev, sizeof(bev)) != sizeof(bev)) + goto out; + + if (header->needs_swap) { + perf_event_header__bswap(&bev.header); + bev.pid = bswap_32(bev.pid); + } + + /* + * size == 0 would loop forever (offset never advances); + * size > remaining would read past the section boundary. + */ + if (bev.header.size == 0 || bev.header.size > limit - offset) + goto out; + + len = bev.header.size - sizeof(bev); + if (len < 0 || len >= PATH_MAX) { + pr_warning("invalid build_id filename length %zd\n", len); + goto out; + } + + if (readn(input, filename, len) != len) + goto out; + /* + * The file data may lack a null terminator, which could + * indicate a corrupt or crafted perf.data file. Ensure + * filename is always a valid C string before passing it + * to functions like machine__findnew_dso(). + */ + filename[len] = '\0'; + /* + * The a1645ce1 changeset: + * + * "perf: 'perf kvm' tool for monitoring guest performance from host" + * + * 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 + * table using the old format if the well known + * '[kernel.kallsyms]' string for the kernel build-id has the + * first 4 characters chopped off (where the pid_t sits). + */ + /* Guard short filenames against memcmp reading past the buffer */ + if (len >= (ssize_t)sizeof("nel.kallsyms]") - 1 && + memcmp(filename, "nel.kallsyms]", sizeof("nel.kallsyms]") - 1) == 0) { + if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1) + return -1; + return perf_header__read_build_ids_abi_quirk(header, input, offset, size); + } + + __event_process_build_id(&bev, filename, session); + + offset += bev.header.size; + } + err = 0; +out: + return err; +} + +/* 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; \ +} + +FEAT_PROCESS_STR_FUN(hostname, hostname); +FEAT_PROCESS_STR_FUN(osrelease, os_release); +FEAT_PROCESS_STR_FUN(version, version); +FEAT_PROCESS_STR_FUN(cpudesc, cpu_desc); +FEAT_PROCESS_STR_FUN(cpuid, cpuid); + +static int process_arch(struct feat_fd *ff, void *data __maybe_unused) +{ + free(ff->ph->env.arch); + ff->ph->env.arch = do_read_string(ff); + if (!ff->ph->env.arch) + return -ENOMEM; + return 0; +} + +static int process_e_machine(struct feat_fd *ff, void *data __maybe_unused) +{ + int ret; + + ret = do_read_u32(ff, &ff->ph->env.e_machine); + if (ret) + return ret; + + return do_read_u32(ff, &ff->ph->env.e_flags); +} + +static int process_tracing_data(struct feat_fd *ff __maybe_unused, void *data __maybe_unused) +{ +#ifdef HAVE_LIBTRACEEVENT + ssize_t ret = trace_report(ff->fd, data, false); + + return ret < 0 ? -1 : 0; +#else + /* Not an error — the feature is simply unsupported in this build */ + pr_debug("Tracing data present but libtraceevent not available, skipping.\n"); + return 0; +#endif +} + +static int process_build_id(struct feat_fd *ff, void *data __maybe_unused) +{ + /* lseek fails in pipe mode — fall back to ff->offset */ + off_t offset = lseek(ff->fd, 0, SEEK_CUR); + + if (offset == (off_t)-1) + offset = ff->offset; + + if (perf_header__read_build_ids(ff->ph, ff->fd, offset, ff->size)) + pr_debug("Failed to read buildids, continuing...\n"); + return 0; +} + +static int process_nrcpus(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + int ret; + u32 nr_cpus_avail, nr_cpus_online; + + ret = do_read_u32(ff, &nr_cpus_avail); + if (ret) + return ret; + + ret = do_read_u32(ff, &nr_cpus_online); + if (ret) + return ret; + + /* + * Cap at 1M CPUs — generous for any real system but prevents + * stack overflow from VLA allocations sized by nr_cpus_avail + * (e.g. DECLARE_BITMAP in builtin-c2c.c node_entry()). + */ + if (nr_cpus_avail > (1U << 20)) { + pr_err("Invalid HEADER_NRCPUS: nr_cpus_avail (%u) exceeds maximum (%u)\n", + nr_cpus_avail, 1U << 20); + return -1; + } + + if (nr_cpus_online > nr_cpus_avail) { + pr_err("Invalid HEADER_NRCPUS: nr_cpus_online (%u) > nr_cpus_avail (%u)\n", + nr_cpus_online, nr_cpus_avail); + return -1; + } + + env->nr_cpus_avail = (int)nr_cpus_avail; + env->nr_cpus_online = (int)nr_cpus_online; + return 0; +} + +static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + u64 total_mem; + int ret; + + ret = do_read_u64(ff, &total_mem); + if (ret) + return -1; + env->total_mem = (unsigned long long)total_mem; + return 0; +} + +static struct evsel *evlist__find_by_index(struct evlist *evlist, int idx) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.idx == idx) + return evsel; + } + + return NULL; +} + +static void evlist__set_event_name(struct evlist *evlist, struct evsel *event) +{ + struct evsel *evsel; + + if (!event->name) + return; + + evsel = evlist__find_by_index(evlist, event->core.idx); + if (!evsel) + return; + + if (evsel->name) + return; + + evsel->name = strdup(event->name); +} + +static int +process_event_desc(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_session *session; + struct evsel *evsel, *events = read_event_desc(ff); + + if (!events) + return 0; + + session = container_of(ff->ph, struct perf_session, header); + + 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; +} + +/* + * Some arbitrary max for the number of command line arguments, + * Wildcards can expand and end up with tons of command line args. + */ +#define MAX_CMDLINE_NR 1048576 + +static int process_cmdline(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + char *str, *cmdline = NULL, **argv = NULL; + u32 nr, i, len = 0; + + if (do_read_u32(ff, &nr)) + return -1; + + if (nr > MAX_CMDLINE_NR) + return -1; + + env->nr_cmdline = nr; + + cmdline = zalloc(ff->size + nr + 1); + if (!cmdline) + return -1; + + argv = calloc(nr + 1, sizeof(char *)); + if (!argv) + goto error; + + for (i = 0; i < nr; i++) { + str = do_read_string(ff); + if (!str) + goto error; + + argv[i] = cmdline + len; + memcpy(argv[i], str, strlen(str) + 1); + len += strlen(str) + 1; + free(str); + } + env->cmdline = cmdline; + env->cmdline_argv = (const char **) argv; + return 0; + +error: + free(argv); + free(cmdline); + return -1; +} + +static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) +{ + u32 nr, i; + char *str = NULL; + struct strbuf sb; + struct perf_env *env = &ff->ph->env; + int cpu_nr = env->nr_cpus_avail; + u64 size = 0; + + if (cpu_nr == 0) { + pr_err("Invalid HEADER_CPU_TOPOLOGY: missing HEADER_NRCPUS\n"); + return -1; + } + + env->cpu = calloc(cpu_nr, sizeof(*env->cpu)); + if (!env->cpu) + return -1; + + if (do_read_u32(ff, &nr)) + goto free_cpu; + + if (nr > (u32)cpu_nr) { + pr_err("Invalid HEADER_CPU_TOPOLOGY: nr_sibling_cores (%u) > nr_cpus_avail (%d)\n", + nr, cpu_nr); + goto free_cpu; + } + + 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(ff); + if (!str) + goto error; + + /* 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_cores = strbuf_detach(&sb, NULL); + + if (do_read_u32(ff, &nr)) + goto free_cpu; + + if (nr > (u32)cpu_nr) { + pr_err("Invalid HEADER_CPU_TOPOLOGY: nr_sibling_threads (%u) > nr_cpus_avail (%d)\n", + nr, cpu_nr); + goto free_cpu; + } + + env->nr_sibling_threads = nr; + size += sizeof(u32); + + for (i = 0; i < nr; i++) { + str = do_read_string(ff); + if (!str) + goto error; + + /* 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)) + goto free_cpu; + + if (nr > (u32)cpu_nr) { + pr_err("Invalid HEADER_CPU_TOPOLOGY: nr_sibling_dies (%u) > nr_cpus_avail (%d)\n", + nr, cpu_nr); + goto free_cpu; + } + + env->nr_sibling_dies = nr; + size += sizeof(u32); + + for (i = 0; i < nr; i++) { + str = do_read_string(ff); + if (!str) + goto error; + + /* 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_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; + } + + return 0; + +error: + strbuf_release(&sb); + zfree(&str); +free_cpu: + zfree(&env->cpu); + return -1; +} + +static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + struct numa_node *nodes, *n; + u32 nr, i; + char *str; + + /* nr nodes */ + if (do_read_u32(ff, &nr)) + return -1; + + if (nr > MAX_NUMA_NODES) { + pr_err("Invalid HEADER_NUMA_TOPOLOGY: nr_nodes (%u) > %u\n", + nr, MAX_NUMA_NODES); + return -1; + } + + if (ff->size < sizeof(u32) + nr * (sizeof(u32) + 2 * sizeof(u64))) { + pr_err("Invalid HEADER_NUMA_TOPOLOGY: section too small (%zu) for %u nodes\n", + ff->size, nr); + return -1; + } + + nodes = calloc(nr, sizeof(*nodes)); + if (!nodes) + return -ENOMEM; + + for (i = 0; i < nr; i++) { + n = &nodes[i]; + + /* node number */ + if (do_read_u32(ff, &n->node)) + goto error; + + if (do_read_u64(ff, &n->mem_total)) + goto error; + + if (do_read_u64(ff, &n->mem_free)) + goto error; + + str = do_read_string(ff); + if (!str) + goto error; + + n->map = perf_cpu_map__new(str); + free(str); + if (!n->map) + goto error; + } + env->nr_numa_nodes = nr; + env->numa_nodes = nodes; + return 0; + +error: + free(nodes); + return -1; +} + +static int process_pmu_mappings(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + char *name; + u32 pmu_num; + u32 type; + struct strbuf sb; + + if (do_read_u32(ff, &pmu_num)) + return -1; + + if (!pmu_num) { + pr_debug("pmu mappings not available\n"); + return 0; + } + + if (pmu_num > MAX_PMU_MAPPINGS) { + pr_err("Invalid HEADER_PMU_MAPPINGS: pmu_num (%u) > %u\n", + pmu_num, MAX_PMU_MAPPINGS); + return -1; + } + + if (ff->size < sizeof(u32) + pmu_num * 2 * sizeof(u32)) { + pr_err("Invalid HEADER_PMU_MAPPINGS: section too small (%zu) for %u PMUs\n", + ff->size, pmu_num); + return -1; + } + + env->nr_pmu_mappings = pmu_num; + if (strbuf_init(&sb, 128) < 0) + return -1; + + while (pmu_num) { + if (do_read_u32(ff, &type)) + goto error; + + name = do_read_string(ff); + if (!name) + goto error; + + if (strbuf_addf(&sb, "%u:%s", type, name) < 0) + goto error; + /* include a NULL character at the end */ + if (strbuf_add(&sb, "", 1) < 0) + goto error; + + if (!strcmp(name, "msr")) + env->msr_pmu_type = type; + + free(name); + pmu_num--; + } + /* 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: + strbuf_release(&sb); + return -1; +} + +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 evsel *evsel, *leader = NULL; + struct group_desc { + char *name; + u32 leader_idx; + u32 nr_members; + } *desc; + + if (do_read_u32(ff, &nr_groups)) + return -1; + + if (!nr_groups) { + pr_debug("group desc not available\n"); + return 0; + } + + if (nr_groups > MAX_GROUP_DESC) { + pr_err("Invalid HEADER_GROUP_DESC: nr_groups (%u) > %u\n", + nr_groups, MAX_GROUP_DESC); + return -1; + } + + if (ff->size < sizeof(u32) + nr_groups * 3 * sizeof(u32)) { + pr_err("Invalid HEADER_GROUP_DESC: section too small (%zu) for %u groups\n", + ff->size, nr_groups); + return -1; + } + + env->nr_groups = nr_groups; + + desc = calloc(nr_groups, sizeof(*desc)); + if (!desc) + return -1; + + for (i = 0; i < nr_groups; i++) { + desc[i].name = do_read_string(ff); + if (!desc[i].name) + goto out_free; + + if (do_read_u32(ff, &desc[i].leader_idx)) + goto out_free; + + if (do_read_u32(ff, &desc[i].nr_members)) + goto out_free; + } + + /* + * Rebuild group relationship based on the group_desc + */ + session = container_of(ff->ph, struct perf_session, header); + + i = nr = 0; + 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}")) { + evsel->group_name = desc[i].name; + desc[i].name = NULL; + } + evsel->core.nr_members = desc[i].nr_members; + + if (i >= nr_groups || nr > 0) { + pr_debug("invalid group desc\n"); + goto out_free; + } + + leader = evsel; + nr = evsel->core.nr_members - 1; + i++; + } else if (nr) { + /* This is a group member */ + evsel__set_leader(evsel, leader); + + nr--; + } + } + + if (i != nr_groups || nr != 0) { + pr_debug("invalid group desc\n"); + goto out_free; + } + + ret = 0; +out_free: + for (i = 0; i < nr_groups; i++) + zfree(&desc[i].name); + free(desc); + + return ret; +} + +static int 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; + + if (cnt > MAX_CACHE_ENTRIES) { + pr_err("Invalid HEADER_CACHE: cnt (%u) > %u\n", + cnt, MAX_CACHE_ENTRIES); + return -1; + } + + if (ff->size < 2 * sizeof(u32) + cnt * 7 * sizeof(u32)) { + pr_err("Invalid HEADER_CACHE: section too small (%zu) for %u entries\n", + ff->size, cnt); + return -1; + } + + caches = calloc(cnt, sizeof(*caches)); + 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_cln_size(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + + if (do_read_u32(ff, &env->cln_size)) + return -1; + + return 0; +} + +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; + + evlist__set_first_sample_time(session->evlist, first_sample_time); + evlist__set_last_sample_time(session->evlist, 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; + + if (nr > MAX_NUMA_NODES) { + pr_err("Invalid HEADER_MEM_TOPOLOGY: nr_nodes (%llu) > %u\n", + (unsigned long long)nr, MAX_NUMA_NODES); + return -1; + } + + /* Per node: node_id(u64) + mem_size(u64) + bitmap_nr_bits(u64) */ + if (ff->size < 3 * sizeof(u64) + nr * 3 * sizeof(u64)) { + pr_err("Invalid HEADER_MEM_TOPOLOGY: section too small (%zu) for %llu nodes\n", + ff->size, (unsigned long long)nr); + return -1; + } + + nodes = calloc(nr, sizeof(*nodes)); + 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) + memory_node__delete_nodes(nodes, nr); + 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; + + if (nr > MAX_PMU_MAPPINGS) { + pr_err("Invalid HEADER_HYBRID_TOPOLOGY: nr_nodes (%u) > %u\n", + nr, MAX_PMU_MAPPINGS); + return -1; + } + + if (ff->size < sizeof(u32) + nr * 2 * sizeof(u32)) { + pr_err("Invalid HEADER_HYBRID_TOPOLOGY: section too small (%zu) for %u nodes\n", + ff->size, nr); + return -1; + } + + nodes = calloc(nr, sizeof(*nodes)); + 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); +} + +static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data __maybe_unused) +{ +#ifdef HAVE_LIBBPF_SUPPORT + 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; + + if (count > MAX_BPF_PROGS) { + pr_err("Invalid HEADER_BPF_PROG_INFO: count (%u) > %u\n", + count, MAX_BPF_PROGS); + return -1; + } + + if (ff->size < sizeof(u32) + count * (2 * sizeof(u32) + sizeof(u64))) { + pr_err("Invalid HEADER_BPF_PROG_INFO: section too small (%zu) for %u entries\n", + ff->size, 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; + } + + if (data_len > MAX_BPF_DATA_LEN) { + pr_warning("Invalid HEADER_BPF_PROG_INFO: data_len (%u) too large\n", + data_len); + 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; +#else + /* Not an error — the feature is simply unsupported in this build */ + pr_debug("BPF prog info present but libbpf not available, skipping.\n"); + return 0; +#endif // HAVE_LIBBPF_SUPPORT +} + +static int process_bpf_btf(struct feat_fd *ff __maybe_unused, void *data __maybe_unused) +{ +#ifdef HAVE_LIBBPF_SUPPORT + 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; + + if (count > MAX_BPF_PROGS) { + pr_err("bpf btf count %u too large (max %u)\n", count, MAX_BPF_PROGS); + return -1; + } + + if (ff->size < sizeof(u32) + count * 2 * sizeof(u32)) { + pr_err("Invalid HEADER_BPF_BTF: section too small (%zu) for %u entries\n", + ff->size, 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; + + if (data_size > MAX_BPF_DATA_LEN) { + pr_err("bpf btf data size %u too large (max %u)\n", + data_size, MAX_BPF_DATA_LEN); + 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; +#else + /* Not an error — the feature is simply unsupported in this build */ + pr_debug("BTF data present but libbpf not available, skipping.\n"); + return 0; +#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; + + /* + * FIXME: perf.data should record the recording system's page + * size — it affects mmap buffer alignment, sample addresses, + * and data_page_size/code_page_size interpretation. Without + * it we assume 4K (the smallest Linux page size) as a safe + * minimum alignment for comp_mmap_len validation. + * + * No upper-bound cap: perf_session__process_compressed_event() + * checks decomp_len + sizeof(struct decomp) against SIZE_MAX + * before allocating, which handles 32-bit safety. + */ + if (env->comp_mmap_len < 4096 || env->comp_mmap_len % 4096) { + pr_err("Invalid HEADER_COMPRESSED: comp_mmap_len (%u) must be a 4K-aligned value >= 4096\n", + 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; + + if (nr_pmu_caps > MAX_PMU_CAPS) { + pr_err("Invalid pmu caps: nr_pmu_caps (%u) > %u\n", + nr_pmu_caps, MAX_PMU_CAPS); + return -1; + } + + *caps = calloc(nr_pmu_caps, sizeof(char *)); + 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); + + 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; + } + + if (nr_pmu > MAX_PMU_MAPPINGS) { + pr_err("Invalid HEADER_PMU_CAPS: nr_pmu (%u) > %u\n", + nr_pmu, MAX_PMU_MAPPINGS); + return -1; + } + + if (ff->size < sizeof(u32) + nr_pmu * sizeof(u32)) { + pr_err("Invalid HEADER_PMU_CAPS: section too small (%zu) for %u PMUs\n", + ff->size, nr_pmu); + return -1; + } + + pmu_caps = calloc(nr_pmu, sizeof(*pmu_caps)); + 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; +} + +static int process_cpu_domain_info(struct feat_fd *ff, void *data __maybe_unused) +{ + u32 schedstat_version, max_sched_domains, cpu, domain, nr_domains; + struct perf_env *env = &ff->ph->env; + char *dname, *cpumask, *cpulist; + struct cpu_domain_map **cd_map; + struct domain_info *d_info; + u32 nra, nr, i, j; + int ret; + + nra = env->nr_cpus_avail; + nr = env->nr_cpus_online; + + if (nra == 0 || nr == 0) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: missing HEADER_NRCPUS\n"); + return -1; + } + + if (ff->size < 2 * sizeof(u32) + nr * 2 * sizeof(u32)) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: section too small (%zu) for %u CPUs\n", + (size_t)ff->size, nr); + return -1; + } + + cd_map = calloc(nra, sizeof(*cd_map)); + if (!cd_map) + return -1; + + env->cpu_domain = cd_map; + + ret = do_read_u32(ff, &schedstat_version); + if (ret) + return ret; + + env->schedstat_version = schedstat_version; + + ret = do_read_u32(ff, &max_sched_domains); + if (ret) + return ret; + + /* + * Sanity check: real systems have at most ~10 sched domain levels + * (SMT, CLS, MC, PKG + NUMA hops). Reject obviously bogus values + * from malformed perf.data files before they cause excessive + * allocation in the per-CPU loop. + */ + if (max_sched_domains > MAX_SCHED_DOMAINS) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: max_sched_domains %u > %u\n", + max_sched_domains, MAX_SCHED_DOMAINS); + return -1; + } + + env->max_sched_domains = max_sched_domains; + + for (i = 0; i < nr; i++) { + if (do_read_u32(ff, &cpu)) + return -1; + + if (cpu >= nra) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: cpu %d >= nr_cpus_avail (%d)\n", cpu, nra); + return -1; + } + + if (cd_map[cpu]) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: duplicate cpu %u\n", cpu); + return -1; + } + + cd_map[cpu] = zalloc(sizeof(*cd_map[cpu])); + if (!cd_map[cpu]) + return -1; + + cd_map[cpu]->cpu = cpu; + + if (do_read_u32(ff, &nr_domains)) + return -1; + + if (nr_domains > max_sched_domains) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: nr_domains %u > max_sched_domains (%u)\n", + nr_domains, max_sched_domains); + return -1; + } + + cd_map[cpu]->nr_domains = nr_domains; + + cd_map[cpu]->domains = calloc(max_sched_domains, sizeof(*d_info)); + if (!cd_map[cpu]->domains) + return -1; + + for (j = 0; j < nr_domains; j++) { + if (do_read_u32(ff, &domain)) + return -1; + + if (domain >= max_sched_domains) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: domain %d >= max_sched_domains (%d)\n", + domain, max_sched_domains); + return -1; + } + + d_info = zalloc(sizeof(*d_info)); + if (!d_info) + return -1; + + if (cd_map[cpu]->domains[domain]) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: duplicate domain %u for cpu %u\n", + domain, cpu); + free(d_info); + return -1; + } + + cd_map[cpu]->domains[domain] = d_info; + d_info->domain = domain; + + if (schedstat_version >= 17) { + dname = do_read_string(ff); + if (!dname) + return -1; + + d_info->dname = dname; + } + + cpumask = do_read_string(ff); + if (!cpumask) + return -1; + + d_info->cpumask = cpumask; + + cpulist = do_read_string(ff); + if (!cpulist) + return -1; + + d_info->cpulist = cpulist; + } + } + + 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 + +#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] = { + FEAT_OPN(TRACING_DATA, tracing_data, false), + 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), + FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, false), + FEAT_OPR(BPF_BTF, bpf_btf, false), + 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), + FEAT_OPR(CPU_DOMAIN_INFO, cpu_domain_info, true), + FEAT_OPR(E_MACHINE, e_machine, false), + FEAT_OPR(CLN_SIZE, cln_size, false), +}; + +struct header_print_data { + FILE *fp; + bool full; /* extended list of headers */ +}; + +const char *header_feat__name(unsigned int id) +{ + if (id < HEADER_LAST_FEATURE) + return feat_ops[id].name ?: "INVALID"; + return "INVALID"; +} + +static int perf_file_section__fprintf_info(struct perf_file_section *section, + struct perf_header *ph, + int feat, int fd, void *data) +{ + struct header_print_data *hd = data; + struct feat_fd ff; + + if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { + pr_debug("Failed to lseek to %" PRIu64 " offset for feature %s (%d), continuing...\n", + section->offset, header_feat__name(feat), feat); + return 0; + } + if (feat >= ph->last_feat) { + pr_warning("unknown feature %d\n", feat); + return 0; + } + if (!feat_ops[feat].print) + return 0; + + ff = (struct feat_fd) { + .fd = fd, + .ph = ph, + .size = section->size, + }; + + if (!feat_ops[feat].full_only || hd->full) + feat_ops[feat].print(&ff, hd->fp); + else + fprintf(hd->fp, "# %s info available, use -I to display\n", + feat_ops[feat].name); + + return 0; +} + +int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) +{ + struct header_print_data hd; + struct perf_header *header = &session->header; + int fd = 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_feat) { + if (bit) + fprintf(fp, "%s ", feat_ops[bit].name); + } + + fprintf(fp, "\n"); + return 0; +} + +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 evlist *evlist, + struct feat_copier *fc) +{ + int err; + int ret = 0; + + if (perf_header__has_feat(ff->ph, type)) { + if (!feat_ops[type].write) + return -1; + + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + + (*p)->offset = lseek(ff->fd, 0, SEEK_CUR); + + /* + * 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 %s\n", feat_ops[type].name); + + /* undo anything written */ + lseek(ff->fd, (*p)->offset, SEEK_SET); + + return -1; + } + (*p)->size = lseek(ff->fd, 0, SEEK_CUR) - (*p)->offset; + (*p)++; + } + return ret; +} + +static int perf_header__adds_write(struct perf_header *header, + 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; + int feat; + int err; + + nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); + if (!nr_sections) + return 0; + + feat_sec = p = calloc(nr_sections, sizeof(*feat_sec)); + if (feat_sec == NULL) + return -ENOMEM; + + sec_size = sizeof(*feat_sec) * nr_sections; + + 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(&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 missing entries + */ + 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; +} + +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){ + .magic = PERF_MAGIC, + .size = 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; +} + +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_header *header = &session->header; + struct evsel *evsel; + struct feat_fd ff = { + .ph = header, + .fd = fd, + }; + u64 attr_offset = sizeof(f_header), attr_size = 0; + int 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); + } + + 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; + } + } + attr_offset += evsel->core.ids * sizeof(u64); + } + + 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); + } + + 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 (!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) + goto err_out; + } + + f_header = (struct perf_file_header){ + .magic = PERF_MAGIC, + .size = sizeof(f_header), + .attr_size = sizeof(struct perf_file_attr), + .attrs = { + .offset = attr_offset, + .size = attr_size, + }, + .data = { + .offset = header->data_offset, + .size = header->data_size, + }, + /* event_types is ignored, store zeros */ + }; + + memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features)); + + lseek(fd, 0, SEEK_SET); + err = do_write(&ff, &f_header, sizeof(f_header)); + if (err < 0) { + pr_debug("failed to write perf header\n"); + goto err_out; + } else { + lseek(fd, 0, SEEK_END); + err = 0; + } +err_out: + free(ff.buf); + return err; +} + +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(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__nr_entries(evlist) * 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, + int fd, void *buf, size_t size) +{ + ssize_t n = readn(fd, buf, size); + + if (n <= 0) { + if (n == 0) + errno = EIO; + return -1; + } + + if (header->needs_swap) + mem_bswap_64(buf, size); + + return 0; +} + +int perf_header__process_sections(struct perf_header *header, int fd, + void *data, + int (*process)(struct perf_file_section *section, + struct perf_header *ph, + int feat, int fd, void *data)) +{ + struct perf_file_section *feat_sec, *sec; + int nr_sections; + int sec_size; + int feat; + int err; + struct stat st; + + nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); + if (!nr_sections) + return 0; + + feat_sec = sec = calloc(nr_sections, sizeof(*feat_sec)); + if (!feat_sec) + return -1; + + sec_size = sizeof(*feat_sec) * nr_sections; + + lseek(fd, header->feat_offset, SEEK_SET); + + err = perf_header__getbuffer64(header, fd, feat_sec, sec_size); + if (err < 0) + goto out_free; + + if (fstat(fd, &st) < 0) { + pr_err("Failed to stat the perf data file\n"); + err = -1; + goto out_free; + } + + for_each_set_bit(feat, header->adds_features, header->last_feat) { + /* + * FIXME: block devices have st_size == 0, so we skip + * bounds checking entirely. Historically perf never + * prevented using a block device as input, but it + * probably should — there's no valid use case for it + * and it bypasses all file-size validation. + */ + if (S_ISREG(st.st_mode) && + (sec->offset > (u64)st.st_size || + sec->size > (u64)st.st_size - sec->offset)) { + pr_err("Feature %s (%d) section extends past EOF (offset=%" PRIu64 ", size=%" PRIu64 ", file=%" PRIu64 ")\n", + header_feat__name(feat), feat, + sec->offset, sec->size, (u64)st.st_size); + err = -1; + goto out_free; + } + err = process(sec++, header, feat, fd, data); + if (err < 0) + goto out_free; + } + err = 0; +out_free: + free(feat_sec); + return err; +} + +static const int attr_file_abi_sizes[] = { + [0] = PERF_ATTR_SIZE_VER0, + [1] = PERF_ATTR_SIZE_VER1, + [2] = PERF_ATTR_SIZE_VER2, + [3] = PERF_ATTR_SIZE_VER3, + [4] = PERF_ATTR_SIZE_VER4, + 0, +}; + +/* + * In the legacy file format, the magic number is not used to encode endianness. + * hdr_sz was used to encode endianness. But given that hdr_sz can vary based + * on ABI revisions, we need to try all combinations for all endianness to + * detect the endianness. + */ +static int try_all_file_abis(uint64_t hdr_sz, struct perf_header *ph) +{ + uint64_t ref_size, attr_size; + int i; + + for (i = 0 ; attr_file_abi_sizes[i]; i++) { + ref_size = attr_file_abi_sizes[i] + + sizeof(struct perf_file_section); + if (hdr_sz != ref_size) { + attr_size = bswap_64(hdr_sz); + if (attr_size != ref_size) + continue; + + ph->needs_swap = true; + } + pr_debug("ABI%d perf.data file detected, need_swap=%d\n", + i, + ph->needs_swap); + return 0; + } + /* could not determine endianness */ + return -1; +} + +#define PERF_PIPE_HDR_VER0 16 + +static const size_t attr_pipe_abi_sizes[] = { + [0] = PERF_PIPE_HDR_VER0, + 0, +}; + +/* + * In the legacy pipe format, there is an implicit assumption that 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 revisions in the perf tool itself. + */ +static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph) +{ + u64 attr_size; + int i; + + for (i = 0 ; attr_pipe_abi_sizes[i]; i++) { + if (hdr_sz != attr_pipe_abi_sizes[i]) { + attr_size = bswap_64(hdr_sz); + if (attr_size != hdr_sz) + continue; + + ph->needs_swap = true; + } + pr_debug("Pipe ABI%d perf.data file detected\n", i); + return 0; + } + return -1; +} + +bool is_perf_magic(u64 magic) +{ + if (!memcmp(&magic, __perf_magic1, sizeof(magic)) + || magic == __perf_magic2 + || magic == __perf_magic2_sw) + return true; + + return false; +} + +static int check_magic_endian(u64 magic, uint64_t hdr_sz, + bool is_pipe, struct perf_header *ph) +{ + int ret; + + /* check for legacy format */ + ret = memcmp(&magic, __perf_magic1, sizeof(magic)); + if (ret == 0) { + ph->version = PERF_HEADER_VERSION_1; + pr_debug("legacy perf.data format\n"); + if (is_pipe) + return try_all_pipe_abis(hdr_sz, ph); + + return try_all_file_abis(hdr_sz, ph); + } + /* + * the new magic number serves two purposes: + * - 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) + return 0; + + /* check magic number with opposite endianness */ + if (magic != __perf_magic2_sw) + return -1; + + ph->needs_swap = true; + + return 0; +} + +int perf_file_header__read(struct perf_file_header *header, + struct perf_header *ph, int fd) +{ + ssize_t ret; + + lseek(fd, 0, SEEK_SET); + + ret = readn(fd, header, sizeof(*header)); + if (ret <= 0) + return -1; + + if (check_magic_endian(header->magic, + header->attr_size, false, ph) < 0) { + pr_debug("magic/endian check failed\n"); + return -1; + } + + if (ph->needs_swap) { + mem_bswap_64(header, offsetof(struct perf_file_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)) + bitmap_zero(header->adds_features, HEADER_FEAT_BITS); + else + return -1; + } else if (ph->needs_swap) { + /* + * feature bitmap is declared as an array of unsigned longs -- + * not good since its size can differ between the host that + * generated the data file and the host analyzing the file. + * + * We need to handle endianness, but we don't know the size of + * the unsigned long where the file was generated. Take a best + * guess at determining it: try 64-bit swap first (ie., file + * created on a 64-bit host), and check if the hostname feature + * bit is set (this feature bit is forced on as of fbe96f2). + * If the bit is not, undo the 64-bit swap and try a 32-bit + * swap. If the hostname bit is still not set (e.g., older data + * file), punt and fallback to the original behavior -- + * clearing all feature bits and setting buildid. + */ + mem_bswap_64(&header->adds_features, + BITS_TO_U64(HEADER_FEAT_BITS)); + + if (!test_bit(HEADER_HOSTNAME, header->adds_features)) { + /* unswap as u64 */ + mem_bswap_64(&header->adds_features, + BITS_TO_U64(HEADER_FEAT_BITS)); + + /* unswap as u32 */ + mem_bswap_32(&header->adds_features, + BITS_TO_U32(HEADER_FEAT_BITS)); + } + + if (!test_bit(HEADER_HOSTNAME, header->adds_features)) { + bitmap_zero(header->adds_features, HEADER_FEAT_BITS); + __set_bit(HEADER_BUILD_ID, header->adds_features); + } + } + + memcpy(&ph->adds_features, &header->adds_features, + sizeof(ph->adds_features)); + + ph->data_offset = header->data.offset; + ph->data_size = header->data.size; + ph->feat_offset = header->data.offset + header->data.size; + ph->last_feat = HEADER_LAST_FEATURE; + return 0; +} + +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 = 0, + }; + + if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { + pr_debug("Failed to lseek to %" PRIu64 " offset for feature %s (%d), continuing...\n", + section->offset, header_feat__name(feat), feat); + return 0; + } + + if (feat >= HEADER_LAST_FEATURE) { + pr_debug("unknown feature %d, continuing...\n", feat); + return 0; + } + + if (!feat_ops[feat].process) + return 0; + + return feat_ops[feat].process(&fdd, data); +} + +static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, + struct perf_header *ph, + struct perf_data *data) +{ + ssize_t ret; + + ret = perf_data__read(data, header, sizeof(*header)); + if (ret <= 0) + return -1; + + if (check_magic_endian(header->magic, header->size, true, ph) < 0) { + pr_debug("endian/magic failed\n"); + return -1; + } + + if (ph->needs_swap) + header->size = bswap_64(header->size); + + /* The last feature is written out as a 0 sized event and will update this value. */ + ph->last_feat = 0; + return 0; +} + +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, session->data) < 0) { + pr_debug("incompatible file format\n"); + return -EINVAL; + } + + return f_header.size == sizeof(f_header) ? 0 : -1; +} + +static int read_attr(int fd, struct perf_header *ph, + struct perf_file_attr *f_attr) +{ + struct perf_event_attr *attr = &f_attr->attr; + size_t sz, left; + size_t our_sz = sizeof(f_attr->attr); + ssize_t ret; + + memset(f_attr, 0, sizeof(*f_attr)); + + /* read minimal guaranteed structure */ + ret = readn(fd, attr, PERF_ATTR_SIZE_VER0); + if (ret <= 0) { + pr_debug("cannot read %d bytes of header attr\n", + PERF_ATTR_SIZE_VER0); + if (ret == 0) + errno = EIO; + return -1; + } + + /* on file perf_event_attr size */ + sz = attr->size; + + if (ph->needs_swap) + sz = bswap_32(sz); + + if (sz == 0) { + /* assume ABI0 */ + sz = PERF_ATTR_SIZE_VER0; + } else if (sz < PERF_ATTR_SIZE_VER0) { + pr_debug("bad attr size %zu, expected at least %d\n", + sz, PERF_ATTR_SIZE_VER0); + errno = EINVAL; + return -1; + } else if (sz > our_sz) { + pr_debug("file uses a more recent and unsupported ABI" + " (%zu bytes extra)\n", sz - our_sz); + errno = EINVAL; + return -1; + } + /* what we have not yet read and that we know about */ + left = sz - PERF_ATTR_SIZE_VER0; + if (left) { + void *ptr = attr; + ptr += PERF_ATTR_SIZE_VER0; + + ret = readn(fd, ptr, left); + if (ret <= 0) { + if (ret == 0) + errno = EIO; + return -1; + } + } + /* read perf_file_section, ids are read in caller */ + ret = readn(fd, &f_attr->ids, sizeof(f_attr->ids)); + if (ret <= 0) { + if (ret == 0) + errno = EIO; + return -1; + } + + return 0; +} + +#ifdef HAVE_LIBTRACEEVENT +static int evsel__prepare_tracepoint_event(struct evsel *evsel, struct tep_handle *pevent) +{ + struct tep_event *event; + char bf[128]; + + /* already prepared */ + if (evsel->tp_format) + return 0; + + if (pevent == NULL) { + pr_debug("broken or missing trace data\n"); + return -1; + } + + 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); + evsel->name = strdup(bf); + if (evsel->name == NULL) + return -1; + } + + evsel->tp_format = event; + return 0; +} + +static int evlist__prepare_tracepoint_events(struct evlist *evlist, struct tep_handle *pevent) +{ + struct evsel *pos; + + 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) +{ + 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; + struct stat input_stat; + int nr_attrs, nr_ids, i, j, err = -ENOMEM; + int fd = perf_data__fd(data); + + session->evlist = evlist__new(); + if (session->evlist == NULL) + return -ENOMEM; + + evlist__set_session(session->evlist, 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; + } + + err = -ENOMEM; + 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; + } + + if (fstat(fd, &input_stat) < 0) + return -errno; + + /* Check before assigning to int to avoid u64-to-int truncation */ + if (f_header.attrs.size / f_header.attr_size > MAX_NR_ATTRS) { + pr_err("Too many attributes: %" PRIu64 " (max %d)\n", + f_header.attrs.size / f_header.attr_size, MAX_NR_ATTRS); + 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 evsel *evsel; + off_t tmp; + + if (read_attr(fd, header, &f_attr) < 0) + goto out_errno; + + 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); + } + + /* + * Validate ids section: must be aligned to u64, and + * the count must fit in an int to avoid truncation in + * nr_ids and size_t overflow in perf_evsel__alloc_id() + * on 32-bit architectures. + */ + if (f_attr.ids.size % sizeof(u64)) { + pr_err("Invalid ids section size %" PRIu64 " for attr %d, not aligned to u64\n", + f_attr.ids.size, i); + err = -EINVAL; + goto out_put_evlist; + } + + /* + * Cap the ID count to avoid int truncation of nr_ids + * on 64-bit and size_t overflow in the allocation + * paths (nr_ids * sizeof(u64), nr_ids * + * sizeof(struct perf_sample_id)) on 32-bit. + */ + if (f_attr.ids.size / sizeof(u64) > MAX_IDS_PER_ATTR) { + pr_err("Invalid ids section size %" PRIu64 " for attr %d, too many IDs\n", + f_attr.ids.size, i); + err = -EINVAL; + goto out_put_evlist; + } + + /* + * FIXME: see perf_header__process_sections() — block + * devices bypass this check because st_size is 0. + */ + if (S_ISREG(input_stat.st_mode) && + (f_attr.ids.offset > (u64)input_stat.st_size || + f_attr.ids.size > (u64)input_stat.st_size - f_attr.ids.offset)) { + pr_err("Invalid ids section for attr %d: offset=%" PRIu64 " size=%" PRIu64 " exceeds file size %" PRIu64 "\n", + i, f_attr.ids.offset, f_attr.ids.size, (u64)input_stat.st_size); + err = -EINVAL; + goto out_put_evlist; + } + + tmp = lseek(fd, 0, SEEK_CUR); + evsel = evsel__new(&f_attr.attr); + + if (evsel == NULL) + goto out_put_evlist; + + evsel->needs_swap = header->needs_swap; + /* + * Do it before so that if perf_evsel__alloc_id fails, this + * entry gets purged too at evlist__put(). + */ + evlist__add(session->evlist, evsel); + + nr_ids = f_attr.ids.size / sizeof(u64); + /* + * We don't have the cpu and thread maps on the header, so + * for allocating the perf_sample_id table we fake 1 cpu and + * hattr->ids threads. + */ + if (perf_evsel__alloc_id(&evsel->core, 1, nr_ids)) + goto out_put_evlist; + + lseek(fd, f_attr.ids.offset, SEEK_SET); + + for (j = 0; j < nr_ids; j++) { + if (perf_header__getbuffer64(header, fd, &f_id, sizeof(f_id))) + goto out_errno; + + perf_evlist__id_add(evlist__core(session->evlist), + &evsel->core, 0, j, f_id); + } + + lseek(fd, tmp, SEEK_SET); + } + + /* + * Skip feature section processing for truncated files + * (data.size == 0 means recording was interrupted). The + * section table is unreliable in that case, and the event + * data can still be processed without the feature headers. + * Clear the bitmap so has_feat() returns false and tools + * use their "feature not present" fallbacks instead of + * accessing uninitialized env fields. + */ + if (f_header.data.size == 0) { + bitmap_zero(header->adds_features, HEADER_FEAT_BITS); + } else { +#ifdef HAVE_LIBTRACEEVENT + err = perf_header__process_sections(header, fd, &session->tevent, + perf_file_section__process); + if (err < 0) + goto out_put_evlist; + + if (evlist__prepare_tracepoint_events(session->evlist, + session->tevent.pevent)) { + err = -ENOMEM; + goto out_put_evlist; + } +#else + err = perf_header__process_sections(header, fd, NULL, + perf_file_section__process); + if (err < 0) + goto out_put_evlist; +#endif + } + + /* + * Without nr_cpus_avail the sample CPU bounds check in + * perf_session__deliver_event() is bypassed, allowing crafted + * CPU IDs to reach downstream consumers that index fixed-size + * arrays (timechart, kwork, sched — all sized MAX_NR_CPUS). + * + * This can happen with truncated files (interrupted recording + * loses all feature sections), very old files that predate + * HEADER_NRCPUS, or crafted files that omit it. Fall back to + * MAX_NR_CPUS so the bounds check is still effective — any + * CPU ID below that limit is safe for all downstream arrays. + */ + if (header->env.nr_cpus_avail == 0) { + header->env.nr_cpus_avail = MAX_NR_CPUS; + pr_warning("WARNING: perf.data is missing HEADER_NRCPUS, using MAX_NR_CPUS (%d) as CPU bound\n", + MAX_NR_CPUS); + } + + return 0; +out_errno: + return -errno; + +out_put_evlist: + evlist__put(session->evlist); + session->evlist = NULL; + return err; +} + +int perf_event__process_feature(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, + union perf_event *event) +{ + struct feat_fd ff = { .fd = 0 }; + struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event; + struct perf_header *header = &session->header; + int type = fe->header.type; + int feat = (int)fe->feat_id; + int ret = 0; + bool print = dump_trace; + bool last_feature_mark = false; + + 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) { + pr_warning("invalid reserved record type in pipe-mode\n"); + return -1; + } + if (feat < 0 || feat == INT_MAX) { + pr_warning("invalid value for feature type %x\n", feat); + return -1; + } + if (feat >= header->last_feat) { + if (event->header.size == sizeof(*fe)) { + /* + * Either an unexpected zero size feature or the + * HEADER_LAST_FEATURE mark. + */ + if (feat > header->last_feat) + header->last_feat = min(feat, HEADER_LAST_FEATURE); + last_feature_mark = true; + } else { + /* + * A feature but beyond what is known as in + * bounds. Assume the last feature is 1 beyond this + * feature. + */ + session->header.last_feat = min(feat + 1, HEADER_LAST_FEATURE); + } + } + if (feat >= HEADER_LAST_FEATURE) { + if (!last_feature_mark) { + pr_warning("unknown feature %d for data file version (%s) in this version of perf (%s)\n", + feat, header->env.version, perf_version_string); + } + return 0; + } + if (event->header.size < sizeof(*fe)) { + pr_warning("feature header size too small\n"); + return -1; + } + ff.buf = (void *)fe->data; + ff.size = event->header.size - sizeof(*fe); + ff.ph = header; + + if (feat_ops[feat].process && feat_ops[feat].process(&ff, NULL)) { + // Processing failed, ignore when this is the last feature mark. + if (!last_feature_mark) + ret = -1; + goto out; + } + + 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 (dump_trace) + printf(", "); + + if (print) { + if (feat_ops[feat].print) + feat_ops[feat].print(&ff, stdout); + else + printf("# %s", feat_ops[feat].name); + } + +out: + free_event_desc(ff.events); + return ret; +} + +size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) +{ + struct perf_record_event_update *ev = &event->event_update; + struct perf_cpu_map *map; + size_t ret; + + ret = fprintf(fp, "\n... id: %" PRI_lu64 "\n", ev->id); + + switch (ev->type) { + case PERF_EVENT_UPDATE__SCALE: + if (event->header.size < offsetof(struct perf_record_event_update, scale) + + sizeof(ev->scale)) { + ret += fprintf(fp, "... scale: (truncated)\n"); + break; + } + ret += fprintf(fp, "... scale: %f\n", ev->scale.scale); + break; + case PERF_EVENT_UPDATE__UNIT: + case PERF_EVENT_UPDATE__NAME: { + size_t str_off = offsetof(struct perf_record_event_update, unit); + size_t max_len = event->header.size > str_off ? + event->header.size - str_off : 0; + + if (max_len == 0 || strnlen(ev->unit, max_len) == max_len) { + ret += fprintf(fp, "... %s: (unterminated)\n", + ev->type == PERF_EVENT_UPDATE__UNIT ? "unit" : "name"); + break; + } + ret += fprintf(fp, "... %s: %s\n", + ev->type == PERF_EVENT_UPDATE__UNIT ? "unit" : "name", + ev->unit); + break; + } + case PERF_EVENT_UPDATE__CPUS: { + size_t cpus_off = offsetof(struct perf_record_event_update, cpus); + u32 cpus_payload; + + if (event->header.size < cpus_off + sizeof(__u16) + + sizeof(struct perf_record_range_cpu_map)) { + ret += fprintf(fp, "... cpus: (truncated)\n"); + break; + } + + /* + * Validate nr against payload — this function may be + * called from the stub handler (dump_trace path) which + * bypasses perf_event__process_event_update() validation. + */ + cpus_payload = event->header.size - cpus_off; + if (ev->cpus.cpus.type == PERF_CPU_MAP__CPUS) { + if (cpus_payload < offsetof(struct perf_record_cpu_map_data, cpus_data.cpu) || + ev->cpus.cpus.cpus_data.nr > + (cpus_payload - offsetof(struct perf_record_cpu_map_data, cpus_data.cpu)) / + sizeof(ev->cpus.cpus.cpus_data.cpu[0])) { + ret += fprintf(fp, "... cpus: nr %u exceeds payload\n", + ev->cpus.cpus.cpus_data.nr); + break; + } + } else if (ev->cpus.cpus.type == PERF_CPU_MAP__MASK) { + if (ev->cpus.cpus.mask32_data.long_size == 4) { + if (cpus_payload < offsetof(struct perf_record_cpu_map_data, mask32_data.mask) || + ev->cpus.cpus.mask32_data.nr > + (cpus_payload - offsetof(struct perf_record_cpu_map_data, mask32_data.mask)) / + sizeof(ev->cpus.cpus.mask32_data.mask[0])) { + ret += fprintf(fp, "... cpus: mask nr %u exceeds payload\n", + ev->cpus.cpus.mask32_data.nr); + break; + } + } else if (ev->cpus.cpus.mask64_data.long_size == 8) { + if (cpus_payload < offsetof(struct perf_record_cpu_map_data, mask64_data.mask) || + ev->cpus.cpus.mask64_data.nr > + (cpus_payload - offsetof(struct perf_record_cpu_map_data, mask64_data.mask)) / + sizeof(ev->cpus.cpus.mask64_data.mask[0])) { + ret += fprintf(fp, "... cpus: mask nr %u exceeds payload\n", + ev->cpus.cpus.mask64_data.nr); + break; + } + } + } + + 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 ret; +} + +size_t perf_event__fprintf_attr(union perf_event *event, FILE *fp) +{ + 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) +{ + struct perf_event_attr attr; + u32 i, n_ids, raw_attr_size; + u64 *ids; + size_t attr_size, copy_size; + struct evsel *evsel; + struct evlist *evlist = *pevlist; + + /* + * HEADER_ATTR event layout (pipe/inject mode): + * + * [header (8 bytes)] [attr (attr_size bytes)] [id0 id1 ... idN] + * |<------------------ header.size --------------------------->| + * + * attr_size varies across perf versions: VER0 = 64 bytes, + * current sizeof(struct perf_event_attr) = larger. A newer + * producer may emit a larger attr than we understand. + * + * attr.size == 0 (ABI0) means the producer didn't set it + * (e.g., bench/inject-buildid, older perf). Treat as VER0. + * + * Require 8-byte alignment so the u64 ID array is aligned + * and attr.size fits cleanly within the payload. + * + * Read attr.size once — the event may be on a shared mmap + * and re-reading could yield a different value. + */ + raw_attr_size = event->attr.attr.size; + if (event->header.size < sizeof(event->header) + PERF_ATTR_SIZE_VER0 || + (raw_attr_size && (raw_attr_size < PERF_ATTR_SIZE_VER0 || + raw_attr_size % sizeof(u64) || + raw_attr_size > event->header.size - sizeof(event->header)))) { + pr_err("PERF_RECORD_HEADER_ATTR: invalid attr.size %u (event size %u, min %d)\n", + raw_attr_size, event->header.size, PERF_ATTR_SIZE_VER0); + return -EINVAL; + } + + if (dump_trace) + perf_event__fprintf_attr(event, stdout); + + if (evlist == NULL) { + *pevlist = evlist = evlist__new(); + if (evlist == NULL) + return -ENOMEM; + } + + /* + * attr_size = footprint of the attr in the event — determines + * where the ID array starts. For ABI0, assume VER0 (64 bytes). + * + * copy_size = how much we copy into our local struct, capped at + * sizeof(attr) so a newer producer's larger attr doesn't + * overflow. Fields beyond copy_size are zeroed. + * + * Do NOT write attr_size back to the event — native-endian + * files use MAP_SHARED (read-only), writing would SIGSEGV. + * The swap path handles ABI0 in perf_event__attr_swap() + * which writes to the writable MAP_PRIVATE copy instead. + */ + attr_size = raw_attr_size ?: PERF_ATTR_SIZE_VER0; + copy_size = min(attr_size, sizeof(attr)); + memcpy(&attr, &event->attr.attr, copy_size); + if (copy_size < sizeof(attr)) + memset((void *)&attr + copy_size, 0, sizeof(attr) - copy_size); + + /* + * Normalize ABI0: the swap path sets attr.size = VER0 on the + * event, but the native path leaves it as 0. Set it on the + * local copy so perf inject re-synthesizes with consistent + * layout regardless of endianness. + */ + attr.size = attr_size; + + evsel = evsel__new(&attr); + if (evsel == NULL) + return -ENOMEM; + + evlist__add(evlist, evsel); + + /* + * IDs occupy the remainder after header + attr. Use attr_size + * (not copy_size) — even if the producer's attr is larger than + * our struct, the IDs start after attr_size bytes in the event. + * Validation above guarantees attr_size <= payload size. + */ + n_ids = event->header.size - sizeof(event->header) - 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->core, 1, n_ids)) + return -ENOMEM; + + /* + * Locate IDs at attr_size bytes past the attr start in the + * event. Cannot use perf_record_header_attr_id() — that + * macro reads event->attr.attr.size, which is 0 for ABI0 + * on the native-endian path (no swap handler to fix it up). + */ + ids = (void *)&event->attr.attr + attr_size; + for (i = 0; i < n_ids; i++) { + perf_evlist__id_add(evlist__core(evlist), &evsel->core, 0, i, ids[i]); + } + + return 0; +} + +int perf_event__process_event_update(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct evlist **pevlist) +{ + struct perf_record_event_update *ev = &event->event_update; + struct evlist *evlist; + struct evsel *evsel; + struct perf_cpu_map *map; + + /* + * Validate payload before dump_trace or processing — both + * paths access variant-specific fields without further checks. + */ + if (ev->type == PERF_EVENT_UPDATE__UNIT || + ev->type == PERF_EVENT_UPDATE__NAME) { + size_t str_off = offsetof(struct perf_record_event_update, unit); + size_t max_len = event->header.size > str_off ? + event->header.size - str_off : 0; + + if (max_len == 0 || strnlen(ev->unit, max_len) == max_len) { + pr_warning("WARNING: PERF_RECORD_EVENT_UPDATE: %s not null-terminated, skipping\n", + ev->type == PERF_EVENT_UPDATE__UNIT ? "unit" : "name"); + return 0; + } + } else if (ev->type == PERF_EVENT_UPDATE__SCALE) { + if (event->header.size < offsetof(struct perf_record_event_update, scale) + + sizeof(ev->scale)) { + pr_warning("WARNING: PERF_RECORD_EVENT_UPDATE: SCALE payload too small, skipping\n"); + return 0; + } + } else if (ev->type == PERF_EVENT_UPDATE__CPUS) { + size_t cpus_off = offsetof(struct perf_record_event_update, cpus); + size_t min_cpus = sizeof(__u16) + + sizeof(struct perf_record_range_cpu_map); + u32 cpus_payload; + + if (event->header.size < cpus_off + min_cpus) { + pr_warning("WARNING: PERF_RECORD_EVENT_UPDATE: CPUS payload too small, skipping\n"); + return 0; + } + + /* + * Validate per-variant nr against the remaining + * payload on the native path — the swap path clamps + * nr in perf_event__event_update_swap(), but native + * events are read-only and cannot be clamped in place. + * cpu_map__new_data() trusts nr for allocation and + * iteration, so unchecked values cause OOB reads. + */ + cpus_payload = event->header.size - cpus_off; + switch (ev->cpus.cpus.type) { + case PERF_CPU_MAP__CPUS: + if (ev->cpus.cpus.cpus_data.nr > + (cpus_payload - offsetof(struct perf_record_cpu_map_data, cpus_data.cpu)) / + sizeof(ev->cpus.cpus.cpus_data.cpu[0])) { + pr_warning("WARNING: EVENT_UPDATE CPUS: nr %u exceeds payload, skipping\n", + ev->cpus.cpus.cpus_data.nr); + return 0; + } + break; + case PERF_CPU_MAP__MASK: + if (ev->cpus.cpus.mask32_data.long_size == 4) { + if (cpus_payload < offsetof(struct perf_record_cpu_map_data, mask32_data.mask) || + ev->cpus.cpus.mask32_data.nr > + (cpus_payload - offsetof(struct perf_record_cpu_map_data, mask32_data.mask)) / + sizeof(ev->cpus.cpus.mask32_data.mask[0])) { + pr_warning("WARNING: EVENT_UPDATE MASK: nr %u exceeds payload, skipping\n", + ev->cpus.cpus.mask32_data.nr); + return 0; + } + } else if (ev->cpus.cpus.mask64_data.long_size == 8) { + if (cpus_payload < offsetof(struct perf_record_cpu_map_data, mask64_data.mask) || + ev->cpus.cpus.mask64_data.nr > + (cpus_payload - offsetof(struct perf_record_cpu_map_data, mask64_data.mask)) / + sizeof(ev->cpus.cpus.mask64_data.mask[0])) { + pr_warning("WARNING: EVENT_UPDATE MASK: nr %u exceeds payload, skipping\n", + ev->cpus.cpus.mask64_data.nr); + return 0; + } + } + break; + default: + break; + } + } + + if (dump_trace) + perf_event__fprintf_event_update(event, stdout); + + if (!pevlist || *pevlist == NULL) + return -EINVAL; + + evlist = *pevlist; + + evsel = evlist__id2evsel(evlist, ev->id); + if (evsel == NULL) + return -EINVAL; + + 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"); + break; + default: + break; + } + + return 0; +} + +#ifdef HAVE_LIBTRACEEVENT +int perf_event__process_tracing_data(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, + union perf_event *event) +{ + ssize_t size_read, padding, size = event->tracing_data.size; + int fd = perf_data__fd(session->data); + char buf[BUFSIZ]; + + /* + * 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. + */ + if (!perf_data__is_pipe(session->data)) { + off_t offset = lseek(fd, 0, SEEK_CUR); + + /* setup for reading amidst mmap */ + lseek(fd, offset + sizeof(struct perf_record_header_tracing_data), + SEEK_SET); + } + + size_read = trace_report(fd, &session->tevent, session->trace_event_repipe); + padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read; + + if (readn(fd, buf, padding) < 0) { + pr_err("%s: reading input file", __func__); + return -1; + } + 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__); + return -1; + } + } + + if (size_read + padding != size) { + pr_err("%s: tracing data size mismatch", __func__); + return -1; + } + + evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent); + + return size_read + padding; +} +#endif + +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; +} -- cgit v1.3.1