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/sha2-ce-core.S | 47 ++++++++++++++++-------------------------------
1 files changed, 16 insertions(+), 31 deletions(-)
diff --git a/kernel/arch/arm64/crypto/sha2-ce-core.S b/kernel/arch/arm64/crypto/sha2-ce-core.S
index cd8b364..4911799 100644
--- a/kernel/arch/arm64/crypto/sha2-ce-core.S
+++ b/kernel/arch/arm64/crypto/sha2-ce-core.S
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* sha2-ce-core.S - core SHA-224/SHA-256 transform using v8 Crypto Extensions
*
* Copyright (C) 2014 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.
*/
#include <linux/linkage.h>
@@ -78,37 +75,31 @@
* int blocks)
*/
.text
-ENTRY(sha2_ce_transform)
- frame_push 3
-
- mov x19, x0
- mov x20, x1
- mov x21, x2
-
+SYM_FUNC_START(sha2_ce_transform)
/* load round constants */
-0: adr_l x8, .Lsha2_rcon
+ adr_l x8, .Lsha2_rcon
ld1 { v0.4s- v3.4s}, [x8], #64
ld1 { v4.4s- v7.4s}, [x8], #64
ld1 { v8.4s-v11.4s}, [x8], #64
ld1 {v12.4s-v15.4s}, [x8]
/* load state */
- ld1 {dgav.4s, dgbv.4s}, [x19]
+ ld1 {dgav.4s, dgbv.4s}, [x0]
/* load sha256_ce_state::finalize */
ldr_l w4, sha256_ce_offsetof_finalize, x4
- ldr w4, [x19, x4]
+ ldr w4, [x0, x4]
/* load input */
-1: ld1 {v16.4s-v19.4s}, [x20], #64
- sub w21, w21, #1
+0: ld1 {v16.4s-v19.4s}, [x1], #64
+ sub w2, w2, #1
CPU_LE( rev32 v16.16b, v16.16b )
CPU_LE( rev32 v17.16b, v17.16b )
CPU_LE( rev32 v18.16b, v18.16b )
CPU_LE( rev32 v19.16b, v19.16b )
-2: add t0.4s, v16.4s, v0.4s
+1: add t0.4s, v16.4s, v0.4s
mov dg0v.16b, dgav.16b
mov dg1v.16b, dgbv.16b
@@ -137,24 +128,18 @@
add dgbv.4s, dgbv.4s, dg1v.4s
/* handled all input blocks? */
- cbz w21, 3f
-
- if_will_cond_yield_neon
- st1 {dgav.4s, dgbv.4s}, [x19]
- do_cond_yield_neon
+ cbz w2, 2f
+ cond_yield 3f, x5, x6
b 0b
- endif_yield_neon
-
- b 1b
/*
* Final block: add padding and total bit count.
* Skip if the input size was not a round multiple of the block size,
* the padding is handled by the C code in that case.
*/
-3: cbz x4, 4f
+2: cbz x4, 3f
ldr_l w4, sha256_ce_offsetof_count, x4
- ldr x4, [x19, x4]
+ ldr x4, [x0, x4]
movi v17.2d, #0
mov x8, #0x80000000
movi v18.2d, #0
@@ -163,10 +148,10 @@
mov x4, #0
mov v19.d[0], xzr
mov v19.d[1], x7
- b 2b
+ b 1b
/* store new state */
-4: st1 {dgav.4s, dgbv.4s}, [x19]
- frame_pop
+3: st1 {dgav.4s, dgbv.4s}, [x0]
+ mov w0, w2
ret
-ENDPROC(sha2_ce_transform)
+SYM_FUNC_END(sha2_ce_transform)
--
Gitblit v1.6.2