fscache: Fix cookie key hashing

[ Upstream commit 35b72573e977ed6b18b094136a4fa3e0ffb13603 ]

The current hash algorithm used for hashing cookie keys is really bad,
producing almost no dispersion (after a test kernel build, ~30000 files
were split over just 18 out of the 32768 hash buckets).

Borrow the full_name_hash() hash function into fscache to do the hashing
for cookie keys and, in the future, volume keys.

I don't want to use full_name_hash() as-is because I want the hash value to
be consistent across arches and over time as the hash value produced may
get used on disk.

I can also optimise parts of it away as the key will always be a padded
array of aligned 32-bit words.

Fixes: ec0328e46d ("fscache: Maintain a catalogue of allocated cookies")
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
cc: linux-cachefs@redhat.com
Link: https://lore.kernel.org/r/162431201844.2908479.8293647220901514696.stgit@warthog.procyon.org.uk/
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
David Howells 2021-06-17 14:21:00 +01:00 committed by Greg Kroah-Hartman
parent e2e3758a2c
commit 57188e2cac
3 changed files with 42 additions and 13 deletions

View File

@ -74,10 +74,8 @@ void fscache_free_cookie(struct fscache_cookie *cookie)
static int fscache_set_key(struct fscache_cookie *cookie, static int fscache_set_key(struct fscache_cookie *cookie,
const void *index_key, size_t index_key_len) const void *index_key, size_t index_key_len)
{ {
unsigned long long h;
u32 *buf; u32 *buf;
int bufs; int bufs;
int i;
bufs = DIV_ROUND_UP(index_key_len, sizeof(*buf)); bufs = DIV_ROUND_UP(index_key_len, sizeof(*buf));
@ -91,17 +89,7 @@ static int fscache_set_key(struct fscache_cookie *cookie,
} }
memcpy(buf, index_key, index_key_len); memcpy(buf, index_key, index_key_len);
cookie->key_hash = fscache_hash(0, buf, bufs);
/* Calculate a hash and combine this with the length in the first word
* or first half word
*/
h = (unsigned long)cookie->parent;
h += index_key_len + cookie->type;
for (i = 0; i < bufs; i++)
h += buf[i];
cookie->key_hash = h ^ (h >> 32);
return 0; return 0;
} }

View File

@ -97,6 +97,8 @@ extern struct workqueue_struct *fscache_object_wq;
extern struct workqueue_struct *fscache_op_wq; extern struct workqueue_struct *fscache_op_wq;
DECLARE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait); DECLARE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait);
extern unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n);
static inline bool fscache_object_congested(void) static inline bool fscache_object_congested(void)
{ {
return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq); return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq);

View File

@ -94,6 +94,45 @@ static struct ctl_table fscache_sysctls_root[] = {
}; };
#endif #endif
/*
* Mixing scores (in bits) for (7,20):
* Input delta: 1-bit 2-bit
* 1 round: 330.3 9201.6
* 2 rounds: 1246.4 25475.4
* 3 rounds: 1907.1 31295.1
* 4 rounds: 2042.3 31718.6
* Perfect: 2048 31744
* (32*64) (32*31/2 * 64)
*/
#define HASH_MIX(x, y, a) \
( x ^= (a), \
y ^= x, x = rol32(x, 7),\
x += y, y = rol32(y,20),\
y *= 9 )
static inline unsigned int fold_hash(unsigned long x, unsigned long y)
{
/* Use arch-optimized multiply if one exists */
return __hash_32(y ^ __hash_32(x));
}
/*
* Generate a hash. This is derived from full_name_hash(), but we want to be
* sure it is arch independent and that it doesn't change as bits of the
* computed hash value might appear on disk. The caller also guarantees that
* the hashed data will be a series of aligned 32-bit words.
*/
unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n)
{
unsigned int a, x = 0, y = salt;
for (; n; n--) {
a = *data++;
HASH_MIX(x, y, a);
}
return fold_hash(x, y);
}
/* /*
* initialise the fs caching module * initialise the fs caching module
*/ */