perf tools: Make perf able to read files from older ABIs

This patches provides a way to handle legacy perf.data
files.  Legacy files are those using the older PERFFILE
signature.

For those, it is still necessary to detect endianness but
without comparing their header->attr_size with the
tool's own version as it may be different. Instead, we use
a reference table for all known sizes from the legacy era.

We try all the combinations for sizes and endianness. If we find
a match, we proceed, otherwise we return: "incompatible file
format".

This is also done for the pipe-mode file format.
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: acme@redhat.com
Cc: robert.richter@amd.com
Cc: ming.m.lin@intel.com
Cc: andi@firstfloor.org
Cc: asharma@fb.com
Cc: ravitillo@lbl.gov
Cc: vweaver1@eecs.utk.edu
Cc: khandual@linux.vnet.ibm.com
Cc: dsahern@gmail.com
Link: http://lkml.kernel.org/r/1328826068-11713-19-git-send-email-eranian@google.comSigned-off-by: Ingo Molnar <mingo@elte.hu>

tools/perf/util/header.c

@@ -1803,35 +1803,101 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 	return err;
 }
 
-static int check_magic_endian(u64 *magic, struct perf_file_header *header,
-			      struct perf_header *ph)
+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)
 {
-	int ret;
+	uint64_t ref_size, attr_size;
+	int i;
 
-	/* check for legacy format */
-	ret = memcmp(magic, __perf_magic1, sizeof(*magic));
-	if (ret == 0) {
-		pr_debug("legacy perf.data format\n");
-		if (!header)
+	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;
+}
 
-		if (header->attr_size != sizeof(struct perf_file_attr)) {
-			u64 attr_size = bswap_64(header->attr_size);
+#define PERF_PIPE_HDR_VER0	16
 
-			if (attr_size != sizeof(struct perf_file_attr))
-				return -1;
+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 same endianness */
-	if (*magic == __perf_magic2)
+	/* check magic number with one endianness */
+	if (magic == __perf_magic2)
 		return 0;
 
-	/* check magic number but opposite endianness */
-	if (*magic != __perf_magic2_sw)
+	/* check magic number with opposite endianness */
+	if (magic != __perf_magic2_sw)
 		return -1;
 
 	ph->needs_swap = true;
@@ -1850,8 +1916,11 @@ int perf_file_header__read(struct perf_file_header *header,
 	if (ret <= 0)
 		return -1;
 
-	if (check_magic_endian(&header->magic, header, ph) < 0)
+	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,
@@ -1938,21 +2007,17 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
 	if (ret <= 0)
 		return -1;
 
-	 if (check_magic_endian(&header->magic, NULL, ph) < 0)
-		return -1;
-
-	if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
+	if (check_magic_endian(header->magic, header->size, true, ph) < 0) {
+		pr_debug("endian/magic failed\n");
 		return -1;
+	}
 
-	if (header->size != sizeof(*header)) {
-		u64 size = bswap_64(header->size);
+	if (ph->needs_swap)
+		header->size = bswap_64(header->size);
 
-		if (size != sizeof(*header))
+	if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
 		return -1;
 
-		ph->needs_swap = true;
-	}
-
 	return 0;
 }
 
@@ -1992,6 +2057,7 @@ static int read_attr(int fd, struct perf_header *ph,
 
 	/* on file perf_event_attr size */
 	sz = attr->size;
+
 	if (ph->needs_swap)
 		sz = bswap_32(sz);