mirror_zfs/module/icp/algs/blake3/blake3_impl.c

285 lines
6.6 KiB
C
Raw Normal View History

Introduce BLAKE3 checksums as an OpenZFS feature 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
2022-06-09 01:55:57 +03:00
/*
* 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 https://opensource.org/licenses/CDDL-1.0.
Introduce BLAKE3 checksums as an OpenZFS feature 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
2022-06-09 01:55:57 +03:00
* 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 (c) 2021-2022 Tino Reichardt <milky-zfs@mcmilk.de>
*/
#include <sys/zfs_context.h>
#include <sys/zio_checksum.h>
#include "blake3_impl.h"
static const blake3_impl_ops_t *const blake3_impls[] = {
&blake3_generic_impl,
#if defined(__aarch64__) || \
(defined(__x86_64) && defined(HAVE_SSE2)) || \
(defined(__PPC64__) && defined(__LITTLE_ENDIAN__))
&blake3_sse2_impl,
#endif
#if defined(__aarch64__) || \
(defined(__x86_64) && defined(HAVE_SSE4_1)) || \
(defined(__PPC64__) && defined(__LITTLE_ENDIAN__))
&blake3_sse41_impl,
#endif
#if defined(__x86_64) && defined(HAVE_SSE4_1) && defined(HAVE_AVX2)
&blake3_avx2_impl,
#endif
#if defined(__x86_64) && defined(HAVE_AVX512F) && defined(HAVE_AVX512VL)
&blake3_avx512_impl,
#endif
};
/* this pointer holds current ops for implementation */
static const blake3_impl_ops_t *blake3_selected_impl = &blake3_generic_impl;
/* special implementation selections */
#define IMPL_FASTEST (UINT32_MAX)
#define IMPL_CYCLE (UINT32_MAX-1)
#define IMPL_USER (UINT32_MAX-2)
#define IMPL_PARAM (UINT32_MAX-3)
#define IMPL_READ(i) (*(volatile uint32_t *) &(i))
static uint32_t icp_blake3_impl = IMPL_FASTEST;
#define BLAKE3_IMPL_NAME_MAX 16
/* id of fastest implementation */
static uint32_t blake3_fastest_id = 0;
/* currently used id */
static uint32_t blake3_current_id = 0;
/* id of module parameter (-1 == unused) */
static int blake3_param_id = -1;
/* return number of supported implementations */
int
blake3_get_impl_count(void)
{
static int impls = 0;
int i;
if (impls)
return (impls);
for (i = 0; i < ARRAY_SIZE(blake3_impls); i++) {
if (!blake3_impls[i]->is_supported()) continue;
impls++;
}
return (impls);
}
/* return id of selected implementation */
int
blake3_get_impl_id(void)
{
return (blake3_current_id);
}
/* return name of selected implementation */
const char *
blake3_get_impl_name(void)
{
return (blake3_selected_impl->name);
}
/* setup id as fastest implementation */
void
blake3_set_impl_fastest(uint32_t id)
{
blake3_fastest_id = id;
}
/* set implementation by id */
void
blake3_set_impl_id(uint32_t id)
{
int i, cid;
/* select fastest */
if (id == IMPL_FASTEST)
id = blake3_fastest_id;
/* select next or first */
if (id == IMPL_CYCLE)
id = (++blake3_current_id) % blake3_get_impl_count();
/* 0..N for the real impl */
for (i = 0, cid = 0; i < ARRAY_SIZE(blake3_impls); i++) {
if (!blake3_impls[i]->is_supported()) continue;
if (cid == id) {
blake3_current_id = cid;
blake3_selected_impl = blake3_impls[i];
return;
}
cid++;
}
}
/* set implementation by name */
int
blake3_set_impl_name(const char *name)
{
int i, cid;
if (strcmp(name, "fastest") == 0) {
atomic_swap_32(&icp_blake3_impl, IMPL_FASTEST);
blake3_set_impl_id(IMPL_FASTEST);
return (0);
} else if (strcmp(name, "cycle") == 0) {
atomic_swap_32(&icp_blake3_impl, IMPL_CYCLE);
blake3_set_impl_id(IMPL_CYCLE);
return (0);
}
for (i = 0, cid = 0; i < ARRAY_SIZE(blake3_impls); i++) {
if (!blake3_impls[i]->is_supported()) continue;
if (strcmp(name, blake3_impls[i]->name) == 0) {
if (icp_blake3_impl == IMPL_PARAM) {
blake3_param_id = cid;
return (0);
}
blake3_selected_impl = blake3_impls[i];
blake3_current_id = cid;
return (0);
}
cid++;
}
return (-EINVAL);
}
/* setup implementation */
void
blake3_setup_impl(void)
{
switch (IMPL_READ(icp_blake3_impl)) {
case IMPL_PARAM:
blake3_set_impl_id(blake3_param_id);
atomic_swap_32(&icp_blake3_impl, IMPL_USER);
break;
case IMPL_FASTEST:
blake3_set_impl_id(IMPL_FASTEST);
break;
case IMPL_CYCLE:
blake3_set_impl_id(IMPL_CYCLE);
break;
default:
blake3_set_impl_id(blake3_current_id);
break;
}
}
/* return selected implementation */
const blake3_impl_ops_t *
blake3_impl_get_ops(void)
{
/* each call to ops will cycle */
if (icp_blake3_impl == IMPL_CYCLE)
blake3_set_impl_id(IMPL_CYCLE);
return (blake3_selected_impl);
}
#if defined(_KERNEL)
void **blake3_per_cpu_ctx;
void
blake3_per_cpu_ctx_init(void)
{
/*
* Create "The Godfather" ptr to hold all blake3 ctx
*/
blake3_per_cpu_ctx = kmem_alloc(max_ncpus * sizeof (void *), KM_SLEEP);
for (int i = 0; i < max_ncpus; i++) {
blake3_per_cpu_ctx[i] = kmem_alloc(sizeof (BLAKE3_CTX),
KM_SLEEP);
}
}
void
blake3_per_cpu_ctx_fini(void)
{
for (int i = 0; i < max_ncpus; i++) {
memset(blake3_per_cpu_ctx[i], 0, sizeof (BLAKE3_CTX));
kmem_free(blake3_per_cpu_ctx[i], sizeof (BLAKE3_CTX));
}
memset(blake3_per_cpu_ctx, 0, max_ncpus * sizeof (void *));
kmem_free(blake3_per_cpu_ctx, max_ncpus * sizeof (void *));
}
#endif
Introduce BLAKE3 checksums as an OpenZFS feature 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
2022-06-09 01:55:57 +03:00
#if defined(_KERNEL) && defined(__linux__)
static int
icp_blake3_impl_set(const char *name, zfs_kernel_param_t *kp)
{
char req_name[BLAKE3_IMPL_NAME_MAX];
size_t i;
/* sanitize input */
i = strnlen(name, BLAKE3_IMPL_NAME_MAX);
if (i == 0 || i >= BLAKE3_IMPL_NAME_MAX)
return (-EINVAL);
strlcpy(req_name, name, BLAKE3_IMPL_NAME_MAX);
while (i > 0 && isspace(req_name[i-1]))
i--;
req_name[i] = '\0';
atomic_swap_32(&icp_blake3_impl, IMPL_PARAM);
return (blake3_set_impl_name(req_name));
}
static int
icp_blake3_impl_get(char *buffer, zfs_kernel_param_t *kp)
{
int i, cid, cnt = 0;
char *fmt;
/* cycling */
fmt = (icp_blake3_impl == IMPL_CYCLE) ? "[cycle] " : "cycle ";
cnt += sprintf(buffer + cnt, fmt);
/* fastest one */
fmt = (icp_blake3_impl == IMPL_FASTEST) ? "[fastest] " : "fastest ";
cnt += sprintf(buffer + cnt, fmt);
/* user selected */
for (i = 0, cid = 0; i < ARRAY_SIZE(blake3_impls); i++) {
if (!blake3_impls[i]->is_supported()) continue;
fmt = (icp_blake3_impl == IMPL_USER &&
cid == blake3_current_id) ? "[%s] " : "%s ";
cnt += sprintf(buffer + cnt, fmt, blake3_impls[i]->name);
cid++;
}
buffer[cnt] = 0;
return (cnt);
}
module_param_call(icp_blake3_impl, icp_blake3_impl_set, icp_blake3_impl_get,
NULL, 0644);
MODULE_PARM_DESC(icp_blake3_impl, "Select BLAKE3 implementation.");
#endif