crc32: optimize inner loop

Taking a pointer reference to each row in the crc table matrix, one can
reduce the inner loop with a few insn's

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Cc: Bob Pearson <rpearson@systemfabricworks.com>
Cc: Frank Zago <fzago@systemfabricworks.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/lib/crc32.c b/lib/crc32.c
index a6e633a48cea887fbba14b7c1cbab84bd485c67b..4b35d2b4437cc76b3b75b45ae2d21ac6076f7809 100644 (file)
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -51,20 +51,21 @@ static inline u32
 crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
 {
 # ifdef __LITTLE_ENDIAN
-#  define DO_CRC(x) crc = tab[0][(crc ^ (x)) & 255] ^ (crc >> 8)
-#  define DO_CRC4 crc = tab[3][(crc) & 255] ^ \
-               tab[2][(crc >> 8) & 255] ^ \
-               tab[1][(crc >> 16) & 255] ^ \
-               tab[0][(crc >> 24) & 255]
+#  define DO_CRC(x) crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8)
+#  define DO_CRC4 crc = t3[(crc) & 255] ^ \
+               t2[(crc >> 8) & 255] ^ \
+               t1[(crc >> 16) & 255] ^ \
+               t0[(crc >> 24) & 255]
 # else
-#  define DO_CRC(x) crc = tab[0][((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
-#  define DO_CRC4 crc = tab[0][(crc) & 255] ^ \
-               tab[1][(crc >> 8) & 255] ^ \
-               tab[2][(crc >> 16) & 255] ^ \
-               tab[3][(crc >> 24) & 255]
+#  define DO_CRC(x) crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
+#  define DO_CRC4 crc = t0[(crc) & 255] ^ \
+               t1[(crc >> 8) & 255] ^  \
+               t2[(crc >> 16) & 255] ^ \
+               t3[(crc >> 24) & 255]
 # endif
        const u32 *b;
        size_t    rem_len;
+       const u32 *t0=tab[0], *t1=tab[1], *t2=tab[2], *t3=tab[3];
 
        /* Align it */
        if (unlikely((long)buf & 3 && len)) {