mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 05:48:40 +00:00
![George Spelvin](/assets/img/avatar_default.png)
We'd like to make more use of the highly-optimized dcache hash functions throughout the kernel, rather than have every subsystem create its own, and a function that hashes basic null-terminated strings is required for that. (The name is to emphasize that it returns both hash and length.) It's actually useful in the dcache itself, specifically d_alloc_name(). Other uses in the next patch. full_name_hash() is also tweaked to make it more generally useful: 1) Take a "char *" rather than "unsigned char *" argument, to be consistent with hash_name(). 2) Handle zero-length inputs. If we want more callers, we don't want to make them worry about corner cases. Signed-off-by: George Spelvin <linux@sciencehorizons.net>
76 lines
2.4 KiB
C
76 lines
2.4 KiB
C
#ifndef __LINUX_STRINGHASH_H
|
|
#define __LINUX_STRINGHASH_H
|
|
|
|
#include <linux/compiler.h> /* For __pure */
|
|
#include <linux/types.h> /* For u32, u64 */
|
|
|
|
/*
|
|
* Routines for hashing strings of bytes to a 32-bit hash value.
|
|
*
|
|
* These hash functions are NOT GUARANTEED STABLE between kernel
|
|
* versions, architectures, or even repeated boots of the same kernel.
|
|
* (E.g. they may depend on boot-time hardware detection or be
|
|
* deliberately randomized.)
|
|
*
|
|
* They are also not intended to be secure against collisions caused by
|
|
* malicious inputs; much slower hash functions are required for that.
|
|
*
|
|
* They are optimized for pathname components, meaning short strings.
|
|
* Even if a majority of files have longer names, the dynamic profile of
|
|
* pathname components skews short due to short directory names.
|
|
* (E.g. /usr/lib/libsesquipedalianism.so.3.141.)
|
|
*/
|
|
|
|
/*
|
|
* Version 1: one byte at a time. Example of use:
|
|
*
|
|
* unsigned long hash = init_name_hash;
|
|
* while (*p)
|
|
* hash = partial_name_hash(tolower(*p++), hash);
|
|
* hash = end_name_hash(hash);
|
|
*
|
|
* Although this is designed for bytes, fs/hfsplus/unicode.c
|
|
* abuses it to hash 16-bit values.
|
|
*/
|
|
|
|
/* Hash courtesy of the R5 hash in reiserfs modulo sign bits */
|
|
#define init_name_hash() 0
|
|
|
|
/* partial hash update function. Assume roughly 4 bits per character */
|
|
static inline unsigned long
|
|
partial_name_hash(unsigned long c, unsigned long prevhash)
|
|
{
|
|
return (prevhash + (c << 4) + (c >> 4)) * 11;
|
|
}
|
|
|
|
/*
|
|
* Finally: cut down the number of bits to a int value (and try to avoid
|
|
* losing bits)
|
|
*/
|
|
static inline unsigned long end_name_hash(unsigned long hash)
|
|
{
|
|
return (unsigned int)hash;
|
|
}
|
|
|
|
/*
|
|
* Version 2: One word (32 or 64 bits) at a time.
|
|
* If CONFIG_DCACHE_WORD_ACCESS is defined (meaning <asm/word-at-a-time.h>
|
|
* exists, which describes major Linux platforms like x86 and ARM), then
|
|
* this computes a different hash function much faster.
|
|
*
|
|
* If not set, this falls back to a wrapper around the preceding.
|
|
*/
|
|
extern unsigned int __pure full_name_hash(const char *, unsigned int);
|
|
|
|
/*
|
|
* A hash_len is a u64 with the hash of a string in the low
|
|
* half and the length in the high half.
|
|
*/
|
|
#define hashlen_hash(hashlen) ((u32)(hashlen))
|
|
#define hashlen_len(hashlen) ((u32)((hashlen) >> 32))
|
|
#define hashlen_create(hash, len) ((u64)(len)<<32 | (u32)(hash))
|
|
|
|
/* Return the "hash_len" (hash and length) of a null-terminated string */
|
|
extern u64 __pure hashlen_string(const char *name);
|
|
|
|
#endif /* __LINUX_STRINGHASH_H */
|