c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2024-12-26 03:09:34 +03:00
Code Issues Packages Projects Releases Wiki Activity
6f73d02168
mirror_zfs/module/Kbuild.in
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

471 lines
11 KiB
Plaintext
Raw Blame History

# When integrated in to a monolithic kernel the spl module must appear
# first. This ensures its module initialization function is run before
# any of the other module initialization functions which depend on it.
ZFS_MODULE_CFLAGS += -std=gnu99 -Wno-declaration-after-statement
ZFS_MODULE_CFLAGS += -Wmissing-prototypes
ZFS_MODULE_CFLAGS += @KERNEL_DEBUG_CFLAGS@ @NO_FORMAT_ZERO_LENGTH@
ifneq ($(KBUILD_EXTMOD),)
zfs_include = @abs_top_srcdir@/include
icp_include = @abs_srcdir@/icp/include
zstd_include = @abs_srcdir@/zstd/include
ZFS_MODULE_CFLAGS += -include @abs_top_builddir@/zfs_config.h
ZFS_MODULE_CFLAGS += -I@abs_top_builddir@/include
src = @abs_srcdir@
obj = @abs_builddir@
else
zfs_include = $(srctree)/include/zfs
icp_include = $(srctree)/$(src)/icp/include
zstd_include = $(srctree)/$(src)/zstd/include
ZFS_MODULE_CFLAGS += -include $(zfs_include)/zfs_config.h
endif
ZFS_MODULE_CFLAGS += -I$(zfs_include)/os/linux/kernel
ZFS_MODULE_CFLAGS += -I$(zfs_include)/os/linux/spl
ZFS_MODULE_CFLAGS += -I$(zfs_include)/os/linux/zfs
ZFS_MODULE_CFLAGS += -I$(zfs_include)
ZFS_MODULE_CPPFLAGS += -D_KERNEL
ZFS_MODULE_CPPFLAGS += @KERNEL_DEBUG_CPPFLAGS@
# KASAN enables -Werror=frame-larger-than=1024, which
# breaks oh so many parts of our build.
ifeq ($(CONFIG_KASAN),y)
ZFS_MODULE_CFLAGS += -Wno-error=frame-larger-than=
endif
ifneq ($(KBUILD_EXTMOD),)
@CONFIG_QAT_TRUE@ZFS_MODULE_CFLAGS += -I@QAT_SRC@/include
@CONFIG_QAT_TRUE@KBUILD_EXTRA_SYMBOLS += @QAT_SYMBOLS@
endif
asflags-y := $(ZFS_MODULE_CFLAGS) $(ZFS_MODULE_CPPFLAGS)
ccflags-y := $(ZFS_MODULE_CFLAGS) $(ZFS_MODULE_CPPFLAGS)
# Suppress unused-value warnings in sparc64 architecture headers
ccflags-$(CONFIG_SPARC64) += -Wno-unused-value
obj-$(CONFIG_ZFS) := spl.o zfs.o
SPL_OBJS := \
spl-atomic.o \
spl-condvar.o \
spl-cred.o \
spl-err.o \
spl-generic.o \
spl-kmem-cache.o \
spl-kmem.o \
spl-kstat.o \
spl-proc.o \
spl-procfs-list.o \
spl-taskq.o \
spl-thread.o \
spl-trace.o \
spl-tsd.o \
spl-vmem.o \
spl-xdr.o \
spl-zlib.o
spl-objs += $(addprefix os/linux/spl/,$(SPL_OBJS))
zfs-objs += avl/avl.o
ICP_OBJS := \
algs/aes/aes_impl.o \
algs/aes/aes_impl_generic.o \
algs/aes/aes_modes.o \
algs/blake3/blake3.o \
algs/blake3/blake3_generic.o \
algs/blake3/blake3_impl.o \
algs/blake3/blake3_x86-64.o \
algs/edonr/edonr.o \
algs/modes/cbc.o \
algs/modes/ccm.o \
algs/modes/ctr.o \
algs/modes/ecb.o \
algs/modes/gcm.o \
algs/modes/gcm_generic.o \
algs/modes/modes.o \
algs/sha2/sha2.o \
algs/skein/skein.o \
algs/skein/skein_block.o \
algs/skein/skein_iv.o \
api/kcf_cipher.o \
api/kcf_ctxops.o \
api/kcf_mac.o \
core/kcf_callprov.o \
core/kcf_mech_tabs.o \
core/kcf_prov_lib.o \
core/kcf_prov_tabs.o \
core/kcf_sched.o \
illumos-crypto.o \
io/aes.o \
io/sha2_mod.o \
io/skein_mod.o \
spi/kcf_spi.o
ICP_OBJS_X86_64 := \
asm-x86_64/aes/aes_aesni.o \
asm-x86_64/aes/aes_amd64.o \
asm-x86_64/aes/aeskey.o \
asm-x86_64/blake3/blake3_avx2.o \
asm-x86_64/blake3/blake3_avx512.o \
asm-x86_64/blake3/blake3_sse2.o \
asm-x86_64/blake3/blake3_sse41.o \
asm-x86_64/modes/aesni-gcm-x86_64.o \
asm-x86_64/modes/gcm_pclmulqdq.o \
asm-x86_64/modes/ghash-x86_64.o \
asm-x86_64/sha2/sha256_impl.o \
asm-x86_64/sha2/sha512_impl.o
ICP_OBJS_X86 := \
algs/aes/aes_impl_aesni.o \
algs/aes/aes_impl_x86-64.o \
algs/modes/gcm_pclmulqdq.o
ICP_OBJS_ARM64 := \
asm-aarch64/blake3/b3_aarch64_sse2.o \
asm-aarch64/blake3/b3_aarch64_sse41.o
ICP_OBJS_PPC_PPC64 := \
asm-ppc64/blake3/b3_ppc64le_sse2.o \
asm-ppc64/blake3/b3_ppc64le_sse41.o
zfs-objs += $(addprefix icp/,$(ICP_OBJS))
zfs-$(CONFIG_X86) += $(addprefix icp/,$(ICP_OBJS_X86))
zfs-$(CONFIG_X86_64) += $(addprefix icp/,$(ICP_OBJS_X86_64))
zfs-$(CONFIG_ARM64) += $(addprefix icp/,$(ICP_OBJS_ARM64))
zfs-$(CONFIG_PPC) += $(addprefix icp/,$(ICP_OBJS_PPC_PPC64))
zfs-$(CONFIG_PPC64) += $(addprefix icp/,$(ICP_OBJS_PPC_PPC64))
$(addprefix $(obj)/icp/,$(ICP_OBJS) $(ICP_OBJS_X86) $(ICP_OBJS_X86_64) \
$(ICP_OBJS_ARM64) $(ICP_OBJS_PPC_PPC64)) : asflags-y += -I$(icp_include)
$(addprefix $(obj)/icp/,$(ICP_OBJS) $(ICP_OBJS_X86) $(ICP_OBJS_X86_64) \
$(ICP_OBJS_ARM64) $(ICP_OBJS_PPC_PPC64)) : ccflags-y += -I$(icp_include)
# Suppress objtool "can't find jump dest instruction at" warnings. They
# are caused by the constants which are defined in the text section of the
# assembly file using .byte instructions (e.g. bswap_mask). The objtool
# utility tries to interpret them as opcodes and obviously fails doing so.
OBJECT_FILES_NON_STANDARD_aesni-gcm-x86_64.o := y
OBJECT_FILES_NON_STANDARD_ghash-x86_64.o := y
# Suppress objtool "unsupported stack pointer realignment" warnings. We are
# not using a DRAP register while aligning the stack to a 64 byte boundary.
# See #6950 for the reasoning.
OBJECT_FILES_NON_STANDARD_sha256_impl.o := y
OBJECT_FILES_NON_STANDARD_sha512_impl.o := y
LUA_OBJS := \
lapi.o \
lauxlib.o \
lbaselib.o \
lcode.o \
lcompat.o \
lcorolib.o \
lctype.o \
ldebug.o \
ldo.o \
lfunc.o \
lgc.o \
llex.o \
lmem.o \
lobject.o \
lopcodes.o \
lparser.o \
lstate.o \
lstring.o \
lstrlib.o \
ltable.o \
ltablib.o \
ltm.o \
lvm.o \
lzio.o \
setjmp/setjmp.o
zfs-objs += $(addprefix lua/,$(LUA_OBJS))
NVPAIR_OBJS := \
fnvpair.o \
nvpair.o \
nvpair_alloc_fixed.o \
nvpair_alloc_spl.o
zfs-objs += $(addprefix nvpair/,$(NVPAIR_OBJS))
UNICODE_OBJS := \
u8_textprep.o \
uconv.o
zfs-objs += $(addprefix unicode/,$(UNICODE_OBJS))
ZCOMMON_OBJS := \
cityhash.o \
zfeature_common.o \
zfs_comutil.o \
zfs_deleg.o \
zfs_fletcher.o \
zfs_fletcher_superscalar.o \
zfs_fletcher_superscalar4.o \
zfs_namecheck.o \
zfs_prop.o \
zpool_prop.o \
zprop_common.o
ZCOMMON_OBJS_X86 := \
zfs_fletcher_avx512.o \
zfs_fletcher_intel.o \
zfs_fletcher_sse.o
ZCOMMON_OBJS_ARM64 := \
zfs_fletcher_aarch64_neon.o
zfs-objs += $(addprefix zcommon/,$(ZCOMMON_OBJS))
zfs-$(CONFIG_X86) += $(addprefix zcommon/,$(ZCOMMON_OBJS_X86))
zfs-$(CONFIG_ARM64) += $(addprefix zcommon/,$(ZCOMMON_OBJS_ARM64))
# Zstd uses -O3 by default, so we should follow
ZFS_ZSTD_FLAGS := -O3
# -fno-tree-vectorize gets set for gcc in zstd/common/compiler.h
# Set it for other compilers, too.
ZFS_ZSTD_FLAGS += -fno-tree-vectorize
# SSE register return with SSE disabled if -march=znverX is passed
ZFS_ZSTD_FLAGS += -U__BMI__
# Quiet warnings about frame size due to unused code in unmodified zstd lib
ZFS_ZSTD_FLAGS += -Wframe-larger-than=20480
ZSTD_OBJS := \
zfs_zstd.o \
zstd_sparc.o
ZSTD_UPSTREAM_OBJS := \
lib/common/entropy_common.o \
lib/common/error_private.o \
lib/common/fse_decompress.o \
lib/common/pool.o \
lib/common/zstd_common.o \
lib/compress/fse_compress.o \
lib/compress/hist.o \
lib/compress/huf_compress.o \
lib/compress/zstd_compress.o \
lib/compress/zstd_compress_literals.o \
lib/compress/zstd_compress_sequences.o \
lib/compress/zstd_compress_superblock.o \
lib/compress/zstd_double_fast.o \
lib/compress/zstd_fast.o \
lib/compress/zstd_lazy.o \
lib/compress/zstd_ldm.o \
lib/compress/zstd_opt.o \
lib/decompress/huf_decompress.o \
lib/decompress/zstd_ddict.o \
lib/decompress/zstd_decompress.o \
lib/decompress/zstd_decompress_block.o
zfs-objs += $(addprefix zstd/,$(ZSTD_OBJS) $(ZSTD_UPSTREAM_OBJS))
# Disable aarch64 neon SIMD instructions for kernel mode
$(addprefix $(obj)/zstd/,$(ZSTD_OBJS) $(ZSTD_UPSTREAM_OBJS)) : ccflags-y += -I$(zstd_include) $(ZFS_ZSTD_FLAGS)
$(addprefix $(obj)/zstd/,$(ZSTD_OBJS) $(ZSTD_UPSTREAM_OBJS)) : asflags-y += -I$(zstd_include)
$(addprefix $(obj)/zstd/,$(ZSTD_UPSTREAM_OBJS)) : ccflags-y += -include $(zstd_include)/aarch64_compat.h -include $(zstd_include)/zstd_compat_wrapper.h -Wp,-w
$(obj)/zstd/zfs_zstd.o : ccflags-y += -include $(zstd_include)/zstd_compat_wrapper.h
ZFS_OBJS := \
abd.o \
aggsum.o \
arc.o \
blake3_zfs.o \
blkptr.o \
bplist.o \
bpobj.o \
bptree.o \
bqueue.o \
btree.o \
dataset_kstats.o \
dbuf.o \
dbuf_stats.o \
ddt.o \
ddt_zap.o \
dmu.o \
dmu_diff.o \
dmu_object.o \
dmu_objset.o \
dmu_recv.o \
dmu_redact.o \
dmu_send.o \
dmu_traverse.o \
dmu_tx.o \
dmu_zfetch.o \
dnode.o \
dnode_sync.o \
dsl_bookmark.o \
dsl_crypt.o \
dsl_dataset.o \
dsl_deadlist.o \
dsl_deleg.o \
dsl_destroy.o \
dsl_dir.o \
dsl_pool.o \
dsl_prop.o \
dsl_scan.o \
dsl_synctask.o \
dsl_userhold.o \
edonr_zfs.o \
fm.o \
gzip.o \
hkdf.o \
lz4.o \
lz4_zfs.o \
lzjb.o \
metaslab.o \
mmp.o \
multilist.o \
objlist.o \
pathname.o \
range_tree.o \
refcount.o \
rrwlock.o \
sa.o \
sha256.o \
skein_zfs.o \
spa.o \
spa_boot.o \
spa_checkpoint.o \
spa_config.o \
spa_errlog.o \
spa_history.o \
spa_log_spacemap.o \
spa_misc.o \
spa_stats.o \
space_map.o \
space_reftree.o \
txg.o \
uberblock.o \
unique.o \
vdev.o \
vdev_cache.o \
vdev_draid.o \
vdev_draid_rand.o \
vdev_indirect.o \
vdev_indirect_births.o \
vdev_indirect_mapping.o \
vdev_initialize.o \
vdev_label.o \
vdev_mirror.o \
vdev_missing.o \
vdev_queue.o \
vdev_raidz.o \
vdev_raidz_math.o \
vdev_raidz_math_scalar.o \
vdev_rebuild.o \
vdev_removal.o \
vdev_root.o \
vdev_trim.o \
zap.o \
zap_leaf.o \
zap_micro.o \
zcp.o \
zcp_get.o \
zcp_global.o \
zcp_iter.o \
zcp_set.o \
zcp_synctask.o \
zfeature.o \
zfs_byteswap.o \
zfs_chksum.o \
zfs_fm.o \
zfs_fuid.o \
zfs_ioctl.o \
zfs_log.o \
zfs_onexit.o \
zfs_quota.o \
zfs_ratelimit.o \
zfs_replay.o \
zfs_rlock.o \
zfs_sa.o \
zfs_vnops.o \
zil.o \
zio.o \
zio_checksum.o \
zio_compress.o \
zio_inject.o \
zle.o \
zrlock.o \
zthr.o \
zvol.o
ZFS_OBJS_OS := \
abd_os.o \
arc_os.o \
mmp_os.o \
policy.o \
qat.o \
qat_compress.o \
qat_crypt.o \
spa_misc_os.o \
trace.o \
vdev_disk.o \
vdev_file.o \
zfs_acl.o \
zfs_ctldir.o \
zfs_debug.o \
zfs_dir.o \
zfs_file_os.o \
zfs_ioctl_os.o \
zfs_racct.o \
zfs_sysfs.o \
zfs_uio.o \
zfs_vfsops.o \
zfs_vnops_os.o \
zfs_znode.o \
zio_crypt.o \
zpl_ctldir.o \
zpl_export.o \
zpl_file.o \
zpl_inode.o \
zpl_super.o \
zpl_xattr.o \
zvol_os.o
ZFS_OBJS_X86 := \
vdev_raidz_math_avx2.o \
vdev_raidz_math_avx512bw.o \
vdev_raidz_math_avx512f.o \
vdev_raidz_math_sse2.o \
vdev_raidz_math_ssse3.o
ZFS_OBJS_ARM64 := \
vdev_raidz_math_aarch64_neon.o \
vdev_raidz_math_aarch64_neonx2.o
ZFS_OBJS_PPC_PPC64 := \
vdev_raidz_math_powerpc_altivec.o
zfs-objs += $(addprefix zfs/,$(ZFS_OBJS)) $(addprefix os/linux/zfs/,$(ZFS_OBJS_OS))
zfs-$(CONFIG_X86) += $(addprefix zfs/,$(ZFS_OBJS_X86))
zfs-$(CONFIG_ARM64) += $(addprefix zfs/,$(ZFS_OBJS_ARM64))
zfs-$(CONFIG_PPC) += $(addprefix zfs/,$(ZFS_OBJS_PPC_PPC64))
zfs-$(CONFIG_PPC64) += $(addprefix zfs/,$(ZFS_OBJS_PPC_PPC64))
# Suppress incorrect warnings from versions of objtool which are not
# aware of x86 EVEX prefix instructions used for AVX512.
OBJECT_FILES_NON_STANDARD_vdev_raidz_math_avx512bw.o := y
OBJECT_FILES_NON_STANDARD_vdev_raidz_math_avx512f.o := y
ifeq ($(CONFIG_ALTIVEC),y)
$(obj)/zfs/vdev_raidz_math_powerpc_altivec.o : c_flags += -maltivec
endif
Reference in New Issue View Git Blame Copy Permalink