From 1f93a7dfd1f8d5ff7a5c53246c7534fe2332d6f4 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 02:46:07 +0000
Subject: [PATCH] add audio
---
kernel/arch/arm64/crypto/aes-neonbs-core.S | 64 +++++++++++++------------------
1 files changed, 27 insertions(+), 37 deletions(-)
diff --git a/kernel/arch/arm64/crypto/aes-neonbs-core.S b/kernel/arch/arm64/crypto/aes-neonbs-core.S
index 8432c8d..a3405b8 100644
--- a/kernel/arch/arm64/crypto/aes-neonbs-core.S
+++ b/kernel/arch/arm64/crypto/aes-neonbs-core.S
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Bit sliced AES using NEON instructions
*
* Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
/*
@@ -383,7 +380,7 @@
/*
* void aesbs_convert_key(u8 out[], u32 const rk[], int rounds)
*/
-ENTRY(aesbs_convert_key)
+SYM_FUNC_START(aesbs_convert_key)
ld1 {v7.4s}, [x1], #16 // load round 0 key
ld1 {v17.4s}, [x1], #16 // load round 1 key
@@ -428,10 +425,10 @@
eor v17.16b, v17.16b, v7.16b
str q17, [x0]
ret
-ENDPROC(aesbs_convert_key)
+SYM_FUNC_END(aesbs_convert_key)
.align 4
-aesbs_encrypt8:
+SYM_FUNC_START_LOCAL(aesbs_encrypt8)
ldr q9, [bskey], #16 // round 0 key
ldr q8, M0SR
ldr q24, SR
@@ -491,10 +488,10 @@
eor v2.16b, v2.16b, v12.16b
eor v5.16b, v5.16b, v12.16b
ret
-ENDPROC(aesbs_encrypt8)
+SYM_FUNC_END(aesbs_encrypt8)
.align 4
-aesbs_decrypt8:
+SYM_FUNC_START_LOCAL(aesbs_decrypt8)
lsl x9, rounds, #7
add bskey, bskey, x9
@@ -556,7 +553,7 @@
eor v3.16b, v3.16b, v12.16b
eor v5.16b, v5.16b, v12.16b
ret
-ENDPROC(aesbs_decrypt8)
+SYM_FUNC_END(aesbs_decrypt8)
/*
* aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
@@ -616,7 +613,6 @@
st1 {\o7\().16b}, [x19], #16
cbz x23, 1f
- cond_yield_neon
b 99b
1: frame_pop
@@ -624,21 +620,21 @@
.endm
.align 4
-ENTRY(aesbs_ecb_encrypt)
+SYM_FUNC_START(aesbs_ecb_encrypt)
__ecb_crypt aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
-ENDPROC(aesbs_ecb_encrypt)
+SYM_FUNC_END(aesbs_ecb_encrypt)
.align 4
-ENTRY(aesbs_ecb_decrypt)
+SYM_FUNC_START(aesbs_ecb_decrypt)
__ecb_crypt aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
-ENDPROC(aesbs_ecb_decrypt)
+SYM_FUNC_END(aesbs_ecb_decrypt)
/*
* aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 iv[])
*/
.align 4
-ENTRY(aesbs_cbc_decrypt)
+SYM_FUNC_START(aesbs_cbc_decrypt)
frame_push 6
mov x19, x0
@@ -718,12 +714,11 @@
1: st1 {v24.16b}, [x24] // store IV
cbz x23, 2f
- cond_yield_neon
b 99b
2: frame_pop
ret
-ENDPROC(aesbs_cbc_decrypt)
+SYM_FUNC_END(aesbs_cbc_decrypt)
.macro next_tweak, out, in, const, tmp
sshr \tmp\().2d, \in\().2d, #63
@@ -733,18 +728,13 @@
eor \out\().16b, \out\().16b, \tmp\().16b
.endm
- .align 4
-.Lxts_mul_x:
-CPU_LE( .quad 1, 0x87 )
-CPU_BE( .quad 0x87, 1 )
-
/*
* aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 iv[])
* aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 iv[])
*/
-__xts_crypt8:
+SYM_FUNC_START_LOCAL(__xts_crypt8)
mov x6, #1
lsl x6, x6, x23
subs w23, w23, #8
@@ -796,8 +786,8 @@
0: mov bskey, x21
mov rounds, x22
- br x7
-ENDPROC(__xts_crypt8)
+ br x16
+SYM_FUNC_END(__xts_crypt8)
.macro __xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
frame_push 6, 64
@@ -809,10 +799,12 @@
mov x23, x4
mov x24, x5
-0: ldr q30, .Lxts_mul_x
+ movi v30.2s, #0x1
+ movi v25.2s, #0x87
+ uzp1 v30.4s, v30.4s, v25.4s
ld1 {v25.16b}, [x24]
-99: adr x7, \do8
+99: adr x16, \do8
bl __xts_crypt8
ldp q16, q17, [sp, #.Lframe_local_offset]
@@ -852,7 +844,6 @@
cbz x23, 1f
st1 {v25.16b}, [x24]
- cond_yield_neon 0b
b 99b
1: st1 {v25.16b}, [x24]
@@ -860,13 +851,13 @@
ret
.endm
-ENTRY(aesbs_xts_encrypt)
+SYM_FUNC_START(aesbs_xts_encrypt)
__xts_crypt aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
-ENDPROC(aesbs_xts_encrypt)
+SYM_FUNC_END(aesbs_xts_encrypt)
-ENTRY(aesbs_xts_decrypt)
+SYM_FUNC_START(aesbs_xts_decrypt)
__xts_crypt aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
-ENDPROC(aesbs_xts_decrypt)
+SYM_FUNC_END(aesbs_xts_decrypt)
.macro next_ctr, v
mov \v\().d[1], x8
@@ -880,7 +871,7 @@
* aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
* int rounds, int blocks, u8 iv[], u8 final[])
*/
-ENTRY(aesbs_ctr_encrypt)
+SYM_FUNC_START(aesbs_ctr_encrypt)
frame_push 8
mov x19, x0
@@ -895,7 +886,7 @@
cset x26, ne
add x23, x23, x26 // do one extra block if final
-98: ldp x7, x8, [x24]
+ ldp x7, x8, [x24]
ld1 {v0.16b}, [x24]
CPU_LE( rev x7, x7 )
CPU_LE( rev x8, x8 )
@@ -973,7 +964,6 @@
st1 {v0.16b}, [x24]
cbz x23, .Lctr_done
- cond_yield_neon 98b
b 99b
.Lctr_done:
@@ -1008,4 +998,4 @@
7: cbz x25, 8b
st1 {v5.16b}, [x25]
b 8b
-ENDPROC(aesbs_ctr_encrypt)
+SYM_FUNC_END(aesbs_ctr_encrypt)
--
Gitblit v1.6.2