346ac4a116
commit e9a688bcb19348862afe30d7c85bc37c4c293471 upstream. Until the very recent commits, many bounded random integers were calculated using `get_random_u32() % max_plus_one`, which not only incurs the price of a division -- indicating performance mostly was not a real issue -- but also does not result in a uniformly distributed output if max_plus_one is not a power of two. Recent commits moved to using `prandom_u32_max(max_plus_one)`, which replaces the division with a faster multiplication, but still does not solve the issue with non-uniform output. For some users, maybe this isn't a problem, and for others, maybe it is, but for the majority of users, probably the question has never been posed and analyzed, and nobody thought much about it, probably assuming random is random is random. In other words, the unthinking expectation of most users is likely that the resultant numbers are uniform. So we implement here an efficient way of generating uniform bounded random integers. Through use of compile-time evaluation, and avoiding divisions as much as possible, this commit introduces no measurable overhead. At least for hot-path uses tested, any potential difference was lost in the noise. On both clang and gcc, code generation is pretty small. The new function, get_random_u32_below(), lives in random.h, rather than prandom.h, and has a "get_random_xxx" function name, because it is suitable for all uses, including cryptography. In order to be efficient, we implement a kernel-specific variant of Daniel Lemire's algorithm from "Fast Random Integer Generation in an Interval", linked below. The kernel's variant takes advantage of constant folding to avoid divisions entirely in the vast majority of cases, works on both 32-bit and 64-bit architectures, and requests a minimal amount of bytes from the RNG. Link: https://arxiv.org/pdf/1805.10941.pdf Cc: stable@vger.kernel.org # to ease future backports that use this api Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
62 lines
1.4 KiB
C
62 lines
1.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* include/linux/prandom.h
|
|
*
|
|
* Include file for the fast pseudo-random 32-bit
|
|
* generation.
|
|
*/
|
|
#ifndef _LINUX_PRANDOM_H
|
|
#define _LINUX_PRANDOM_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/random.h>
|
|
|
|
struct rnd_state {
|
|
__u32 s1, s2, s3, s4;
|
|
};
|
|
|
|
u32 prandom_u32_state(struct rnd_state *state);
|
|
void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
|
|
void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
|
|
|
|
#define prandom_init_once(pcpu_state) \
|
|
DO_ONCE(prandom_seed_full_state, (pcpu_state))
|
|
|
|
/* Deprecated: use get_random_u32_below() instead. */
|
|
static inline u32 prandom_u32_max(u32 ep_ro)
|
|
{
|
|
return get_random_u32_below(ep_ro);
|
|
}
|
|
|
|
/*
|
|
* Handle minimum values for seeds
|
|
*/
|
|
static inline u32 __seed(u32 x, u32 m)
|
|
{
|
|
return (x < m) ? x + m : x;
|
|
}
|
|
|
|
/**
|
|
* prandom_seed_state - set seed for prandom_u32_state().
|
|
* @state: pointer to state structure to receive the seed.
|
|
* @seed: arbitrary 64-bit value to use as a seed.
|
|
*/
|
|
static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
|
|
{
|
|
u32 i = ((seed >> 32) ^ (seed << 10) ^ seed) & 0xffffffffUL;
|
|
|
|
state->s1 = __seed(i, 2U);
|
|
state->s2 = __seed(i, 8U);
|
|
state->s3 = __seed(i, 16U);
|
|
state->s4 = __seed(i, 128U);
|
|
}
|
|
|
|
/* Pseudo random number generator from numerical recipes. */
|
|
static inline u32 next_pseudo_random32(u32 seed)
|
|
{
|
|
return seed * 1664525 + 1013904223;
|
|
}
|
|
|
|
#endif
|