165 lines
3 KiB
ArmAsm
Executable file
165 lines
3 KiB
ArmAsm
Executable file
#include "arm_arch.h"
|
|
|
|
.text
|
|
#if defined(__thumb2__) && !defined(__APPLE__)
|
|
.syntax unified
|
|
.thumb
|
|
#else
|
|
.code 32
|
|
#undef __thumb2__
|
|
#endif
|
|
|
|
.align 5
|
|
.globl OPENSSL_atomic_add
|
|
.type OPENSSL_atomic_add,%function
|
|
OPENSSL_atomic_add:
|
|
#if __ARM_ARCH__>=6
|
|
.Ladd: ldrex r2,[r0]
|
|
add r3,r2,r1
|
|
strex r2,r3,[r0]
|
|
cmp r2,#0
|
|
bne .Ladd
|
|
mov r0,r3
|
|
bx lr
|
|
#else
|
|
stmdb sp!,{r4,r5,r6,lr}
|
|
ldr r2,.Lspinlock
|
|
adr r3,.Lspinlock
|
|
mov r4,r0
|
|
mov r5,r1
|
|
add r6,r3,r2 @ &spinlock
|
|
b .+8
|
|
.Lspin: bl sched_yield
|
|
mov r0,#-1
|
|
swp r0,r0,[r6]
|
|
cmp r0,#0
|
|
bne .Lspin
|
|
|
|
ldr r2,[r4]
|
|
add r2,r2,r5
|
|
str r2,[r4]
|
|
str r0,[r6] @ release spinlock
|
|
ldmia sp!,{r4,r5,r6,lr}
|
|
tst lr,#1
|
|
moveq pc,lr
|
|
.word 0xe12fff1e @ bx lr
|
|
#endif
|
|
.size OPENSSL_atomic_add,.-OPENSSL_atomic_add
|
|
|
|
#if __ARM_ARCH__>=7
|
|
.arch armv7-a
|
|
.fpu neon
|
|
|
|
.align 5
|
|
.globl _armv7_neon_probe
|
|
.type _armv7_neon_probe,%function
|
|
_armv7_neon_probe:
|
|
vorr q0,q0,q0
|
|
bx lr
|
|
.size _armv7_neon_probe,.-_armv7_neon_probe
|
|
|
|
.globl _armv8_aes_probe
|
|
.type _armv8_aes_probe,%function
|
|
_armv8_aes_probe:
|
|
#if defined(__thumb2__) && !defined(__APPLE__)
|
|
.byte 0xb0,0xff,0x00,0x03 @ aese.8 q0,q0
|
|
#else
|
|
.byte 0x00,0x03,0xb0,0xf3 @ aese.8 q0,q0
|
|
#endif
|
|
bx lr
|
|
.size _armv8_aes_probe,.-_armv8_aes_probe
|
|
|
|
.globl _armv8_sha1_probe
|
|
.type _armv8_sha1_probe,%function
|
|
_armv8_sha1_probe:
|
|
#if defined(__thumb2__) && !defined(__APPLE__)
|
|
.byte 0x00,0xef,0x40,0x0c @ sha1c.32 q0,q0,q0
|
|
#else
|
|
.byte 0x40,0x0c,0x00,0xf2 @ sha1c.32 q0,q0,q0
|
|
#endif
|
|
bx lr
|
|
.size _armv8_sha1_probe,.-_armv8_sha1_probe
|
|
|
|
.globl _armv8_sha256_probe
|
|
.type _armv8_sha256_probe,%function
|
|
_armv8_sha256_probe:
|
|
#if defined(__thumb2__) && !defined(__APPLE__)
|
|
.byte 0x00,0xff,0x40,0x0c @ sha256h.32 q0,q0,q0
|
|
#else
|
|
.byte 0x40,0x0c,0x00,0xf3 @ sha256h.32 q0,q0,q0
|
|
#endif
|
|
bx lr
|
|
.size _armv8_sha256_probe,.-_armv8_sha256_probe
|
|
.globl _armv8_pmull_probe
|
|
.type _armv8_pmull_probe,%function
|
|
_armv8_pmull_probe:
|
|
#if defined(__thumb2__) && !defined(__APPLE__)
|
|
.byte 0xa0,0xef,0x00,0x0e @ vmull.p64 q0,d0,d0
|
|
#else
|
|
.byte 0x00,0x0e,0xa0,0xf2 @ vmull.p64 q0,d0,d0
|
|
#endif
|
|
bx lr
|
|
.size _armv8_pmull_probe,.-_armv8_pmull_probe
|
|
#endif
|
|
|
|
.globl OPENSSL_wipe_cpu
|
|
.type OPENSSL_wipe_cpu,%function
|
|
OPENSSL_wipe_cpu:
|
|
#if __ARM_ARCH__>=7
|
|
ldr r0,.LOPENSSL_armcap
|
|
adr r1,.LOPENSSL_armcap
|
|
ldr r0,[r1,r0]
|
|
#ifdef __APPLE__
|
|
ldr r0,[r0]
|
|
#endif
|
|
#endif
|
|
eor r2,r2,r2
|
|
eor r3,r3,r3
|
|
eor ip,ip,ip
|
|
#if __ARM_ARCH__>=7
|
|
tst r0,#1
|
|
beq .Lwipe_done
|
|
veor q0, q0, q0
|
|
veor q1, q1, q1
|
|
veor q2, q2, q2
|
|
veor q3, q3, q3
|
|
veor q8, q8, q8
|
|
veor q9, q9, q9
|
|
veor q10, q10, q10
|
|
veor q11, q11, q11
|
|
veor q12, q12, q12
|
|
veor q13, q13, q13
|
|
veor q14, q14, q14
|
|
veor q15, q15, q15
|
|
.Lwipe_done:
|
|
#endif
|
|
mov r0,sp
|
|
#if __ARM_ARCH__>=5
|
|
bx lr
|
|
#else
|
|
tst lr,#1
|
|
moveq pc,lr
|
|
.word 0xe12fff1e @ bx lr
|
|
#endif
|
|
.size OPENSSL_wipe_cpu,.-OPENSSL_wipe_cpu
|
|
|
|
.align 5
|
|
#if __ARM_ARCH__>=7
|
|
.LOPENSSL_armcap:
|
|
.word OPENSSL_armcap_P-.
|
|
#endif
|
|
#if __ARM_ARCH__>=6
|
|
.align 5
|
|
#else
|
|
.Lspinlock:
|
|
.word atomic_add_spinlock-.Lspinlock
|
|
.align 5
|
|
|
|
.data
|
|
.align 2
|
|
atomic_add_spinlock:
|
|
.word 0
|
|
#endif
|
|
|
|
.comm OPENSSL_armcap_P,4,4
|
|
.hidden OPENSSL_armcap_P
|