crypto: blowfish - add AVX2/x86_64 implementation of blowfish cipher

Patch adds AVX2/x86-64 implementation of Blowfish cipher, requiring 32 parallel blocks for input (256 bytes). Table look-ups are performed using vpgatherdd instruction directly from vector registers and thus should be faster than earlier implementations. Signed-off-by: Jussi Kivilinna <[email protected]> Signed-off-by: Herbert Xu <[email protected]>
Baughn · Apr 25, 2013 · 6048801 · 6048801
1 parent ad8b7c3
commit 6048801
Show file tree

Hide file tree

Showing 8 changed files with 1,127 additions and 24 deletions.
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
@@ -3,6 +3,8 @@
 #
 
 avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no)
+avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
+					$(comma)4)$(comma)%ymm2,yes,no)
 
 obj-$(CONFIG_CRYPTO_ABLK_HELPER_X86) += ablk_helper.o
 obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
@@ -38,6 +40,11 @@ ifeq ($(avx_supported),yes)
 	obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
 endif
 
+# These modules require assembler to support AVX2.
+ifeq ($(avx2_supported),yes)
+	obj-$(CONFIG_CRYPTO_BLOWFISH_AVX2_X86_64) += blowfish-avx2.o
+endif
+
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
 twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
 salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o
@@ -62,6 +69,10 @@ ifeq ($(avx_supported),yes)
 				serpent_avx_glue.o
 endif
 
+ifeq ($(avx2_supported),yes)
+	blowfish-avx2-y := blowfish-avx2-asm_64.o blowfish_avx2_glue.o
+endif
+
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
 sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o