freebsd-skq/sys/dev/random/uint128.h
cem b0dcb77676 random(4): Fortuna: allow increased concurrency
Add experimental feature to increase concurrency in Fortuna.  As this
diverges slightly from canonical Fortuna, and due to the security
sensitivity of random(4), it is off by default.  To enable it, set the
tunable kern.random.fortuna.concurrent_read="1".  The rest of this commit
message describes the behavior when enabled.

Readers continue to update shared Fortuna state under global mutex, as they
do in the status quo implementation of the algorithm, but shift the actual
PRF generation out from under the global lock.  This massively reduces the
CPU time readers spend holding the global lock, allowing for increased
concurrency on SMP systems and less bullying of the harvestq kthread.

It is somewhat of a deviation from FS&K.  I think the primary difference is
that the specific sequence of AES keys will differ if READ_RANDOM_UIO is
accessed concurrently (as the 2nd thread to take the mutex will no longer
receive a key derived from rekeying the first thread).  However, I believe
the goals of rekeying AES are maintained: trivially, we continue to rekey
every 1MB for the statistical property; and each consumer gets a
forward-secret, independent AES key for their PRF.

Since Chacha doesn't need to rekey for sequences of any length, this change
makes no difference to the sequence of Chacha keys and PRF generated when
Chacha is used in place of AES.

On a GENERIC 4-thread VM (so, INVARIANTS/WITNESS, numbers not necessarily
representative), 3x concurrent AES performance jumped from ~55 MiB/s per
thread to ~197 MB/s per thread.  Concurrent Chacha20 at 3 threads went from
roughly ~113 MB/s per thread to ~430 MB/s per thread.

Prior to this change, the system was extremely unresponsive with 3-4
concurrent random readers; each thread had high variance in latency and
throughput, depending on who got lucky and won the lock.  "rand_harvestq"
thread CPU use was high (double digits), seemingly due to spinning on the
global lock.

After the change, concurrent random readers and the system in general are
much more responsive, and rand_harvestq CPU use dropped to basically zero.

Tests are added to the devrandom suite to ensure the uint128_add64 primitive
utilized by unlocked read functions to specification.

Reviewed by:	markm
Approved by:	secteam(delphij)
Relnotes:	yes
Differential Revision:	https://reviews.freebsd.org/D20313
2019-06-17 20:29:13 +00:00

130 lines
3.3 KiB
C

/*-
* Copyright (c) 2015 Mark R V Murray
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer
* in this position and unchanged.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* $FreeBSD$
*/
#ifndef SYS_DEV_RANDOM_UINT128_H_INCLUDED
#define SYS_DEV_RANDOM_UINT128_H_INCLUDED
#include <sys/endian.h>
/* This whole thing is a crock :-(
*
* Everyone knows you always need the __uint128_t types!
*/
#ifdef __SIZEOF_INT128__
#define USE_REAL_UINT128_T
#endif
#ifdef USE_REAL_UINT128_T
typedef __uint128_t uint128_t;
#define UINT128_ZERO 0ULL
#else
typedef struct {
/* Ignore endianness */
uint64_t u128t_word0;
uint64_t u128t_word1;
} uint128_t;
static const uint128_t very_long_zero = {0UL,0UL};
#define UINT128_ZERO very_long_zero
#endif
static __inline void
uint128_increment(uint128_t *big_uintp)
{
#ifdef USE_REAL_UINT128_T
(*big_uintp)++;
#else
big_uintp->u128t_word0++;
if (big_uintp->u128t_word0 == 0UL)
big_uintp->u128t_word1++;
#endif
}
static __inline void
uint128_add64(uint128_t *big_uintp, uint64_t add)
{
#ifdef USE_REAL_UINT128_T
(*big_uintp) += add;
#else
uint64_t word0p;
word0p = big_uintp->u128t_word0 + add;
if (word0p < big_uintp->u128t_word0)
big_uintp->u128t_word1++;
big_uintp->u128t_word0 = word0p;
#endif
}
static __inline bool
uint128_equals(uint128_t a, uint128_t b)
{
#ifdef USE_REAL_UINT128_T
return (a == b);
#else
return (a.u128t_word0 == b.u128t_word0 &&
a.u128t_word1 == b.u128t_word1);
#endif
}
static __inline int
uint128_is_zero(uint128_t big_uint)
{
return (uint128_equals(big_uint, UINT128_ZERO));
}
static __inline uint128_t
le128dec(const void *pp)
{
const uint8_t *p = pp;
#ifdef USE_REAL_UINT128_T
return (((uint128_t)le64dec(p + 8) << 64) | le64dec(p));
#else
return ((uint128_t){
.u128t_word0 = le64dec(p),
.u128t_word1 = le64dec(p + 8),
});
#endif
}
static __inline void
le128enc(void *pp, uint128_t u)
{
uint8_t *p = pp;
#ifdef USE_REAL_UINT128_T
le64enc(p, (uint64_t)(u & UINT64_MAX));
le64enc(p + 8, (uint64_t)(u >> 64));
#else
le64enc(p, u.u128t_word0);
le64enc(p + 8, u.u128t_word1);
#endif
}
#endif /* SYS_DEV_RANDOM_UINT128_H_INCLUDED */