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 <[e-mail]>
Signed-off-by: Will Deacon <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

fs/dcache.c

···
 		if (!tcount)
 			return 0;
 	}
-	mask = ~(~0ul << tcount*8);
+	mask = bytemask_from_count(tcount);
 	return unlikely(!!((a ^ b) & mask));
 }
 

fs/namei.c

···
  *   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.
···
 		if (!len)
 			goto done;
 	}
-	mask = ~(~0ul << len*8);
+	mask = bytemask_from_count(len);
 	hash += mask & a;
 done:
 	return fold_hash(hash);

include/linux/dcache.h

···
 /* 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
 
 /*