diff options
| author | Huang Ying <ying.huang@intel.com> | 2009-11-23 19:55:22 +0800 |
|---|---|---|
| committer | Herbert Xu <herbert@gondor.apana.org.au> | 2009-11-23 19:55:22 +0800 |
| commit | 564ec0ec05ac6ee409bde81f7ef27a3dadbf3a6a (patch) | |
| tree | b4bb4e29cdfc2ceb90ac10ed4da139546375faa7 /arch/x86/crypto | |
| parent | b369e521237d6ef21c453f3ac4f4b8577ec14f87 (diff) | |
| download | kernel_samsung_smdk4412-564ec0ec05ac6ee409bde81f7ef27a3dadbf3a6a.zip kernel_samsung_smdk4412-564ec0ec05ac6ee409bde81f7ef27a3dadbf3a6a.tar.gz kernel_samsung_smdk4412-564ec0ec05ac6ee409bde81f7ef27a3dadbf3a6a.tar.bz2 | |
crypto: ghash-clmulni-intel - Use gas macro for PCLMULQDQ-NI and PSHUFB
Old binutils do not support PCLMULQDQ-NI and PSHUFB, to make kernel
can be compiled by them, .byte code is used instead of assembly
instructions. But the readability and flexibility of raw .byte code is
not good.
So corresponding assembly instruction like gas macro is used instead.
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/x86/crypto')
| -rw-r--r-- | arch/x86/crypto/ghash-clmulni-intel_asm.S | 29 |
1 files changed, 10 insertions, 19 deletions
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S index 5958498..1528dc4 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_asm.S +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -17,7 +17,7 @@ */ #include <linux/linkage.h> -#include <asm/i387.h> +#include <asm/inst.h> .align 16 .Lbswap_mask: @@ -56,12 +56,9 @@ __clmul_gf128mul_ble: pxor DATA, T2 pxor SHASH, T3 - # pclmulqdq $0x00, SHASH, DATA # DATA = a0 * b0 - .byte 0x66, 0x0f, 0x3a, 0x44, 0xc1, 0x00 - # pclmulqdq $0x11, SHASH, T1 # T1 = a1 * b1 - .byte 0x66, 0x0f, 0x3a, 0x44, 0xd1, 0x11 - # pclmulqdq $0x00, T3, T2 # T2 = (a1 + a0) * (b1 + b0) - .byte 0x66, 0x0f, 0x3a, 0x44, 0xdc, 0x00 + PCLMULQDQ 0x00 SHASH DATA # DATA = a0 * b0 + PCLMULQDQ 0x11 SHASH T1 # T1 = a1 * b1 + PCLMULQDQ 0x00 T3 T2 # T2 = (a1 + a0) * (b1 + b0) pxor DATA, T2 pxor T1, T2 # T2 = a0 * b1 + a1 * b0 @@ -101,11 +98,9 @@ ENTRY(clmul_ghash_mul) movups (%rdi), DATA movups (%rsi), SHASH movaps .Lbswap_mask, BSWAP - # pshufb BSWAP, DATA - PSHUFB_XMM5_XMM0 + PSHUFB_XMM BSWAP DATA call __clmul_gf128mul_ble - # pshufb BSWAP, DATA - .byte 0x66, 0x0f, 0x38, 0x00, 0xc5 + PSHUFB_XMM BSWAP DATA movups DATA, (%rdi) ret @@ -119,21 +114,18 @@ ENTRY(clmul_ghash_update) movaps .Lbswap_mask, BSWAP movups (%rdi), DATA movups (%rcx), SHASH - # pshufb BSWAP, DATA - PSHUFB_XMM5_XMM0 + PSHUFB_XMM BSWAP DATA .align 4 .Lupdate_loop: movups (%rsi), IN1 - # pshufb BSWAP, IN1 - PSHUFB_XMM5_XMM6 + PSHUFB_XMM BSWAP IN1 pxor IN1, DATA call __clmul_gf128mul_ble sub $16, %rdx add $16, %rsi cmp $16, %rdx jge .Lupdate_loop - # pshufb BSWAP, DATA - PSHUFB_XMM5_XMM0 + PSHUFB_XMM BSWAP DATA movups DATA, (%rdi) .Lupdate_just_ret: ret @@ -146,8 +138,7 @@ ENTRY(clmul_ghash_update) ENTRY(clmul_ghash_setkey) movaps .Lbswap_mask, BSWAP movups (%rsi), %xmm0 - # pshufb BSWAP, %xmm0 - PSHUFB_XMM5_XMM0 + PSHUFB_XMM BSWAP %xmm0 movaps %xmm0, %xmm1 psllq $1, %xmm0 psrlq $63, %xmm1 |