glibc/malloc/thread-freeres.c
Adhemerval Zanella Netto 6f4e0fcfa2 stdlib: Add arc4random, arc4random_buf, and arc4random_uniform (BZ #4417)
The implementation is based on scalar Chacha20 with per-thread cache.
It uses getrandom or /dev/urandom as fallback to get the initial entropy,
and reseeds the internal state on every 16MB of consumed buffer.

To improve performance and lower memory consumption the per-thread cache
is allocated lazily on first arc4random functions call, and if the
memory allocation fails getentropy or /dev/urandom is used as fallback.
The cache is also cleared on thread exit iff it was initialized (so if
arc4random is not called it is not touched).

Although it is lock-free, arc4random is still not async-signal-safe
(the per thread state is not updated atomically).

The ChaCha20 implementation is based on RFC8439 [1], omitting the final
XOR of the keystream with the plaintext because the plaintext is a
stream of zeros.  This strategy is similar to what OpenBSD arc4random
does.

The arc4random_uniform is based on previous work by Florian Weimer,
where the algorithm is based on Jérémie Lumbroso paper Optimal Discrete
Uniform Generation from Coin Flips, and Applications (2013) [2], who
credits Donald E. Knuth and Andrew C. Yao, The complexity of nonuniform
random number generation (1976), for solving the general case.

The main advantage of this method is the that the unit of randomness is not
the uniform random variable (uint32_t), but a random bit.  It optimizes the
internal buffer sampling by initially consuming a 32-bit random variable
and then sampling byte per byte.  Depending of the upper bound requested,
it might lead to better CPU utilization.

Checked on x86_64-linux-gnu, aarch64-linux, and powerpc64le-linux-gnu.

Co-authored-by: Florian Weimer <fweimer@redhat.com>
Reviewed-by: Yann Droneaud <ydroneaud@opteya.com>

[1] https://datatracker.ietf.org/doc/html/rfc8439
[2] https://arxiv.org/pdf/1304.1916.pdf
2022-07-22 11:58:27 -03:00

46 lines
1.8 KiB
C

/* Free resources stored in thread-local variables on thread exit.
Copyright (C) 2003-2022 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
<https://www.gnu.org/licenses/>. */
#include <dlfcn/dlerror.h>
#include <libc-internal.h>
#include <malloc-internal.h>
#include <resolv/resolv-internal.h>
#include <rpc/rpc.h>
#include <string.h>
#include <tls-internal.h>
#include <shlib-compat.h>
/* Thread shutdown function. Note that this function must be called
for threads during shutdown for correctness reasons. Unlike
__libc_subfreeres, skipping calls to it is not a valid optimization.
This is called directly from pthread_create as the thread exits. */
void
__libc_thread_freeres (void)
{
#if SHLIB_COMPAT (libc, GLIBC_2_0, GLIBC_2_32)
__rpc_thread_destroy ();
#endif
call_function_static_weak (__res_thread_freeres);
call_function_static_weak (__glibc_tls_internal_free);
call_function_static_weak (__libc_dlerror_result_free);
/* This should come last because it shuts down malloc for this
thread and the other shutdown functions might well call free. */
call_function_static_weak (__malloc_arena_thread_freeres);
}