kris/boringssl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
3c19830f6f
boringssl/crypto/fipsmodule/CMakeLists.txt
David Benjamin 4545503926 Add a constant-time pshufb-based GHASH implementation. 
We currently require clmul instructions for constant-time GHASH
on x86_64. Otherwise, it falls back to a variable-time 4-bit table
implementation. However, a significant proportion of clients lack these
instructions.

Inspired by vpaes, we can use pshufb and a slightly different order of
incorporating the bits to make a constant-time GHASH. This requires
SSSE3, which is very common. Benchmarking old machines we had on hand,
it appears to be a no-op on Sandy Bridge and a small slowdown for
Penryn.

Sandy Bridge (Intel Pentium CPU 987 @ 1.50GHz):
(Note: these numbers are before 16-byte-aligning the table. That was an
improvement on Penryn, so it's possible Sandy Bridge is now better.)
Before:
Did 4244750 AES-128-GCM (16 bytes) seal operations in 4015000us (1057222.9 ops/sec): 16.9 MB/s
Did 442000 AES-128-GCM (1350 bytes) seal operations in 4016000us (110059.8 ops/sec): 148.6 MB/s
Did 84000 AES-128-GCM (8192 bytes) seal operations in 4015000us (20921.5 ops/sec): 171.4 MB/s
Did 3349250 AES-256-GCM (16 bytes) seal operations in 4016000us (833976.6 ops/sec): 13.3 MB/s
Did 343500 AES-256-GCM (1350 bytes) seal operations in 4016000us (85532.9 ops/sec): 115.5 MB/s
Did 65250 AES-256-GCM (8192 bytes) seal operations in 4015000us (16251.6 ops/sec): 133.1 MB/s
After:
Did 4229250 AES-128-GCM (16 bytes) seal operations in 4016000us (1053100.1 ops/sec): 16.8 MB/s [-0.4%]
Did 442250 AES-128-GCM (1350 bytes) seal operations in 4016000us (110122.0 ops/sec): 148.7 MB/s [+0.1%]
Did 83500 AES-128-GCM (8192 bytes) seal operations in 4015000us (20797.0 ops/sec): 170.4 MB/s [-0.6%]
Did 3286500 AES-256-GCM (16 bytes) seal operations in 4016000us (818351.6 ops/sec): 13.1 MB/s [-1.9%]
Did 342750 AES-256-GCM (1350 bytes) seal operations in 4015000us (85367.4 ops/sec): 115.2 MB/s [-0.2%]
Did 65250 AES-256-GCM (8192 bytes) seal operations in 4016000us (16247.5 ops/sec): 133.1 MB/s [-0.0%]

Penryn (Intel Core 2 Duo CPU P8600 @ 2.40GHz):
Before:
Did 1179000 AES-128-GCM (16 bytes) seal operations in 1000139us (1178836.1 ops/sec): 18.9 MB/s
Did 97000 AES-128-GCM (1350 bytes) seal operations in 1006347us (96388.2 ops/sec): 130.1 MB/s
Did 18000 AES-128-GCM (8192 bytes) seal operations in 1028943us (17493.7 ops/sec): 143.3 MB/s
Did 977000 AES-256-GCM (16 bytes) seal operations in 1000197us (976807.6 ops/sec): 15.6 MB/s
Did 82000 AES-256-GCM (1350 bytes) seal operations in 1012434us (80992.9 ops/sec): 109.3 MB/s
Did 15000 AES-256-GCM (8192 bytes) seal operations in 1006528us (14902.7 ops/sec): 122.1 MB/s
After:
Did 1306000 AES-128-GCM (16 bytes) seal operations in 1000153us (1305800.2 ops/sec): 20.9 MB/s [+10.8%]
Did 94000 AES-128-GCM (1350 bytes) seal operations in 1009852us (93082.9 ops/sec): 125.7 MB/s [-3.4%]
Did 17000 AES-128-GCM (8192 bytes) seal operations in 1012096us (16796.8 ops/sec): 137.6 MB/s [-4.0%]
Did 1070000 AES-256-GCM (16 bytes) seal operations in 1000929us (1069006.9 ops/sec): 17.1 MB/s [+9.4%]
Did 79000 AES-256-GCM (1350 bytes) seal operations in 1002209us (78825.9 ops/sec): 106.4 MB/s [-2.7%]
Did 15000 AES-256-GCM (8192 bytes) seal operations in 1061489us (14131.1 ops/sec): 115.8 MB/s [-5.2%]

Change-Id: I1c3760a77af7bee4aee3745d1c648d9e34594afb
Reviewed-on: https://boringssl-review.googlesource.com/c/34267
Commit-Queue: David Benjamin <davidben@google.com>
Reviewed-by: Adam Langley <agl@google.com>
2019-01-24 17:19:21 +00:00

208 lines
5.9 KiB
CMake
Raw Blame History

include_directories(../../include)
if(${ARCH} STREQUAL "x86_64")
set(
BCM_ASM_SOURCES
aesni-gcm-x86_64.${ASM_EXT}
aesni-x86_64.${ASM_EXT}
aes-x86_64.${ASM_EXT}
bsaes-x86_64.${ASM_EXT}
ghash-ssse3-x86_64.${ASM_EXT}
ghash-x86_64.${ASM_EXT}
md5-x86_64.${ASM_EXT}
p256-x86_64-asm.${ASM_EXT}
p256_beeu-x86_64-asm.${ASM_EXT}
rdrand-x86_64.${ASM_EXT}
rsaz-avx2.${ASM_EXT}
sha1-x86_64.${ASM_EXT}
sha256-x86_64.${ASM_EXT}
sha512-x86_64.${ASM_EXT}
vpaes-x86_64.${ASM_EXT}
x86_64-mont5.${ASM_EXT}
x86_64-mont.${ASM_EXT}
)
endif()
if(${ARCH} STREQUAL "x86")
set(
BCM_ASM_SOURCES
aes-586.${ASM_EXT}
aesni-x86.${ASM_EXT}
bn-586.${ASM_EXT}
co-586.${ASM_EXT}
ghash-x86.${ASM_EXT}
md5-586.${ASM_EXT}
sha1-586.${ASM_EXT}
sha256-586.${ASM_EXT}
sha512-586.${ASM_EXT}
vpaes-x86.${ASM_EXT}
x86-mont.${ASM_EXT}
)
endif()
if(${ARCH} STREQUAL "arm")
set(
BCM_ASM_SOURCES
aes-armv4.${ASM_EXT}
aesv8-armx.${ASM_EXT}
armv4-mont.${ASM_EXT}
bsaes-armv7.${ASM_EXT}
ghash-armv4.${ASM_EXT}
ghashv8-armx.${ASM_EXT}
sha1-armv4-large.${ASM_EXT}
sha256-armv4.${ASM_EXT}
sha512-armv4.${ASM_EXT}
)
endif()
if(${ARCH} STREQUAL "aarch64")
set(
BCM_ASM_SOURCES
aesv8-armx.${ASM_EXT}
armv8-mont.${ASM_EXT}
ghashv8-armx.${ASM_EXT}
sha1-armv8.${ASM_EXT}
sha256-armv8.${ASM_EXT}
sha512-armv8.${ASM_EXT}
)
endif()
if(${ARCH} STREQUAL "ppc64le")
set(
BCM_ASM_SOURCES
aesp8-ppc.${ASM_EXT}
ghashp8-ppc.${ASM_EXT}
)
endif()
perlasm(aes-586.${ASM_EXT} aes/asm/aes-586.pl)
perlasm(aes-armv4.${ASM_EXT} aes/asm/aes-armv4.pl)
perlasm(aesni-gcm-x86_64.${ASM_EXT} modes/asm/aesni-gcm-x86_64.pl)
perlasm(aesni-x86_64.${ASM_EXT} aes/asm/aesni-x86_64.pl)
perlasm(aesni-x86.${ASM_EXT} aes/asm/aesni-x86.pl)
perlasm(aesp8-ppc.${ASM_EXT} aes/asm/aesp8-ppc.pl)
perlasm(aesv8-armx.${ASM_EXT} aes/asm/aesv8-armx.pl)
perlasm(aes-x86_64.${ASM_EXT} aes/asm/aes-x86_64.pl)
perlasm(armv4-mont.${ASM_EXT} bn/asm/armv4-mont.pl)
perlasm(armv8-mont.${ASM_EXT} bn/asm/armv8-mont.pl)
perlasm(bn-586.${ASM_EXT} bn/asm/bn-586.pl)
perlasm(bsaes-armv7.${ASM_EXT} aes/asm/bsaes-armv7.pl)
perlasm(bsaes-x86_64.${ASM_EXT} aes/asm/bsaes-x86_64.pl)
perlasm(co-586.${ASM_EXT} bn/asm/co-586.pl)
perlasm(ghash-armv4.${ASM_EXT} modes/asm/ghash-armv4.pl)
perlasm(ghashp8-ppc.${ASM_EXT} modes/asm/ghashp8-ppc.pl)
perlasm(ghashv8-armx.${ASM_EXT} modes/asm/ghashv8-armx.pl)
perlasm(ghash-ssse3-x86_64.${ASM_EXT} modes/asm/ghash-ssse3-x86_64.pl)
perlasm(ghash-x86_64.${ASM_EXT} modes/asm/ghash-x86_64.pl)
perlasm(ghash-x86.${ASM_EXT} modes/asm/ghash-x86.pl)
perlasm(md5-586.${ASM_EXT} md5/asm/md5-586.pl)
perlasm(md5-x86_64.${ASM_EXT} md5/asm/md5-x86_64.pl)
perlasm(p256-x86_64-asm.${ASM_EXT} ec/asm/p256-x86_64-asm.pl)
perlasm(p256_beeu-x86_64-asm.${ASM_EXT} ec/asm/p256_beeu-x86_64-asm.pl)
perlasm(rdrand-x86_64.${ASM_EXT} rand/asm/rdrand-x86_64.pl)
perlasm(rsaz-avx2.${ASM_EXT} bn/asm/rsaz-avx2.pl)
perlasm(sha1-586.${ASM_EXT} sha/asm/sha1-586.pl)
perlasm(sha1-armv4-large.${ASM_EXT} sha/asm/sha1-armv4-large.pl)
perlasm(sha1-armv8.${ASM_EXT} sha/asm/sha1-armv8.pl)
perlasm(sha1-x86_64.${ASM_EXT} sha/asm/sha1-x86_64.pl)
perlasm(sha256-586.${ASM_EXT} sha/asm/sha256-586.pl)
perlasm(sha256-armv4.${ASM_EXT} sha/asm/sha256-armv4.pl)
perlasm(sha256-armv8.${ASM_EXT} sha/asm/sha512-armv8.pl)
perlasm(sha256-x86_64.${ASM_EXT} sha/asm/sha512-x86_64.pl)
perlasm(sha512-586.${ASM_EXT} sha/asm/sha512-586.pl)
perlasm(sha512-armv4.${ASM_EXT} sha/asm/sha512-armv4.pl)
perlasm(sha512-armv8.${ASM_EXT} sha/asm/sha512-armv8.pl)
perlasm(sha512-x86_64.${ASM_EXT} sha/asm/sha512-x86_64.pl)
perlasm(vpaes-x86_64.${ASM_EXT} aes/asm/vpaes-x86_64.pl)
perlasm(vpaes-x86.${ASM_EXT} aes/asm/vpaes-x86.pl)
perlasm(x86_64-mont5.${ASM_EXT} bn/asm/x86_64-mont5.pl)
perlasm(x86_64-mont.${ASM_EXT} bn/asm/x86_64-mont.pl)
perlasm(x86-mont.${ASM_EXT} bn/asm/x86-mont.pl)
if(FIPS_DELOCATE)
if(OPENSSL_NO_ASM)
# If OPENSSL_NO_ASM was defined then ASM will not have been enabled, but in
# FIPS mode we have to have it because the module build requires going via
# textual assembly.
enable_language(ASM)
endif()
add_library(
bcm_c_generated_asm
STATIC
bcm.c
)
add_dependencies(bcm_c_generated_asm global_target)
set_target_properties(bcm_c_generated_asm PROPERTIES COMPILE_OPTIONS "-S")
set_target_properties(bcm_c_generated_asm PROPERTIES POSITION_INDEPENDENT_CODE ON)
go_executable(delocate boringssl.googlesource.com/boringssl/util/fipstools/delocate)
add_custom_command(
OUTPUT bcm-delocated.S
COMMAND ./delocate -a $<TARGET_FILE:bcm_c_generated_asm> -o bcm-delocated.S ${BCM_ASM_SOURCES}
DEPENDS bcm_c_generated_asm delocate ${BCM_ASM_SOURCES}
WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}
)
add_library(
bcm_hashunset
STATIC
bcm-delocated.S
)
add_dependencies(bcm_hashunset global_target)
set_target_properties(bcm_hashunset PROPERTIES POSITION_INDEPENDENT_CODE ON)
set_target_properties(bcm_hashunset PROPERTIES LINKER_LANGUAGE C)
go_executable(inject_hash
boringssl.googlesource.com/boringssl/util/fipstools/inject_hash)
add_custom_command(
OUTPUT bcm.o
COMMAND ./inject_hash -o bcm.o -in-archive $<TARGET_FILE:bcm_hashunset>
DEPENDS bcm_hashunset inject_hash
WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}
)
# The outputs of add_custom_command cannot be referenced outside of the
# CMakeLists.txt that defines it. Thus we have to wrap bcm.o in a custom target
# so that crypto can depend on it.
add_custom_target(bcm_o_target DEPENDS bcm.o)
add_library(
fipsmodule
OBJECT
is_fips.c
)
add_dependencies(fipsmodule global_target)
set_target_properties(fipsmodule PROPERTIES LINKER_LANGUAGE C)
else()
add_library(
fipsmodule
OBJECT
bcm.c
is_fips.c
${BCM_ASM_SOURCES}
)
add_dependencies(fipsmodule global_target)
endif()
Reference in New Issue View Git Blame Copy Permalink