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: Uros 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: Herbert Xu <herbert@gondor.apana.org.au>

arch/x86/crypto/aes_ctrby8_avx-x86_64.S

@@ -63,7 +63,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/inst.h>
 
 #define VMOVDQ		vmovdqu
 

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

@@ -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

@@ -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

@@ -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

arch/x86/crypto/ghash-clmulni-intel_asm.S

@@ -14,7 +14,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/inst.h>
 #include <asm/frame.h>
 
 .section	.rodata.cst16.bswap_mask, "aM", @progbits, 16
@@ -51,9 +50,9 @@ SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble)
 	pxor DATA, T2
 	pxor SHASH, T3
 
-	PCLMULQDQ 0x00 SHASH DATA	# DATA = a0 * b0
-	PCLMULQDQ 0x11 SHASH T1		# T1 = a1 * b1
-	PCLMULQDQ 0x00 T3 T2		# T2 = (a1 + a0) * (b1 + b0)
+	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
 
@@ -95,9 +94,9 @@ SYM_FUNC_START(clmul_ghash_mul)
 	movups (%rdi), DATA
 	movups (%rsi), SHASH
 	movaps .Lbswap_mask, BSWAP
-	PSHUFB_XMM BSWAP DATA
+	pshufb BSWAP, DATA
 	call __clmul_gf128mul_ble
-	PSHUFB_XMM BSWAP DATA
+	pshufb BSWAP, DATA
 	movups DATA, (%rdi)
 	FRAME_END
 	ret
@@ -114,18 +113,18 @@ SYM_FUNC_START(clmul_ghash_update)
 	movaps .Lbswap_mask, BSWAP
 	movups (%rdi), DATA
 	movups (%rcx), SHASH
-	PSHUFB_XMM BSWAP DATA
+	pshufb BSWAP, DATA
 .align 4
 .Lupdate_loop:
 	movups (%rsi), IN1
-	PSHUFB_XMM BSWAP IN1
+	pshufb BSWAP, IN1
 	pxor IN1, DATA
 	call __clmul_gf128mul_ble
 	sub $16, %rdx
 	add $16, %rsi
 	cmp $16, %rdx
 	jge .Lupdate_loop
-	PSHUFB_XMM BSWAP DATA
+	pshufb BSWAP, DATA
 	movups DATA, (%rdi)
 .Lupdate_just_ret:
 	FRAME_END

arch/x86/include/asm/inst.h

-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Generate .byte code for some instructions not supported by old
- * binutils.
- */
-#ifndef X86_ASM_INST_H
-#define X86_ASM_INST_H
-
-#ifdef __ASSEMBLY__
-
-#define REG_NUM_INVALID		100
-
-#define REG_TYPE_R32		0
-#define REG_TYPE_R64		1
-#define REG_TYPE_XMM		2
-#define REG_TYPE_INVALID	100
-
-	.macro R32_NUM opd r32
-	\opd = REG_NUM_INVALID
-	.ifc \r32,%eax
-	\opd = 0
-	.endif
-	.ifc \r32,%ecx
-	\opd = 1
-	.endif
-	.ifc \r32,%edx
-	\opd = 2
-	.endif
-	.ifc \r32,%ebx
-	\opd = 3
-	.endif
-	.ifc \r32,%esp
-	\opd = 4
-	.endif
-	.ifc \r32,%ebp
-	\opd = 5
-	.endif
-	.ifc \r32,%esi
-	\opd = 6
-	.endif
-	.ifc \r32,%edi
-	\opd = 7
-	.endif
-#ifdef CONFIG_X86_64
-	.ifc \r32,%r8d
-	\opd = 8
-	.endif
-	.ifc \r32,%r9d
-	\opd = 9
-	.endif
-	.ifc \r32,%r10d
-	\opd = 10
-	.endif
-	.ifc \r32,%r11d
-	\opd = 11
-	.endif
-	.ifc \r32,%r12d
-	\opd = 12
-	.endif
-	.ifc \r32,%r13d
-	\opd = 13
-	.endif
-	.ifc \r32,%r14d
-	\opd = 14
-	.endif
-	.ifc \r32,%r15d
-	\opd = 15
-	.endif
-#endif
-	.endm
-
-	.macro R64_NUM opd r64
-	\opd = REG_NUM_INVALID
-#ifdef CONFIG_X86_64
-	.ifc \r64,%rax
-	\opd = 0
-	.endif
-	.ifc \r64,%rcx
-	\opd = 1
-	.endif
-	.ifc \r64,%rdx
-	\opd = 2
-	.endif
-	.ifc \r64,%rbx
-	\opd = 3
-	.endif
-	.ifc \r64,%rsp
-	\opd = 4
-	.endif
-	.ifc \r64,%rbp
-	\opd = 5
-	.endif
-	.ifc \r64,%rsi
-	\opd = 6
-	.endif
-	.ifc \r64,%rdi
-	\opd = 7
-	.endif
-	.ifc \r64,%r8
-	\opd = 8
-	.endif
-	.ifc \r64,%r9
-	\opd = 9
-	.endif
-	.ifc \r64,%r10
-	\opd = 10
-	.endif
-	.ifc \r64,%r11
-	\opd = 11
-	.endif
-	.ifc \r64,%r12
-	\opd = 12
-	.endif
-	.ifc \r64,%r13
-	\opd = 13
-	.endif
-	.ifc \r64,%r14
-	\opd = 14
-	.endif
-	.ifc \r64,%r15
-	\opd = 15
-	.endif
-#endif
-	.endm
-
-	.macro XMM_NUM opd xmm
-	\opd = REG_NUM_INVALID
-	.ifc \xmm,%xmm0
-	\opd = 0
-	.endif
-	.ifc \xmm,%xmm1
-	\opd = 1
-	.endif
-	.ifc \xmm,%xmm2
-	\opd = 2
-	.endif
-	.ifc \xmm,%xmm3
-	\opd = 3
-	.endif
-	.ifc \xmm,%xmm4
-	\opd = 4
-	.endif
-	.ifc \xmm,%xmm5
-	\opd = 5
-	.endif
-	.ifc \xmm,%xmm6
-	\opd = 6
-	.endif
-	.ifc \xmm,%xmm7
-	\opd = 7
-	.endif
-	.ifc \xmm,%xmm8
-	\opd = 8
-	.endif
-	.ifc \xmm,%xmm9
-	\opd = 9
-	.endif
-	.ifc \xmm,%xmm10
-	\opd = 10
-	.endif
-	.ifc \xmm,%xmm11
-	\opd = 11
-	.endif
-	.ifc \xmm,%xmm12
-	\opd = 12
-	.endif
-	.ifc \xmm,%xmm13
-	\opd = 13
-	.endif
-	.ifc \xmm,%xmm14
-	\opd = 14
-	.endif
-	.ifc \xmm,%xmm15
-	\opd = 15
-	.endif
-	.endm
-
-	.macro REG_TYPE type reg
-	R32_NUM reg_type_r32 \reg
-	R64_NUM reg_type_r64 \reg
-	XMM_NUM reg_type_xmm \reg
-	.if reg_type_r64 <> REG_NUM_INVALID
-	\type = REG_TYPE_R64
-	.elseif reg_type_r32 <> REG_NUM_INVALID
-	\type = REG_TYPE_R32
-	.elseif reg_type_xmm <> REG_NUM_INVALID
-	\type = REG_TYPE_XMM
-	.else
-	\type = REG_TYPE_INVALID
-	.endif
-	.endm
-
-	.macro PFX_OPD_SIZE
-	.byte 0x66
-	.endm
-
-	.macro PFX_REX opd1 opd2 W=0
-	.if ((\opd1 | \opd2) & 8) || \W
-	.byte 0x40 | ((\opd1 & 8) >> 3) | ((\opd2 & 8) >> 1) | (\W << 3)
-	.endif
-	.endm
-
-	.macro MODRM mod opd1 opd2
-	.byte \mod | (\opd1 & 7) | ((\opd2 & 7) << 3)
-	.endm
-
-	.macro PSHUFB_XMM xmm1 xmm2
-	XMM_NUM pshufb_opd1 \xmm1
-	XMM_NUM pshufb_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX pshufb_opd1 pshufb_opd2
-	.byte 0x0f, 0x38, 0x00
-	MODRM 0xc0 pshufb_opd1 pshufb_opd2
-	.endm
-
-	.macro PCLMULQDQ imm8 xmm1 xmm2
-	XMM_NUM clmul_opd1 \xmm1
-	XMM_NUM clmul_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX clmul_opd1 clmul_opd2
-	.byte 0x0f, 0x3a, 0x44
-	MODRM 0xc0 clmul_opd1 clmul_opd2
-	.byte \imm8
-	.endm
-
-	.macro PEXTRD imm8 xmm gpr
-	R32_NUM extrd_opd1 \gpr
-	XMM_NUM extrd_opd2 \xmm
-	PFX_OPD_SIZE
-	PFX_REX extrd_opd1 extrd_opd2
-	.byte 0x0f, 0x3a, 0x16
-	MODRM 0xc0 extrd_opd1 extrd_opd2
-	.byte \imm8
-	.endm
-
-	.macro AESKEYGENASSIST rcon xmm1 xmm2
-	XMM_NUM aeskeygen_opd1 \xmm1
-	XMM_NUM aeskeygen_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aeskeygen_opd1 aeskeygen_opd2
-	.byte 0x0f, 0x3a, 0xdf
-	MODRM 0xc0 aeskeygen_opd1 aeskeygen_opd2
-	.byte \rcon
-	.endm
-
-	.macro AESIMC xmm1 xmm2
-	XMM_NUM aesimc_opd1 \xmm1
-	XMM_NUM aesimc_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aesimc_opd1 aesimc_opd2
-	.byte 0x0f, 0x38, 0xdb
-	MODRM 0xc0 aesimc_opd1 aesimc_opd2
-	.endm
-
-	.macro AESENC xmm1 xmm2
-	XMM_NUM aesenc_opd1 \xmm1
-	XMM_NUM aesenc_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aesenc_opd1 aesenc_opd2
-	.byte 0x0f, 0x38, 0xdc
-	MODRM 0xc0 aesenc_opd1 aesenc_opd2
-	.endm
-
-	.macro AESENCLAST xmm1 xmm2
-	XMM_NUM aesenclast_opd1 \xmm1
-	XMM_NUM aesenclast_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aesenclast_opd1 aesenclast_opd2
-	.byte 0x0f, 0x38, 0xdd
-	MODRM 0xc0 aesenclast_opd1 aesenclast_opd2
-	.endm
-
-	.macro AESDEC xmm1 xmm2
-	XMM_NUM aesdec_opd1 \xmm1
-	XMM_NUM aesdec_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aesdec_opd1 aesdec_opd2
-	.byte 0x0f, 0x38, 0xde
-	MODRM 0xc0 aesdec_opd1 aesdec_opd2
-	.endm
-
-	.macro AESDECLAST xmm1 xmm2
-	XMM_NUM aesdeclast_opd1 \xmm1
-	XMM_NUM aesdeclast_opd2 \xmm2
-	PFX_OPD_SIZE
-	PFX_REX aesdeclast_opd1 aesdeclast_opd2
-	.byte 0x0f, 0x38, 0xdf
-	MODRM 0xc0 aesdeclast_opd1 aesdeclast_opd2
-	.endm
-
-	.macro MOVQ_R64_XMM opd1 opd2
-	REG_TYPE movq_r64_xmm_opd1_type \opd1
-	.if movq_r64_xmm_opd1_type == REG_TYPE_XMM
-	XMM_NUM movq_r64_xmm_opd1 \opd1
-	R64_NUM movq_r64_xmm_opd2 \opd2
-	.else
-	R64_NUM movq_r64_xmm_opd1 \opd1
-	XMM_NUM movq_r64_xmm_opd2 \opd2
-	.endif
-	PFX_OPD_SIZE
-	PFX_REX movq_r64_xmm_opd1 movq_r64_xmm_opd2 1
-	.if movq_r64_xmm_opd1_type == REG_TYPE_XMM
-	.byte 0x0f, 0x7e
-	.else
-	.byte 0x0f, 0x6e
-	.endif
-	MODRM 0xc0 movq_r64_xmm_opd1 movq_r64_xmm_opd2
-	.endm
-#endif
-
-#endif