[PATCH] tools/perf: fix the word selected in find_*_bit

[Madhavan Srinivasan]

When decoding the perf_regs mask in regs_dump__printf(),
we loop through the mask using find_first_bit and find_next_bit functions.
And mask is of type "u64". But "u64" is send as a "unsigned long *" to
lib functions along with sizeof().

While the exisitng code works fine in most of the case, when using a 32bit perf
on a 64bit kernel (Big Endian), we end reading the wrong word. In find_first_bit(),
one word at a time (based on BITS_PER_LONG) is loaded and
checked for any bit set. In 32bit BE userspace,
BITS_PER_LONG turns out to be 32, and for a mask value of
"0x00000000000000ff", find_first_bit will return 32, instead of 0.
Reason for this is that, value in the word0 is all zeros and value
in word1 is 0xff. Ideally, second word in the mask should be loaded
and searched. Patch swaps the word to look incase of 32bit BE.

Cc: Arnaldo Carvalho de Melo <acme at kernel.org>
Cc: Adrian Hunter <adrian.hunter at intel.com>
Cc: Borislav Petkov <bp at suse.de>
Cc: David Ahern <dsahern at gmail.com>
Cc: George Spelvin <linux at horizon.com>
Cc: Jiri Olsa <jolsa at redhat.com>
Cc: Namhyung Kim <namhyung at kernel.org>
Cc: Rasmus Villemoes <linux at rasmusvillemoes.dk>
Cc: Wang Nan <wangnan0 at huawei.com>
Cc: Yury Norov <yury.norov at gmail.com>
Cc: Michael Ellerman <mpe at ellerman.id.au>
Signed-off-by: Madhavan Srinivasan <maddy at linux.vnet.ibm.com>
---
 tools/lib/find_bit.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
index 9122a9e80046..996b3e04324f 100644
--- a/tools/lib/find_bit.c
+++ b/tools/lib/find_bit.c
@@ -37,7 +37,12 @@ static unsigned long _find_next_bit(const unsigned long *addr,
 	if (!nbits || start >= nbits)
 		return nbits;

+#if (__BYTE_ORDER == __BIG_ENDIAN) && (BITS_PER_LONG != 64)
+	tmp = addr[(((nbits - 1)/BITS_PER_LONG) - (start / BITS_PER_LONG))]
+								^ invert;
+#else
 	tmp = addr[start / BITS_PER_LONG] ^ invert;
+#endif

 	/* Handle 1st word. */
 	tmp &= BITMAP_FIRST_WORD_MASK(start);
@@ -48,7 +53,12 @@ static unsigned long _find_next_bit(const unsigned long *addr,
 		if (start >= nbits)
 			return nbits;

+#if (__BYTE_ORDER == __BIG_ENDIAN) && (BITS_PER_LONG != 64)
+		tmp = addr[(((nbits - 1)/BITS_PER_LONG) - (start / BITS_PER_LONG))]
+								^ invert;
+#else
 		tmp = addr[start / BITS_PER_LONG] ^ invert;
+#endif
 	}

 	return min(start + __ffs(tmp), nbits);
@@ -75,8 +85,15 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 	unsigned long idx;

 	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+#if (__BYTE_ORDER == __BIG_ENDIAN) && (BITS_PER_LONG != 64)
+		if (addr[(((size-1)/BITS_PER_LONG) - idx)])
+			return min(idx * BITS_PER_LONG +
+				__ffs(addr[(((size-1)/BITS_PER_LONG) - idx)]),
+									size);
+#else
 		if (addr[idx])
 			return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size);
+#endif
 	}

 	return size;
--
1.9.1