perf symbols: Handle different endians properly during symbol load

Currently we dont care about the file object's endianness. It's possible
we read buildid file object from different architecture than we are
currentlly running on. So we need to care about properly reading such
object's data - handle different endianness properly.

Adding:
	needs_swap DSO field
	dso__swap_init function to initialize DSO's needs_swap
	DSO__SWAP to read the data with proper swaps

Together with other endianity patches, this change fixies perf report
discrepancies on origin and target systems as described in test 1 below,
e.g. following perf report diff:

...
      0.12%               ps  [kernel.kallsyms]    [k] clear_page
-     0.12%              awk  bash                 [.] alloc_word_desc
+     0.12%              awk  bash                 [.] yyparse
      0.11%   beah-rhts-task  libpython2.6.so.1.0  [.] 0x5560e
      0.10%             perf  libc-2.12.so         [.] __ctype_toupper_loc
-     0.09%  rhts-test-runne  bash                 [.] maybe_make_export_env
+     0.09%  rhts-test-runne  bash                 [.] 0x385a0
      0.09%               ps  [kernel.kallsyms]    [k] page_fault
...

Note, running following to test perf endianity handling:
test 1)
  - origin system:
    # perf record -a -- sleep 10 (any perf record will do)
    # perf report > report.origin
    # perf archive perf.data

  - copy the perf.data, report.origin and perf.data.tar.bz2
    to a target system and run:
    # tar xjvf perf.data.tar.bz2 -C ~/.debug
    # perf report > report.target
    # diff -u report.origin report.target

  - the diff should produce no output
    (besides some white space stuff and possibly different
     date/TZ output)

test 1)
  - origin system:
    # perf record -ag -fo /tmp/perf.data -- sleep 1
  - mount origin system root to the target system on /mnt/origin
  - target system:
    # perf script --symfs /mnt/origin -I -i /mnt/origin/tmp/perf.data \
     --kallsyms /mnt/origin/proc/kallsyms
  - complete perf.data header is displayed

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1338380624-7443-2-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 62 insertions, 1 deletions

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e2ba885..9d04dcd 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -323,6 +323,7 @@ struct dso *dso__new(const char *name)
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
 		dso->kernel = DSO_TYPE_USER;
+		dso->needs_swap = DSO_SWAP__UNSET;
 		INIT_LIST_HEAD(&dso->node);
 	}
 
@@ -1156,6 +1157,33 @@ static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
 	return -1;
 }
 
+static int dso__swap_init(struct dso *dso, unsigned char eidata)
+{
+	static unsigned int const endian = 1;
+
+	dso->needs_swap = DSO_SWAP__NO;
+
+	switch (eidata) {
+	case ELFDATA2LSB:
+		/* We are big endian, DSO is little endian. */
+		if (*(unsigned char const *)&endian != 1)
+			dso->needs_swap = DSO_SWAP__YES;
+		break;
+
+	case ELFDATA2MSB:
+		/* We are little endian, DSO is big endian. */
+		if (*(unsigned char const *)&endian != 0)
+			dso->needs_swap = DSO_SWAP__YES;
+		break;
+
+	default:
+		pr_err("unrecognized DSO data encoding %d\n", eidata);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 			 int fd, symbol_filter_t filter, int kmodule,
 			 int want_symtab)
@@ -1187,6 +1215,9 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 		goto out_elf_end;
 	}
 
+	if (dso__swap_init(dso, ehdr.e_ident[EI_DATA]))
+		goto out_elf_end;
+
 	/* Always reject images with a mismatched build-id: */
 	if (dso->has_build_id) {
 		u8 build_id[BUILD_ID_SIZE];
@@ -1272,7 +1303,7 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 		if (opdsec && sym.st_shndx == opdidx) {
 			u32 offset = sym.st_value - opdshdr.sh_addr;
 			u64 *opd = opddata->d_buf + offset;
-			sym.st_value = *opd;
+			sym.st_value = DSO__SWAP(dso, u64, *opd);
 			sym.st_shndx = elf_addr_to_index(elf, sym.st_value);
 		}
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5649d63..af0752b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -9,6 +9,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
+#include <byteswap.h>
 
 #ifdef HAVE_CPLUS_DEMANGLE
 extern char *cplus_demangle(const char *, int);
@@ -160,11 +161,18 @@ enum dso_kernel_type {
 	DSO_TYPE_GUEST_KERNEL
 };
 
+enum dso_swap_type {
+	DSO_SWAP__UNSET,
+	DSO_SWAP__NO,
+	DSO_SWAP__YES,
+};
+
 struct dso {
 	struct list_head node;
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	enum dso_kernel_type	kernel;
+	enum dso_swap_type	needs_swap;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 hit:1;
@@ -182,6 +190,28 @@ struct dso {
 	char		 name[0];
 };
 
+#define DSO__SWAP(dso, type, val)			\
+({							\
+	type ____r = val;				\
+	BUG_ON(dso->needs_swap == DSO_SWAP__UNSET);	\
+	if (dso->needs_swap == DSO_SWAP__YES) {		\
+		switch (sizeof(____r)) {		\
+		case 2:					\
+			____r = bswap_16(val);		\
+			break;				\
+		case 4:					\
+			____r = bswap_32(val);		\
+			break;				\
+		case 8:					\
+			____r = bswap_64(val);		\
+			break;				\
+		default:				\
+			BUG_ON(1);			\
+		}					\
+	}						\
+	____r;						\
+})
+
 struct dso *dso__new(const char *name);
 void dso__delete(struct dso *dso);