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 4bdb300b16e2e940bab8eeb07417b7f87914815f..6055d61811d30f6d037daed87ffb11924b0ac5e5 100644 (file)
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -192,7 +192,7 @@ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char
                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 c53d3a9547f9295408fa3cfe0d5abfb72023e29e..3531deebad3084104e6a9fca7116ba68890ad5af 100644 (file)
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1598,11 +1598,6 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
  *   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 @@ unsigned int full_name_hash(const unsigned char *name, unsigned int len)
                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 57e87e749a484cbf09a2f9f21fac3d3f52574df9..bf72e9ac6de01d1b1783b0b4adfd441c9c9ac58c 100644 (file)
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -29,8 +29,10 @@ struct vfsmount;
 /* 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
 
 /*