[PATCH 0/6] crypto: x86_64 optimized XChaCha and NHPoly1305 (for Adiantum)

[PATCH 0/6] crypto: x86_64 optimized XChaCha and NHPoly1305 (for Adiantum)

[Eric Biggers]

Hello,

This series optimizes the Adiantum encryption mode for x86_64 by adding
SSE2 and AVX2 accelerated implementations of NHPoly1305, specifically
the NH part; and by modifying the existing x86_64 SSSE3/AVX2 ChaCha20
implementation to support XChaCha20 and XChaCha12.

This greatly improves Adiantum performance on x86_64.  For example, with
a 4096-byte input size on a Zen-based processor, which supports AVX2:

                           Before                After
                           --------              ---------
adiantum(xchacha12,aes)    505 MB/s              1250 MB/s
adiantum(xchacha20,aes)    387 MB/s              989 MB/s

Encryption and decryption are the same speed.

The biggest benefit comes from accelerating XChaCha.  Accelerating NH
gives a somewhat smaller, but still significant benefit.

Performance on 512-byte inputs is also improved, though that is much
slower in the first place.  When Adiantium is used with dm-crypt (or
cryptsetup), we recommend using a 4096-byte sector size.

For comparison, AES-256-XTS is 4140 MB/s on the same processor, but it
has the benefit of direct AES-NI hardware support for AES whereas
Adiantum is implemented entirely with general-purpose instructions
(scalar and SIMD).  The corresponding C implementation of AES-256-XTS is
only 288 MB/s, and AES isn't particularly well-suited for optimizing
with general-purpose SIMD instructions.  Also unlike Adiantum, XTS isn't
a super-pseudorandom permutation over the entire sector.

Note that XChaCha20 and XChaCha12 can be used for other purposes too.

Eric Biggers (6):
  crypto: x86/nhpoly1305 - add SSE2 accelerated NHPoly1305
  crypto: x86/nhpoly1305 - add AVX2 accelerated NHPoly1305
  crypto: x86/chacha20 - limit the preemption-disabled section
  crypto: x86/chacha20 - add XChaCha20 support
  crypto: x86/chacha20 - refactor to allow varying number of rounds
  crypto: x86/chacha - add XChaCha12 support

 arch/x86/crypto/Makefile                      |  13 +-
 ...a20-avx2-x86_64.S => chacha-avx2-x86_64.S} |  33 ++-
 ...0-ssse3-x86_64.S => chacha-ssse3-x86_64.S} |  99 +++++---
 arch/x86/crypto/chacha20_glue.c               | 168 -------------
 arch/x86/crypto/chacha_glue.c                 | 236 ++++++++++++++++++
 arch/x86/crypto/nh-avx2-x86_64.S              | 157 ++++++++++++
 arch/x86/crypto/nh-sse2-x86_64.S              | 123 +++++++++
 arch/x86/crypto/nhpoly1305-avx2-glue.c        |  77 ++++++
 arch/x86/crypto/nhpoly1305-sse2-glue.c        |  76 ++++++
 crypto/Kconfig                                |  28 ++-
 10 files changed, 778 insertions(+), 232 deletions(-)
 rename arch/x86/crypto/{chacha20-avx2-x86_64.S => chacha-avx2-x86_64.S} (97%)
 rename arch/x86/crypto/{chacha20-ssse3-x86_64.S => chacha-ssse3-x86_64.S} (93%)
 delete mode 100644 arch/x86/crypto/chacha20_glue.c
 create mode 100644 arch/x86/crypto/chacha_glue.c
 create mode 100644 arch/x86/crypto/nh-avx2-x86_64.S
 create mode 100644 arch/x86/crypto/nh-sse2-x86_64.S
 create mode 100644 arch/x86/crypto/nhpoly1305-avx2-glue.c
 create mode 100644 arch/x86/crypto/nhpoly1305-sse2-glue.c

-- 
2.19.2

[PATCH 1/6] crypto: x86/nhpoly1305 - add SSE2 accelerated NHPoly1305

[Eric Biggers]

From: Eric Biggers <ebiggers@google.com>

Add a 64-bit SSE2 implementation of NHPoly1305, an ε-almost-∆-universal
hash function used in the Adiantum encryption mode.  For now, only the
NH portion is actually SSE2-accelerated; the Poly1305 part is less
performance-critical so is just implemented in C.

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 arch/x86/crypto/Makefile               |   4 +
 arch/x86/crypto/nh-sse2-x86_64.S       | 123 +++++++++++++++++++++++++
 arch/x86/crypto/nhpoly1305-sse2-glue.c |  76 +++++++++++++++
 crypto/Kconfig                         |   8 ++
 4 files changed, 211 insertions(+)
 create mode 100644 arch/x86/crypto/nh-sse2-x86_64.S
 create mode 100644 arch/x86/crypto/nhpoly1305-sse2-glue.c

diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index a4b0007a54e17..49dc3d50041c9 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -46,6 +46,8 @@ obj-$(CONFIG_CRYPTO_MORUS1280_GLUE) += morus1280_glue.o
 obj-$(CONFIG_CRYPTO_MORUS640_SSE2) += morus640-sse2.o
 obj-$(CONFIG_CRYPTO_MORUS1280_SSE2) += morus1280-sse2.o
 
+obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
+
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += \
@@ -84,6 +86,8 @@ aegis256-aesni-y := aegis256-aesni-asm.o aegis256-aesni-glue.o
 morus640-sse2-y := morus640-sse2-asm.o morus640-sse2-glue.o
 morus1280-sse2-y := morus1280-sse2-asm.o morus1280-sse2-glue.o
 
+nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
+
 ifeq ($(avx_supported),yes)
 	camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
 					camellia_aesni_avx_glue.o
diff --git a/arch/x86/crypto/nh-sse2-x86_64.S b/arch/x86/crypto/nh-sse2-x86_64.S
new file mode 100644
index 0000000000000..51f52d4ab4bbc
--- /dev/null
+++ b/arch/x86/crypto/nh-sse2-x86_64.S
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * NH - ε-almost-universal hash function, x86_64 SSE2 accelerated
+ *
+ * Copyright 2018 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+#define		PASS0_SUMS	%xmm0
+#define		PASS1_SUMS	%xmm1
+#define		PASS2_SUMS	%xmm2
+#define		PASS3_SUMS	%xmm3
+#define		K0		%xmm4
+#define		K1		%xmm5
+#define		K2		%xmm6
+#define		K3		%xmm7
+#define		T0		%xmm8
+#define		T1		%xmm9
+#define		T2		%xmm10
+#define		T3		%xmm11
+#define		T4		%xmm12
+#define		T5		%xmm13
+#define		T6		%xmm14
+#define		T7		%xmm15
+#define		KEY		%rdi
+#define		MESSAGE		%rsi
+#define		MESSAGE_LEN	%rdx
+#define		HASH		%rcx
+
+.macro _nh_stride	k0, k1, k2, k3, offset
+
+	// Load next message stride
+	movdqu		\offset(MESSAGE), T1
+
+	// Load next key stride
+	movdqu		\offset(KEY), \k3
+
+	// Add message words to key words
+	movdqa		T1, T2
+	movdqa		T1, T3
+	paddd		T1, \k0    // reuse k0 to avoid a move
+	paddd		\k1, T1
+	paddd		\k2, T2
+	paddd		\k3, T3
+
+	// Multiply 32x32 => 64 and accumulate
+	pshufd		$0x10, \k0, T4
+	pshufd		$0x32, \k0, \k0
+	pshufd		$0x10, T1, T5
+	pshufd		$0x32, T1, T1
+	pshufd		$0x10, T2, T6
+	pshufd		$0x32, T2, T2
+	pshufd		$0x10, T3, T7
+	pshufd		$0x32, T3, T3
+	pmuludq		T4, \k0
+	pmuludq		T5, T1
+	pmuludq		T6, T2
+	pmuludq		T7, T3
+	paddq		\k0, PASS0_SUMS
+	paddq		T1, PASS1_SUMS
+	paddq		T2, PASS2_SUMS
+	paddq		T3, PASS3_SUMS
+.endm
+
+/*
+ * void nh_sse2(const u32 *key, const u8 *message, size_t message_len,
+ *		u8 hash[NH_HASH_BYTES])
+ *
+ * It's guaranteed that message_len % 16 == 0.
+ */
+ENTRY(nh_sse2)
+
+	movdqu		0x00(KEY), K0
+	movdqu		0x10(KEY), K1
+	movdqu		0x20(KEY), K2
+	add		$0x30, KEY
+	pxor		PASS0_SUMS, PASS0_SUMS
+	pxor		PASS1_SUMS, PASS1_SUMS
+	pxor		PASS2_SUMS, PASS2_SUMS
+	pxor		PASS3_SUMS, PASS3_SUMS
+
+	sub		$0x40, MESSAGE_LEN
+	jl		.Lloop4_done
+.Lloop4:
+	_nh_stride	K0, K1, K2, K3, 0x00
+	_nh_stride	K1, K2, K3, K0, 0x10
+	_nh_stride	K2, K3, K0, K1, 0x20
+	_nh_stride	K3, K0, K1, K2, 0x30
+	add		$0x40, KEY
+	add		$0x40, MESSAGE
+	sub		$0x40, MESSAGE_LEN
+	jge		.Lloop4
+
+.Lloop4_done:
+	and		$0x3f, MESSAGE_LEN
+	jz		.Ldone
+	_nh_stride	K0, K1, K2, K3, 0x00
+
+	sub		$0x10, MESSAGE_LEN
+	jz		.Ldone
+	_nh_stride	K1, K2, K3, K0, 0x10
+
+	sub		$0x10, MESSAGE_LEN
+	jz		.Ldone
+	_nh_stride	K2, K3, K0, K1, 0x20
+
+.Ldone:
+	// Sum the accumulators for each pass, then store the sums to 'hash'
+	movdqa		PASS0_SUMS, T0
+	movdqa		PASS2_SUMS, T1
+	punpcklqdq	PASS1_SUMS, T0		// => (PASS0_SUM_A PASS1_SUM_A)
+	punpcklqdq	PASS3_SUMS, T1		// => (PASS2_SUM_A PASS3_SUM_A)
+	punpckhqdq	PASS1_SUMS, PASS0_SUMS	// => (PASS0_SUM_B PASS1_SUM_B)
+	punpckhqdq	PASS3_SUMS, PASS2_SUMS	// => (PASS2_SUM_B PASS3_SUM_B)
+	paddq		PASS0_SUMS, T0
+	paddq		PASS2_SUMS, T1
+	movdqu		T0, 0x00(HASH)
+	movdqu		T1, 0x10(HASH)
+	ret
+ENDPROC(nh_sse2)
diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c
new file mode 100644
index 0000000000000..ed68d164ce140
--- /dev/null
+++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum
+ * (SSE2 accelerated version)
+ *
+ * Copyright 2018 Google LLC
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/nhpoly1305.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+
+asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len,
+			u8 hash[NH_HASH_BYTES]);
+
+/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */
+static void _nh_sse2(const u32 *key, const u8 *message, size_t message_len,
+		     __le64 hash[NH_NUM_PASSES])
+{
+	nh_sse2(key, message, message_len, (u8 *)hash);
+}
+
+static int nhpoly1305_sse2_update(struct shash_desc *desc,
+				  const u8 *src, unsigned int srclen)
+{
+	if (srclen < 64 || !irq_fpu_usable())
+		return crypto_nhpoly1305_update(desc, src, srclen);
+
+	do {
+		unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+
+		kernel_fpu_begin();
+		crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2);
+		kernel_fpu_end();
+		src += n;
+		srclen -= n;
+	} while (srclen);
+	return 0;
+}
+
+static struct shash_alg nhpoly1305_alg = {
+	.base.cra_name		= "nhpoly1305",
+	.base.cra_driver_name	= "nhpoly1305-sse2",
+	.base.cra_priority	= 200,
+	.base.cra_ctxsize	= sizeof(struct nhpoly1305_key),
+	.base.cra_module	= THIS_MODULE,
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.init			= crypto_nhpoly1305_init,
+	.update			= nhpoly1305_sse2_update,
+	.final			= crypto_nhpoly1305_final,
+	.setkey			= crypto_nhpoly1305_setkey,
+	.descsize		= sizeof(struct nhpoly1305_state),
+};
+
+static int __init nhpoly1305_mod_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_XMM2))
+		return -ENODEV;
+
+	return crypto_register_shash(&nhpoly1305_alg);
+}
+
+static void __exit nhpoly1305_mod_exit(void)
+{
+	crypto_unregister_shash(&nhpoly1305_alg);
+}
+
+module_init(nhpoly1305_mod_init);
+module_exit(nhpoly1305_mod_exit);
+
+MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function (SSE2-accelerated)");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("nhpoly1305");
+MODULE_ALIAS_CRYPTO("nhpoly1305-sse2");
diff --git a/crypto/Kconfig b/crypto/Kconfig
index b6376d5d973e0..b85133966d643 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -501,6 +501,14 @@ config CRYPTO_NHPOLY1305
 	select CRYPTO_HASH
 	select CRYPTO_POLY1305
 
+config CRYPTO_NHPOLY1305_SSE2
+	tristate "NHPoly1305 hash function (x86_64 SSE2 implementation)"
+	depends on X86 && 64BIT
+	select CRYPTO_NHPOLY1305
+	help
+	  SSE2 optimized implementation of the hash function used by the
+	  Adiantum encryption mode.
+
 config CRYPTO_ADIANTUM
 	tristate "Adiantum support"
 	select CRYPTO_CHACHA20
-- 
2.19.2

[PATCH 2/6] crypto: x86/nhpoly1305 - add AVX2 accelerated NHPoly1305

[Eric Biggers]

From: Eric Biggers <ebiggers@google.com>

Add a 64-bit AVX2 implementation of NHPoly1305, an ε-almost-∆-universal
hash function used in the Adiantum encryption mode.  For now, only the
NH portion is actually AVX2-accelerated; the Poly1305 part is less
performance-critical so is just implemented in C.

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 arch/x86/crypto/Makefile               |   3 +
 arch/x86/crypto/nh-avx2-x86_64.S       | 157 +++++++++++++++++++++++++
 arch/x86/crypto/nhpoly1305-avx2-glue.c |  77 ++++++++++++
 crypto/Kconfig                         |   8 ++
 4 files changed, 245 insertions(+)
 create mode 100644 arch/x86/crypto/nh-avx2-x86_64.S
 create mode 100644 arch/x86/crypto/nhpoly1305-avx2-glue.c

diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 49dc3d50041c9..006433da45f8c 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -47,6 +47,7 @@ obj-$(CONFIG_CRYPTO_MORUS640_SSE2) += morus640-sse2.o
 obj-$(CONFIG_CRYPTO_MORUS1280_SSE2) += morus1280-sse2.o
 
 obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
+obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
 
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)
@@ -105,6 +106,8 @@ ifeq ($(avx2_supported),yes)
 	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
 
 	morus1280-avx2-y := morus1280-avx2-asm.o morus1280-avx2-glue.o
+
+	nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o
 endif
 
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S
new file mode 100644
index 0000000000000..f7946ea1b7046
--- /dev/null
+++ b/arch/x86/crypto/nh-avx2-x86_64.S
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * NH - ε-almost-universal hash function, x86_64 AVX2 accelerated
+ *
+ * Copyright 2018 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+#define		PASS0_SUMS	%ymm0
+#define		PASS1_SUMS	%ymm1
+#define		PASS2_SUMS	%ymm2
+#define		PASS3_SUMS	%ymm3
+#define		K0		%ymm4
+#define		K0_XMM		%xmm4
+#define		K1		%ymm5
+#define		K1_XMM		%xmm5
+#define		K2		%ymm6
+#define		K2_XMM		%xmm6
+#define		K3		%ymm7
+#define		K3_XMM		%xmm7
+#define		T0		%ymm8
+#define		T1		%ymm9
+#define		T2		%ymm10
+#define		T2_XMM		%xmm10
+#define		T3		%ymm11
+#define		T3_XMM		%xmm11
+#define		T4		%ymm12
+#define		T5		%ymm13
+#define		T6		%ymm14
+#define		T7		%ymm15
+#define		KEY		%rdi
+#define		MESSAGE		%rsi
+#define		MESSAGE_LEN	%rdx
+#define		HASH		%rcx
+
+.macro _nh_2xstride	k0, k1, k2, k3
+
+	// Add message words to key words
+	vpaddd		\k0, T3, T0
+	vpaddd		\k1, T3, T1
+	vpaddd		\k2, T3, T2
+	vpaddd		\k3, T3, T3
+
+	// Multiply 32x32 => 64 and accumulate
+	vpshufd		$0x10, T0, T4
+	vpshufd		$0x32, T0, T0
+	vpshufd		$0x10, T1, T5
+	vpshufd		$0x32, T1, T1
+	vpshufd		$0x10, T2, T6
+	vpshufd		$0x32, T2, T2
+	vpshufd		$0x10, T3, T7
+	vpshufd		$0x32, T3, T3
+	vpmuludq	T4, T0, T0
+	vpmuludq	T5, T1, T1
+	vpmuludq	T6, T2, T2
+	vpmuludq	T7, T3, T3
+	vpaddq		T0, PASS0_SUMS, PASS0_SUMS
+	vpaddq		T1, PASS1_SUMS, PASS1_SUMS
+	vpaddq		T2, PASS2_SUMS, PASS2_SUMS
+	vpaddq		T3, PASS3_SUMS, PASS3_SUMS
+.endm
+
+/*
+ * void nh_avx2(const u32 *key, const u8 *message, size_t message_len,
+ *		u8 hash[NH_HASH_BYTES])
+ *
+ * It's guaranteed that message_len % 16 == 0.
+ */
+ENTRY(nh_avx2)
+
+	vmovdqu		0x00(KEY), K0
+	vmovdqu		0x10(KEY), K1
+	add		$0x20, KEY
+	vpxor		PASS0_SUMS, PASS0_SUMS, PASS0_SUMS
+	vpxor		PASS1_SUMS, PASS1_SUMS, PASS1_SUMS
+	vpxor		PASS2_SUMS, PASS2_SUMS, PASS2_SUMS
+	vpxor		PASS3_SUMS, PASS3_SUMS, PASS3_SUMS
+
+	sub		$0x40, MESSAGE_LEN
+	jl		.Lloop4_done
+.Lloop4:
+	vmovdqu		(MESSAGE), T3
+	vmovdqu		0x00(KEY), K2
+	vmovdqu		0x10(KEY), K3
+	_nh_2xstride	K0, K1, K2, K3
+
+	vmovdqu		0x20(MESSAGE), T3
+	vmovdqu		0x20(KEY), K0
+	vmovdqu		0x30(KEY), K1
+	_nh_2xstride	K2, K3, K0, K1
+
+	add		$0x40, MESSAGE
+	add		$0x40, KEY
+	sub		$0x40, MESSAGE_LEN
+	jge		.Lloop4
+
+.Lloop4_done:
+	and		$0x3f, MESSAGE_LEN
+	jz		.Ldone
+
+	cmp		$0x20, MESSAGE_LEN
+	jl		.Llast
+
+	// 2 or 3 strides remain; do 2 more.
+	vmovdqu		(MESSAGE), T3
+	vmovdqu		0x00(KEY), K2
+	vmovdqu		0x10(KEY), K3
+	_nh_2xstride	K0, K1, K2, K3
+	add		$0x20, MESSAGE
+	add		$0x20, KEY
+	sub		$0x20, MESSAGE_LEN
+	jz		.Ldone
+	vmovdqa		K2, K0
+	vmovdqa		K3, K1
+.Llast:
+	// Last stride.  Zero the high 128 bits of the message and keys so they
+	// don't affect the result when processing them like 2 strides.
+	vmovdqu		(MESSAGE), T3_XMM
+	vmovdqa		K0_XMM, K0_XMM
+	vmovdqa		K1_XMM, K1_XMM
+	vmovdqu		0x00(KEY), K2_XMM
+	vmovdqu		0x10(KEY), K3_XMM
+	_nh_2xstride	K0, K1, K2, K3
+
+.Ldone:
+	// Sum the accumulators for each pass, then store the sums to 'hash'
+
+	// PASS0_SUMS is (0A 0B 0C 0D)
+	// PASS1_SUMS is (1A 1B 1C 1D)
+	// PASS2_SUMS is (2A 2B 2C 2D)
+	// PASS3_SUMS is (3A 3B 3C 3D)
+	// We need the horizontal sums:
+	//     (0A + 0B + 0C + 0D,
+	//	1A + 1B + 1C + 1D,
+	//	2A + 2B + 2C + 2D,
+	//	3A + 3B + 3C + 3D)
+	//
+
+	vpunpcklqdq	PASS1_SUMS, PASS0_SUMS, T0	// T0 = (0A 1A 0C 1C)
+	vpunpckhqdq	PASS1_SUMS, PASS0_SUMS, T1	// T1 = (0B 1B 0D 1D)
+	vpunpcklqdq	PASS3_SUMS, PASS2_SUMS, T2	// T2 = (2A 3A 2C 3C)
+	vpunpckhqdq	PASS3_SUMS, PASS2_SUMS, T3	// T3 = (2B 3B 2D 3D)
+
+	vinserti128	$0x1, T2_XMM, T0, T4		// T4 = (0A 1A 2A 3A)
+	vinserti128	$0x1, T3_XMM, T1, T5		// T5 = (0B 1B 2B 3B)
+	vperm2i128	$0x31, T2, T0, T0		// T0 = (0C 1C 2C 3C)
+	vperm2i128	$0x31, T3, T1, T1		// T1 = (0D 1D 2D 3D)
+
+	vpaddq		T5, T4, T4
+	vpaddq		T1, T0, T0
+	vpaddq		T4, T0, T0
+	vmovdqu		T0, (HASH)
+	ret
+ENDPROC(nh_avx2)
diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c
new file mode 100644
index 0000000000000..20d815ea4b6a9
--- /dev/null
+++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum
+ * (AVX2 accelerated version)
+ *
+ * Copyright 2018 Google LLC
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/nhpoly1305.h>
+#include <linux/module.h>
+#include <asm/fpu/api.h>
+
+asmlinkage void nh_avx2(const u32 *key, const u8 *message, size_t message_len,
+			u8 hash[NH_HASH_BYTES]);
+
+/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */
+static void _nh_avx2(const u32 *key, const u8 *message, size_t message_len,
+		     __le64 hash[NH_NUM_PASSES])
+{
+	nh_avx2(key, message, message_len, (u8 *)hash);
+}
+
+static int nhpoly1305_avx2_update(struct shash_desc *desc,
+				  const u8 *src, unsigned int srclen)
+{
+	if (srclen < 64 || !irq_fpu_usable())
+		return crypto_nhpoly1305_update(desc, src, srclen);
+
+	do {
+		unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+
+		kernel_fpu_begin();
+		crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2);
+		kernel_fpu_end();
+		src += n;
+		srclen -= n;
+	} while (srclen);
+	return 0;
+}
+
+static struct shash_alg nhpoly1305_alg = {
+	.base.cra_name		= "nhpoly1305",
+	.base.cra_driver_name	= "nhpoly1305-avx2",
+	.base.cra_priority	= 300,
+	.base.cra_ctxsize	= sizeof(struct nhpoly1305_key),
+	.base.cra_module	= THIS_MODULE,
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.init			= crypto_nhpoly1305_init,
+	.update			= nhpoly1305_avx2_update,
+	.final			= crypto_nhpoly1305_final,
+	.setkey			= crypto_nhpoly1305_setkey,
+	.descsize		= sizeof(struct nhpoly1305_state),
+};
+
+static int __init nhpoly1305_mod_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE))
+		return -ENODEV;
+
+	return crypto_register_shash(&nhpoly1305_alg);
+}
+
+static void __exit nhpoly1305_mod_exit(void)
+{
+	crypto_unregister_shash(&nhpoly1305_alg);
+}
+
+module_init(nhpoly1305_mod_init);
+module_exit(nhpoly1305_mod_exit);
+
+MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function (AVX2-accelerated)");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("nhpoly1305");
+MODULE_ALIAS_CRYPTO("nhpoly1305-avx2");
diff --git a/crypto/Kconfig b/crypto/Kconfig
index b85133966d643..e084e2fb6743b 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -509,6 +509,14 @@ config CRYPTO_NHPOLY1305_SSE2
 	  SSE2 optimized implementation of the hash function used by the
 	  Adiantum encryption mode.
 
+config CRYPTO_NHPOLY1305_AVX2
+	tristate "NHPoly1305 hash function (x86_64 AVX2 implementation)"
+	depends on X86 && 64BIT
+	select CRYPTO_NHPOLY1305
+	help
+	  AVX2 optimized implementation of the hash function used by the
+	  Adiantum encryption mode.
+
 config CRYPTO_ADIANTUM
 	tristate "Adiantum support"
 	select CRYPTO_CHACHA20
-- 
2.19.2

[PATCH 3/6] crypto: x86/chacha20 - limit the preemption-disabled section

[Eric Biggers]

From: Eric Biggers <ebiggers@google.com>

To improve responsiveness, disable preemption for each step of the walk
(which is at most PAGE_SIZE) rather than for the entire
encryption/decryption operation.

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 arch/x86/crypto/chacha20_glue.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 1e9e665092264..5928fee7acdd4 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -100,26 +100,24 @@ static int chacha20_simd(struct skcipher_request *req)
 	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd())
 		return crypto_chacha_crypt(req);
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	crypto_chacha_init(state, ctx, walk.iv);
 
-	kernel_fpu_begin();
-
 	while (walk.nbytes > 0) {
 		unsigned int nbytes = walk.nbytes;
 
 		if (nbytes < walk.total)
 			nbytes = round_down(nbytes, walk.stride);
 
+		kernel_fpu_begin();
 		chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
 				nbytes);
+		kernel_fpu_end();
 
 		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
-	kernel_fpu_end();
-
 	return err;
 }
 
-- 
2.19.2

[PATCH 4/6] crypto: x86/chacha20 - add XChaCha20 support

[Eric Biggers]

From: Eric Biggers <ebiggers@google.com>

Add an XChaCha20 implementation that is hooked up to the x86_64 SIMD
implementation of ChaCha20.  This can be used by Adiantum.

An SSSE3 implementation of single-block HChaCha20 is also added so that
XChaCha20 can use it rather than the generic implementation.  This
required refactoring the ChaCha permutation into its own function.

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 arch/x86/crypto/chacha20-ssse3-x86_64.S |  76 ++++++++++++------
 arch/x86/crypto/chacha20_glue.c         | 101 ++++++++++++++++++------
 crypto/Kconfig                          |  12 +--
 3 files changed, 130 insertions(+), 59 deletions(-)

diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S
index d8ac75bb448f9..45e4ccdd9c98b 100644
--- a/arch/x86/crypto/chacha20-ssse3-x86_64.S
+++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S
@@ -23,37 +23,24 @@ CTRINC:	.octa 0x00000003000000020000000100000000
 
 .text
 
-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
-
-	# 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 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.
-
-	# 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
+/*
+ * 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		%rcx,%rax
 	mov		$10,%ecx
 
 .Ldoubleround:
-
 	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
 	paddd		%xmm1,%xmm0
 	pxor		%xmm0,%xmm3
@@ -123,6 +110,28 @@ ENTRY(chacha20_block_xor_ssse3)
 	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
+
+	# 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
@@ -189,6 +198,23 @@ ENTRY(chacha20_block_xor_ssse3)
 
 ENDPROC(chacha20_block_xor_ssse3)
 
+ENTRY(hchacha20_block_ssse3)
+	# %rdi: Input state matrix, s
+	# %rsi: output (8 32-bit words)
+
+	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)
+
+	ret
+ENDPROC(hchacha20_block_ssse3)
+
 ENTRY(chacha20_4block_xor_ssse3)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 4 data blocks output, o
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 5928fee7acdd4..ca85b5d2c4751 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -23,6 +23,7 @@ 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);
@@ -86,23 +87,19 @@ static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src,
 	}
 }
 
-static int chacha20_simd(struct skcipher_request *req)
+static int chacha20_simd_stream_xor(struct skcipher_request *req,
+				    struct chacha_ctx *ctx, u8 *iv)
 {
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	u32 *state, state_buf[16 + 2] __aligned(8);
 	struct skcipher_walk walk;
+	u32 *state, state_buf[16 + 2] __aligned(8);
 	int err;
 
 	BUILD_BUG_ON(CHACHA20_STATE_ALIGN != 16);
 	state = PTR_ALIGN(state_buf + 0, CHACHA20_STATE_ALIGN);
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd())
-		return crypto_chacha_crypt(req);
-
 	err = skcipher_walk_virt(&walk, req, false);
 
-	crypto_chacha_init(state, ctx, walk.iv);
+	crypto_chacha_init(state, ctx, iv);
 
 	while (walk.nbytes > 0) {
 		unsigned int nbytes = walk.nbytes;
@@ -121,21 +118,73 @@ static int chacha20_simd(struct skcipher_request *req)
 	return err;
 }
 
-static struct skcipher_alg alg = {
-	.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,
+static int chacha20_simd(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !irq_fpu_usable())
+		return crypto_chacha_crypt(req);
+
+	return chacha20_simd_stream_xor(req, ctx, req->iv);
+}
+
+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];
+
+	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);
+	kernel_fpu_end();
+
+	memcpy(&real_iv[0], req->iv + 24, 8);
+	memcpy(&real_iv[8], req->iv + 16, 8);
+	return chacha20_simd_stream_xor(req, &subctx, real_iv);
+}
+
+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)
@@ -148,12 +197,12 @@ static int __init chacha20_simd_mod_init(void)
 			    boot_cpu_has(X86_FEATURE_AVX2) &&
 			    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
 #endif
-	return crypto_register_skcipher(&alg);
+	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 static void __exit chacha20_simd_mod_fini(void)
 {
-	crypto_unregister_skcipher(&alg);
+	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 module_init(chacha20_simd_mod_init);
@@ -164,3 +213,5 @@ 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/crypto/Kconfig b/crypto/Kconfig
index e084e2fb6743b..ecfc10a3e9f3e 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1468,19 +1468,13 @@ config CRYPTO_CHACHA20
 	  in some performance-sensitive scenarios.
 
 config CRYPTO_CHACHA20_X86_64
-	tristate "ChaCha20 cipher algorithm (x86_64/SSSE3/AVX2)"
+	tristate "ChaCha stream cipher algorithms (x86_64/SSSE3/AVX2)"
 	depends on X86 && 64BIT
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_CHACHA20
 	help
-	  ChaCha20 cipher algorithm, RFC7539.
-
-	  ChaCha20 is a 256-bit high-speed stream cipher designed by Daniel J.
-	  Bernstein and further specified in RFC7539 for use in IETF protocols.
-	  This is the x86_64 assembler implementation using SIMD instructions.
-
-	  See also:
-	  <http://cr.yp.to/chacha/chacha-20080128.pdf>
+	  SSSE3 and AVX2 optimized implementations of the ChaCha20 and XChaCha20
+	  stream ciphers.
 
 config CRYPTO_SEED
 	tristate "SEED cipher algorithm"
-- 
2.19.2

[PATCH 5/6] crypto: x86/chacha20 - refactor to allow varying number of rounds

[Eric Biggers]

From: Eric Biggers <ebiggers@google.com>

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

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 arch/x86/crypto/Makefile                      |   6 +-
 ...a20-avx2-x86_64.S => chacha-avx2-x86_64.S} |  33 +++---
 ...0-ssse3-x86_64.S => chacha-ssse3-x86_64.S} |  41 ++++---
 .../crypto/{chacha20_glue.c => chacha_glue.c} | 110 +++++++++---------
 4 files changed, 97 insertions(+), 93 deletions(-)
 rename arch/x86/crypto/{chacha20-avx2-x86_64.S => chacha-avx2-x86_64.S} (97%)
 rename arch/x86/crypto/{chacha20-ssse3-x86_64.S => chacha-ssse3-x86_64.S} (96%)
 rename arch/x86/crypto/{chacha20_glue.c => chacha_glue.c} (56%)

diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 006433da45f8c..164b4e792e8d2 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -23,7 +23,7 @@ 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
@@ -77,7 +77,7 @@ 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
@@ -102,7 +102,7 @@ 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
diff --git a/arch/x86/crypto/chacha20-avx2-x86_64.S b/arch/x86/crypto/chacha-avx2-x86_64.S
similarity index 97%
rename from arch/x86/crypto/chacha20-avx2-x86_64.S
rename to arch/x86/crypto/chacha-avx2-x86_64.S
index b6ab082be6572..32da1be9a3550 100644
--- a/arch/x86/crypto/chacha20-avx2-x86_64.S
+++ b/arch/x86/crypto/chacha-avx2-x86_64.S
@@ -1,5 +1,5 @@
 /*
- * ChaCha20 256-bit cipher algorithm, RFC7539, x64 AVX2 functions
+ * ChaCha 256-bit cipher algorithm, x64 AVX2 functions
  *
  * Copyright (C) 2015 Martin Willi
  *
@@ -38,13 +38,14 @@ CTR4BL:	.octa 0x00000000000000000000000000000002
 
 .text
 
-ENTRY(chacha20_2block_xor_avx2)
+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 ChaCha20 blocks by loading the state
+	# 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.
@@ -68,7 +69,6 @@ ENTRY(chacha20_2block_xor_avx2)
 	vmovdqa		ROT16(%rip),%ymm5
 
 	mov		%rcx,%rax
-	mov		$10,%ecx
 
 .Ldoubleround:
 
@@ -138,7 +138,7 @@ ENTRY(chacha20_2block_xor_avx2)
 	# x3 = shuffle32(x3, MASK(0, 3, 2, 1))
 	vpshufd		$0x39,%ymm3,%ymm3
 
-	dec		%ecx
+	sub		$2,%r8d
 	jnz		.Ldoubleround
 
 	# o0 = i0 ^ (x0 + s0)
@@ -228,15 +228,16 @@ ENTRY(chacha20_2block_xor_avx2)
 	lea		-8(%r10),%rsp
 	jmp		.Ldone2
 
-ENDPROC(chacha20_2block_xor_avx2)
+ENDPROC(chacha_2block_xor_avx2)
 
-ENTRY(chacha20_4block_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 ChaCha20 block by loading the state
+	# This function encrypts four ChaCha 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
@@ -269,7 +270,6 @@ ENTRY(chacha20_4block_xor_avx2)
 	vmovdqa		ROT16(%rip),%ymm9
 
 	mov		%rcx,%rax
-	mov		$10,%ecx
 
 .Ldoubleround4:
 
@@ -389,7 +389,7 @@ ENTRY(chacha20_4block_xor_avx2)
 	vpshufd		$0x39,%ymm3,%ymm3
 	vpshufd		$0x39,%ymm7,%ymm7
 
-	dec		%ecx
+	sub		$2,%r8d
 	jnz		.Ldoubleround4
 
 	# o0 = i0 ^ (x0 + s0), first block
@@ -533,15 +533,16 @@ ENTRY(chacha20_4block_xor_avx2)
 	lea		-8(%r10),%rsp
 	jmp		.Ldone4
 
-ENDPROC(chacha20_4block_xor_avx2)
+ENDPROC(chacha_4block_xor_avx2)
 
-ENTRY(chacha20_8block_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 ChaCha20 blocks by loading
+	# 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
@@ -588,8 +589,6 @@ ENTRY(chacha20_8block_xor_avx2)
 	# 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
@@ -775,7 +774,7 @@ ENTRY(chacha20_8block_xor_avx2)
 	vpsrld		$25,%ymm4,%ymm4
 	vpor		%ymm0,%ymm4,%ymm4
 
-	dec		%ecx
+	sub		$2,%r8d
 	jnz		.Ldoubleround8
 
 	# x0..15[0-3] += s[0..15]
@@ -1023,4 +1022,4 @@ ENTRY(chacha20_8block_xor_avx2)
 
 	jmp		.Ldone8
 
-ENDPROC(chacha20_8block_xor_avx2)
+ENDPROC(chacha_8block_xor_avx2)
diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha-ssse3-x86_64.S
similarity index 96%
rename from arch/x86/crypto/chacha20-ssse3-x86_64.S
rename to arch/x86/crypto/chacha-ssse3-x86_64.S
index 45e4ccdd9c98b..613f80ae98576 100644
--- a/arch/x86/crypto/chacha20-ssse3-x86_64.S
+++ b/arch/x86/crypto/chacha-ssse3-x86_64.S
@@ -1,5 +1,5 @@
 /*
- * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSSE3 functions
+ * ChaCha 256-bit cipher algorithm, x64 SSSE3 functions
  *
  * Copyright (C) 2015 Martin Willi
  *
@@ -24,7 +24,7 @@ CTRINC:	.octa 0x00000003000000020000000100000000
 .text
 
 /*
- * chacha20_permute - permute one block
+ * 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
@@ -32,13 +32,14 @@ CTRINC:	.octa 0x00000003000000020000000100000000
  * done with the slightly better performing SSSE3 byte shuffling, 7/12-bit word
  * rotation uses traditional shift+OR.
  *
- * Clobbers: %ecx, %xmm4-%xmm7
+ * The round count is given in %r8d.
+ *
+ * Clobbers: %r8d, %xmm4-%xmm7
  */
-chacha20_permute:
+chacha_permute:
 
 	movdqa		ROT8(%rip),%xmm4
 	movdqa		ROT16(%rip),%xmm5
-	mov		$10,%ecx
 
 .Ldoubleround:
 	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
@@ -107,17 +108,18 @@ chacha20_permute:
 	# x3 = shuffle32(x3, MASK(0, 3, 2, 1))
 	pshufd		$0x39,%xmm3,%xmm3
 
-	dec		%ecx
+	sub		$2,%r8d
 	jnz		.Ldoubleround
 
 	ret
-ENDPROC(chacha20_permute)
+ENDPROC(chacha_permute)
 
-ENTRY(chacha20_block_xor_ssse3)
+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
 
 	# x0..3 = s0..3
 	movdqa		0x00(%rdi),%xmm0
@@ -130,7 +132,7 @@ ENTRY(chacha20_block_xor_ssse3)
 	movdqa		%xmm3,%xmm11
 
 	mov		%rcx,%rax
-	call		chacha20_permute
+	call		chacha_permute
 
 	# o0 = i0 ^ (x0 + s0)
 	paddd		%xmm8,%xmm0
@@ -196,32 +198,35 @@ ENTRY(chacha20_block_xor_ssse3)
 	lea		-8(%r10),%rsp
 	jmp		.Ldone
 
-ENDPROC(chacha20_block_xor_ssse3)
+ENDPROC(chacha_block_xor_ssse3)
 
-ENTRY(hchacha20_block_ssse3)
+ENTRY(hchacha_block_ssse3)
 	# %rdi: Input state matrix, s
 	# %rsi: output (8 32-bit words)
+	# %edx: nrounds
 
 	movdqa		0x00(%rdi),%xmm0
 	movdqa		0x10(%rdi),%xmm1
 	movdqa		0x20(%rdi),%xmm2
 	movdqa		0x30(%rdi),%xmm3
 
-	call		chacha20_permute
+	mov		%edx,%r8d
+	call		chacha_permute
 
 	movdqu		%xmm0,0x00(%rsi)
 	movdqu		%xmm3,0x10(%rsi)
 
 	ret
-ENDPROC(hchacha20_block_ssse3)
+ENDPROC(hchacha_block_ssse3)
 
-ENTRY(chacha20_4block_xor_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 ChaCha20 blocks by loading the
+	# 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
@@ -274,8 +279,6 @@ ENTRY(chacha20_4block_xor_ssse3)
 	# x12 += counter values 0-3
 	paddd		%xmm1,%xmm12
 
-	mov		$10,%ecx
-
 .Ldoubleround4:
 	# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
 	movdqa		0x00(%rsp),%xmm0
@@ -493,7 +496,7 @@ ENTRY(chacha20_4block_xor_ssse3)
 	psrld		$25,%xmm4
 	por		%xmm0,%xmm4
 
-	dec		%ecx
+	sub		$2,%r8d
 	jnz		.Ldoubleround4
 
 	# x0[0-3] += s0[0]
@@ -784,4 +787,4 @@ ENTRY(chacha20_4block_xor_ssse3)
 
 	jmp		.Ldone4
 
-ENDPROC(chacha20_4block_xor_ssse3)
+ENDPROC(chacha_4block_xor_ssse3)
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha_glue.c
similarity index 56%
rename from arch/x86/crypto/chacha20_glue.c
rename to arch/x86/crypto/chacha_glue.c
index ca85b5d2c4751..c643993a29c9f 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -1,5 +1,6 @@
 /*
- * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
+ * x64 SIMD accelerated ChaCha and XChaCha stream ciphers,
+ * including ChaCha20 (RFC7539)
  *
  * Copyright (C) 2015 Martin Willi
  *
@@ -17,85 +18,85 @@
 #include <asm/fpu/api.h>
 #include <asm/simd.h>
 
-#define CHACHA20_STATE_ALIGN 16
+#define CHACHA_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);
+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 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;
+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;
 #endif
 
-static unsigned int chacha20_advance(unsigned int len, unsigned int maxblocks)
+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 chacha20_dosimd(u32 *state, u8 *dst, const u8 *src,
-			    unsigned int bytes)
+static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds)
 {
 #ifdef CONFIG_AS_AVX2
-	if (chacha20_use_avx2) {
+	if (chacha_use_avx2) {
 		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
-			chacha20_8block_xor_avx2(state, dst, src, bytes);
+			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) {
-			chacha20_8block_xor_avx2(state, dst, src, bytes);
-			state[12] += chacha20_advance(bytes, 8);
+			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
+			state[12] += chacha_advance(bytes, 8);
 			return;
 		}
 		if (bytes > CHACHA_BLOCK_SIZE * 2) {
-			chacha20_4block_xor_avx2(state, dst, src, bytes);
-			state[12] += chacha20_advance(bytes, 4);
+			chacha_4block_xor_avx2(state, dst, src, bytes, nrounds);
+			state[12] += chacha_advance(bytes, 4);
 			return;
 		}
 		if (bytes > CHACHA_BLOCK_SIZE) {
-			chacha20_2block_xor_avx2(state, dst, src, bytes);
-			state[12] += chacha20_advance(bytes, 2);
+			chacha_2block_xor_avx2(state, dst, src, bytes, nrounds);
+			state[12] += chacha_advance(bytes, 2);
 			return;
 		}
 	}
 #endif
 	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
-		chacha20_4block_xor_ssse3(state, dst, src, bytes);
+		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) {
-		chacha20_4block_xor_ssse3(state, dst, src, bytes);
-		state[12] += chacha20_advance(bytes, 4);
+		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
+		state[12] += chacha_advance(bytes, 4);
 		return;
 	}
 	if (bytes) {
-		chacha20_block_xor_ssse3(state, dst, src, bytes);
+		chacha_block_xor_ssse3(state, dst, src, bytes, nrounds);
 		state[12]++;
 	}
 }
 
-static int chacha20_simd_stream_xor(struct skcipher_request *req,
-				    struct chacha_ctx *ctx, u8 *iv)
+static int chacha_simd_stream_xor(struct skcipher_request *req,
+				  struct chacha_ctx *ctx, u8 *iv)
 {
 	struct skcipher_walk walk;
 	u32 *state, state_buf[16 + 2] __aligned(8);
 	int err;
 
-	BUILD_BUG_ON(CHACHA20_STATE_ALIGN != 16);
-	state = PTR_ALIGN(state_buf + 0, CHACHA20_STATE_ALIGN);
+	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
+	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
 
 	err = skcipher_walk_virt(&walk, req, false);
 
@@ -108,8 +109,8 @@ static int chacha20_simd_stream_xor(struct skcipher_request *req,
 			nbytes = round_down(nbytes, walk.stride);
 
 		kernel_fpu_begin();
-		chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
-				nbytes);
+		chacha_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
+			      nbytes, ctx->nrounds);
 		kernel_fpu_end();
 
 		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
@@ -118,7 +119,7 @@ static int chacha20_simd_stream_xor(struct skcipher_request *req,
 	return err;
 }
 
-static int chacha20_simd(struct skcipher_request *req)
+static int chacha_simd(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
@@ -126,10 +127,10 @@ static int chacha20_simd(struct skcipher_request *req)
 	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !irq_fpu_usable())
 		return crypto_chacha_crypt(req);
 
-	return chacha20_simd_stream_xor(req, ctx, req->iv);
+	return chacha_simd_stream_xor(req, ctx, req->iv);
 }
 
-static int xchacha20_simd(struct skcipher_request *req)
+static int xchacha_simd(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
@@ -140,17 +141,18 @@ static int xchacha20_simd(struct skcipher_request *req)
 	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);
+	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();
-	hchacha20_block_ssse3(state, subctx.key);
+	hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
 	kernel_fpu_end();
+	subctx.nrounds = ctx->nrounds;
 
 	memcpy(&real_iv[0], req->iv + 24, 8);
 	memcpy(&real_iv[8], req->iv + 16, 8);
-	return chacha20_simd_stream_xor(req, &subctx, real_iv);
+	return chacha_simd_stream_xor(req, &subctx, real_iv);
 }
 
 static struct skcipher_alg algs[] = {
@@ -167,8 +169,8 @@ static struct skcipher_alg algs[] = {
 		.ivsize			= CHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
 		.setkey			= crypto_chacha20_setkey,
-		.encrypt		= chacha20_simd,
-		.decrypt		= chacha20_simd,
+		.encrypt		= chacha_simd,
+		.decrypt		= chacha_simd,
 	}, {
 		.base.cra_name		= "xchacha20",
 		.base.cra_driver_name	= "xchacha20-simd",
@@ -182,35 +184,35 @@ static struct skcipher_alg algs[] = {
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
 		.setkey			= crypto_chacha20_setkey,
-		.encrypt		= xchacha20_simd,
-		.decrypt		= xchacha20_simd,
+		.encrypt		= xchacha_simd,
+		.decrypt		= xchacha_simd,
 	},
 };
 
-static int __init chacha20_simd_mod_init(void)
+static int __init chacha_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);
+	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);
 #endif
 	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
 }
 
-static void __exit chacha20_simd_mod_fini(void)
+static void __exit chacha_simd_mod_fini(void)
 {
 	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
 }
 
-module_init(chacha20_simd_mod_init);
-module_exit(chacha20_simd_mod_fini);
+module_init(chacha_simd_mod_init);
+module_exit(chacha_simd_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
-MODULE_DESCRIPTION("chacha20 cipher algorithm, SIMD accelerated");
+MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (x64 SIMD accelerated)");
 MODULE_ALIAS_CRYPTO("chacha20");
 MODULE_ALIAS_CRYPTO("chacha20-simd");
 MODULE_ALIAS_CRYPTO("xchacha20");
-- 
2.19.2

[PATCH 6/6] crypto: x86/chacha - add XChaCha12 support

[Eric Biggers]

From: Eric Biggers <ebiggers@google.com>

Now that the x86_64 SIMD implementations of ChaCha20 and XChaCha20 have
been refactored to support varying the number of rounds, add support for
XChaCha12.  This is identical to XChaCha20 except for the number of
rounds, which is 12 instead of 20.  This can be used by Adiantum.

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 arch/x86/crypto/chacha_glue.c | 17 +++++++++++++++++
 crypto/Kconfig                |  4 ++--
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index c643993a29c9f..1aa43cdd5f7cb 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -186,6 +186,21 @@ static struct skcipher_alg algs[] = {
 		.setkey			= crypto_chacha20_setkey,
 		.encrypt		= xchacha_simd,
 		.decrypt		= xchacha_simd,
+	}, {
+		.base.cra_name		= "xchacha12",
+		.base.cra_driver_name	= "xchacha12-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_chacha12_setkey,
+		.encrypt		= xchacha_simd,
+		.decrypt		= xchacha_simd,
 	},
 };
 
@@ -217,3 +232,5 @@ MODULE_ALIAS_CRYPTO("chacha20");
 MODULE_ALIAS_CRYPTO("chacha20-simd");
 MODULE_ALIAS_CRYPTO("xchacha20");
 MODULE_ALIAS_CRYPTO("xchacha20-simd");
+MODULE_ALIAS_CRYPTO("xchacha12");
+MODULE_ALIAS_CRYPTO("xchacha12-simd");
diff --git a/crypto/Kconfig b/crypto/Kconfig
index ecfc10a3e9f3e..a3ee51a711447 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1473,8 +1473,8 @@ config CRYPTO_CHACHA20_X86_64
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_CHACHA20
 	help
-	  SSSE3 and AVX2 optimized implementations of the ChaCha20 and XChaCha20
-	  stream ciphers.
+	  SSSE3 and AVX2 optimized implementations of the ChaCha20, XChaCha20,
+	  and XChaCha12 stream ciphers.
 
 config CRYPTO_SEED
 	tristate "SEED cipher algorithm"
-- 
2.19.2