dcache: allow word-at-a-time name hashing with big-endian CPUs

When explicitly hashing the end of a string with the word-at-a-time
interface, we have to be careful which end of the word we pick up.

On big-endian CPUs, the upper-bits will contain the data we're after, so
ensure we generate our masks accordingly (and avoid hashing whatever
random junk may have been sitting after the string).

This patch adds a new dcache helper, bytemask_from_count, which creates
a mask appropriate for the CPU endianness.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/dcache.c b/fs/dcache.c
index 4bdb300..6055d61 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -192,7 +192,7 @@
 		if (!tcount)
 			return 0;
 	}
-	mask = ~(~0ul << tcount*8);
+	mask = bytemask_from_count(tcount);
 	return unlikely(!!((a ^ b) & mask));
 }
 
diff --git a/fs/namei.c b/fs/namei.c
index c53d3a9..3531dee 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1598,11 +1598,6 @@
  *   do a "get_unaligned()" if this helps and is sufficiently
  *   fast.
  *
- * - Little-endian machines (so that we can generate the mask
- *   of low bytes efficiently). Again, we *could* do a byte
- *   swapping load on big-endian architectures if that is not
- *   expensive enough to make the optimization worthless.
- *
  * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
  *   do not trap on the (extremely unlikely) case of a page
  *   crossing operation.
@@ -1646,7 +1641,7 @@
 		if (!len)
 			goto done;
 	}
-	mask = ~(~0ul << len*8);
+	mask = bytemask_from_count(len);
 	hash += mask & a;
 done:
 	return fold_hash(hash);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 57e87e7..bf72e9a 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -29,8 +29,10 @@
 /* The hash is always the low bits of hash_len */
 #ifdef __LITTLE_ENDIAN
  #define HASH_LEN_DECLARE u32 hash; u32 len;
+ #define bytemask_from_count(cnt)	(~(~0ul << (cnt)*8))
 #else
  #define HASH_LEN_DECLARE u32 len; u32 hash;
+ #define bytemask_from_count(cnt)	(~(~0ul >> (cnt)*8))
 #endif
 
 /*