From 8b65f34c5821e7361488dc668d21195ea4c9f14d Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 4 Dec 2018 22:20:03 -0800
Subject: crypto: x86/chacha20 - refactor to allow varying number of rounds

In preparation for adding XChaCha12 support, rename/refactor the x86_64
SIMD implementations of ChaCha20 to support different numbers of rounds.

Reviewed-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/x86/crypto/Makefile                   |    8 +-
 arch/x86/crypto/chacha-avx2-x86_64.S       | 1025 +++++++++++++++++++++++++++
 arch/x86/crypto/chacha-avx512vl-x86_64.S   |  836 +++++++++++++++++++++++
 arch/x86/crypto/chacha-ssse3-x86_64.S      |  795 +++++++++++++++++++++
 arch/x86/crypto/chacha20-avx2-x86_64.S     | 1026 ----------------------------
 arch/x86/crypto/chacha20-avx512vl-x86_64.S |  839 -----------------------
 arch/x86/crypto/chacha20-ssse3-x86_64.S    |  792 ---------------------
 arch/x86/crypto/chacha20_glue.c            |  264 -------
 arch/x86/crypto/chacha_glue.c              |  270 ++++++++
 9 files changed, 2930 insertions(+), 2925 deletions(-)
 create mode 100644 arch/x86/crypto/chacha-avx2-x86_64.S
 create mode 100644 arch/x86/crypto/chacha-avx512vl-x86_64.S
 create mode 100644 arch/x86/crypto/chacha-ssse3-x86_64.S
 delete mode 100644 arch/x86/crypto/chacha20-avx2-x86_64.S
 delete mode 100644 arch/x86/crypto/chacha20-avx512vl-x86_64.S
 delete mode 100644 arch/x86/crypto/chacha20-ssse3-x86_64.S
 delete mode 100644 arch/x86/crypto/chacha20_glue.c
 create mode 100644 arch/x86/crypto/chacha_glue.c

(limited to 'arch')

diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 0b31b16f49d8..45734e1cf967 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -24,7 +24,7 @@ obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
-obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha20-x86_64.o
+obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o
 obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
 obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
 obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
@@ -78,7 +78,7 @@ camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
 blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
 twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
 twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
-chacha20-x86_64-y := chacha20-ssse3-x86_64.o chacha20_glue.o
+chacha-x86_64-y := chacha-ssse3-x86_64.o chacha_glue.o
 serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
 
 aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
@@ -103,7 +103,7 @@ endif
 
 ifeq ($(avx2_supported),yes)
 	camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
-	chacha20-x86_64-y += chacha20-avx2-x86_64.o
+	chacha-x86_64-y += chacha-avx2-x86_64.o
 	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
 
 	morus1280-avx2-y := morus1280-avx2-asm.o morus1280-avx2-glue.o
@@ -112,7 +112,7 @@ ifeq ($(avx2_supported),yes)
 endif
 
 ifeq ($(avx512_supported),yes)
-	chacha20-x86_64-y += chacha20-avx512vl-x86_64.o
+	chacha-x86_64-y += chacha-avx512vl-x86_64.o
 endif
 
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
diff --git a/arch/x86/crypto/chacha-avx2-x86_64.S b/arch/x86/crypto/chacha-avx2-x86_64.S
new file mode 100644
index 000000000000..32903fd450af
--- /dev/null
+++ b/arch/x86/crypto/chacha-avx2-x86_64.S
@@ -0,0 +1,1025 @@
+/*
+ * ChaCha 256-bit cipher algorithm, x64 AVX2 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+
+.section	.rodata.cst32.ROT8, "aM", @progbits, 32
+.align 32
+ROT8:	.octa 0x0e0d0c0f0a09080b0605040702010003
+	.octa 0x0e0d0c0f0a09080b0605040702010003
+
+.section	.rodata.cst32.ROT16, "aM", @progbits, 32
+.align 32
+ROT16:	.octa 0x0d0c0f0e09080b0a0504070601000302
+	.octa 0x0d0c0f0e09080b0a0504070601000302
+
+.section	.rodata.cst32.CTRINC, "aM", @progbits, 32
+.align 32
+CTRINC:	.octa 0x00000003000000020000000100000000
+	.octa 0x00000007000000060000000500000004
+
+.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
+
+.text
+
+ENTRY(chacha_2block_xor_avx2)
+	# %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
+
+	vmovdqa		ROT8(%rip),%ymm4
+	vmovdqa		ROT16(%rip),%ymm5
+
+	mov		%rcx,%rax
+
+.Ldoubleround:
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	vpaddd		%ymm1,%ymm0,%ymm0
+	vpxor		%ymm0,%ymm3,%ymm3
+	vpshufb		%ymm5,%ymm3,%ymm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	vpaddd		%ymm3,%ymm2,%ymm2
+	vpxor		%ymm2,%ymm1,%ymm1
+	vmovdqa		%ymm1,%ymm6
+	vpslld		$12,%ymm6,%ymm6
+	vpsrld		$20,%ymm1,%ymm1
+	vpor		%ymm6,%ymm1,%ymm1
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	vpaddd		%ymm1,%ymm0,%ymm0
+	vpxor		%ymm0,%ymm3,%ymm3
+	vpshufb		%ymm4,%ymm3,%ymm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	vpaddd		%ymm3,%ymm2,%ymm2
+	vpxor		%ymm2,%ymm1,%ymm1
+	vmovdqa		%ymm1,%ymm7
+	vpslld		$7,%ymm7,%ymm7
+	vpsrld		$25,%ymm1,%ymm1
+	vpor		%ymm7,%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
+	vpxor		%ymm0,%ymm3,%ymm3
+	vpshufb		%ymm5,%ymm3,%ymm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	vpaddd		%ymm3,%ymm2,%ymm2
+	vpxor		%ymm2,%ymm1,%ymm1
+	vmovdqa		%ymm1,%ymm6
+	vpslld		$12,%ymm6,%ymm6
+	vpsrld		$20,%ymm1,%ymm1
+	vpor		%ymm6,%ymm1,%ymm1
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	vpaddd		%ymm1,%ymm0,%ymm0
+	vpxor		%ymm0,%ymm3,%ymm3
+	vpshufb		%ymm4,%ymm3,%ymm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	vpaddd		%ymm3,%ymm2,%ymm2
+	vpxor		%ymm2,%ymm1,%ymm1
+	vmovdqa		%ymm1,%ymm7
+	vpslld		$7,%ymm7,%ymm7
+	vpsrld		$25,%ymm1,%ymm1
+	vpor		%ymm7,%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,%rax
+	jl		.Lxorpart2
+	vpxor		0x00(%rdx),%xmm7,%xmm6
+	vmovdqu		%xmm6,0x00(%rsi)
+	vextracti128	$1,%ymm7,%xmm0
+	# o1 = i1 ^ (x1 + s1)
+	vpaddd		%ymm9,%ymm1,%ymm7
+	cmp		$0x20,%rax
+	jl		.Lxorpart2
+	vpxor		0x10(%rdx),%xmm7,%xmm6
+	vmovdqu		%xmm6,0x10(%rsi)
+	vextracti128	$1,%ymm7,%xmm1
+	# o2 = i2 ^ (x2 + s2)
+	vpaddd		%ymm10,%ymm2,%ymm7
+	cmp		$0x30,%rax
+	jl		.Lxorpart2
+	vpxor		0x20(%rdx),%xmm7,%xmm6
+	vmovdqu		%xmm6,0x20(%rsi)
+	vextracti128	$1,%ymm7,%xmm2
+	# o3 = i3 ^ (x3 + s3)
+	vpaddd		%ymm11,%ymm3,%ymm7
+	cmp		$0x40,%rax
+	jl		.Lxorpart2
+	vpxor		0x30(%rdx),%xmm7,%xmm6
+	vmovdqu		%xmm6,0x30(%rsi)
+	vextracti128	$1,%ymm7,%xmm3
+
+	# xor and write second block
+	vmovdqa		%xmm0,%xmm7
+	cmp		$0x50,%rax
+	jl		.Lxorpart2
+	vpxor		0x40(%rdx),%xmm7,%xmm6
+	vmovdqu		%xmm6,0x40(%rsi)
+
+	vmovdqa		%xmm1,%xmm7
+	cmp		$0x60,%rax
+	jl		.Lxorpart2
+	vpxor		0x50(%rdx),%xmm7,%xmm6
+	vmovdqu		%xmm6,0x50(%rsi)
+
+	vmovdqa		%xmm2,%xmm7
+	cmp		$0x70,%rax
+	jl		.Lxorpart2
+	vpxor		0x60(%rdx),%xmm7,%xmm6
+	vmovdqu		%xmm6,0x60(%rsi)
+
+	vmovdqa		%xmm3,%xmm7
+	cmp		$0x80,%rax
+	jl		.Lxorpart2
+	vpxor		0x70(%rdx),%xmm7,%xmm6
+	vmovdqu		%xmm6,0x70(%rsi)
+
+.Ldone2:
+	vzeroupper
+	ret
+
+.Lxorpart2:
+	# xor remaining bytes from partial register into output
+	mov		%rax,%r9
+	and		$0x0f,%r9
+	jz		.Ldone2
+	and		$~0x0f,%rax
+
+	mov		%rsi,%r11
+
+	lea		8(%rsp),%r10
+	sub		$0x10,%rsp
+	and		$~31,%rsp
+
+	lea		(%rdx,%rax),%rsi
+	mov		%rsp,%rdi
+	mov		%r9,%rcx
+	rep movsb
+
+	vpxor		0x00(%rsp),%xmm7,%xmm7
+	vmovdqa		%xmm7,0x00(%rsp)
+
+	mov		%rsp,%rsi
+	lea		(%r11,%rax),%rdi
+	mov		%r9,%rcx
+	rep movsb
+
+	lea		-8(%r10),%rsp
+	jmp		.Ldone2
+
+ENDPROC(chacha_2block_xor_avx2)
+
+ENTRY(chacha_4block_xor_avx2)
+	# %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
+
+	vmovdqa		ROT8(%rip),%ymm8
+	vmovdqa		ROT16(%rip),%ymm9
+
+	mov		%rcx,%rax
+
+.Ldoubleround4:
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	vpaddd		%ymm1,%ymm0,%ymm0
+	vpxor		%ymm0,%ymm3,%ymm3
+	vpshufb		%ymm9,%ymm3,%ymm3
+
+	vpaddd		%ymm5,%ymm4,%ymm4
+	vpxor		%ymm4,%ymm7,%ymm7
+	vpshufb		%ymm9,%ymm7,%ymm7
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	vpaddd		%ymm3,%ymm2,%ymm2
+	vpxor		%ymm2,%ymm1,%ymm1
+	vmovdqa		%ymm1,%ymm10
+	vpslld		$12,%ymm10,%ymm10
+	vpsrld		$20,%ymm1,%ymm1
+	vpor		%ymm10,%ymm1,%ymm1
+
+	vpaddd		%ymm7,%ymm6,%ymm6
+	vpxor		%ymm6,%ymm5,%ymm5
+	vmovdqa		%ymm5,%ymm10
+	vpslld		$12,%ymm10,%ymm10
+	vpsrld		$20,%ymm5,%ymm5
+	vpor		%ymm10,%ymm5,%ymm5
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	vpaddd		%ymm1,%ymm0,%ymm0
+	vpxor		%ymm0,%ymm3,%ymm3
+	vpshufb		%ymm8,%ymm3,%ymm3
+
+	vpaddd		%ymm5,%ymm4,%ymm4
+	vpxor		%ymm4,%ymm7,%ymm7
+	vpshufb		%ymm8,%ymm7,%ymm7
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	vpaddd		%ymm3,%ymm2,%ymm2
+	vpxor		%ymm2,%ymm1,%ymm1
+	vmovdqa		%ymm1,%ymm10
+	vpslld		$7,%ymm10,%ymm10
+	vpsrld		$25,%ymm1,%ymm1
+	vpor		%ymm10,%ymm1,%ymm1
+
+	vpaddd		%ymm7,%ymm6,%ymm6
+	vpxor		%ymm6,%ymm5,%ymm5
+	vmovdqa		%ymm5,%ymm10
+	vpslld		$7,%ymm10,%ymm10
+	vpsrld		$25,%ymm5,%ymm5
+	vpor		%ymm10,%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
+	vpxor		%ymm0,%ymm3,%ymm3
+	vpshufb		%ymm9,%ymm3,%ymm3
+
+	vpaddd		%ymm5,%ymm4,%ymm4
+	vpxor		%ymm4,%ymm7,%ymm7
+	vpshufb		%ymm9,%ymm7,%ymm7
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	vpaddd		%ymm3,%ymm2,%ymm2
+	vpxor		%ymm2,%ymm1,%ymm1
+	vmovdqa		%ymm1,%ymm10
+	vpslld		$12,%ymm10,%ymm10
+	vpsrld		$20,%ymm1,%ymm1
+	vpor		%ymm10,%ymm1,%ymm1
+
+	vpaddd		%ymm7,%ymm6,%ymm6
+	vpxor		%ymm6,%ymm5,%ymm5
+	vmovdqa		%ymm5,%ymm10
+	vpslld		$12,%ymm10,%ymm10
+	vpsrld		$20,%ymm5,%ymm5
+	vpor		%ymm10,%ymm5,%ymm5
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	vpaddd		%ymm1,%ymm0,%ymm0
+	vpxor		%ymm0,%ymm3,%ymm3
+	vpshufb		%ymm8,%ymm3,%ymm3
+
+	vpaddd		%ymm5,%ymm4,%ymm4
+	vpxor		%ymm4,%ymm7,%ymm7
+	vpshufb		%ymm8,%ymm7,%ymm7
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	vpaddd		%ymm3,%ymm2,%ymm2
+	vpxor		%ymm2,%ymm1,%ymm1
+	vmovdqa		%ymm1,%ymm10
+	vpslld		$7,%ymm10,%ymm10
+	vpsrld		$25,%ymm1,%ymm1
+	vpor		%ymm10,%ymm1,%ymm1
+
+	vpaddd		%ymm7,%ymm6,%ymm6
+	vpxor		%ymm6,%ymm5,%ymm5
+	vmovdqa		%ymm5,%ymm10
+	vpslld		$7,%ymm10,%ymm10
+	vpsrld		$25,%ymm5,%ymm5
+	vpor		%ymm10,%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,%rax
+	jl		.Lxorpart4
+	vpxor		0x00(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0x00(%rsi)
+	vextracti128	$1,%ymm10,%xmm0
+	# o1 = i1 ^ (x1 + s1), first block
+	vpaddd		%ymm12,%ymm1,%ymm10
+	cmp		$0x20,%rax
+	jl		.Lxorpart4
+	vpxor		0x10(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0x10(%rsi)
+	vextracti128	$1,%ymm10,%xmm1
+	# o2 = i2 ^ (x2 + s2), first block
+	vpaddd		%ymm13,%ymm2,%ymm10
+	cmp		$0x30,%rax
+	jl		.Lxorpart4
+	vpxor		0x20(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0x20(%rsi)
+	vextracti128	$1,%ymm10,%xmm2
+	# o3 = i3 ^ (x3 + s3), first block
+	vpaddd		%ymm14,%ymm3,%ymm10
+	cmp		$0x40,%rax
+	jl		.Lxorpart4
+	vpxor		0x30(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0x30(%rsi)
+	vextracti128	$1,%ymm10,%xmm3
+
+	# xor and write second block
+	vmovdqa		%xmm0,%xmm10
+	cmp		$0x50,%rax
+	jl		.Lxorpart4
+	vpxor		0x40(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0x40(%rsi)
+
+	vmovdqa		%xmm1,%xmm10
+	cmp		$0x60,%rax
+	jl		.Lxorpart4
+	vpxor		0x50(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0x50(%rsi)
+
+	vmovdqa		%xmm2,%xmm10
+	cmp		$0x70,%rax
+	jl		.Lxorpart4
+	vpxor		0x60(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0x60(%rsi)
+
+	vmovdqa		%xmm3,%xmm10
+	cmp		$0x80,%rax
+	jl		.Lxorpart4
+	vpxor		0x70(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0x70(%rsi)
+
+	# o0 = i0 ^ (x0 + s0), third block
+	vpaddd		%ymm11,%ymm4,%ymm10
+	cmp		$0x90,%rax
+	jl		.Lxorpart4
+	vpxor		0x80(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0x80(%rsi)
+	vextracti128	$1,%ymm10,%xmm4
+	# o1 = i1 ^ (x1 + s1), third block
+	vpaddd		%ymm12,%ymm5,%ymm10
+	cmp		$0xa0,%rax
+	jl		.Lxorpart4
+	vpxor		0x90(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0x90(%rsi)
+	vextracti128	$1,%ymm10,%xmm5
+	# o2 = i2 ^ (x2 + s2), third block
+	vpaddd		%ymm13,%ymm6,%ymm10
+	cmp		$0xb0,%rax
+	jl		.Lxorpart4
+	vpxor		0xa0(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0xa0(%rsi)
+	vextracti128	$1,%ymm10,%xmm6
+	# o3 = i3 ^ (x3 + s3), third block
+	vpaddd		%ymm15,%ymm7,%ymm10
+	cmp		$0xc0,%rax
+	jl		.Lxorpart4
+	vpxor		0xb0(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0xb0(%rsi)
+	vextracti128	$1,%ymm10,%xmm7
+
+	# xor and write fourth block
+	vmovdqa		%xmm4,%xmm10
+	cmp		$0xd0,%rax
+	jl		.Lxorpart4
+	vpxor		0xc0(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0xc0(%rsi)
+
+	vmovdqa		%xmm5,%xmm10
+	cmp		$0xe0,%rax
+	jl		.Lxorpart4
+	vpxor		0xd0(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0xd0(%rsi)
+
+	vmovdqa		%xmm6,%xmm10
+	cmp		$0xf0,%rax
+	jl		.Lxorpart4
+	vpxor		0xe0(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0xe0(%rsi)
+
+	vmovdqa		%xmm7,%xmm10
+	cmp		$0x100,%rax
+	jl		.Lxorpart4
+	vpxor		0xf0(%rdx),%xmm10,%xmm9
+	vmovdqu		%xmm9,0xf0(%rsi)
+
+.Ldone4:
+	vzeroupper
+	ret
+
+.Lxorpart4:
+	# xor remaining bytes from partial register into output
+	mov		%rax,%r9
+	and		$0x0f,%r9
+	jz		.Ldone4
+	and		$~0x0f,%rax
+
+	mov		%rsi,%r11
+
+	lea		8(%rsp),%r10
+	sub		$0x10,%rsp
+	and		$~31,%rsp
+
+	lea		(%rdx,%rax),%rsi
+	mov		%rsp,%rdi
+	mov		%r9,%rcx
+	rep movsb
+
+	vpxor		0x00(%rsp),%xmm10,%xmm10
+	vmovdqa		%xmm10,0x00(%rsp)
+
+	mov		%rsp,%rsi
+	lea		(%r11,%rax),%rdi
+	mov		%r9,%rcx
+	rep movsb
+
+	lea		-8(%r10),%rsp
+	jmp		.Ldone4
+
+ENDPROC(chacha_4block_xor_avx2)
+
+ENTRY(chacha_8block_xor_avx2)
+	# %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. As we need some
+	# scratch registers, we save the first four registers on the stack. The
+	# algorithm performs each operation on the corresponding word of each
+	# state matrix, hence requires no word shuffling. For final XORing step
+	# we transpose the matrix by interleaving 32-, 64- and then 128-bit
+	# words, which allows us to do XOR in AVX registers. 8/16-bit word
+	# rotation is done with the slightly better performing byte shuffling,
+	# 7/12-bit word rotation uses traditional shift+OR.
+
+	vzeroupper
+	# 4 * 32 byte stack, 32-byte aligned
+	lea		8(%rsp),%r10
+	and		$~31, %rsp
+	sub		$0x80, %rsp
+	mov		%rcx,%rax
+
+	# 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
+	# x0..3 on stack
+	vmovdqa		%ymm0,0x00(%rsp)
+	vmovdqa		%ymm1,0x20(%rsp)
+	vmovdqa		%ymm2,0x40(%rsp)
+	vmovdqa		%ymm3,0x60(%rsp)
+
+	vmovdqa		CTRINC(%rip),%ymm1
+	vmovdqa		ROT8(%rip),%ymm2
+	vmovdqa		ROT16(%rip),%ymm3
+
+	# x12 += counter values 0-3
+	vpaddd		%ymm1,%ymm12,%ymm12
+
+.Ldoubleround8:
+	# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
+	vpaddd		0x00(%rsp),%ymm4,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+	vpxor		%ymm0,%ymm12,%ymm12
+	vpshufb		%ymm3,%ymm12,%ymm12
+	# x1 += x5, x13 = rotl32(x13 ^ x1, 16)
+	vpaddd		0x20(%rsp),%ymm5,%ymm0
+	vmovdqa		%ymm0,0x20(%rsp)
+	vpxor		%ymm0,%ymm13,%ymm13
+	vpshufb		%ymm3,%ymm13,%ymm13
+	# x2 += x6, x14 = rotl32(x14 ^ x2, 16)
+	vpaddd		0x40(%rsp),%ymm6,%ymm0
+	vmovdqa		%ymm0,0x40(%rsp)
+	vpxor		%ymm0,%ymm14,%ymm14
+	vpshufb		%ymm3,%ymm14,%ymm14
+	# x3 += x7, x15 = rotl32(x15 ^ x3, 16)
+	vpaddd		0x60(%rsp),%ymm7,%ymm0
+	vmovdqa		%ymm0,0x60(%rsp)
+	vpxor		%ymm0,%ymm15,%ymm15
+	vpshufb		%ymm3,%ymm15,%ymm15
+
+	# x8 += x12, x4 = rotl32(x4 ^ x8, 12)
+	vpaddd		%ymm12,%ymm8,%ymm8
+	vpxor		%ymm8,%ymm4,%ymm4
+	vpslld		$12,%ymm4,%ymm0
+	vpsrld		$20,%ymm4,%ymm4
+	vpor		%ymm0,%ymm4,%ymm4
+	# x9 += x13, x5 = rotl32(x5 ^ x9, 12)
+	vpaddd		%ymm13,%ymm9,%ymm9
+	vpxor		%ymm9,%ymm5,%ymm5
+	vpslld		$12,%ymm5,%ymm0
+	vpsrld		$20,%ymm5,%ymm5
+	vpor		%ymm0,%ymm5,%ymm5
+	# x10 += x14, x6 = rotl32(x6 ^ x10, 12)
+	vpaddd		%ymm14,%ymm10,%ymm10
+	vpxor		%ymm10,%ymm6,%ymm6
+	vpslld		$12,%ymm6,%ymm0
+	vpsrld		$20,%ymm6,%ymm6
+	vpor		%ymm0,%ymm6,%ymm6
+	# x11 += x15, x7 = rotl32(x7 ^ x11, 12)
+	vpaddd		%ymm15,%ymm11,%ymm11
+	vpxor		%ymm11,%ymm7,%ymm7
+	vpslld		$12,%ymm7,%ymm0
+	vpsrld		$20,%ymm7,%ymm7
+	vpor		%ymm0,%ymm7,%ymm7
+
+	# x0 += x4, x12 = rotl32(x12 ^ x0, 8)
+	vpaddd		0x00(%rsp),%ymm4,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+	vpxor		%ymm0,%ymm12,%ymm12
+	vpshufb		%ymm2,%ymm12,%ymm12
+	# x1 += x5, x13 = rotl32(x13 ^ x1, 8)
+	vpaddd		0x20(%rsp),%ymm5,%ymm0
+	vmovdqa		%ymm0,0x20(%rsp)
+	vpxor		%ymm0,%ymm13,%ymm13
+	vpshufb		%ymm2,%ymm13,%ymm13
+	# x2 += x6, x14 = rotl32(x14 ^ x2, 8)
+	vpaddd		0x40(%rsp),%ymm6,%ymm0
+	vmovdqa		%ymm0,0x40(%rsp)
+	vpxor		%ymm0,%ymm14,%ymm14
+	vpshufb		%ymm2,%ymm14,%ymm14
+	# x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+	vpaddd		0x60(%rsp),%ymm7,%ymm0
+	vmovdqa		%ymm0,0x60(%rsp)
+	vpxor		%ymm0,%ymm15,%ymm15
+	vpshufb		%ymm2,%ymm15,%ymm15
+
+	# x8 += x12, x4 = rotl32(x4 ^ x8, 7)
+	vpaddd		%ymm12,%ymm8,%ymm8
+	vpxor		%ymm8,%ymm4,%ymm4
+	vpslld		$7,%ymm4,%ymm0
+	vpsrld		$25,%ymm4,%ymm4
+	vpor		%ymm0,%ymm4,%ymm4
+	# x9 += x13, x5 = rotl32(x5 ^ x9, 7)
+	vpaddd		%ymm13,%ymm9,%ymm9
+	vpxor		%ymm9,%ymm5,%ymm5
+	vpslld		$7,%ymm5,%ymm0
+	vpsrld		$25,%ymm5,%ymm5
+	vpor		%ymm0,%ymm5,%ymm5
+	# x10 += x14, x6 = rotl32(x6 ^ x10, 7)
+	vpaddd		%ymm14,%ymm10,%ymm10
+	vpxor		%ymm10,%ymm6,%ymm6
+	vpslld		$7,%ymm6,%ymm0
+	vpsrld		$25,%ymm6,%ymm6
+	vpor		%ymm0,%ymm6,%ymm6
+	# x11 += x15, x7 = rotl32(x7 ^ x11, 7)
+	vpaddd		%ymm15,%ymm11,%ymm11
+	vpxor		%ymm11,%ymm7,%ymm7
+	vpslld		$7,%ymm7,%ymm0
+	vpsrld		$25,%ymm7,%ymm7
+	vpor		%ymm0,%ymm7,%ymm7
+
+	# x0 += x5, x15 = rotl32(x15 ^ x0, 16)
+	vpaddd		0x00(%rsp),%ymm5,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+	vpxor		%ymm0,%ymm15,%ymm15
+	vpshufb		%ymm3,%ymm15,%ymm15
+	# x1 += x6, x12 = rotl32(x12 ^ x1, 16)%ymm0
+	vpaddd		0x20(%rsp),%ymm6,%ymm0
+	vmovdqa		%ymm0,0x20(%rsp)
+	vpxor		%ymm0,%ymm12,%ymm12
+	vpshufb		%ymm3,%ymm12,%ymm12
+	# x2 += x7, x13 = rotl32(x13 ^ x2, 16)
+	vpaddd		0x40(%rsp),%ymm7,%ymm0
+	vmovdqa		%ymm0,0x40(%rsp)
+	vpxor		%ymm0,%ymm13,%ymm13
+	vpshufb		%ymm3,%ymm13,%ymm13
+	# x3 += x4, x14 = rotl32(x14 ^ x3, 16)
+	vpaddd		0x60(%rsp),%ymm4,%ymm0
+	vmovdqa		%ymm0,0x60(%rsp)
+	vpxor		%ymm0,%ymm14,%ymm14
+	vpshufb		%ymm3,%ymm14,%ymm14
+
+	# x10 += x15, x5 = rotl32(x5 ^ x10, 12)
+	vpaddd		%ymm15,%ymm10,%ymm10
+	vpxor		%ymm10,%ymm5,%ymm5
+	vpslld		$12,%ymm5,%ymm0
+	vpsrld		$20,%ymm5,%ymm5
+	vpor		%ymm0,%ymm5,%ymm5
+	# x11 += x12, x6 = rotl32(x6 ^ x11, 12)
+	vpaddd		%ymm12,%ymm11,%ymm11
+	vpxor		%ymm11,%ymm6,%ymm6
+	vpslld		$12,%ymm6,%ymm0
+	vpsrld		$20,%ymm6,%ymm6
+	vpor		%ymm0,%ymm6,%ymm6
+	# x8 += x13, x7 = rotl32(x7 ^ x8, 12)
+	vpaddd		%ymm13,%ymm8,%ymm8
+	vpxor		%ymm8,%ymm7,%ymm7
+	vpslld		$12,%ymm7,%ymm0
+	vpsrld		$20,%ymm7,%ymm7
+	vpor		%ymm0,%ymm7,%ymm7
+	# x9 += x14, x4 = rotl32(x4 ^ x9, 12)
+	vpaddd		%ymm14,%ymm9,%ymm9
+	vpxor		%ymm9,%ymm4,%ymm4
+	vpslld		$12,%ymm4,%ymm0
+	vpsrld		$20,%ymm4,%ymm4
+	vpor		%ymm0,%ymm4,%ymm4
+
+	# x0 += x5, x15 = rotl32(x15 ^ x0, 8)
+	vpaddd		0x00(%rsp),%ymm5,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+	vpxor		%ymm0,%ymm15,%ymm15
+	vpshufb		%ymm2,%ymm15,%ymm15
+	# x1 += x6, x12 = rotl32(x12 ^ x1, 8)
+	vpaddd		0x20(%rsp),%ymm6,%ymm0
+	vmovdqa		%ymm0,0x20(%rsp)
+	vpxor		%ymm0,%ymm12,%ymm12
+	vpshufb		%ymm2,%ymm12,%ymm12
+	# x2 += x7, x13 = rotl32(x13 ^ x2, 8)
+	vpaddd		0x40(%rsp),%ymm7,%ymm0
+	vmovdqa		%ymm0,0x40(%rsp)
+	vpxor		%ymm0,%ymm13,%ymm13
+	vpshufb		%ymm2,%ymm13,%ymm13
+	# x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+	vpaddd		0x60(%rsp),%ymm4,%ymm0
+	vmovdqa		%ymm0,0x60(%rsp)
+	vpxor		%ymm0,%ymm14,%ymm14
+	vpshufb		%ymm2,%ymm14,%ymm14
+
+	# x10 += x15, x5 = rotl32(x5 ^ x10, 7)
+	vpaddd		%ymm15,%ymm10,%ymm10
+	vpxor		%ymm10,%ymm5,%ymm5
+	vpslld		$7,%ymm5,%ymm0
+	vpsrld		$25,%ymm5,%ymm5
+	vpor		%ymm0,%ymm5,%ymm5
+	# x11 += x12, x6 = rotl32(x6 ^ x11, 7)
+	vpaddd		%ymm12,%ymm11,%ymm11
+	vpxor		%ymm11,%ymm6,%ymm6
+	vpslld		$7,%ymm6,%ymm0
+	vpsrld		$25,%ymm6,%ymm6
+	vpor		%ymm0,%ymm6,%ymm6
+	# x8 += x13, x7 = rotl32(x7 ^ x8, 7)
+	vpaddd		%ymm13,%ymm8,%ymm8
+	vpxor		%ymm8,%ymm7,%ymm7
+	vpslld		$7,%ymm7,%ymm0
+	vpsrld		$25,%ymm7,%ymm7
+	vpor		%ymm0,%ymm7,%ymm7
+	# x9 += x14, x4 = rotl32(x4 ^ x9, 7)
+	vpaddd		%ymm14,%ymm9,%ymm9
+	vpxor		%ymm9,%ymm4,%ymm4
+	vpslld		$7,%ymm4,%ymm0
+	vpsrld		$25,%ymm4,%ymm4
+	vpor		%ymm0,%ymm4,%ymm4
+
+	sub		$2,%r8d
+	jnz		.Ldoubleround8
+
+	# x0..15[0-3] += s[0..15]
+	vpbroadcastd	0x00(%rdi),%ymm0
+	vpaddd		0x00(%rsp),%ymm0,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+	vpbroadcastd	0x04(%rdi),%ymm0
+	vpaddd		0x20(%rsp),%ymm0,%ymm0
+	vmovdqa		%ymm0,0x20(%rsp)
+	vpbroadcastd	0x08(%rdi),%ymm0
+	vpaddd		0x40(%rsp),%ymm0,%ymm0
+	vmovdqa		%ymm0,0x40(%rsp)
+	vpbroadcastd	0x0c(%rdi),%ymm0
+	vpaddd		0x60(%rsp),%ymm0,%ymm0
+	vmovdqa		%ymm0,0x60(%rsp)
+	vpbroadcastd	0x10(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm4,%ymm4
+	vpbroadcastd	0x14(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm5,%ymm5
+	vpbroadcastd	0x18(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm6,%ymm6
+	vpbroadcastd	0x1c(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm7,%ymm7
+	vpbroadcastd	0x20(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm8,%ymm8
+	vpbroadcastd	0x24(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm9,%ymm9
+	vpbroadcastd	0x28(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm10,%ymm10
+	vpbroadcastd	0x2c(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm11,%ymm11
+	vpbroadcastd	0x30(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm12,%ymm12
+	vpbroadcastd	0x34(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm13,%ymm13
+	vpbroadcastd	0x38(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm14,%ymm14
+	vpbroadcastd	0x3c(%rdi),%ymm0
+	vpaddd		%ymm0,%ymm15,%ymm15
+
+	# x12 += counter values 0-3
+	vpaddd		%ymm1,%ymm12,%ymm12
+
+	# interleave 32-bit words in state n, n+1
+	vmovdqa		0x00(%rsp),%ymm0
+	vmovdqa		0x20(%rsp),%ymm1
+	vpunpckldq	%ymm1,%ymm0,%ymm2
+	vpunpckhdq	%ymm1,%ymm0,%ymm1
+	vmovdqa		%ymm2,0x00(%rsp)
+	vmovdqa		%ymm1,0x20(%rsp)
+	vmovdqa		0x40(%rsp),%ymm0
+	vmovdqa		0x60(%rsp),%ymm1
+	vpunpckldq	%ymm1,%ymm0,%ymm2
+	vpunpckhdq	%ymm1,%ymm0,%ymm1
+	vmovdqa		%ymm2,0x40(%rsp)
+	vmovdqa		%ymm1,0x60(%rsp)
+	vmovdqa		%ymm4,%ymm0
+	vpunpckldq	%ymm5,%ymm0,%ymm4
+	vpunpckhdq	%ymm5,%ymm0,%ymm5
+	vmovdqa		%ymm6,%ymm0
+	vpunpckldq	%ymm7,%ymm0,%ymm6
+	vpunpckhdq	%ymm7,%ymm0,%ymm7
+	vmovdqa		%ymm8,%ymm0
+	vpunpckldq	%ymm9,%ymm0,%ymm8
+	vpunpckhdq	%ymm9,%ymm0,%ymm9
+	vmovdqa		%ymm10,%ymm0
+	vpunpckldq	%ymm11,%ymm0,%ymm10
+	vpunpckhdq	%ymm11,%ymm0,%ymm11
+	vmovdqa		%ymm12,%ymm0
+	vpunpckldq	%ymm13,%ymm0,%ymm12
+	vpunpckhdq	%ymm13,%ymm0,%ymm13
+	vmovdqa		%ymm14,%ymm0
+	vpunpckldq	%ymm15,%ymm0,%ymm14
+	vpunpckhdq	%ymm15,%ymm0,%ymm15
+
+	# interleave 64-bit words in state n, n+2
+	vmovdqa		0x00(%rsp),%ymm0
+	vmovdqa		0x40(%rsp),%ymm2
+	vpunpcklqdq	%ymm2,%ymm0,%ymm1
+	vpunpckhqdq	%ymm2,%ymm0,%ymm2
+	vmovdqa		%ymm1,0x00(%rsp)
+	vmovdqa		%ymm2,0x40(%rsp)
+	vmovdqa		0x20(%rsp),%ymm0
+	vmovdqa		0x60(%rsp),%ymm2
+	vpunpcklqdq	%ymm2,%ymm0,%ymm1
+	vpunpckhqdq	%ymm2,%ymm0,%ymm2
+	vmovdqa		%ymm1,0x20(%rsp)
+	vmovdqa		%ymm2,0x60(%rsp)
+	vmovdqa		%ymm4,%ymm0
+	vpunpcklqdq	%ymm6,%ymm0,%ymm4
+	vpunpckhqdq	%ymm6,%ymm0,%ymm6
+	vmovdqa		%ymm5,%ymm0
+	vpunpcklqdq	%ymm7,%ymm0,%ymm5
+	vpunpckhqdq	%ymm7,%ymm0,%ymm7
+	vmovdqa		%ymm8,%ymm0
+	vpunpcklqdq	%ymm10,%ymm0,%ymm8
+	vpunpckhqdq	%ymm10,%ymm0,%ymm10
+	vmovdqa		%ymm9,%ymm0
+	vpunpcklqdq	%ymm11,%ymm0,%ymm9
+	vpunpckhqdq	%ymm11,%ymm0,%ymm11
+	vmovdqa		%ymm12,%ymm0
+	vpunpcklqdq	%ymm14,%ymm0,%ymm12
+	vpunpckhqdq	%ymm14,%ymm0,%ymm14
+	vmovdqa		%ymm13,%ymm0
+	vpunpcklqdq	%ymm15,%ymm0,%ymm13
+	vpunpckhqdq	%ymm15,%ymm0,%ymm15
+
+	# interleave 128-bit words in state n, n+4
+	# xor/write first four blocks
+	vmovdqa		0x00(%rsp),%ymm1
+	vperm2i128	$0x20,%ymm4,%ymm1,%ymm0
+	cmp		$0x0020,%rax
+	jl		.Lxorpart8
+	vpxor		0x0000(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0000(%rsi)
+	vperm2i128	$0x31,%ymm4,%ymm1,%ymm4
+
+	vperm2i128	$0x20,%ymm12,%ymm8,%ymm0
+	cmp		$0x0040,%rax
+	jl		.Lxorpart8
+	vpxor		0x0020(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0020(%rsi)
+	vperm2i128	$0x31,%ymm12,%ymm8,%ymm12
+
+	vmovdqa		0x40(%rsp),%ymm1
+	vperm2i128	$0x20,%ymm6,%ymm1,%ymm0
+	cmp		$0x0060,%rax
+	jl		.Lxorpart8
+	vpxor		0x0040(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0040(%rsi)
+	vperm2i128	$0x31,%ymm6,%ymm1,%ymm6
+
+	vperm2i128	$0x20,%ymm14,%ymm10,%ymm0
+	cmp		$0x0080,%rax
+	jl		.Lxorpart8
+	vpxor		0x0060(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0060(%rsi)
+	vperm2i128	$0x31,%ymm14,%ymm10,%ymm14
+
+	vmovdqa		0x20(%rsp),%ymm1
+	vperm2i128	$0x20,%ymm5,%ymm1,%ymm0
+	cmp		$0x00a0,%rax
+	jl		.Lxorpart8
+	vpxor		0x0080(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0080(%rsi)
+	vperm2i128	$0x31,%ymm5,%ymm1,%ymm5
+
+	vperm2i128	$0x20,%ymm13,%ymm9,%ymm0
+	cmp		$0x00c0,%rax
+	jl		.Lxorpart8
+	vpxor		0x00a0(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x00a0(%rsi)
+	vperm2i128	$0x31,%ymm13,%ymm9,%ymm13
+
+	vmovdqa		0x60(%rsp),%ymm1
+	vperm2i128	$0x20,%ymm7,%ymm1,%ymm0
+	cmp		$0x00e0,%rax
+	jl		.Lxorpart8
+	vpxor		0x00c0(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x00c0(%rsi)
+	vperm2i128	$0x31,%ymm7,%ymm1,%ymm7
+
+	vperm2i128	$0x20,%ymm15,%ymm11,%ymm0
+	cmp		$0x0100,%rax
+	jl		.Lxorpart8
+	vpxor		0x00e0(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x00e0(%rsi)
+	vperm2i128	$0x31,%ymm15,%ymm11,%ymm15
+
+	# xor remaining blocks, write to output
+	vmovdqa		%ymm4,%ymm0
+	cmp		$0x0120,%rax
+	jl		.Lxorpart8
+	vpxor		0x0100(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0100(%rsi)
+
+	vmovdqa		%ymm12,%ymm0
+	cmp		$0x0140,%rax
+	jl		.Lxorpart8
+	vpxor		0x0120(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0120(%rsi)
+
+	vmovdqa		%ymm6,%ymm0
+	cmp		$0x0160,%rax
+	jl		.Lxorpart8
+	vpxor		0x0140(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0140(%rsi)
+
+	vmovdqa		%ymm14,%ymm0
+	cmp		$0x0180,%rax
+	jl		.Lxorpart8
+	vpxor		0x0160(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0160(%rsi)
+
+	vmovdqa		%ymm5,%ymm0
+	cmp		$0x01a0,%rax
+	jl		.Lxorpart8
+	vpxor		0x0180(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0180(%rsi)
+
+	vmovdqa		%ymm13,%ymm0
+	cmp		$0x01c0,%rax
+	jl		.Lxorpart8
+	vpxor		0x01a0(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x01a0(%rsi)
+
+	vmovdqa		%ymm7,%ymm0
+	cmp		$0x01e0,%rax
+	jl		.Lxorpart8
+	vpxor		0x01c0(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x01c0(%rsi)
+
+	vmovdqa		%ymm15,%ymm0
+	cmp		$0x0200,%rax
+	jl		.Lxorpart8
+	vpxor		0x01e0(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x01e0(%rsi)
+
+.Ldone8:
+	vzeroupper
+	lea		-8(%r10),%rsp
+	ret
+
+.Lxorpart8:
+	# xor remaining bytes from partial register into output
+	mov		%rax,%r9
+	and		$0x1f,%r9
+	jz		.Ldone8
+	and		$~0x1f,%rax
+
+	mov		%rsi,%r11
+
+	lea		(%rdx,%rax),%rsi
+	mov		%rsp,%rdi
+	mov		%r9,%rcx
+	rep movsb
+
+	vpxor		0x00(%rsp),%ymm0,%ymm0
+	vmovdqa		%ymm0,0x00(%rsp)
+
+	mov		%rsp,%rsi
+	lea		(%r11,%rax),%rdi
+	mov		%r9,%rcx
+	rep movsb
+
+	jmp		.Ldone8
+
+ENDPROC(chacha_8block_xor_avx2)
diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/crypto/chacha-avx512vl-x86_64.S
new file mode 100644
index 000000000000..848f9c75fd4f
--- /dev/null
+++ b/arch/x86/crypto/chacha-avx512vl-x86_64.S
@@ -0,0 +1,836 @@
+/* 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		.Ldone8
+	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		.Ldone8
+	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)
diff --git a/arch/x86/crypto/chacha-ssse3-x86_64.S b/arch/x86/crypto/chacha-ssse3-x86_64.S
new file mode 100644
index 000000000000..c05a7a963dc3
--- /dev/null
+++ b/arch/x86/crypto/chacha-ssse3-x86_64.S
@@ -0,0 +1,795 @@
+/*
+ * ChaCha 256-bit cipher algorithm, x64 SSSE3 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+.section	.rodata.cst16.ROT8, "aM", @progbits, 16
+.align 16
+ROT8:	.octa 0x0e0d0c0f0a09080b0605040702010003
+.section	.rodata.cst16.ROT16, "aM", @progbits, 16
+.align 16
+ROT16:	.octa 0x0d0c0f0e09080b0a0504070601000302
+.section	.rodata.cst16.CTRINC, "aM", @progbits, 16
+.align 16
+CTRINC:	.octa 0x00000003000000020000000100000000
+
+.text
+
+/*
+ * chacha_permute - permute one block
+ *
+ * Permute one 64-byte block where the state matrix is in %xmm0-%xmm3.  This
+ * function performs matrix operations on four words in parallel, but requires
+ * shuffling to rearrange the words after each round.  8/16-bit word rotation is
+ * done with the slightly better performing SSSE3 byte shuffling, 7/12-bit word
+ * rotation uses traditional shift+OR.
+ *
+ * The round count is given in %r8d.
+ *
+ * Clobbers: %r8d, %xmm4-%xmm7
+ */
+chacha_permute:
+
+	movdqa		ROT8(%rip),%xmm4
+	movdqa		ROT16(%rip),%xmm5
+
+.Ldoubleround:
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm5,%xmm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm6
+	pslld		$12,%xmm6
+	psrld		$20,%xmm1
+	por		%xmm6,%xmm1
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm4,%xmm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm7
+	pslld		$7,%xmm7
+	psrld		$25,%xmm1
+	por		%xmm7,%xmm1
+
+	# x1 = shuffle32(x1, MASK(0, 3, 2, 1))
+	pshufd		$0x39,%xmm1,%xmm1
+	# x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	pshufd		$0x4e,%xmm2,%xmm2
+	# x3 = shuffle32(x3, MASK(2, 1, 0, 3))
+	pshufd		$0x93,%xmm3,%xmm3
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm5,%xmm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm6
+	pslld		$12,%xmm6
+	psrld		$20,%xmm1
+	por		%xmm6,%xmm1
+
+	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	paddd		%xmm1,%xmm0
+	pxor		%xmm0,%xmm3
+	pshufb		%xmm4,%xmm3
+
+	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	paddd		%xmm3,%xmm2
+	pxor		%xmm2,%xmm1
+	movdqa		%xmm1,%xmm7
+	pslld		$7,%xmm7
+	psrld		$25,%xmm1
+	por		%xmm7,%xmm1
+
+	# x1 = shuffle32(x1, MASK(2, 1, 0, 3))
+	pshufd		$0x93,%xmm1,%xmm1
+	# x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	pshufd		$0x4e,%xmm2,%xmm2
+	# x3 = shuffle32(x3, MASK(0, 3, 2, 1))
+	pshufd		$0x39,%xmm3,%xmm3
+
+	sub		$2,%r8d
+	jnz		.Ldoubleround
+
+	ret
+ENDPROC(chacha_permute)
+
+ENTRY(chacha_block_xor_ssse3)
+	# %rdi: Input state matrix, s
+	# %rsi: up to 1 data block output, o
+	# %rdx: up to 1 data block input, i
+	# %rcx: input/output length in bytes
+	# %r8d: nrounds
+	FRAME_BEGIN
+
+	# x0..3 = s0..3
+	movdqa		0x00(%rdi),%xmm0
+	movdqa		0x10(%rdi),%xmm1
+	movdqa		0x20(%rdi),%xmm2
+	movdqa		0x30(%rdi),%xmm3
+	movdqa		%xmm0,%xmm8
+	movdqa		%xmm1,%xmm9
+	movdqa		%xmm2,%xmm10
+	movdqa		%xmm3,%xmm11
+
+	mov		%rcx,%rax
+	call		chacha_permute
+
+	# o0 = i0 ^ (x0 + s0)
+	paddd		%xmm8,%xmm0
+	cmp		$0x10,%rax
+	jl		.Lxorpart
+	movdqu		0x00(%rdx),%xmm4
+	pxor		%xmm4,%xmm0
+	movdqu		%xmm0,0x00(%rsi)
+	# o1 = i1 ^ (x1 + s1)
+	paddd		%xmm9,%xmm1
+	movdqa		%xmm1,%xmm0
+	cmp		$0x20,%rax
+	jl		.Lxorpart
+	movdqu		0x10(%rdx),%xmm0
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x10(%rsi)
+	# o2 = i2 ^ (x2 + s2)
+	paddd		%xmm10,%xmm2
+	movdqa		%xmm2,%xmm0
+	cmp		$0x30,%rax
+	jl		.Lxorpart
+	movdqu		0x20(%rdx),%xmm0
+	pxor		%xmm2,%xmm0
+	movdqu		%xmm0,0x20(%rsi)
+	# o3 = i3 ^ (x3 + s3)
+	paddd		%xmm11,%xmm3
+	movdqa		%xmm3,%xmm0
+	cmp		$0x40,%rax
+	jl		.Lxorpart
+	movdqu		0x30(%rdx),%xmm0
+	pxor		%xmm3,%xmm0
+	movdqu		%xmm0,0x30(%rsi)
+
+.Ldone:
+	FRAME_END
+	ret
+
+.Lxorpart:
+	# xor remaining bytes from partial register into output
+	mov		%rax,%r9
+	and		$0x0f,%r9
+	jz		.Ldone
+	and		$~0x0f,%rax
+
+	mov		%rsi,%r11
+
+	lea		8(%rsp),%r10
+	sub		$0x10,%rsp
+	and		$~31,%rsp
+
+	lea		(%rdx,%rax),%rsi
+	mov		%rsp,%rdi
+	mov		%r9,%rcx
+	rep movsb
+
+	pxor		0x00(%rsp),%xmm0
+	movdqa		%xmm0,0x00(%rsp)
+
+	mov		%rsp,%rsi
+	lea		(%r11,%rax),%rdi
+	mov		%r9,%rcx
+	rep movsb
+
+	lea		-8(%r10),%rsp
+	jmp		.Ldone
+
+ENDPROC(chacha_block_xor_ssse3)
+
+ENTRY(hchacha_block_ssse3)
+	# %rdi: Input state matrix, s
+	# %rsi: output (8 32-bit words)
+	# %edx: nrounds
+	FRAME_BEGIN
+
+	movdqa		0x00(%rdi),%xmm0
+	movdqa		0x10(%rdi),%xmm1
+	movdqa		0x20(%rdi),%xmm2
+	movdqa		0x30(%rdi),%xmm3
+
+	mov		%edx,%r8d
+	call		chacha_permute
+
+	movdqu		%xmm0,0x00(%rsi)
+	movdqu		%xmm3,0x10(%rsi)
+
+	FRAME_END
+	ret
+ENDPROC(hchacha_block_ssse3)
+
+ENTRY(chacha_4block_xor_ssse3)
+	# %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 consecutive ChaCha blocks by loading the
+	# the state matrix in SSE registers four times. As we need some scratch
+	# registers, we save the first four registers on the stack. The
+	# algorithm performs each operation on the corresponding word of each
+	# state matrix, hence requires no word shuffling. For final XORing step
+	# we transpose the matrix by interleaving 32- and then 64-bit words,
+	# which allows us to do XOR in SSE registers. 8/16-bit word rotation is
+	# done with the slightly better performing SSSE3 byte shuffling,
+	# 7/12-bit word rotation uses traditional shift+OR.
+
+	lea		8(%rsp),%r10
+	sub		$0x80,%rsp
+	and		$~63,%rsp
+	mov		%rcx,%rax
+
+	# x0..15[0-3] = s0..3[0..3]
+	movq		0x00(%rdi),%xmm1
+	pshufd		$0x00,%xmm1,%xmm0
+	pshufd		$0x55,%xmm1,%xmm1
+	movq		0x08(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	movq		0x10(%rdi),%xmm5
+	pshufd		$0x00,%xmm5,%xmm4
+	pshufd		$0x55,%xmm5,%xmm5
+	movq		0x18(%rdi),%xmm7
+	pshufd		$0x00,%xmm7,%xmm6
+	pshufd		$0x55,%xmm7,%xmm7
+	movq		0x20(%rdi),%xmm9
+	pshufd		$0x00,%xmm9,%xmm8
+	pshufd		$0x55,%xmm9,%xmm9
+	movq		0x28(%rdi),%xmm11
+	pshufd		$0x00,%xmm11,%xmm10
+	pshufd		$0x55,%xmm11,%xmm11
+	movq		0x30(%rdi),%xmm13
+	pshufd		$0x00,%xmm13,%xmm12
+	pshufd		$0x55,%xmm13,%xmm13
+	movq		0x38(%rdi),%xmm15
+	pshufd		$0x00,%xmm15,%xmm14
+	pshufd		$0x55,%xmm15,%xmm15
+	# x0..3 on stack
+	movdqa		%xmm0,0x00(%rsp)
+	movdqa		%xmm1,0x10(%rsp)
+	movdqa		%xmm2,0x20(%rsp)
+	movdqa		%xmm3,0x30(%rsp)
+
+	movdqa		CTRINC(%rip),%xmm1
+	movdqa		ROT8(%rip),%xmm2
+	movdqa		ROT16(%rip),%xmm3
+
+	# x12 += counter values 0-3
+	paddd		%xmm1,%xmm12
+
+.Ldoubleround4:
+	# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
+	movdqa		0x00(%rsp),%xmm0
+	paddd		%xmm4,%xmm0
+	movdqa		%xmm0,0x00(%rsp)
+	pxor		%xmm0,%xmm12
+	pshufb		%xmm3,%xmm12
+	# x1 += x5, x13 = rotl32(x13 ^ x1, 16)
+	movdqa		0x10(%rsp),%xmm0
+	paddd		%xmm5,%xmm0
+	movdqa		%xmm0,0x10(%rsp)
+	pxor		%xmm0,%xmm13
+	pshufb		%xmm3,%xmm13
+	# x2 += x6, x14 = rotl32(x14 ^ x2, 16)
+	movdqa		0x20(%rsp),%xmm0
+	paddd		%xmm6,%xmm0
+	movdqa		%xmm0,0x20(%rsp)
+	pxor		%xmm0,%xmm14
+	pshufb		%xmm3,%xmm14
+	# x3 += x7, x15 = rotl32(x15 ^ x3, 16)
+	movdqa		0x30(%rsp),%xmm0
+	paddd		%xmm7,%xmm0
+	movdqa		%xmm0,0x30(%rsp)
+	pxor		%xmm0,%xmm15
+	pshufb		%xmm3,%xmm15
+
+	# x8 += x12, x4 = rotl32(x4 ^ x8, 12)
+	paddd		%xmm12,%xmm8
+	pxor		%xmm8,%xmm4
+	movdqa		%xmm4,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm4
+	por		%xmm0,%xmm4
+	# x9 += x13, x5 = rotl32(x5 ^ x9, 12)
+	paddd		%xmm13,%xmm9
+	pxor		%xmm9,%xmm5
+	movdqa		%xmm5,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm5
+	por		%xmm0,%xmm5
+	# x10 += x14, x6 = rotl32(x6 ^ x10, 12)
+	paddd		%xmm14,%xmm10
+	pxor		%xmm10,%xmm6
+	movdqa		%xmm6,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm6
+	por		%xmm0,%xmm6
+	# x11 += x15, x7 = rotl32(x7 ^ x11, 12)
+	paddd		%xmm15,%xmm11
+	pxor		%xmm11,%xmm7
+	movdqa		%xmm7,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm7
+	por		%xmm0,%xmm7
+
+	# x0 += x4, x12 = rotl32(x12 ^ x0, 8)
+	movdqa		0x00(%rsp),%xmm0
+	paddd		%xmm4,%xmm0
+	movdqa		%xmm0,0x00(%rsp)
+	pxor		%xmm0,%xmm12
+	pshufb		%xmm2,%xmm12
+	# x1 += x5, x13 = rotl32(x13 ^ x1, 8)
+	movdqa		0x10(%rsp),%xmm0
+	paddd		%xmm5,%xmm0
+	movdqa		%xmm0,0x10(%rsp)
+	pxor		%xmm0,%xmm13
+	pshufb		%xmm2,%xmm13
+	# x2 += x6, x14 = rotl32(x14 ^ x2, 8)
+	movdqa		0x20(%rsp),%xmm0
+	paddd		%xmm6,%xmm0
+	movdqa		%xmm0,0x20(%rsp)
+	pxor		%xmm0,%xmm14
+	pshufb		%xmm2,%xmm14
+	# x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+	movdqa		0x30(%rsp),%xmm0
+	paddd		%xmm7,%xmm0
+	movdqa		%xmm0,0x30(%rsp)
+	pxor		%xmm0,%xmm15
+	pshufb		%xmm2,%xmm15
+
+	# x8 += x12, x4 = rotl32(x4 ^ x8, 7)
+	paddd		%xmm12,%xmm8
+	pxor		%xmm8,%xmm4
+	movdqa		%xmm4,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm4
+	por		%xmm0,%xmm4
+	# x9 += x13, x5 = rotl32(x5 ^ x9, 7)
+	paddd		%xmm13,%xmm9
+	pxor		%xmm9,%xmm5
+	movdqa		%xmm5,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm5
+	por		%xmm0,%xmm5
+	# x10 += x14, x6 = rotl32(x6 ^ x10, 7)
+	paddd		%xmm14,%xmm10
+	pxor		%xmm10,%xmm6
+	movdqa		%xmm6,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm6
+	por		%xmm0,%xmm6
+	# x11 += x15, x7 = rotl32(x7 ^ x11, 7)
+	paddd		%xmm15,%xmm11
+	pxor		%xmm11,%xmm7
+	movdqa		%xmm7,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm7
+	por		%xmm0,%xmm7
+
+	# x0 += x5, x15 = rotl32(x15 ^ x0, 16)
+	movdqa		0x00(%rsp),%xmm0
+	paddd		%xmm5,%xmm0
+	movdqa		%xmm0,0x00(%rsp)
+	pxor		%xmm0,%xmm15
+	pshufb		%xmm3,%xmm15
+	# x1 += x6, x12 = rotl32(x12 ^ x1, 16)
+	movdqa		0x10(%rsp),%xmm0
+	paddd		%xmm6,%xmm0
+	movdqa		%xmm0,0x10(%rsp)
+	pxor		%xmm0,%xmm12
+	pshufb		%xmm3,%xmm12
+	# x2 += x7, x13 = rotl32(x13 ^ x2, 16)
+	movdqa		0x20(%rsp),%xmm0
+	paddd		%xmm7,%xmm0
+	movdqa		%xmm0,0x20(%rsp)
+	pxor		%xmm0,%xmm13
+	pshufb		%xmm3,%xmm13
+	# x3 += x4, x14 = rotl32(x14 ^ x3, 16)
+	movdqa		0x30(%rsp),%xmm0
+	paddd		%xmm4,%xmm0
+	movdqa		%xmm0,0x30(%rsp)
+	pxor		%xmm0,%xmm14
+	pshufb		%xmm3,%xmm14
+
+	# x10 += x15, x5 = rotl32(x5 ^ x10, 12)
+	paddd		%xmm15,%xmm10
+	pxor		%xmm10,%xmm5
+	movdqa		%xmm5,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm5
+	por		%xmm0,%xmm5
+	# x11 += x12, x6 = rotl32(x6 ^ x11, 12)
+	paddd		%xmm12,%xmm11
+	pxor		%xmm11,%xmm6
+	movdqa		%xmm6,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm6
+	por		%xmm0,%xmm6
+	# x8 += x13, x7 = rotl32(x7 ^ x8, 12)
+	paddd		%xmm13,%xmm8
+	pxor		%xmm8,%xmm7
+	movdqa		%xmm7,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm7
+	por		%xmm0,%xmm7
+	# x9 += x14, x4 = rotl32(x4 ^ x9, 12)
+	paddd		%xmm14,%xmm9
+	pxor		%xmm9,%xmm4
+	movdqa		%xmm4,%xmm0
+	pslld		$12,%xmm0
+	psrld		$20,%xmm4
+	por		%xmm0,%xmm4
+
+	# x0 += x5, x15 = rotl32(x15 ^ x0, 8)
+	movdqa		0x00(%rsp),%xmm0
+	paddd		%xmm5,%xmm0
+	movdqa		%xmm0,0x00(%rsp)
+	pxor		%xmm0,%xmm15
+	pshufb		%xmm2,%xmm15
+	# x1 += x6, x12 = rotl32(x12 ^ x1, 8)
+	movdqa		0x10(%rsp),%xmm0
+	paddd		%xmm6,%xmm0
+	movdqa		%xmm0,0x10(%rsp)
+	pxor		%xmm0,%xmm12
+	pshufb		%xmm2,%xmm12
+	# x2 += x7, x13 = rotl32(x13 ^ x2, 8)
+	movdqa		0x20(%rsp),%xmm0
+	paddd		%xmm7,%xmm0
+	movdqa		%xmm0,0x20(%rsp)
+	pxor		%xmm0,%xmm13
+	pshufb		%xmm2,%xmm13
+	# x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+	movdqa		0x30(%rsp),%xmm0
+	paddd		%xmm4,%xmm0
+	movdqa		%xmm0,0x30(%rsp)
+	pxor		%xmm0,%xmm14
+	pshufb		%xmm2,%xmm14
+
+	# x10 += x15, x5 = rotl32(x5 ^ x10, 7)
+	paddd		%xmm15,%xmm10
+	pxor		%xmm10,%xmm5
+	movdqa		%xmm5,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm5
+	por		%xmm0,%xmm5
+	# x11 += x12, x6 = rotl32(x6 ^ x11, 7)
+	paddd		%xmm12,%xmm11
+	pxor		%xmm11,%xmm6
+	movdqa		%xmm6,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm6
+	por		%xmm0,%xmm6
+	# x8 += x13, x7 = rotl32(x7 ^ x8, 7)
+	paddd		%xmm13,%xmm8
+	pxor		%xmm8,%xmm7
+	movdqa		%xmm7,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm7
+	por		%xmm0,%xmm7
+	# x9 += x14, x4 = rotl32(x4 ^ x9, 7)
+	paddd		%xmm14,%xmm9
+	pxor		%xmm9,%xmm4
+	movdqa		%xmm4,%xmm0
+	pslld		$7,%xmm0
+	psrld		$25,%xmm4
+	por		%xmm0,%xmm4
+
+	sub		$2,%r8d
+	jnz		.Ldoubleround4
+
+	# x0[0-3] += s0[0]
+	# x1[0-3] += s0[1]
+	movq		0x00(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		0x00(%rsp),%xmm2
+	movdqa		%xmm2,0x00(%rsp)
+	paddd		0x10(%rsp),%xmm3
+	movdqa		%xmm3,0x10(%rsp)
+	# x2[0-3] += s0[2]
+	# x3[0-3] += s0[3]
+	movq		0x08(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		0x20(%rsp),%xmm2
+	movdqa		%xmm2,0x20(%rsp)
+	paddd		0x30(%rsp),%xmm3
+	movdqa		%xmm3,0x30(%rsp)
+
+	# x4[0-3] += s1[0]
+	# x5[0-3] += s1[1]
+	movq		0x10(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm4
+	paddd		%xmm3,%xmm5
+	# x6[0-3] += s1[2]
+	# x7[0-3] += s1[3]
+	movq		0x18(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm6
+	paddd		%xmm3,%xmm7
+
+	# x8[0-3] += s2[0]
+	# x9[0-3] += s2[1]
+	movq		0x20(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm8
+	paddd		%xmm3,%xmm9
+	# x10[0-3] += s2[2]
+	# x11[0-3] += s2[3]
+	movq		0x28(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm10
+	paddd		%xmm3,%xmm11
+
+	# x12[0-3] += s3[0]
+	# x13[0-3] += s3[1]
+	movq		0x30(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm12
+	paddd		%xmm3,%xmm13
+	# x14[0-3] += s3[2]
+	# x15[0-3] += s3[3]
+	movq		0x38(%rdi),%xmm3
+	pshufd		$0x00,%xmm3,%xmm2
+	pshufd		$0x55,%xmm3,%xmm3
+	paddd		%xmm2,%xmm14
+	paddd		%xmm3,%xmm15
+
+	# x12 += counter values 0-3
+	paddd		%xmm1,%xmm12
+
+	# interleave 32-bit words in state n, n+1
+	movdqa		0x00(%rsp),%xmm0
+	movdqa		0x10(%rsp),%xmm1
+	movdqa		%xmm0,%xmm2
+	punpckldq	%xmm1,%xmm2
+	punpckhdq	%xmm1,%xmm0
+	movdqa		%xmm2,0x00(%rsp)
+	movdqa		%xmm0,0x10(%rsp)
+	movdqa		0x20(%rsp),%xmm0
+	movdqa		0x30(%rsp),%xmm1
+	movdqa		%xmm0,%xmm2
+	punpckldq	%xmm1,%xmm2
+	punpckhdq	%xmm1,%xmm0
+	movdqa		%xmm2,0x20(%rsp)
+	movdqa		%xmm0,0x30(%rsp)
+	movdqa		%xmm4,%xmm0
+	punpckldq	%xmm5,%xmm4
+	punpckhdq	%xmm5,%xmm0
+	movdqa		%xmm0,%xmm5
+	movdqa		%xmm6,%xmm0
+	punpckldq	%xmm7,%xmm6
+	punpckhdq	%xmm7,%xmm0
+	movdqa		%xmm0,%xmm7
+	movdqa		%xmm8,%xmm0
+	punpckldq	%xmm9,%xmm8
+	punpckhdq	%xmm9,%xmm0
+	movdqa		%xmm0,%xmm9
+	movdqa		%xmm10,%xmm0
+	punpckldq	%xmm11,%xmm10
+	punpckhdq	%xmm11,%xmm0
+	movdqa		%xmm0,%xmm11
+	movdqa		%xmm12,%xmm0
+	punpckldq	%xmm13,%xmm12
+	punpckhdq	%xmm13,%xmm0
+	movdqa		%xmm0,%xmm13
+	movdqa		%xmm14,%xmm0
+	punpckldq	%xmm15,%xmm14
+	punpckhdq	%xmm15,%xmm0
+	movdqa		%xmm0,%xmm15
+
+	# interleave 64-bit words in state n, n+2
+	movdqa		0x00(%rsp),%xmm0
+	movdqa		0x20(%rsp),%xmm1
+	movdqa		%xmm0,%xmm2
+	punpcklqdq	%xmm1,%xmm2
+	punpckhqdq	%xmm1,%xmm0
+	movdqa		%xmm2,0x00(%rsp)
+	movdqa		%xmm0,0x20(%rsp)
+	movdqa		0x10(%rsp),%xmm0
+	movdqa		0x30(%rsp),%xmm1
+	movdqa		%xmm0,%xmm2
+	punpcklqdq	%xmm1,%xmm2
+	punpckhqdq	%xmm1,%xmm0
+	movdqa		%xmm2,0x10(%rsp)
+	movdqa		%xmm0,0x30(%rsp)
+	movdqa		%xmm4,%xmm0
+	punpcklqdq	%xmm6,%xmm4
+	punpckhqdq	%xmm6,%xmm0
+	movdqa		%xmm0,%xmm6
+	movdqa		%xmm5,%xmm0
+	punpcklqdq	%xmm7,%xmm5
+	punpckhqdq	%xmm7,%xmm0
+	movdqa		%xmm0,%xmm7
+	movdqa		%xmm8,%xmm0
+	punpcklqdq	%xmm10,%xmm8
+	punpckhqdq	%xmm10,%xmm0
+	movdqa		%xmm0,%xmm10
+	movdqa		%xmm9,%xmm0
+	punpcklqdq	%xmm11,%xmm9
+	punpckhqdq	%xmm11,%xmm0
+	movdqa		%xmm0,%xmm11
+	movdqa		%xmm12,%xmm0
+	punpcklqdq	%xmm14,%xmm12
+	punpckhqdq	%xmm14,%xmm0
+	movdqa		%xmm0,%xmm14
+	movdqa		%xmm13,%xmm0
+	punpcklqdq	%xmm15,%xmm13
+	punpckhqdq	%xmm15,%xmm0
+	movdqa		%xmm0,%xmm15
+
+	# xor with corresponding input, write to output
+	movdqa		0x00(%rsp),%xmm0
+	cmp		$0x10,%rax
+	jl		.Lxorpart4
+	movdqu		0x00(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x00(%rsi)
+
+	movdqu		%xmm4,%xmm0
+	cmp		$0x20,%rax
+	jl		.Lxorpart4
+	movdqu		0x10(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x10(%rsi)
+
+	movdqu		%xmm8,%xmm0
+	cmp		$0x30,%rax
+	jl		.Lxorpart4
+	movdqu		0x20(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x20(%rsi)
+
+	movdqu		%xmm12,%xmm0
+	cmp		$0x40,%rax
+	jl		.Lxorpart4
+	movdqu		0x30(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x30(%rsi)
+
+	movdqa		0x20(%rsp),%xmm0
+	cmp		$0x50,%rax
+	jl		.Lxorpart4
+	movdqu		0x40(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x40(%rsi)
+
+	movdqu		%xmm6,%xmm0
+	cmp		$0x60,%rax
+	jl		.Lxorpart4
+	movdqu		0x50(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x50(%rsi)
+
+	movdqu		%xmm10,%xmm0
+	cmp		$0x70,%rax
+	jl		.Lxorpart4
+	movdqu		0x60(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x60(%rsi)
+
+	movdqu		%xmm14,%xmm0
+	cmp		$0x80,%rax
+	jl		.Lxorpart4
+	movdqu		0x70(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x70(%rsi)
+
+	movdqa		0x10(%rsp),%xmm0
+	cmp		$0x90,%rax
+	jl		.Lxorpart4
+	movdqu		0x80(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x80(%rsi)
+
+	movdqu		%xmm5,%xmm0
+	cmp		$0xa0,%rax
+	jl		.Lxorpart4
+	movdqu		0x90(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x90(%rsi)
+
+	movdqu		%xmm9,%xmm0
+	cmp		$0xb0,%rax
+	jl		.Lxorpart4
+	movdqu		0xa0(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0xa0(%rsi)
+
+	movdqu		%xmm13,%xmm0
+	cmp		$0xc0,%rax
+	jl		.Lxorpart4
+	movdqu		0xb0(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0xb0(%rsi)
+
+	movdqa		0x30(%rsp),%xmm0
+	cmp		$0xd0,%rax
+	jl		.Lxorpart4
+	movdqu		0xc0(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0xc0(%rsi)
+
+	movdqu		%xmm7,%xmm0
+	cmp		$0xe0,%rax
+	jl		.Lxorpart4
+	movdqu		0xd0(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0xd0(%rsi)
+
+	movdqu		%xmm11,%xmm0
+	cmp		$0xf0,%rax
+	jl		.Lxorpart4
+	movdqu		0xe0(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0xe0(%rsi)
+
+	movdqu		%xmm15,%xmm0
+	cmp		$0x100,%rax
+	jl		.Lxorpart4
+	movdqu		0xf0(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0xf0(%rsi)
+
+.Ldone4:
+	lea		-8(%r10),%rsp
+	ret
+
+.Lxorpart4:
+	# xor remaining bytes from partial register into output
+	mov		%rax,%r9
+	and		$0x0f,%r9
+	jz		.Ldone4
+	and		$~0x0f,%rax
+
+	mov		%rsi,%r11
+
+	lea		(%rdx,%rax),%rsi
+	mov		%rsp,%rdi
+	mov		%r9,%rcx
+	rep movsb
+
+	pxor		0x00(%rsp),%xmm0
+	movdqa		%xmm0,0x00(%rsp)
+
+	mov		%rsp,%rsi
+	lea		(%r11,%rax),%rdi
+	mov		%r9,%rcx
+	rep movsb
+
+	jmp		.Ldone4
+
+ENDPROC(chacha_4block_xor_ssse3)
diff --git a/arch/x86/crypto/chacha20-avx2-x86_64.S b/arch/x86/crypto/chacha20-avx2-x86_64.S
deleted file mode 100644
index b6ab082be657..000000000000
--- a/arch/x86/crypto/chacha20-avx2-x86_64.S
+++ /dev/null
@@ -1,1026 +0,0 @@
-/*
- * ChaCha20 256-bit cipher algorithm, RFC7539, x64 AVX2 functions
- *
- * Copyright (C) 2015 Martin Willi
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <linux/linkage.h>
-
-.section	.rodata.cst32.ROT8, "aM", @progbits, 32
-.align 32
-ROT8:	.octa 0x0e0d0c0f0a09080b0605040702010003
-	.octa 0x0e0d0c0f0a09080b0605040702010003
-
-.section	.rodata.cst32.ROT16, "aM", @progbits, 32
-.align 32
-ROT16:	.octa 0x0d0c0f0e09080b0a0504070601000302
-	.octa 0x0d0c0f0e09080b0a0504070601000302
-
-.section	.rodata.cst32.CTRINC, "aM", @progbits, 32
-.align 32
-CTRINC:	.octa 0x00000003000000020000000100000000
-	.octa 0x00000007000000060000000500000004
-
-.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
-
-.text
-
-ENTRY(chacha20_2block_xor_avx2)
-	# %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
-
-	# This function encrypts two ChaCha20 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
-
-	vmovdqa		ROT8(%rip),%ymm4
-	vmovdqa		ROT16(%rip),%ymm5
-
-	mov		%rcx,%rax
-	mov		$10,%ecx
-
-.Ldoubleround:
-
-	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
-	vpaddd		%ymm1,%ymm0,%ymm0
-	vpxor		%ymm0,%ymm3,%ymm3
-	vpshufb		%ymm5,%ymm3,%ymm3
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
-	vpaddd		%ymm3,%ymm2,%ymm2
-	vpxor		%ymm2,%ymm1,%ymm1
-	vmovdqa		%ymm1,%ymm6
-	vpslld		$12,%ymm6,%ymm6
-	vpsrld		$20,%ymm1,%ymm1
-	vpor		%ymm6,%ymm1,%ymm1
-
-	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
-	vpaddd		%ymm1,%ymm0,%ymm0
-	vpxor		%ymm0,%ymm3,%ymm3
-	vpshufb		%ymm4,%ymm3,%ymm3
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
-	vpaddd		%ymm3,%ymm2,%ymm2
-	vpxor		%ymm2,%ymm1,%ymm1
-	vmovdqa		%ymm1,%ymm7
-	vpslld		$7,%ymm7,%ymm7
-	vpsrld		$25,%ymm1,%ymm1
-	vpor		%ymm7,%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
-	vpxor		%ymm0,%ymm3,%ymm3
-	vpshufb		%ymm5,%ymm3,%ymm3
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
-	vpaddd		%ymm3,%ymm2,%ymm2
-	vpxor		%ymm2,%ymm1,%ymm1
-	vmovdqa		%ymm1,%ymm6
-	vpslld		$12,%ymm6,%ymm6
-	vpsrld		$20,%ymm1,%ymm1
-	vpor		%ymm6,%ymm1,%ymm1
-
-	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
-	vpaddd		%ymm1,%ymm0,%ymm0
-	vpxor		%ymm0,%ymm3,%ymm3
-	vpshufb		%ymm4,%ymm3,%ymm3
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
-	vpaddd		%ymm3,%ymm2,%ymm2
-	vpxor		%ymm2,%ymm1,%ymm1
-	vmovdqa		%ymm1,%ymm7
-	vpslld		$7,%ymm7,%ymm7
-	vpsrld		$25,%ymm1,%ymm1
-	vpor		%ymm7,%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
-
-	dec		%ecx
-	jnz		.Ldoubleround
-
-	# o0 = i0 ^ (x0 + s0)
-	vpaddd		%ymm8,%ymm0,%ymm7
-	cmp		$0x10,%rax
-	jl		.Lxorpart2
-	vpxor		0x00(%rdx),%xmm7,%xmm6
-	vmovdqu		%xmm6,0x00(%rsi)
-	vextracti128	$1,%ymm7,%xmm0
-	# o1 = i1 ^ (x1 + s1)
-	vpaddd		%ymm9,%ymm1,%ymm7
-	cmp		$0x20,%rax
-	jl		.Lxorpart2
-	vpxor		0x10(%rdx),%xmm7,%xmm6
-	vmovdqu		%xmm6,0x10(%rsi)
-	vextracti128	$1,%ymm7,%xmm1
-	# o2 = i2 ^ (x2 + s2)
-	vpaddd		%ymm10,%ymm2,%ymm7
-	cmp		$0x30,%rax
-	jl		.Lxorpart2
-	vpxor		0x20(%rdx),%xmm7,%xmm6
-	vmovdqu		%xmm6,0x20(%rsi)
-	vextracti128	$1,%ymm7,%xmm2
-	# o3 = i3 ^ (x3 + s3)
-	vpaddd		%ymm11,%ymm3,%ymm7
-	cmp		$0x40,%rax
-	jl		.Lxorpart2
-	vpxor		0x30(%rdx),%xmm7,%xmm6
-	vmovdqu		%xmm6,0x30(%rsi)
-	vextracti128	$1,%ymm7,%xmm3
-
-	# xor and write second block
-	vmovdqa		%xmm0,%xmm7
-	cmp		$0x50,%rax
-	jl		.Lxorpart2
-	vpxor		0x40(%rdx),%xmm7,%xmm6
-	vmovdqu		%xmm6,0x40(%rsi)
-
-	vmovdqa		%xmm1,%xmm7
-	cmp		$0x60,%rax
-	jl		.Lxorpart2
-	vpxor		0x50(%rdx),%xmm7,%xmm6
-	vmovdqu		%xmm6,0x50(%rsi)
-
-	vmovdqa		%xmm2,%xmm7
-	cmp		$0x70,%rax
-	jl		.Lxorpart2
-	vpxor		0x60(%rdx),%xmm7,%xmm6
-	vmovdqu		%xmm6,0x60(%rsi)
-
-	vmovdqa		%xmm3,%xmm7
-	cmp		$0x80,%rax
-	jl		.Lxorpart2
-	vpxor		0x70(%rdx),%xmm7,%xmm6
-	vmovdqu		%xmm6,0x70(%rsi)
-
-.Ldone2:
-	vzeroupper
-	ret
-
-.Lxorpart2:
-	# xor remaining bytes from partial register into output
-	mov		%rax,%r9
-	and		$0x0f,%r9
-	jz		.Ldone2
-	and		$~0x0f,%rax
-
-	mov		%rsi,%r11
-
-	lea		8(%rsp),%r10
-	sub		$0x10,%rsp
-	and		$~31,%rsp
-
-	lea		(%rdx,%rax),%rsi
-	mov		%rsp,%rdi
-	mov		%r9,%rcx
-	rep movsb
-
-	vpxor		0x00(%rsp),%xmm7,%xmm7
-	vmovdqa		%xmm7,0x00(%rsp)
-
-	mov		%rsp,%rsi
-	lea		(%r11,%rax),%rdi
-	mov		%r9,%rcx
-	rep movsb
-
-	lea		-8(%r10),%rsp
-	jmp		.Ldone2
-
-ENDPROC(chacha20_2block_xor_avx2)
-
-ENTRY(chacha20_4block_xor_avx2)
-	# %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
-
-	# This function encrypts four ChaCha20 block 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
-
-	vmovdqa		ROT8(%rip),%ymm8
-	vmovdqa		ROT16(%rip),%ymm9
-
-	mov		%rcx,%rax
-	mov		$10,%ecx
-
-.Ldoubleround4:
-
-	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
-	vpaddd		%ymm1,%ymm0,%ymm0
-	vpxor		%ymm0,%ymm3,%ymm3
-	vpshufb		%ymm9,%ymm3,%ymm3
-
-	vpaddd		%ymm5,%ymm4,%ymm4
-	vpxor		%ymm4,%ymm7,%ymm7
-	vpshufb		%ymm9,%ymm7,%ymm7
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
-	vpaddd		%ymm3,%ymm2,%ymm2
-	vpxor		%ymm2,%ymm1,%ymm1
-	vmovdqa		%ymm1,%ymm10
-	vpslld		$12,%ymm10,%ymm10
-	vpsrld		$20,%ymm1,%ymm1
-	vpor		%ymm10,%ymm1,%ymm1
-
-	vpaddd		%ymm7,%ymm6,%ymm6
-	vpxor		%ymm6,%ymm5,%ymm5
-	vmovdqa		%ymm5,%ymm10
-	vpslld		$12,%ymm10,%ymm10
-	vpsrld		$20,%ymm5,%ymm5
-	vpor		%ymm10,%ymm5,%ymm5
-
-	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
-	vpaddd		%ymm1,%ymm0,%ymm0
-	vpxor		%ymm0,%ymm3,%ymm3
-	vpshufb		%ymm8,%ymm3,%ymm3
-
-	vpaddd		%ymm5,%ymm4,%ymm4
-	vpxor		%ymm4,%ymm7,%ymm7
-	vpshufb		%ymm8,%ymm7,%ymm7
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
-	vpaddd		%ymm3,%ymm2,%ymm2
-	vpxor		%ymm2,%ymm1,%ymm1
-	vmovdqa		%ymm1,%ymm10
-	vpslld		$7,%ymm10,%ymm10
-	vpsrld		$25,%ymm1,%ymm1
-	vpor		%ymm10,%ymm1,%ymm1
-
-	vpaddd		%ymm7,%ymm6,%ymm6
-	vpxor		%ymm6,%ymm5,%ymm5
-	vmovdqa		%ymm5,%ymm10
-	vpslld		$7,%ymm10,%ymm10
-	vpsrld		$25,%ymm5,%ymm5
-	vpor		%ymm10,%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
-	vpxor		%ymm0,%ymm3,%ymm3
-	vpshufb		%ymm9,%ymm3,%ymm3
-
-	vpaddd		%ymm5,%ymm4,%ymm4
-	vpxor		%ymm4,%ymm7,%ymm7
-	vpshufb		%ymm9,%ymm7,%ymm7
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
-	vpaddd		%ymm3,%ymm2,%ymm2
-	vpxor		%ymm2,%ymm1,%ymm1
-	vmovdqa		%ymm1,%ymm10
-	vpslld		$12,%ymm10,%ymm10
-	vpsrld		$20,%ymm1,%ymm1
-	vpor		%ymm10,%ymm1,%ymm1
-
-	vpaddd		%ymm7,%ymm6,%ymm6
-	vpxor		%ymm6,%ymm5,%ymm5
-	vmovdqa		%ymm5,%ymm10
-	vpslld		$12,%ymm10,%ymm10
-	vpsrld		$20,%ymm5,%ymm5
-	vpor		%ymm10,%ymm5,%ymm5
-
-	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
-	vpaddd		%ymm1,%ymm0,%ymm0
-	vpxor		%ymm0,%ymm3,%ymm3
-	vpshufb		%ymm8,%ymm3,%ymm3
-
-	vpaddd		%ymm5,%ymm4,%ymm4
-	vpxor		%ymm4,%ymm7,%ymm7
-	vpshufb		%ymm8,%ymm7,%ymm7
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
-	vpaddd		%ymm3,%ymm2,%ymm2
-	vpxor		%ymm2,%ymm1,%ymm1
-	vmovdqa		%ymm1,%ymm10
-	vpslld		$7,%ymm10,%ymm10
-	vpsrld		$25,%ymm1,%ymm1
-	vpor		%ymm10,%ymm1,%ymm1
-
-	vpaddd		%ymm7,%ymm6,%ymm6
-	vpxor		%ymm6,%ymm5,%ymm5
-	vmovdqa		%ymm5,%ymm10
-	vpslld		$7,%ymm10,%ymm10
-	vpsrld		$25,%ymm5,%ymm5
-	vpor		%ymm10,%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
-
-	dec		%ecx
-	jnz		.Ldoubleround4
-
-	# o0 = i0 ^ (x0 + s0), first block
-	vpaddd		%ymm11,%ymm0,%ymm10
-	cmp		$0x10,%rax
-	jl		.Lxorpart4
-	vpxor		0x00(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0x00(%rsi)
-	vextracti128	$1,%ymm10,%xmm0
-	# o1 = i1 ^ (x1 + s1), first block
-	vpaddd		%ymm12,%ymm1,%ymm10
-	cmp		$0x20,%rax
-	jl		.Lxorpart4
-	vpxor		0x10(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0x10(%rsi)
-	vextracti128	$1,%ymm10,%xmm1
-	# o2 = i2 ^ (x2 + s2), first block
-	vpaddd		%ymm13,%ymm2,%ymm10
-	cmp		$0x30,%rax
-	jl		.Lxorpart4
-	vpxor		0x20(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0x20(%rsi)
-	vextracti128	$1,%ymm10,%xmm2
-	# o3 = i3 ^ (x3 + s3), first block
-	vpaddd		%ymm14,%ymm3,%ymm10
-	cmp		$0x40,%rax
-	jl		.Lxorpart4
-	vpxor		0x30(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0x30(%rsi)
-	vextracti128	$1,%ymm10,%xmm3
-
-	# xor and write second block
-	vmovdqa		%xmm0,%xmm10
-	cmp		$0x50,%rax
-	jl		.Lxorpart4
-	vpxor		0x40(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0x40(%rsi)
-
-	vmovdqa		%xmm1,%xmm10
-	cmp		$0x60,%rax
-	jl		.Lxorpart4
-	vpxor		0x50(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0x50(%rsi)
-
-	vmovdqa		%xmm2,%xmm10
-	cmp		$0x70,%rax
-	jl		.Lxorpart4
-	vpxor		0x60(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0x60(%rsi)
-
-	vmovdqa		%xmm3,%xmm10
-	cmp		$0x80,%rax
-	jl		.Lxorpart4
-	vpxor		0x70(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0x70(%rsi)
-
-	# o0 = i0 ^ (x0 + s0), third block
-	vpaddd		%ymm11,%ymm4,%ymm10
-	cmp		$0x90,%rax
-	jl		.Lxorpart4
-	vpxor		0x80(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0x80(%rsi)
-	vextracti128	$1,%ymm10,%xmm4
-	# o1 = i1 ^ (x1 + s1), third block
-	vpaddd		%ymm12,%ymm5,%ymm10
-	cmp		$0xa0,%rax
-	jl		.Lxorpart4
-	vpxor		0x90(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0x90(%rsi)
-	vextracti128	$1,%ymm10,%xmm5
-	# o2 = i2 ^ (x2 + s2), third block
-	vpaddd		%ymm13,%ymm6,%ymm10
-	cmp		$0xb0,%rax
-	jl		.Lxorpart4
-	vpxor		0xa0(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0xa0(%rsi)
-	vextracti128	$1,%ymm10,%xmm6
-	# o3 = i3 ^ (x3 + s3), third block
-	vpaddd		%ymm15,%ymm7,%ymm10
-	cmp		$0xc0,%rax
-	jl		.Lxorpart4
-	vpxor		0xb0(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0xb0(%rsi)
-	vextracti128	$1,%ymm10,%xmm7
-
-	# xor and write fourth block
-	vmovdqa		%xmm4,%xmm10
-	cmp		$0xd0,%rax
-	jl		.Lxorpart4
-	vpxor		0xc0(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0xc0(%rsi)
-
-	vmovdqa		%xmm5,%xmm10
-	cmp		$0xe0,%rax
-	jl		.Lxorpart4
-	vpxor		0xd0(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0xd0(%rsi)
-
-	vmovdqa		%xmm6,%xmm10
-	cmp		$0xf0,%rax
-	jl		.Lxorpart4
-	vpxor		0xe0(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0xe0(%rsi)
-
-	vmovdqa		%xmm7,%xmm10
-	cmp		$0x100,%rax
-	jl		.Lxorpart4
-	vpxor		0xf0(%rdx),%xmm10,%xmm9
-	vmovdqu		%xmm9,0xf0(%rsi)
-
-.Ldone4:
-	vzeroupper
-	ret
-
-.Lxorpart4:
-	# xor remaining bytes from partial register into output
-	mov		%rax,%r9
-	and		$0x0f,%r9
-	jz		.Ldone4
-	and		$~0x0f,%rax
-
-	mov		%rsi,%r11
-
-	lea		8(%rsp),%r10
-	sub		$0x10,%rsp
-	and		$~31,%rsp
-
-	lea		(%rdx,%rax),%rsi
-	mov		%rsp,%rdi
-	mov		%r9,%rcx
-	rep movsb
-
-	vpxor		0x00(%rsp),%xmm10,%xmm10
-	vmovdqa		%xmm10,0x00(%rsp)
-
-	mov		%rsp,%rsi
-	lea		(%r11,%rax),%rdi
-	mov		%r9,%rcx
-	rep movsb
-
-	lea		-8(%r10),%rsp
-	jmp		.Ldone4
-
-ENDPROC(chacha20_4block_xor_avx2)
-
-ENTRY(chacha20_8block_xor_avx2)
-	# %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
-
-	# This function encrypts eight consecutive ChaCha20 blocks by loading
-	# the state matrix in AVX registers eight times. As we need some
-	# scratch registers, we save the first four registers on the stack. The
-	# algorithm performs each operation on the corresponding word of each
-	# state matrix, hence requires no word shuffling. For final XORing step
-	# we transpose the matrix by interleaving 32-, 64- and then 128-bit
-	# words, which allows us to do XOR in AVX registers. 8/16-bit word
-	# rotation is done with the slightly better performing byte shuffling,
-	# 7/12-bit word rotation uses traditional shift+OR.
-
-	vzeroupper
-	# 4 * 32 byte stack, 32-byte aligned
-	lea		8(%rsp),%r10
-	and		$~31, %rsp
-	sub		$0x80, %rsp
-	mov		%rcx,%rax
-
-	# 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
-	# x0..3 on stack
-	vmovdqa		%ymm0,0x00(%rsp)
-	vmovdqa		%ymm1,0x20(%rsp)
-	vmovdqa		%ymm2,0x40(%rsp)
-	vmovdqa		%ymm3,0x60(%rsp)
-
-	vmovdqa		CTRINC(%rip),%ymm1
-	vmovdqa		ROT8(%rip),%ymm2
-	vmovdqa		ROT16(%rip),%ymm3
-
-	# x12 += counter values 0-3
-	vpaddd		%ymm1,%ymm12,%ymm12
-
-	mov		$10,%ecx
-
-.Ldoubleround8:
-	# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
-	vpaddd		0x00(%rsp),%ymm4,%ymm0
-	vmovdqa		%ymm0,0x00(%rsp)
-	vpxor		%ymm0,%ymm12,%ymm12
-	vpshufb		%ymm3,%ymm12,%ymm12
-	# x1 += x5, x13 = rotl32(x13 ^ x1, 16)
-	vpaddd		0x20(%rsp),%ymm5,%ymm0
-	vmovdqa		%ymm0,0x20(%rsp)
-	vpxor		%ymm0,%ymm13,%ymm13
-	vpshufb		%ymm3,%ymm13,%ymm13
-	# x2 += x6, x14 = rotl32(x14 ^ x2, 16)
-	vpaddd		0x40(%rsp),%ymm6,%ymm0
-	vmovdqa		%ymm0,0x40(%rsp)
-	vpxor		%ymm0,%ymm14,%ymm14
-	vpshufb		%ymm3,%ymm14,%ymm14
-	# x3 += x7, x15 = rotl32(x15 ^ x3, 16)
-	vpaddd		0x60(%rsp),%ymm7,%ymm0
-	vmovdqa		%ymm0,0x60(%rsp)
-	vpxor		%ymm0,%ymm15,%ymm15
-	vpshufb		%ymm3,%ymm15,%ymm15
-
-	# x8 += x12, x4 = rotl32(x4 ^ x8, 12)
-	vpaddd		%ymm12,%ymm8,%ymm8
-	vpxor		%ymm8,%ymm4,%ymm4
-	vpslld		$12,%ymm4,%ymm0
-	vpsrld		$20,%ymm4,%ymm4
-	vpor		%ymm0,%ymm4,%ymm4
-	# x9 += x13, x5 = rotl32(x5 ^ x9, 12)
-	vpaddd		%ymm13,%ymm9,%ymm9
-	vpxor		%ymm9,%ymm5,%ymm5
-	vpslld		$12,%ymm5,%ymm0
-	vpsrld		$20,%ymm5,%ymm5
-	vpor		%ymm0,%ymm5,%ymm5
-	# x10 += x14, x6 = rotl32(x6 ^ x10, 12)
-	vpaddd		%ymm14,%ymm10,%ymm10
-	vpxor		%ymm10,%ymm6,%ymm6
-	vpslld		$12,%ymm6,%ymm0
-	vpsrld		$20,%ymm6,%ymm6
-	vpor		%ymm0,%ymm6,%ymm6
-	# x11 += x15, x7 = rotl32(x7 ^ x11, 12)
-	vpaddd		%ymm15,%ymm11,%ymm11
-	vpxor		%ymm11,%ymm7,%ymm7
-	vpslld		$12,%ymm7,%ymm0
-	vpsrld		$20,%ymm7,%ymm7
-	vpor		%ymm0,%ymm7,%ymm7
-
-	# x0 += x4, x12 = rotl32(x12 ^ x0, 8)
-	vpaddd		0x00(%rsp),%ymm4,%ymm0
-	vmovdqa		%ymm0,0x00(%rsp)
-	vpxor		%ymm0,%ymm12,%ymm12
-	vpshufb		%ymm2,%ymm12,%ymm12
-	# x1 += x5, x13 = rotl32(x13 ^ x1, 8)
-	vpaddd		0x20(%rsp),%ymm5,%ymm0
-	vmovdqa		%ymm0,0x20(%rsp)
-	vpxor		%ymm0,%ymm13,%ymm13
-	vpshufb		%ymm2,%ymm13,%ymm13
-	# x2 += x6, x14 = rotl32(x14 ^ x2, 8)
-	vpaddd		0x40(%rsp),%ymm6,%ymm0
-	vmovdqa		%ymm0,0x40(%rsp)
-	vpxor		%ymm0,%ymm14,%ymm14
-	vpshufb		%ymm2,%ymm14,%ymm14
-	# x3 += x7, x15 = rotl32(x15 ^ x3, 8)
-	vpaddd		0x60(%rsp),%ymm7,%ymm0
-	vmovdqa		%ymm0,0x60(%rsp)
-	vpxor		%ymm0,%ymm15,%ymm15
-	vpshufb		%ymm2,%ymm15,%ymm15
-
-	# x8 += x12, x4 = rotl32(x4 ^ x8, 7)
-	vpaddd		%ymm12,%ymm8,%ymm8
-	vpxor		%ymm8,%ymm4,%ymm4
-	vpslld		$7,%ymm4,%ymm0
-	vpsrld		$25,%ymm4,%ymm4
-	vpor		%ymm0,%ymm4,%ymm4
-	# x9 += x13, x5 = rotl32(x5 ^ x9, 7)
-	vpaddd		%ymm13,%ymm9,%ymm9
-	vpxor		%ymm9,%ymm5,%ymm5
-	vpslld		$7,%ymm5,%ymm0
-	vpsrld		$25,%ymm5,%ymm5
-	vpor		%ymm0,%ymm5,%ymm5
-	# x10 += x14, x6 = rotl32(x6 ^ x10, 7)
-	vpaddd		%ymm14,%ymm10,%ymm10
-	vpxor		%ymm10,%ymm6,%ymm6
-	vpslld		$7,%ymm6,%ymm0
-	vpsrld		$25,%ymm6,%ymm6
-	vpor		%ymm0,%ymm6,%ymm6
-	# x11 += x15, x7 = rotl32(x7 ^ x11, 7)
-	vpaddd		%ymm15,%ymm11,%ymm11
-	vpxor		%ymm11,%ymm7,%ymm7
-	vpslld		$7,%ymm7,%ymm0
-	vpsrld		$25,%ymm7,%ymm7
-	vpor		%ymm0,%ymm7,%ymm7
-
-	# x0 += x5, x15 = rotl32(x15 ^ x0, 16)
-	vpaddd		0x00(%rsp),%ymm5,%ymm0
-	vmovdqa		%ymm0,0x00(%rsp)
-	vpxor		%ymm0,%ymm15,%ymm15
-	vpshufb		%ymm3,%ymm15,%ymm15
-	# x1 += x6, x12 = rotl32(x12 ^ x1, 16)%ymm0
-	vpaddd		0x20(%rsp),%ymm6,%ymm0
-	vmovdqa		%ymm0,0x20(%rsp)
-	vpxor		%ymm0,%ymm12,%ymm12
-	vpshufb		%ymm3,%ymm12,%ymm12
-	# x2 += x7, x13 = rotl32(x13 ^ x2, 16)
-	vpaddd		0x40(%rsp),%ymm7,%ymm0
-	vmovdqa		%ymm0,0x40(%rsp)
-	vpxor		%ymm0,%ymm13,%ymm13
-	vpshufb		%ymm3,%ymm13,%ymm13
-	# x3 += x4, x14 = rotl32(x14 ^ x3, 16)
-	vpaddd		0x60(%rsp),%ymm4,%ymm0
-	vmovdqa		%ymm0,0x60(%rsp)
-	vpxor		%ymm0,%ymm14,%ymm14
-	vpshufb		%ymm3,%ymm14,%ymm14
-
-	# x10 += x15, x5 = rotl32(x5 ^ x10, 12)
-	vpaddd		%ymm15,%ymm10,%ymm10
-	vpxor		%ymm10,%ymm5,%ymm5
-	vpslld		$12,%ymm5,%ymm0
-	vpsrld		$20,%ymm5,%ymm5
-	vpor		%ymm0,%ymm5,%ymm5
-	# x11 += x12, x6 = rotl32(x6 ^ x11, 12)
-	vpaddd		%ymm12,%ymm11,%ymm11
-	vpxor		%ymm11,%ymm6,%ymm6
-	vpslld		$12,%ymm6,%ymm0
-	vpsrld		$20,%ymm6,%ymm6
-	vpor		%ymm0,%ymm6,%ymm6
-	# x8 += x13, x7 = rotl32(x7 ^ x8, 12)
-	vpaddd		%ymm13,%ymm8,%ymm8
-	vpxor		%ymm8,%ymm7,%ymm7
-	vpslld		$12,%ymm7,%ymm0
-	vpsrld		$20,%ymm7,%ymm7
-	vpor		%ymm0,%ymm7,%ymm7
-	# x9 += x14, x4 = rotl32(x4 ^ x9, 12)
-	vpaddd		%ymm14,%ymm9,%ymm9
-	vpxor		%ymm9,%ymm4,%ymm4
-	vpslld		$12,%ymm4,%ymm0
-	vpsrld		$20,%ymm4,%ymm4
-	vpor		%ymm0,%ymm4,%ymm4
-
-	# x0 += x5, x15 = rotl32(x15 ^ x0, 8)
-	vpaddd		0x00(%rsp),%ymm5,%ymm0
-	vmovdqa		%ymm0,0x00(%rsp)
-	vpxor		%ymm0,%ymm15,%ymm15
-	vpshufb		%ymm2,%ymm15,%ymm15
-	# x1 += x6, x12 = rotl32(x12 ^ x1, 8)
-	vpaddd		0x20(%rsp),%ymm6,%ymm0
-	vmovdqa		%ymm0,0x20(%rsp)
-	vpxor		%ymm0,%ymm12,%ymm12
-	vpshufb		%ymm2,%ymm12,%ymm12
-	# x2 += x7, x13 = rotl32(x13 ^ x2, 8)
-	vpaddd		0x40(%rsp),%ymm7,%ymm0
-	vmovdqa		%ymm0,0x40(%rsp)
-	vpxor		%ymm0,%ymm13,%ymm13
-	vpshufb		%ymm2,%ymm13,%ymm13
-	# x3 += x4, x14 = rotl32(x14 ^ x3, 8)
-	vpaddd		0x60(%rsp),%ymm4,%ymm0
-	vmovdqa		%ymm0,0x60(%rsp)
-	vpxor		%ymm0,%ymm14,%ymm14
-	vpshufb		%ymm2,%ymm14,%ymm14
-
-	# x10 += x15, x5 = rotl32(x5 ^ x10, 7)
-	vpaddd		%ymm15,%ymm10,%ymm10
-	vpxor		%ymm10,%ymm5,%ymm5
-	vpslld		$7,%ymm5,%ymm0
-	vpsrld		$25,%ymm5,%ymm5
-	vpor		%ymm0,%ymm5,%ymm5
-	# x11 += x12, x6 = rotl32(x6 ^ x11, 7)
-	vpaddd		%ymm12,%ymm11,%ymm11
-	vpxor		%ymm11,%ymm6,%ymm6
-	vpslld		$7,%ymm6,%ymm0
-	vpsrld		$25,%ymm6,%ymm6
-	vpor		%ymm0,%ymm6,%ymm6
-	# x8 += x13, x7 = rotl32(x7 ^ x8, 7)
-	vpaddd		%ymm13,%ymm8,%ymm8
-	vpxor		%ymm8,%ymm7,%ymm7
-	vpslld		$7,%ymm7,%ymm0
-	vpsrld		$25,%ymm7,%ymm7
-	vpor		%ymm0,%ymm7,%ymm7
-	# x9 += x14, x4 = rotl32(x4 ^ x9, 7)
-	vpaddd		%ymm14,%ymm9,%ymm9
-	vpxor		%ymm9,%ymm4,%ymm4
-	vpslld		$7,%ymm4,%ymm0
-	vpsrld		$25,%ymm4,%ymm4
-	vpor		%ymm0,%ymm4,%ymm4
-
-	dec		%ecx
-	jnz		.Ldoubleround8
-
-	# x0..15[0-3] += s[0..15]
-	vpbroadcastd	0x00(%rdi),%ymm0
-	vpaddd		0x00(%rsp),%ymm0,%ymm0
-	vmovdqa		%ymm0,0x00(%rsp)
-	vpbroadcastd	0x04(%rdi),%ymm0
-	vpaddd		0x20(%rsp),%ymm0,%ymm0
-	vmovdqa		%ymm0,0x20(%rsp)
-	vpbroadcastd	0x08(%rdi),%ymm0
-	vpaddd		0x40(%rsp),%ymm0,%ymm0
-	vmovdqa		%ymm0,0x40(%rsp)
-	vpbroadcastd	0x0c(%rdi),%ymm0
-	vpaddd		0x60(%rsp),%ymm0,%ymm0
-	vmovdqa		%ymm0,0x60(%rsp)
-	vpbroadcastd	0x10(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm4,%ymm4
-	vpbroadcastd	0x14(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm5,%ymm5
-	vpbroadcastd	0x18(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm6,%ymm6
-	vpbroadcastd	0x1c(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm7,%ymm7
-	vpbroadcastd	0x20(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm8,%ymm8
-	vpbroadcastd	0x24(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm9,%ymm9
-	vpbroadcastd	0x28(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm10,%ymm10
-	vpbroadcastd	0x2c(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm11,%ymm11
-	vpbroadcastd	0x30(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm12,%ymm12
-	vpbroadcastd	0x34(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm13,%ymm13
-	vpbroadcastd	0x38(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm14,%ymm14
-	vpbroadcastd	0x3c(%rdi),%ymm0
-	vpaddd		%ymm0,%ymm15,%ymm15
-
-	# x12 += counter values 0-3
-	vpaddd		%ymm1,%ymm12,%ymm12
-
-	# interleave 32-bit words in state n, n+1
-	vmovdqa		0x00(%rsp),%ymm0
-	vmovdqa		0x20(%rsp),%ymm1
-	vpunpckldq	%ymm1,%ymm0,%ymm2
-	vpunpckhdq	%ymm1,%ymm0,%ymm1
-	vmovdqa		%ymm2,0x00(%rsp)
-	vmovdqa		%ymm1,0x20(%rsp)
-	vmovdqa		0x40(%rsp),%ymm0
-	vmovdqa		0x60(%rsp),%ymm1
-	vpunpckldq	%ymm1,%ymm0,%ymm2
-	vpunpckhdq	%ymm1,%ymm0,%ymm1
-	vmovdqa		%ymm2,0x40(%rsp)
-	vmovdqa		%ymm1,0x60(%rsp)
-	vmovdqa		%ymm4,%ymm0
-	vpunpckldq	%ymm5,%ymm0,%ymm4
-	vpunpckhdq	%ymm5,%ymm0,%ymm5
-	vmovdqa		%ymm6,%ymm0
-	vpunpckldq	%ymm7,%ymm0,%ymm6
-	vpunpckhdq	%ymm7,%ymm0,%ymm7
-	vmovdqa		%ymm8,%ymm0
-	vpunpckldq	%ymm9,%ymm0,%ymm8
-	vpunpckhdq	%ymm9,%ymm0,%ymm9
-	vmovdqa		%ymm10,%ymm0
-	vpunpckldq	%ymm11,%ymm0,%ymm10
-	vpunpckhdq	%ymm11,%ymm0,%ymm11
-	vmovdqa		%ymm12,%ymm0
-	vpunpckldq	%ymm13,%ymm0,%ymm12
-	vpunpckhdq	%ymm13,%ymm0,%ymm13
-	vmovdqa		%ymm14,%ymm0
-	vpunpckldq	%ymm15,%ymm0,%ymm14
-	vpunpckhdq	%ymm15,%ymm0,%ymm15
-
-	# interleave 64-bit words in state n, n+2
-	vmovdqa		0x00(%rsp),%ymm0
-	vmovdqa		0x40(%rsp),%ymm2
-	vpunpcklqdq	%ymm2,%ymm0,%ymm1
-	vpunpckhqdq	%ymm2,%ymm0,%ymm2
-	vmovdqa		%ymm1,0x00(%rsp)
-	vmovdqa		%ymm2,0x40(%rsp)
-	vmovdqa		0x20(%rsp),%ymm0
-	vmovdqa		0x60(%rsp),%ymm2
-	vpunpcklqdq	%ymm2,%ymm0,%ymm1
-	vpunpckhqdq	%ymm2,%ymm0,%ymm2
-	vmovdqa		%ymm1,0x20(%rsp)
-	vmovdqa		%ymm2,0x60(%rsp)
-	vmovdqa		%ymm4,%ymm0
-	vpunpcklqdq	%ymm6,%ymm0,%ymm4
-	vpunpckhqdq	%ymm6,%ymm0,%ymm6
-	vmovdqa		%ymm5,%ymm0
-	vpunpcklqdq	%ymm7,%ymm0,%ymm5
-	vpunpckhqdq	%ymm7,%ymm0,%ymm7
-	vmovdqa		%ymm8,%ymm0
-	vpunpcklqdq	%ymm10,%ymm0,%ymm8
-	vpunpckhqdq	%ymm10,%ymm0,%ymm10
-	vmovdqa		%ymm9,%ymm0
-	vpunpcklqdq	%ymm11,%ymm0,%ymm9
-	vpunpckhqdq	%ymm11,%ymm0,%ymm11
-	vmovdqa		%ymm12,%ymm0
-	vpunpcklqdq	%ymm14,%ymm0,%ymm12
-	vpunpckhqdq	%ymm14,%ymm0,%ymm14
-	vmovdqa		%ymm13,%ymm0
-	vpunpcklqdq	%ymm15,%ymm0,%ymm13
-	vpunpckhqdq	%ymm15,%ymm0,%ymm15
-
-	# interleave 128-bit words in state n, n+4
-	# xor/write first four blocks
-	vmovdqa		0x00(%rsp),%ymm1
-	vperm2i128	$0x20,%ymm4,%ymm1,%ymm0
-	cmp		$0x0020,%rax
-	jl		.Lxorpart8
-	vpxor		0x0000(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x0000(%rsi)
-	vperm2i128	$0x31,%ymm4,%ymm1,%ymm4
-
-	vperm2i128	$0x20,%ymm12,%ymm8,%ymm0
-	cmp		$0x0040,%rax
-	jl		.Lxorpart8
-	vpxor		0x0020(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x0020(%rsi)
-	vperm2i128	$0x31,%ymm12,%ymm8,%ymm12
-
-	vmovdqa		0x40(%rsp),%ymm1
-	vperm2i128	$0x20,%ymm6,%ymm1,%ymm0
-	cmp		$0x0060,%rax
-	jl		.Lxorpart8
-	vpxor		0x0040(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x0040(%rsi)
-	vperm2i128	$0x31,%ymm6,%ymm1,%ymm6
-
-	vperm2i128	$0x20,%ymm14,%ymm10,%ymm0
-	cmp		$0x0080,%rax
-	jl		.Lxorpart8
-	vpxor		0x0060(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x0060(%rsi)
-	vperm2i128	$0x31,%ymm14,%ymm10,%ymm14
-
-	vmovdqa		0x20(%rsp),%ymm1
-	vperm2i128	$0x20,%ymm5,%ymm1,%ymm0
-	cmp		$0x00a0,%rax
-	jl		.Lxorpart8
-	vpxor		0x0080(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x0080(%rsi)
-	vperm2i128	$0x31,%ymm5,%ymm1,%ymm5
-
-	vperm2i128	$0x20,%ymm13,%ymm9,%ymm0
-	cmp		$0x00c0,%rax
-	jl		.Lxorpart8
-	vpxor		0x00a0(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x00a0(%rsi)
-	vperm2i128	$0x31,%ymm13,%ymm9,%ymm13
-
-	vmovdqa		0x60(%rsp),%ymm1
-	vperm2i128	$0x20,%ymm7,%ymm1,%ymm0
-	cmp		$0x00e0,%rax
-	jl		.Lxorpart8
-	vpxor		0x00c0(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x00c0(%rsi)
-	vperm2i128	$0x31,%ymm7,%ymm1,%ymm7
-
-	vperm2i128	$0x20,%ymm15,%ymm11,%ymm0
-	cmp		$0x0100,%rax
-	jl		.Lxorpart8
-	vpxor		0x00e0(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x00e0(%rsi)
-	vperm2i128	$0x31,%ymm15,%ymm11,%ymm15
-
-	# xor remaining blocks, write to output
-	vmovdqa		%ymm4,%ymm0
-	cmp		$0x0120,%rax
-	jl		.Lxorpart8
-	vpxor		0x0100(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x0100(%rsi)
-
-	vmovdqa		%ymm12,%ymm0
-	cmp		$0x0140,%rax
-	jl		.Lxorpart8
-	vpxor		0x0120(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x0120(%rsi)
-
-	vmovdqa		%ymm6,%ymm0
-	cmp		$0x0160,%rax
-	jl		.Lxorpart8
-	vpxor		0x0140(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x0140(%rsi)
-
-	vmovdqa		%ymm14,%ymm0
-	cmp		$0x0180,%rax
-	jl		.Lxorpart8
-	vpxor		0x0160(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x0160(%rsi)
-
-	vmovdqa		%ymm5,%ymm0
-	cmp		$0x01a0,%rax
-	jl		.Lxorpart8
-	vpxor		0x0180(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x0180(%rsi)
-
-	vmovdqa		%ymm13,%ymm0
-	cmp		$0x01c0,%rax
-	jl		.Lxorpart8
-	vpxor		0x01a0(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x01a0(%rsi)
-
-	vmovdqa		%ymm7,%ymm0
-	cmp		$0x01e0,%rax
-	jl		.Lxorpart8
-	vpxor		0x01c0(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x01c0(%rsi)
-
-	vmovdqa		%ymm15,%ymm0
-	cmp		$0x0200,%rax
-	jl		.Lxorpart8
-	vpxor		0x01e0(%rdx),%ymm0,%ymm0
-	vmovdqu		%ymm0,0x01e0(%rsi)
-
-.Ldone8:
-	vzeroupper
-	lea		-8(%r10),%rsp
-	ret
-
-.Lxorpart8:
-	# xor remaining bytes from partial register into output
-	mov		%rax,%r9
-	and		$0x1f,%r9
-	jz		.Ldone8
-	and		$~0x1f,%rax
-
-	mov		%rsi,%r11
-
-	lea		(%rdx,%rax),%rsi
-	mov		%rsp,%rdi
-	mov		%r9,%rcx
-	rep movsb
-
-	vpxor		0x00(%rsp),%ymm0,%ymm0
-	vmovdqa		%ymm0,0x00(%rsp)
-
-	mov		%rsp,%rsi
-	lea		(%r11,%rax),%rdi
-	mov		%r9,%rcx
-	rep movsb
-
-	jmp		.Ldone8
-
-ENDPROC(chacha20_8block_xor_avx2)
diff --git a/arch/x86/crypto/chacha20-avx512vl-x86_64.S b/arch/x86/crypto/chacha20-avx512vl-x86_64.S
deleted file mode 100644
index 55d34de29e3e..000000000000
--- a/arch/x86/crypto/chacha20-avx512vl-x86_64.S
+++ /dev/null
@@ -1,839 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ */
-/*
- * ChaCha20 256-bit cipher algorithm, RFC7539, 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(chacha20_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
-
-	# This function encrypts two ChaCha20 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
-
-	mov		$10,%rax
-
-.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
-
-	dec		%rax
-	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		.Ldone8
-	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(chacha20_2block_xor_avx512vl)
-
-ENTRY(chacha20_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
-
-	# This function encrypts four ChaCha20 block 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
-
-	mov		$10,%rax
-
-.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
-
-	dec		%rax
-	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		.Ldone8
-	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(chacha20_4block_xor_avx512vl)
-
-ENTRY(chacha20_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
-
-	# This function encrypts eight consecutive ChaCha20 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
-
-	mov		$10,%eax
-
-.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
-
-	dec		%eax
-	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(chacha20_8block_xor_avx512vl)
diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S
deleted file mode 100644
index f6792789f875..000000000000
--- a/arch/x86/crypto/chacha20-ssse3-x86_64.S
+++ /dev/null
@@ -1,792 +0,0 @@
-/*
- * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSSE3 functions
- *
- * Copyright (C) 2015 Martin Willi
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <linux/linkage.h>
-#include <asm/frame.h>
-
-.section	.rodata.cst16.ROT8, "aM", @progbits, 16
-.align 16
-ROT8:	.octa 0x0e0d0c0f0a09080b0605040702010003
-.section	.rodata.cst16.ROT16, "aM", @progbits, 16
-.align 16
-ROT16:	.octa 0x0d0c0f0e09080b0a0504070601000302
-.section	.rodata.cst16.CTRINC, "aM", @progbits, 16
-.align 16
-CTRINC:	.octa 0x00000003000000020000000100000000
-
-.text
-
-/*
- * chacha20_permute - permute one block
- *
- * Permute one 64-byte block where the state matrix is in %xmm0-%xmm3.  This
- * function performs matrix operations on four words in parallel, but requires
- * shuffling to rearrange the words after each round.  8/16-bit word rotation is
- * done with the slightly better performing SSSE3 byte shuffling, 7/12-bit word
- * rotation uses traditional shift+OR.
- *
- * Clobbers: %ecx, %xmm4-%xmm7
- */
-chacha20_permute:
-
-	movdqa		ROT8(%rip),%xmm4
-	movdqa		ROT16(%rip),%xmm5
-	mov		$10,%ecx
-
-.Ldoubleround:
-	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
-	paddd		%xmm1,%xmm0
-	pxor		%xmm0,%xmm3
-	pshufb		%xmm5,%xmm3
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
-	paddd		%xmm3,%xmm2
-	pxor		%xmm2,%xmm1
-	movdqa		%xmm1,%xmm6
-	pslld		$12,%xmm6
-	psrld		$20,%xmm1
-	por		%xmm6,%xmm1
-
-	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
-	paddd		%xmm1,%xmm0
-	pxor		%xmm0,%xmm3
-	pshufb		%xmm4,%xmm3
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
-	paddd		%xmm3,%xmm2
-	pxor		%xmm2,%xmm1
-	movdqa		%xmm1,%xmm7
-	pslld		$7,%xmm7
-	psrld		$25,%xmm1
-	por		%xmm7,%xmm1
-
-	# x1 = shuffle32(x1, MASK(0, 3, 2, 1))
-	pshufd		$0x39,%xmm1,%xmm1
-	# x2 = shuffle32(x2, MASK(1, 0, 3, 2))
-	pshufd		$0x4e,%xmm2,%xmm2
-	# x3 = shuffle32(x3, MASK(2, 1, 0, 3))
-	pshufd		$0x93,%xmm3,%xmm3
-
-	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
-	paddd		%xmm1,%xmm0
-	pxor		%xmm0,%xmm3
-	pshufb		%xmm5,%xmm3
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 12)
-	paddd		%xmm3,%xmm2
-	pxor		%xmm2,%xmm1
-	movdqa		%xmm1,%xmm6
-	pslld		$12,%xmm6
-	psrld		$20,%xmm1
-	por		%xmm6,%xmm1
-
-	# x0 += x1, x3 = rotl32(x3 ^ x0, 8)
-	paddd		%xmm1,%xmm0
-	pxor		%xmm0,%xmm3
-	pshufb		%xmm4,%xmm3
-
-	# x2 += x3, x1 = rotl32(x1 ^ x2, 7)
-	paddd		%xmm3,%xmm2
-	pxor		%xmm2,%xmm1
-	movdqa		%xmm1,%xmm7
-	pslld		$7,%xmm7
-	psrld		$25,%xmm1
-	por		%xmm7,%xmm1
-
-	# x1 = shuffle32(x1, MASK(2, 1, 0, 3))
-	pshufd		$0x93,%xmm1,%xmm1
-	# x2 = shuffle32(x2, MASK(1, 0, 3, 2))
-	pshufd		$0x4e,%xmm2,%xmm2
-	# x3 = shuffle32(x3, MASK(0, 3, 2, 1))
-	pshufd		$0x39,%xmm3,%xmm3
-
-	dec		%ecx
-	jnz		.Ldoubleround
-
-	ret
-ENDPROC(chacha20_permute)
-
-ENTRY(chacha20_block_xor_ssse3)
-	# %rdi: Input state matrix, s
-	# %rsi: up to 1 data block output, o
-	# %rdx: up to 1 data block input, i
-	# %rcx: input/output length in bytes
-	FRAME_BEGIN
-
-	# x0..3 = s0..3
-	movdqa		0x00(%rdi),%xmm0
-	movdqa		0x10(%rdi),%xmm1
-	movdqa		0x20(%rdi),%xmm2
-	movdqa		0x30(%rdi),%xmm3
-	movdqa		%xmm0,%xmm8
-	movdqa		%xmm1,%xmm9
-	movdqa		%xmm2,%xmm10
-	movdqa		%xmm3,%xmm11
-
-	mov		%rcx,%rax
-	call		chacha20_permute
-
-	# o0 = i0 ^ (x0 + s0)
-	paddd		%xmm8,%xmm0
-	cmp		$0x10,%rax
-	jl		.Lxorpart
-	movdqu		0x00(%rdx),%xmm4
-	pxor		%xmm4,%xmm0
-	movdqu		%xmm0,0x00(%rsi)
-	# o1 = i1 ^ (x1 + s1)
-	paddd		%xmm9,%xmm1
-	movdqa		%xmm1,%xmm0
-	cmp		$0x20,%rax
-	jl		.Lxorpart
-	movdqu		0x10(%rdx),%xmm0
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x10(%rsi)
-	# o2 = i2 ^ (x2 + s2)
-	paddd		%xmm10,%xmm2
-	movdqa		%xmm2,%xmm0
-	cmp		$0x30,%rax
-	jl		.Lxorpart
-	movdqu		0x20(%rdx),%xmm0
-	pxor		%xmm2,%xmm0
-	movdqu		%xmm0,0x20(%rsi)
-	# o3 = i3 ^ (x3 + s3)
-	paddd		%xmm11,%xmm3
-	movdqa		%xmm3,%xmm0
-	cmp		$0x40,%rax
-	jl		.Lxorpart
-	movdqu		0x30(%rdx),%xmm0
-	pxor		%xmm3,%xmm0
-	movdqu		%xmm0,0x30(%rsi)
-
-.Ldone:
-	FRAME_END
-	ret
-
-.Lxorpart:
-	# xor remaining bytes from partial register into output
-	mov		%rax,%r9
-	and		$0x0f,%r9
-	jz		.Ldone
-	and		$~0x0f,%rax
-
-	mov		%rsi,%r11
-
-	lea		8(%rsp),%r10
-	sub		$0x10,%rsp
-	and		$~31,%rsp
-
-	lea		(%rdx,%rax),%rsi
-	mov		%rsp,%rdi
-	mov		%r9,%rcx
-	rep movsb
-
-	pxor		0x00(%rsp),%xmm0
-	movdqa		%xmm0,0x00(%rsp)
-
-	mov		%rsp,%rsi
-	lea		(%r11,%rax),%rdi
-	mov		%r9,%rcx
-	rep movsb
-
-	lea		-8(%r10),%rsp
-	jmp		.Ldone
-
-ENDPROC(chacha20_block_xor_ssse3)
-
-ENTRY(hchacha20_block_ssse3)
-	# %rdi: Input state matrix, s
-	# %rsi: output (8 32-bit words)
-	FRAME_BEGIN
-
-	movdqa		0x00(%rdi),%xmm0
-	movdqa		0x10(%rdi),%xmm1
-	movdqa		0x20(%rdi),%xmm2
-	movdqa		0x30(%rdi),%xmm3
-
-	call		chacha20_permute
-
-	movdqu		%xmm0,0x00(%rsi)
-	movdqu		%xmm3,0x10(%rsi)
-
-	FRAME_END
-	ret
-ENDPROC(hchacha20_block_ssse3)
-
-ENTRY(chacha20_4block_xor_ssse3)
-	# %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
-
-	# This function encrypts four consecutive ChaCha20 blocks by loading the
-	# the state matrix in SSE registers four times. As we need some scratch
-	# registers, we save the first four registers on the stack. The
-	# algorithm performs each operation on the corresponding word of each
-	# state matrix, hence requires no word shuffling. For final XORing step
-	# we transpose the matrix by interleaving 32- and then 64-bit words,
-	# which allows us to do XOR in SSE registers. 8/16-bit word rotation is
-	# done with the slightly better performing SSSE3 byte shuffling,
-	# 7/12-bit word rotation uses traditional shift+OR.
-
-	lea		8(%rsp),%r10
-	sub		$0x80,%rsp
-	and		$~63,%rsp
-	mov		%rcx,%rax
-
-	# x0..15[0-3] = s0..3[0..3]
-	movq		0x00(%rdi),%xmm1
-	pshufd		$0x00,%xmm1,%xmm0
-	pshufd		$0x55,%xmm1,%xmm1
-	movq		0x08(%rdi),%xmm3
-	pshufd		$0x00,%xmm3,%xmm2
-	pshufd		$0x55,%xmm3,%xmm3
-	movq		0x10(%rdi),%xmm5
-	pshufd		$0x00,%xmm5,%xmm4
-	pshufd		$0x55,%xmm5,%xmm5
-	movq		0x18(%rdi),%xmm7
-	pshufd		$0x00,%xmm7,%xmm6
-	pshufd		$0x55,%xmm7,%xmm7
-	movq		0x20(%rdi),%xmm9
-	pshufd		$0x00,%xmm9,%xmm8
-	pshufd		$0x55,%xmm9,%xmm9
-	movq		0x28(%rdi),%xmm11
-	pshufd		$0x00,%xmm11,%xmm10
-	pshufd		$0x55,%xmm11,%xmm11
-	movq		0x30(%rdi),%xmm13
-	pshufd		$0x00,%xmm13,%xmm12
-	pshufd		$0x55,%xmm13,%xmm13
-	movq		0x38(%rdi),%xmm15
-	pshufd		$0x00,%xmm15,%xmm14
-	pshufd		$0x55,%xmm15,%xmm15
-	# x0..3 on stack
-	movdqa		%xmm0,0x00(%rsp)
-	movdqa		%xmm1,0x10(%rsp)
-	movdqa		%xmm2,0x20(%rsp)
-	movdqa		%xmm3,0x30(%rsp)
-
-	movdqa		CTRINC(%rip),%xmm1
-	movdqa		ROT8(%rip),%xmm2
-	movdqa		ROT16(%rip),%xmm3
-
-	# x12 += counter values 0-3
-	paddd		%xmm1,%xmm12
-
-	mov		$10,%ecx
-
-.Ldoubleround4:
-	# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
-	movdqa		0x00(%rsp),%xmm0
-	paddd		%xmm4,%xmm0
-	movdqa		%xmm0,0x00(%rsp)
-	pxor		%xmm0,%xmm12
-	pshufb		%xmm3,%xmm12
-	# x1 += x5, x13 = rotl32(x13 ^ x1, 16)
-	movdqa		0x10(%rsp),%xmm0
-	paddd		%xmm5,%xmm0
-	movdqa		%xmm0,0x10(%rsp)
-	pxor		%xmm0,%xmm13
-	pshufb		%xmm3,%xmm13
-	# x2 += x6, x14 = rotl32(x14 ^ x2, 16)
-	movdqa		0x20(%rsp),%xmm0
-	paddd		%xmm6,%xmm0
-	movdqa		%xmm0,0x20(%rsp)
-	pxor		%xmm0,%xmm14
-	pshufb		%xmm3,%xmm14
-	# x3 += x7, x15 = rotl32(x15 ^ x3, 16)
-	movdqa		0x30(%rsp),%xmm0
-	paddd		%xmm7,%xmm0
-	movdqa		%xmm0,0x30(%rsp)
-	pxor		%xmm0,%xmm15
-	pshufb		%xmm3,%xmm15
-
-	# x8 += x12, x4 = rotl32(x4 ^ x8, 12)
-	paddd		%xmm12,%xmm8
-	pxor		%xmm8,%xmm4
-	movdqa		%xmm4,%xmm0
-	pslld		$12,%xmm0
-	psrld		$20,%xmm4
-	por		%xmm0,%xmm4
-	# x9 += x13, x5 = rotl32(x5 ^ x9, 12)
-	paddd		%xmm13,%xmm9
-	pxor		%xmm9,%xmm5
-	movdqa		%xmm5,%xmm0
-	pslld		$12,%xmm0
-	psrld		$20,%xmm5
-	por		%xmm0,%xmm5
-	# x10 += x14, x6 = rotl32(x6 ^ x10, 12)
-	paddd		%xmm14,%xmm10
-	pxor		%xmm10,%xmm6
-	movdqa		%xmm6,%xmm0
-	pslld		$12,%xmm0
-	psrld		$20,%xmm6
-	por		%xmm0,%xmm6
-	# x11 += x15, x7 = rotl32(x7 ^ x11, 12)
-	paddd		%xmm15,%xmm11
-	pxor		%xmm11,%xmm7
-	movdqa		%xmm7,%xmm0
-	pslld		$12,%xmm0
-	psrld		$20,%xmm7
-	por		%xmm0,%xmm7
-
-	# x0 += x4, x12 = rotl32(x12 ^ x0, 8)
-	movdqa		0x00(%rsp),%xmm0
-	paddd		%xmm4,%xmm0
-	movdqa		%xmm0,0x00(%rsp)
-	pxor		%xmm0,%xmm12
-	pshufb		%xmm2,%xmm12
-	# x1 += x5, x13 = rotl32(x13 ^ x1, 8)
-	movdqa		0x10(%rsp),%xmm0
-	paddd		%xmm5,%xmm0
-	movdqa		%xmm0,0x10(%rsp)
-	pxor		%xmm0,%xmm13
-	pshufb		%xmm2,%xmm13
-	# x2 += x6, x14 = rotl32(x14 ^ x2, 8)
-	movdqa		0x20(%rsp),%xmm0
-	paddd		%xmm6,%xmm0
-	movdqa		%xmm0,0x20(%rsp)
-	pxor		%xmm0,%xmm14
-	pshufb		%xmm2,%xmm14
-	# x3 += x7, x15 = rotl32(x15 ^ x3, 8)
-	movdqa		0x30(%rsp),%xmm0
-	paddd		%xmm7,%xmm0
-	movdqa		%xmm0,0x30(%rsp)
-	pxor		%xmm0,%xmm15
-	pshufb		%xmm2,%xmm15
-
-	# x8 += x12, x4 = rotl32(x4 ^ x8, 7)
-	paddd		%xmm12,%xmm8
-	pxor		%xmm8,%xmm4
-	movdqa		%xmm4,%xmm0
-	pslld		$7,%xmm0
-	psrld		$25,%xmm4
-	por		%xmm0,%xmm4
-	# x9 += x13, x5 = rotl32(x5 ^ x9, 7)
-	paddd		%xmm13,%xmm9
-	pxor		%xmm9,%xmm5
-	movdqa		%xmm5,%xmm0
-	pslld		$7,%xmm0
-	psrld		$25,%xmm5
-	por		%xmm0,%xmm5
-	# x10 += x14, x6 = rotl32(x6 ^ x10, 7)
-	paddd		%xmm14,%xmm10
-	pxor		%xmm10,%xmm6
-	movdqa		%xmm6,%xmm0
-	pslld		$7,%xmm0
-	psrld		$25,%xmm6
-	por		%xmm0,%xmm6
-	# x11 += x15, x7 = rotl32(x7 ^ x11, 7)
-	paddd		%xmm15,%xmm11
-	pxor		%xmm11,%xmm7
-	movdqa		%xmm7,%xmm0
-	pslld		$7,%xmm0
-	psrld		$25,%xmm7
-	por		%xmm0,%xmm7
-
-	# x0 += x5, x15 = rotl32(x15 ^ x0, 16)
-	movdqa		0x00(%rsp),%xmm0
-	paddd		%xmm5,%xmm0
-	movdqa		%xmm0,0x00(%rsp)
-	pxor		%xmm0,%xmm15
-	pshufb		%xmm3,%xmm15
-	# x1 += x6, x12 = rotl32(x12 ^ x1, 16)
-	movdqa		0x10(%rsp),%xmm0
-	paddd		%xmm6,%xmm0
-	movdqa		%xmm0,0x10(%rsp)
-	pxor		%xmm0,%xmm12
-	pshufb		%xmm3,%xmm12
-	# x2 += x7, x13 = rotl32(x13 ^ x2, 16)
-	movdqa		0x20(%rsp),%xmm0
-	paddd		%xmm7,%xmm0
-	movdqa		%xmm0,0x20(%rsp)
-	pxor		%xmm0,%xmm13
-	pshufb		%xmm3,%xmm13
-	# x3 += x4, x14 = rotl32(x14 ^ x3, 16)
-	movdqa		0x30(%rsp),%xmm0
-	paddd		%xmm4,%xmm0
-	movdqa		%xmm0,0x30(%rsp)
-	pxor		%xmm0,%xmm14
-	pshufb		%xmm3,%xmm14
-
-	# x10 += x15, x5 = rotl32(x5 ^ x10, 12)
-	paddd		%xmm15,%xmm10
-	pxor		%xmm10,%xmm5
-	movdqa		%xmm5,%xmm0
-	pslld		$12,%xmm0
-	psrld		$20,%xmm5
-	por		%xmm0,%xmm5
-	# x11 += x12, x6 = rotl32(x6 ^ x11, 12)
-	paddd		%xmm12,%xmm11
-	pxor		%xmm11,%xmm6
-	movdqa		%xmm6,%xmm0
-	pslld		$12,%xmm0
-	psrld		$20,%xmm6
-	por		%xmm0,%xmm6
-	# x8 += x13, x7 = rotl32(x7 ^ x8, 12)
-	paddd		%xmm13,%xmm8
-	pxor		%xmm8,%xmm7
-	movdqa		%xmm7,%xmm0
-	pslld		$12,%xmm0
-	psrld		$20,%xmm7
-	por		%xmm0,%xmm7
-	# x9 += x14, x4 = rotl32(x4 ^ x9, 12)
-	paddd		%xmm14,%xmm9
-	pxor		%xmm9,%xmm4
-	movdqa		%xmm4,%xmm0
-	pslld		$12,%xmm0
-	psrld		$20,%xmm4
-	por		%xmm0,%xmm4
-
-	# x0 += x5, x15 = rotl32(x15 ^ x0, 8)
-	movdqa		0x00(%rsp),%xmm0
-	paddd		%xmm5,%xmm0
-	movdqa		%xmm0,0x00(%rsp)
-	pxor		%xmm0,%xmm15
-	pshufb		%xmm2,%xmm15
-	# x1 += x6, x12 = rotl32(x12 ^ x1, 8)
-	movdqa		0x10(%rsp),%xmm0
-	paddd		%xmm6,%xmm0
-	movdqa		%xmm0,0x10(%rsp)
-	pxor		%xmm0,%xmm12
-	pshufb		%xmm2,%xmm12
-	# x2 += x7, x13 = rotl32(x13 ^ x2, 8)
-	movdqa		0x20(%rsp),%xmm0
-	paddd		%xmm7,%xmm0
-	movdqa		%xmm0,0x20(%rsp)
-	pxor		%xmm0,%xmm13
-	pshufb		%xmm2,%xmm13
-	# x3 += x4, x14 = rotl32(x14 ^ x3, 8)
-	movdqa		0x30(%rsp),%xmm0
-	paddd		%xmm4,%xmm0
-	movdqa		%xmm0,0x30(%rsp)
-	pxor		%xmm0,%xmm14
-	pshufb		%xmm2,%xmm14
-
-	# x10 += x15, x5 = rotl32(x5 ^ x10, 7)
-	paddd		%xmm15,%xmm10
-	pxor		%xmm10,%xmm5
-	movdqa		%xmm5,%xmm0
-	pslld		$7,%xmm0
-	psrld		$25,%xmm5
-	por		%xmm0,%xmm5
-	# x11 += x12, x6 = rotl32(x6 ^ x11, 7)
-	paddd		%xmm12,%xmm11
-	pxor		%xmm11,%xmm6
-	movdqa		%xmm6,%xmm0
-	pslld		$7,%xmm0
-	psrld		$25,%xmm6
-	por		%xmm0,%xmm6
-	# x8 += x13, x7 = rotl32(x7 ^ x8, 7)
-	paddd		%xmm13,%xmm8
-	pxor		%xmm8,%xmm7
-	movdqa		%xmm7,%xmm0
-	pslld		$7,%xmm0
-	psrld		$25,%xmm7
-	por		%xmm0,%xmm7
-	# x9 += x14, x4 = rotl32(x4 ^ x9, 7)
-	paddd		%xmm14,%xmm9
-	pxor		%xmm9,%xmm4
-	movdqa		%xmm4,%xmm0
-	pslld		$7,%xmm0
-	psrld		$25,%xmm4
-	por		%xmm0,%xmm4
-
-	dec		%ecx
-	jnz		.Ldoubleround4
-
-	# x0[0-3] += s0[0]
-	# x1[0-3] += s0[1]
-	movq		0x00(%rdi),%xmm3
-	pshufd		$0x00,%xmm3,%xmm2
-	pshufd		$0x55,%xmm3,%xmm3
-	paddd		0x00(%rsp),%xmm2
-	movdqa		%xmm2,0x00(%rsp)
-	paddd		0x10(%rsp),%xmm3
-	movdqa		%xmm3,0x10(%rsp)
-	# x2[0-3] += s0[2]
-	# x3[0-3] += s0[3]
-	movq		0x08(%rdi),%xmm3
-	pshufd		$0x00,%xmm3,%xmm2
-	pshufd		$0x55,%xmm3,%xmm3
-	paddd		0x20(%rsp),%xmm2
-	movdqa		%xmm2,0x20(%rsp)
-	paddd		0x30(%rsp),%xmm3
-	movdqa		%xmm3,0x30(%rsp)
-
-	# x4[0-3] += s1[0]
-	# x5[0-3] += s1[1]
-	movq		0x10(%rdi),%xmm3
-	pshufd		$0x00,%xmm3,%xmm2
-	pshufd		$0x55,%xmm3,%xmm3
-	paddd		%xmm2,%xmm4
-	paddd		%xmm3,%xmm5
-	# x6[0-3] += s1[2]
-	# x7[0-3] += s1[3]
-	movq		0x18(%rdi),%xmm3
-	pshufd		$0x00,%xmm3,%xmm2
-	pshufd		$0x55,%xmm3,%xmm3
-	paddd		%xmm2,%xmm6
-	paddd		%xmm3,%xmm7
-
-	# x8[0-3] += s2[0]
-	# x9[0-3] += s2[1]
-	movq		0x20(%rdi),%xmm3
-	pshufd		$0x00,%xmm3,%xmm2
-	pshufd		$0x55,%xmm3,%xmm3
-	paddd		%xmm2,%xmm8
-	paddd		%xmm3,%xmm9
-	# x10[0-3] += s2[2]
-	# x11[0-3] += s2[3]
-	movq		0x28(%rdi),%xmm3
-	pshufd		$0x00,%xmm3,%xmm2
-	pshufd		$0x55,%xmm3,%xmm3
-	paddd		%xmm2,%xmm10
-	paddd		%xmm3,%xmm11
-
-	# x12[0-3] += s3[0]
-	# x13[0-3] += s3[1]
-	movq		0x30(%rdi),%xmm3
-	pshufd		$0x00,%xmm3,%xmm2
-	pshufd		$0x55,%xmm3,%xmm3
-	paddd		%xmm2,%xmm12
-	paddd		%xmm3,%xmm13
-	# x14[0-3] += s3[2]
-	# x15[0-3] += s3[3]
-	movq		0x38(%rdi),%xmm3
-	pshufd		$0x00,%xmm3,%xmm2
-	pshufd		$0x55,%xmm3,%xmm3
-	paddd		%xmm2,%xmm14
-	paddd		%xmm3,%xmm15
-
-	# x12 += counter values 0-3
-	paddd		%xmm1,%xmm12
-
-	# interleave 32-bit words in state n, n+1
-	movdqa		0x00(%rsp),%xmm0
-	movdqa		0x10(%rsp),%xmm1
-	movdqa		%xmm0,%xmm2
-	punpckldq	%xmm1,%xmm2
-	punpckhdq	%xmm1,%xmm0
-	movdqa		%xmm2,0x00(%rsp)
-	movdqa		%xmm0,0x10(%rsp)
-	movdqa		0x20(%rsp),%xmm0
-	movdqa		0x30(%rsp),%xmm1
-	movdqa		%xmm0,%xmm2
-	punpckldq	%xmm1,%xmm2
-	punpckhdq	%xmm1,%xmm0
-	movdqa		%xmm2,0x20(%rsp)
-	movdqa		%xmm0,0x30(%rsp)
-	movdqa		%xmm4,%xmm0
-	punpckldq	%xmm5,%xmm4
-	punpckhdq	%xmm5,%xmm0
-	movdqa		%xmm0,%xmm5
-	movdqa		%xmm6,%xmm0
-	punpckldq	%xmm7,%xmm6
-	punpckhdq	%xmm7,%xmm0
-	movdqa		%xmm0,%xmm7
-	movdqa		%xmm8,%xmm0
-	punpckldq	%xmm9,%xmm8
-	punpckhdq	%xmm9,%xmm0
-	movdqa		%xmm0,%xmm9
-	movdqa		%xmm10,%xmm0
-	punpckldq	%xmm11,%xmm10
-	punpckhdq	%xmm11,%xmm0
-	movdqa		%xmm0,%xmm11
-	movdqa		%xmm12,%xmm0
-	punpckldq	%xmm13,%xmm12
-	punpckhdq	%xmm13,%xmm0
-	movdqa		%xmm0,%xmm13
-	movdqa		%xmm14,%xmm0
-	punpckldq	%xmm15,%xmm14
-	punpckhdq	%xmm15,%xmm0
-	movdqa		%xmm0,%xmm15
-
-	# interleave 64-bit words in state n, n+2
-	movdqa		0x00(%rsp),%xmm0
-	movdqa		0x20(%rsp),%xmm1
-	movdqa		%xmm0,%xmm2
-	punpcklqdq	%xmm1,%xmm2
-	punpckhqdq	%xmm1,%xmm0
-	movdqa		%xmm2,0x00(%rsp)
-	movdqa		%xmm0,0x20(%rsp)
-	movdqa		0x10(%rsp),%xmm0
-	movdqa		0x30(%rsp),%xmm1
-	movdqa		%xmm0,%xmm2
-	punpcklqdq	%xmm1,%xmm2
-	punpckhqdq	%xmm1,%xmm0
-	movdqa		%xmm2,0x10(%rsp)
-	movdqa		%xmm0,0x30(%rsp)
-	movdqa		%xmm4,%xmm0
-	punpcklqdq	%xmm6,%xmm4
-	punpckhqdq	%xmm6,%xmm0
-	movdqa		%xmm0,%xmm6
-	movdqa		%xmm5,%xmm0
-	punpcklqdq	%xmm7,%xmm5
-	punpckhqdq	%xmm7,%xmm0
-	movdqa		%xmm0,%xmm7
-	movdqa		%xmm8,%xmm0
-	punpcklqdq	%xmm10,%xmm8
-	punpckhqdq	%xmm10,%xmm0
-	movdqa		%xmm0,%xmm10
-	movdqa		%xmm9,%xmm0
-	punpcklqdq	%xmm11,%xmm9
-	punpckhqdq	%xmm11,%xmm0
-	movdqa		%xmm0,%xmm11
-	movdqa		%xmm12,%xmm0
-	punpcklqdq	%xmm14,%xmm12
-	punpckhqdq	%xmm14,%xmm0
-	movdqa		%xmm0,%xmm14
-	movdqa		%xmm13,%xmm0
-	punpcklqdq	%xmm15,%xmm13
-	punpckhqdq	%xmm15,%xmm0
-	movdqa		%xmm0,%xmm15
-
-	# xor with corresponding input, write to output
-	movdqa		0x00(%rsp),%xmm0
-	cmp		$0x10,%rax
-	jl		.Lxorpart4
-	movdqu		0x00(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x00(%rsi)
-
-	movdqu		%xmm4,%xmm0
-	cmp		$0x20,%rax
-	jl		.Lxorpart4
-	movdqu		0x10(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x10(%rsi)
-
-	movdqu		%xmm8,%xmm0
-	cmp		$0x30,%rax
-	jl		.Lxorpart4
-	movdqu		0x20(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x20(%rsi)
-
-	movdqu		%xmm12,%xmm0
-	cmp		$0x40,%rax
-	jl		.Lxorpart4
-	movdqu		0x30(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x30(%rsi)
-
-	movdqa		0x20(%rsp),%xmm0
-	cmp		$0x50,%rax
-	jl		.Lxorpart4
-	movdqu		0x40(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x40(%rsi)
-
-	movdqu		%xmm6,%xmm0
-	cmp		$0x60,%rax
-	jl		.Lxorpart4
-	movdqu		0x50(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x50(%rsi)
-
-	movdqu		%xmm10,%xmm0
-	cmp		$0x70,%rax
-	jl		.Lxorpart4
-	movdqu		0x60(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x60(%rsi)
-
-	movdqu		%xmm14,%xmm0
-	cmp		$0x80,%rax
-	jl		.Lxorpart4
-	movdqu		0x70(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x70(%rsi)
-
-	movdqa		0x10(%rsp),%xmm0
-	cmp		$0x90,%rax
-	jl		.Lxorpart4
-	movdqu		0x80(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x80(%rsi)
-
-	movdqu		%xmm5,%xmm0
-	cmp		$0xa0,%rax
-	jl		.Lxorpart4
-	movdqu		0x90(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0x90(%rsi)
-
-	movdqu		%xmm9,%xmm0
-	cmp		$0xb0,%rax
-	jl		.Lxorpart4
-	movdqu		0xa0(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0xa0(%rsi)
-
-	movdqu		%xmm13,%xmm0
-	cmp		$0xc0,%rax
-	jl		.Lxorpart4
-	movdqu		0xb0(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0xb0(%rsi)
-
-	movdqa		0x30(%rsp),%xmm0
-	cmp		$0xd0,%rax
-	jl		.Lxorpart4
-	movdqu		0xc0(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0xc0(%rsi)
-
-	movdqu		%xmm7,%xmm0
-	cmp		$0xe0,%rax
-	jl		.Lxorpart4
-	movdqu		0xd0(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0xd0(%rsi)
-
-	movdqu		%xmm11,%xmm0
-	cmp		$0xf0,%rax
-	jl		.Lxorpart4
-	movdqu		0xe0(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0xe0(%rsi)
-
-	movdqu		%xmm15,%xmm0
-	cmp		$0x100,%rax
-	jl		.Lxorpart4
-	movdqu		0xf0(%rdx),%xmm1
-	pxor		%xmm1,%xmm0
-	movdqu		%xmm0,0xf0(%rsi)
-
-.Ldone4:
-	lea		-8(%r10),%rsp
-	ret
-
-.Lxorpart4:
-	# xor remaining bytes from partial register into output
-	mov		%rax,%r9
-	and		$0x0f,%r9
-	jz		.Ldone4
-	and		$~0x0f,%rax
-
-	mov		%rsi,%r11
-
-	lea		(%rdx,%rax),%rsi
-	mov		%rsp,%rdi
-	mov		%r9,%rcx
-	rep movsb
-
-	pxor		0x00(%rsp),%xmm0
-	movdqa		%xmm0,0x00(%rsp)
-
-	mov		%rsp,%rsi
-	lea		(%r11,%rax),%rdi
-	mov		%r9,%rcx
-	rep movsb
-
-	jmp		.Ldone4
-
-ENDPROC(chacha20_4block_xor_ssse3)
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
deleted file mode 100644
index 70d388e4a3a2..000000000000
--- a/arch/x86/crypto/chacha20_glue.c
+++ /dev/null
@@ -1,264 +0,0 @@
-/*
- * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
- *
- * Copyright (C) 2015 Martin Willi
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <crypto/algapi.h>
-#include <crypto/chacha.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <asm/fpu/api.h>
-#include <asm/simd.h>
-
-#define CHACHA20_STATE_ALIGN 16
-
-asmlinkage void chacha20_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
-					 unsigned int len);
-asmlinkage void chacha20_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
-					  unsigned int len);
-asmlinkage void hchacha20_block_ssse3(const u32 *state, u32 *out);
-#ifdef CONFIG_AS_AVX2
-asmlinkage void chacha20_2block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
-					 unsigned int len);
-asmlinkage void chacha20_4block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
-					 unsigned int len);
-asmlinkage void chacha20_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
-					 unsigned int len);
-static bool chacha20_use_avx2;
-#ifdef CONFIG_AS_AVX512
-asmlinkage void chacha20_2block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
-					     unsigned int len);
-asmlinkage void chacha20_4block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
-					     unsigned int len);
-asmlinkage void chacha20_8block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
-					     unsigned int len);
-static bool chacha20_use_avx512vl;
-#endif
-#endif
-
-static unsigned int chacha20_advance(unsigned int len, unsigned int maxblocks)
-{
-	len = min(len, maxblocks * CHACHA_BLOCK_SIZE);
-	return round_up(len, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE;
-}
-
-static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src,
-			    unsigned int bytes)
-{
-#ifdef CONFIG_AS_AVX2
-#ifdef CONFIG_AS_AVX512
-	if (chacha20_use_avx512vl) {
-		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
-			chacha20_8block_xor_avx512vl(state, dst, src, bytes);
-			bytes -= CHACHA_BLOCK_SIZE * 8;
-			src += CHACHA_BLOCK_SIZE * 8;
-			dst += CHACHA_BLOCK_SIZE * 8;
-			state[12] += 8;
-		}
-		if (bytes > CHACHA_BLOCK_SIZE * 4) {
-			chacha20_8block_xor_avx512vl(state, dst, src, bytes);
-			state[12] += chacha20_advance(bytes, 8);
-			return;
-		}
-		if (bytes > CHACHA_BLOCK_SIZE * 2) {
-			chacha20_4block_xor_avx512vl(state, dst, src, bytes);
-			state[12] += chacha20_advance(bytes, 4);
-			return;
-		}
-		if (bytes) {
-			chacha20_2block_xor_avx512vl(state, dst, src, bytes);
-			state[12] += chacha20_advance(bytes, 2);
-			return;
-		}
-	}
-#endif
-	if (chacha20_use_avx2) {
-		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
-			chacha20_8block_xor_avx2(state, dst, src, bytes);
-			bytes -= CHACHA_BLOCK_SIZE * 8;
-			src += CHACHA_BLOCK_SIZE * 8;
-			dst += CHACHA_BLOCK_SIZE * 8;
-			state[12] += 8;
-		}
-		if (bytes > CHACHA_BLOCK_SIZE * 4) {
-			chacha20_8block_xor_avx2(state, dst, src, bytes);
-			state[12] += chacha20_advance(bytes, 8);
-			return;
-		}
-		if (bytes > CHACHA_BLOCK_SIZE * 2) {
-			chacha20_4block_xor_avx2(state, dst, src, bytes);
-			state[12] += chacha20_advance(bytes, 4);
-			return;
-		}
-		if (bytes > CHACHA_BLOCK_SIZE) {
-			chacha20_2block_xor_avx2(state, dst, src, bytes);
-			state[12] += chacha20_advance(bytes, 2);
-			return;
-		}
-	}
-#endif
-	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
-		chacha20_4block_xor_ssse3(state, dst, src, bytes);
-		bytes -= CHACHA_BLOCK_SIZE * 4;
-		src += CHACHA_BLOCK_SIZE * 4;
-		dst += CHACHA_BLOCK_SIZE * 4;
-		state[12] += 4;
-	}
-	if (bytes > CHACHA_BLOCK_SIZE) {
-		chacha20_4block_xor_ssse3(state, dst, src, bytes);
-		state[12] += chacha20_advance(bytes, 4);
-		return;
-	}
-	if (bytes) {
-		chacha20_block_xor_ssse3(state, dst, src, bytes);
-		state[12]++;
-	}
-}
-
-static int chacha20_simd_stream_xor(struct skcipher_request *req,
-				    struct chacha_ctx *ctx, u8 *iv)
-{
-	u32 *state, state_buf[16 + 2] __aligned(8);
-	struct skcipher_walk walk;
-	int err;
-
-	BUILD_BUG_ON(CHACHA20_STATE_ALIGN != 16);
-	state = PTR_ALIGN(state_buf + 0, CHACHA20_STATE_ALIGN);
-
-	err = skcipher_walk_virt(&walk, req, true);
-
-	crypto_chacha_init(state, ctx, iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
-
-		chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
-				nbytes);
-
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-	}
-
-	return err;
-}
-
-static int chacha20_simd(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err;
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !irq_fpu_usable())
-		return crypto_chacha_crypt(req);
-
-	kernel_fpu_begin();
-	err = chacha20_simd_stream_xor(req, ctx, req->iv);
-	kernel_fpu_end();
-	return err;
-}
-
-static int xchacha20_simd(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct chacha_ctx subctx;
-	u32 *state, state_buf[16 + 2] __aligned(8);
-	u8 real_iv[16];
-	int err;
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !irq_fpu_usable())
-		return crypto_xchacha_crypt(req);
-
-	BUILD_BUG_ON(CHACHA20_STATE_ALIGN != 16);
-	state = PTR_ALIGN(state_buf + 0, CHACHA20_STATE_ALIGN);
-	crypto_chacha_init(state, ctx, req->iv);
-
-	kernel_fpu_begin();
-
-	hchacha20_block_ssse3(state, subctx.key);
-
-	memcpy(&real_iv[0], req->iv + 24, 8);
-	memcpy(&real_iv[8], req->iv + 16, 8);
-	err = chacha20_simd_stream_xor(req, &subctx, real_iv);
-
-	kernel_fpu_end();
-
-	return err;
-}
-
-static struct skcipher_alg algs[] = {
-	{
-		.base.cra_name		= "chacha20",
-		.base.cra_driver_name	= "chacha20-simd",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= CHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
-		.encrypt		= chacha20_simd,
-		.decrypt		= chacha20_simd,
-	}, {
-		.base.cra_name		= "xchacha20",
-		.base.cra_driver_name	= "xchacha20-simd",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
-		.encrypt		= xchacha20_simd,
-		.decrypt		= xchacha20_simd,
-	},
-};
-
-static int __init chacha20_simd_mod_init(void)
-{
-	if (!boot_cpu_has(X86_FEATURE_SSSE3))
-		return -ENODEV;
-
-#ifdef CONFIG_AS_AVX2
-	chacha20_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) &&
-			    boot_cpu_has(X86_FEATURE_AVX2) &&
-			    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
-#ifdef CONFIG_AS_AVX512
-	chacha20_use_avx512vl = chacha20_use_avx2 &&
-				boot_cpu_has(X86_FEATURE_AVX512VL) &&
-				boot_cpu_has(X86_FEATURE_AVX512BW); /* kmovq */
-#endif
-#endif
-	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit chacha20_simd_mod_fini(void)
-{
-	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-module_init(chacha20_simd_mod_init);
-module_exit(chacha20_simd_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
-MODULE_DESCRIPTION("chacha20 cipher algorithm, SIMD accelerated");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-simd");
-MODULE_ALIAS_CRYPTO("xchacha20");
-MODULE_ALIAS_CRYPTO("xchacha20-simd");
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
new file mode 100644
index 000000000000..35fd02b50d27
--- /dev/null
+++ b/arch/x86/crypto/chacha_glue.c
@@ -0,0 +1,270 @@
+/*
+ * x64 SIMD accelerated ChaCha and XChaCha stream ciphers,
+ * including ChaCha20 (RFC7539)
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/chacha.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/simd.h>
+
+#define CHACHA_STATE_ALIGN 16
+
+asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
+					unsigned int len, int nrounds);
+asmlinkage void hchacha_block_ssse3(const u32 *state, u32 *out, int nrounds);
+#ifdef CONFIG_AS_AVX2
+asmlinkage void chacha_2block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+asmlinkage void chacha_4block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+asmlinkage void chacha_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+static bool chacha_use_avx2;
+#ifdef CONFIG_AS_AVX512
+asmlinkage void chacha_2block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
+					   unsigned int len, int nrounds);
+asmlinkage void chacha_4block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
+					   unsigned int len, int nrounds);
+asmlinkage void chacha_8block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
+					   unsigned int len, int nrounds);
+static bool chacha_use_avx512vl;
+#endif
+#endif
+
+static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
+{
+	len = min(len, maxblocks * CHACHA_BLOCK_SIZE);
+	return round_up(len, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE;
+}
+
+static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds)
+{
+#ifdef CONFIG_AS_AVX2
+#ifdef CONFIG_AS_AVX512
+	if (chacha_use_avx512vl) {
+		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
+			chacha_8block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			bytes -= CHACHA_BLOCK_SIZE * 8;
+			src += CHACHA_BLOCK_SIZE * 8;
+			dst += CHACHA_BLOCK_SIZE * 8;
+			state[12] += 8;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 4) {
+			chacha_8block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			state[12] += chacha_advance(bytes, 8);
+			return;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 2) {
+			chacha_4block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			state[12] += chacha_advance(bytes, 4);
+			return;
+		}
+		if (bytes) {
+			chacha_2block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			state[12] += chacha_advance(bytes, 2);
+			return;
+		}
+	}
+#endif
+	if (chacha_use_avx2) {
+		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
+			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
+			bytes -= CHACHA_BLOCK_SIZE * 8;
+			src += CHACHA_BLOCK_SIZE * 8;
+			dst += CHACHA_BLOCK_SIZE * 8;
+			state[12] += 8;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 4) {
+			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
+			state[12] += chacha_advance(bytes, 8);
+			return;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 2) {
+			chacha_4block_xor_avx2(state, dst, src, bytes, nrounds);
+			state[12] += chacha_advance(bytes, 4);
+			return;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE) {
+			chacha_2block_xor_avx2(state, dst, src, bytes, nrounds);
+			state[12] += chacha_advance(bytes, 2);
+			return;
+		}
+	}
+#endif
+	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
+		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
+		bytes -= CHACHA_BLOCK_SIZE * 4;
+		src += CHACHA_BLOCK_SIZE * 4;
+		dst += CHACHA_BLOCK_SIZE * 4;
+		state[12] += 4;
+	}
+	if (bytes > CHACHA_BLOCK_SIZE) {
+		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
+		state[12] += chacha_advance(bytes, 4);
+		return;
+	}
+	if (bytes) {
+		chacha_block_xor_ssse3(state, dst, src, bytes, nrounds);
+		state[12]++;
+	}
+}
+
+static int chacha_simd_stream_xor(struct skcipher_request *req,
+				  struct chacha_ctx *ctx, u8 *iv)
+{
+	u32 *state, state_buf[16 + 2] __aligned(8);
+	struct skcipher_walk walk;
+	int err;
+
+	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
+	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	crypto_chacha_init(state, ctx, iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
+
+		chacha_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
+			      nbytes, ctx->nrounds);
+
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+
+	return err;
+}
+
+static int chacha_simd(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !irq_fpu_usable())
+		return crypto_chacha_crypt(req);
+
+	kernel_fpu_begin();
+	err = chacha_simd_stream_xor(req, ctx, req->iv);
+	kernel_fpu_end();
+	return err;
+}
+
+static int xchacha_simd(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct chacha_ctx subctx;
+	u32 *state, state_buf[16 + 2] __aligned(8);
+	u8 real_iv[16];
+	int err;
+
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !irq_fpu_usable())
+		return crypto_xchacha_crypt(req);
+
+	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
+	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
+	crypto_chacha_init(state, ctx, req->iv);
+
+	kernel_fpu_begin();
+
+	hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
+	subctx.nrounds = ctx->nrounds;
+
+	memcpy(&real_iv[0], req->iv + 24, 8);
+	memcpy(&real_iv[8], req->iv + 16, 8);
+	err = chacha_simd_stream_xor(req, &subctx, real_iv);
+
+	kernel_fpu_end();
+
+	return err;
+}
+
+static struct skcipher_alg algs[] = {
+	{
+		.base.cra_name		= "chacha20",
+		.base.cra_driver_name	= "chacha20-simd",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= CHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= crypto_chacha20_setkey,
+		.encrypt		= chacha_simd,
+		.decrypt		= chacha_simd,
+	}, {
+		.base.cra_name		= "xchacha20",
+		.base.cra_driver_name	= "xchacha20-simd",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.setkey			= crypto_chacha20_setkey,
+		.encrypt		= xchacha_simd,
+		.decrypt		= xchacha_simd,
+	},
+};
+
+static int __init chacha_simd_mod_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_SSSE3))
+		return -ENODEV;
+
+#ifdef CONFIG_AS_AVX2
+	chacha_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) &&
+			  boot_cpu_has(X86_FEATURE_AVX2) &&
+			  cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
+#ifdef CONFIG_AS_AVX512
+	chacha_use_avx512vl = chacha_use_avx2 &&
+			      boot_cpu_has(X86_FEATURE_AVX512VL) &&
+			      boot_cpu_has(X86_FEATURE_AVX512BW); /* kmovq */
+#endif
+#endif
+	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit chacha_simd_mod_fini(void)
+{
+	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+module_init(chacha_simd_mod_init);
+module_exit(chacha_simd_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (x64 SIMD accelerated)");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-simd");
+MODULE_ALIAS_CRYPTO("xchacha20");
+MODULE_ALIAS_CRYPTO("xchacha20-simd");
-- 
cgit v1.2.3