Commit d7866e50 authored by Uros Bizjak's avatar Uros Bizjak Committed by Herbert Xu
Browse files

crypto: x86 - Remove include/asm/inst.h 



Current minimum required version of binutils is 2.23,
which supports PSHUFB, PCLMULQDQ, PEXTRD, AESKEYGENASSIST,
AESIMC, AESENC, AESENCLAST, AESDEC, AESDECLAST and MOVQ
instruction mnemonics.

Substitute macros from include/asm/inst.h with a proper
instruction mnemonics in various assmbly files from
x86/crypto directory, and remove now unneeded file.

The patch was tested by calculating and comparing sha256sum
hashes of stripped object files before and after the patch,
to be sure that executable code didn't change.

Signed-off-by: default avatarUros Bizjak <ubizjak@gmail.com>
CC: Herbert Xu <herbert@gondor.apana.org.au>
CC: "David S. Miller" <davem@davemloft.net>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Ingo Molnar <mingo@redhat.com>
CC: Borislav Petkov <bp@alien8.de>
CC: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: default avatarHerbert Xu <herbert@gondor.apana.org.au>
parent 2c2e1836

arch/x86/crypto/aes_ctrby8_avx-x86_64.S

+0 −1
Original line number Diff line number Diff line
@@ -63,7 +63,6 @@ 
 */



#include <linux/linkage.h>

#include <asm/inst.h>



#define VMOVDQ		vmovdqu

arch/x86/crypto/aesni-intel_asm.S

+366 −367

File changed.

Preview size limit exceeded, changes collapsed.

arch/x86/crypto/aesni-intel_avx-x86_64.S

+0 −1
Original line number Diff line number Diff line
@@ -120,7 +120,6 @@ 
##



#include <linux/linkage.h>

#include <asm/inst.h>



# constants in mergeable sections, linker can reorder and merge

.section	.rodata.cst16.POLY, "aM", @progbits, 16

arch/x86/crypto/crc32-pclmul_asm.S

+23 −24
Original line number Diff line number Diff line
@@ -38,7 +38,6 @@ 
 */



#include <linux/linkage.h>

#include <asm/inst.h>





.section .rodata
@@ -129,17 +128,17 @@ loop_64:/* 64 bytes Full cache line folding */ 
#ifdef __x86_64__

	movdqa  %xmm4, %xmm8

#endif

	PCLMULQDQ 00, CONSTANT, %xmm1

	PCLMULQDQ 00, CONSTANT, %xmm2

	PCLMULQDQ 00, CONSTANT, %xmm3

	pclmulqdq $0x00, CONSTANT, %xmm1

	pclmulqdq $0x00, CONSTANT, %xmm2

	pclmulqdq $0x00, CONSTANT, %xmm3

#ifdef __x86_64__

	PCLMULQDQ 00, CONSTANT, %xmm4

	pclmulqdq $0x00, CONSTANT, %xmm4

#endif

	PCLMULQDQ 0x11, CONSTANT, %xmm5

	PCLMULQDQ 0x11, CONSTANT, %xmm6

	PCLMULQDQ 0x11, CONSTANT, %xmm7

	pclmulqdq $0x11, CONSTANT, %xmm5

	pclmulqdq $0x11, CONSTANT, %xmm6

	pclmulqdq $0x11, CONSTANT, %xmm7

#ifdef __x86_64__

	PCLMULQDQ 0x11, CONSTANT, %xmm8

	pclmulqdq $0x11, CONSTANT, %xmm8

#endif

	pxor    %xmm5, %xmm1

	pxor    %xmm6, %xmm2
@@ -149,8 +148,8 @@ loop_64:/* 64 bytes Full cache line folding */ 
#else

	/* xmm8 unsupported for x32 */

	movdqa  %xmm4, %xmm5

	PCLMULQDQ 00, CONSTANT, %xmm4

	PCLMULQDQ 0x11, CONSTANT, %xmm5

	pclmulqdq $0x00, CONSTANT, %xmm4

	pclmulqdq $0x11, CONSTANT, %xmm5

	pxor    %xmm5, %xmm4

#endif
@@ -172,20 +171,20 @@ less_64:/* Folding cache line into 128bit */ 
	prefetchnta     (BUF)



	movdqa  %xmm1, %xmm5

	PCLMULQDQ 0x00, CONSTANT, %xmm1

	PCLMULQDQ 0x11, CONSTANT, %xmm5

	pclmulqdq $0x00, CONSTANT, %xmm1

	pclmulqdq $0x11, CONSTANT, %xmm5

	pxor    %xmm5, %xmm1

	pxor    %xmm2, %xmm1



	movdqa  %xmm1, %xmm5

	PCLMULQDQ 0x00, CONSTANT, %xmm1

	PCLMULQDQ 0x11, CONSTANT, %xmm5

	pclmulqdq $0x00, CONSTANT, %xmm1

	pclmulqdq $0x11, CONSTANT, %xmm5

	pxor    %xmm5, %xmm1

	pxor    %xmm3, %xmm1



	movdqa  %xmm1, %xmm5

	PCLMULQDQ 0x00, CONSTANT, %xmm1

	PCLMULQDQ 0x11, CONSTANT, %xmm5

	pclmulqdq $0x00, CONSTANT, %xmm1

	pclmulqdq $0x11, CONSTANT, %xmm5

	pxor    %xmm5, %xmm1

	pxor    %xmm4, %xmm1
@@ -193,8 +192,8 @@ less_64:/* Folding cache line into 128bit */ 
	jb      fold_64

loop_16:/* Folding rest buffer into 128bit */

	movdqa  %xmm1, %xmm5

	PCLMULQDQ 0x00, CONSTANT, %xmm1

	PCLMULQDQ 0x11, CONSTANT, %xmm5

	pclmulqdq $0x00, CONSTANT, %xmm1

	pclmulqdq $0x11, CONSTANT, %xmm5

	pxor    %xmm5, %xmm1

	pxor    (BUF), %xmm1

	sub     $0x10, LEN
@@ -205,7 +204,7 @@ loop_16:/* Folding rest buffer into 128bit */ 
fold_64:

	/* perform the last 64 bit fold, also adds 32 zeroes

	 * to the input stream */

	PCLMULQDQ 0x01, %xmm1, CONSTANT /* R4 * xmm1.low */

	pclmulqdq $0x01, %xmm1, CONSTANT /* R4 * xmm1.low */

	psrldq  $0x08, %xmm1

	pxor    CONSTANT, %xmm1
@@ -220,7 +219,7 @@ fold_64: 
#endif

	psrldq  $0x04, %xmm2

	pand    %xmm3, %xmm1

	PCLMULQDQ 0x00, CONSTANT, %xmm1

	pclmulqdq $0x00, CONSTANT, %xmm1

	pxor    %xmm2, %xmm1



	/* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
@@ -231,11 +230,11 @@ fold_64: 
#endif

	movdqa  %xmm1, %xmm2

	pand    %xmm3, %xmm1

	PCLMULQDQ 0x10, CONSTANT, %xmm1

	pclmulqdq $0x10, CONSTANT, %xmm1

	pand    %xmm3, %xmm1

	PCLMULQDQ 0x00, CONSTANT, %xmm1

	pclmulqdq $0x00, CONSTANT, %xmm1

	pxor    %xmm2, %xmm1

	PEXTRD  0x01, %xmm1, %eax

	pextrd  $0x01, %xmm1, %eax



	ret

SYM_FUNC_END(crc32_pclmul_le_16)

arch/x86/crypto/crc32c-pcl-intel-asm_64.S

+2 −3
Original line number Diff line number Diff line
@@ -43,7 +43,6 @@ 
 * SOFTWARE.

 */



#include <asm/inst.h>

#include <linux/linkage.h>

#include <asm/nospec-branch.h>
@@ -225,10 +224,10 @@ LABEL crc_ %i 
	subq    %rax, tmp			# tmp -= rax*24



	movq    crc_init, %xmm1			# CRC for block 1

	PCLMULQDQ 0x00,%xmm0,%xmm1		# Multiply by K2

	pclmulqdq $0x00, %xmm0, %xmm1		# Multiply by K2



	movq    crc1, %xmm2			# CRC for block 2

	PCLMULQDQ 0x10, %xmm0, %xmm2		# Multiply by K1

	pclmulqdq $0x10, %xmm0, %xmm2		# Multiply by K1



	pxor    %xmm2,%xmm1

	movq    %xmm1, %rax

CRA Git | Maintained and supported by SUSTech CRA and CCSE