Pull out string hash to <linux/stringhash.h> (f4bcbe79) · Commits · EulixOS / Software / Kernel

include/linux/dcache.h

+1 −26

Original line number	Diff line number	Diff line
		@@ -10,6 +10,7 @@
		#include <linux/cache.h>
		#include <linux/rcupdate.h>
		#include <linux/lockref.h>
		#include <linux/stringhash.h>

		struct path;
		struct vfsmount;
		@@ -52,9 +53,6 @@ struct qstr {
		};

		#define QSTR_INIT(n,l) { { { .len = l } }, .name = n }
		#define hashlen_hash(hashlen) ((u32) (hashlen))
		#define hashlen_len(hashlen) ((u32)((hashlen) >> 32))
		#define hashlen_create(hash,len) (((u64)(len)<<32)\|(u32)(hash))

		struct dentry_stat_t {
		long nr_dentry;
		@@ -65,29 +63,6 @@ struct dentry_stat_t {
		};
		extern struct dentry_stat_t dentry_stat;

		/* Name hashing routines. Initial hash value */
		/* 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;
		}

		/* Compute the hash for a name string. */
		extern unsigned int full_name_hash(const unsigned char *, unsigned int);

		/*
		* Try to keep struct dentry aligned on 64 byte cachelines (this will
		* give reasonable cacheline footprint with larger lines without the

include/linux/stringhash.h

0 → 100644

+72 −0

Original line number	Diff line number	Diff line
		#ifndef __LINUX_STRINGHASH_H
		#define __LINUX_STRINGHASH_H

		#include <linux/types.h>

		/*
		* 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 full_name_hash(const unsigned 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))

		#endif /* __LINUX_STRINGHASH_H */