2020-04-15 02:36:28 +08:00
|
|
|
.if !defined(WITH_CTF)
|
|
|
|
WITH_CTF=1
|
|
|
|
.endif
|
|
|
|
|
|
|
|
.include <bsd.sys.mk>
|
|
|
|
|
2020-06-20 10:08:59 +08:00
|
|
|
SRCDIR=${.CURDIR}
|
2020-04-15 02:36:28 +08:00
|
|
|
INCDIR=${.CURDIR:H}/include
|
|
|
|
|
|
|
|
KMOD= openzfs
|
|
|
|
|
|
|
|
.PATH: ${SRCDIR}/avl \
|
2023-03-01 09:33:59 +08:00
|
|
|
${SRCDIR}/lua \
|
|
|
|
${SRCDIR}/nvpair \
|
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 06:55:57 +08:00
|
|
|
${SRCDIR}/icp/algs/blake3 \
|
Add generic implementation handling and SHA2 impl
The skeleton file module/icp/include/generic_impl.c can be used for
iterating over different implementations of algorithms.
It is used by SHA256, SHA512 and BLAKE3 currently.
The Solaris SHA2 implementation got replaced with a version which is
based on public domain code of cppcrypto v0.10.
These assembly files are taken from current openssl master:
- sha256-x86_64.S: x64, SSSE3, AVX, AVX2, SHA-NI (x86_64)
- sha512-x86_64.S: x64, AVX, AVX2 (x86_64)
- sha256-armv7.S: ARMv7, NEON, ARMv8-CE (arm)
- sha512-armv7.S: ARMv7, NEON (arm)
- sha256-armv8.S: ARMv7, NEON, ARMv8-CE (aarch64)
- sha512-armv8.S: ARMv7, ARMv8-CE (aarch64)
- sha256-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha512-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha256-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
- sha512-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
Tested-by: Rich Ercolani <rincebrain@gmail.com>
Tested-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tino Reichardt <milky-zfs@mcmilk.de>
Closes #13741
2023-03-01 16:40:28 +08:00
|
|
|
${SRCDIR}/icp/algs/edonr \
|
|
|
|
${SRCDIR}/icp/algs/sha2 \
|
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 06:55:57 +08:00
|
|
|
${SRCDIR}/icp/asm-aarch64/blake3 \
|
Add generic implementation handling and SHA2 impl
The skeleton file module/icp/include/generic_impl.c can be used for
iterating over different implementations of algorithms.
It is used by SHA256, SHA512 and BLAKE3 currently.
The Solaris SHA2 implementation got replaced with a version which is
based on public domain code of cppcrypto v0.10.
These assembly files are taken from current openssl master:
- sha256-x86_64.S: x64, SSSE3, AVX, AVX2, SHA-NI (x86_64)
- sha512-x86_64.S: x64, AVX, AVX2 (x86_64)
- sha256-armv7.S: ARMv7, NEON, ARMv8-CE (arm)
- sha512-armv7.S: ARMv7, NEON (arm)
- sha256-armv8.S: ARMv7, NEON, ARMv8-CE (aarch64)
- sha512-armv8.S: ARMv7, ARMv8-CE (aarch64)
- sha256-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha512-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha256-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
- sha512-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
Tested-by: Rich Ercolani <rincebrain@gmail.com>
Tested-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tino Reichardt <milky-zfs@mcmilk.de>
Closes #13741
2023-03-01 16:40:28 +08:00
|
|
|
${SRCDIR}/icp/asm-aarch64/sha2 \
|
|
|
|
${SRCDIR}/icp/asm-arm/sha2 \
|
|
|
|
${SRCDIR}/icp/asm-ppc64/sha2 \
|
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 06:55:57 +08:00
|
|
|
${SRCDIR}/icp/asm-ppc64/blake3 \
|
|
|
|
${SRCDIR}/icp/asm-x86_64/blake3 \
|
Add generic implementation handling and SHA2 impl
The skeleton file module/icp/include/generic_impl.c can be used for
iterating over different implementations of algorithms.
It is used by SHA256, SHA512 and BLAKE3 currently.
The Solaris SHA2 implementation got replaced with a version which is
based on public domain code of cppcrypto v0.10.
These assembly files are taken from current openssl master:
- sha256-x86_64.S: x64, SSSE3, AVX, AVX2, SHA-NI (x86_64)
- sha512-x86_64.S: x64, AVX, AVX2 (x86_64)
- sha256-armv7.S: ARMv7, NEON, ARMv8-CE (arm)
- sha512-armv7.S: ARMv7, NEON (arm)
- sha256-armv8.S: ARMv7, NEON, ARMv8-CE (aarch64)
- sha512-armv8.S: ARMv7, ARMv8-CE (aarch64)
- sha256-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha512-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha256-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
- sha512-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
Tested-by: Rich Ercolani <rincebrain@gmail.com>
Tested-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tino Reichardt <milky-zfs@mcmilk.de>
Closes #13741
2023-03-01 16:40:28 +08:00
|
|
|
${SRCDIR}/icp/asm-x86_64/sha2 \
|
2020-04-15 02:36:28 +08:00
|
|
|
${SRCDIR}/os/freebsd/spl \
|
|
|
|
${SRCDIR}/os/freebsd/zfs \
|
|
|
|
${SRCDIR}/unicode \
|
|
|
|
${SRCDIR}/zcommon \
|
Add zstd support to zfs
This PR adds two new compression types, based on ZStandard:
- zstd: A basic ZStandard compression algorithm Available compression.
Levels for zstd are zstd-1 through zstd-19, where the compression
increases with every level, but speed decreases.
- zstd-fast: A faster version of the ZStandard compression algorithm
zstd-fast is basically a "negative" level of zstd. The compression
decreases with every level, but speed increases.
Available compression levels for zstd-fast:
- zstd-fast-1 through zstd-fast-10
- zstd-fast-20 through zstd-fast-100 (in increments of 10)
- zstd-fast-500 and zstd-fast-1000
For more information check the man page.
Implementation details:
Rather than treat each level of zstd as a different algorithm (as was
done historically with gzip), the block pointer `enum zio_compress`
value is simply zstd for all levels, including zstd-fast, since they all
use the same decompression function.
The compress= property (a 64bit unsigned integer) uses the lower 7 bits
to store the compression algorithm (matching the number of bits used in
a block pointer, as the 8th bit was borrowed for embedded block
pointers). The upper bits are used to store the compression level.
It is necessary to be able to determine what compression level was used
when later reading a block back, so the concept used in LZ4, where the
first 32bits of the on-disk value are the size of the compressed data
(since the allocation is rounded up to the nearest ashift), was
extended, and we store the version of ZSTD and the level as well as the
compressed size. This value is returned when decompressing a block, so
that if the block needs to be recompressed (L2ARC, nop-write, etc), that
the same parameters will be used to result in the matching checksum.
All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`,
`zio_prop_t`, etc.) uses the separated _compress and _complevel
variables. Only the properties ZAP contains the combined/bit-shifted
value. The combined value is split when the compression_changed_cb()
callback is called, and sets both objset members (os_compress and
os_complevel).
The userspace tools all use the combined/bit-shifted value.
Additional notes:
zdb can now also decode the ZSTD compression header (flag -Z) and
inspect the size, version and compression level saved in that header.
For each record, if it is ZSTD compressed, the parameters of the decoded
compression header get printed.
ZSTD is included with all current tests and new tests are added
as-needed.
Per-dataset feature flags now get activated when the property is set.
If a compression algorithm requires a feature flag, zfs activates the
feature when the property is set, rather than waiting for the first
block to be born. This is currently only used by zstd but can be
extended as needed.
Portions-Sponsored-By: The FreeBSD Foundation
Co-authored-by: Allan Jude <allanjude@freebsd.org>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Co-authored-by: Michael Niewöhner <foss@mniewoehner.de>
Signed-off-by: Allan Jude <allan@klarasystems.com>
Signed-off-by: Allan Jude <allanjude@freebsd.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #6247
Closes #9024
Closes #10277
Closes #10278
2020-08-19 01:10:17 +08:00
|
|
|
${SRCDIR}/zfs \
|
|
|
|
${SRCDIR}/zstd \
|
2022-03-01 21:32:52 +08:00
|
|
|
${SRCDIR}/zstd/lib/common \
|
|
|
|
${SRCDIR}/zstd/lib/compress \
|
|
|
|
${SRCDIR}/zstd/lib/decompress
|
Add zstd support to zfs
This PR adds two new compression types, based on ZStandard:
- zstd: A basic ZStandard compression algorithm Available compression.
Levels for zstd are zstd-1 through zstd-19, where the compression
increases with every level, but speed decreases.
- zstd-fast: A faster version of the ZStandard compression algorithm
zstd-fast is basically a "negative" level of zstd. The compression
decreases with every level, but speed increases.
Available compression levels for zstd-fast:
- zstd-fast-1 through zstd-fast-10
- zstd-fast-20 through zstd-fast-100 (in increments of 10)
- zstd-fast-500 and zstd-fast-1000
For more information check the man page.
Implementation details:
Rather than treat each level of zstd as a different algorithm (as was
done historically with gzip), the block pointer `enum zio_compress`
value is simply zstd for all levels, including zstd-fast, since they all
use the same decompression function.
The compress= property (a 64bit unsigned integer) uses the lower 7 bits
to store the compression algorithm (matching the number of bits used in
a block pointer, as the 8th bit was borrowed for embedded block
pointers). The upper bits are used to store the compression level.
It is necessary to be able to determine what compression level was used
when later reading a block back, so the concept used in LZ4, where the
first 32bits of the on-disk value are the size of the compressed data
(since the allocation is rounded up to the nearest ashift), was
extended, and we store the version of ZSTD and the level as well as the
compressed size. This value is returned when decompressing a block, so
that if the block needs to be recompressed (L2ARC, nop-write, etc), that
the same parameters will be used to result in the matching checksum.
All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`,
`zio_prop_t`, etc.) uses the separated _compress and _complevel
variables. Only the properties ZAP contains the combined/bit-shifted
value. The combined value is split when the compression_changed_cb()
callback is called, and sets both objset members (os_compress and
os_complevel).
The userspace tools all use the combined/bit-shifted value.
Additional notes:
zdb can now also decode the ZSTD compression header (flag -Z) and
inspect the size, version and compression level saved in that header.
For each record, if it is ZSTD compressed, the parameters of the decoded
compression header get printed.
ZSTD is included with all current tests and new tests are added
as-needed.
Per-dataset feature flags now get activated when the property is set.
If a compression algorithm requires a feature flag, zfs activates the
feature when the property is set, rather than waiting for the first
block to be born. This is currently only used by zstd but can be
extended as needed.
Portions-Sponsored-By: The FreeBSD Foundation
Co-authored-by: Allan Jude <allanjude@freebsd.org>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Co-authored-by: Michael Niewöhner <foss@mniewoehner.de>
Signed-off-by: Allan Jude <allan@klarasystems.com>
Signed-off-by: Allan Jude <allanjude@freebsd.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #6247
Closes #9024
Closes #10277
Closes #10278
2020-08-19 01:10:17 +08:00
|
|
|
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS+= -I${INCDIR}
|
2023-03-11 03:59:53 +08:00
|
|
|
CFLAGS+= -I${SRCDIR}/icp/include
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS+= -I${INCDIR}/os/freebsd
|
|
|
|
CFLAGS+= -I${INCDIR}/os/freebsd/spl
|
|
|
|
CFLAGS+= -I${INCDIR}/os/freebsd/zfs
|
Add zstd support to zfs
This PR adds two new compression types, based on ZStandard:
- zstd: A basic ZStandard compression algorithm Available compression.
Levels for zstd are zstd-1 through zstd-19, where the compression
increases with every level, but speed decreases.
- zstd-fast: A faster version of the ZStandard compression algorithm
zstd-fast is basically a "negative" level of zstd. The compression
decreases with every level, but speed increases.
Available compression levels for zstd-fast:
- zstd-fast-1 through zstd-fast-10
- zstd-fast-20 through zstd-fast-100 (in increments of 10)
- zstd-fast-500 and zstd-fast-1000
For more information check the man page.
Implementation details:
Rather than treat each level of zstd as a different algorithm (as was
done historically with gzip), the block pointer `enum zio_compress`
value is simply zstd for all levels, including zstd-fast, since they all
use the same decompression function.
The compress= property (a 64bit unsigned integer) uses the lower 7 bits
to store the compression algorithm (matching the number of bits used in
a block pointer, as the 8th bit was borrowed for embedded block
pointers). The upper bits are used to store the compression level.
It is necessary to be able to determine what compression level was used
when later reading a block back, so the concept used in LZ4, where the
first 32bits of the on-disk value are the size of the compressed data
(since the allocation is rounded up to the nearest ashift), was
extended, and we store the version of ZSTD and the level as well as the
compressed size. This value is returned when decompressing a block, so
that if the block needs to be recompressed (L2ARC, nop-write, etc), that
the same parameters will be used to result in the matching checksum.
All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`,
`zio_prop_t`, etc.) uses the separated _compress and _complevel
variables. Only the properties ZAP contains the combined/bit-shifted
value. The combined value is split when the compression_changed_cb()
callback is called, and sets both objset members (os_compress and
os_complevel).
The userspace tools all use the combined/bit-shifted value.
Additional notes:
zdb can now also decode the ZSTD compression header (flag -Z) and
inspect the size, version and compression level saved in that header.
For each record, if it is ZSTD compressed, the parameters of the decoded
compression header get printed.
ZSTD is included with all current tests and new tests are added
as-needed.
Per-dataset feature flags now get activated when the property is set.
If a compression algorithm requires a feature flag, zfs activates the
feature when the property is set, rather than waiting for the first
block to be born. This is currently only used by zstd but can be
extended as needed.
Portions-Sponsored-By: The FreeBSD Foundation
Co-authored-by: Allan Jude <allanjude@freebsd.org>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Co-authored-by: Michael Niewöhner <foss@mniewoehner.de>
Signed-off-by: Allan Jude <allan@klarasystems.com>
Signed-off-by: Allan Jude <allanjude@freebsd.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #6247
Closes #9024
Closes #10277
Closes #10278
2020-08-19 01:10:17 +08:00
|
|
|
CFLAGS+= -I${SRCDIR}/zstd/include
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS+= -include ${INCDIR}/os/freebsd/spl/sys/ccompile.h
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS+= -I${.CURDIR}
|
2020-04-15 02:36:28 +08:00
|
|
|
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS+= -D__KERNEL__ -DFREEBSD_NAMECACHE -DBUILDING_ZFS -D__BSD_VISIBLE=1 \
|
|
|
|
-DHAVE_UIO_ZEROCOPY -DWITHOUT_NETDUMP -D__KERNEL -D_SYS_CONDVAR_H_ \
|
|
|
|
-D_SYS_VMEM_H_ -DKDTRACE_HOOKS -DCOMPAT_FREEBSD11
|
2020-04-15 02:36:28 +08:00
|
|
|
|
|
|
|
.if ${MACHINE_ARCH} == "amd64"
|
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 06:55:57 +08:00
|
|
|
CFLAGS+= -D__x86_64 -DHAVE_SSE2 -DHAVE_SSSE3 -DHAVE_SSE4_1 -DHAVE_SSE4_2 \
|
2023-03-01 09:33:59 +08:00
|
|
|
-DHAVE_AVX -DHAVE_AVX2 -DHAVE_AVX512F -DHAVE_AVX512VL -DHAVE_AVX512BW
|
2020-04-15 02:36:28 +08:00
|
|
|
.endif
|
|
|
|
|
|
|
|
.if defined(WITH_DEBUG) && ${WITH_DEBUG} == "true"
|
2020-11-25 01:16:46 +08:00
|
|
|
CFLAGS+= -DZFS_DEBUG -g
|
|
|
|
.if defined(WITH_INVARIANTS) && ${WITH_INVARIANTS} == "true"
|
|
|
|
CFLAGS+= -DINVARIANTS -DWITNESS -DOPENSOLARIS_WITNESS
|
|
|
|
.endif
|
|
|
|
.if defined(WITH_O0) && ${WITH_O0} == "true"
|
|
|
|
CFLAGS+= -O0
|
|
|
|
.endif
|
2020-04-15 02:36:28 +08:00
|
|
|
.else
|
|
|
|
CFLAGS += -DNDEBUG
|
|
|
|
.endif
|
|
|
|
|
|
|
|
.if defined(WITH_VFS_DEBUG) && ${WITH_VFS_DEBUG} == "true"
|
|
|
|
# kernel must also be built with this option for this to work
|
|
|
|
CFLAGS+= -DDEBUG_VFS_LOCKS
|
|
|
|
.endif
|
|
|
|
|
|
|
|
.if defined(WITH_GCOV) && ${WITH_GCOV} == "true"
|
|
|
|
CFLAGS+= -fprofile-arcs -ftest-coverage
|
|
|
|
.endif
|
|
|
|
|
|
|
|
DEBUG_FLAGS=-g
|
|
|
|
|
|
|
|
.if ${MACHINE_ARCH} == "i386" || ${MACHINE_ARCH} == "powerpc" || \
|
2023-03-01 09:33:59 +08:00
|
|
|
${MACHINE_ARCH} == "powerpcspe" || ${MACHINE_ARCH} == "arm"
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS+= -DBITS_PER_LONG=32
|
|
|
|
.else
|
|
|
|
CFLAGS+= -DBITS_PER_LONG=64
|
|
|
|
.endif
|
|
|
|
|
|
|
|
SRCS= vnode_if.h device_if.h bus_if.h
|
|
|
|
|
2023-03-01 09:33:59 +08:00
|
|
|
# avl
|
2020-04-15 02:36:28 +08:00
|
|
|
SRCS+= avl.c
|
|
|
|
|
2021-11-17 03:40:10 +08:00
|
|
|
# icp
|
2023-03-01 09:33:59 +08:00
|
|
|
SRCS+= edonr.c
|
2021-11-17 03:40:10 +08:00
|
|
|
|
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 06:55:57 +08:00
|
|
|
#icp/algs/blake3
|
|
|
|
SRCS+= blake3.c \
|
|
|
|
blake3_generic.c \
|
Add generic implementation handling and SHA2 impl
The skeleton file module/icp/include/generic_impl.c can be used for
iterating over different implementations of algorithms.
It is used by SHA256, SHA512 and BLAKE3 currently.
The Solaris SHA2 implementation got replaced with a version which is
based on public domain code of cppcrypto v0.10.
These assembly files are taken from current openssl master:
- sha256-x86_64.S: x64, SSSE3, AVX, AVX2, SHA-NI (x86_64)
- sha512-x86_64.S: x64, AVX, AVX2 (x86_64)
- sha256-armv7.S: ARMv7, NEON, ARMv8-CE (arm)
- sha512-armv7.S: ARMv7, NEON (arm)
- sha256-armv8.S: ARMv7, NEON, ARMv8-CE (aarch64)
- sha512-armv8.S: ARMv7, ARMv8-CE (aarch64)
- sha256-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha512-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha256-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
- sha512-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
Tested-by: Rich Ercolani <rincebrain@gmail.com>
Tested-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tino Reichardt <milky-zfs@mcmilk.de>
Closes #13741
2023-03-01 16:40:28 +08:00
|
|
|
blake3_impl.c
|
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 06:55:57 +08:00
|
|
|
|
|
|
|
#icp/asm-aarch64/blake3
|
|
|
|
SRCS+= b3_aarch64_sse2.S \
|
|
|
|
b3_aarch64_sse41.S
|
|
|
|
|
|
|
|
#icp/asm-ppc64/blake3
|
|
|
|
SRCS+= b3_ppc64le_sse2.S \
|
|
|
|
b3_ppc64le_sse41.S
|
|
|
|
|
|
|
|
#icp/asm-x86_64/blake3
|
|
|
|
SRCS+= blake3_avx2.S \
|
|
|
|
blake3_avx512.S \
|
|
|
|
blake3_sse2.S \
|
|
|
|
blake3_sse41.S
|
|
|
|
|
Add generic implementation handling and SHA2 impl
The skeleton file module/icp/include/generic_impl.c can be used for
iterating over different implementations of algorithms.
It is used by SHA256, SHA512 and BLAKE3 currently.
The Solaris SHA2 implementation got replaced with a version which is
based on public domain code of cppcrypto v0.10.
These assembly files are taken from current openssl master:
- sha256-x86_64.S: x64, SSSE3, AVX, AVX2, SHA-NI (x86_64)
- sha512-x86_64.S: x64, AVX, AVX2 (x86_64)
- sha256-armv7.S: ARMv7, NEON, ARMv8-CE (arm)
- sha512-armv7.S: ARMv7, NEON (arm)
- sha256-armv8.S: ARMv7, NEON, ARMv8-CE (aarch64)
- sha512-armv8.S: ARMv7, ARMv8-CE (aarch64)
- sha256-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha512-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha256-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
- sha512-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
Tested-by: Rich Ercolani <rincebrain@gmail.com>
Tested-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tino Reichardt <milky-zfs@mcmilk.de>
Closes #13741
2023-03-01 16:40:28 +08:00
|
|
|
#icp/algs/sha2
|
|
|
|
SRCS+= sha2_generic.c \
|
|
|
|
sha256_impl.c \
|
|
|
|
sha512_impl.c
|
|
|
|
|
|
|
|
#icp/asm-arm/sha2
|
|
|
|
SRCS+= sha256-armv7.S \
|
|
|
|
sha512-armv7.S
|
|
|
|
|
|
|
|
#icp/asm-aarch64/sha2
|
|
|
|
SRCS+= sha256-armv8.S \
|
|
|
|
sha512-armv8.S
|
|
|
|
|
|
|
|
#icp/asm-ppc64/sha2
|
|
|
|
SRCS+= sha256-p8.S \
|
|
|
|
sha512-p8.S \
|
|
|
|
sha256-ppc.S \
|
|
|
|
sha512-ppc.S
|
|
|
|
|
|
|
|
#icp/asm-x86_64/sha2
|
|
|
|
SRCS+= sha256-x86_64.S \
|
|
|
|
sha512-x86_64.S
|
|
|
|
|
2020-04-15 02:36:28 +08:00
|
|
|
#lua
|
|
|
|
SRCS+= lapi.c \
|
|
|
|
lauxlib.c \
|
|
|
|
lbaselib.c \
|
|
|
|
lcode.c \
|
|
|
|
lcompat.c \
|
|
|
|
lcorolib.c \
|
|
|
|
lctype.c \
|
|
|
|
ldebug.c \
|
|
|
|
ldo.c \
|
|
|
|
lfunc.c \
|
|
|
|
lgc.c \
|
|
|
|
llex.c \
|
|
|
|
lmem.c \
|
|
|
|
lobject.c \
|
|
|
|
lopcodes.c \
|
|
|
|
lparser.c \
|
|
|
|
lstate.c \
|
|
|
|
lstring.c \
|
|
|
|
lstrlib.c \
|
|
|
|
ltable.c \
|
|
|
|
ltablib.c \
|
|
|
|
ltm.c \
|
|
|
|
lvm.c \
|
|
|
|
lzio.c
|
|
|
|
|
|
|
|
#nvpair
|
|
|
|
SRCS+= nvpair.c \
|
|
|
|
fnvpair.c \
|
|
|
|
nvpair_alloc_spl.c \
|
|
|
|
nvpair_alloc_fixed.c
|
|
|
|
|
|
|
|
#os/freebsd/spl
|
|
|
|
SRCS+= acl_common.c \
|
|
|
|
callb.c \
|
|
|
|
list.c \
|
|
|
|
spl_acl.c \
|
|
|
|
spl_cmn_err.c \
|
|
|
|
spl_dtrace.c \
|
|
|
|
spl_kmem.c \
|
|
|
|
spl_kstat.c \
|
|
|
|
spl_misc.c \
|
|
|
|
spl_policy.c \
|
2020-10-22 05:08:06 +08:00
|
|
|
spl_procfs_list.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
spl_string.c \
|
|
|
|
spl_sunddi.c \
|
|
|
|
spl_sysevent.c \
|
|
|
|
spl_taskq.c \
|
|
|
|
spl_uio.c \
|
|
|
|
spl_vfs.c \
|
|
|
|
spl_vm.c \
|
2020-10-22 05:08:06 +08:00
|
|
|
spl_zlib.c \
|
|
|
|
spl_zone.c
|
2020-04-15 02:36:28 +08:00
|
|
|
|
|
|
|
|
|
|
|
.if ${MACHINE_ARCH} == "i386" || ${MACHINE_ARCH} == "powerpc" || \
|
2023-03-01 09:33:59 +08:00
|
|
|
${MACHINE_ARCH} == "powerpcspe" || ${MACHINE_ARCH} == "arm"
|
2020-04-15 02:36:28 +08:00
|
|
|
SRCS+= spl_atomic.c
|
|
|
|
.endif
|
|
|
|
|
|
|
|
#os/freebsd/zfs
|
2020-05-11 03:23:52 +08:00
|
|
|
SRCS+= abd_os.c \
|
2020-10-22 05:08:06 +08:00
|
|
|
arc_os.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
crypto_os.c \
|
|
|
|
dmu_os.c \
|
2022-08-14 13:09:49 +08:00
|
|
|
event_os.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
hkdf.c \
|
|
|
|
kmod_core.c \
|
|
|
|
spa_os.c \
|
|
|
|
sysctl_os.c \
|
|
|
|
vdev_file.c \
|
|
|
|
vdev_geom.c \
|
2020-10-22 05:08:06 +08:00
|
|
|
vdev_label_os.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
zfs_acl.c \
|
|
|
|
zfs_ctldir.c \
|
2020-10-22 05:08:06 +08:00
|
|
|
zfs_debug.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
zfs_dir.c \
|
2020-07-16 12:32:50 +08:00
|
|
|
zfs_ioctl_compat.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
zfs_ioctl_os.c \
|
2021-02-20 14:34:33 +08:00
|
|
|
zfs_racct.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
zfs_vfsops.c \
|
2020-10-22 05:08:06 +08:00
|
|
|
zfs_vnops_os.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
zfs_znode.c \
|
|
|
|
zio_crypt.c \
|
|
|
|
zvol_os.c
|
|
|
|
|
|
|
|
#unicode
|
|
|
|
SRCS+= uconv.c \
|
|
|
|
u8_textprep.c
|
|
|
|
|
|
|
|
#zcommon
|
|
|
|
SRCS+= zfeature_common.c \
|
|
|
|
zfs_comutil.c \
|
|
|
|
zfs_deleg.c \
|
|
|
|
zfs_fletcher.c \
|
|
|
|
zfs_fletcher_avx512.c \
|
|
|
|
zfs_fletcher_intel.c \
|
|
|
|
zfs_fletcher_sse.c \
|
|
|
|
zfs_fletcher_superscalar.c \
|
|
|
|
zfs_fletcher_superscalar4.c \
|
|
|
|
zfs_namecheck.c \
|
|
|
|
zfs_prop.c \
|
|
|
|
zpool_prop.c \
|
|
|
|
zprop_common.c
|
|
|
|
|
|
|
|
#zfs
|
2020-05-11 03:23:52 +08:00
|
|
|
SRCS+= abd.c \
|
|
|
|
aggsum.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
arc.c \
|
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 06:55:57 +08:00
|
|
|
blake3_zfs.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
blkptr.c \
|
|
|
|
bplist.c \
|
|
|
|
bpobj.c \
|
2023-03-11 03:59:53 +08:00
|
|
|
brt.c \
|
2020-10-22 05:08:06 +08:00
|
|
|
btree.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
cityhash.c \
|
|
|
|
dbuf.c \
|
|
|
|
dbuf_stats.c \
|
|
|
|
bptree.c \
|
|
|
|
bqueue.c \
|
|
|
|
dataset_kstats.c \
|
|
|
|
ddt.c \
|
|
|
|
ddt_zap.c \
|
|
|
|
dmu.c \
|
|
|
|
dmu_diff.c \
|
|
|
|
dmu_object.c \
|
|
|
|
dmu_objset.c \
|
|
|
|
dmu_recv.c \
|
|
|
|
dmu_redact.c \
|
|
|
|
dmu_send.c \
|
|
|
|
dmu_traverse.c \
|
|
|
|
dmu_tx.c \
|
|
|
|
dmu_zfetch.c \
|
|
|
|
dnode.c \
|
|
|
|
dnode_sync.c \
|
|
|
|
dsl_dataset.c \
|
|
|
|
dsl_deadlist.c \
|
|
|
|
dsl_deleg.c \
|
|
|
|
dsl_bookmark.c \
|
|
|
|
dsl_dir.c \
|
|
|
|
dsl_crypt.c \
|
|
|
|
dsl_destroy.c \
|
|
|
|
dsl_pool.c \
|
|
|
|
dsl_prop.c \
|
|
|
|
dsl_scan.c \
|
|
|
|
dsl_synctask.c \
|
|
|
|
dsl_userhold.c \
|
2021-11-17 03:40:10 +08:00
|
|
|
edonr_zfs.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
fm.c \
|
|
|
|
gzip.c \
|
|
|
|
lzjb.c \
|
|
|
|
lz4.c \
|
2022-01-08 02:36:49 +08:00
|
|
|
lz4_zfs.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
metaslab.c \
|
|
|
|
mmp.c \
|
|
|
|
multilist.c \
|
|
|
|
objlist.c \
|
|
|
|
pathname.c \
|
|
|
|
range_tree.c \
|
|
|
|
refcount.c \
|
|
|
|
rrwlock.c \
|
|
|
|
sa.c \
|
2023-02-27 23:11:51 +08:00
|
|
|
sha2_zfs.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
skein_zfs.c \
|
|
|
|
spa.c \
|
|
|
|
spa_checkpoint.c \
|
|
|
|
spa_config.c \
|
|
|
|
spa_errlog.c \
|
|
|
|
spa_history.c \
|
|
|
|
spa_log_spacemap.c \
|
|
|
|
spa_misc.c \
|
|
|
|
spa_stats.c \
|
|
|
|
space_map.c \
|
|
|
|
space_reftree.c \
|
|
|
|
txg.c \
|
|
|
|
uberblock.c \
|
|
|
|
unique.c \
|
|
|
|
vdev.c \
|
|
|
|
vdev_cache.c \
|
Distributed Spare (dRAID) Feature
This patch adds a new top-level vdev type called dRAID, which stands
for Distributed parity RAID. This pool configuration allows all dRAID
vdevs to participate when rebuilding to a distributed hot spare device.
This can substantially reduce the total time required to restore full
parity to pool with a failed device.
A dRAID pool can be created using the new top-level `draid` type.
Like `raidz`, the desired redundancy is specified after the type:
`draid[1,2,3]`. No additional information is required to create the
pool and reasonable default values will be chosen based on the number
of child vdevs in the dRAID vdev.
zpool create <pool> draid[1,2,3] <vdevs...>
Unlike raidz, additional optional dRAID configuration values can be
provided as part of the draid type as colon separated values. This
allows administrators to fully specify a layout for either performance
or capacity reasons. The supported options include:
zpool create <pool> \
draid[<parity>][:<data>d][:<children>c][:<spares>s] \
<vdevs...>
- draid[parity] - Parity level (default 1)
- draid[:<data>d] - Data devices per group (default 8)
- draid[:<children>c] - Expected number of child vdevs
- draid[:<spares>s] - Distributed hot spares (default 0)
Abbreviated example `zpool status` output for a 68 disk dRAID pool
with two distributed spares using special allocation classes.
```
pool: tank
state: ONLINE
config:
NAME STATE READ WRITE CKSUM
slag7 ONLINE 0 0 0
draid2:8d:68c:2s-0 ONLINE 0 0 0
L0 ONLINE 0 0 0
L1 ONLINE 0 0 0
...
U25 ONLINE 0 0 0
U26 ONLINE 0 0 0
spare-53 ONLINE 0 0 0
U27 ONLINE 0 0 0
draid2-0-0 ONLINE 0 0 0
U28 ONLINE 0 0 0
U29 ONLINE 0 0 0
...
U42 ONLINE 0 0 0
U43 ONLINE 0 0 0
special
mirror-1 ONLINE 0 0 0
L5 ONLINE 0 0 0
U5 ONLINE 0 0 0
mirror-2 ONLINE 0 0 0
L6 ONLINE 0 0 0
U6 ONLINE 0 0 0
spares
draid2-0-0 INUSE currently in use
draid2-0-1 AVAIL
```
When adding test coverage for the new dRAID vdev type the following
options were added to the ztest command. These options are leverages
by zloop.sh to test a wide range of dRAID configurations.
-K draid|raidz|random - kind of RAID to test
-D <value> - dRAID data drives per group
-S <value> - dRAID distributed hot spares
-R <value> - RAID parity (raidz or dRAID)
The zpool_create, zpool_import, redundancy, replacement and fault
test groups have all been updated provide test coverage for the
dRAID feature.
Co-authored-by: Isaac Huang <he.huang@intel.com>
Co-authored-by: Mark Maybee <mmaybee@cray.com>
Co-authored-by: Don Brady <don.brady@delphix.com>
Co-authored-by: Matthew Ahrens <mahrens@delphix.com>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Mark Maybee <mmaybee@cray.com>
Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10102
2020-11-14 05:51:51 +08:00
|
|
|
vdev_draid.c \
|
|
|
|
vdev_draid_rand.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
vdev_indirect.c \
|
|
|
|
vdev_indirect_births.c \
|
|
|
|
vdev_indirect_mapping.c \
|
|
|
|
vdev_initialize.c \
|
|
|
|
vdev_label.c \
|
|
|
|
vdev_mirror.c \
|
|
|
|
vdev_missing.c \
|
|
|
|
vdev_queue.c \
|
|
|
|
vdev_raidz.c \
|
|
|
|
vdev_raidz_math.c \
|
|
|
|
vdev_raidz_math_scalar.c \
|
|
|
|
vdev_raidz_math_avx2.c \
|
|
|
|
vdev_raidz_math_avx512bw.c \
|
|
|
|
vdev_raidz_math_avx512f.c \
|
|
|
|
vdev_raidz_math_sse2.c \
|
|
|
|
vdev_raidz_math_ssse3.c \
|
2021-12-01 02:32:38 +08:00
|
|
|
vdev_rebuild.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
vdev_removal.c \
|
|
|
|
vdev_root.c \
|
|
|
|
vdev_trim.c \
|
|
|
|
zap.c \
|
|
|
|
zap_leaf.c \
|
|
|
|
zap_micro.c \
|
|
|
|
zcp.c \
|
|
|
|
zcp_get.c \
|
|
|
|
zcp_global.c \
|
|
|
|
zcp_iter.c \
|
|
|
|
zcp_set.c \
|
|
|
|
zcp_synctask.c \
|
|
|
|
zfeature.c \
|
|
|
|
zfs_byteswap.c \
|
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 06:55:57 +08:00
|
|
|
zfs_chksum.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
zfs_file_os.c \
|
|
|
|
zfs_fm.c \
|
|
|
|
zfs_fuid.c \
|
Add generic implementation handling and SHA2 impl
The skeleton file module/icp/include/generic_impl.c can be used for
iterating over different implementations of algorithms.
It is used by SHA256, SHA512 and BLAKE3 currently.
The Solaris SHA2 implementation got replaced with a version which is
based on public domain code of cppcrypto v0.10.
These assembly files are taken from current openssl master:
- sha256-x86_64.S: x64, SSSE3, AVX, AVX2, SHA-NI (x86_64)
- sha512-x86_64.S: x64, AVX, AVX2 (x86_64)
- sha256-armv7.S: ARMv7, NEON, ARMv8-CE (arm)
- sha512-armv7.S: ARMv7, NEON (arm)
- sha256-armv8.S: ARMv7, NEON, ARMv8-CE (aarch64)
- sha512-armv8.S: ARMv7, ARMv8-CE (aarch64)
- sha256-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha512-ppc.S: Generic PPC64 LE/BE (ppc64)
- sha256-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
- sha512-p8.S: Power8 ISA Version 2.07 LE/BE (ppc64)
Tested-by: Rich Ercolani <rincebrain@gmail.com>
Tested-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tino Reichardt <milky-zfs@mcmilk.de>
Closes #13741
2023-03-01 16:40:28 +08:00
|
|
|
zfs_impl.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
zfs_ioctl.c \
|
2020-10-22 05:08:06 +08:00
|
|
|
zfs_log.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
zfs_onexit.c \
|
|
|
|
zfs_quota.c \
|
|
|
|
zfs_ratelimit.c \
|
2020-10-22 05:08:06 +08:00
|
|
|
zfs_replay.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
zfs_rlock.c \
|
|
|
|
zfs_sa.c \
|
2020-10-22 05:08:06 +08:00
|
|
|
zfs_vnops.c \
|
2020-04-15 02:36:28 +08:00
|
|
|
zil.c \
|
|
|
|
zio.c \
|
|
|
|
zio_checksum.c \
|
|
|
|
zio_compress.c \
|
|
|
|
zio_inject.c \
|
|
|
|
zle.c \
|
|
|
|
zrlock.c \
|
|
|
|
zthr.c \
|
|
|
|
zvol.c
|
|
|
|
|
Add zstd support to zfs
This PR adds two new compression types, based on ZStandard:
- zstd: A basic ZStandard compression algorithm Available compression.
Levels for zstd are zstd-1 through zstd-19, where the compression
increases with every level, but speed decreases.
- zstd-fast: A faster version of the ZStandard compression algorithm
zstd-fast is basically a "negative" level of zstd. The compression
decreases with every level, but speed increases.
Available compression levels for zstd-fast:
- zstd-fast-1 through zstd-fast-10
- zstd-fast-20 through zstd-fast-100 (in increments of 10)
- zstd-fast-500 and zstd-fast-1000
For more information check the man page.
Implementation details:
Rather than treat each level of zstd as a different algorithm (as was
done historically with gzip), the block pointer `enum zio_compress`
value is simply zstd for all levels, including zstd-fast, since they all
use the same decompression function.
The compress= property (a 64bit unsigned integer) uses the lower 7 bits
to store the compression algorithm (matching the number of bits used in
a block pointer, as the 8th bit was borrowed for embedded block
pointers). The upper bits are used to store the compression level.
It is necessary to be able to determine what compression level was used
when later reading a block back, so the concept used in LZ4, where the
first 32bits of the on-disk value are the size of the compressed data
(since the allocation is rounded up to the nearest ashift), was
extended, and we store the version of ZSTD and the level as well as the
compressed size. This value is returned when decompressing a block, so
that if the block needs to be recompressed (L2ARC, nop-write, etc), that
the same parameters will be used to result in the matching checksum.
All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`,
`zio_prop_t`, etc.) uses the separated _compress and _complevel
variables. Only the properties ZAP contains the combined/bit-shifted
value. The combined value is split when the compression_changed_cb()
callback is called, and sets both objset members (os_compress and
os_complevel).
The userspace tools all use the combined/bit-shifted value.
Additional notes:
zdb can now also decode the ZSTD compression header (flag -Z) and
inspect the size, version and compression level saved in that header.
For each record, if it is ZSTD compressed, the parameters of the decoded
compression header get printed.
ZSTD is included with all current tests and new tests are added
as-needed.
Per-dataset feature flags now get activated when the property is set.
If a compression algorithm requires a feature flag, zfs activates the
feature when the property is set, rather than waiting for the first
block to be born. This is currently only used by zstd but can be
extended as needed.
Portions-Sponsored-By: The FreeBSD Foundation
Co-authored-by: Allan Jude <allanjude@freebsd.org>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Co-authored-by: Michael Niewöhner <foss@mniewoehner.de>
Signed-off-by: Allan Jude <allan@klarasystems.com>
Signed-off-by: Allan Jude <allanjude@freebsd.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #6247
Closes #9024
Closes #10277
Closes #10278
2020-08-19 01:10:17 +08:00
|
|
|
#zstd
|
|
|
|
SRCS+= zfs_zstd.c \
|
2022-03-01 21:32:52 +08:00
|
|
|
entropy_common.c \
|
|
|
|
error_private.c \
|
|
|
|
fse_compress.c \
|
2023-03-01 09:33:59 +08:00
|
|
|
fse_decompress.c \
|
2022-03-01 21:32:52 +08:00
|
|
|
hist.c \
|
|
|
|
huf_compress.c \
|
2023-03-01 09:33:59 +08:00
|
|
|
huf_decompress.c \
|
|
|
|
pool.c \
|
|
|
|
xxhash.c \
|
|
|
|
zstd_common.c \
|
2022-03-01 21:32:52 +08:00
|
|
|
zstd_compress.c \
|
|
|
|
zstd_compress_literals.c \
|
|
|
|
zstd_compress_sequences.c \
|
|
|
|
zstd_compress_superblock.c \
|
2023-03-01 09:33:59 +08:00
|
|
|
zstd_ddict.c \
|
|
|
|
zstd_decompress.c \
|
|
|
|
zstd_decompress_block.c \
|
2022-03-01 21:32:52 +08:00
|
|
|
zstd_double_fast.c \
|
|
|
|
zstd_fast.c \
|
|
|
|
zstd_lazy.c \
|
|
|
|
zstd_ldm.c \
|
2023-03-01 09:33:59 +08:00
|
|
|
zstd_opt.c
|
2022-03-01 21:32:52 +08:00
|
|
|
|
2020-04-15 02:36:28 +08:00
|
|
|
beforeinstall:
|
|
|
|
.if ${MK_DEBUG_FILES} != "no"
|
|
|
|
mtree -eu \
|
|
|
|
-f /etc/mtree/BSD.debug.dist \
|
|
|
|
-p ${DESTDIR}/usr/lib
|
|
|
|
.endif
|
|
|
|
|
|
|
|
.include <bsd.kmod.mk>
|
|
|
|
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.sysctl_os.c= -include ../zfs_config.h
|
|
|
|
CFLAGS.xxhash.c+= -include ${SYSDIR}/sys/_null.h
|
2020-04-15 02:36:28 +08:00
|
|
|
|
|
|
|
CFLAGS.gcc+= -Wno-pointer-to-int-cast
|
|
|
|
|
|
|
|
CFLAGS.abd.c= -Wno-cast-qual
|
2020-06-17 07:46:04 +08:00
|
|
|
CFLAGS.ddt.c= -Wno-cast-qual
|
|
|
|
CFLAGS.dmu.c= -Wno-cast-qual
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS.dmu_traverse.c= -Wno-cast-qual
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.dnode.c= ${NO_WUNUSED_BUT_SET_VARIABLE}
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS.dsl_deadlist.c= -Wno-cast-qual
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.dsl_dir.c= -Wno-cast-qual
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS.dsl_prop.c= -Wno-cast-qual
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.edonr.c= -Wno-cast-qual
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS.fm.c= -Wno-cast-qual
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.hist.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.lapi.c= -Wno-cast-qual
|
|
|
|
CFLAGS.lcompat.c= -Wno-cast-qual
|
|
|
|
CFLAGS.ldo.c= ${NO_WINFINITE_RECURSION}
|
|
|
|
CFLAGS.lobject.c= -Wno-cast-qual
|
|
|
|
CFLAGS.ltable.c= -Wno-cast-qual
|
|
|
|
CFLAGS.lvm.c= -Wno-cast-qual
|
|
|
|
CFLAGS.lz4.c= -Wno-cast-qual
|
2022-01-08 02:36:49 +08:00
|
|
|
CFLAGS.lz4_zfs.c= -Wno-cast-qual
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.nvpair.c= -Wno-cast-qual -DHAVE_RPC_TYPES ${NO_WSTRINGOP_OVERREAD}
|
|
|
|
CFLAGS.pool.c+= ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.pool.c= -U__BMI__ -fno-tree-vectorize
|
2020-06-17 07:46:04 +08:00
|
|
|
CFLAGS.spa.c= -Wno-cast-qual
|
|
|
|
CFLAGS.spa_misc.c= -Wno-cast-qual
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.spl_string.c= -Wno-cast-qual
|
|
|
|
CFLAGS.spl_vm.c= -Wno-cast-qual
|
|
|
|
CFLAGS.spl_zlib.c= -Wno-cast-qual
|
|
|
|
CFLAGS.u8_textprep.c= -Wno-cast-qual
|
Distributed Spare (dRAID) Feature
This patch adds a new top-level vdev type called dRAID, which stands
for Distributed parity RAID. This pool configuration allows all dRAID
vdevs to participate when rebuilding to a distributed hot spare device.
This can substantially reduce the total time required to restore full
parity to pool with a failed device.
A dRAID pool can be created using the new top-level `draid` type.
Like `raidz`, the desired redundancy is specified after the type:
`draid[1,2,3]`. No additional information is required to create the
pool and reasonable default values will be chosen based on the number
of child vdevs in the dRAID vdev.
zpool create <pool> draid[1,2,3] <vdevs...>
Unlike raidz, additional optional dRAID configuration values can be
provided as part of the draid type as colon separated values. This
allows administrators to fully specify a layout for either performance
or capacity reasons. The supported options include:
zpool create <pool> \
draid[<parity>][:<data>d][:<children>c][:<spares>s] \
<vdevs...>
- draid[parity] - Parity level (default 1)
- draid[:<data>d] - Data devices per group (default 8)
- draid[:<children>c] - Expected number of child vdevs
- draid[:<spares>s] - Distributed hot spares (default 0)
Abbreviated example `zpool status` output for a 68 disk dRAID pool
with two distributed spares using special allocation classes.
```
pool: tank
state: ONLINE
config:
NAME STATE READ WRITE CKSUM
slag7 ONLINE 0 0 0
draid2:8d:68c:2s-0 ONLINE 0 0 0
L0 ONLINE 0 0 0
L1 ONLINE 0 0 0
...
U25 ONLINE 0 0 0
U26 ONLINE 0 0 0
spare-53 ONLINE 0 0 0
U27 ONLINE 0 0 0
draid2-0-0 ONLINE 0 0 0
U28 ONLINE 0 0 0
U29 ONLINE 0 0 0
...
U42 ONLINE 0 0 0
U43 ONLINE 0 0 0
special
mirror-1 ONLINE 0 0 0
L5 ONLINE 0 0 0
U5 ONLINE 0 0 0
mirror-2 ONLINE 0 0 0
L6 ONLINE 0 0 0
U6 ONLINE 0 0 0
spares
draid2-0-0 INUSE currently in use
draid2-0-1 AVAIL
```
When adding test coverage for the new dRAID vdev type the following
options were added to the ztest command. These options are leverages
by zloop.sh to test a wide range of dRAID configurations.
-K draid|raidz|random - kind of RAID to test
-D <value> - dRAID data drives per group
-S <value> - dRAID distributed hot spares
-R <value> - RAID parity (raidz or dRAID)
The zpool_create, zpool_import, redundancy, replacement and fault
test groups have all been updated provide test coverage for the
dRAID feature.
Co-authored-by: Isaac Huang <he.huang@intel.com>
Co-authored-by: Mark Maybee <mmaybee@cray.com>
Co-authored-by: Don Brady <don.brady@delphix.com>
Co-authored-by: Matthew Ahrens <mahrens@delphix.com>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Mark Maybee <mmaybee@cray.com>
Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10102
2020-11-14 05:51:51 +08:00
|
|
|
CFLAGS.vdev_draid.c= -Wno-cast-qual
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS.vdev_raidz.c= -Wno-cast-qual
|
|
|
|
CFLAGS.vdev_raidz_math.c= -Wno-cast-qual
|
|
|
|
CFLAGS.vdev_raidz_math_avx2.c= -Wno-cast-qual -Wno-duplicate-decl-specifier
|
|
|
|
CFLAGS.vdev_raidz_math_avx512f.c= -Wno-cast-qual -Wno-duplicate-decl-specifier
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.vdev_raidz_math_scalar.c= -Wno-cast-qual
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS.vdev_raidz_math_sse2.c= -Wno-cast-qual -Wno-duplicate-decl-specifier
|
|
|
|
CFLAGS.zap_leaf.c= -Wno-cast-qual
|
2020-06-17 07:46:04 +08:00
|
|
|
CFLAGS.zap_micro.c= -Wno-cast-qual
|
2020-04-15 02:36:28 +08:00
|
|
|
CFLAGS.zcp.c= -Wno-cast-qual
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.zfs_fletcher.c= -Wno-cast-qual -Wno-pointer-arith
|
|
|
|
CFLAGS.zfs_fletcher_avx512.c= -Wno-cast-qual -Wno-pointer-arith
|
|
|
|
CFLAGS.zfs_fletcher_intel.c= -Wno-cast-qual -Wno-pointer-arith
|
|
|
|
CFLAGS.zfs_fletcher_sse.c= -Wno-cast-qual -Wno-pointer-arith
|
|
|
|
CFLAGS.zfs_fm.c= -Wno-cast-qual ${NO_WUNUSED_BUT_SET_VARIABLE}
|
2020-06-17 07:46:04 +08:00
|
|
|
CFLAGS.zfs_ioctl.c= -Wno-cast-qual
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.zfs_log.c= -Wno-cast-qual
|
|
|
|
CFLAGS.zfs_vnops_os.c= -Wno-pointer-arith
|
|
|
|
CFLAGS.zfs_zstd.c= -Wno-cast-qual -Wno-pointer-arith
|
2020-06-17 07:46:04 +08:00
|
|
|
CFLAGS.zil.c= -Wno-cast-qual
|
|
|
|
CFLAGS.zio.c= -Wno-cast-qual
|
2023-03-01 09:33:59 +08:00
|
|
|
CFLAGS.zprop_common.c= -Wno-cast-qual
|
2020-06-17 07:46:04 +08:00
|
|
|
CFLAGS.zrlock.c= -Wno-cast-qual
|
2023-03-01 09:33:59 +08:00
|
|
|
|
|
|
|
#zstd
|
|
|
|
CFLAGS.entropy_common.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.error_private.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.fse_compress.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL} ${NO_WUNUSED_BUT_SET_VARIABLE}
|
|
|
|
CFLAGS.fse_decompress.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.huf_compress.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.huf_decompress.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.xxhash.c+= -U__BMI__ -fno-tree-vectorize
|
|
|
|
CFLAGS.xxhash.c+= ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_common.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_compress.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_compress_literals.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_compress_sequences.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_compress_superblock.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL} ${NO_WUNUSED_BUT_SET_VARIABLE}
|
|
|
|
CFLAGS.zstd_ddict.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_decompress.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_decompress_block.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_double_fast.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_fast.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_lazy.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_ldm.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
CFLAGS.zstd_opt.c= -U__BMI__ -fno-tree-vectorize ${NO_WBITWISE_INSTEAD_OF_LOGICAL}
|
|
|
|
|
|
|
|
.if ${MACHINE_CPUARCH} == "aarch64"
|
|
|
|
__ZFS_ZSTD_AARCH64_FLAGS= -include ${SRCDIR}/zstd/include/aarch64_compat.h
|
|
|
|
CFLAGS.zstd.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.entropy_common.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.error_private.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.fse_compress.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.fse_decompress.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.hist.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.huf_compress.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.huf_decompress.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.pool.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.xxhash.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_common.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_compress.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_compress_literals.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_compress_sequences.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_compress_superblock.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_ddict.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_decompress.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_decompress_block.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_double_fast.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_fast.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_lazy.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_ldm.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
CFLAGS.zstd_opt.c+= ${__ZFS_ZSTD_AARCH64_FLAGS}
|
|
|
|
|
|
|
|
b3_aarch64_sse2.o: b3_aarch64_sse2.S
|
|
|
|
${CC} -c ${CFLAGS:N-mgeneral-regs-only} ${WERROR} ${.IMPSRC} \
|
|
|
|
-o ${.TARGET}
|
|
|
|
${CTFCONVERT_CMD}
|
|
|
|
|
|
|
|
b3_aarch64_sse41.o: b3_aarch64_sse41.S
|
|
|
|
${CC} -c ${CFLAGS:N-mgeneral-regs-only} ${WERROR} ${.IMPSRC} \
|
|
|
|
-o ${.TARGET}
|
|
|
|
${CTFCONVERT_CMD}
|
|
|
|
|
|
|
|
.endif
|