4616bb1e6e
This affects bignum and sha. Also now that we're passing the SSE2 flag, revert the change to ghash-x86.pl which unconditionally sets $sse2, just to minimize upstream divergence. Chromium assumes SSE2 support, so relying on it is okay. See https://crbug.com/349320. Note: this change needs to be mirrored in Chromium to take. bssl speed numbers: SSE2: Did 552 RSA 2048 signing operations in 3007814us (183.5 ops/sec) Did 19003 RSA 2048 verify operations in 3070779us (6188.3 ops/sec) Did 72 RSA 4096 signing operations in 3055885us (23.6 ops/sec) Did 4650 RSA 4096 verify operations in 3024926us (1537.2 ops/sec) Without SSE2: Did 350 RSA 2048 signing operations in 3042021us (115.1 ops/sec) Did 11760 RSA 2048 verify operations in 3003197us (3915.8 ops/sec) Did 46 RSA 4096 signing operations in 3042692us (15.1 ops/sec) Did 3400 RSA 4096 verify operations in 3083035us (1102.8 ops/sec) SSE2: Did 16407000 SHA-1 (16 bytes) operations in 3000141us (5468743.0 ops/sec): 87.5 MB/s Did 4367000 SHA-1 (256 bytes) operations in 3000436us (1455455.1 ops/sec): 372.6 MB/s Did 185000 SHA-1 (8192 bytes) operations in 3002666us (61611.9 ops/sec): 504.7 MB/s Did 9444000 SHA-256 (16 bytes) operations in 3000052us (3147945.4 ops/sec): 50.4 MB/s Did 2283000 SHA-256 (256 bytes) operations in 3000457us (760884.1 ops/sec): 194.8 MB/s Did 89000 SHA-256 (8192 bytes) operations in 3016024us (29509.0 ops/sec): 241.7 MB/s Did 5550000 SHA-512 (16 bytes) operations in 3000350us (1849784.2 ops/sec): 29.6 MB/s Did 1820000 SHA-512 (256 bytes) operations in 3001039us (606456.6 ops/sec): 155.3 MB/s Did 93000 SHA-512 (8192 bytes) operations in 3007874us (30918.8 ops/sec): 253.3 MB/s Without SSE2: Did 10573000 SHA-1 (16 bytes) operations in 3000261us (3524026.7 ops/sec): 56.4 MB/s Did 2937000 SHA-1 (256 bytes) operations in 3000621us (978797.4 ops/sec): 250.6 MB/s Did 123000 SHA-1 (8192 bytes) operations in 3033202us (40551.2 ops/sec): 332.2 MB/s Did 5846000 SHA-256 (16 bytes) operations in 3000294us (1948475.7 ops/sec): 31.2 MB/s Did 1377000 SHA-256 (256 bytes) operations in 3000335us (458948.8 ops/sec): 117.5 MB/s Did 54000 SHA-256 (8192 bytes) operations in 3027962us (17833.8 ops/sec): 146.1 MB/s Did 2075000 SHA-512 (16 bytes) operations in 3000967us (691443.8 ops/sec): 11.1 MB/s Did 638000 SHA-512 (256 bytes) operations in 3000576us (212625.8 ops/sec): 54.4 MB/s Did 30000 SHA-512 (8192 bytes) operations in 3042797us (9859.3 ops/sec): 80.8 MB/s BUG=430237 Change-Id: I47d1c1ffcd71afe4f4a192272f8cb92af9505ee1 Reviewed-on: https://boringssl-review.googlesource.com/4130 Reviewed-by: Adam Langley <agl@google.com>
200 lines
4.1 KiB
CMake
200 lines
4.1 KiB
CMake
include_directories(. ../include)
|
|
|
|
if(APPLE)
|
|
if (${ARCH} STREQUAL "x86")
|
|
set(PERLASM_FLAGS "-fPIC -DOPENSSL_IA32_SSE2")
|
|
endif()
|
|
set(PERLASM_STYLE macosx)
|
|
set(ASM_EXT S)
|
|
enable_language(ASM)
|
|
elseif(UNIX)
|
|
if (${ARCH} STREQUAL "aarch64")
|
|
# The "armx" Perl scripts look for "64" in the style argument
|
|
# in order to decide whether to generate 32- or 64-bit asm.
|
|
set(PERLASM_STYLE linux64)
|
|
elseif (${ARCH} STREQUAL "x86")
|
|
set(PERLASM_FLAGS "-fPIC -DOPENSSL_IA32_SSE2")
|
|
set(PERLASM_STYLE elf)
|
|
else()
|
|
set(PERLASM_STYLE elf)
|
|
endif()
|
|
set(ASM_EXT S)
|
|
enable_language(ASM)
|
|
else()
|
|
if (CMAKE_CL_64)
|
|
message("Using nasm")
|
|
set(PERLASM_STYLE nasm)
|
|
else()
|
|
message("Using win32n")
|
|
set(PERLASM_STYLE win32n)
|
|
set(PERLASM_FLAGS "-DOPENSSL_IA32_SSE2")
|
|
endif()
|
|
|
|
# On Windows, we use the NASM output, specifically built with Yasm.
|
|
set(ASM_EXT asm)
|
|
enable_language(ASM_NASM)
|
|
endif()
|
|
|
|
function(perlasm dest src)
|
|
add_custom_command(
|
|
OUTPUT ${dest}
|
|
COMMAND ${PERL_EXECUTABLE} ${CMAKE_CURRENT_SOURCE_DIR}/${src} ${PERLASM_STYLE} ${PERLASM_FLAGS} ${ARGN} > ${dest}
|
|
DEPENDS
|
|
${src}
|
|
${PROJECT_SOURCE_DIR}/crypto/perlasm/x86_64-xlate.pl
|
|
${PROJECT_SOURCE_DIR}/crypto/perlasm/x86asm.pl
|
|
${PROJECT_SOURCE_DIR}/crypto/perlasm/x86gas.pl
|
|
${PROJECT_SOURCE_DIR}/crypto/perlasm/x86masm.pl
|
|
${PROJECT_SOURCE_DIR}/crypto/perlasm/x86nasm.pl
|
|
WORKING_DIRECTORY .
|
|
)
|
|
endfunction()
|
|
|
|
if (${ARCH} STREQUAL "x86_64")
|
|
set(
|
|
CRYPTO_ARCH_SOURCES
|
|
|
|
cpu-x86_64-asm.${ASM_EXT}
|
|
cpu-intel.c
|
|
)
|
|
endif()
|
|
|
|
if (${ARCH} STREQUAL "x86")
|
|
set(
|
|
CRYPTO_ARCH_SOURCES
|
|
|
|
cpu-x86-asm.${ASM_EXT}
|
|
cpu-intel.c
|
|
)
|
|
endif()
|
|
|
|
if (${ARCH} STREQUAL "arm")
|
|
set(
|
|
CRYPTO_ARCH_SOURCES
|
|
|
|
cpu-arm.c
|
|
cpu-arm-asm.S
|
|
)
|
|
endif()
|
|
|
|
if (${ARCH} STREQUAL "aarch64")
|
|
set(
|
|
CRYPTO_ARCH_SOURCES
|
|
|
|
cpu-arm.c
|
|
)
|
|
endif()
|
|
|
|
# Level 0.1 - depends on nothing outside this set.
|
|
add_subdirectory(stack)
|
|
add_subdirectory(lhash)
|
|
add_subdirectory(err)
|
|
add_subdirectory(buf)
|
|
add_subdirectory(base64)
|
|
add_subdirectory(bytestring)
|
|
|
|
# Level 0.2 - depends on nothing but itself
|
|
add_subdirectory(sha)
|
|
add_subdirectory(md4)
|
|
add_subdirectory(md5)
|
|
add_subdirectory(modes)
|
|
add_subdirectory(aes)
|
|
add_subdirectory(des)
|
|
add_subdirectory(rc4)
|
|
add_subdirectory(conf)
|
|
add_subdirectory(chacha)
|
|
add_subdirectory(poly1305)
|
|
|
|
# Level 1, depends only on 0.*
|
|
add_subdirectory(digest)
|
|
add_subdirectory(cipher)
|
|
add_subdirectory(rand)
|
|
add_subdirectory(bio)
|
|
add_subdirectory(bn)
|
|
add_subdirectory(obj)
|
|
add_subdirectory(asn1)
|
|
|
|
# Level 2
|
|
add_subdirectory(engine)
|
|
add_subdirectory(dh)
|
|
add_subdirectory(dsa)
|
|
add_subdirectory(rsa)
|
|
add_subdirectory(ec)
|
|
add_subdirectory(ecdh)
|
|
add_subdirectory(ecdsa)
|
|
add_subdirectory(hmac)
|
|
|
|
# Level 3
|
|
add_subdirectory(evp)
|
|
add_subdirectory(hkdf)
|
|
add_subdirectory(pem)
|
|
add_subdirectory(x509)
|
|
add_subdirectory(x509v3)
|
|
|
|
# Level 4
|
|
add_subdirectory(pkcs8)
|
|
|
|
add_library(
|
|
crypto
|
|
|
|
crypto.c
|
|
mem.c
|
|
thread.c
|
|
ex_data.c
|
|
ex_data_impl.c
|
|
time_support.c
|
|
directory_posix.c
|
|
directory_win.c
|
|
|
|
${CRYPTO_ARCH_SOURCES}
|
|
|
|
$<TARGET_OBJECTS:stack>
|
|
$<TARGET_OBJECTS:lhash>
|
|
$<TARGET_OBJECTS:err>
|
|
$<TARGET_OBJECTS:base64>
|
|
$<TARGET_OBJECTS:bytestring>
|
|
$<TARGET_OBJECTS:sha>
|
|
$<TARGET_OBJECTS:md4>
|
|
$<TARGET_OBJECTS:md5>
|
|
$<TARGET_OBJECTS:digest>
|
|
$<TARGET_OBJECTS:cipher>
|
|
$<TARGET_OBJECTS:modes>
|
|
$<TARGET_OBJECTS:aes>
|
|
$<TARGET_OBJECTS:des>
|
|
$<TARGET_OBJECTS:rc4>
|
|
$<TARGET_OBJECTS:conf>
|
|
$<TARGET_OBJECTS:chacha>
|
|
$<TARGET_OBJECTS:poly1305>
|
|
$<TARGET_OBJECTS:buf>
|
|
$<TARGET_OBJECTS:bn>
|
|
$<TARGET_OBJECTS:bio>
|
|
$<TARGET_OBJECTS:rand>
|
|
$<TARGET_OBJECTS:obj>
|
|
$<TARGET_OBJECTS:asn1>
|
|
$<TARGET_OBJECTS:engine>
|
|
$<TARGET_OBJECTS:dh>
|
|
$<TARGET_OBJECTS:dsa>
|
|
$<TARGET_OBJECTS:rsa>
|
|
$<TARGET_OBJECTS:ec>
|
|
$<TARGET_OBJECTS:ecdh>
|
|
$<TARGET_OBJECTS:ecdsa>
|
|
$<TARGET_OBJECTS:hmac>
|
|
$<TARGET_OBJECTS:evp>
|
|
$<TARGET_OBJECTS:hkdf>
|
|
$<TARGET_OBJECTS:pem>
|
|
$<TARGET_OBJECTS:x509>
|
|
$<TARGET_OBJECTS:x509v3>
|
|
$<TARGET_OBJECTS:pkcs8>
|
|
)
|
|
|
|
add_executable(
|
|
constant_time_test
|
|
|
|
constant_time_test.c
|
|
)
|
|
|
|
target_link_libraries(constant_time_test crypto)
|
|
|
|
perlasm(cpu-x86_64-asm.${ASM_EXT} cpu-x86_64-asm.pl)
|
|
perlasm(cpu-x86-asm.${ASM_EXT} cpu-x86-asm.pl)
|