From 36126f8f2ed8168eb13aa0662b9b9585cba100a9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 26 May 2012 10:43:17 -0700 Subject: word-at-a-time: make the interfaces truly generic This changes the interfaces in to be a bit more complicated, but a lot more generic. In particular, it allows us to really do the operations efficiently on both little-endian and big-endian machines, pretty much regardless of machine details. For example, if you can rely on a fast population count instruction on your architecture, this will allow you to make your optimized file with that. NOTE! The "generic" version in include/asm-generic/word-at-a-time.h is not truly generic, it actually only works on big-endian. Why? Because on little-endian the generic algorithms are wasteful, since you can inevitably do better. The x86 implementation is an example of that. (The only truly non-generic part of the asm-generic implementation is the "find_zero()" function, and you could make a little-endian version of it. And if the Kbuild infrastructure allowed us to pick a particular header file, that would be lovely) The functions are as follows: - WORD_AT_A_TIME_CONSTANTS: specific constants that the algorithm uses. - has_zero(): take a word, and determine if it has a zero byte in it. It gets the word, the pointer to the constant pool, and a pointer to an intermediate "data" field it can set. This is the "quick-and-dirty" zero tester: it's what is run inside the hot loops. - "prep_zero_mask()": take the word, the data that has_zero() produced, and the constant pool, and generate an *exact* mask of which byte had the first zero. This is run directly *outside* the loop, and allows the "has_zero()" function to answer the "is there a zero byte" question without necessarily getting exactly *which* byte is the first one to contain a zero. If you do multiple byte lookups concurrently (eg "hash_name()", which looks for both NUL and '/' bytes), after you've done the prep_zero_mask() phase, the result of those can be or'ed together to get the "either or" case. - The result from "prep_zero_mask()" can then be fed into "find_zero()" (to find the byte offset of the first byte that was zero) or into "zero_bytemask()" (to find the bytemask of the bytes preceding the zero byte). The existence of zero_bytemask() is optional, and is not necessary for the normal string routines. But dentry name hashing needs it, so if you enable DENTRY_WORD_AT_A_TIME you need to expose it. This changes the generic strncpy_from_user() function and the dentry hashing functions to use these modified word-at-a-time interfaces. This gets us back to the optimized state of the x86 strncpy that we lost in the previous commit when moving over to the generic version. Signed-off-by: Linus Torvalds --- lib/strncpy_from_user.c | 47 +++++++---------------------------------------- 1 file changed, 7 insertions(+), 40 deletions(-) (limited to 'lib') diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index c4c09b0e96b..bb2b201d6ad 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -4,37 +4,7 @@ #include #include - -static inline long find_zero(unsigned long mask) -{ - long byte = 0; - -#ifdef __BIG_ENDIAN -#ifdef CONFIG_64BIT - if (mask >> 32) - mask >>= 32; - else - byte = 4; -#endif - if (mask >> 16) - mask >>= 16; - else - byte += 2; - return (mask >> 8) ? byte : byte + 1; -#else -#ifdef CONFIG_64BIT - if (!((unsigned int) mask)) { - mask >>= 32; - byte = 4; - } -#endif - if (!(mask & 0xffff)) { - mask >>= 16; - byte += 2; - } - return (mask & 0xff) ? byte : byte + 1; -#endif -} +#include #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define IS_UNALIGNED(src, dst) 0 @@ -51,8 +21,7 @@ static inline long find_zero(unsigned long mask) */ static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max) { - const unsigned long high_bits = REPEAT_BYTE(0xfe) + 1; - const unsigned long low_bits = REPEAT_BYTE(0x7f); + const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; long res = 0; /* @@ -66,18 +35,16 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, long goto byte_at_a_time; while (max >= sizeof(unsigned long)) { - unsigned long c, v, rhs; + unsigned long c, data; /* Fall back to byte-at-a-time if we get a page fault */ if (unlikely(__get_user(c,(unsigned long __user *)(src+res)))) break; - rhs = c | low_bits; - v = (c + high_bits) & ~rhs; *(unsigned long *)(dst+res) = c; - if (v) { - v = (c & low_bits) + low_bits; - v = ~(v | rhs); - return res + find_zero(v); + if (has_zero(c, &data, &constants)) { + data = prep_zero_mask(c, data, &constants); + data = create_zero_mask(data); + return res + find_zero(data); } res += sizeof(unsigned long); max -= sizeof(unsigned long); -- cgit v1.2.3