mirror_zfs/include/sys/zio_checksum.h
Tino Reichardt 985c33b132
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
2022-06-08 15:55:57 -07:00

156 lines
4.9 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://www.opensolaris.org/os/licensing.
* 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) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2014, 2016 by Delphix. All rights reserved.
* Copyright (c) 2013 Saso Kiselkov, All rights reserved.
* Copyright (c) 2021 Tino Reichardt <milky-zfs@mcmilk.de>
*/
#ifndef _SYS_ZIO_CHECKSUM_H
#define _SYS_ZIO_CHECKSUM_H extern __attribute__((visibility("default")))
#include <sys/zio.h>
#include <zfeature_common.h>
#include <zfs_fletcher.h>
#ifdef __cplusplus
extern "C" {
#endif
struct abd;
/*
* Signature for checksum functions.
*/
typedef void zio_checksum_t(struct abd *abd, uint64_t size,
const void *ctx_template, zio_cksum_t *zcp);
typedef void *zio_checksum_tmpl_init_t(const zio_cksum_salt_t *salt);
typedef void zio_checksum_tmpl_free_t(void *ctx_template);
typedef enum zio_checksum_flags {
/* Strong enough for metadata? */
ZCHECKSUM_FLAG_METADATA = (1 << 1),
/* ZIO embedded checksum */
ZCHECKSUM_FLAG_EMBEDDED = (1 << 2),
/* Strong enough for dedup (without verification)? */
ZCHECKSUM_FLAG_DEDUP = (1 << 3),
/* Uses salt value */
ZCHECKSUM_FLAG_SALTED = (1 << 4),
/* Strong enough for nopwrite? */
ZCHECKSUM_FLAG_NOPWRITE = (1 << 5)
} zio_checksum_flags_t;
typedef enum {
ZIO_CHECKSUM_NATIVE,
ZIO_CHECKSUM_BYTESWAP
} zio_byteorder_t;
typedef struct zio_abd_checksum_data {
zio_byteorder_t acd_byteorder;
fletcher_4_ctx_t *acd_ctx;
zio_cksum_t *acd_zcp;
void *acd_private;
} zio_abd_checksum_data_t;
typedef void zio_abd_checksum_init_t(zio_abd_checksum_data_t *);
typedef void zio_abd_checksum_fini_t(zio_abd_checksum_data_t *);
typedef int zio_abd_checksum_iter_t(void *, size_t, void *);
typedef const struct zio_abd_checksum_func {
zio_abd_checksum_init_t *acf_init;
zio_abd_checksum_fini_t *acf_fini;
zio_abd_checksum_iter_t *acf_iter;
} zio_abd_checksum_func_t;
/*
* Information about each checksum function.
*/
typedef const struct zio_checksum_info {
/* checksum function for each byteorder */
zio_checksum_t *ci_func[2];
zio_checksum_tmpl_init_t *ci_tmpl_init;
zio_checksum_tmpl_free_t *ci_tmpl_free;
zio_checksum_flags_t ci_flags;
char *ci_name; /* descriptive name */
} zio_checksum_info_t;
typedef struct zio_bad_cksum {
zio_cksum_t zbc_expected;
zio_cksum_t zbc_actual;
const char *zbc_checksum_name;
uint8_t zbc_byteswapped;
uint8_t zbc_injected;
uint8_t zbc_has_cksum; /* expected/actual valid */
} zio_bad_cksum_t;
_SYS_ZIO_CHECKSUM_H zio_checksum_info_t
zio_checksum_table[ZIO_CHECKSUM_FUNCTIONS];
/*
* Checksum routines.
*/
/* SHA2 */
extern zio_checksum_t abd_checksum_SHA256;
extern zio_checksum_t abd_checksum_SHA512_native;
extern zio_checksum_t abd_checksum_SHA512_byteswap;
/* Skein */
extern zio_checksum_t abd_checksum_skein_native;
extern zio_checksum_t abd_checksum_skein_byteswap;
extern zio_checksum_tmpl_init_t abd_checksum_skein_tmpl_init;
extern zio_checksum_tmpl_free_t abd_checksum_skein_tmpl_free;
/* Edon-R */
extern zio_checksum_t abd_checksum_edonr_native;
extern zio_checksum_t abd_checksum_edonr_byteswap;
extern zio_checksum_tmpl_init_t abd_checksum_edonr_tmpl_init;
extern zio_checksum_tmpl_free_t abd_checksum_edonr_tmpl_free;
/* BLAKE3 */
extern zio_checksum_t abd_checksum_blake3_native;
extern zio_checksum_t abd_checksum_blake3_byteswap;
extern zio_checksum_tmpl_init_t abd_checksum_blake3_tmpl_init;
extern zio_checksum_tmpl_free_t abd_checksum_blake3_tmpl_free;
/* Fletcher 4 */
_SYS_ZIO_CHECKSUM_H zio_abd_checksum_func_t fletcher_4_abd_ops;
extern zio_checksum_t abd_fletcher_4_native;
extern zio_checksum_t abd_fletcher_4_byteswap;
extern int zio_checksum_equal(spa_t *, blkptr_t *, enum zio_checksum,
void *, uint64_t, uint64_t, zio_bad_cksum_t *);
extern void zio_checksum_compute(zio_t *, enum zio_checksum,
struct abd *, uint64_t);
extern int zio_checksum_error_impl(spa_t *, const blkptr_t *, enum zio_checksum,
struct abd *, uint64_t, uint64_t, zio_bad_cksum_t *);
extern int zio_checksum_error(zio_t *zio, zio_bad_cksum_t *out);
extern enum zio_checksum spa_dedup_checksum(spa_t *spa);
extern void zio_checksum_templates_free(spa_t *spa);
extern spa_feature_t zio_checksum_to_feature(enum zio_checksum cksum);
#ifdef __cplusplus
}
#endif
#endif /* _SYS_ZIO_CHECKSUM_H */