widevine-partner/ce_cdm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Source release 17.1.0

Browse Source
This commit is contained in:
John "Juce" Bruce
2022-07-07 17:14:31 -07:00
parent 8c17574083
commit 694cf6fb25
2233 changed files with 272026 additions and 223371 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
third_party/boringssl/kit/ios-aarch64/crypto/fipsmodule/aesv8-armx64.S vendored
View File

@@ -32,6 +32,8 @@ Lrcon:
.align 5
_aes_hw_set_encrypt_key:
Lenc_key:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
stp x29,x30,[sp,#-16]!
add x29,sp,#0
mov x3,#-1
@@ -200,6 +202,7 @@ Lenc_key_abort:
.align 5
_aes_hw_set_decrypt_key:
AARCH64_SIGN_LINK_REGISTER
stp x29,x30,[sp,#-16]!
add x29,sp,#0
bl Lenc_key
@@ -233,6 +236,7 @@ Loop_imc:
eor x0,x0,x0 // return value
Ldec_key_abort:
ldp x29,x30,[sp],#16
AARCH64_VALIDATE_LINK_REGISTER
ret
.globl _aes_hw_encrypt
@@ -240,6 +244,7 @@ Ldec_key_abort:
.align 5
_aes_hw_encrypt:
AARCH64_VALID_CALL_TARGET
ldr w3,[x2,#240]
ld1 {v0.4s},[x2],#16
ld1 {v2.16b},[x0]
@@ -270,6 +275,7 @@ Loop_enc:
.align 5
_aes_hw_decrypt:
AARCH64_VALID_CALL_TARGET
ldr w3,[x2,#240]
ld1 {v0.4s},[x2],#16
ld1 {v2.16b},[x0]
@@ -300,6 +306,8 @@ Loop_dec:
.align 5
_aes_hw_cbc_encrypt:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
stp x29,x30,[sp,#-16]!
add x29,sp,#0
subs x2,x2,#16
@@ -591,6 +599,8 @@ Lcbc_abort:
.align 5
_aes_hw_ctr32_encrypt_blocks:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
stp x29,x30,[sp,#-16]!
add x29,sp,#0
ldr w5,[x3,#240]
@@ -610,20 +620,34 @@ _aes_hw_ctr32_encrypt_blocks:
add x7,x3,#32
mov w6,w5
csel x12,xzr,x12,lo
// ARM Cortex-A57 and Cortex-A72 cores running in 32-bit mode are
// affected by silicon errata #1742098 [0] and #1655431 [1],
// respectively, where the second instruction of an aese/aesmc
// instruction pair may execute twice if an interrupt is taken right
// after the first instruction consumes an input register of which a
// single 32-bit lane has been updated the last time it was modified.
//
// This function uses a counter in one 32-bit lane. The vmov lines
// could write to v1.16b and v18.16b directly, but that trips this bugs.
// We write to v6.16b and copy to the final register as a workaround.
//
// [0] ARM-EPM-049219 v23 Cortex-A57 MPCore Software Developers Errata Notice
// [1] ARM-EPM-012079 v11.0 Cortex-A72 MPCore Software Developers Errata Notice
#ifndef __ARMEB__
rev w8, w8
#endif
orr v1.16b,v0.16b,v0.16b
add w10, w8, #1
orr v18.16b,v0.16b,v0.16b
add w8, w8, #2
orr v6.16b,v0.16b,v0.16b
rev w10, w10
mov v1.s[3],w10
mov v6.s[3],w10
add w8, w8, #2
orr v1.16b,v6.16b,v6.16b
b.ls Lctr32_tail
rev w12, w8
mov v6.s[3],w12
sub x2,x2,#3 // bias
mov v18.s[3],w12
orr v18.16b,v6.16b,v6.16b
b Loop3x_ctr32
.align 4
@@ -650,11 +674,11 @@ Loop3x_ctr32:
aese v1.16b,v16.16b
aesmc v5.16b,v1.16b
ld1 {v2.16b},[x0],#16
orr v0.16b,v6.16b,v6.16b
add w9,w8,#1
aese v18.16b,v16.16b
aesmc v18.16b,v18.16b
ld1 {v3.16b},[x0],#16
orr v1.16b,v6.16b,v6.16b
rev w9,w9
aese v4.16b,v17.16b
aesmc v4.16b,v4.16b
aese v5.16b,v17.16b
@@ -663,8 +687,6 @@ Loop3x_ctr32:
mov x7,x3
aese v18.16b,v17.16b
aesmc v17.16b,v18.16b
orr v18.16b,v6.16b,v6.16b
add w9,w8,#1
aese v4.16b,v20.16b
aesmc v4.16b,v4.16b
aese v5.16b,v20.16b
@@ -679,21 +701,26 @@ Loop3x_ctr32:
aesmc v4.16b,v4.16b
aese v5.16b,v21.16b
aesmc v5.16b,v5.16b
// Note the logic to update v0.16b, v1.16b, and v1.16b is written to work
// around a bug in ARM Cortex-A57 and Cortex-A72 cores running in
// 32-bit mode. See the comment above.
eor v19.16b,v19.16b,v7.16b
rev w9,w9
mov v6.s[3], w9
aese v17.16b,v21.16b
aesmc v17.16b,v17.16b
mov v0.s[3], w9
orr v0.16b,v6.16b,v6.16b
rev w10,w10
aese v4.16b,v22.16b
aesmc v4.16b,v4.16b
mov v6.s[3], w10
rev w12,w8
aese v5.16b,v22.16b
aesmc v5.16b,v5.16b
mov v1.s[3], w10
rev w12,w8
orr v1.16b,v6.16b,v6.16b
mov v6.s[3], w12
aese v17.16b,v22.16b
aesmc v17.16b,v17.16b
mov v18.s[3], w12
orr v18.16b,v6.16b,v6.16b
subs x2,x2,#3
aese v4.16b,v23.16b
aese v5.16b,v23.16b

13
third_party/boringssl/kit/ios-aarch64/crypto/fipsmodule/armv8-mont.S vendored
View File

@@ -12,6 +12,8 @@
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
.text
.globl _bn_mul_mont
@@ -19,6 +21,7 @@
.align 5
_bn_mul_mont:
AARCH64_SIGN_LINK_REGISTER
tst x5,#7
b.eq __bn_sqr8x_mont
tst x5,#3
@@ -216,11 +219,14 @@ Lcond_copy:
mov x0,#1
ldp x23,x24,[x29,#48]
ldr x29,[sp],#64
AARCH64_VALIDATE_LINK_REGISTER
ret
.align 5
__bn_sqr8x_mont:
// Not adding AARCH64_SIGN_LINK_REGISTER here because __bn_sqr8x_mont is jumped to
// only from bn_mul_mont which has already signed the return address.
cmp x1,x2
b.ne __bn_mul4x_mont
Lsqr8x_mont:
@@ -974,11 +980,16 @@ Lsqr8x_done:
ldp x25,x26,[x29,#64]
ldp x27,x28,[x29,#80]
ldr x29,[sp],#128
// x30 is popped earlier
AARCH64_VALIDATE_LINK_REGISTER
ret
.align 5
__bn_mul4x_mont:
// Not adding AARCH64_SIGN_LINK_REGISTER here because __bn_mul4x_mont is jumped to
// only from bn_mul_mont or __bn_mul8x_mont which have already signed the
// return address.
stp x29,x30,[sp,#-128]!
add x29,sp,#0
stp x19,x20,[sp,#16]
@@ -1412,6 +1423,8 @@ Lmul4x_done:
ldp x25,x26,[x29,#64]
ldp x27,x28,[x29,#80]
ldr x29,[sp],#128
// x30 is popped earlier
AARCH64_VALIDATE_LINK_REGISTER
ret
.byte 77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105,112,108,105,99,97,116,105,111,110,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0

5
third_party/boringssl/kit/ios-aarch64/crypto/fipsmodule/ghash-neon-armv8.S vendored
View File

@@ -12,6 +12,8 @@
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
.text
.globl _gcm_init_neon
@@ -19,6 +21,7 @@
.align 4
_gcm_init_neon:
AARCH64_VALID_CALL_TARGET
// This function is adapted from gcm_init_v8. xC2 is t3.
ld1 {v17.2d}, [x1] // load H
movi v19.16b, #0xe1
@@ -44,6 +47,7 @@ _gcm_init_neon:
.align 4
_gcm_gmult_neon:
AARCH64_VALID_CALL_TARGET
ld1 {v3.16b}, [x0] // load Xi
ld1 {v5.1d}, [x1], #8 // load twisted H
ld1 {v6.1d}, [x1]
@@ -63,6 +67,7 @@ _gcm_gmult_neon:
.align 4
_gcm_ghash_neon:
AARCH64_VALID_CALL_TARGET
ld1 {v0.16b}, [x0] // load Xi
ld1 {v5.1d}, [x1], #8 // load twisted H
ld1 {v6.1d}, [x1]

329
third_party/boringssl/kit/ios-aarch64/crypto/fipsmodule/ghashv8-armx64.S vendored
View File

@@ -14,6 +14,7 @@
#endif
#include <openssl/arm_arch.h>
#if __ARM_MAX_ARCH__>=7
.text
.globl _gcm_init_v8
@@ -21,6 +22,7 @@
.align 4
_gcm_init_v8:
AARCH64_VALID_CALL_TARGET
ld1 {v17.2d},[x1] //load input H
movi v19.16b,#0xe1
shl v19.2d,v19.2d,#57 //0xc2.0
@@ -63,8 +65,48 @@ _gcm_init_v8:
ext v17.16b,v22.16b,v22.16b,#8 //Karatsuba pre-processing
eor v17.16b,v17.16b,v22.16b
ext v21.16b,v16.16b,v17.16b,#8 //pack Karatsuba pre-processed
st1 {v21.2d,v22.2d},[x0] //store Htable[1..2]
st1 {v21.2d,v22.2d},[x0],#32 //store Htable[1..2]
//calculate H^3 and H^4
pmull v0.1q,v20.1d, v22.1d
pmull v5.1q,v22.1d,v22.1d
pmull2 v2.1q,v20.2d, v22.2d
pmull2 v7.1q,v22.2d,v22.2d
pmull v1.1q,v16.1d,v17.1d
pmull v6.1q,v17.1d,v17.1d
ext v16.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
ext v17.16b,v5.16b,v7.16b,#8
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v16.16b
eor v4.16b,v5.16b,v7.16b
eor v6.16b,v6.16b,v17.16b
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase
eor v6.16b,v6.16b,v4.16b
pmull v4.1q,v5.1d,v19.1d
ins v2.d[0],v1.d[1]
ins v7.d[0],v6.d[1]
ins v1.d[1],v0.d[0]
ins v6.d[1],v5.d[0]
eor v0.16b,v1.16b,v18.16b
eor v5.16b,v6.16b,v4.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase
ext v4.16b,v5.16b,v5.16b,#8
pmull v0.1q,v0.1d,v19.1d
pmull v5.1q,v5.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
eor v4.16b,v4.16b,v7.16b
eor v20.16b, v0.16b,v18.16b //H^3
eor v22.16b,v5.16b,v4.16b //H^4
ext v16.16b,v20.16b, v20.16b,#8 //Karatsuba pre-processing
ext v17.16b,v22.16b,v22.16b,#8
eor v16.16b,v16.16b,v20.16b
eor v17.16b,v17.16b,v22.16b
ext v21.16b,v16.16b,v17.16b,#8 //pack Karatsuba pre-processed
st1 {v20.2d,v21.2d,v22.2d},[x0] //store Htable[3..5]
ret
.globl _gcm_gmult_v8
@@ -72,6 +114,7 @@ _gcm_init_v8:
.align 4
_gcm_gmult_v8:
AARCH64_VALID_CALL_TARGET
ld1 {v17.2d},[x0] //load Xi
movi v19.16b,#0xe1
ld1 {v20.2d,v21.2d},[x1] //load twisted H, ...
@@ -114,6 +157,9 @@ _gcm_gmult_v8:
.align 4
_gcm_ghash_v8:
AARCH64_VALID_CALL_TARGET
cmp x3,#64
b.hs Lgcm_ghash_v8_4x
ld1 {v0.2d},[x0] //load [rotated] Xi
//"[rotated]" means that
//loaded value would have
@@ -240,7 +286,288 @@ Ldone_v8:
ret
.align 4
gcm_ghash_v8_4x:
Lgcm_ghash_v8_4x:
ld1 {v0.2d},[x0] //load [rotated] Xi
ld1 {v20.2d,v21.2d,v22.2d},[x1],#48 //load twisted H, ..., H^2
movi v19.16b,#0xe1
ld1 {v26.2d,v27.2d,v28.2d},[x1] //load twisted H^3, ..., H^4
shl v19.2d,v19.2d,#57 //compose 0xc2.0 constant
ld1 {v4.2d,v5.2d,v6.2d,v7.2d},[x2],#64
#ifndef __ARMEB__
rev64 v0.16b,v0.16b
rev64 v5.16b,v5.16b
rev64 v6.16b,v6.16b
rev64 v7.16b,v7.16b
rev64 v4.16b,v4.16b
#endif
ext v25.16b,v7.16b,v7.16b,#8
ext v24.16b,v6.16b,v6.16b,#8
ext v23.16b,v5.16b,v5.16b,#8
pmull v29.1q,v20.1d,v25.1d //H·Ii+3
eor v7.16b,v7.16b,v25.16b
pmull2 v31.1q,v20.2d,v25.2d
pmull v30.1q,v21.1d,v7.1d
pmull v16.1q,v22.1d,v24.1d //H^2·Ii+2
eor v6.16b,v6.16b,v24.16b
pmull2 v24.1q,v22.2d,v24.2d
pmull2 v6.1q,v21.2d,v6.2d
eor v29.16b,v29.16b,v16.16b
eor v31.16b,v31.16b,v24.16b
eor v30.16b,v30.16b,v6.16b
pmull v7.1q,v26.1d,v23.1d //H^3·Ii+1
eor v5.16b,v5.16b,v23.16b
pmull2 v23.1q,v26.2d,v23.2d
pmull v5.1q,v27.1d,v5.1d
eor v29.16b,v29.16b,v7.16b
eor v31.16b,v31.16b,v23.16b
eor v30.16b,v30.16b,v5.16b
subs x3,x3,#128
b.lo Ltail4x
b Loop4x
.align 4
Loop4x:
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__
rev64 v5.16b,v5.16b
rev64 v6.16b,v6.16b
rev64 v7.16b,v7.16b
rev64 v4.16b,v4.16b
#endif
pmull v0.1q,v28.1d,v3.1d //H^4·(Xi+Ii)
eor v16.16b,v16.16b,v3.16b
pmull2 v2.1q,v28.2d,v3.2d
ext v25.16b,v7.16b,v7.16b,#8
pmull2 v1.1q,v27.2d,v16.2d
eor v0.16b,v0.16b,v29.16b
eor v2.16b,v2.16b,v31.16b
ext v24.16b,v6.16b,v6.16b,#8
eor v1.16b,v1.16b,v30.16b
ext v23.16b,v5.16b,v5.16b,#8
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
pmull v29.1q,v20.1d,v25.1d //H·Ii+3
eor v7.16b,v7.16b,v25.16b
eor v1.16b,v1.16b,v17.16b
pmull2 v31.1q,v20.2d,v25.2d
eor v1.16b,v1.16b,v18.16b
pmull v30.1q,v21.1d,v7.1d
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
pmull v16.1q,v22.1d,v24.1d //H^2·Ii+2
eor v6.16b,v6.16b,v24.16b
pmull2 v24.1q,v22.2d,v24.2d
eor v0.16b,v1.16b,v18.16b
pmull2 v6.1q,v21.2d,v6.2d
eor v29.16b,v29.16b,v16.16b
eor v31.16b,v31.16b,v24.16b
eor v30.16b,v30.16b,v6.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
pmull v7.1q,v26.1d,v23.1d //H^3·Ii+1
eor v5.16b,v5.16b,v23.16b
eor v18.16b,v18.16b,v2.16b
pmull2 v23.1q,v26.2d,v23.2d
pmull v5.1q,v27.1d,v5.1d
eor v0.16b,v0.16b,v18.16b
eor v29.16b,v29.16b,v7.16b
eor v31.16b,v31.16b,v23.16b
ext v0.16b,v0.16b,v0.16b,#8
eor v30.16b,v30.16b,v5.16b
subs x3,x3,#64
b.hs Loop4x
Ltail4x:
eor v16.16b,v4.16b,v0.16b
ext v3.16b,v16.16b,v16.16b,#8
pmull v0.1q,v28.1d,v3.1d //H^4·(Xi+Ii)
eor v16.16b,v16.16b,v3.16b
pmull2 v2.1q,v28.2d,v3.2d
pmull2 v1.1q,v27.2d,v16.2d
eor v0.16b,v0.16b,v29.16b
eor v2.16b,v2.16b,v31.16b
eor v1.16b,v1.16b,v30.16b
adds x3,x3,#64
b.eq Ldone4x
cmp x3,#32
b.lo Lone
b.eq Ltwo
Lthree:
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
ld1 {v4.2d,v5.2d,v6.2d},[x2]
eor v1.16b,v1.16b,v18.16b
#ifndef __ARMEB__
rev64 v5.16b,v5.16b
rev64 v6.16b,v6.16b
rev64 v4.16b,v4.16b
#endif
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
ext v24.16b,v6.16b,v6.16b,#8
ext v23.16b,v5.16b,v5.16b,#8
eor v0.16b,v1.16b,v18.16b
pmull v29.1q,v20.1d,v24.1d //H·Ii+2
eor v6.16b,v6.16b,v24.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
pmull2 v31.1q,v20.2d,v24.2d
pmull v30.1q,v21.1d,v6.1d
eor v0.16b,v0.16b,v18.16b
pmull v7.1q,v22.1d,v23.1d //H^2·Ii+1
eor v5.16b,v5.16b,v23.16b
ext v0.16b,v0.16b,v0.16b,#8
pmull2 v23.1q,v22.2d,v23.2d
eor v16.16b,v4.16b,v0.16b
pmull2 v5.1q,v21.2d,v5.2d
ext v3.16b,v16.16b,v16.16b,#8
eor v29.16b,v29.16b,v7.16b
eor v31.16b,v31.16b,v23.16b
eor v30.16b,v30.16b,v5.16b
pmull v0.1q,v26.1d,v3.1d //H^3·(Xi+Ii)
eor v16.16b,v16.16b,v3.16b
pmull2 v2.1q,v26.2d,v3.2d
pmull v1.1q,v27.1d,v16.1d
eor v0.16b,v0.16b,v29.16b
eor v2.16b,v2.16b,v31.16b
eor v1.16b,v1.16b,v30.16b
b Ldone4x
.align 4
Ltwo:
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
ld1 {v4.2d,v5.2d},[x2]
eor v1.16b,v1.16b,v18.16b
#ifndef __ARMEB__
rev64 v5.16b,v5.16b
rev64 v4.16b,v4.16b
#endif
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
ext v23.16b,v5.16b,v5.16b,#8
eor v0.16b,v1.16b,v18.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
eor v0.16b,v0.16b,v18.16b
ext v0.16b,v0.16b,v0.16b,#8
pmull v29.1q,v20.1d,v23.1d //H·Ii+1
eor v5.16b,v5.16b,v23.16b
eor v16.16b,v4.16b,v0.16b
ext v3.16b,v16.16b,v16.16b,#8
pmull2 v31.1q,v20.2d,v23.2d
pmull v30.1q,v21.1d,v5.1d
pmull v0.1q,v22.1d,v3.1d //H^2·(Xi+Ii)
eor v16.16b,v16.16b,v3.16b
pmull2 v2.1q,v22.2d,v3.2d
pmull2 v1.1q,v21.2d,v16.2d
eor v0.16b,v0.16b,v29.16b
eor v2.16b,v2.16b,v31.16b
eor v1.16b,v1.16b,v30.16b
b Ldone4x
.align 4
Lone:
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
ld1 {v4.2d},[x2]
eor v1.16b,v1.16b,v18.16b
#ifndef __ARMEB__
rev64 v4.16b,v4.16b
#endif
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
eor v0.16b,v1.16b,v18.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
eor v0.16b,v0.16b,v18.16b
ext v0.16b,v0.16b,v0.16b,#8
eor v16.16b,v4.16b,v0.16b
ext v3.16b,v16.16b,v16.16b,#8
pmull v0.1q,v20.1d,v3.1d
eor v16.16b,v16.16b,v3.16b
pmull2 v2.1q,v20.2d,v3.2d
pmull v1.1q,v21.1d,v16.1d
Ldone4x:
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
eor v0.16b,v1.16b,v18.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
eor v0.16b,v0.16b,v18.16b
ext v0.16b,v0.16b,v0.16b,#8
#ifndef __ARMEB__
rev64 v0.16b,v0.16b
#endif
st1 {v0.2d},[x0] //write out Xi
ret
.byte 71,72,65,83,72,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
.align 2
.align 2
#endif
#endif // !OPENSSL_NO_ASM

7
third_party/boringssl/kit/ios-aarch64/crypto/fipsmodule/sha1-armv8.S vendored
View File

@@ -17,11 +17,14 @@
.text
.private_extern _OPENSSL_armcap_P
.globl _sha1_block_data_order
.private_extern _sha1_block_data_order
.align 6
_sha1_block_data_order:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
#if __has_feature(hwaddress_sanitizer) && __clang_major__ >= 10
adrp x16,:pg_hi21_nc:_OPENSSL_armcap_P
#else
@@ -1089,6 +1092,8 @@ Loop:
.align 6
sha1_block_armv8:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
Lv8_entry:
stp x29,x30,[sp,#-16]!
add x29,sp,#0
@@ -1227,6 +1232,4 @@ Lconst:
.byte 83,72,65,49,32,98,108,111,99,107,32,116,114,97,110,115,102,111,114,109,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
.align 2
.align 2
.comm _OPENSSL_armcap_P,4,4
.private_extern _OPENSSL_armcap_P
#endif // !OPENSSL_NO_ASM

9
third_party/boringssl/kit/ios-aarch64/crypto/fipsmodule/sha256-armv8.S vendored
View File

@@ -58,11 +58,13 @@
.text
.private_extern _OPENSSL_armcap_P
.globl _sha256_block_data_order
.private_extern _sha256_block_data_order
.align 6
_sha256_block_data_order:
AARCH64_VALID_CALL_TARGET
#ifndef __KERNEL__
#if __has_feature(hwaddress_sanitizer) && __clang_major__ >= 10
adrp x16,:pg_hi21_nc:_OPENSSL_armcap_P
@@ -73,6 +75,7 @@ _sha256_block_data_order:
tst w16,#ARMV8_SHA256
b.ne Lv8_entry
#endif
AARCH64_SIGN_LINK_REGISTER
stp x29,x30,[sp,#-128]!
add x29,sp,#0
@@ -1033,6 +1036,7 @@ Loop_16_xx:
ldp x25,x26,[x29,#64]
ldp x27,x28,[x29,#80]
ldp x29,x30,[sp],#128
AARCH64_VALIDATE_LINK_REGISTER
ret
@@ -1067,6 +1071,7 @@ LK256:
.align 6
sha256_block_armv8:
Lv8_entry:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
stp x29,x30,[sp,#-16]!
add x29,sp,#0
@@ -1202,9 +1207,5 @@ Loop_hw:
ldr x29,[sp],#16
ret
#endif
#ifndef __KERNEL__
.comm _OPENSSL_armcap_P,4,4
.private_extern _OPENSSL_armcap_P
#endif
#endif // !OPENSSL_NO_ASM

7
third_party/boringssl/kit/ios-aarch64/crypto/fipsmodule/sha512-armv8.S vendored
View File

@@ -58,11 +58,13 @@
.text
.private_extern _OPENSSL_armcap_P
.globl _sha512_block_data_order
.private_extern _sha512_block_data_order
.align 6
_sha512_block_data_order:
AARCH64_SIGN_LINK_REGISTER
stp x29,x30,[sp,#-128]!
add x29,sp,#0
@@ -1023,6 +1025,7 @@ Loop_16_xx:
ldp x25,x26,[x29,#64]
ldp x27,x28,[x29,#80]
ldp x29,x30,[sp],#128
AARCH64_VALIDATE_LINK_REGISTER
ret
@@ -1075,8 +1078,4 @@ LK512:
.byte 83,72,65,53,49,50,32,98,108,111,99,107,32,116,114,97,110,115,102,111,114,109,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
.align 2
.align 2
#ifndef __KERNEL__
.comm _OPENSSL_armcap_P,4,4
.private_extern _OPENSSL_armcap_P
#endif
#endif // !OPENSSL_NO_ASM

21
third_party/boringssl/kit/ios-aarch64/crypto/fipsmodule/vpaes-armv8.S vendored
View File

@@ -12,6 +12,8 @@
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
.section __TEXT,__const
@@ -214,6 +216,7 @@ Lenc_entry:
.align 4
_vpaes_encrypt:
AARCH64_SIGN_LINK_REGISTER
stp x29,x30,[sp,#-16]!
add x29,sp,#0
@@ -223,6 +226,7 @@ _vpaes_encrypt:
st1 {v0.16b}, [x1]
ldp x29,x30,[sp],#16
AARCH64_VALIDATE_LINK_REGISTER
ret
@@ -451,6 +455,7 @@ Ldec_entry:
.align 4
_vpaes_decrypt:
AARCH64_SIGN_LINK_REGISTER
stp x29,x30,[sp,#-16]!
add x29,sp,#0
@@ -460,6 +465,7 @@ _vpaes_decrypt:
st1 {v0.16b}, [x1]
ldp x29,x30,[sp],#16
AARCH64_VALIDATE_LINK_REGISTER
ret
@@ -629,6 +635,7 @@ _vpaes_key_preheat:
.align 4
_vpaes_schedule_core:
AARCH64_SIGN_LINK_REGISTER
stp x29, x30, [sp,#-16]!
add x29,sp,#0
@@ -798,6 +805,7 @@ Lschedule_mangle_last_dec:
eor v6.16b, v6.16b, v6.16b // vpxor %xmm6, %xmm6, %xmm6
eor v7.16b, v7.16b, v7.16b // vpxor %xmm7, %xmm7, %xmm7
ldp x29, x30, [sp],#16
AARCH64_VALIDATE_LINK_REGISTER
ret
@@ -1000,7 +1008,7 @@ Lschedule_mangle_dec:
Lschedule_mangle_both:
tbl v3.16b, {v3.16b}, v1.16b // vpshufb %xmm1, %xmm3, %xmm3
add x8, x8, #64-16 // add $-16, %r8
add x8, x8, #48 // add $-16, %r8
and x8, x8, #~(1<<6) // and $0x30, %r8
st1 {v3.2d}, [x2] // vmovdqu %xmm3, (%rdx)
ret
@@ -1011,6 +1019,7 @@ Lschedule_mangle_both:
.align 4
_vpaes_set_encrypt_key:
AARCH64_SIGN_LINK_REGISTER
stp x29,x30,[sp,#-16]!
add x29,sp,#0
stp d8,d9,[sp,#-16]! // ABI spec says so
@@ -1026,6 +1035,7 @@ _vpaes_set_encrypt_key:
ldp d8,d9,[sp],#16
ldp x29,x30,[sp],#16
AARCH64_VALIDATE_LINK_REGISTER
ret
@@ -1034,6 +1044,7 @@ _vpaes_set_encrypt_key:
.align 4
_vpaes_set_decrypt_key:
AARCH64_SIGN_LINK_REGISTER
stp x29,x30,[sp,#-16]!
add x29,sp,#0
stp d8,d9,[sp,#-16]! // ABI spec says so
@@ -1053,6 +1064,7 @@ _vpaes_set_decrypt_key:
ldp d8,d9,[sp],#16
ldp x29,x30,[sp],#16
AARCH64_VALIDATE_LINK_REGISTER
ret
.globl _vpaes_cbc_encrypt
@@ -1060,6 +1072,7 @@ _vpaes_set_decrypt_key:
.align 4
_vpaes_cbc_encrypt:
AARCH64_SIGN_LINK_REGISTER
cbz x2, Lcbc_abort
cmp w5, #0 // check direction
b.eq vpaes_cbc_decrypt
@@ -1087,12 +1100,15 @@ Lcbc_enc_loop:
ldp x29,x30,[sp],#16
Lcbc_abort:
AARCH64_VALIDATE_LINK_REGISTER
ret
.align 4
vpaes_cbc_decrypt:
// Not adding AARCH64_SIGN_LINK_REGISTER here because vpaes_cbc_decrypt is jumped to
// only from vpaes_cbc_encrypt which has already signed the return address.
stp x29,x30,[sp,#-16]!
add x29,sp,#0
stp d8,d9,[sp,#-16]! // ABI spec says so
@@ -1134,6 +1150,7 @@ Lcbc_dec_done:
ldp d10,d11,[sp],#16
ldp d8,d9,[sp],#16
ldp x29,x30,[sp],#16
AARCH64_VALIDATE_LINK_REGISTER
ret
.globl _vpaes_ctr32_encrypt_blocks
@@ -1141,6 +1158,7 @@ Lcbc_dec_done:
.align 4
_vpaes_ctr32_encrypt_blocks:
AARCH64_SIGN_LINK_REGISTER
stp x29,x30,[sp,#-16]!
add x29,sp,#0
stp d8,d9,[sp,#-16]! // ABI spec says so
@@ -1208,6 +1226,7 @@ Lctr32_done:
ldp d10,d11,[sp],#16
ldp d8,d9,[sp],#16
ldp x29,x30,[sp],#16
AARCH64_VALIDATE_LINK_REGISTER
ret
#endif // !OPENSSL_NO_ASM