OpenSSL: regenerate asm files for 3.0.12

Fixes: ad991e4c14 ("OpenSSL: update to 3.0.12")
Sponsored by:	The FreeBSD Foundation
This commit is contained in:
Ed Maste 2023-10-25 13:28:47 -04:00
parent 876fddc886
commit 575878a533
4 changed files with 29 additions and 34 deletions

View file

@ -106,7 +106,7 @@ aes_v8_set_encrypt_key:
.Loop192:
tbl v6.16b,{v4.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
#ifdef __ARMEB__
#ifdef __AARCH64EB__
st1 {v4.4s},[x2],#16
sub x2,x2,#8
#else
@ -1520,7 +1520,7 @@ aes_v8_ctr32_encrypt_blocks:
ldr w5,[x3,#240]
ldr w8, [x4, #12]
#ifdef __ARMEB__
#ifdef __AARCH64EB__
ld1 {v0.16b},[x4]
#else
ld1 {v0.4s},[x4]
@ -1537,7 +1537,7 @@ aes_v8_ctr32_encrypt_blocks:
add x7,x3,#32
mov w6,w5
csel x12,xzr,x12,lo
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev w8, w8
#endif
orr v1.16b,v0.16b,v0.16b

View file

@ -1,5 +1,5 @@
/*
* Copyright 2011-2022 The OpenSSL Project Authors. All Rights Reserved.
* Copyright 2011-2023 The OpenSSL Project Authors. All Rights Reserved.
*
* Licensed under the Apache License 2.0 (the "License"). You may not use
* this file except in compliance with the License. You can obtain a copy
@ -21,11 +21,6 @@
# elif defined(__GNUC__)
# if defined(__aarch64__)
# define __ARM_ARCH__ 8
# if __BYTE_ORDER__==__ORDER_BIG_ENDIAN__
# define __ARMEB__
# else
# define __ARMEL__
# endif
/*
* Why doesn't gcc define __ARM_ARCH__? Instead it defines
* bunch of below macros. See all_architectures[] table in

View file

@ -104,7 +104,7 @@ gcm_gmult_v8:
movi v19.16b,#0xe1
ld1 {v20.2d,v21.2d},[x1] //load twisted H, ...
shl v19.2d,v19.2d,#57
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v17.16b,v17.16b
#endif
ext v3.16b,v17.16b,v17.16b,#8
@ -129,7 +129,7 @@ gcm_gmult_v8:
eor v18.16b,v18.16b,v2.16b
eor v0.16b,v0.16b,v18.16b
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v0.16b,v0.16b
#endif
ext v0.16b,v0.16b,v0.16b,#8
@ -167,14 +167,14 @@ gcm_ghash_v8:
ext v0.16b,v0.16b,v0.16b,#8 //rotate Xi
ld1 {v16.2d},[x2],#16 //load [rotated] I[0]
shl v19.2d,v19.2d,#57 //compose 0xc2.0 constant
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v16.16b,v16.16b
rev64 v0.16b,v0.16b
#endif
ext v3.16b,v16.16b,v16.16b,#8 //rotate I[0]
b.lo .Lodd_tail_v8 //x3 was less than 32
ld1 {v17.2d},[x2],x12 //load [rotated] I[1]
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v17.16b,v17.16b
#endif
ext v7.16b,v17.16b,v17.16b,#8
@ -206,13 +206,13 @@ gcm_ghash_v8:
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
ld1 {v17.2d},[x2],x12 //load [rotated] I[i+3]
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v16.16b,v16.16b
#endif
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v17.16b,v17.16b
#endif
ins v2.d[0],v1.d[1]
@ -262,7 +262,7 @@ gcm_ghash_v8:
eor v0.16b,v0.16b,v18.16b
.Ldone_v8:
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v0.16b,v0.16b
#endif
ext v0.16b,v0.16b,v0.16b,#8
@ -281,7 +281,7 @@ gcm_ghash_v8_4x:
shl v19.2d,v19.2d,#57 //compose 0xc2.0 constant
ld1 {v4.2d,v5.2d,v6.2d,v7.2d},[x2],#64
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v0.16b,v0.16b
rev64 v5.16b,v5.16b
rev64 v6.16b,v6.16b
@ -325,7 +325,7 @@ gcm_ghash_v8_4x:
eor v16.16b,v4.16b,v0.16b
ld1 {v4.2d,v5.2d,v6.2d,v7.2d},[x2],#64
ext v3.16b,v16.16b,v16.16b,#8
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v5.16b,v5.16b
rev64 v6.16b,v6.16b
rev64 v7.16b,v7.16b
@ -408,7 +408,7 @@ gcm_ghash_v8_4x:
eor v1.16b,v1.16b,v17.16b
ld1 {v4.2d,v5.2d,v6.2d},[x2]
eor v1.16b,v1.16b,v18.16b
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v5.16b,v5.16b
rev64 v6.16b,v6.16b
rev64 v4.16b,v4.16b
@ -460,7 +460,7 @@ gcm_ghash_v8_4x:
eor v1.16b,v1.16b,v17.16b
ld1 {v4.2d,v5.2d},[x2]
eor v1.16b,v1.16b,v18.16b
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v5.16b,v5.16b
rev64 v4.16b,v4.16b
#endif
@ -503,7 +503,7 @@ gcm_ghash_v8_4x:
eor v1.16b,v1.16b,v17.16b
ld1 {v4.2d},[x2]
eor v1.16b,v1.16b,v18.16b
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v4.16b,v4.16b
#endif
@ -543,7 +543,7 @@ gcm_ghash_v8_4x:
eor v0.16b,v0.16b,v18.16b
ext v0.16b,v0.16b,v0.16b,#8
#ifndef __ARMEB__
#ifndef __AARCH64EB__
rev64 v0.16b,v0.16b
#endif
st1 {v0.2d},[x0] //write out Xi

View file

@ -30,7 +30,7 @@ poly1305_init:
ldp x7,x8,[x1] // load key
mov x9,#0xfffffffc0fffffff
movk x9,#0x0fff,lsl#48
#ifdef __ARMEB__
#ifdef __AARCH64EB__
rev x7,x7 // flip bytes
rev x8,x8
#endif
@ -80,7 +80,7 @@ poly1305_blocks:
.Loop:
ldp x10,x11,[x1],#16 // load input
sub x2,x2,#16
#ifdef __ARMEB__
#ifdef __AARCH64EB__
rev x10,x10
rev x11,x11
#endif
@ -148,13 +148,13 @@ poly1305_emit:
csel x4,x4,x12,eq
csel x5,x5,x13,eq
#ifdef __ARMEB__
#ifdef __AARCH64EB__
ror x10,x10,#32 // flip nonce words
ror x11,x11,#32
#endif
adds x4,x4,x10 // accumulate nonce
adc x5,x5,x11
#ifdef __ARMEB__
#ifdef __AARCH64EB__
rev x4,x4 // flip output bytes
rev x5,x5
#endif
@ -277,7 +277,7 @@ poly1305_blocks_neon:
adcs x5,x5,xzr
adc x6,x6,xzr
#ifdef __ARMEB__
#ifdef __AARCH64EB__
rev x12,x12
rev x13,x13
#endif
@ -323,7 +323,7 @@ poly1305_blocks_neon:
ldp x12,x13,[x1],#16 // load input
sub x2,x2,#16
add x9,x8,x8,lsr#2 // s1 = r1 + (r1 >> 2)
#ifdef __ARMEB__
#ifdef __AARCH64EB__
rev x12,x12
rev x13,x13
#endif
@ -408,7 +408,7 @@ poly1305_blocks_neon:
lsl x3,x3,#24
add x15,x0,#48
#ifdef __ARMEB__
#ifdef __AARCH64EB__
rev x8,x8
rev x12,x12
rev x9,x9
@ -444,7 +444,7 @@ poly1305_blocks_neon:
ld1 {v4.4s,v5.4s,v6.4s,v7.4s},[x15],#64
ld1 {v8.4s},[x15]
#ifdef __ARMEB__
#ifdef __AARCH64EB__
rev x8,x8
rev x12,x12
rev x9,x9
@ -505,7 +505,7 @@ poly1305_blocks_neon:
umull v20.2d,v14.2s,v1.s[2]
ldp x9,x13,[x16],#48
umull v19.2d,v14.2s,v0.s[2]
#ifdef __ARMEB__
#ifdef __AARCH64EB__
rev x8,x8
rev x12,x12
rev x9,x9
@ -570,7 +570,7 @@ poly1305_blocks_neon:
umlal v23.2d,v11.2s,v3.s[0]
umlal v20.2d,v11.2s,v8.s[0]
umlal v21.2d,v11.2s,v0.s[0]
#ifdef __ARMEB__
#ifdef __AARCH64EB__
rev x8,x8
rev x12,x12
rev x9,x9
@ -854,13 +854,13 @@ poly1305_emit_neon:
csel x4,x4,x12,eq
csel x5,x5,x13,eq
#ifdef __ARMEB__
#ifdef __AARCH64EB__
ror x10,x10,#32 // flip nonce words
ror x11,x11,#32
#endif
adds x4,x4,x10 // accumulate nonce
adc x5,x5,x11
#ifdef __ARMEB__
#ifdef __AARCH64EB__
rev x4,x4 // flip output bytes
rev x5,x5
#endif