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
This commit is contained in:
Tino Reichardt
2022-06-09 00:55:57 +02:00
committed by GitHub
parent b9d98453f9
commit 985c33b132
53 changed files with 22804 additions and 52 deletions
+89
View File
@@ -121,6 +121,7 @@
#include <sys/zfeature.h>
#include <sys/dsl_userhold.h>
#include <sys/abd.h>
#include <sys/blake3.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
@@ -417,6 +418,7 @@ ztest_func_t ztest_device_removal;
ztest_func_t ztest_spa_checkpoint_create_discard;
ztest_func_t ztest_initialize;
ztest_func_t ztest_trim;
ztest_func_t ztest_blake3;
ztest_func_t ztest_fletcher;
ztest_func_t ztest_fletcher_incr;
ztest_func_t ztest_verify_dnode_bt;
@@ -470,6 +472,7 @@ ztest_info_t ztest_info[] = {
ZTI_INIT(ztest_spa_checkpoint_create_discard, 1, &zopt_rarely),
ZTI_INIT(ztest_initialize, 1, &zopt_sometimes),
ZTI_INIT(ztest_trim, 1, &zopt_sometimes),
ZTI_INIT(ztest_blake3, 1, &zopt_rarely),
ZTI_INIT(ztest_fletcher, 1, &zopt_rarely),
ZTI_INIT(ztest_fletcher_incr, 1, &zopt_rarely),
ZTI_INIT(ztest_verify_dnode_bt, 1, &zopt_sometimes),
@@ -6373,6 +6376,92 @@ ztest_reguid(ztest_ds_t *zd, uint64_t id)
VERIFY3U(load, ==, spa_load_guid(spa));
}
void
ztest_blake3(ztest_ds_t *zd, uint64_t id)
{
(void) zd, (void) id;
hrtime_t end = gethrtime() + NANOSEC;
zio_cksum_salt_t salt;
void *salt_ptr = &salt.zcs_bytes;
struct abd *abd_data, *abd_meta;
void *buf, *templ;
int i, *ptr;
uint32_t size;
BLAKE3_CTX ctx;
size = ztest_random_blocksize();
buf = umem_alloc(size, UMEM_NOFAIL);
abd_data = abd_alloc(size, B_FALSE);
abd_meta = abd_alloc(size, B_TRUE);
for (i = 0, ptr = buf; i < size / sizeof (*ptr); i++, ptr++)
*ptr = ztest_random(UINT_MAX);
memset(salt_ptr, 'A', 32);
abd_copy_from_buf_off(abd_data, buf, 0, size);
abd_copy_from_buf_off(abd_meta, buf, 0, size);
while (gethrtime() <= end) {
int run_count = 100;
zio_cksum_t zc_ref1, zc_ref2;
zio_cksum_t zc_res1, zc_res2;
void *ref1 = &zc_ref1;
void *ref2 = &zc_ref2;
void *res1 = &zc_res1;
void *res2 = &zc_res2;
/* BLAKE3_KEY_LEN = 32 */
VERIFY0(blake3_set_impl_name("generic"));
templ = abd_checksum_blake3_tmpl_init(&salt);
Blake3_InitKeyed(&ctx, salt_ptr);
Blake3_Update(&ctx, buf, size);
Blake3_Final(&ctx, ref1);
zc_ref2 = zc_ref1;
ZIO_CHECKSUM_BSWAP(&zc_ref2);
abd_checksum_blake3_tmpl_free(templ);
VERIFY0(blake3_set_impl_name("cycle"));
while (run_count-- > 0) {
/* Test current implementation */
Blake3_InitKeyed(&ctx, salt_ptr);
Blake3_Update(&ctx, buf, size);
Blake3_Final(&ctx, res1);
zc_res2 = zc_res1;
ZIO_CHECKSUM_BSWAP(&zc_res2);
VERIFY0(memcmp(ref1, res1, 32));
VERIFY0(memcmp(ref2, res2, 32));
/* Test ABD - data */
templ = abd_checksum_blake3_tmpl_init(&salt);
abd_checksum_blake3_native(abd_data, size,
templ, &zc_res1);
abd_checksum_blake3_byteswap(abd_data, size,
templ, &zc_res2);
VERIFY0(memcmp(ref1, res1, 32));
VERIFY0(memcmp(ref2, res2, 32));
/* Test ABD - metadata */
abd_checksum_blake3_native(abd_meta, size,
templ, &zc_res1);
abd_checksum_blake3_byteswap(abd_meta, size,
templ, &zc_res2);
abd_checksum_blake3_tmpl_free(templ);
VERIFY0(memcmp(ref1, res1, 32));
VERIFY0(memcmp(ref2, res2, 32));
}
}
abd_free(abd_data);
abd_free(abd_meta);
umem_free(buf, size);
}
void
ztest_fletcher(ztest_ds_t *zd, uint64_t id)
{