4c128c7823
It adds vectorized ChaCha20 implementation based on libgcrypt cipher/chacha20-aarch64.S. It is used as default and only little-endian is supported (BE uses generic code). As for generic implementation, the last step that XOR with the input is omited. The final state register clearing is also omitted. On a virtualized Linux on Apple M1 it shows the following improvements (using formatted bench-arc4random data): GENERIC MB/s ----------------------------------------------- arc4random [single-thread] 380.89 arc4random_buf(16) [single-thread] 500.73 arc4random_buf(32) [single-thread] 552.61 arc4random_buf(48) [single-thread] 566.82 arc4random_buf(64) [single-thread] 574.01 arc4random_buf(80) [single-thread] 581.02 arc4random_buf(96) [single-thread] 591.19 arc4random_buf(112) [single-thread] 592.29 arc4random_buf(128) [single-thread] 596.43 ----------------------------------------------- OPTIMIZED MB/s ----------------------------------------------- arc4random [single-thread] 569.60 arc4random_buf(16) [single-thread] 825.78 arc4random_buf(32) [single-thread] 987.03 arc4random_buf(48) [single-thread] 1042.39 arc4random_buf(64) [single-thread] 1075.50 arc4random_buf(80) [single-thread] 1094.68 arc4random_buf(96) [single-thread] 1130.16 arc4random_buf(112) [single-thread] 1129.58 arc4random_buf(128) [single-thread] 1137.91 ----------------------------------------------- Checked on aarch64-linux-gnu.
75 lines
1.7 KiB
Makefile
75 lines
1.7 KiB
Makefile
long-double-fcts = yes
|
|
|
|
ifeq (yes,$(aarch64-bti))
|
|
# Mark linker output BTI compatible, it warns on non-BTI inputs.
|
|
sysdep-LDFLAGS += -Wl,-z,force-bti
|
|
# Make warnings fatal outside the test system.
|
|
LDFLAGS-lib.so += -Wl,--fatal-warnings
|
|
LDFLAGS-rtld += -Wl,-z,force-bti,--fatal-warnings
|
|
endif
|
|
|
|
ifeq ($(subdir),elf)
|
|
sysdep-dl-routines += dl-bti
|
|
|
|
tests += tst-audit26 \
|
|
tst-audit27
|
|
|
|
modules-names += \
|
|
tst-audit26mod \
|
|
tst-auditmod26 \
|
|
tst-audit27mod \
|
|
tst-auditmod27
|
|
|
|
$(objpfx)tst-audit26: $(objpfx)tst-audit26mod.so \
|
|
$(objpfx)tst-auditmod26.so
|
|
LDFLAGS-tst-audit26 += -Wl,-z,lazy
|
|
tst-audit26-ENV = LD_AUDIT=$(objpfx)tst-auditmod26.so
|
|
|
|
$(objpfx)tst-audit27: $(objpfx)tst-audit27mod.so \
|
|
$(objpfx)tst-auditmod27.so
|
|
$(objpfx)tst-audit27mod.so: $(libsupport)
|
|
LDFLAGS-tst-audit27 += -Wl,-z,lazy
|
|
tst-audit27-ENV = LD_AUDIT=$(objpfx)tst-auditmod27.so
|
|
endif
|
|
|
|
ifeq ($(subdir),elf)
|
|
sysdep-rtld-routines += dl-start
|
|
sysdep-dl-routines += tlsdesc dl-tlsdesc
|
|
gen-as-const-headers += dl-link.sym
|
|
|
|
tests-internal += tst-ifunc-arg-1 tst-ifunc-arg-2
|
|
|
|
ifeq (yes,$(aarch64-variant-pcs))
|
|
tests += tst-vpcs
|
|
modules-names += tst-vpcs-mod
|
|
LDFLAGS-tst-vpcs-mod.so = -Wl,-z,lazy
|
|
$(objpfx)tst-vpcs: $(objpfx)tst-vpcs-mod.so
|
|
endif
|
|
endif
|
|
|
|
ifeq ($(subdir),csu)
|
|
gen-as-const-headers += tlsdesc.sym
|
|
endif
|
|
|
|
ifeq ($(subdir),stdlib)
|
|
sysdep_routines += chacha20-aarch64
|
|
endif
|
|
|
|
ifeq ($(subdir),gmon)
|
|
CFLAGS-mcount.c += -mgeneral-regs-only
|
|
endif
|
|
|
|
ifeq ($(subdir),math)
|
|
CPPFLAGS += -I../soft-fp
|
|
endif
|
|
|
|
ifeq ($(subdir),misc)
|
|
sysdep_headers += sys/ifunc.h
|
|
sysdep_routines += __mtag_tag_zero_region \
|
|
__mtag_tag_region
|
|
endif
|
|
|
|
ifeq ($(subdir),malloc)
|
|
sysdep_malloc_debug_routines = __mtag_tag_zero_region __mtag_tag_region
|
|
endif
|