OpenCloudOS-Kernel/arch/x86/crypto/chacha-avx512vl-x86_64.S

837 lines
20 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0+ */
/*
* ChaCha 256-bit cipher algorithm, x64 AVX-512VL functions
*
* Copyright (C) 2018 Martin Willi
*/
#include <linux/linkage.h>
.section .rodata.cst32.CTR2BL, "aM", @progbits, 32
.align 32
CTR2BL: .octa 0x00000000000000000000000000000000
.octa 0x00000000000000000000000000000001
.section .rodata.cst32.CTR4BL, "aM", @progbits, 32
.align 32
CTR4BL: .octa 0x00000000000000000000000000000002
.octa 0x00000000000000000000000000000003
.section .rodata.cst32.CTR8BL, "aM", @progbits, 32
.align 32
CTR8BL: .octa 0x00000003000000020000000100000000
.octa 0x00000007000000060000000500000004
.text
ENTRY(chacha_2block_xor_avx512vl)
# %rdi: Input state matrix, s
# %rsi: up to 2 data blocks output, o
# %rdx: up to 2 data blocks input, i
# %rcx: input/output length in bytes
# %r8d: nrounds
# This function encrypts two ChaCha blocks by loading the state
# matrix twice across four AVX registers. It performs matrix operations
# on four words in each matrix in parallel, but requires shuffling to
# rearrange the words after each round.
vzeroupper
# x0..3[0-2] = s0..3
vbroadcasti128 0x00(%rdi),%ymm0
vbroadcasti128 0x10(%rdi),%ymm1
vbroadcasti128 0x20(%rdi),%ymm2
vbroadcasti128 0x30(%rdi),%ymm3
vpaddd CTR2BL(%rip),%ymm3,%ymm3
vmovdqa %ymm0,%ymm8
vmovdqa %ymm1,%ymm9
vmovdqa %ymm2,%ymm10
vmovdqa %ymm3,%ymm11
.Ldoubleround:
# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
vpaddd %ymm1,%ymm0,%ymm0
vpxord %ymm0,%ymm3,%ymm3
vprold $16,%ymm3,%ymm3
# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
vpaddd %ymm3,%ymm2,%ymm2
vpxord %ymm2,%ymm1,%ymm1
vprold $12,%ymm1,%ymm1
# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
vpaddd %ymm1,%ymm0,%ymm0
vpxord %ymm0,%ymm3,%ymm3
vprold $8,%ymm3,%ymm3
# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
vpaddd %ymm3,%ymm2,%ymm2
vpxord %ymm2,%ymm1,%ymm1
vprold $7,%ymm1,%ymm1
# x1 = shuffle32(x1, MASK(0, 3, 2, 1))
vpshufd $0x39,%ymm1,%ymm1
# x2 = shuffle32(x2, MASK(1, 0, 3, 2))
vpshufd $0x4e,%ymm2,%ymm2
# x3 = shuffle32(x3, MASK(2, 1, 0, 3))
vpshufd $0x93,%ymm3,%ymm3
# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
vpaddd %ymm1,%ymm0,%ymm0
vpxord %ymm0,%ymm3,%ymm3
vprold $16,%ymm3,%ymm3
# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
vpaddd %ymm3,%ymm2,%ymm2
vpxord %ymm2,%ymm1,%ymm1
vprold $12,%ymm1,%ymm1
# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
vpaddd %ymm1,%ymm0,%ymm0
vpxord %ymm0,%ymm3,%ymm3
vprold $8,%ymm3,%ymm3
# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
vpaddd %ymm3,%ymm2,%ymm2
vpxord %ymm2,%ymm1,%ymm1
vprold $7,%ymm1,%ymm1
# x1 = shuffle32(x1, MASK(2, 1, 0, 3))
vpshufd $0x93,%ymm1,%ymm1
# x2 = shuffle32(x2, MASK(1, 0, 3, 2))
vpshufd $0x4e,%ymm2,%ymm2
# x3 = shuffle32(x3, MASK(0, 3, 2, 1))
vpshufd $0x39,%ymm3,%ymm3
sub $2,%r8d
jnz .Ldoubleround
# o0 = i0 ^ (x0 + s0)
vpaddd %ymm8,%ymm0,%ymm7
cmp $0x10,%rcx
jl .Lxorpart2
vpxord 0x00(%rdx),%xmm7,%xmm6
vmovdqu %xmm6,0x00(%rsi)
vextracti128 $1,%ymm7,%xmm0
# o1 = i1 ^ (x1 + s1)
vpaddd %ymm9,%ymm1,%ymm7
cmp $0x20,%rcx
jl .Lxorpart2
vpxord 0x10(%rdx),%xmm7,%xmm6
vmovdqu %xmm6,0x10(%rsi)
vextracti128 $1,%ymm7,%xmm1
# o2 = i2 ^ (x2 + s2)
vpaddd %ymm10,%ymm2,%ymm7
cmp $0x30,%rcx
jl .Lxorpart2
vpxord 0x20(%rdx),%xmm7,%xmm6
vmovdqu %xmm6,0x20(%rsi)
vextracti128 $1,%ymm7,%xmm2
# o3 = i3 ^ (x3 + s3)
vpaddd %ymm11,%ymm3,%ymm7
cmp $0x40,%rcx
jl .Lxorpart2
vpxord 0x30(%rdx),%xmm7,%xmm6
vmovdqu %xmm6,0x30(%rsi)
vextracti128 $1,%ymm7,%xmm3
# xor and write second block
vmovdqa %xmm0,%xmm7
cmp $0x50,%rcx
jl .Lxorpart2
vpxord 0x40(%rdx),%xmm7,%xmm6
vmovdqu %xmm6,0x40(%rsi)
vmovdqa %xmm1,%xmm7
cmp $0x60,%rcx
jl .Lxorpart2
vpxord 0x50(%rdx),%xmm7,%xmm6
vmovdqu %xmm6,0x50(%rsi)
vmovdqa %xmm2,%xmm7
cmp $0x70,%rcx
jl .Lxorpart2
vpxord 0x60(%rdx),%xmm7,%xmm6
vmovdqu %xmm6,0x60(%rsi)
vmovdqa %xmm3,%xmm7
cmp $0x80,%rcx
jl .Lxorpart2
vpxord 0x70(%rdx),%xmm7,%xmm6
vmovdqu %xmm6,0x70(%rsi)
.Ldone2:
vzeroupper
ret
.Lxorpart2:
# xor remaining bytes from partial register into output
mov %rcx,%rax
and $0xf,%rcx
jz .Ldone2
mov %rax,%r9
and $~0xf,%r9
mov $1,%rax
shld %cl,%rax,%rax
sub $1,%rax
kmovq %rax,%k1
vmovdqu8 (%rdx,%r9),%xmm1{%k1}{z}
vpxord %xmm7,%xmm1,%xmm1
vmovdqu8 %xmm1,(%rsi,%r9){%k1}
jmp .Ldone2
ENDPROC(chacha_2block_xor_avx512vl)
ENTRY(chacha_4block_xor_avx512vl)
# %rdi: Input state matrix, s
# %rsi: up to 4 data blocks output, o
# %rdx: up to 4 data blocks input, i
# %rcx: input/output length in bytes
# %r8d: nrounds
# This function encrypts four ChaCha blocks by loading the state
# matrix four times across eight AVX registers. It performs matrix
# operations on four words in two matrices in parallel, sequentially
# to the operations on the four words of the other two matrices. The
# required word shuffling has a rather high latency, we can do the
# arithmetic on two matrix-pairs without much slowdown.
vzeroupper
# x0..3[0-4] = s0..3
vbroadcasti128 0x00(%rdi),%ymm0
vbroadcasti128 0x10(%rdi),%ymm1
vbroadcasti128 0x20(%rdi),%ymm2
vbroadcasti128 0x30(%rdi),%ymm3
vmovdqa %ymm0,%ymm4
vmovdqa %ymm1,%ymm5
vmovdqa %ymm2,%ymm6
vmovdqa %ymm3,%ymm7
vpaddd CTR2BL(%rip),%ymm3,%ymm3
vpaddd CTR4BL(%rip),%ymm7,%ymm7
vmovdqa %ymm0,%ymm11
vmovdqa %ymm1,%ymm12
vmovdqa %ymm2,%ymm13
vmovdqa %ymm3,%ymm14
vmovdqa %ymm7,%ymm15
.Ldoubleround4:
# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
vpaddd %ymm1,%ymm0,%ymm0
vpxord %ymm0,%ymm3,%ymm3
vprold $16,%ymm3,%ymm3
vpaddd %ymm5,%ymm4,%ymm4
vpxord %ymm4,%ymm7,%ymm7
vprold $16,%ymm7,%ymm7
# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
vpaddd %ymm3,%ymm2,%ymm2
vpxord %ymm2,%ymm1,%ymm1
vprold $12,%ymm1,%ymm1
vpaddd %ymm7,%ymm6,%ymm6
vpxord %ymm6,%ymm5,%ymm5
vprold $12,%ymm5,%ymm5
# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
vpaddd %ymm1,%ymm0,%ymm0
vpxord %ymm0,%ymm3,%ymm3
vprold $8,%ymm3,%ymm3
vpaddd %ymm5,%ymm4,%ymm4
vpxord %ymm4,%ymm7,%ymm7
vprold $8,%ymm7,%ymm7
# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
vpaddd %ymm3,%ymm2,%ymm2
vpxord %ymm2,%ymm1,%ymm1
vprold $7,%ymm1,%ymm1
vpaddd %ymm7,%ymm6,%ymm6
vpxord %ymm6,%ymm5,%ymm5
vprold $7,%ymm5,%ymm5
# x1 = shuffle32(x1, MASK(0, 3, 2, 1))
vpshufd $0x39,%ymm1,%ymm1
vpshufd $0x39,%ymm5,%ymm5
# x2 = shuffle32(x2, MASK(1, 0, 3, 2))
vpshufd $0x4e,%ymm2,%ymm2
vpshufd $0x4e,%ymm6,%ymm6
# x3 = shuffle32(x3, MASK(2, 1, 0, 3))
vpshufd $0x93,%ymm3,%ymm3
vpshufd $0x93,%ymm7,%ymm7
# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
vpaddd %ymm1,%ymm0,%ymm0
vpxord %ymm0,%ymm3,%ymm3
vprold $16,%ymm3,%ymm3
vpaddd %ymm5,%ymm4,%ymm4
vpxord %ymm4,%ymm7,%ymm7
vprold $16,%ymm7,%ymm7
# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
vpaddd %ymm3,%ymm2,%ymm2
vpxord %ymm2,%ymm1,%ymm1
vprold $12,%ymm1,%ymm1
vpaddd %ymm7,%ymm6,%ymm6
vpxord %ymm6,%ymm5,%ymm5
vprold $12,%ymm5,%ymm5
# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
vpaddd %ymm1,%ymm0,%ymm0
vpxord %ymm0,%ymm3,%ymm3
vprold $8,%ymm3,%ymm3
vpaddd %ymm5,%ymm4,%ymm4
vpxord %ymm4,%ymm7,%ymm7
vprold $8,%ymm7,%ymm7
# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
vpaddd %ymm3,%ymm2,%ymm2
vpxord %ymm2,%ymm1,%ymm1
vprold $7,%ymm1,%ymm1
vpaddd %ymm7,%ymm6,%ymm6
vpxord %ymm6,%ymm5,%ymm5
vprold $7,%ymm5,%ymm5
# x1 = shuffle32(x1, MASK(2, 1, 0, 3))
vpshufd $0x93,%ymm1,%ymm1
vpshufd $0x93,%ymm5,%ymm5
# x2 = shuffle32(x2, MASK(1, 0, 3, 2))
vpshufd $0x4e,%ymm2,%ymm2
vpshufd $0x4e,%ymm6,%ymm6
# x3 = shuffle32(x3, MASK(0, 3, 2, 1))
vpshufd $0x39,%ymm3,%ymm3
vpshufd $0x39,%ymm7,%ymm7
sub $2,%r8d
jnz .Ldoubleround4
# o0 = i0 ^ (x0 + s0), first block
vpaddd %ymm11,%ymm0,%ymm10
cmp $0x10,%rcx
jl .Lxorpart4
vpxord 0x00(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0x00(%rsi)
vextracti128 $1,%ymm10,%xmm0
# o1 = i1 ^ (x1 + s1), first block
vpaddd %ymm12,%ymm1,%ymm10
cmp $0x20,%rcx
jl .Lxorpart4
vpxord 0x10(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0x10(%rsi)
vextracti128 $1,%ymm10,%xmm1
# o2 = i2 ^ (x2 + s2), first block
vpaddd %ymm13,%ymm2,%ymm10
cmp $0x30,%rcx
jl .Lxorpart4
vpxord 0x20(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0x20(%rsi)
vextracti128 $1,%ymm10,%xmm2
# o3 = i3 ^ (x3 + s3), first block
vpaddd %ymm14,%ymm3,%ymm10
cmp $0x40,%rcx
jl .Lxorpart4
vpxord 0x30(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0x30(%rsi)
vextracti128 $1,%ymm10,%xmm3
# xor and write second block
vmovdqa %xmm0,%xmm10
cmp $0x50,%rcx
jl .Lxorpart4
vpxord 0x40(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0x40(%rsi)
vmovdqa %xmm1,%xmm10
cmp $0x60,%rcx
jl .Lxorpart4
vpxord 0x50(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0x50(%rsi)
vmovdqa %xmm2,%xmm10
cmp $0x70,%rcx
jl .Lxorpart4
vpxord 0x60(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0x60(%rsi)
vmovdqa %xmm3,%xmm10
cmp $0x80,%rcx
jl .Lxorpart4
vpxord 0x70(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0x70(%rsi)
# o0 = i0 ^ (x0 + s0), third block
vpaddd %ymm11,%ymm4,%ymm10
cmp $0x90,%rcx
jl .Lxorpart4
vpxord 0x80(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0x80(%rsi)
vextracti128 $1,%ymm10,%xmm4
# o1 = i1 ^ (x1 + s1), third block
vpaddd %ymm12,%ymm5,%ymm10
cmp $0xa0,%rcx
jl .Lxorpart4
vpxord 0x90(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0x90(%rsi)
vextracti128 $1,%ymm10,%xmm5
# o2 = i2 ^ (x2 + s2), third block
vpaddd %ymm13,%ymm6,%ymm10
cmp $0xb0,%rcx
jl .Lxorpart4
vpxord 0xa0(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0xa0(%rsi)
vextracti128 $1,%ymm10,%xmm6
# o3 = i3 ^ (x3 + s3), third block
vpaddd %ymm15,%ymm7,%ymm10
cmp $0xc0,%rcx
jl .Lxorpart4
vpxord 0xb0(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0xb0(%rsi)
vextracti128 $1,%ymm10,%xmm7
# xor and write fourth block
vmovdqa %xmm4,%xmm10
cmp $0xd0,%rcx
jl .Lxorpart4
vpxord 0xc0(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0xc0(%rsi)
vmovdqa %xmm5,%xmm10
cmp $0xe0,%rcx
jl .Lxorpart4
vpxord 0xd0(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0xd0(%rsi)
vmovdqa %xmm6,%xmm10
cmp $0xf0,%rcx
jl .Lxorpart4
vpxord 0xe0(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0xe0(%rsi)
vmovdqa %xmm7,%xmm10
cmp $0x100,%rcx
jl .Lxorpart4
vpxord 0xf0(%rdx),%xmm10,%xmm9
vmovdqu %xmm9,0xf0(%rsi)
.Ldone4:
vzeroupper
ret
.Lxorpart4:
# xor remaining bytes from partial register into output
mov %rcx,%rax
and $0xf,%rcx
jz .Ldone4
mov %rax,%r9
and $~0xf,%r9
mov $1,%rax
shld %cl,%rax,%rax
sub $1,%rax
kmovq %rax,%k1
vmovdqu8 (%rdx,%r9),%xmm1{%k1}{z}
vpxord %xmm10,%xmm1,%xmm1
vmovdqu8 %xmm1,(%rsi,%r9){%k1}
jmp .Ldone4
ENDPROC(chacha_4block_xor_avx512vl)
ENTRY(chacha_8block_xor_avx512vl)
# %rdi: Input state matrix, s
# %rsi: up to 8 data blocks output, o
# %rdx: up to 8 data blocks input, i
# %rcx: input/output length in bytes
# %r8d: nrounds
# This function encrypts eight consecutive ChaCha blocks by loading
# the state matrix in AVX registers eight times. Compared to AVX2, this
# mostly benefits from the new rotate instructions in VL and the
# additional registers.
vzeroupper
# x0..15[0-7] = s[0..15]
vpbroadcastd 0x00(%rdi),%ymm0
vpbroadcastd 0x04(%rdi),%ymm1
vpbroadcastd 0x08(%rdi),%ymm2
vpbroadcastd 0x0c(%rdi),%ymm3
vpbroadcastd 0x10(%rdi),%ymm4
vpbroadcastd 0x14(%rdi),%ymm5
vpbroadcastd 0x18(%rdi),%ymm6
vpbroadcastd 0x1c(%rdi),%ymm7
vpbroadcastd 0x20(%rdi),%ymm8
vpbroadcastd 0x24(%rdi),%ymm9
vpbroadcastd 0x28(%rdi),%ymm10
vpbroadcastd 0x2c(%rdi),%ymm11
vpbroadcastd 0x30(%rdi),%ymm12
vpbroadcastd 0x34(%rdi),%ymm13
vpbroadcastd 0x38(%rdi),%ymm14
vpbroadcastd 0x3c(%rdi),%ymm15
# x12 += counter values 0-3
vpaddd CTR8BL(%rip),%ymm12,%ymm12
vmovdqa64 %ymm0,%ymm16
vmovdqa64 %ymm1,%ymm17
vmovdqa64 %ymm2,%ymm18
vmovdqa64 %ymm3,%ymm19
vmovdqa64 %ymm4,%ymm20
vmovdqa64 %ymm5,%ymm21
vmovdqa64 %ymm6,%ymm22
vmovdqa64 %ymm7,%ymm23
vmovdqa64 %ymm8,%ymm24
vmovdqa64 %ymm9,%ymm25
vmovdqa64 %ymm10,%ymm26
vmovdqa64 %ymm11,%ymm27
vmovdqa64 %ymm12,%ymm28
vmovdqa64 %ymm13,%ymm29
vmovdqa64 %ymm14,%ymm30
vmovdqa64 %ymm15,%ymm31
.Ldoubleround8:
# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
vpaddd %ymm0,%ymm4,%ymm0
vpxord %ymm0,%ymm12,%ymm12
vprold $16,%ymm12,%ymm12
# x1 += x5, x13 = rotl32(x13 ^ x1, 16)
vpaddd %ymm1,%ymm5,%ymm1
vpxord %ymm1,%ymm13,%ymm13
vprold $16,%ymm13,%ymm13
# x2 += x6, x14 = rotl32(x14 ^ x2, 16)
vpaddd %ymm2,%ymm6,%ymm2
vpxord %ymm2,%ymm14,%ymm14
vprold $16,%ymm14,%ymm14
# x3 += x7, x15 = rotl32(x15 ^ x3, 16)
vpaddd %ymm3,%ymm7,%ymm3
vpxord %ymm3,%ymm15,%ymm15
vprold $16,%ymm15,%ymm15
# x8 += x12, x4 = rotl32(x4 ^ x8, 12)
vpaddd %ymm12,%ymm8,%ymm8
vpxord %ymm8,%ymm4,%ymm4
vprold $12,%ymm4,%ymm4
# x9 += x13, x5 = rotl32(x5 ^ x9, 12)
vpaddd %ymm13,%ymm9,%ymm9
vpxord %ymm9,%ymm5,%ymm5
vprold $12,%ymm5,%ymm5
# x10 += x14, x6 = rotl32(x6 ^ x10, 12)
vpaddd %ymm14,%ymm10,%ymm10
vpxord %ymm10,%ymm6,%ymm6
vprold $12,%ymm6,%ymm6
# x11 += x15, x7 = rotl32(x7 ^ x11, 12)
vpaddd %ymm15,%ymm11,%ymm11
vpxord %ymm11,%ymm7,%ymm7
vprold $12,%ymm7,%ymm7
# x0 += x4, x12 = rotl32(x12 ^ x0, 8)
vpaddd %ymm0,%ymm4,%ymm0
vpxord %ymm0,%ymm12,%ymm12
vprold $8,%ymm12,%ymm12
# x1 += x5, x13 = rotl32(x13 ^ x1, 8)
vpaddd %ymm1,%ymm5,%ymm1
vpxord %ymm1,%ymm13,%ymm13
vprold $8,%ymm13,%ymm13
# x2 += x6, x14 = rotl32(x14 ^ x2, 8)
vpaddd %ymm2,%ymm6,%ymm2
vpxord %ymm2,%ymm14,%ymm14
vprold $8,%ymm14,%ymm14
# x3 += x7, x15 = rotl32(x15 ^ x3, 8)
vpaddd %ymm3,%ymm7,%ymm3
vpxord %ymm3,%ymm15,%ymm15
vprold $8,%ymm15,%ymm15
# x8 += x12, x4 = rotl32(x4 ^ x8, 7)
vpaddd %ymm12,%ymm8,%ymm8
vpxord %ymm8,%ymm4,%ymm4
vprold $7,%ymm4,%ymm4
# x9 += x13, x5 = rotl32(x5 ^ x9, 7)
vpaddd %ymm13,%ymm9,%ymm9
vpxord %ymm9,%ymm5,%ymm5
vprold $7,%ymm5,%ymm5
# x10 += x14, x6 = rotl32(x6 ^ x10, 7)
vpaddd %ymm14,%ymm10,%ymm10
vpxord %ymm10,%ymm6,%ymm6
vprold $7,%ymm6,%ymm6
# x11 += x15, x7 = rotl32(x7 ^ x11, 7)
vpaddd %ymm15,%ymm11,%ymm11
vpxord %ymm11,%ymm7,%ymm7
vprold $7,%ymm7,%ymm7
# x0 += x5, x15 = rotl32(x15 ^ x0, 16)
vpaddd %ymm0,%ymm5,%ymm0
vpxord %ymm0,%ymm15,%ymm15
vprold $16,%ymm15,%ymm15
# x1 += x6, x12 = rotl32(x12 ^ x1, 16)
vpaddd %ymm1,%ymm6,%ymm1
vpxord %ymm1,%ymm12,%ymm12
vprold $16,%ymm12,%ymm12
# x2 += x7, x13 = rotl32(x13 ^ x2, 16)
vpaddd %ymm2,%ymm7,%ymm2
vpxord %ymm2,%ymm13,%ymm13
vprold $16,%ymm13,%ymm13
# x3 += x4, x14 = rotl32(x14 ^ x3, 16)
vpaddd %ymm3,%ymm4,%ymm3
vpxord %ymm3,%ymm14,%ymm14
vprold $16,%ymm14,%ymm14
# x10 += x15, x5 = rotl32(x5 ^ x10, 12)
vpaddd %ymm15,%ymm10,%ymm10
vpxord %ymm10,%ymm5,%ymm5
vprold $12,%ymm5,%ymm5
# x11 += x12, x6 = rotl32(x6 ^ x11, 12)
vpaddd %ymm12,%ymm11,%ymm11
vpxord %ymm11,%ymm6,%ymm6
vprold $12,%ymm6,%ymm6
# x8 += x13, x7 = rotl32(x7 ^ x8, 12)
vpaddd %ymm13,%ymm8,%ymm8
vpxord %ymm8,%ymm7,%ymm7
vprold $12,%ymm7,%ymm7
# x9 += x14, x4 = rotl32(x4 ^ x9, 12)
vpaddd %ymm14,%ymm9,%ymm9
vpxord %ymm9,%ymm4,%ymm4
vprold $12,%ymm4,%ymm4
# x0 += x5, x15 = rotl32(x15 ^ x0, 8)
vpaddd %ymm0,%ymm5,%ymm0
vpxord %ymm0,%ymm15,%ymm15
vprold $8,%ymm15,%ymm15
# x1 += x6, x12 = rotl32(x12 ^ x1, 8)
vpaddd %ymm1,%ymm6,%ymm1
vpxord %ymm1,%ymm12,%ymm12
vprold $8,%ymm12,%ymm12
# x2 += x7, x13 = rotl32(x13 ^ x2, 8)
vpaddd %ymm2,%ymm7,%ymm2
vpxord %ymm2,%ymm13,%ymm13
vprold $8,%ymm13,%ymm13
# x3 += x4, x14 = rotl32(x14 ^ x3, 8)
vpaddd %ymm3,%ymm4,%ymm3
vpxord %ymm3,%ymm14,%ymm14
vprold $8,%ymm14,%ymm14
# x10 += x15, x5 = rotl32(x5 ^ x10, 7)
vpaddd %ymm15,%ymm10,%ymm10
vpxord %ymm10,%ymm5,%ymm5
vprold $7,%ymm5,%ymm5
# x11 += x12, x6 = rotl32(x6 ^ x11, 7)
vpaddd %ymm12,%ymm11,%ymm11
vpxord %ymm11,%ymm6,%ymm6
vprold $7,%ymm6,%ymm6
# x8 += x13, x7 = rotl32(x7 ^ x8, 7)
vpaddd %ymm13,%ymm8,%ymm8
vpxord %ymm8,%ymm7,%ymm7
vprold $7,%ymm7,%ymm7
# x9 += x14, x4 = rotl32(x4 ^ x9, 7)
vpaddd %ymm14,%ymm9,%ymm9
vpxord %ymm9,%ymm4,%ymm4
vprold $7,%ymm4,%ymm4
sub $2,%r8d
jnz .Ldoubleround8
# x0..15[0-3] += s[0..15]
vpaddd %ymm16,%ymm0,%ymm0
vpaddd %ymm17,%ymm1,%ymm1
vpaddd %ymm18,%ymm2,%ymm2
vpaddd %ymm19,%ymm3,%ymm3
vpaddd %ymm20,%ymm4,%ymm4
vpaddd %ymm21,%ymm5,%ymm5
vpaddd %ymm22,%ymm6,%ymm6
vpaddd %ymm23,%ymm7,%ymm7
vpaddd %ymm24,%ymm8,%ymm8
vpaddd %ymm25,%ymm9,%ymm9
vpaddd %ymm26,%ymm10,%ymm10
vpaddd %ymm27,%ymm11,%ymm11
vpaddd %ymm28,%ymm12,%ymm12
vpaddd %ymm29,%ymm13,%ymm13
vpaddd %ymm30,%ymm14,%ymm14
vpaddd %ymm31,%ymm15,%ymm15
# interleave 32-bit words in state n, n+1
vpunpckldq %ymm1,%ymm0,%ymm16
vpunpckhdq %ymm1,%ymm0,%ymm17
vpunpckldq %ymm3,%ymm2,%ymm18
vpunpckhdq %ymm3,%ymm2,%ymm19
vpunpckldq %ymm5,%ymm4,%ymm20
vpunpckhdq %ymm5,%ymm4,%ymm21
vpunpckldq %ymm7,%ymm6,%ymm22
vpunpckhdq %ymm7,%ymm6,%ymm23
vpunpckldq %ymm9,%ymm8,%ymm24
vpunpckhdq %ymm9,%ymm8,%ymm25
vpunpckldq %ymm11,%ymm10,%ymm26
vpunpckhdq %ymm11,%ymm10,%ymm27
vpunpckldq %ymm13,%ymm12,%ymm28
vpunpckhdq %ymm13,%ymm12,%ymm29
vpunpckldq %ymm15,%ymm14,%ymm30
vpunpckhdq %ymm15,%ymm14,%ymm31
# interleave 64-bit words in state n, n+2
vpunpcklqdq %ymm18,%ymm16,%ymm0
vpunpcklqdq %ymm19,%ymm17,%ymm1
vpunpckhqdq %ymm18,%ymm16,%ymm2
vpunpckhqdq %ymm19,%ymm17,%ymm3
vpunpcklqdq %ymm22,%ymm20,%ymm4
vpunpcklqdq %ymm23,%ymm21,%ymm5
vpunpckhqdq %ymm22,%ymm20,%ymm6
vpunpckhqdq %ymm23,%ymm21,%ymm7
vpunpcklqdq %ymm26,%ymm24,%ymm8
vpunpcklqdq %ymm27,%ymm25,%ymm9
vpunpckhqdq %ymm26,%ymm24,%ymm10
vpunpckhqdq %ymm27,%ymm25,%ymm11
vpunpcklqdq %ymm30,%ymm28,%ymm12
vpunpcklqdq %ymm31,%ymm29,%ymm13
vpunpckhqdq %ymm30,%ymm28,%ymm14
vpunpckhqdq %ymm31,%ymm29,%ymm15
# interleave 128-bit words in state n, n+4
# xor/write first four blocks
vmovdqa64 %ymm0,%ymm16
vperm2i128 $0x20,%ymm4,%ymm0,%ymm0
cmp $0x0020,%rcx
jl .Lxorpart8
vpxord 0x0000(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x0000(%rsi)
vmovdqa64 %ymm16,%ymm0
vperm2i128 $0x31,%ymm4,%ymm0,%ymm4
vperm2i128 $0x20,%ymm12,%ymm8,%ymm0
cmp $0x0040,%rcx
jl .Lxorpart8
vpxord 0x0020(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x0020(%rsi)
vperm2i128 $0x31,%ymm12,%ymm8,%ymm12
vperm2i128 $0x20,%ymm6,%ymm2,%ymm0
cmp $0x0060,%rcx
jl .Lxorpart8
vpxord 0x0040(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x0040(%rsi)
vperm2i128 $0x31,%ymm6,%ymm2,%ymm6
vperm2i128 $0x20,%ymm14,%ymm10,%ymm0
cmp $0x0080,%rcx
jl .Lxorpart8
vpxord 0x0060(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x0060(%rsi)
vperm2i128 $0x31,%ymm14,%ymm10,%ymm14
vperm2i128 $0x20,%ymm5,%ymm1,%ymm0
cmp $0x00a0,%rcx
jl .Lxorpart8
vpxord 0x0080(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x0080(%rsi)
vperm2i128 $0x31,%ymm5,%ymm1,%ymm5
vperm2i128 $0x20,%ymm13,%ymm9,%ymm0
cmp $0x00c0,%rcx
jl .Lxorpart8
vpxord 0x00a0(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x00a0(%rsi)
vperm2i128 $0x31,%ymm13,%ymm9,%ymm13
vperm2i128 $0x20,%ymm7,%ymm3,%ymm0
cmp $0x00e0,%rcx
jl .Lxorpart8
vpxord 0x00c0(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x00c0(%rsi)
vperm2i128 $0x31,%ymm7,%ymm3,%ymm7
vperm2i128 $0x20,%ymm15,%ymm11,%ymm0
cmp $0x0100,%rcx
jl .Lxorpart8
vpxord 0x00e0(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x00e0(%rsi)
vperm2i128 $0x31,%ymm15,%ymm11,%ymm15
# xor remaining blocks, write to output
vmovdqa64 %ymm4,%ymm0
cmp $0x0120,%rcx
jl .Lxorpart8
vpxord 0x0100(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x0100(%rsi)
vmovdqa64 %ymm12,%ymm0
cmp $0x0140,%rcx
jl .Lxorpart8
vpxord 0x0120(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x0120(%rsi)
vmovdqa64 %ymm6,%ymm0
cmp $0x0160,%rcx
jl .Lxorpart8
vpxord 0x0140(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x0140(%rsi)
vmovdqa64 %ymm14,%ymm0
cmp $0x0180,%rcx
jl .Lxorpart8
vpxord 0x0160(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x0160(%rsi)
vmovdqa64 %ymm5,%ymm0
cmp $0x01a0,%rcx
jl .Lxorpart8
vpxord 0x0180(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x0180(%rsi)
vmovdqa64 %ymm13,%ymm0
cmp $0x01c0,%rcx
jl .Lxorpart8
vpxord 0x01a0(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x01a0(%rsi)
vmovdqa64 %ymm7,%ymm0
cmp $0x01e0,%rcx
jl .Lxorpart8
vpxord 0x01c0(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x01c0(%rsi)
vmovdqa64 %ymm15,%ymm0
cmp $0x0200,%rcx
jl .Lxorpart8
vpxord 0x01e0(%rdx),%ymm0,%ymm0
vmovdqu64 %ymm0,0x01e0(%rsi)
.Ldone8:
vzeroupper
ret
.Lxorpart8:
# xor remaining bytes from partial register into output
mov %rcx,%rax
and $0x1f,%rcx
jz .Ldone8
mov %rax,%r9
and $~0x1f,%r9
mov $1,%rax
shld %cl,%rax,%rax
sub $1,%rax
kmovq %rax,%k1
vmovdqu8 (%rdx,%r9),%ymm1{%k1}{z}
vpxord %ymm0,%ymm1,%ymm1
vmovdqu8 %ymm1,(%rsi,%r9){%k1}
jmp .Ldone8
ENDPROC(chacha_8block_xor_avx512vl)