c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2025-01-12 19:20:28 +03:00
Code Issues Packages Projects Releases Wiki Activity
b3ad3f48d9
mirror_zfs/module/Kbuild.in
Richard Yao 677c6f8457
btree: Implement faster binary search algorithm 
This implements a binary search algorithm for B-Trees that reduces
branching to the absolute minimum necessary for a binary search
algorithm. It also enables the compiler to inline the comparator to
ensure that the only slowdown when doing binary search is from waiting
for memory accesses. Additionally, it instructs the compiler to unroll
the loop, which gives an additional 40% improve with Clang and 8%
improvement with GCC.

Consumers must opt into using the faster algorithm. At present, only
B-Trees used inside kernel code have been modified to use the faster
algorithm.

Micro-benchmarks suggest that this can improve binary search performance
by up to 3.5 times when compiling with Clang 16 and up to 1.9 times when
compiling with GCC 12.2.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu>
Closes #14866
2023-05-26 10:03:12 -07:00

499 lines
12 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
# Generated binary search code is particularly bad with this optimization.
# Oddly, range_tree.c is not affected when unrolling is not done and dsl_scan.c
# is not affected when unrolling is done.
# Disable it until the following upstream issue is resolved:
# https://github.com/llvm/llvm-project/issues/62790
ifeq ($(CONFIG_X86),y)
ifeq ($(CONFIG_CC_IS_CLANG),y)
CFLAGS_zfs/dsl_scan.o += -mllvm -x86-cmov-converter=false
CFLAGS_zfs/metaslab.o += -mllvm -x86-cmov-converter=false
CFLAGS_zfs/range_tree.o += -mllvm -x86-cmov-converter=false
CFLAGS_zfs/zap_micro.o += -mllvm -x86-cmov-converter=false
endif
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) $(ZFS_MODULE_CPPFLAGS)
ifeq ($(CONFIG_ARM64),y)
CFLAGS_REMOVE_zcommon/zfs_fletcher_aarch64_neon.o += -mgeneral-regs-only
CFLAGS_REMOVE_zfs/vdev_raidz_math_aarch64_neon.o += -mgeneral-regs-only
CFLAGS_REMOVE_zfs/vdev_raidz_math_aarch64_neonx2.o += -mgeneral-regs-only
endif
# 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-zone.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/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_generic.o \
algs/sha2/sha256_impl.o \
algs/sha2/sha512_impl.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/sha2/sha256-x86_64.o \
asm-x86_64/sha2/sha512-x86_64.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
ICP_OBJS_X86 := \
algs/aes/aes_impl_aesni.o \
algs/aes/aes_impl_x86-64.o \
algs/modes/gcm_pclmulqdq.o
ICP_OBJS_ARM := \
asm-arm/sha2/sha256-armv7.o \
asm-arm/sha2/sha512-armv7.o
ICP_OBJS_ARM64 := \
asm-aarch64/blake3/b3_aarch64_sse2.o \
asm-aarch64/blake3/b3_aarch64_sse41.o \
asm-aarch64/sha2/sha256-armv8.o \
asm-aarch64/sha2/sha512-armv8.o
ICP_OBJS_PPC_PPC64 := \
asm-ppc64/blake3/b3_ppc64le_sse2.o \
asm-ppc64/blake3/b3_ppc64le_sse41.o \
asm-ppc64/sha2/sha256-p8.o \
asm-ppc64/sha2/sha512-p8.o \
asm-ppc64/sha2/sha256-ppc.o \
asm-ppc64/sha2/sha512-ppc.o
zfs-objs += $(addprefix icp/,$(ICP_OBJS))
zfs-$(CONFIG_X86) += $(addprefix icp/,$(ICP_OBJS_X86))
zfs-$(CONFIG_UML_X86)+= $(addprefix icp/,$(ICP_OBJS_X86))
zfs-$(CONFIG_X86_64) += $(addprefix icp/,$(ICP_OBJS_X86_64))
zfs-$(CONFIG_ARM) += $(addprefix icp/,$(ICP_OBJS_ARM))
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) -I$(zfs_include)/os/linux/spl -I$(zfs_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) -I$(zfs_include)/os/linux/spl -I$(zfs_include)
# Suppress objtool "return with modified stack frame" warnings.
OBJECT_FILES_NON_STANDARD_aesni-gcm-x86_64.o := y
# Suppress objtool "unsupported stack pointer realignment" warnings.
# See #6950 for the reasoning.
OBJECT_FILES_NON_STANDARD_sha256-x86_64.o := y
OBJECT_FILES_NON_STANDARD_sha512-x86_64.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_UML_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 \
brt.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 \
sha2_zfs.o \
skein_zfs.o \
spa.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_impl.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_UML_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