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>

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 59584982fb75..1528dc4886cf 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