crc32: major optimization

Precompute more crc32 values(0xcc00, 0xcc0000 and 0xcc000000) into tables.
 This increases the table size from 1KB to 4KB but the performance benfit
makes it worth it:

28% faster on MPC8321, 266 MHz
2x faster on Core 2 Duo, 3.1GHz

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 15 insertions, 9 deletions

diff --git a/lib/crc32.c b/lib/crc32.c
index bc5b936e9142..4855995fcde9 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -48,12 +48,20 @@ MODULE_LICENSE("GPL");
 #if CRC_LE_BITS == 8 || CRC_BE_BITS == 8
 
 static inline u32
-crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 *tab)
+crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
 {
 # ifdef __LITTLE_ENDIAN
-#  define DO_CRC(x) crc = tab[(crc ^ (x)) & 255 ] ^ (crc >> 8)
+#  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]
 # else
-#  define DO_CRC(x) crc = tab[((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
+#  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]
 # endif
         const u32 *b;
         size_t    rem_len;
@@ -70,10 +78,7 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 *tab)
         b = (const u32 *)buf;
         for (--b; len; --len) {
                 crc ^= *++b; /* use pre increment for speed */
-                DO_CRC(0);
-                DO_CRC(0);
-                DO_CRC(0);
-                DO_CRC(0);
+                DO_CRC4;
         }
         len = rem_len;
         /* And the last few bytes */
@@ -85,6 +90,7 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 *tab)
         }
         return crc;
 #undef DO_CRC
+#undef DO_CRC4
 }
 #endif
 /**
@@ -117,7 +123,7 @@ u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
 u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
 {
 # if CRC_LE_BITS == 8
-        const u32      *tab = crc32table_le;
+        const u32      (*tab)[] = crc32table_le;
 
         crc = __cpu_to_le32(crc);
         crc = crc32_body(crc, p, len, tab);
@@ -174,7 +180,7 @@ u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 {
 # if CRC_BE_BITS == 8
-        const u32      *tab = crc32table_be;
+        const u32      (*tab)[] = crc32table_be;
 
         crc = __cpu_to_be32(crc);
         crc = crc32_body(crc, p, len, tab);