Linux-libre 4.3.2-gnu

8 files changed, 2417 insertions, 35 deletions

diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 5a4a089e8..9a2838cf0 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -20,6 +20,7 @@ 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_SALSA20_X86_64) += salsa20-x86_64.o
+obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha20-x86_64.o
 obj-$(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
@@ -30,6 +31,7 @@ obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
 obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
 obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
 obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
+obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
 
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)
@@ -60,6 +62,7 @@ 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
 salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
+chacha20-x86_64-y := chacha20-ssse3-x86_64.o chacha20_glue.o
 serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
 
 ifeq ($(avx_supported),yes)
@@ -75,6 +78,7 @@ 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
 	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
 endif
 
@@ -82,8 +86,10 @@ aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
 aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
 sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
+poly1305-x86_64-y := poly1305-sse2-x86_64.o poly1305_glue.o
 ifeq ($(avx2_supported),yes)
 sha1-ssse3-y += sha1_avx2_x86_64_asm.o
+poly1305-x86_64-y += poly1305-avx2-x86_64.o
 endif
 crc32c-intel-y := crc32c-intel_glue.o
 crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index dccad38b5..3633ad614 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -803,10 +803,7 @@ static int rfc4106_init(struct crypto_aead *aead)
 		return PTR_ERR(cryptd_tfm);
 
 	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(
-		aead,
-		sizeof(struct aead_request) +
-		crypto_aead_reqsize(&cryptd_tfm->base));
+	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
 	return 0;
 }
 
@@ -955,8 +952,8 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
 
 	/* Assuming we are supporting rfc4106 64-bit extended */
 	/* sequence numbers We need to have the AAD length equal */
-	/* to 8 or 12 bytes */
-	if (unlikely(req->assoclen != 8 && req->assoclen != 12))
+	/* to 16 or 20 bytes */
+	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
 		return -EINVAL;
 
 	/* IV below built */
@@ -992,9 +989,9 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
 	}
 
 	kernel_fpu_begin();
-	aesni_gcm_enc_tfm(aes_ctx, dst, src, (unsigned long)req->cryptlen, iv,
-		ctx->hash_subkey, assoc, (unsigned long)req->assoclen, dst
-		+ ((unsigned long)req->cryptlen), auth_tag_len);
+	aesni_gcm_enc_tfm(aes_ctx, dst, src, req->cryptlen, iv,
+			  ctx->hash_subkey, assoc, req->assoclen - 8,
+			  dst + req->cryptlen, auth_tag_len);
 	kernel_fpu_end();
 
 	/* The authTag (aka the Integrity Check Value) needs to be written
@@ -1033,12 +1030,12 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 	struct scatter_walk dst_sg_walk;
 	unsigned int i;
 
-	if (unlikely(req->assoclen != 8 && req->assoclen != 12))
+	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
 		return -EINVAL;
 
 	/* Assuming we are supporting rfc4106 64-bit extended */
 	/* sequence numbers We need to have the AAD length */
-	/* equal to 8 or 12 bytes */
+	/* equal to 16 or 20 bytes */
 
 	tempCipherLen = (unsigned long)(req->cryptlen - auth_tag_len);
 	/* IV below built */
@@ -1075,8 +1072,8 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 
 	kernel_fpu_begin();
 	aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv,
-		ctx->hash_subkey, assoc, (unsigned long)req->assoclen,
-		authTag, auth_tag_len);
+			  ctx->hash_subkey, assoc, req->assoclen - 8,
+			  authTag, auth_tag_len);
 	kernel_fpu_end();
 
 	/* Compare generated tag with passed in tag. */
@@ -1105,19 +1102,12 @@ static int rfc4106_encrypt(struct aead_request *req)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
 	struct cryptd_aead *cryptd_tfm = *ctx;
-	struct aead_request *subreq = aead_request_ctx(req);
 
-	aead_request_set_tfm(subreq, irq_fpu_usable() ?
-				     cryptd_aead_child(cryptd_tfm) :
-				     &cryptd_tfm->base);
+	aead_request_set_tfm(req, irq_fpu_usable() ?
+				  cryptd_aead_child(cryptd_tfm) :
+				  &cryptd_tfm->base);
 
-	aead_request_set_callback(subreq, req->base.flags,
-				  req->base.complete, req->base.data);
-	aead_request_set_crypt(subreq, req->src, req->dst,
-			       req->cryptlen, req->iv);
-	aead_request_set_ad(subreq, req->assoclen);
-
-	return crypto_aead_encrypt(subreq);
+	return crypto_aead_encrypt(req);
 }
 
 static int rfc4106_decrypt(struct aead_request *req)
@@ -1125,19 +1115,12 @@ static int rfc4106_decrypt(struct aead_request *req)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
 	struct cryptd_aead *cryptd_tfm = *ctx;
-	struct aead_request *subreq = aead_request_ctx(req);
-
-	aead_request_set_tfm(subreq, irq_fpu_usable() ?
-				     cryptd_aead_child(cryptd_tfm) :
-				     &cryptd_tfm->base);
 
-	aead_request_set_callback(subreq, req->base.flags,
-				  req->base.complete, req->base.data);
-	aead_request_set_crypt(subreq, req->src, req->dst,
-			       req->cryptlen, req->iv);
-	aead_request_set_ad(subreq, req->assoclen);
+	aead_request_set_tfm(req, irq_fpu_usable() ?
+				  cryptd_aead_child(cryptd_tfm) :
+				  &cryptd_tfm->base);
 
-	return crypto_aead_decrypt(subreq);
+	return crypto_aead_decrypt(req);
 }
 #endif
 
diff --git a/arch/x86/crypto/chacha20-avx2-x86_64.S b/arch/x86/crypto/chacha20-avx2-x86_64.S
new file mode 100644
index 000000000..16694e625
--- /dev/null
+++ b/arch/x86/crypto/chacha20-avx2-x86_64.S
@@ -0,0 +1,443 @@
+/*
+ * 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>
+
+.data
+.align 32
+
+ROT8:	.octa 0x0e0d0c0f0a09080b0605040702010003
+	.octa 0x0e0d0c0f0a09080b0605040702010003
+ROT16:	.octa 0x0d0c0f0e09080b0a0504070601000302
+	.octa 0x0d0c0f0e09080b0a0504070601000302
+CTRINC:	.octa 0x00000003000000020000000100000000
+	.octa 0x00000007000000060000000500000004
+
+.text
+
+ENTRY(chacha20_8block_xor_avx2)
+	# %rdi: Input state matrix, s
+	# %rsi: 8 data blocks output, o
+	# %rdx: 8 data blocks input, i
+
+	# 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
+	mov		%rsp, %r8
+	and		$~31, %rsp
+	sub		$0x80, %rsp
+
+	# 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
+	vmovdqa		0x00(%rsp),%ymm0
+	vperm2i128	$0x20,%ymm4,%ymm0,%ymm1
+	vperm2i128	$0x31,%ymm4,%ymm0,%ymm4
+	vmovdqa		%ymm1,0x00(%rsp)
+	vmovdqa		0x20(%rsp),%ymm0
+	vperm2i128	$0x20,%ymm5,%ymm0,%ymm1
+	vperm2i128	$0x31,%ymm5,%ymm0,%ymm5
+	vmovdqa		%ymm1,0x20(%rsp)
+	vmovdqa		0x40(%rsp),%ymm0
+	vperm2i128	$0x20,%ymm6,%ymm0,%ymm1
+	vperm2i128	$0x31,%ymm6,%ymm0,%ymm6
+	vmovdqa		%ymm1,0x40(%rsp)
+	vmovdqa		0x60(%rsp),%ymm0
+	vperm2i128	$0x20,%ymm7,%ymm0,%ymm1
+	vperm2i128	$0x31,%ymm7,%ymm0,%ymm7
+	vmovdqa		%ymm1,0x60(%rsp)
+	vperm2i128	$0x20,%ymm12,%ymm8,%ymm0
+	vperm2i128	$0x31,%ymm12,%ymm8,%ymm12
+	vmovdqa		%ymm0,%ymm8
+	vperm2i128	$0x20,%ymm13,%ymm9,%ymm0
+	vperm2i128	$0x31,%ymm13,%ymm9,%ymm13
+	vmovdqa		%ymm0,%ymm9
+	vperm2i128	$0x20,%ymm14,%ymm10,%ymm0
+	vperm2i128	$0x31,%ymm14,%ymm10,%ymm14
+	vmovdqa		%ymm0,%ymm10
+	vperm2i128	$0x20,%ymm15,%ymm11,%ymm0
+	vperm2i128	$0x31,%ymm15,%ymm11,%ymm15
+	vmovdqa		%ymm0,%ymm11
+
+	# xor with corresponding input, write to output
+	vmovdqa		0x00(%rsp),%ymm0
+	vpxor		0x0000(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0000(%rsi)
+	vmovdqa		0x20(%rsp),%ymm0
+	vpxor		0x0080(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0080(%rsi)
+	vmovdqa		0x40(%rsp),%ymm0
+	vpxor		0x0040(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x0040(%rsi)
+	vmovdqa		0x60(%rsp),%ymm0
+	vpxor		0x00c0(%rdx),%ymm0,%ymm0
+	vmovdqu		%ymm0,0x00c0(%rsi)
+	vpxor		0x0100(%rdx),%ymm4,%ymm4
+	vmovdqu		%ymm4,0x0100(%rsi)
+	vpxor		0x0180(%rdx),%ymm5,%ymm5
+	vmovdqu		%ymm5,0x00180(%rsi)
+	vpxor		0x0140(%rdx),%ymm6,%ymm6
+	vmovdqu		%ymm6,0x0140(%rsi)
+	vpxor		0x01c0(%rdx),%ymm7,%ymm7
+	vmovdqu		%ymm7,0x01c0(%rsi)
+	vpxor		0x0020(%rdx),%ymm8,%ymm8
+	vmovdqu		%ymm8,0x0020(%rsi)
+	vpxor		0x00a0(%rdx),%ymm9,%ymm9
+	vmovdqu		%ymm9,0x00a0(%rsi)
+	vpxor		0x0060(%rdx),%ymm10,%ymm10
+	vmovdqu		%ymm10,0x0060(%rsi)
+	vpxor		0x00e0(%rdx),%ymm11,%ymm11
+	vmovdqu		%ymm11,0x00e0(%rsi)
+	vpxor		0x0120(%rdx),%ymm12,%ymm12
+	vmovdqu		%ymm12,0x0120(%rsi)
+	vpxor		0x01a0(%rdx),%ymm13,%ymm13
+	vmovdqu		%ymm13,0x01a0(%rsi)
+	vpxor		0x0160(%rdx),%ymm14,%ymm14
+	vmovdqu		%ymm14,0x0160(%rsi)
+	vpxor		0x01e0(%rdx),%ymm15,%ymm15
+	vmovdqu		%ymm15,0x01e0(%rsi)
+
+	vzeroupper
+	mov		%r8,%rsp
+	ret
+ENDPROC(chacha20_8block_xor_avx2)
diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S
new file mode 100644
index 000000000..712b13047
--- /dev/null
+++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S
@@ -0,0 +1,625 @@
+/*
+ * 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>
+
+.data
+.align 16
+
+ROT8:	.octa 0x0e0d0c0f0a09080b0605040702010003
+ROT16:	.octa 0x0d0c0f0e09080b0a0504070601000302
+CTRINC:	.octa 0x00000003000000020000000100000000
+
+.text
+
+ENTRY(chacha20_block_xor_ssse3)
+	# %rdi: Input state matrix, s
+	# %rsi: 1 data block output, o
+	# %rdx: 1 data block input, i
+
+	# This function encrypts one ChaCha20 block by loading the state matrix
+	# in four SSE registers. It performs matrix operation on four words in
+	# parallel, but requireds 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.
+
+	# 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
+
+	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
+
+	# o0 = i0 ^ (x0 + s0)
+	movdqu		0x00(%rdx),%xmm4
+	paddd		%xmm8,%xmm0
+	pxor		%xmm4,%xmm0
+	movdqu		%xmm0,0x00(%rsi)
+	# o1 = i1 ^ (x1 + s1)
+	movdqu		0x10(%rdx),%xmm5
+	paddd		%xmm9,%xmm1
+	pxor		%xmm5,%xmm1
+	movdqu		%xmm1,0x10(%rsi)
+	# o2 = i2 ^ (x2 + s2)
+	movdqu		0x20(%rdx),%xmm6
+	paddd		%xmm10,%xmm2
+	pxor		%xmm6,%xmm2
+	movdqu		%xmm2,0x20(%rsi)
+	# o3 = i3 ^ (x3 + s3)
+	movdqu		0x30(%rdx),%xmm7
+	paddd		%xmm11,%xmm3
+	pxor		%xmm7,%xmm3
+	movdqu		%xmm3,0x30(%rsi)
+
+	ret
+ENDPROC(chacha20_block_xor_ssse3)
+
+ENTRY(chacha20_4block_xor_ssse3)
+	# %rdi: Input state matrix, s
+	# %rsi: 4 data blocks output, o
+	# %rdx: 4 data blocks input, i
+
+	# 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.
+
+	sub		$0x40,%rsp
+
+	# 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
+	movdqu		0x00(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x00(%rsi)
+	movdqa		0x10(%rsp),%xmm0
+	movdqu		0x80(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x80(%rsi)
+	movdqa		0x20(%rsp),%xmm0
+	movdqu		0x40(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0x40(%rsi)
+	movdqa		0x30(%rsp),%xmm0
+	movdqu		0xc0(%rdx),%xmm1
+	pxor		%xmm1,%xmm0
+	movdqu		%xmm0,0xc0(%rsi)
+	movdqu		0x10(%rdx),%xmm1
+	pxor		%xmm1,%xmm4
+	movdqu		%xmm4,0x10(%rsi)
+	movdqu		0x90(%rdx),%xmm1
+	pxor		%xmm1,%xmm5
+	movdqu		%xmm5,0x90(%rsi)
+	movdqu		0x50(%rdx),%xmm1
+	pxor		%xmm1,%xmm6
+	movdqu		%xmm6,0x50(%rsi)
+	movdqu		0xd0(%rdx),%xmm1
+	pxor		%xmm1,%xmm7
+	movdqu		%xmm7,0xd0(%rsi)
+	movdqu		0x20(%rdx),%xmm1
+	pxor		%xmm1,%xmm8
+	movdqu		%xmm8,0x20(%rsi)
+	movdqu		0xa0(%rdx),%xmm1
+	pxor		%xmm1,%xmm9
+	movdqu		%xmm9,0xa0(%rsi)
+	movdqu		0x60(%rdx),%xmm1
+	pxor		%xmm1,%xmm10
+	movdqu		%xmm10,0x60(%rsi)
+	movdqu		0xe0(%rdx),%xmm1
+	pxor		%xmm1,%xmm11
+	movdqu		%xmm11,0xe0(%rsi)
+	movdqu		0x30(%rdx),%xmm1
+	pxor		%xmm1,%xmm12
+	movdqu		%xmm12,0x30(%rsi)
+	movdqu		0xb0(%rdx),%xmm1
+	pxor		%xmm1,%xmm13
+	movdqu		%xmm13,0xb0(%rsi)
+	movdqu		0x70(%rdx),%xmm1
+	pxor		%xmm1,%xmm14
+	movdqu		%xmm14,0x70(%rsi)
+	movdqu		0xf0(%rdx),%xmm1
+	pxor		%xmm1,%xmm15
+	movdqu		%xmm15,0xf0(%rsi)
+
+	add		$0x40,%rsp
+	ret
+ENDPROC(chacha20_4block_xor_ssse3)
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
new file mode 100644
index 000000000..effe2160b
--- /dev/null
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -0,0 +1,150 @@
+/*
+ * 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/chacha20.h>
+#include <linux/crypto.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);
+asmlinkage void chacha20_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src);
+#ifdef CONFIG_AS_AVX2
+asmlinkage void chacha20_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src);
+static bool chacha20_use_avx2;
+#endif
+
+static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src,
+			    unsigned int bytes)
+{
+	u8 buf[CHACHA20_BLOCK_SIZE];
+
+#ifdef CONFIG_AS_AVX2
+	if (chacha20_use_avx2) {
+		while (bytes >= CHACHA20_BLOCK_SIZE * 8) {
+			chacha20_8block_xor_avx2(state, dst, src);
+			bytes -= CHACHA20_BLOCK_SIZE * 8;
+			src += CHACHA20_BLOCK_SIZE * 8;
+			dst += CHACHA20_BLOCK_SIZE * 8;
+			state[12] += 8;
+		}
+	}
+#endif
+	while (bytes >= CHACHA20_BLOCK_SIZE * 4) {
+		chacha20_4block_xor_ssse3(state, dst, src);
+		bytes -= CHACHA20_BLOCK_SIZE * 4;
+		src += CHACHA20_BLOCK_SIZE * 4;
+		dst += CHACHA20_BLOCK_SIZE * 4;
+		state[12] += 4;
+	}
+	while (bytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_block_xor_ssse3(state, dst, src);
+		bytes -= CHACHA20_BLOCK_SIZE;
+		src += CHACHA20_BLOCK_SIZE;
+		dst += CHACHA20_BLOCK_SIZE;
+		state[12]++;
+	}
+	if (bytes) {
+		memcpy(buf, src, bytes);
+		chacha20_block_xor_ssse3(state, buf, buf);
+		memcpy(dst, buf, bytes);
+	}
+}
+
+static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst,
+			 struct scatterlist *src, unsigned int nbytes)
+{
+	u32 *state, state_buf[16 + (CHACHA20_STATE_ALIGN / sizeof(u32)) - 1];
+	struct blkcipher_walk walk;
+	int err;
+
+	if (!may_use_simd())
+		return crypto_chacha20_crypt(desc, dst, src, nbytes);
+
+	state = (u32 *)roundup((uintptr_t)state_buf, CHACHA20_STATE_ALIGN);
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
+
+	crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
+
+	kernel_fpu_begin();
+
+	while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
+				rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % CHACHA20_BLOCK_SIZE);
+	}
+
+	if (walk.nbytes) {
+		chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
+				walk.nbytes);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+
+	kernel_fpu_end();
+
+	return err;
+}
+
+static struct crypto_alg alg = {
+	.cra_name		= "chacha20",
+	.cra_driver_name	= "chacha20-simd",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_ctxsize		= sizeof(struct chacha20_ctx),
+	.cra_alignmask		= sizeof(u32) - 1,
+	.cra_module		= THIS_MODULE,
+	.cra_u			= {
+		.blkcipher = {
+			.min_keysize	= CHACHA20_KEY_SIZE,
+			.max_keysize	= CHACHA20_KEY_SIZE,
+			.ivsize		= CHACHA20_IV_SIZE,
+			.geniv		= "seqiv",
+			.setkey		= crypto_chacha20_setkey,
+			.encrypt	= chacha20_simd,
+			.decrypt	= chacha20_simd,
+		},
+	},
+};
+
+static int __init chacha20_simd_mod_init(void)
+{
+	if (!cpu_has_ssse3)
+		return -ENODEV;
+
+#ifdef CONFIG_AS_AVX2
+	chacha20_use_avx2 = cpu_has_avx && cpu_has_avx2 &&
+			    cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL);
+#endif
+	return crypto_register_alg(&alg);
+}
+
+static void __exit chacha20_simd_mod_fini(void)
+{
+	crypto_unregister_alg(&alg);
+}
+
+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");
diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S
new file mode 100644
index 000000000..eff2f414e
--- /dev/null
+++ b/arch/x86/crypto/poly1305-avx2-x86_64.S
@@ -0,0 +1,386 @@
+/*
+ * Poly1305 authenticator 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>
+
+.data
+.align 32
+
+ANMASK:	.octa 0x0000000003ffffff0000000003ffffff
+	.octa 0x0000000003ffffff0000000003ffffff
+ORMASK:	.octa 0x00000000010000000000000001000000
+	.octa 0x00000000010000000000000001000000
+
+.text
+
+#define h0 0x00(%rdi)
+#define h1 0x04(%rdi)
+#define h2 0x08(%rdi)
+#define h3 0x0c(%rdi)
+#define h4 0x10(%rdi)
+#define r0 0x00(%rdx)
+#define r1 0x04(%rdx)
+#define r2 0x08(%rdx)
+#define r3 0x0c(%rdx)
+#define r4 0x10(%rdx)
+#define u0 0x00(%r8)
+#define u1 0x04(%r8)
+#define u2 0x08(%r8)
+#define u3 0x0c(%r8)
+#define u4 0x10(%r8)
+#define w0 0x14(%r8)
+#define w1 0x18(%r8)
+#define w2 0x1c(%r8)
+#define w3 0x20(%r8)
+#define w4 0x24(%r8)
+#define y0 0x28(%r8)
+#define y1 0x2c(%r8)
+#define y2 0x30(%r8)
+#define y3 0x34(%r8)
+#define y4 0x38(%r8)
+#define m %rsi
+#define hc0 %ymm0
+#define hc1 %ymm1
+#define hc2 %ymm2
+#define hc3 %ymm3
+#define hc4 %ymm4
+#define hc0x %xmm0
+#define hc1x %xmm1
+#define hc2x %xmm2
+#define hc3x %xmm3
+#define hc4x %xmm4
+#define t1 %ymm5
+#define t2 %ymm6
+#define t1x %xmm5
+#define t2x %xmm6
+#define ruwy0 %ymm7
+#define ruwy1 %ymm8
+#define ruwy2 %ymm9
+#define ruwy3 %ymm10
+#define ruwy4 %ymm11
+#define ruwy0x %xmm7
+#define ruwy1x %xmm8
+#define ruwy2x %xmm9
+#define ruwy3x %xmm10
+#define ruwy4x %xmm11
+#define svxz1 %ymm12
+#define svxz2 %ymm13
+#define svxz3 %ymm14
+#define svxz4 %ymm15
+#define d0 %r9
+#define d1 %r10
+#define d2 %r11
+#define d3 %r12
+#define d4 %r13
+
+ENTRY(poly1305_4block_avx2)
+	# %rdi: Accumulator h[5]
+	# %rsi: 64 byte input block m
+	# %rdx: Poly1305 key r[5]
+	# %rcx: Quadblock count
+	# %r8:  Poly1305 derived key r^2 u[5], r^3 w[5], r^4 y[5],
+
+	# This four-block variant uses loop unrolled block processing. It
+	# requires 4 Poly1305 keys: r, r^2, r^3 and r^4:
+	# h = (h + m) * r  =>  h = (h + m1) * r^4 + m2 * r^3 + m3 * r^2 + m4 * r
+
+	vzeroupper
+	push		%rbx
+	push		%r12
+	push		%r13
+
+	# combine r0,u0,w0,y0
+	vmovd		y0,ruwy0x
+	vmovd		w0,t1x
+	vpunpcklqdq	t1,ruwy0,ruwy0
+	vmovd		u0,t1x
+	vmovd		r0,t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,ruwy0,ruwy0
+
+	# combine r1,u1,w1,y1 and s1=r1*5,v1=u1*5,x1=w1*5,z1=y1*5
+	vmovd		y1,ruwy1x
+	vmovd		w1,t1x
+	vpunpcklqdq	t1,ruwy1,ruwy1
+	vmovd		u1,t1x
+	vmovd		r1,t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,ruwy1,ruwy1
+	vpslld		$2,ruwy1,svxz1
+	vpaddd		ruwy1,svxz1,svxz1
+
+	# combine r2,u2,w2,y2 and s2=r2*5,v2=u2*5,x2=w2*5,z2=y2*5
+	vmovd		y2,ruwy2x
+	vmovd		w2,t1x
+	vpunpcklqdq	t1,ruwy2,ruwy2
+	vmovd		u2,t1x
+	vmovd		r2,t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,ruwy2,ruwy2
+	vpslld		$2,ruwy2,svxz2
+	vpaddd		ruwy2,svxz2,svxz2
+
+	# combine r3,u3,w3,y3 and s3=r3*5,v3=u3*5,x3=w3*5,z3=y3*5
+	vmovd		y3,ruwy3x
+	vmovd		w3,t1x
+	vpunpcklqdq	t1,ruwy3,ruwy3
+	vmovd		u3,t1x
+	vmovd		r3,t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,ruwy3,ruwy3
+	vpslld		$2,ruwy3,svxz3
+	vpaddd		ruwy3,svxz3,svxz3
+
+	# combine r4,u4,w4,y4 and s4=r4*5,v4=u4*5,x4=w4*5,z4=y4*5
+	vmovd		y4,ruwy4x
+	vmovd		w4,t1x
+	vpunpcklqdq	t1,ruwy4,ruwy4
+	vmovd		u4,t1x
+	vmovd		r4,t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,ruwy4,ruwy4
+	vpslld		$2,ruwy4,svxz4
+	vpaddd		ruwy4,svxz4,svxz4
+
+.Ldoblock4:
+	# hc0 = [m[48-51] & 0x3ffffff, m[32-35] & 0x3ffffff,
+	#	 m[16-19] & 0x3ffffff, m[ 0- 3] & 0x3ffffff + h0]
+	vmovd		0x00(m),hc0x
+	vmovd		0x10(m),t1x
+	vpunpcklqdq	t1,hc0,hc0
+	vmovd		0x20(m),t1x
+	vmovd		0x30(m),t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,hc0,hc0
+	vpand		ANMASK(%rip),hc0,hc0
+	vmovd		h0,t1x
+	vpaddd		t1,hc0,hc0
+	# hc1 = [(m[51-54] >> 2) & 0x3ffffff, (m[35-38] >> 2) & 0x3ffffff,
+	#	 (m[19-22] >> 2) & 0x3ffffff, (m[ 3- 6] >> 2) & 0x3ffffff + h1]
+	vmovd		0x03(m),hc1x
+	vmovd		0x13(m),t1x
+	vpunpcklqdq	t1,hc1,hc1
+	vmovd		0x23(m),t1x
+	vmovd		0x33(m),t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,hc1,hc1
+	vpsrld		$2,hc1,hc1
+	vpand		ANMASK(%rip),hc1,hc1
+	vmovd		h1,t1x
+	vpaddd		t1,hc1,hc1
+	# hc2 = [(m[54-57] >> 4) & 0x3ffffff, (m[38-41] >> 4) & 0x3ffffff,
+	#	 (m[22-25] >> 4) & 0x3ffffff, (m[ 6- 9] >> 4) & 0x3ffffff + h2]
+	vmovd		0x06(m),hc2x
+	vmovd		0x16(m),t1x
+	vpunpcklqdq	t1,hc2,hc2
+	vmovd		0x26(m),t1x
+	vmovd		0x36(m),t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,hc2,hc2
+	vpsrld		$4,hc2,hc2
+	vpand		ANMASK(%rip),hc2,hc2
+	vmovd		h2,t1x
+	vpaddd		t1,hc2,hc2
+	# hc3 = [(m[57-60] >> 6) & 0x3ffffff, (m[41-44] >> 6) & 0x3ffffff,
+	#	 (m[25-28] >> 6) & 0x3ffffff, (m[ 9-12] >> 6) & 0x3ffffff + h3]
+	vmovd		0x09(m),hc3x
+	vmovd		0x19(m),t1x
+	vpunpcklqdq	t1,hc3,hc3
+	vmovd		0x29(m),t1x
+	vmovd		0x39(m),t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,hc3,hc3
+	vpsrld		$6,hc3,hc3
+	vpand		ANMASK(%rip),hc3,hc3
+	vmovd		h3,t1x
+	vpaddd		t1,hc3,hc3
+	# hc4 = [(m[60-63] >> 8) | (1<<24), (m[44-47] >> 8) | (1<<24),
+	#	 (m[28-31] >> 8) | (1<<24), (m[12-15] >> 8) | (1<<24) + h4]
+	vmovd		0x0c(m),hc4x
+	vmovd		0x1c(m),t1x
+	vpunpcklqdq	t1,hc4,hc4
+	vmovd		0x2c(m),t1x
+	vmovd		0x3c(m),t2x
+	vpunpcklqdq	t2,t1,t1
+	vperm2i128	$0x20,t1,hc4,hc4
+	vpsrld		$8,hc4,hc4
+	vpor		ORMASK(%rip),hc4,hc4
+	vmovd		h4,t1x
+	vpaddd		t1,hc4,hc4
+
+	# t1 = [ hc0[3] * r0, hc0[2] * u0, hc0[1] * w0, hc0[0] * y0 ]
+	vpmuludq	hc0,ruwy0,t1
+	# t1 += [ hc1[3] * s4, hc1[2] * v4, hc1[1] * x4, hc1[0] * z4 ]
+	vpmuludq	hc1,svxz4,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc2[3] * s3, hc2[2] * v3, hc2[1] * x3, hc2[0] * z3 ]
+	vpmuludq	hc2,svxz3,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc3[3] * s2, hc3[2] * v2, hc3[1] * x2, hc3[0] * z2 ]
+	vpmuludq	hc3,svxz2,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc4[3] * s1, hc4[2] * v1, hc4[1] * x1, hc4[0] * z1 ]
+	vpmuludq	hc4,svxz1,t2
+	vpaddq		t2,t1,t1
+	# d0 = t1[0] + t1[1] + t[2] + t[3]
+	vpermq		$0xee,t1,t2
+	vpaddq		t2,t1,t1
+	vpsrldq		$8,t1,t2
+	vpaddq		t2,t1,t1
+	vmovq		t1x,d0
+
+	# t1 = [ hc0[3] * r1, hc0[2] * u1,hc0[1] * w1, hc0[0] * y1 ]
+	vpmuludq	hc0,ruwy1,t1
+	# t1 += [ hc1[3] * r0, hc1[2] * u0, hc1[1] * w0, hc1[0] * y0 ]
+	vpmuludq	hc1,ruwy0,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc2[3] * s4, hc2[2] * v4, hc2[1] * x4, hc2[0] * z4 ]
+	vpmuludq	hc2,svxz4,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc3[3] * s3, hc3[2] * v3, hc3[1] * x3, hc3[0] * z3 ]
+	vpmuludq	hc3,svxz3,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc4[3] * s2, hc4[2] * v2, hc4[1] * x2, hc4[0] * z2 ]
+	vpmuludq	hc4,svxz2,t2
+	vpaddq		t2,t1,t1
+	# d1 = t1[0] + t1[1] + t1[3] + t1[4]
+	vpermq		$0xee,t1,t2
+	vpaddq		t2,t1,t1
+	vpsrldq		$8,t1,t2
+	vpaddq		t2,t1,t1
+	vmovq		t1x,d1
+
+	# t1 = [ hc0[3] * r2, hc0[2] * u2, hc0[1] * w2, hc0[0] * y2 ]
+	vpmuludq	hc0,ruwy2,t1
+	# t1 += [ hc1[3] * r1, hc1[2] * u1, hc1[1] * w1, hc1[0] * y1 ]
+	vpmuludq	hc1,ruwy1,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc2[3] * r0, hc2[2] * u0, hc2[1] * w0, hc2[0] * y0 ]
+	vpmuludq	hc2,ruwy0,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc3[3] * s4, hc3[2] * v4, hc3[1] * x4, hc3[0] * z4 ]
+	vpmuludq	hc3,svxz4,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc4[3] * s3, hc4[2] * v3, hc4[1] * x3, hc4[0] * z3 ]
+	vpmuludq	hc4,svxz3,t2
+	vpaddq		t2,t1,t1
+	# d2 = t1[0] + t1[1] + t1[2] + t1[3]
+	vpermq		$0xee,t1,t2
+	vpaddq		t2,t1,t1
+	vpsrldq		$8,t1,t2
+	vpaddq		t2,t1,t1
+	vmovq		t1x,d2
+
+	# t1 = [ hc0[3] * r3, hc0[2] * u3, hc0[1] * w3, hc0[0] * y3 ]
+	vpmuludq	hc0,ruwy3,t1
+	# t1 += [ hc1[3] * r2, hc1[2] * u2, hc1[1] * w2, hc1[0] * y2 ]
+	vpmuludq	hc1,ruwy2,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc2[3] * r1, hc2[2] * u1, hc2[1] * w1, hc2[0] * y1 ]
+	vpmuludq	hc2,ruwy1,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc3[3] * r0, hc3[2] * u0, hc3[1] * w0, hc3[0] * y0 ]
+	vpmuludq	hc3,ruwy0,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc4[3] * s4, hc4[2] * v4, hc4[1] * x4, hc4[0] * z4 ]
+	vpmuludq	hc4,svxz4,t2
+	vpaddq		t2,t1,t1
+	# d3 = t1[0] + t1[1] + t1[2] + t1[3]
+	vpermq		$0xee,t1,t2
+	vpaddq		t2,t1,t1
+	vpsrldq		$8,t1,t2
+	vpaddq		t2,t1,t1
+	vmovq		t1x,d3
+
+	# t1 = [ hc0[3] * r4, hc0[2] * u4, hc0[1] * w4, hc0[0] * y4 ]
+	vpmuludq	hc0,ruwy4,t1
+	# t1 += [ hc1[3] * r3, hc1[2] * u3, hc1[1] * w3, hc1[0] * y3 ]
+	vpmuludq	hc1,ruwy3,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc2[3] * r2, hc2[2] * u2, hc2[1] * w2, hc2[0] * y2 ]
+	vpmuludq	hc2,ruwy2,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc3[3] * r1, hc3[2] * u1, hc3[1] * w1, hc3[0] * y1 ]
+	vpmuludq	hc3,ruwy1,t2
+	vpaddq		t2,t1,t1
+	# t1 += [ hc4[3] * r0, hc4[2] * u0, hc4[1] * w0, hc4[0] * y0 ]
+	vpmuludq	hc4,ruwy0,t2
+	vpaddq		t2,t1,t1
+	# d4 = t1[0] + t1[1] + t1[2] + t1[3]
+	vpermq		$0xee,t1,t2
+	vpaddq		t2,t1,t1
+	vpsrldq		$8,t1,t2
+	vpaddq		t2,t1,t1
+	vmovq		t1x,d4
+
+	# d1 += d0 >> 26
+	mov		d0,%rax
+	shr		$26,%rax
+	add		%rax,d1
+	# h0 = d0 & 0x3ffffff
+	mov		d0,%rbx
+	and		$0x3ffffff,%ebx
+
+	# d2 += d1 >> 26
+	mov		d1,%rax
+	shr		$26,%rax
+	add		%rax,d2
+	# h1 = d1 & 0x3ffffff
+	mov		d1,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h1
+
+	# d3 += d2 >> 26
+	mov		d2,%rax
+	shr		$26,%rax
+	add		%rax,d3
+	# h2 = d2 & 0x3ffffff
+	mov		d2,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h2
+
+	# d4 += d3 >> 26
+	mov		d3,%rax
+	shr		$26,%rax
+	add		%rax,d4
+	# h3 = d3 & 0x3ffffff
+	mov		d3,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h3
+
+	# h0 += (d4 >> 26) * 5
+	mov		d4,%rax
+	shr		$26,%rax
+	lea		(%eax,%eax,4),%eax
+	add		%eax,%ebx
+	# h4 = d4 & 0x3ffffff
+	mov		d4,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h4
+
+	# h1 += h0 >> 26
+	mov		%ebx,%eax
+	shr		$26,%eax
+	add		%eax,h1
+	# h0 = h0 & 0x3ffffff
+	andl		$0x3ffffff,%ebx
+	mov		%ebx,h0
+
+	add		$0x40,m
+	dec		%rcx
+	jnz		.Ldoblock4
+
+	vzeroupper
+	pop		%r13
+	pop		%r12
+	pop		%rbx
+	ret
+ENDPROC(poly1305_4block_avx2)
diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S
new file mode 100644
index 000000000..338c74805
--- /dev/null
+++ b/arch/x86/crypto/poly1305-sse2-x86_64.S
@@ -0,0 +1,582 @@
+/*
+ * Poly1305 authenticator algorithm, RFC7539, x64 SSE2 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>
+
+.data
+.align 16
+
+ANMASK:	.octa 0x0000000003ffffff0000000003ffffff
+ORMASK:	.octa 0x00000000010000000000000001000000
+
+.text
+
+#define h0 0x00(%rdi)
+#define h1 0x04(%rdi)
+#define h2 0x08(%rdi)
+#define h3 0x0c(%rdi)
+#define h4 0x10(%rdi)
+#define r0 0x00(%rdx)
+#define r1 0x04(%rdx)
+#define r2 0x08(%rdx)
+#define r3 0x0c(%rdx)
+#define r4 0x10(%rdx)
+#define s1 0x00(%rsp)
+#define s2 0x04(%rsp)
+#define s3 0x08(%rsp)
+#define s4 0x0c(%rsp)
+#define m %rsi
+#define h01 %xmm0
+#define h23 %xmm1
+#define h44 %xmm2
+#define t1 %xmm3
+#define t2 %xmm4
+#define t3 %xmm5
+#define t4 %xmm6
+#define mask %xmm7
+#define d0 %r8
+#define d1 %r9
+#define d2 %r10
+#define d3 %r11
+#define d4 %r12
+
+ENTRY(poly1305_block_sse2)
+	# %rdi: Accumulator h[5]
+	# %rsi: 16 byte input block m
+	# %rdx: Poly1305 key r[5]
+	# %rcx: Block count
+
+	# This single block variant tries to improve performance by doing two
+	# multiplications in parallel using SSE instructions. There is quite
+	# some quardword packing involved, hence the speedup is marginal.
+
+	push		%rbx
+	push		%r12
+	sub		$0x10,%rsp
+
+	# s1..s4 = r1..r4 * 5
+	mov		r1,%eax
+	lea		(%eax,%eax,4),%eax
+	mov		%eax,s1
+	mov		r2,%eax
+	lea		(%eax,%eax,4),%eax
+	mov		%eax,s2
+	mov		r3,%eax
+	lea		(%eax,%eax,4),%eax
+	mov		%eax,s3
+	mov		r4,%eax
+	lea		(%eax,%eax,4),%eax
+	mov		%eax,s4
+
+	movdqa		ANMASK(%rip),mask
+
+.Ldoblock:
+	# h01 = [0, h1, 0, h0]
+	# h23 = [0, h3, 0, h2]
+	# h44 = [0, h4, 0, h4]
+	movd		h0,h01
+	movd		h1,t1
+	movd		h2,h23
+	movd		h3,t2
+	movd		h4,h44
+	punpcklqdq	t1,h01
+	punpcklqdq	t2,h23
+	punpcklqdq	h44,h44
+
+	# h01 += [ (m[3-6] >> 2) & 0x3ffffff, m[0-3] & 0x3ffffff ]
+	movd		0x00(m),t1
+	movd		0x03(m),t2
+	psrld		$2,t2
+	punpcklqdq	t2,t1
+	pand		mask,t1
+	paddd		t1,h01
+	# h23 += [ (m[9-12] >> 6) & 0x3ffffff, (m[6-9] >> 4) & 0x3ffffff ]
+	movd		0x06(m),t1
+	movd		0x09(m),t2
+	psrld		$4,t1
+	psrld		$6,t2
+	punpcklqdq	t2,t1
+	pand		mask,t1
+	paddd		t1,h23
+	# h44 += [ (m[12-15] >> 8) | (1 << 24), (m[12-15] >> 8) | (1 << 24) ]
+	mov		0x0c(m),%eax
+	shr		$8,%eax
+	or		$0x01000000,%eax
+	movd		%eax,t1
+	pshufd		$0xc4,t1,t1
+	paddd		t1,h44
+
+	# t1[0] = h0 * r0 + h2 * s3
+	# t1[1] = h1 * s4 + h3 * s2
+	movd		r0,t1
+	movd		s4,t2
+	punpcklqdq	t2,t1
+	pmuludq		h01,t1
+	movd		s3,t2
+	movd		s2,t3
+	punpcklqdq	t3,t2
+	pmuludq		h23,t2
+	paddq		t2,t1
+	# t2[0] = h0 * r1 + h2 * s4
+	# t2[1] = h1 * r0 + h3 * s3
+	movd		r1,t2
+	movd		r0,t3
+	punpcklqdq	t3,t2
+	pmuludq		h01,t2
+	movd		s4,t3
+	movd		s3,t4
+	punpcklqdq	t4,t3
+	pmuludq		h23,t3
+	paddq		t3,t2
+	# t3[0] = h4 * s1
+	# t3[1] = h4 * s2
+	movd		s1,t3
+	movd		s2,t4
+	punpcklqdq	t4,t3
+	pmuludq		h44,t3
+	# d0 = t1[0] + t1[1] + t3[0]
+	# d1 = t2[0] + t2[1] + t3[1]
+	movdqa		t1,t4
+	punpcklqdq	t2,t4
+	punpckhqdq	t2,t1
+	paddq		t4,t1
+	paddq		t3,t1
+	movq		t1,d0
+	psrldq		$8,t1
+	movq		t1,d1
+
+	# t1[0] = h0 * r2 + h2 * r0
+	# t1[1] = h1 * r1 + h3 * s4
+	movd		r2,t1
+	movd		r1,t2
+	punpcklqdq 	t2,t1
+	pmuludq		h01,t1
+	movd		r0,t2
+	movd		s4,t3
+	punpcklqdq	t3,t2
+	pmuludq		h23,t2
+	paddq		t2,t1
+	# t2[0] = h0 * r3 + h2 * r1
+	# t2[1] = h1 * r2 + h3 * r0
+	movd		r3,t2
+	movd		r2,t3
+	punpcklqdq	t3,t2
+	pmuludq		h01,t2
+	movd		r1,t3
+	movd		r0,t4
+	punpcklqdq	t4,t3
+	pmuludq		h23,t3
+	paddq		t3,t2
+	# t3[0] = h4 * s3
+	# t3[1] = h4 * s4
+	movd		s3,t3
+	movd		s4,t4
+	punpcklqdq	t4,t3
+	pmuludq		h44,t3
+	# d2 = t1[0] + t1[1] + t3[0]
+	# d3 = t2[0] + t2[1] + t3[1]
+	movdqa		t1,t4
+	punpcklqdq	t2,t4
+	punpckhqdq	t2,t1
+	paddq		t4,t1
+	paddq		t3,t1
+	movq		t1,d2
+	psrldq		$8,t1
+	movq		t1,d3
+
+	# t1[0] = h0 * r4 + h2 * r2
+	# t1[1] = h1 * r3 + h3 * r1
+	movd		r4,t1
+	movd		r3,t2
+	punpcklqdq	t2,t1
+	pmuludq		h01,t1
+	movd		r2,t2
+	movd		r1,t3
+	punpcklqdq	t3,t2
+	pmuludq		h23,t2
+	paddq		t2,t1
+	# t3[0] = h4 * r0
+	movd		r0,t3
+	pmuludq		h44,t3
+	# d4 = t1[0] + t1[1] + t3[0]
+	movdqa		t1,t4
+	psrldq		$8,t4
+	paddq		t4,t1
+	paddq		t3,t1
+	movq		t1,d4
+
+	# d1 += d0 >> 26
+	mov		d0,%rax
+	shr		$26,%rax
+	add		%rax,d1
+	# h0 = d0 & 0x3ffffff
+	mov		d0,%rbx
+	and		$0x3ffffff,%ebx
+
+	# d2 += d1 >> 26
+	mov		d1,%rax
+	shr		$26,%rax
+	add		%rax,d2
+	# h1 = d1 & 0x3ffffff
+	mov		d1,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h1
+
+	# d3 += d2 >> 26
+	mov		d2,%rax
+	shr		$26,%rax
+	add		%rax,d3
+	# h2 = d2 & 0x3ffffff
+	mov		d2,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h2
+
+	# d4 += d3 >> 26
+	mov		d3,%rax
+	shr		$26,%rax
+	add		%rax,d4
+	# h3 = d3 & 0x3ffffff
+	mov		d3,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h3
+
+	# h0 += (d4 >> 26) * 5
+	mov		d4,%rax
+	shr		$26,%rax
+	lea		(%eax,%eax,4),%eax
+	add		%eax,%ebx
+	# h4 = d4 & 0x3ffffff
+	mov		d4,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h4
+
+	# h1 += h0 >> 26
+	mov		%ebx,%eax
+	shr		$26,%eax
+	add		%eax,h1
+	# h0 = h0 & 0x3ffffff
+	andl		$0x3ffffff,%ebx
+	mov		%ebx,h0
+
+	add		$0x10,m
+	dec		%rcx
+	jnz		.Ldoblock
+
+	add		$0x10,%rsp
+	pop		%r12
+	pop		%rbx
+	ret
+ENDPROC(poly1305_block_sse2)
+
+
+#define u0 0x00(%r8)
+#define u1 0x04(%r8)
+#define u2 0x08(%r8)
+#define u3 0x0c(%r8)
+#define u4 0x10(%r8)
+#define hc0 %xmm0
+#define hc1 %xmm1
+#define hc2 %xmm2
+#define hc3 %xmm5
+#define hc4 %xmm6
+#define ru0 %xmm7
+#define ru1 %xmm8
+#define ru2 %xmm9
+#define ru3 %xmm10
+#define ru4 %xmm11
+#define sv1 %xmm12
+#define sv2 %xmm13
+#define sv3 %xmm14
+#define sv4 %xmm15
+#undef d0
+#define d0 %r13
+
+ENTRY(poly1305_2block_sse2)
+	# %rdi: Accumulator h[5]
+	# %rsi: 16 byte input block m
+	# %rdx: Poly1305 key r[5]
+	# %rcx: Doubleblock count
+	# %r8:  Poly1305 derived key r^2 u[5]
+
+	# This two-block variant further improves performance by using loop
+	# unrolled block processing. This is more straight forward and does
+	# less byte shuffling, but requires a second Poly1305 key r^2:
+	# h = (h + m) * r    =>    h = (h + m1) * r^2 + m2 * r
+
+	push		%rbx
+	push		%r12
+	push		%r13
+
+	# combine r0,u0
+	movd		u0,ru0
+	movd		r0,t1
+	punpcklqdq	t1,ru0
+
+	# combine r1,u1 and s1=r1*5,v1=u1*5
+	movd		u1,ru1
+	movd		r1,t1
+	punpcklqdq	t1,ru1
+	movdqa		ru1,sv1
+	pslld		$2,sv1
+	paddd		ru1,sv1
+
+	# combine r2,u2 and s2=r2*5,v2=u2*5
+	movd		u2,ru2
+	movd		r2,t1
+	punpcklqdq	t1,ru2
+	movdqa		ru2,sv2
+	pslld		$2,sv2
+	paddd		ru2,sv2
+
+	# combine r3,u3 and s3=r3*5,v3=u3*5
+	movd		u3,ru3
+	movd		r3,t1
+	punpcklqdq	t1,ru3
+	movdqa		ru3,sv3
+	pslld		$2,sv3
+	paddd		ru3,sv3
+
+	# combine r4,u4 and s4=r4*5,v4=u4*5
+	movd		u4,ru4
+	movd		r4,t1
+	punpcklqdq	t1,ru4
+	movdqa		ru4,sv4
+	pslld		$2,sv4
+	paddd		ru4,sv4
+
+.Ldoblock2:
+	# hc0 = [ m[16-19] & 0x3ffffff, h0 + m[0-3] & 0x3ffffff ]
+	movd		0x00(m),hc0
+	movd		0x10(m),t1
+	punpcklqdq	t1,hc0
+	pand		ANMASK(%rip),hc0
+	movd		h0,t1
+	paddd		t1,hc0
+	# hc1 = [ (m[19-22] >> 2) & 0x3ffffff, h1 + (m[3-6] >> 2) & 0x3ffffff ]
+	movd		0x03(m),hc1
+	movd		0x13(m),t1
+	punpcklqdq	t1,hc1
+	psrld		$2,hc1
+	pand		ANMASK(%rip),hc1
+	movd		h1,t1
+	paddd		t1,hc1
+	# hc2 = [ (m[22-25] >> 4) & 0x3ffffff, h2 + (m[6-9] >> 4) & 0x3ffffff ]
+	movd		0x06(m),hc2
+	movd		0x16(m),t1
+	punpcklqdq	t1,hc2
+	psrld		$4,hc2
+	pand		ANMASK(%rip),hc2
+	movd		h2,t1
+	paddd		t1,hc2
+	# hc3 = [ (m[25-28] >> 6) & 0x3ffffff, h3 + (m[9-12] >> 6) & 0x3ffffff ]
+	movd		0x09(m),hc3
+	movd		0x19(m),t1
+	punpcklqdq	t1,hc3
+	psrld		$6,hc3
+	pand		ANMASK(%rip),hc3
+	movd		h3,t1
+	paddd		t1,hc3
+	# hc4 = [ (m[28-31] >> 8) | (1<<24), h4 + (m[12-15] >> 8) | (1<<24) ]
+	movd		0x0c(m),hc4
+	movd		0x1c(m),t1
+	punpcklqdq	t1,hc4
+	psrld		$8,hc4
+	por		ORMASK(%rip),hc4
+	movd		h4,t1
+	paddd		t1,hc4
+
+	# t1 = [ hc0[1] * r0, hc0[0] * u0 ]
+	movdqa		ru0,t1
+	pmuludq		hc0,t1
+	# t1 += [ hc1[1] * s4, hc1[0] * v4 ]
+	movdqa		sv4,t2
+	pmuludq		hc1,t2
+	paddq		t2,t1
+	# t1 += [ hc2[1] * s3, hc2[0] * v3 ]
+	movdqa		sv3,t2
+	pmuludq		hc2,t2
+	paddq		t2,t1
+	# t1 += [ hc3[1] * s2, hc3[0] * v2 ]
+	movdqa		sv2,t2
+	pmuludq		hc3,t2
+	paddq		t2,t1
+	# t1 += [ hc4[1] * s1, hc4[0] * v1 ]
+	movdqa		sv1,t2
+	pmuludq		hc4,t2
+	paddq		t2,t1
+	# d0 = t1[0] + t1[1]
+	movdqa		t1,t2
+	psrldq		$8,t2
+	paddq		t2,t1
+	movq		t1,d0
+
+	# t1 = [ hc0[1] * r1, hc0[0] * u1 ]
+	movdqa		ru1,t1
+	pmuludq		hc0,t1
+	# t1 += [ hc1[1] * r0, hc1[0] * u0 ]
+	movdqa		ru0,t2
+	pmuludq		hc1,t2
+	paddq		t2,t1
+	# t1 += [ hc2[1] * s4, hc2[0] * v4 ]
+	movdqa		sv4,t2
+	pmuludq		hc2,t2
+	paddq		t2,t1
+	# t1 += [ hc3[1] * s3, hc3[0] * v3 ]
+	movdqa		sv3,t2
+	pmuludq		hc3,t2
+	paddq		t2,t1
+	# t1 += [ hc4[1] * s2, hc4[0] * v2 ]
+	movdqa		sv2,t2
+	pmuludq		hc4,t2
+	paddq		t2,t1
+	# d1 = t1[0] + t1[1]
+	movdqa		t1,t2
+	psrldq		$8,t2
+	paddq		t2,t1
+	movq		t1,d1
+
+	# t1 = [ hc0[1] * r2, hc0[0] * u2 ]
+	movdqa		ru2,t1
+	pmuludq		hc0,t1
+	# t1 += [ hc1[1] * r1, hc1[0] * u1 ]
+	movdqa		ru1,t2
+	pmuludq		hc1,t2
+	paddq		t2,t1
+	# t1 += [ hc2[1] * r0, hc2[0] * u0 ]
+	movdqa		ru0,t2
+	pmuludq		hc2,t2
+	paddq		t2,t1
+	# t1 += [ hc3[1] * s4, hc3[0] * v4 ]
+	movdqa		sv4,t2
+	pmuludq		hc3,t2
+	paddq		t2,t1
+	# t1 += [ hc4[1] * s3, hc4[0] * v3 ]
+	movdqa		sv3,t2
+	pmuludq		hc4,t2
+	paddq		t2,t1
+	# d2 = t1[0] + t1[1]
+	movdqa		t1,t2
+	psrldq		$8,t2
+	paddq		t2,t1
+	movq		t1,d2
+
+	# t1 = [ hc0[1] * r3, hc0[0] * u3 ]
+	movdqa		ru3,t1
+	pmuludq		hc0,t1
+	# t1 += [ hc1[1] * r2, hc1[0] * u2 ]
+	movdqa		ru2,t2
+	pmuludq		hc1,t2
+	paddq		t2,t1
+	# t1 += [ hc2[1] * r1, hc2[0] * u1 ]
+	movdqa		ru1,t2
+	pmuludq		hc2,t2
+	paddq		t2,t1
+	# t1 += [ hc3[1] * r0, hc3[0] * u0 ]
+	movdqa		ru0,t2
+	pmuludq		hc3,t2
+	paddq		t2,t1
+	# t1 += [ hc4[1] * s4, hc4[0] * v4 ]
+	movdqa		sv4,t2
+	pmuludq		hc4,t2
+	paddq		t2,t1
+	# d3 = t1[0] + t1[1]
+	movdqa		t1,t2
+	psrldq		$8,t2
+	paddq		t2,t1
+	movq		t1,d3
+
+	# t1 = [ hc0[1] * r4, hc0[0] * u4 ]
+	movdqa		ru4,t1
+	pmuludq		hc0,t1
+	# t1 += [ hc1[1] * r3, hc1[0] * u3 ]
+	movdqa		ru3,t2
+	pmuludq		hc1,t2
+	paddq		t2,t1
+	# t1 += [ hc2[1] * r2, hc2[0] * u2 ]
+	movdqa		ru2,t2
+	pmuludq		hc2,t2
+	paddq		t2,t1
+	# t1 += [ hc3[1] * r1, hc3[0] * u1 ]
+	movdqa		ru1,t2
+	pmuludq		hc3,t2
+	paddq		t2,t1
+	# t1 += [ hc4[1] * r0, hc4[0] * u0 ]
+	movdqa		ru0,t2
+	pmuludq		hc4,t2
+	paddq		t2,t1
+	# d4 = t1[0] + t1[1]
+	movdqa		t1,t2
+	psrldq		$8,t2
+	paddq		t2,t1
+	movq		t1,d4
+
+	# d1 += d0 >> 26
+	mov		d0,%rax
+	shr		$26,%rax
+	add		%rax,d1
+	# h0 = d0 & 0x3ffffff
+	mov		d0,%rbx
+	and		$0x3ffffff,%ebx
+
+	# d2 += d1 >> 26
+	mov		d1,%rax
+	shr		$26,%rax
+	add		%rax,d2
+	# h1 = d1 & 0x3ffffff
+	mov		d1,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h1
+
+	# d3 += d2 >> 26
+	mov		d2,%rax
+	shr		$26,%rax
+	add		%rax,d3
+	# h2 = d2 & 0x3ffffff
+	mov		d2,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h2
+
+	# d4 += d3 >> 26
+	mov		d3,%rax
+	shr		$26,%rax
+	add		%rax,d4
+	# h3 = d3 & 0x3ffffff
+	mov		d3,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h3
+
+	# h0 += (d4 >> 26) * 5
+	mov		d4,%rax
+	shr		$26,%rax
+	lea		(%eax,%eax,4),%eax
+	add		%eax,%ebx
+	# h4 = d4 & 0x3ffffff
+	mov		d4,%rax
+	and		$0x3ffffff,%eax
+	mov		%eax,h4
+
+	# h1 += h0 >> 26
+	mov		%ebx,%eax
+	shr		$26,%eax
+	add		%eax,h1
+	# h0 = h0 & 0x3ffffff
+	andl		$0x3ffffff,%ebx
+	mov		%ebx,h0
+
+	add		$0x20,m
+	dec		%rcx
+	jnz		.Ldoblock2
+
+	pop		%r13
+	pop		%r12
+	pop		%rbx
+	ret
+ENDPROC(poly1305_2block_sse2)
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
new file mode 100644
index 000000000..f7170d764
--- /dev/null
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -0,0 +1,207 @@
+/*
+ * Poly1305 authenticator 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/internal/hash.h>
+#include <crypto/poly1305.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+#include <asm/simd.h>
+
+struct poly1305_simd_desc_ctx {
+	struct poly1305_desc_ctx base;
+	/* derived key u set? */
+	bool uset;
+#ifdef CONFIG_AS_AVX2
+	/* derived keys r^3, r^4 set? */
+	bool wset;
+#endif
+	/* derived Poly1305 key r^2 */
+	u32 u[5];
+	/* ... silently appended r^3 and r^4 when using AVX2 */
+};
+
+asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src,
+				    const u32 *r, unsigned int blocks);
+asmlinkage void poly1305_2block_sse2(u32 *h, const u8 *src, const u32 *r,
+				     unsigned int blocks, const u32 *u);
+#ifdef CONFIG_AS_AVX2
+asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r,
+				     unsigned int blocks, const u32 *u);
+static bool poly1305_use_avx2;
+#endif
+
+static int poly1305_simd_init(struct shash_desc *desc)
+{
+	struct poly1305_simd_desc_ctx *sctx = shash_desc_ctx(desc);
+
+	sctx->uset = false;
+#ifdef CONFIG_AS_AVX2
+	sctx->wset = false;
+#endif
+
+	return crypto_poly1305_init(desc);
+}
+
+static void poly1305_simd_mult(u32 *a, const u32 *b)
+{
+	u8 m[POLY1305_BLOCK_SIZE];
+
+	memset(m, 0, sizeof(m));
+	/* The poly1305 block function adds a hi-bit to the accumulator which
+	 * we don't need for key multiplication; compensate for it. */
+	a[4] -= 1 << 24;
+	poly1305_block_sse2(a, m, b, 1);
+}
+
+static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx,
+					 const u8 *src, unsigned int srclen)
+{
+	struct poly1305_simd_desc_ctx *sctx;
+	unsigned int blocks, datalen;
+
+	BUILD_BUG_ON(offsetof(struct poly1305_simd_desc_ctx, base));
+	sctx = container_of(dctx, struct poly1305_simd_desc_ctx, base);
+
+	if (unlikely(!dctx->sset)) {
+		datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
+		src += srclen - datalen;
+		srclen = datalen;
+	}
+
+#ifdef CONFIG_AS_AVX2
+	if (poly1305_use_avx2 && srclen >= POLY1305_BLOCK_SIZE * 4) {
+		if (unlikely(!sctx->wset)) {
+			if (!sctx->uset) {
+				memcpy(sctx->u, dctx->r, sizeof(sctx->u));
+				poly1305_simd_mult(sctx->u, dctx->r);
+				sctx->uset = true;
+			}
+			memcpy(sctx->u + 5, sctx->u, sizeof(sctx->u));
+			poly1305_simd_mult(sctx->u + 5, dctx->r);
+			memcpy(sctx->u + 10, sctx->u + 5, sizeof(sctx->u));
+			poly1305_simd_mult(sctx->u + 10, dctx->r);
+			sctx->wset = true;
+		}
+		blocks = srclen / (POLY1305_BLOCK_SIZE * 4);
+		poly1305_4block_avx2(dctx->h, src, dctx->r, blocks, sctx->u);
+		src += POLY1305_BLOCK_SIZE * 4 * blocks;
+		srclen -= POLY1305_BLOCK_SIZE * 4 * blocks;
+	}
+#endif
+	if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) {
+		if (unlikely(!sctx->uset)) {
+			memcpy(sctx->u, dctx->r, sizeof(sctx->u));
+			poly1305_simd_mult(sctx->u, dctx->r);
+			sctx->uset = true;
+		}
+		blocks = srclen / (POLY1305_BLOCK_SIZE * 2);
+		poly1305_2block_sse2(dctx->h, src, dctx->r, blocks, sctx->u);
+		src += POLY1305_BLOCK_SIZE * 2 * blocks;
+		srclen -= POLY1305_BLOCK_SIZE * 2 * blocks;
+	}
+	if (srclen >= POLY1305_BLOCK_SIZE) {
+		poly1305_block_sse2(dctx->h, src, dctx->r, 1);
+		srclen -= POLY1305_BLOCK_SIZE;
+	}
+	return srclen;
+}
+
+static int poly1305_simd_update(struct shash_desc *desc,
+				const u8 *src, unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+	unsigned int bytes;
+
+	/* kernel_fpu_begin/end is costly, use fallback for small updates */
+	if (srclen <= 288 || !may_use_simd())
+		return crypto_poly1305_update(desc, src, srclen);
+
+	kernel_fpu_begin();
+
+	if (unlikely(dctx->buflen)) {
+		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		srclen -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_simd_blocks(dctx, dctx->buf,
+					     POLY1305_BLOCK_SIZE);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
+		bytes = poly1305_simd_blocks(dctx, src, srclen);
+		src += srclen - bytes;
+		srclen = bytes;
+	}
+
+	kernel_fpu_end();
+
+	if (unlikely(srclen)) {
+		dctx->buflen = srclen;
+		memcpy(dctx->buf, src, srclen);
+	}
+
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.digestsize	= POLY1305_DIGEST_SIZE,
+	.init		= poly1305_simd_init,
+	.update		= poly1305_simd_update,
+	.final		= crypto_poly1305_final,
+	.setkey		= crypto_poly1305_setkey,
+	.descsize	= sizeof(struct poly1305_simd_desc_ctx),
+	.base		= {
+		.cra_name		= "poly1305",
+		.cra_driver_name	= "poly1305-simd",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_alignmask		= sizeof(u32) - 1,
+		.cra_blocksize		= POLY1305_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	},
+};
+
+static int __init poly1305_simd_mod_init(void)
+{
+	if (!cpu_has_xmm2)
+		return -ENODEV;
+
+#ifdef CONFIG_AS_AVX2
+	poly1305_use_avx2 = cpu_has_avx && cpu_has_avx2 &&
+			    cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL);
+	alg.descsize = sizeof(struct poly1305_simd_desc_ctx);
+	if (poly1305_use_avx2)
+		alg.descsize += 10 * sizeof(u32);
+#endif
+	return crypto_register_shash(&alg);
+}
+
+static void __exit poly1305_simd_mod_exit(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(poly1305_simd_mod_init);
+module_exit(poly1305_simd_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("Poly1305 authenticator");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-simd");