Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events changes for v3.4 from Ingo Molnar:

 - New "hardware based branch profiling" feature both on the kernel and
   the tooling side, on CPUs that support it.  (modern x86 Intel CPUs
   with the 'LBR' hardware feature currently.)

   This new feature is basically a sophisticated 'magnifying glass' for
   branch execution - something that is pretty difficult to extract from
   regular, function histogram centric profiles.

   The simplest mode is activated via 'perf record -b', and the result
   looks like this in perf report:

	$ perf record -b any_call,u -e cycles:u branchy

	$ perf report -b --sort=symbol
	    52.34%  [.] main                   [.] f1
	    24.04%  [.] f1                     [.] f3
	    23.60%  [.] f1                     [.] f2
	     0.01%  [k] _IO_new_file_xsputn    [k] _IO_file_overflow
	     0.01%  [k] _IO_vfprintf_internal  [k] _IO_new_file_xsputn
	     0.01%  [k] _IO_vfprintf_internal  [k] strchrnul
	     0.01%  [k] __printf               [k] _IO_vfprintf_internal
	     0.01%  [k] main                   [k] __printf

   This output shows from/to branch columns and shows the highest
   percentage (from,to) jump combinations - i.e.  the most likely taken
   branches in the system.  "branches" can also include function calls
   and any other synchronous and asynchronous transitions of the
   instruction pointer that are not 'next instruction' - such as system
   calls, traps, interrupts, etc.

   This feature comes with (hopefully intuitive) flat ascii and TUI
   support in perf report.

 - Various 'perf annotate' visual improvements for us assembly junkies.
   It will now recognize function calls in the TUI and by hitting enter
   you can follow the call (recursively) and back, amongst other
   improvements.

 - Multiple threads/processes recording support in perf record, perf
   stat, perf top - which is activated via a comma-list of PIDs:

	perf top -p 21483,21485
	perf stat -p 21483,21485 -ddd
	perf record -p 21483,21485

 - Support for per UID views, via the --uid paramter to perf top, perf
   report, etc.  For example 'perf top --uid mingo' will only show the
   tasks that I am running, excluding other users, root, etc.

 - Jump label restructurings and improvements - this includes the
   factoring out of the (hopefully much clearer) include/linux/static_key.h
   generic facility:

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

	if (static_key_false(&key))
	        do unlikely code
	else
	        do likely code

	...
	static_key_slow_inc();
	...
	static_key_slow_inc();
	...

   The static_key_false() branch will be generated into the code with as
   little impact to the likely code path as possible.  the
   static_key_slow_*() APIs flip the branch via live kernel code patching.

   This facility can now be used more widely within the kernel to
   micro-optimize hot branches whose likelihood matches the static-key
   usage and fast/slow cost patterns.

 - SW function tracer improvements: perf support and filtering support.

 - Various hardenings of the perf.data ABI, to make older perf.data's
   smoother on newer tool versions, to make new features integrate more
   smoothly, to support cross-endian recording/analyzing workflows
   better, etc.

 - Restructuring of the kprobes code, the splitting out of 'optprobes',
   and a corner case bugfix.

 - Allow the tracing of kernel console output (printk).

 - Improvements/fixes to user-space RDPMC support, allowing user-space
   self-profiling code to extract PMU counts without performing any
   system calls, while playing nice with the kernel side.

 - 'perf bench' improvements

 - ... and lots of internal restructurings, cleanups and fixes that made
   these features possible.  And, as usual this list is incomplete as
   there were also lots of other improvements

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
  perf report: Fix annotate double quit issue in branch view mode
  perf report: Remove duplicate annotate choice in branch view mode
  perf/x86: Prettify pmu config literals
  perf report: Enable TUI in branch view mode
  perf report: Auto-detect branch stack sampling mode
  perf record: Add HEADER_BRANCH_STACK tag
  perf record: Provide default branch stack sampling mode option
  perf tools: Make perf able to read files from older ABIs
  perf tools: Fix ABI compatibility bug in print_event_desc()
  perf tools: Enable reading of perf.data files from different ABI rev
  perf: Add ABI reference sizes
  perf report: Add support for taken branch sampling
  perf record: Add support for sampling taken branch
  perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
  x86/kprobes: Split out optprobe related code to kprobes-opt.c
  x86/kprobes: Fix a bug which can modify kernel code permanently
  x86/kprobes: Fix instruction recovery on optimized path
  perf: Add callback to flush branch_stack on context switch
  perf: Disable PERF_SAMPLE_BRANCH_* when not supported
  perf/x86: Add LBR software filter support for Intel CPUs
  ...

1 files changed, 387 insertions, 201 deletions

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 14bb035c5fd9..fcd9cf3ea63e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -63,9 +63,20 @@ char *perf_header__find_event(u64 id)
 	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;
@@ -1012,6 +1023,12 @@ write_it:
 	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);
@@ -1133,8 +1150,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 	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));
@@ -1151,25 +1169,23 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 	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;
@@ -1305,25 +1321,204 @@ static void print_cpuid(struct perf_header *ph, int fd, FILE *fp)
 	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),
@@ -1336,6 +1531,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	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 {
@@ -1620,24 +1816,128 @@ out_free:
 	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)) {
@@ -1689,156 +1989,6 @@ int perf_file_header__read(struct perf_file_header *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)
@@ -1854,40 +2004,32 @@ static int perf_file_section__process(struct perf_file_section *section,
 		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;
 }
@@ -1908,6 +2050,52 @@ static int perf_header__read_pipe(struct perf_session *session, int fd)
 	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;
@@ -1923,19 +2111,17 @@ int perf_session__read_header(struct perf_session *session, int fd)
 	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)