From f43804bf5f9ae1e60077c5f22aee5fdfe4f09837 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 23 Mar 2012 15:02:14 -0700 Subject: [PATCH] string: memchr_inv() speed improvements - Generate a 64-bit pattern more efficiently memchr_inv needs to generate a 64-bit pattern filled with a target character. The operation can be done by more efficient way. - Don't call the slow check_bytes() if the memory area is 64-bit aligned memchr_inv compares contiguous 64-bit words with the 64-bit pattern as much as possible. The outside of the region is checked by check_bytes() that scans for each byte. Unfortunately, the first 64-bit word is unexpectedly scanned by check_bytes() even if the memory area is aligned to a 64-bit boundary. Both changes were originally suggested by Eric Dumazet. Signed-off-by: Akinobu Mita Suggested-by: Eric Dumazet Cc: Brian Norris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/string.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/lib/string.c b/lib/string.c index dc4a86341f91..3a03782720c8 100644 --- a/lib/string.c +++ b/lib/string.c @@ -785,12 +785,24 @@ void *memchr_inv(const void *start, int c, size_t bytes) if (bytes <= 16) return check_bytes8(start, value, bytes); - value64 = value | value << 8 | value << 16 | value << 24; - value64 = (value64 & 0xffffffff) | value64 << 32; - prefix = 8 - ((unsigned long)start) % 8; + value64 = value; +#if defined(ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64 + value64 *= 0x0101010101010101; +#elif defined(ARCH_HAS_FAST_MULTIPLIER) + value64 *= 0x01010101; + value64 |= value64 << 32; +#else + value64 |= value64 << 8; + value64 |= value64 << 16; + value64 |= value64 << 32; +#endif + prefix = (unsigned long)start % 8; if (prefix) { - u8 *r = check_bytes8(start, value, prefix); + u8 *r; + + prefix = 8 - prefix; + r = check_bytes8(start, value, prefix); if (r) return r; start += prefix; -- 2.20.1