return NULL;
}
-static const char *__perf_magic = "PERFFILE";
+/*
+ * 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 (*(u64 *)__perf_magic)
+#define PERF_MAGIC __perf_magic2
struct perf_file_attr {
struct perf_event_attr attr;
return do_write_string(fd, buffer);
}
+static int write_branch_stack(int fd __used, struct perf_header *h __used,
+ struct perf_evlist *evlist __used)
+{
+ return 0;
+}
+
static void print_hostname(struct perf_header *ph, int fd, FILE *fp)
{
char *str = do_read_string(fd, ph);
uint64_t id;
void *buf = NULL;
char *str;
- u32 nre, sz, nr, i, j, msz;
- int ret;
+ u32 nre, sz, nr, i, j;
+ ssize_t ret;
+ size_t msz;
/* number of events */
ret = read(fd, &nre, sizeof(nre));
if (ph->needs_swap)
sz = bswap_32(sz);
- /*
- * ensure it is at least to our ABI rev
- */
- if (sz < (u32)sizeof(attr))
- goto error;
-
memset(&attr, 0, sizeof(attr));
- /* read entire region to sync up to next field */
+ /* buffer to hold on file attr struct */
buf = malloc(sz);
if (!buf)
goto error;
msz = sizeof(attr);
- if (sz < msz)
+ if (sz < (ssize_t)msz)
msz = sz;
for (i = 0 ; i < nre; i++) {
+ /*
+ * must read entire on-file attr struct to
+ * sync up with layout.
+ */
ret = read(fd, buf, sz);
if (ret != (ssize_t)sz)
goto error;
free(str);
}
+static void print_branch_stack(struct perf_header *ph __used, int fd __used,
+ FILE *fp)
+{
+ fprintf(fp, "# contains samples with branch stack\n");
+}
+
+static int __event_process_build_id(struct build_id_event *bev,
+ char *filename,
+ struct perf_session *session)
+{
+ int err = -1;
+ struct list_head *head;
+ struct machine *machine;
+ u16 misc;
+ struct dso *dso;
+ enum dso_kernel_type dso_type;
+
+ machine = perf_session__findnew_machine(session, bev->pid);
+ if (!machine)
+ goto out;
+
+ misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+ switch (misc) {
+ case PERF_RECORD_MISC_KERNEL:
+ dso_type = DSO_TYPE_KERNEL;
+ head = &machine->kernel_dsos;
+ break;
+ case PERF_RECORD_MISC_GUEST_KERNEL:
+ dso_type = DSO_TYPE_GUEST_KERNEL;
+ head = &machine->kernel_dsos;
+ break;
+ case PERF_RECORD_MISC_USER:
+ case PERF_RECORD_MISC_GUEST_USER:
+ dso_type = DSO_TYPE_USER;
+ head = &machine->user_dsos;
+ break;
+ default:
+ goto out;
+ }
+
+ dso = __dsos__findnew(head, filename);
+ if (dso != NULL) {
+ char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+ dso__set_build_id(dso, &bev->build_id);
+
+ if (filename[0] == '[')
+ dso->kernel = dso_type;
+
+ build_id__sprintf(dso->build_id, sizeof(dso->build_id),
+ sbuild_id);
+ pr_debug("build id event received for %s: %s\n",
+ dso->long_name, sbuild_id);
+ }
+
+ 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[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
+ char filename[0];
+ } old_bev;
+ struct build_id_event bev;
+ char filename[PATH_MAX];
+ u64 limit = offset + size;
+
+ while (offset < limit) {
+ ssize_t len;
+
+ if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
+ return -1;
+
+ if (header->needs_swap)
+ perf_event_header__bswap(&old_bev.header);
+
+ len = old_bev.header.size - sizeof(old_bev);
+ if (read(input, filename, len) != len)
+ return -1;
+
+ bev.header = old_bev.header;
+
+ /*
+ * As the pid is the missing value, we need to fill
+ * it properly. The header.misc value give us nice hint.
+ */
+ bev.pid = HOST_KERNEL_ID;
+ if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER ||
+ bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL)
+ bev.pid = DEFAULT_GUEST_KERNEL_ID;
+
+ memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id));
+ __event_process_build_id(&bev, filename, session);
+
+ offset += bev.header.size;
+ }
+
+ return 0;
+}
+
+static int perf_header__read_build_ids(struct perf_header *header,
+ int input, u64 offset, u64 size)
+{
+ struct perf_session *session = container_of(header, struct perf_session, header);
+ struct build_id_event bev;
+ char filename[PATH_MAX];
+ u64 limit = offset + size, orig_offset = offset;
+ int err = -1;
+
+ while (offset < limit) {
+ ssize_t len;
+
+ if (read(input, &bev, sizeof(bev)) != sizeof(bev))
+ goto out;
+
+ if (header->needs_swap)
+ perf_event_header__bswap(&bev.header);
+
+ len = bev.header.size - sizeof(bev);
+ if (read(input, filename, len) != len)
+ goto out;
+ /*
+ * The a1645ce1 changeset:
+ *
+ * "perf: 'perf kvm' tool for monitoring guest performance from host"
+ *
+ * Added a field to struct build_id_event that broke the file
+ * format.
+ *
+ * Since the kernel build-id is the first entry, process the
+ * table using the old format if the well known
+ * '[kernel.kallsyms]' string for the kernel build-id has the
+ * first 4 characters chopped off (where the pid_t sits).
+ */
+ if (memcmp(filename, "nel.kallsyms]", 13) == 0) {
+ if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1)
+ return -1;
+ return perf_header__read_build_ids_abi_quirk(header, input, offset, size);
+ }
+
+ __event_process_build_id(&bev, filename, session);
+
+ offset += bev.header.size;
+ }
+ err = 0;
+out:
+ return err;
+}
+
+static int process_trace_info(struct perf_file_section *section __unused,
+ struct perf_header *ph __unused,
+ int feat __unused, int fd)
+{
+ trace_report(fd, false);
+ return 0;
+}
+
+static int process_build_id(struct perf_file_section *section,
+ struct perf_header *ph,
+ int feat __unused, int fd)
+{
+ if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
+ pr_debug("Failed to read buildids, continuing...\n");
+ return 0;
+}
+
struct feature_ops {
int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
void (*print)(struct perf_header *h, int fd, FILE *fp);
+ int (*process)(struct perf_file_section *section,
+ struct perf_header *h, int feat, int fd);
const char *name;
bool full_only;
};
#define FEAT_OPA(n, func) \
[n] = { .name = #n, .write = write_##func, .print = print_##func }
+#define FEAT_OPP(n, func) \
+ [n] = { .name = #n, .write = write_##func, .print = print_##func, \
+ .process = process_##func }
#define FEAT_OPF(n, func) \
- [n] = { .name = #n, .write = write_##func, .print = print_##func, .full_only = true }
+ [n] = { .name = #n, .write = write_##func, .print = print_##func, \
+ .full_only = true }
/* feature_ops not implemented: */
#define print_trace_info NULL
#define print_build_id NULL
static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
- FEAT_OPA(HEADER_TRACE_INFO, trace_info),
- FEAT_OPA(HEADER_BUILD_ID, build_id),
+ FEAT_OPP(HEADER_TRACE_INFO, trace_info),
+ FEAT_OPP(HEADER_BUILD_ID, build_id),
FEAT_OPA(HEADER_HOSTNAME, hostname),
FEAT_OPA(HEADER_OSRELEASE, osrelease),
FEAT_OPA(HEADER_VERSION, version),
FEAT_OPA(HEADER_CMDLINE, cmdline),
FEAT_OPF(HEADER_CPU_TOPOLOGY, cpu_topology),
FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology),
+ FEAT_OPA(HEADER_BRANCH_STACK, branch_stack),
};
struct header_print_data {
return err;
}
+static const int attr_file_abi_sizes[] = {
+ [0] = PERF_ATTR_SIZE_VER0,
+ [1] = PERF_ATTR_SIZE_VER1,
+ 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 endiannesss
+ * between host recording the samples, and host parsing the samples is the
+ * same. This is not always the case given that the pipe output may always be
+ * redirected into a file and analyzed on a different machine with possibly a
+ * different endianness and perf_event ABI revsions in the perf tool itself.
+ */
+static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph)
+{
+ u64 attr_size;
+ int i;
+
+ for (i = 0 ; attr_pipe_abi_sizes[i]; i++) {
+ if (hdr_sz != attr_pipe_abi_sizes[i]) {
+ attr_size = bswap_64(hdr_sz);
+ if (attr_size != hdr_sz)
+ continue;
+
+ ph->needs_swap = true;
+ }
+ pr_debug("Pipe ABI%d perf.data file detected\n", i);
+ return 0;
+ }
+ return -1;
+}
+
+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) {
+ 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
+ */
+
+ /* 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)
{
+ int ret;
+
lseek(fd, 0, SEEK_SET);
- if (readn(fd, header, sizeof(*header)) <= 0 ||
- memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
+ ret = readn(fd, header, sizeof(*header));
+ if (ret <= 0)
return -1;
- if (header->attr_size != sizeof(struct perf_file_attr)) {
- u64 attr_size = bswap_64(header->attr_size);
-
- if (attr_size != sizeof(struct perf_file_attr))
- 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));
- ph->needs_swap = true;
+ adds_features));
}
if (header->size != sizeof(*header)) {
return 0;
}
-static int __event_process_build_id(struct build_id_event *bev,
- char *filename,
- struct perf_session *session)
-{
- int err = -1;
- struct list_head *head;
- struct machine *machine;
- u16 misc;
- struct dso *dso;
- enum dso_kernel_type dso_type;
-
- machine = perf_session__findnew_machine(session, bev->pid);
- if (!machine)
- goto out;
-
- misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-
- switch (misc) {
- case PERF_RECORD_MISC_KERNEL:
- dso_type = DSO_TYPE_KERNEL;
- head = &machine->kernel_dsos;
- break;
- case PERF_RECORD_MISC_GUEST_KERNEL:
- dso_type = DSO_TYPE_GUEST_KERNEL;
- head = &machine->kernel_dsos;
- break;
- case PERF_RECORD_MISC_USER:
- case PERF_RECORD_MISC_GUEST_USER:
- dso_type = DSO_TYPE_USER;
- head = &machine->user_dsos;
- break;
- default:
- goto out;
- }
-
- dso = __dsos__findnew(head, filename);
- if (dso != NULL) {
- char sbuild_id[BUILD_ID_SIZE * 2 + 1];
-
- dso__set_build_id(dso, &bev->build_id);
-
- if (filename[0] == '[')
- dso->kernel = dso_type;
-
- build_id__sprintf(dso->build_id, sizeof(dso->build_id),
- sbuild_id);
- pr_debug("build id event received for %s: %s\n",
- dso->long_name, sbuild_id);
- }
-
- 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[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
- char filename[0];
- } old_bev;
- struct build_id_event bev;
- char filename[PATH_MAX];
- u64 limit = offset + size;
-
- while (offset < limit) {
- ssize_t len;
-
- if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
- return -1;
-
- if (header->needs_swap)
- perf_event_header__bswap(&old_bev.header);
-
- len = old_bev.header.size - sizeof(old_bev);
- if (read(input, filename, len) != len)
- return -1;
-
- bev.header = old_bev.header;
-
- /*
- * As the pid is the missing value, we need to fill
- * it properly. The header.misc value give us nice hint.
- */
- bev.pid = HOST_KERNEL_ID;
- if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER ||
- bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL)
- bev.pid = DEFAULT_GUEST_KERNEL_ID;
-
- memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id));
- __event_process_build_id(&bev, filename, session);
-
- offset += bev.header.size;
- }
-
- return 0;
-}
-
-static int perf_header__read_build_ids(struct perf_header *header,
- int input, u64 offset, u64 size)
-{
- struct perf_session *session = container_of(header, struct perf_session, header);
- struct build_id_event bev;
- char filename[PATH_MAX];
- u64 limit = offset + size, orig_offset = offset;
- int err = -1;
-
- while (offset < limit) {
- ssize_t len;
-
- if (read(input, &bev, sizeof(bev)) != sizeof(bev))
- goto out;
-
- if (header->needs_swap)
- perf_event_header__bswap(&bev.header);
-
- len = bev.header.size - sizeof(bev);
- if (read(input, filename, len) != len)
- goto out;
- /*
- * The a1645ce1 changeset:
- *
- * "perf: 'perf kvm' tool for monitoring guest performance from host"
- *
- * Added a field to struct build_id_event that broke the file
- * format.
- *
- * Since the kernel build-id is the first entry, process the
- * table using the old format if the well known
- * '[kernel.kallsyms]' string for the kernel build-id has the
- * first 4 characters chopped off (where the pid_t sits).
- */
- if (memcmp(filename, "nel.kallsyms]", 13) == 0) {
- if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1)
- return -1;
- return perf_header__read_build_ids_abi_quirk(header, input, offset, size);
- }
-
- __event_process_build_id(&bev, filename, session);
-
- offset += bev.header.size;
- }
- err = 0;
-out:
- return err;
-}
-
static int perf_file_section__process(struct perf_file_section *section,
struct perf_header *ph,
int feat, int fd, void *data __used)
return 0;
}
- switch (feat) {
- case HEADER_TRACE_INFO:
- trace_report(fd, false);
- break;
- case HEADER_BUILD_ID:
- if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
- pr_debug("Failed to read buildids, continuing...\n");
- break;
- default:
- break;
- }
+ if (!feat_ops[feat].process)
+ return 0;
- return 0;
+ return feat_ops[feat].process(section, ph, feat, fd);
}
static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
struct perf_header *ph, int fd,
bool repipe)
{
- if (readn(fd, header, sizeof(*header)) <= 0 ||
- memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
- return -1;
+ int ret;
- if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
+ ret = readn(fd, header, sizeof(*header));
+ if (ret <= 0)
return -1;
- if (header->size != sizeof(*header)) {
- u64 size = bswap_64(header->size);
+ if (check_magic_endian(header->magic, header->size, true, ph) < 0) {
+ pr_debug("endian/magic failed\n");
+ return -1;
+ }
- if (size != sizeof(*header))
- return -1;
+ if (ph->needs_swap)
+ header->size = bswap_64(header->size);
- ph->needs_swap = true;
- }
+ if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
+ return -1;
return 0;
}
return 0;
}
+static int read_attr(int fd, struct perf_header *ph,
+ struct perf_file_attr *f_attr)
+{
+ struct perf_event_attr *attr = &f_attr->attr;
+ size_t sz, left;
+ size_t our_sz = sizeof(f_attr->attr);
+ int ret;
+
+ memset(f_attr, 0, sizeof(*f_attr));
+
+ /* read minimal guaranteed structure */
+ ret = readn(fd, attr, PERF_ATTR_SIZE_VER0);
+ if (ret <= 0) {
+ pr_debug("cannot read %d bytes of header attr\n",
+ PERF_ATTR_SIZE_VER0);
+ return -1;
+ }
+
+ /* on file perf_event_attr size */
+ sz = attr->size;
+
+ if (ph->needs_swap)
+ sz = bswap_32(sz);
+
+ if (sz == 0) {
+ /* assume ABI0 */
+ sz = PERF_ATTR_SIZE_VER0;
+ } else if (sz > our_sz) {
+ pr_debug("file uses a more recent and unsupported ABI"
+ " (%zu bytes extra)\n", sz - our_sz);
+ return -1;
+ }
+ /* what we have not yet read and that we know about */
+ left = sz - PERF_ATTR_SIZE_VER0;
+ if (left) {
+ void *ptr = attr;
+ ptr += PERF_ATTR_SIZE_VER0;
+
+ ret = readn(fd, ptr, left);
+ }
+ /* read perf_file_section, ids are read in caller */
+ ret = readn(fd, &f_attr->ids, sizeof(f_attr->ids));
+
+ return ret <= 0 ? -1 : 0;
+}
+
int perf_session__read_header(struct perf_session *session, int fd)
{
struct perf_header *header = &session->header;
if (session->fd_pipe)
return perf_header__read_pipe(session, fd);
- if (perf_file_header__read(&f_header, header, fd) < 0) {
- pr_debug("incompatible file format\n");
+ if (perf_file_header__read(&f_header, header, fd) < 0)
return -EINVAL;
- }
- nr_attrs = f_header.attrs.size / sizeof(f_attr);
+ nr_attrs = f_header.attrs.size / f_header.attr_size;
lseek(fd, f_header.attrs.offset, SEEK_SET);
for (i = 0; i < nr_attrs; i++) {
struct perf_evsel *evsel;
off_t tmp;
- if (readn(fd, &f_attr, sizeof(f_attr)) <= 0)
+ if (read_attr(fd, header, &f_attr) < 0)
goto out_errno;
if (header->needs_swap)
projects / linux-flexiantxendom0-3.2.10.git / blobdiff