linux/security/selinux/ss/symtab.c
Christian Göttsche 32db469edf selinux: improve symtab string hashing
The number of buckets is calculated by performing a binary AND against
the mask of the hash table, which is one less than its size (which is a
power of two).  This leads to all top bits being discarded, requiring
for short or similar inputs a hash function with a good avalanche
effect.

Use djb2a:

    # current
    common prefixes:  7 entries and 5/8 buckets used, longest chain
                      length 2, sum of chain length^2 11
    classes:  134 entries and 100/256 buckets used, longest chain
              length 5, sum of chain length^2 234
    roles:  15 entries and 6/16 buckets used, longest chain length 5,
            sum of chain length^2 57
    types:  4448 entries and 3016/8192 buckets used, longest chain
            length 41, sum of chain length^2 14922
    users:  7 entries and 3/8 buckets used, longest chain length 3,
            sum of chain length^2 17
    bools:  306 entries and 221/512 buckets used, longest chain
            length 4, sum of chain length^2 524
    levels:  1 entries and 1/1 buckets used, longest chain length 1,
             sum of chain length^2 1
    categories:  1024 entries and 400/1024 buckets used, longest chain
                 length 4, sum of chain length^2 2740

    # patch
    common prefixes:  7 entries and 5/8 buckets used, longest chain
                     length 2, sum of chain length^2 11
    classes:  134 entries and 101/256 buckets used, longest chain
              length 3, sum of chain length^2 210
    roles:  15 entries and 9/16 buckets used, longest chain length 3,
            sum of chain length^2 31
    types:  4448 entries and 3459/8192 buckets used, longest chain
            length 5, sum of chain length^2 6778
    users:  7 entries and 5/8 buckets used, longest chain length 3,
            sum of chain length^2 13
    bools:  306 entries and 236/512 buckets used, longest chain
            length 5, sum of chain length^2 470
    levels:  1 entries and 1/1 buckets used, longest chain length 1,
             sum of chain length^2 1
    categories:  1024 entries and 518/1024 buckets used, longest chain
                 length 7, sum of chain length^2 2992

Signed-off-by: Christian Göttsche <cgzones@googlemail.com>
[PM: line length fixes in the commit message]
Signed-off-by: Paul Moore <paul@paul-moore.com>
2024-03-27 19:26:25 -04:00

57 lines
1.1 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Implementation of the symbol table type.
*
* Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
*/
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include "symtab.h"
static unsigned int symhash(const void *key)
{
/*
* djb2a
* Public domain from cdb v0.75
*/
unsigned int hash = 5381;
unsigned char c;
while ((c = *(const unsigned char *)key++))
hash = ((hash << 5) + hash) ^ c;
return hash;
}
static int symcmp(const void *key1, const void *key2)
{
const char *keyp1, *keyp2;
keyp1 = key1;
keyp2 = key2;
return strcmp(keyp1, keyp2);
}
static const struct hashtab_key_params symtab_key_params = {
.hash = symhash,
.cmp = symcmp,
};
int symtab_init(struct symtab *s, u32 size)
{
s->nprim = 0;
return hashtab_init(&s->table, size);
}
int symtab_insert(struct symtab *s, char *name, void *datum)
{
return hashtab_insert(&s->table, name, datum, symtab_key_params);
}
void *symtab_search(struct symtab *s, const char *name)
{
return hashtab_search(&s->table, name, symtab_key_params);
}