mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-26 19:19:32 +03:00
985c33b132
This commit adds BLAKE3 checksums to OpenZFS, it has similar performance to Edon-R, but without the caveats around the latter. Homepage of BLAKE3: https://github.com/BLAKE3-team/BLAKE3 Wikipedia: https://en.wikipedia.org/wiki/BLAKE_(hash_function)#BLAKE3 Short description of Wikipedia: BLAKE3 is a cryptographic hash function based on Bao and BLAKE2, created by Jack O'Connor, Jean-Philippe Aumasson, Samuel Neves, and Zooko Wilcox-O'Hearn. It was announced on January 9, 2020, at Real World Crypto. BLAKE3 is a single algorithm with many desirable features (parallelism, XOF, KDF, PRF and MAC), in contrast to BLAKE and BLAKE2, which are algorithm families with multiple variants. BLAKE3 has a binary tree structure, so it supports a practically unlimited degree of parallelism (both SIMD and multithreading) given enough input. The official Rust and C implementations are dual-licensed as public domain (CC0) and the Apache License. Along with adding the BLAKE3 hash into the OpenZFS infrastructure a new benchmarking file called chksum_bench was introduced. When read it reports the speed of the available checksum functions. On Linux: cat /proc/spl/kstat/zfs/chksum_bench On FreeBSD: sysctl kstat.zfs.misc.chksum_bench This is an example output of an i3-1005G1 test system with Debian 11: implementation 1k 4k 16k 64k 256k 1m 4m edonr-generic 1196 1602 1761 1749 1762 1759 1751 skein-generic 546 591 608 615 619 612 616 sha256-generic 240 300 316 314 304 285 276 sha512-generic 353 441 467 476 472 467 426 blake3-generic 308 313 313 313 312 313 312 blake3-sse2 402 1289 1423 1446 1432 1458 1413 blake3-sse41 427 1470 1625 1704 1679 1607 1629 blake3-avx2 428 1920 3095 3343 3356 3318 3204 blake3-avx512 473 2687 4905 5836 5844 5643 5374 Output on Debian 5.10.0-10-amd64 system: (Ryzen 7 5800X) implementation 1k 4k 16k 64k 256k 1m 4m edonr-generic 1840 2458 2665 2719 2711 2723 2693 skein-generic 870 966 996 992 1003 1005 1009 sha256-generic 415 442 453 455 457 457 457 sha512-generic 608 690 711 718 719 720 721 blake3-generic 301 313 311 309 309 310 310 blake3-sse2 343 1865 2124 2188 2180 2181 2186 blake3-sse41 364 2091 2396 2509 2463 2482 2488 blake3-avx2 365 2590 4399 4971 4915 4802 4764 Output on Debian 5.10.0-9-powerpc64le system: (POWER 9) implementation 1k 4k 16k 64k 256k 1m 4m edonr-generic 1213 1703 1889 1918 1957 1902 1907 skein-generic 434 492 520 522 511 525 525 sha256-generic 167 183 187 188 188 187 188 sha512-generic 186 216 222 221 225 224 224 blake3-generic 153 152 154 153 151 153 153 blake3-sse2 391 1170 1366 1406 1428 1426 1414 blake3-sse41 352 1049 1212 1174 1262 1258 1259 Output on Debian 5.10.0-11-arm64 system: (Pi400) implementation 1k 4k 16k 64k 256k 1m 4m edonr-generic 487 603 629 639 643 641 641 skein-generic 271 299 303 308 309 309 307 sha256-generic 117 127 128 130 130 129 130 sha512-generic 145 165 170 172 173 174 175 blake3-generic 81 29 71 89 89 89 89 blake3-sse2 112 323 368 379 380 371 374 blake3-sse41 101 315 357 368 369 364 360 Structurally, the new code is mainly split into these parts: - 1x cross platform generic c variant: blake3_generic.c - 4x assembly for X86-64 (SSE2, SSE4.1, AVX2, AVX512) - 2x assembly for ARMv8 (NEON converted from SSE2) - 2x assembly for PPC64-LE (POWER8 converted from SSE2) - one file for switching between the implementations Note the PPC64 assembly requires the VSX instruction set and the kfpu_begin() / kfpu_end() calls on PowerPC were updated accordingly. Reviewed-by: Felix Dörre <felix@dogcraft.de> Reviewed-by: Ahelenia Ziemiańska <nabijaczleweli@nabijaczleweli.xyz> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tino Reichardt <milky-zfs@mcmilk.de> Co-authored-by: Rich Ercolani <rincebrain@gmail.com> Closes #10058 Closes #12918
114 lines
2.9 KiB
C
114 lines
2.9 KiB
C
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* The contents of this file are subject to the terms of the
|
|
* Common Development and Distribution License (the "License").
|
|
* You may not use this file except in compliance with the License.
|
|
*
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
* or http://opensource.org/licenses/CDDL-1.0.
|
|
* See the License for the specific language governing permissions
|
|
* and limitations under the License.
|
|
*
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
|
|
/*
|
|
* Copyright 2022 Tino Reichardt <milky-zfs@mcmilk.de>
|
|
*/
|
|
|
|
#include <sys/zfs_context.h>
|
|
#include <sys/zio_checksum.h>
|
|
#include <sys/blake3.h>
|
|
#include <sys/abd.h>
|
|
|
|
static int
|
|
blake3_incremental(void *buf, size_t size, void *arg)
|
|
{
|
|
BLAKE3_CTX *ctx = arg;
|
|
|
|
Blake3_Update(ctx, buf, size);
|
|
|
|
return (0);
|
|
}
|
|
|
|
/*
|
|
* Computes a native 256-bit BLAKE3 MAC checksum. Please note that this
|
|
* function requires the presence of a ctx_template that should be allocated
|
|
* using abd_checksum_blake3_tmpl_init.
|
|
*/
|
|
void
|
|
abd_checksum_blake3_native(abd_t *abd, uint64_t size, const void *ctx_template,
|
|
zio_cksum_t *zcp)
|
|
{
|
|
BLAKE3_CTX *ctx;
|
|
|
|
ctx = kmem_alloc(sizeof (*ctx), KM_NOSLEEP);
|
|
ASSERT(ctx != 0);
|
|
ASSERT(ctx_template != 0);
|
|
|
|
memcpy(ctx, ctx_template, sizeof (*ctx));
|
|
(void) abd_iterate_func(abd, 0, size, blake3_incremental, ctx);
|
|
Blake3_Final(ctx, (uint8_t *)zcp);
|
|
|
|
memset(ctx, 0, sizeof (*ctx));
|
|
kmem_free(ctx, sizeof (*ctx));
|
|
}
|
|
|
|
/*
|
|
* Byteswapped version of abd_checksum_blake3_native. This just invokes
|
|
* the native checksum function and byteswaps the resulting checksum (since
|
|
* BLAKE3 is internally endian-insensitive).
|
|
*/
|
|
void
|
|
abd_checksum_blake3_byteswap(abd_t *abd, uint64_t size,
|
|
const void *ctx_template, zio_cksum_t *zcp)
|
|
{
|
|
zio_cksum_t tmp;
|
|
|
|
ASSERT(ctx_template != 0);
|
|
|
|
abd_checksum_blake3_native(abd, size, ctx_template, &tmp);
|
|
zcp->zc_word[0] = BSWAP_64(tmp.zc_word[0]);
|
|
zcp->zc_word[1] = BSWAP_64(tmp.zc_word[1]);
|
|
zcp->zc_word[2] = BSWAP_64(tmp.zc_word[2]);
|
|
zcp->zc_word[3] = BSWAP_64(tmp.zc_word[3]);
|
|
}
|
|
|
|
/*
|
|
* Allocates a BLAKE3 MAC template suitable for using in BLAKE3 MAC checksum
|
|
* computations and returns a pointer to it.
|
|
*/
|
|
void *
|
|
abd_checksum_blake3_tmpl_init(const zio_cksum_salt_t *salt)
|
|
{
|
|
BLAKE3_CTX *ctx;
|
|
|
|
ASSERT(sizeof (salt->zcs_bytes) == 32);
|
|
|
|
/* init reference object */
|
|
ctx = kmem_zalloc(sizeof (*ctx), KM_SLEEP);
|
|
Blake3_InitKeyed(ctx, salt->zcs_bytes);
|
|
|
|
return (ctx);
|
|
}
|
|
|
|
/*
|
|
* Frees a BLAKE3 context template previously allocated using
|
|
* zio_checksum_blake3_tmpl_init.
|
|
*/
|
|
void
|
|
abd_checksum_blake3_tmpl_free(void *ctx_template)
|
|
{
|
|
BLAKE3_CTX *ctx = ctx_template;
|
|
|
|
memset(ctx, 0, sizeof (*ctx));
|
|
kmem_free(ctx, sizeof (*ctx));
|
|
}
|