14 files changed, 5721 insertions, 243 deletions

diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 043b0b18bf7e..2674de6ada1f 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -30,7 +30,7 @@ config CRYPTO_SHA1_ARM_NEON
 
 config CRYPTO_SHA1_ARM_CE
 	tristate "SHA1 digest algorithm (ARM v8 Crypto Extensions)"
-	depends on KERNEL_MODE_NEON
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
 	select CRYPTO_SHA1_ARM
 	select CRYPTO_HASH
 	help
@@ -39,7 +39,7 @@ config CRYPTO_SHA1_ARM_CE
 
 config CRYPTO_SHA2_ARM_CE
 	tristate "SHA-224/256 digest algorithm (ARM v8 Crypto Extensions)"
-	depends on KERNEL_MODE_NEON
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
 	select CRYPTO_SHA256_ARM
 	select CRYPTO_HASH
 	help
@@ -81,7 +81,7 @@ config CRYPTO_AES_ARM
 config CRYPTO_AES_ARM_BS
 	tristate "Bit sliced AES using NEON instructions"
 	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
 	select CRYPTO_SIMD
 	help
@@ -96,8 +96,8 @@ config CRYPTO_AES_ARM_BS
 
 config CRYPTO_AES_ARM_CE
 	tristate "Accelerated AES using ARMv8 Crypto Extensions"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
 	select CRYPTO_SIMD
 	help
@@ -106,7 +106,7 @@ config CRYPTO_AES_ARM_CE
 
 config CRYPTO_GHASH_ARM_CE
 	tristate "PMULL-accelerated GHASH using NEON/ARMv8 Crypto Extensions"
-	depends on KERNEL_MODE_NEON
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
 	select CRYPTO_HASH
 	select CRYPTO_CRYPTD
 	select CRYPTO_GF128MUL
@@ -118,23 +118,35 @@ config CRYPTO_GHASH_ARM_CE
 
 config CRYPTO_CRCT10DIF_ARM_CE
 	tristate "CRCT10DIF digest algorithm using PMULL instructions"
-	depends on KERNEL_MODE_NEON && CRC_T10DIF
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	depends on CRC_T10DIF
 	select CRYPTO_HASH
 
 config CRYPTO_CRC32_ARM_CE
 	tristate "CRC32(C) digest algorithm using CRC and/or PMULL instructions"
-	depends on KERNEL_MODE_NEON && CRC32
+	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	depends on CRC32
 	select CRYPTO_HASH
 
 config CRYPTO_CHACHA20_NEON
-	tristate "NEON accelerated ChaCha stream cipher algorithms"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
-	select CRYPTO_CHACHA20
+	tristate "NEON and scalar accelerated ChaCha stream cipher algorithms"
+	select CRYPTO_SKCIPHER
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_ARM
+	tristate "Accelerated scalar and SIMD Poly1305 hash implementations"
+	select CRYPTO_HASH
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
 
 config CRYPTO_NHPOLY1305_NEON
 	tristate "NEON accelerated NHPoly1305 hash function (for Adiantum)"
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_NHPOLY1305
 
+config CRYPTO_CURVE25519_NEON
+	tristate "NEON accelerated Curve25519 scalar multiplication library"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_LIB_CURVE25519_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CURVE25519
+
 endif
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 4180f3a13512..b745c17d356f 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -10,34 +10,16 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
+obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.o
 obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
+obj-$(CONFIG_CRYPTO_CURVE25519_NEON) += curve25519-neon.o
 
-ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
-ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
-ce-obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o
-ce-obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
-ce-obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM_CE) += crct10dif-arm-ce.o
-crc-obj-$(CONFIG_CRYPTO_CRC32_ARM_CE) += crc32-arm-ce.o
-
-ifneq ($(crc-obj-y)$(crc-obj-m),)
-ifeq ($(call as-instr,.arch armv8-a\n.arch_extension crc,y,n),y)
-ce-obj-y += $(crc-obj-y)
-ce-obj-m += $(crc-obj-m)
-else
-$(warning These CRC Extensions modules need binutils 2.23 or higher)
-$(warning $(crc-obj-y) $(crc-obj-m))
-endif
-endif
-
-ifneq ($(ce-obj-y)$(ce-obj-m),)
-ifeq ($(call as-instr,.fpu crypto-neon-fp-armv8,y,n),y)
-obj-y += $(ce-obj-y)
-obj-m += $(ce-obj-m)
-else
-$(warning These ARMv8 Crypto Extensions modules need binutils 2.23 or higher)
-$(warning $(ce-obj-y) $(ce-obj-m))
-endif
-endif
+obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
+obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
+obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o
+obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM_CE) += crct10dif-arm-ce.o
+obj-$(CONFIG_CRYPTO_CRC32_ARM_CE) += crc32-arm-ce.o
 
 aes-arm-y	:= aes-cipher-core.o aes-cipher-glue.o
 aes-arm-bs-y	:= aes-neonbs-core.o aes-neonbs-glue.o
@@ -53,13 +35,19 @@ aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
 ghash-arm-ce-y	:= ghash-ce-core.o ghash-ce-glue.o
 crct10dif-arm-ce-y	:= crct10dif-ce-core.o crct10dif-ce-glue.o
 crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o
-chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
+chacha-neon-y := chacha-scalar-core.o chacha-glue.o
+chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o
+poly1305-arm-y := poly1305-core.o poly1305-glue.o
 nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
+curve25519-neon-y := curve25519-core.o curve25519-glue.o
 
 ifdef REGENERATE_ARM_CRYPTO
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)
 
+$(src)/poly1305-core.S_shipped: $(src)/poly1305-armv4.pl
+	$(call cmd,perl)
+
 $(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
 	$(call cmd,perl)
 
@@ -67,4 +55,9 @@ $(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
 	$(call cmd,perl)
 endif
 
-clean-files += sha256-core.S sha512-core.S
+clean-files += poly1305-core.S sha256-core.S sha512-core.S
+
+# massage the perlasm code a bit so we only get the NEON routine if we need it
+poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5
+poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7
+AFLAGS_poly1305-core.o += $(poly1305-aflags-y)
diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c
new file mode 100644
index 000000000000..6ebbb2b241d2
--- /dev/null
+++ b/arch/arm/crypto/chacha-glue.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM NEON accelerated ChaCha and XChaCha stream ciphers,
+ * including ChaCha20 (RFC7539)
+ *
+ * Copyright (C) 2016-2019 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/chacha.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cputype.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void chacha_block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
+				      int nrounds);
+asmlinkage void chacha_4block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
+				       int nrounds);
+asmlinkage void hchacha_block_arm(const u32 *state, u32 *out, int nrounds);
+asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
+
+asmlinkage void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
+			     const u32 *state, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_neon);
+
+static inline bool neon_usable(void)
+{
+	return static_branch_likely(&use_neon) && crypto_simd_usable();
+}
+
+static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds)
+{
+	u8 buf[CHACHA_BLOCK_SIZE];
+
+	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
+		chacha_4block_xor_neon(state, dst, src, nrounds);
+		bytes -= CHACHA_BLOCK_SIZE * 4;
+		src += CHACHA_BLOCK_SIZE * 4;
+		dst += CHACHA_BLOCK_SIZE * 4;
+		state[12] += 4;
+	}
+	while (bytes >= CHACHA_BLOCK_SIZE) {
+		chacha_block_xor_neon(state, dst, src, nrounds);
+		bytes -= CHACHA_BLOCK_SIZE;
+		src += CHACHA_BLOCK_SIZE;
+		dst += CHACHA_BLOCK_SIZE;
+		state[12]++;
+	}
+	if (bytes) {
+		memcpy(buf, src, bytes);
+		chacha_block_xor_neon(state, buf, buf, nrounds);
+		memcpy(dst, buf, bytes);
+	}
+}
+
+void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
+{
+	if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable()) {
+		hchacha_block_arm(state, stream, nrounds);
+	} else {
+		kernel_neon_begin();
+		hchacha_block_neon(state, stream, nrounds);
+		kernel_neon_end();
+	}
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+{
+	chacha_init_generic(state, key, iv);
+}
+EXPORT_SYMBOL(chacha_init_arch);
+
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+		       int nrounds)
+{
+	if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable() ||
+	    bytes <= CHACHA_BLOCK_SIZE) {
+		chacha_doarm(dst, src, bytes, state, nrounds);
+		state[12] += DIV_ROUND_UP(bytes, CHACHA_BLOCK_SIZE);
+		return;
+	}
+
+	kernel_neon_begin();
+	chacha_doneon(state, dst, src, bytes, nrounds);
+	kernel_neon_end();
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+static int chacha_stream_xor(struct skcipher_request *req,
+			     const struct chacha_ctx *ctx, const u8 *iv,
+			     bool neon)
+{
+	struct skcipher_walk walk;
+	u32 state[16];
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	chacha_init_generic(state, ctx->key, iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
+
+		if (!neon) {
+			chacha_doarm(walk.dst.virt.addr, walk.src.virt.addr,
+				     nbytes, state, ctx->nrounds);
+			state[12] += DIV_ROUND_UP(nbytes, CHACHA_BLOCK_SIZE);
+		} else {
+			kernel_neon_begin();
+			chacha_doneon(state, walk.dst.virt.addr,
+				      walk.src.virt.addr, nbytes, ctx->nrounds);
+			kernel_neon_end();
+		}
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+
+	return err;
+}
+
+static int do_chacha(struct skcipher_request *req, bool neon)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	return chacha_stream_xor(req, ctx, req->iv, neon);
+}
+
+static int chacha_arm(struct skcipher_request *req)
+{
+	return do_chacha(req, false);
+}
+
+static int chacha_neon(struct skcipher_request *req)
+{
+	return do_chacha(req, neon_usable());
+}
+
+static int do_xchacha(struct skcipher_request *req, bool neon)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct chacha_ctx subctx;
+	u32 state[16];
+	u8 real_iv[16];
+
+	chacha_init_generic(state, ctx->key, req->iv);
+
+	if (!neon) {
+		hchacha_block_arm(state, subctx.key, ctx->nrounds);
+	} else {
+		kernel_neon_begin();
+		hchacha_block_neon(state, subctx.key, ctx->nrounds);
+		kernel_neon_end();
+	}
+	subctx.nrounds = ctx->nrounds;
+
+	memcpy(&real_iv[0], req->iv + 24, 8);
+	memcpy(&real_iv[8], req->iv + 16, 8);
+	return chacha_stream_xor(req, &subctx, real_iv, neon);
+}
+
+static int xchacha_arm(struct skcipher_request *req)
+{
+	return do_xchacha(req, false);
+}
+
+static int xchacha_neon(struct skcipher_request *req)
+{
+	return do_xchacha(req, neon_usable());
+}
+
+static struct skcipher_alg arm_algs[] = {
+	{
+		.base.cra_name		= "chacha20",
+		.base.cra_driver_name	= "chacha20-arm",
+		.base.cra_priority	= 200,
+		.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			= chacha20_setkey,
+		.encrypt		= chacha_arm,
+		.decrypt		= chacha_arm,
+	}, {
+		.base.cra_name		= "xchacha20",
+		.base.cra_driver_name	= "xchacha20-arm",
+		.base.cra_priority	= 200,
+		.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			= chacha20_setkey,
+		.encrypt		= xchacha_arm,
+		.decrypt		= xchacha_arm,
+	}, {
+		.base.cra_name		= "xchacha12",
+		.base.cra_driver_name	= "xchacha12-arm",
+		.base.cra_priority	= 200,
+		.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			= chacha12_setkey,
+		.encrypt		= xchacha_arm,
+		.decrypt		= xchacha_arm,
+	},
+};
+
+static struct skcipher_alg neon_algs[] = {
+	{
+		.base.cra_name		= "chacha20",
+		.base.cra_driver_name	= "chacha20-neon",
+		.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,
+		.walksize		= 4 * CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= chacha_neon,
+		.decrypt		= chacha_neon,
+	}, {
+		.base.cra_name		= "xchacha20",
+		.base.cra_driver_name	= "xchacha20-neon",
+		.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,
+		.walksize		= 4 * CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= xchacha_neon,
+		.decrypt		= xchacha_neon,
+	}, {
+		.base.cra_name		= "xchacha12",
+		.base.cra_driver_name	= "xchacha12-neon",
+		.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,
+		.walksize		= 4 * CHACHA_BLOCK_SIZE,
+		.setkey			= chacha12_setkey,
+		.encrypt		= xchacha_neon,
+		.decrypt		= xchacha_neon,
+	}
+};
+
+static int __init chacha_simd_mod_init(void)
+{
+	int err = 0;
+
+	if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER)) {
+		err = crypto_register_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
+		if (err)
+			return err;
+	}
+
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON)) {
+		int i;
+
+		switch (read_cpuid_part()) {
+		case ARM_CPU_PART_CORTEX_A7:
+		case ARM_CPU_PART_CORTEX_A5:
+			/*
+			 * The Cortex-A7 and Cortex-A5 do not perform well with
+			 * the NEON implementation but do incredibly with the
+			 * scalar one and use less power.
+			 */
+			for (i = 0; i < ARRAY_SIZE(neon_algs); i++)
+				neon_algs[i].base.cra_priority = 0;
+			break;
+		default:
+			static_branch_enable(&use_neon);
+		}
+
+		if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER)) {
+			err = crypto_register_skciphers(neon_algs, ARRAY_SIZE(neon_algs));
+			if (err)
+				crypto_unregister_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
+		}
+	}
+	return err;
+}
+
+static void __exit chacha_simd_mod_fini(void)
+{
+	if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER)) {
+		crypto_unregister_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
+		if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON))
+			crypto_unregister_skciphers(neon_algs, ARRAY_SIZE(neon_algs));
+	}
+}
+
+module_init(chacha_simd_mod_init);
+module_exit(chacha_simd_mod_fini);
+
+MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (scalar and NEON accelerated)");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-arm");
+MODULE_ALIAS_CRYPTO("xchacha20");
+MODULE_ALIAS_CRYPTO("xchacha20-arm");
+MODULE_ALIAS_CRYPTO("xchacha12");
+MODULE_ALIAS_CRYPTO("xchacha12-arm");
+#ifdef CONFIG_KERNEL_MODE_NEON
+MODULE_ALIAS_CRYPTO("chacha20-neon");
+MODULE_ALIAS_CRYPTO("xchacha20-neon");
+MODULE_ALIAS_CRYPTO("xchacha12-neon");
+#endif
diff --git a/arch/arm/crypto/chacha-neon-glue.c b/arch/arm/crypto/chacha-neon-glue.c
deleted file mode 100644
index a8e9b534c8da..000000000000
--- a/arch/arm/crypto/chacha-neon-glue.c
+++ /dev/null
@@ -1,202 +0,0 @@
-/*
- * ARM NEON accelerated ChaCha and XChaCha stream ciphers,
- * including ChaCha20 (RFC7539)
- *
- * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Based on:
- * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
- *
- * Copyright (C) 2015 Martin Willi
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <crypto/algapi.h>
-#include <crypto/chacha.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-
-asmlinkage void chacha_block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
-				      int nrounds);
-asmlinkage void chacha_4block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
-				       int nrounds);
-asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
-
-static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
-			  unsigned int bytes, int nrounds)
-{
-	u8 buf[CHACHA_BLOCK_SIZE];
-
-	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
-		chacha_4block_xor_neon(state, dst, src, nrounds);
-		bytes -= CHACHA_BLOCK_SIZE * 4;
-		src += CHACHA_BLOCK_SIZE * 4;
-		dst += CHACHA_BLOCK_SIZE * 4;
-		state[12] += 4;
-	}
-	while (bytes >= CHACHA_BLOCK_SIZE) {
-		chacha_block_xor_neon(state, dst, src, nrounds);
-		bytes -= CHACHA_BLOCK_SIZE;
-		src += CHACHA_BLOCK_SIZE;
-		dst += CHACHA_BLOCK_SIZE;
-		state[12]++;
-	}
-	if (bytes) {
-		memcpy(buf, src, bytes);
-		chacha_block_xor_neon(state, buf, buf, nrounds);
-		memcpy(dst, buf, bytes);
-	}
-}
-
-static int chacha_neon_stream_xor(struct skcipher_request *req,
-				  const struct chacha_ctx *ctx, const u8 *iv)
-{
-	struct skcipher_walk walk;
-	u32 state[16];
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	crypto_chacha_init(state, ctx, iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
-
-		kernel_neon_begin();
-		chacha_doneon(state, walk.dst.virt.addr, walk.src.virt.addr,
-			      nbytes, ctx->nrounds);
-		kernel_neon_end();
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-	}
-
-	return err;
-}
-
-static int chacha_neon(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 || !crypto_simd_usable())
-		return crypto_chacha_crypt(req);
-
-	return chacha_neon_stream_xor(req, ctx, req->iv);
-}
-
-static int xchacha_neon(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[16];
-	u8 real_iv[16];
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_xchacha_crypt(req);
-
-	crypto_chacha_init(state, ctx, req->iv);
-
-	kernel_neon_begin();
-	hchacha_block_neon(state, subctx.key, ctx->nrounds);
-	kernel_neon_end();
-	subctx.nrounds = ctx->nrounds;
-
-	memcpy(&real_iv[0], req->iv + 24, 8);
-	memcpy(&real_iv[8], req->iv + 16, 8);
-	return chacha_neon_stream_xor(req, &subctx, real_iv);
-}
-
-static struct skcipher_alg algs[] = {
-	{
-		.base.cra_name		= "chacha20",
-		.base.cra_driver_name	= "chacha20-neon",
-		.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,
-		.walksize		= 4 * CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
-		.encrypt		= chacha_neon,
-		.decrypt		= chacha_neon,
-	}, {
-		.base.cra_name		= "xchacha20",
-		.base.cra_driver_name	= "xchacha20-neon",
-		.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,
-		.walksize		= 4 * CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
-		.encrypt		= xchacha_neon,
-		.decrypt		= xchacha_neon,
-	}, {
-		.base.cra_name		= "xchacha12",
-		.base.cra_driver_name	= "xchacha12-neon",
-		.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,
-		.walksize		= 4 * CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha12_setkey,
-		.encrypt		= xchacha_neon,
-		.decrypt		= xchacha_neon,
-	}
-};
-
-static int __init chacha_simd_mod_init(void)
-{
-	if (!(elf_hwcap & HWCAP_NEON))
-		return -ENODEV;
-
-	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit chacha_simd_mod_fini(void)
-{
-	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-module_init(chacha_simd_mod_init);
-module_exit(chacha_simd_mod_fini);
-
-MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (NEON accelerated)");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-neon");
-MODULE_ALIAS_CRYPTO("xchacha20");
-MODULE_ALIAS_CRYPTO("xchacha20-neon");
-MODULE_ALIAS_CRYPTO("xchacha12");
-MODULE_ALIAS_CRYPTO("xchacha12-neon");
diff --git a/arch/arm/crypto/chacha-scalar-core.S b/arch/arm/crypto/chacha-scalar-core.S
new file mode 100644
index 000000000000..2985b80a45b5
--- /dev/null
+++ b/arch/arm/crypto/chacha-scalar-core.S
@@ -0,0 +1,460 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Google, Inc.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Design notes:
+ *
+ * 16 registers would be needed to hold the state matrix, but only 14 are
+ * available because 'sp' and 'pc' cannot be used.  So we spill the elements
+ * (x8, x9) to the stack and swap them out with (x10, x11).  This adds one
+ * 'ldrd' and one 'strd' instruction per round.
+ *
+ * All rotates are performed using the implicit rotate operand accepted by the
+ * 'add' and 'eor' instructions.  This is faster than using explicit rotate
+ * instructions.  To make this work, we allow the values in the second and last
+ * rows of the ChaCha state matrix (rows 'b' and 'd') to temporarily have the
+ * wrong rotation amount.  The rotation amount is then fixed up just in time
+ * when the values are used.  'brot' is the number of bits the values in row 'b'
+ * need to be rotated right to arrive at the correct values, and 'drot'
+ * similarly for row 'd'.  (brot, drot) start out as (0, 0) but we make it such
+ * that they end up as (25, 24) after every round.
+ */
+
+	// ChaCha state registers
+	X0	.req	r0
+	X1	.req	r1
+	X2	.req	r2
+	X3	.req	r3
+	X4	.req	r4
+	X5	.req	r5
+	X6	.req	r6
+	X7	.req	r7
+	X8_X10	.req	r8	// shared by x8 and x10
+	X9_X11	.req	r9	// shared by x9 and x11
+	X12	.req	r10
+	X13	.req	r11
+	X14	.req	r12
+	X15	.req	r14
+
+.macro __rev		out, in,  t0, t1, t2
+.if __LINUX_ARM_ARCH__ >= 6
+	rev		\out, \in
+.else
+	lsl		\t0, \in, #24
+	and		\t1, \in, #0xff00
+	and		\t2, \in, #0xff0000
+	orr		\out, \t0, \in, lsr #24
+	orr		\out, \out, \t1, lsl #8
+	orr		\out, \out, \t2, lsr #8
+.endif
+.endm
+
+.macro _le32_bswap	x,  t0, t1, t2
+#ifdef __ARMEB__
+	__rev		\x, \x,  \t0, \t1, \t2
+#endif
+.endm
+
+.macro _le32_bswap_4x	a, b, c, d,  t0, t1, t2
+	_le32_bswap	\a,  \t0, \t1, \t2
+	_le32_bswap	\b,  \t0, \t1, \t2
+	_le32_bswap	\c,  \t0, \t1, \t2
+	_le32_bswap	\d,  \t0, \t1, \t2
+.endm
+
+.macro __ldrd		a, b, src, offset
+#if __LINUX_ARM_ARCH__ >= 6
+	ldrd		\a, \b, [\src, #\offset]
+#else
+	ldr		\a, [\src, #\offset]
+	ldr		\b, [\src, #\offset + 4]
+#endif
+.endm
+
+.macro __strd		a, b, dst, offset
+#if __LINUX_ARM_ARCH__ >= 6
+	strd		\a, \b, [\dst, #\offset]
+#else
+	str		\a, [\dst, #\offset]
+	str		\b, [\dst, #\offset + 4]
+#endif
+.endm
+
+.macro _halfround	a1, b1, c1, d1,  a2, b2, c2, d2
+
+	// a += b; d ^= a; d = rol(d, 16);
+	add		\a1, \a1, \b1, ror #brot
+	add		\a2, \a2, \b2, ror #brot
+	eor		\d1, \a1, \d1, ror #drot
+	eor		\d2, \a2, \d2, ror #drot
+	// drot == 32 - 16 == 16
+
+	// c += d; b ^= c; b = rol(b, 12);
+	add		\c1, \c1, \d1, ror #16
+	add		\c2, \c2, \d2, ror #16
+	eor		\b1, \c1, \b1, ror #brot
+	eor		\b2, \c2, \b2, ror #brot
+	// brot == 32 - 12 == 20
+
+	// a += b; d ^= a; d = rol(d, 8);
+	add		\a1, \a1, \b1, ror #20
+	add		\a2, \a2, \b2, ror #20
+	eor		\d1, \a1, \d1, ror #16
+	eor		\d2, \a2, \d2, ror #16
+	// drot == 32 - 8 == 24
+
+	// c += d; b ^= c; b = rol(b, 7);
+	add		\c1, \c1, \d1, ror #24
+	add		\c2, \c2, \d2, ror #24
+	eor		\b1, \c1, \b1, ror #20
+	eor		\b2, \c2, \b2, ror #20
+	// brot == 32 - 7 == 25
+.endm
+
+.macro _doubleround
+
+	// column round
+
+	// quarterrounds: (x0, x4, x8, x12) and (x1, x5, x9, x13)
+	_halfround	X0, X4, X8_X10, X12,  X1, X5, X9_X11, X13
+
+	// save (x8, x9); restore (x10, x11)
+	__strd		X8_X10, X9_X11, sp, 0
+	__ldrd		X8_X10, X9_X11, sp, 8
+
+	// quarterrounds: (x2, x6, x10, x14) and (x3, x7, x11, x15)
+	_halfround	X2, X6, X8_X10, X14,  X3, X7, X9_X11, X15
+
+	.set brot, 25
+	.set drot, 24
+
+	// diagonal round
+
+	// quarterrounds: (x0, x5, x10, x15) and (x1, x6, x11, x12)
+	_halfround	X0, X5, X8_X10, X15,  X1, X6, X9_X11, X12
+
+	// save (x10, x11); restore (x8, x9)
+	__strd		X8_X10, X9_X11, sp, 8
+	__ldrd		X8_X10, X9_X11, sp, 0
+
+	// quarterrounds: (x2, x7, x8, x13) and (x3, x4, x9, x14)
+	_halfround	X2, X7, X8_X10, X13,  X3, X4, X9_X11, X14
+.endm
+
+.macro _chacha_permute	nrounds
+	.set brot, 0
+	.set drot, 0
+	.rept \nrounds / 2
+	 _doubleround
+	.endr
+.endm
+
+.macro _chacha		nrounds
+
+.Lnext_block\@:
+	// Stack: unused0-unused1 x10-x11 x0-x15 OUT IN LEN
+	// Registers contain x0-x9,x12-x15.
+
+	// Do the core ChaCha permutation to update x0-x15.
+	_chacha_permute	\nrounds
+
+	add		sp, #8
+	// Stack: x10-x11 orig_x0-orig_x15 OUT IN LEN
+	// Registers contain x0-x9,x12-x15.
+	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+	// Free up some registers (r8-r12,r14) by pushing (x8-x9,x12-x15).
+	push		{X8_X10, X9_X11, X12, X13, X14, X15}
+
+	// Load (OUT, IN, LEN).
+	ldr		r14, [sp, #96]
+	ldr		r12, [sp, #100]
+	ldr		r11, [sp, #104]
+
+	orr		r10, r14, r12
+
+	// Use slow path if fewer than 64 bytes remain.
+	cmp		r11, #64
+	blt		.Lxor_slowpath\@
+
+	// Use slow path if IN and/or OUT isn't 4-byte aligned.  Needed even on
+	// ARMv6+, since ldmia and stmia (used below) still require alignment.
+	tst		r10, #3
+	bne		.Lxor_slowpath\@
+
+	// Fast path: XOR 64 bytes of aligned data.
+
+	// Stack: x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
+	// Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is OUT.
+	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+	// x0-x3
+	__ldrd		r8, r9, sp, 32
+	__ldrd		r10, r11, sp, 40
+	add		X0, X0, r8
+	add		X1, X1, r9
+	add		X2, X2, r10
+	add		X3, X3, r11
+	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
+	ldmia		r12!, {r8-r11}
+	eor		X0, X0, r8
+	eor		X1, X1, r9
+	eor		X2, X2, r10
+	eor		X3, X3, r11
+	stmia		r14!, {X0-X3}
+
+	// x4-x7
+	__ldrd		r8, r9, sp, 48
+	__ldrd		r10, r11, sp, 56
+	add		X4, r8, X4, ror #brot
+	add		X5, r9, X5, ror #brot
+	ldmia		r12!, {X0-X3}
+	add		X6, r10, X6, ror #brot
+	add		X7, r11, X7, ror #brot
+	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
+	eor		X4, X4, X0
+	eor		X5, X5, X1
+	eor		X6, X6, X2
+	eor		X7, X7, X3
+	stmia		r14!, {X4-X7}
+
+	// x8-x15
+	pop		{r0-r7}			// (x8-x9,x12-x15,x10-x11)
+	__ldrd		r8, r9, sp, 32
+	__ldrd		r10, r11, sp, 40
+	add		r0, r0, r8		// x8
+	add		r1, r1, r9		// x9
+	add		r6, r6, r10		// x10
+	add		r7, r7, r11		// x11
+	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
+	ldmia		r12!, {r8-r11}
+	eor		r0, r0, r8		// x8
+	eor		r1, r1, r9		// x9
+	eor		r6, r6, r10		// x10
+	eor		r7, r7, r11		// x11
+	stmia		r14!, {r0,r1,r6,r7}
+	ldmia		r12!, {r0,r1,r6,r7}
+	__ldrd		r8, r9, sp, 48
+	__ldrd		r10, r11, sp, 56
+	add		r2, r8, r2, ror #drot	// x12
+	add		r3, r9, r3, ror #drot	// x13
+	add		r4, r10, r4, ror #drot	// x14
+	add		r5, r11, r5, ror #drot	// x15
+	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
+	  ldr		r9, [sp, #72]		// load LEN
+	eor		r2, r2, r0		// x12
+	eor		r3, r3, r1		// x13
+	eor		r4, r4, r6		// x14
+	eor		r5, r5, r7		// x15
+	  subs		r9, #64			// decrement and check LEN
+	stmia		r14!, {r2-r5}
+
+	beq		.Ldone\@
+
+.Lprepare_for_next_block\@:
+
+	// Stack: x0-x15 OUT IN LEN
+
+	// Increment block counter (x12)
+	add		r8, #1
+
+	// Store updated (OUT, IN, LEN)
+	str		r14, [sp, #64]
+	str		r12, [sp, #68]
+	str		r9, [sp, #72]
+
+	  mov		r14, sp
+
+	// Store updated block counter (x12)
+	str		r8, [sp, #48]
+
+	  sub		sp, #16
+
+	// Reload state and do next block
+	ldmia		r14!, {r0-r11}		// load x0-x11
+	__strd		r10, r11, sp, 8		// store x10-x11 before state
+	ldmia		r14, {r10-r12,r14}	// load x12-x15
+	b		.Lnext_block\@
+
+.Lxor_slowpath\@:
+	// Slow path: < 64 bytes remaining, or unaligned input or output buffer.
+	// We handle it by storing the 64 bytes of keystream to the stack, then
+	// XOR-ing the needed portion with the data.
+
+	// Allocate keystream buffer
+	sub		sp, #64
+	mov		r14, sp
+
+	// Stack: ks0-ks15 x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
+	// Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is &ks0.
+	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+	// Save keystream for x0-x3
+	__ldrd		r8, r9, sp, 96
+	__ldrd		r10, r11, sp, 104
+	add		X0, X0, r8
+	add		X1, X1, r9
+	add		X2, X2, r10
+	add		X3, X3, r11
+	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
+	stmia		r14!, {X0-X3}
+
+	// Save keystream for x4-x7
+	__ldrd		r8, r9, sp, 112
+	__ldrd		r10, r11, sp, 120
+	add		X4, r8, X4, ror #brot
+	add		X5, r9, X5, ror #brot
+	add		X6, r10, X6, ror #brot
+	add		X7, r11, X7, ror #brot
+	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
+	  add		r8, sp, #64
+	stmia		r14!, {X4-X7}
+
+	// Save keystream for x8-x15
+	ldm		r8, {r0-r7}		// (x8-x9,x12-x15,x10-x11)
+	__ldrd		r8, r9, sp, 128
+	__ldrd		r10, r11, sp, 136
+	add		r0, r0, r8		// x8
+	add		r1, r1, r9		// x9
+	add		r6, r6, r10		// x10
+	add		r7, r7, r11		// x11
+	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
+	stmia		r14!, {r0,r1,r6,r7}
+	__ldrd		r8, r9, sp, 144
+	__ldrd		r10, r11, sp, 152
+	add		r2, r8, r2, ror #drot	// x12
+	add		r3, r9, r3, ror #drot	// x13
+	add		r4, r10, r4, ror #drot	// x14
+	add		r5, r11, r5, ror #drot	// x15
+	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
+	stmia		r14, {r2-r5}
+
+	// Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN
+	// Registers: r8 is block counter, r12 is IN.
+
+	ldr		r9, [sp, #168]		// LEN
+	ldr		r14, [sp, #160]		// OUT
+	cmp		r9, #64
+	  mov		r0, sp
+	movle		r1, r9
+	movgt		r1, #64
+	// r1 is number of bytes to XOR, in range [1, 64]
+
+.if __LINUX_ARM_ARCH__ < 6
+	orr		r2, r12, r14
+	tst		r2, #3			// IN or OUT misaligned?
+	bne		.Lxor_next_byte\@
+.endif
+
+	// XOR a word at a time
+.rept 16
+	subs		r1, #4
+	blt		.Lxor_words_done\@
+	ldr		r2, [r12], #4
+	ldr		r3, [r0], #4
+	eor		r2, r2, r3
+	str		r2, [r14], #4
+.endr
+	b		.Lxor_slowpath_done\@
+.Lxor_words_done\@:
+	ands		r1, r1, #3
+	beq		.Lxor_slowpath_done\@
+
+	// XOR a byte at a time
+.Lxor_next_byte\@:
+	ldrb		r2, [r12], #1
+	ldrb		r3, [r0], #1
+	eor		r2, r2, r3
+	strb		r2, [r14], #1
+	subs		r1, #1
+	bne		.Lxor_next_byte\@
+
+.Lxor_slowpath_done\@:
+	subs		r9, #64
+	add		sp, #96
+	bgt		.Lprepare_for_next_block\@
+
+.Ldone\@:
+.endm	// _chacha
+
+/*
+ * void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
+ *		     const u32 *state, int nrounds);
+ */
+ENTRY(chacha_doarm)
+	cmp		r2, #0			// len == 0?
+	reteq		lr
+
+	ldr		ip, [sp]
+	cmp		ip, #12
+
+	push		{r0-r2,r4-r11,lr}
+
+	// Push state x0-x15 onto stack.
+	// Also store an extra copy of x10-x11 just before the state.
+
+	add		X12, r3, #48
+	ldm		X12, {X12,X13,X14,X15}
+	push		{X12,X13,X14,X15}
+	sub		sp, sp, #64
+
+	__ldrd		X8_X10, X9_X11, r3, 40
+	__strd		X8_X10, X9_X11, sp, 8
+	__strd		X8_X10, X9_X11, sp, 56
+	ldm		r3, {X0-X9_X11}
+	__strd		X0, X1, sp, 16
+	__strd		X2, X3, sp, 24
+	__strd		X4, X5, sp, 32
+	__strd		X6, X7, sp, 40
+	__strd		X8_X10, X9_X11, sp, 48
+
+	beq		1f
+	_chacha		20
+
+0:	add		sp, #76
+	pop		{r4-r11, pc}
+
+1:	_chacha		12
+	b		0b
+ENDPROC(chacha_doarm)
+
+/*
+ * void hchacha_block_arm(const u32 state[16], u32 out[8], int nrounds);
+ */
+ENTRY(hchacha_block_arm)
+	push		{r1,r4-r11,lr}
+
+	cmp		r2, #12			// ChaCha12 ?
+
+	mov		r14, r0
+	ldmia		r14!, {r0-r11}		// load x0-x11
+	push		{r10-r11}		// store x10-x11 to stack
+	ldm		r14, {r10-r12,r14}	// load x12-x15
+	sub		sp, #8
+
+	beq		1f
+	_chacha_permute	20
+
+	// Skip over (unused0-unused1, x10-x11)
+0:	add		sp, #16
+
+	// Fix up rotations of x12-x15
+	ror		X12, X12, #drot
+	ror		X13, X13, #drot
+	  pop		{r4}			// load 'out'
+	ror		X14, X14, #drot
+	ror		X15, X15, #drot
+
+	// Store (x0-x3,x12-x15) to 'out'
+	stm		r4, {X0,X1,X2,X3,X12,X13,X14,X15}
+
+	pop		{r4-r11,pc}
+
+1:	_chacha_permute	12
+	b		0b
+ENDPROC(hchacha_block_arm)
diff --git a/arch/arm/crypto/crct10dif-ce-core.S b/arch/arm/crypto/crct10dif-ce-core.S
index 86be258a803f..46c02c518a30 100644
--- a/arch/arm/crypto/crct10dif-ce-core.S
+++ b/arch/arm/crypto/crct10dif-ce-core.S
@@ -72,7 +72,7 @@
 #endif
 
 	.text
-	.arch		armv7-a
+	.arch		armv8-a
 	.fpu		crypto-neon-fp-armv8
 
 	init_crc	.req	r0
diff --git a/arch/arm/crypto/curve25519-core.S b/arch/arm/crypto/curve25519-core.S
new file mode 100644
index 000000000000..be18af52e7dc
--- /dev/null
+++ b/arch/arm/crypto/curve25519-core.S
@@ -0,0 +1,2062 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * Based on public domain code from Daniel J. Bernstein and Peter Schwabe. This
+ * began from SUPERCOP's curve25519/neon2/scalarmult.s, but has subsequently been
+ * manually reworked for use in kernel space.
+ */
+
+#include <linux/linkage.h>
+
+.text
+.fpu neon
+.arch armv7-a
+.align 4
+
+ENTRY(curve25519_neon)
+	push		{r4-r11, lr}
+	mov		ip, sp
+	sub		r3, sp, #704
+	and		r3, r3, #0xfffffff0
+	mov		sp, r3
+	movw		r4, #0
+	movw		r5, #254
+	vmov.i32	q0, #1
+	vshr.u64	q1, q0, #7
+	vshr.u64	q0, q0, #8
+	vmov.i32	d4, #19
+	vmov.i32	d5, #38
+	add		r6, sp, #480
+	vst1.8		{d2-d3}, [r6, : 128]!
+	vst1.8		{d0-d1}, [r6, : 128]!
+	vst1.8		{d4-d5}, [r6, : 128]
+	add		r6, r3, #0
+	vmov.i32	q2, #0
+	vst1.8		{d4-d5}, [r6, : 128]!
+	vst1.8		{d4-d5}, [r6, : 128]!
+	vst1.8		d4, [r6, : 64]
+	add		r6, r3, #0
+	movw		r7, #960
+	sub		r7, r7, #2
+	neg		r7, r7
+	sub		r7, r7, r7, LSL #7
+	str		r7, [r6]
+	add		r6, sp, #672
+	vld1.8		{d4-d5}, [r1]!
+	vld1.8		{d6-d7}, [r1]
+	vst1.8		{d4-d5}, [r6, : 128]!
+	vst1.8		{d6-d7}, [r6, : 128]
+	sub		r1, r6, #16
+	ldrb		r6, [r1]
+	and		r6, r6, #248
+	strb		r6, [r1]
+	ldrb		r6, [r1, #31]
+	and		r6, r6, #127
+	orr		r6, r6, #64
+	strb		r6, [r1, #31]
+	vmov.i64	q2, #0xffffffff
+	vshr.u64	q3, q2, #7
+	vshr.u64	q2, q2, #6
+	vld1.8		{d8}, [r2]
+	vld1.8		{d10}, [r2]
+	add		r2, r2, #6
+	vld1.8		{d12}, [r2]
+	vld1.8		{d14}, [r2]
+	add		r2, r2, #6
+	vld1.8		{d16}, [r2]
+	add		r2, r2, #4
+	vld1.8		{d18}, [r2]
+	vld1.8		{d20}, [r2]
+	add		r2, r2, #6
+	vld1.8		{d22}, [r2]
+	add		r2, r2, #2
+	vld1.8		{d24}, [r2]
+	vld1.8		{d26}, [r2]
+	vshr.u64	q5, q5, #26
+	vshr.u64	q6, q6, #3
+	vshr.u64	q7, q7, #29
+	vshr.u64	q8, q8, #6
+	vshr.u64	q10, q10, #25
+	vshr.u64	q11, q11, #3
+	vshr.u64	q12, q12, #12
+	vshr.u64	q13, q13, #38
+	vand		q4, q4, q2
+	vand		q6, q6, q2
+	vand		q8, q8, q2
+	vand		q10, q10, q2
+	vand		q2, q12, q2
+	vand		q5, q5, q3
+	vand		q7, q7, q3
+	vand		q9, q9, q3
+	vand		q11, q11, q3
+	vand		q3, q13, q3
+	add		r2, r3, #48
+	vadd.i64	q12, q4, q1
+	vadd.i64	q13, q10, q1
+	vshr.s64	q12, q12, #26
+	vshr.s64	q13, q13, #26
+	vadd.i64	q5, q5, q12
+	vshl.i64	q12, q12, #26
+	vadd.i64	q14, q5, q0
+	vadd.i64	q11, q11, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q15, q11, q0
+	vsub.i64	q4, q4, q12
+	vshr.s64	q12, q14, #25
+	vsub.i64	q10, q10, q13
+	vshr.s64	q13, q15, #25
+	vadd.i64	q6, q6, q12
+	vshl.i64	q12, q12, #25
+	vadd.i64	q14, q6, q1
+	vadd.i64	q2, q2, q13
+	vsub.i64	q5, q5, q12
+	vshr.s64	q12, q14, #26
+	vshl.i64	q13, q13, #25
+	vadd.i64	q14, q2, q1
+	vadd.i64	q7, q7, q12
+	vshl.i64	q12, q12, #26
+	vadd.i64	q15, q7, q0
+	vsub.i64	q11, q11, q13
+	vshr.s64	q13, q14, #26
+	vsub.i64	q6, q6, q12
+	vshr.s64	q12, q15, #25
+	vadd.i64	q3, q3, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q14, q3, q0
+	vadd.i64	q8, q8, q12
+	vshl.i64	q12, q12, #25
+	vadd.i64	q15, q8, q1
+	add		r2, r2, #8
+	vsub.i64	q2, q2, q13
+	vshr.s64	q13, q14, #25
+	vsub.i64	q7, q7, q12
+	vshr.s64	q12, q15, #26
+	vadd.i64	q14, q13, q13
+	vadd.i64	q9, q9, q12
+	vtrn.32		d12, d14
+	vshl.i64	q12, q12, #26
+	vtrn.32		d13, d15
+	vadd.i64	q0, q9, q0
+	vadd.i64	q4, q4, q14
+	vst1.8		d12, [r2, : 64]!
+	vshl.i64	q6, q13, #4
+	vsub.i64	q7, q8, q12
+	vshr.s64	q0, q0, #25
+	vadd.i64	q4, q4, q6
+	vadd.i64	q6, q10, q0
+	vshl.i64	q0, q0, #25
+	vadd.i64	q8, q6, q1
+	vadd.i64	q4, q4, q13
+	vshl.i64	q10, q13, #25
+	vadd.i64	q1, q4, q1
+	vsub.i64	q0, q9, q0
+	vshr.s64	q8, q8, #26
+	vsub.i64	q3, q3, q10
+	vtrn.32		d14, d0
+	vshr.s64	q1, q1, #26
+	vtrn.32		d15, d1
+	vadd.i64	q0, q11, q8
+	vst1.8		d14, [r2, : 64]
+	vshl.i64	q7, q8, #26
+	vadd.i64	q5, q5, q1
+	vtrn.32		d4, d6
+	vshl.i64	q1, q1, #26
+	vtrn.32		d5, d7
+	vsub.i64	q3, q6, q7
+	add		r2, r2, #16
+	vsub.i64	q1, q4, q1
+	vst1.8		d4, [r2, : 64]
+	vtrn.32		d6, d0
+	vtrn.32		d7, d1
+	sub		r2, r2, #8
+	vtrn.32		d2, d10
+	vtrn.32		d3, d11
+	vst1.8		d6, [r2, : 64]
+	sub		r2, r2, #24
+	vst1.8		d2, [r2, : 64]
+	add		r2, r3, #96
+	vmov.i32	q0, #0
+	vmov.i64	d2, #0xff
+	vmov.i64	d3, #0
+	vshr.u32	q1, q1, #7
+	vst1.8		{d2-d3}, [r2, : 128]!
+	vst1.8		{d0-d1}, [r2, : 128]!
+	vst1.8		d0, [r2, : 64]
+	add		r2, r3, #144
+	vmov.i32	q0, #0
+	vst1.8		{d0-d1}, [r2, : 128]!
+	vst1.8		{d0-d1}, [r2, : 128]!
+	vst1.8		d0, [r2, : 64]
+	add		r2, r3, #240
+	vmov.i32	q0, #0
+	vmov.i64	d2, #0xff
+	vmov.i64	d3, #0
+	vshr.u32	q1, q1, #7
+	vst1.8		{d2-d3}, [r2, : 128]!
+	vst1.8		{d0-d1}, [r2, : 128]!
+	vst1.8		d0, [r2, : 64]
+	add		r2, r3, #48
+	add		r6, r3, #192
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d4}, [r2, : 64]
+	vst1.8		{d0-d1}, [r6, : 128]!
+	vst1.8		{d2-d3}, [r6, : 128]!
+	vst1.8		d4, [r6, : 64]
+.Lmainloop:
+	mov		r2, r5, LSR #3
+	and		r6, r5, #7
+	ldrb		r2, [r1, r2]
+	mov		r2, r2, LSR r6
+	and		r2, r2, #1
+	str		r5, [sp, #456]
+	eor		r4, r4, r2
+	str		r2, [sp, #460]
+	neg		r2, r4
+	add		r4, r3, #96
+	add		r5, r3, #192
+	add		r6, r3, #144
+	vld1.8		{d8-d9}, [r4, : 128]!
+	add		r7, r3, #240
+	vld1.8		{d10-d11}, [r5, : 128]!
+	veor		q6, q4, q5
+	vld1.8		{d14-d15}, [r6, : 128]!
+	vdup.i32	q8, r2
+	vld1.8		{d18-d19}, [r7, : 128]!
+	veor		q10, q7, q9
+	vld1.8		{d22-d23}, [r4, : 128]!
+	vand		q6, q6, q8
+	vld1.8		{d24-d25}, [r5, : 128]!
+	vand		q10, q10, q8
+	vld1.8		{d26-d27}, [r6, : 128]!
+	veor		q4, q4, q6
+	vld1.8		{d28-d29}, [r7, : 128]!
+	veor		q5, q5, q6
+	vld1.8		{d0}, [r4, : 64]
+	veor		q6, q7, q10
+	vld1.8		{d2}, [r5, : 64]
+	veor		q7, q9, q10
+	vld1.8		{d4}, [r6, : 64]
+	veor		q9, q11, q12
+	vld1.8		{d6}, [r7, : 64]
+	veor		q10, q0, q1
+	sub		r2, r4, #32
+	vand		q9, q9, q8
+	sub		r4, r5, #32
+	vand		q10, q10, q8
+	sub		r5, r6, #32
+	veor		q11, q11, q9
+	sub		r6, r7, #32
+	veor		q0, q0, q10
+	veor		q9, q12, q9
+	veor		q1, q1, q10
+	veor		q10, q13, q14
+	veor		q12, q2, q3
+	vand		q10, q10, q8
+	vand		q8, q12, q8
+	veor		q12, q13, q10
+	veor		q2, q2, q8
+	veor		q10, q14, q10
+	veor		q3, q3, q8
+	vadd.i32	q8, q4, q6
+	vsub.i32	q4, q4, q6
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vadd.i32	q6, q11, q12
+	vst1.8		{d8-d9}, [r5, : 128]!
+	vsub.i32	q4, q11, q12
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vadd.i32	q6, q0, q2
+	vst1.8		{d8-d9}, [r5, : 128]!
+	vsub.i32	q0, q0, q2
+	vst1.8		d12, [r2, : 64]
+	vadd.i32	q2, q5, q7
+	vst1.8		d0, [r5, : 64]
+	vsub.i32	q0, q5, q7
+	vst1.8		{d4-d5}, [r4, : 128]!
+	vadd.i32	q2, q9, q10
+	vst1.8		{d0-d1}, [r6, : 128]!
+	vsub.i32	q0, q9, q10
+	vst1.8		{d4-d5}, [r4, : 128]!
+	vadd.i32	q2, q1, q3
+	vst1.8		{d0-d1}, [r6, : 128]!
+	vsub.i32	q0, q1, q3
+	vst1.8		d4, [r4, : 64]
+	vst1.8		d0, [r6, : 64]
+	add		r2, sp, #512
+	add		r4, r3, #96
+	add		r5, r3, #144
+	vld1.8		{d0-d1}, [r2, : 128]
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vld1.8		{d4-d5}, [r5, : 128]!
+	vzip.i32	q1, q2
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vld1.8		{d8-d9}, [r5, : 128]!
+	vshl.i32	q5, q1, #1
+	vzip.i32	q3, q4
+	vshl.i32	q6, q2, #1
+	vld1.8		{d14}, [r4, : 64]
+	vshl.i32	q8, q3, #1
+	vld1.8		{d15}, [r5, : 64]
+	vshl.i32	q9, q4, #1
+	vmul.i32	d21, d7, d1
+	vtrn.32		d14, d15
+	vmul.i32	q11, q4, q0
+	vmul.i32	q0, q7, q0
+	vmull.s32	q12, d2, d2
+	vmlal.s32	q12, d11, d1
+	vmlal.s32	q12, d12, d0
+	vmlal.s32	q12, d13, d23
+	vmlal.s32	q12, d16, d22
+	vmlal.s32	q12, d7, d21
+	vmull.s32	q10, d2, d11
+	vmlal.s32	q10, d4, d1
+	vmlal.s32	q10, d13, d0
+	vmlal.s32	q10, d6, d23
+	vmlal.s32	q10, d17, d22
+	vmull.s32	q13, d10, d4
+	vmlal.s32	q13, d11, d3
+	vmlal.s32	q13, d13, d1
+	vmlal.s32	q13, d16, d0
+	vmlal.s32	q13, d17, d23
+	vmlal.s32	q13, d8, d22
+	vmull.s32	q1, d10, d5
+	vmlal.s32	q1, d11, d4
+	vmlal.s32	q1, d6, d1
+	vmlal.s32	q1, d17, d0
+	vmlal.s32	q1, d8, d23
+	vmull.s32	q14, d10, d6
+	vmlal.s32	q14, d11, d13
+	vmlal.s32	q14, d4, d4
+	vmlal.s32	q14, d17, d1
+	vmlal.s32	q14, d18, d0
+	vmlal.s32	q14, d9, d23
+	vmull.s32	q11, d10, d7
+	vmlal.s32	q11, d11, d6
+	vmlal.s32	q11, d12, d5
+	vmlal.s32	q11, d8, d1
+	vmlal.s32	q11, d19, d0
+	vmull.s32	q15, d10, d8
+	vmlal.s32	q15, d11, d17
+	vmlal.s32	q15, d12, d6
+	vmlal.s32	q15, d13, d5
+	vmlal.s32	q15, d19, d1
+	vmlal.s32	q15, d14, d0
+	vmull.s32	q2, d10, d9
+	vmlal.s32	q2, d11, d8
+	vmlal.s32	q2, d12, d7
+	vmlal.s32	q2, d13, d6
+	vmlal.s32	q2, d14, d1
+	vmull.s32	q0, d15, d1
+	vmlal.s32	q0, d10, d14
+	vmlal.s32	q0, d11, d19
+	vmlal.s32	q0, d12, d8
+	vmlal.s32	q0, d13, d17
+	vmlal.s32	q0, d6, d6
+	add		r2, sp, #480
+	vld1.8		{d18-d19}, [r2, : 128]!
+	vmull.s32	q3, d16, d7
+	vmlal.s32	q3, d10, d15
+	vmlal.s32	q3, d11, d14
+	vmlal.s32	q3, d12, d9
+	vmlal.s32	q3, d13, d8
+	vld1.8		{d8-d9}, [r2, : 128]
+	vadd.i64	q5, q12, q9
+	vadd.i64	q6, q15, q9
+	vshr.s64	q5, q5, #26
+	vshr.s64	q6, q6, #26
+	vadd.i64	q7, q10, q5
+	vshl.i64	q5, q5, #26
+	vadd.i64	q8, q7, q4
+	vadd.i64	q2, q2, q6
+	vshl.i64	q6, q6, #26
+	vadd.i64	q10, q2, q4
+	vsub.i64	q5, q12, q5
+	vshr.s64	q8, q8, #25
+	vsub.i64	q6, q15, q6
+	vshr.s64	q10, q10, #25
+	vadd.i64	q12, q13, q8
+	vshl.i64	q8, q8, #25
+	vadd.i64	q13, q12, q9
+	vadd.i64	q0, q0, q10
+	vsub.i64	q7, q7, q8
+	vshr.s64	q8, q13, #26
+	vshl.i64	q10, q10, #25
+	vadd.i64	q13, q0, q9
+	vadd.i64	q1, q1, q8
+	vshl.i64	q8, q8, #26
+	vadd.i64	q15, q1, q4
+	vsub.i64	q2, q2, q10
+	vshr.s64	q10, q13, #26
+	vsub.i64	q8, q12, q8
+	vshr.s64	q12, q15, #25
+	vadd.i64	q3, q3, q10
+	vshl.i64	q10, q10, #26
+	vadd.i64	q13, q3, q4
+	vadd.i64	q14, q14, q12
+	add		r2, r3, #288
+	vshl.i64	q12, q12, #25
+	add		r4, r3, #336
+	vadd.i64	q15, q14, q9
+	add		r2, r2, #8
+	vsub.i64	q0, q0, q10
+	add		r4, r4, #8
+	vshr.s64	q10, q13, #25
+	vsub.i64	q1, q1, q12
+	vshr.s64	q12, q15, #26
+	vadd.i64	q13, q10, q10
+	vadd.i64	q11, q11, q12
+	vtrn.32		d16, d2
+	vshl.i64	q12, q12, #26
+	vtrn.32		d17, d3
+	vadd.i64	q1, q11, q4
+	vadd.i64	q4, q5, q13
+	vst1.8		d16, [r2, : 64]!
+	vshl.i64	q5, q10, #4
+	vst1.8		d17, [r4, : 64]!
+	vsub.i64	q8, q14, q12
+	vshr.s64	q1, q1, #25
+	vadd.i64	q4, q4, q5
+	vadd.i64	q5, q6, q1
+	vshl.i64	q1, q1, #25
+	vadd.i64	q6, q5, q9
+	vadd.i64	q4, q4, q10
+	vshl.i64	q10, q10, #25
+	vadd.i64	q9, q4, q9
+	vsub.i64	q1, q11, q1
+	vshr.s64	q6, q6, #26
+	vsub.i64	q3, q3, q10
+	vtrn.32		d16, d2
+	vshr.s64	q9, q9, #26
+	vtrn.32		d17, d3
+	vadd.i64	q1, q2, q6
+	vst1.8		d16, [r2, : 64]
+	vshl.i64	q2, q6, #26
+	vst1.8		d17, [r4, : 64]
+	vadd.i64	q6, q7, q9
+	vtrn.32		d0, d6
+	vshl.i64	q7, q9, #26
+	vtrn.32		d1, d7
+	vsub.i64	q2, q5, q2
+	add		r2, r2, #16
+	vsub.i64	q3, q4, q7
+	vst1.8		d0, [r2, : 64]
+	add		r4, r4, #16
+	vst1.8		d1, [r4, : 64]
+	vtrn.32		d4, d2
+	vtrn.32		d5, d3
+	sub		r2, r2, #8
+	sub		r4, r4, #8
+	vtrn.32		d6, d12
+	vtrn.32		d7, d13
+	vst1.8		d4, [r2, : 64]
+	vst1.8		d5, [r4, : 64]
+	sub		r2, r2, #24
+	sub		r4, r4, #24
+	vst1.8		d6, [r2, : 64]
+	vst1.8		d7, [r4, : 64]
+	add		r2, r3, #240
+	add		r4, r3, #96
+	vld1.8		{d0-d1}, [r4, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vld1.8		{d4}, [r4, : 64]
+	add		r4, r3, #144
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vtrn.32		q0, q3
+	vld1.8		{d8-d9}, [r4, : 128]!
+	vshl.i32	q5, q0, #4
+	vtrn.32		q1, q4
+	vshl.i32	q6, q3, #4
+	vadd.i32	q5, q5, q0
+	vadd.i32	q6, q6, q3
+	vshl.i32	q7, q1, #4
+	vld1.8		{d5}, [r4, : 64]
+	vshl.i32	q8, q4, #4
+	vtrn.32		d4, d5
+	vadd.i32	q7, q7, q1
+	vadd.i32	q8, q8, q4
+	vld1.8		{d18-d19}, [r2, : 128]!
+	vshl.i32	q10, q2, #4
+	vld1.8		{d22-d23}, [r2, : 128]!
+	vadd.i32	q10, q10, q2
+	vld1.8		{d24}, [r2, : 64]
+	vadd.i32	q5, q5, q0
+	add		r2, r3, #192
+	vld1.8		{d26-d27}, [r2, : 128]!
+	vadd.i32	q6, q6, q3
+	vld1.8		{d28-d29}, [r2, : 128]!
+	vadd.i32	q8, q8, q4
+	vld1.8		{d25}, [r2, : 64]
+	vadd.i32	q10, q10, q2
+	vtrn.32		q9, q13
+	vadd.i32	q7, q7, q1
+	vadd.i32	q5, q5, q0
+	vtrn.32		q11, q14
+	vadd.i32	q6, q6, q3
+	add		r2, sp, #528
+	vadd.i32	q10, q10, q2
+	vtrn.32		d24, d25
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q6, q13, #1
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vshl.i32	q10, q14, #1
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q15, q12, #1
+	vadd.i32	q8, q8, q4
+	vext.32		d10, d31, d30, #0
+	vadd.i32	q7, q7, q1
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vmull.s32	q8, d18, d5
+	vmlal.s32	q8, d26, d4
+	vmlal.s32	q8, d19, d9
+	vmlal.s32	q8, d27, d3
+	vmlal.s32	q8, d22, d8
+	vmlal.s32	q8, d28, d2
+	vmlal.s32	q8, d23, d7
+	vmlal.s32	q8, d29, d1
+	vmlal.s32	q8, d24, d6
+	vmlal.s32	q8, d25, d0
+	vst1.8		{d14-d15}, [r2, : 128]!
+	vmull.s32	q2, d18, d4
+	vmlal.s32	q2, d12, d9
+	vmlal.s32	q2, d13, d8
+	vmlal.s32	q2, d19, d3
+	vmlal.s32	q2, d22, d2
+	vmlal.s32	q2, d23, d1
+	vmlal.s32	q2, d24, d0
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vmull.s32	q7, d18, d9
+	vmlal.s32	q7, d26, d3
+	vmlal.s32	q7, d19, d8
+	vmlal.s32	q7, d27, d2
+	vmlal.s32	q7, d22, d7
+	vmlal.s32	q7, d28, d1
+	vmlal.s32	q7, d23, d6
+	vmlal.s32	q7, d29, d0
+	vst1.8		{d10-d11}, [r2, : 128]!
+	vmull.s32	q5, d18, d3
+	vmlal.s32	q5, d19, d2
+	vmlal.s32	q5, d22, d1
+	vmlal.s32	q5, d23, d0
+	vmlal.s32	q5, d12, d8
+	vst1.8		{d16-d17}, [r2, : 128]
+	vmull.s32	q4, d18, d8
+	vmlal.s32	q4, d26, d2
+	vmlal.s32	q4, d19, d7
+	vmlal.s32	q4, d27, d1
+	vmlal.s32	q4, d22, d6
+	vmlal.s32	q4, d28, d0
+	vmull.s32	q8, d18, d7
+	vmlal.s32	q8, d26, d1
+	vmlal.s32	q8, d19, d6
+	vmlal.s32	q8, d27, d0
+	add		r2, sp, #544
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q7, d24, d21
+	vmlal.s32	q7, d25, d20
+	vmlal.s32	q4, d23, d21
+	vmlal.s32	q4, d29, d20
+	vmlal.s32	q8, d22, d21
+	vmlal.s32	q8, d28, d20
+	vmlal.s32	q5, d24, d20
+	vst1.8		{d14-d15}, [r2, : 128]
+	vmull.s32	q7, d18, d6
+	vmlal.s32	q7, d26, d0
+	add		r2, sp, #624
+	vld1.8		{d30-d31}, [r2, : 128]
+	vmlal.s32	q2, d30, d21
+	vmlal.s32	q7, d19, d21
+	vmlal.s32	q7, d27, d20
+	add		r2, sp, #592
+	vld1.8		{d26-d27}, [r2, : 128]
+	vmlal.s32	q4, d25, d27
+	vmlal.s32	q8, d29, d27
+	vmlal.s32	q8, d25, d26
+	vmlal.s32	q7, d28, d27
+	vmlal.s32	q7, d29, d26
+	add		r2, sp, #576
+	vld1.8		{d28-d29}, [r2, : 128]
+	vmlal.s32	q4, d24, d29
+	vmlal.s32	q8, d23, d29
+	vmlal.s32	q8, d24, d28
+	vmlal.s32	q7, d22, d29
+	vmlal.s32	q7, d23, d28
+	vst1.8		{d8-d9}, [r2, : 128]
+	add		r2, sp, #528
+	vld1.8		{d8-d9}, [r2, : 128]
+	vmlal.s32	q7, d24, d9
+	vmlal.s32	q7, d25, d31
+	vmull.s32	q1, d18, d2
+	vmlal.s32	q1, d19, d1
+	vmlal.s32	q1, d22, d0
+	vmlal.s32	q1, d24, d27
+	vmlal.s32	q1, d23, d20
+	vmlal.s32	q1, d12, d7
+	vmlal.s32	q1, d13, d6
+	vmull.s32	q6, d18, d1
+	vmlal.s32	q6, d19, d0
+	vmlal.s32	q6, d23, d27
+	vmlal.s32	q6, d22, d20
+	vmlal.s32	q6, d24, d26
+	vmull.s32	q0, d18, d0
+	vmlal.s32	q0, d22, d27
+	vmlal.s32	q0, d23, d26
+	vmlal.s32	q0, d24, d31
+	vmlal.s32	q0, d19, d20
+	add		r2, sp, #608
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q2, d18, d7
+	vmlal.s32	q5, d18, d6
+	vmlal.s32	q1, d18, d21
+	vmlal.s32	q0, d18, d28
+	vmlal.s32	q6, d18, d29
+	vmlal.s32	q2, d19, d6
+	vmlal.s32	q5, d19, d21
+	vmlal.s32	q1, d19, d29
+	vmlal.s32	q0, d19, d9
+	vmlal.s32	q6, d19, d28
+	add		r2, sp, #560
+	vld1.8		{d18-d19}, [r2, : 128]
+	add		r2, sp, #480
+	vld1.8		{d22-d23}, [r2, : 128]
+	vmlal.s32	q5, d19, d7
+	vmlal.s32	q0, d18, d21
+	vmlal.s32	q0, d19, d29
+	vmlal.s32	q6, d18, d6
+	add		r2, sp, #496
+	vld1.8		{d6-d7}, [r2, : 128]
+	vmlal.s32	q6, d19, d21
+	add		r2, sp, #544
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q0, d30, d8
+	add		r2, sp, #640
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q5, d30, d29
+	add		r2, sp, #576
+	vld1.8		{d24-d25}, [r2, : 128]
+	vmlal.s32	q1, d30, d28
+	vadd.i64	q13, q0, q11
+	vadd.i64	q14, q5, q11
+	vmlal.s32	q6, d30, d9
+	vshr.s64	q4, q13, #26
+	vshr.s64	q13, q14, #26
+	vadd.i64	q7, q7, q4
+	vshl.i64	q4, q4, #26
+	vadd.i64	q14, q7, q3
+	vadd.i64	q9, q9, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q15, q9, q3
+	vsub.i64	q0, q0, q4
+	vshr.s64	q4, q14, #25
+	vsub.i64	q5, q5, q13
+	vshr.s64	q13, q15, #25
+	vadd.i64	q6, q6, q4
+	vshl.i64	q4, q4, #25
+	vadd.i64	q14, q6, q11
+	vadd.i64	q2, q2, q13
+	vsub.i64	q4, q7, q4
+	vshr.s64	q7, q14, #26
+	vshl.i64	q13, q13, #25
+	vadd.i64	q14, q2, q11
+	vadd.i64	q8, q8, q7
+	vshl.i64	q7, q7, #26
+	vadd.i64	q15, q8, q3
+	vsub.i64	q9, q9, q13
+	vshr.s64	q13, q14, #26
+	vsub.i64	q6, q6, q7
+	vshr.s64	q7, q15, #25
+	vadd.i64	q10, q10, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q14, q10, q3
+	vadd.i64	q1, q1, q7
+	add		r2, r3, #144
+	vshl.i64	q7, q7, #25
+	add		r4, r3, #96
+	vadd.i64	q15, q1, q11
+	add		r2, r2, #8
+	vsub.i64	q2, q2, q13
+	add		r4, r4, #8
+	vshr.s64	q13, q14, #25
+	vsub.i64	q7, q8, q7
+	vshr.s64	q8, q15, #26
+	vadd.i64	q14, q13, q13
+	vadd.i64	q12, q12, q8
+	vtrn.32		d12, d14
+	vshl.i64	q8, q8, #26
+	vtrn.32		d13, d15
+	vadd.i64	q3, q12, q3
+	vadd.i64	q0, q0, q14
+	vst1.8		d12, [r2, : 64]!
+	vshl.i64	q7, q13, #4
+	vst1.8		d13, [r4, : 64]!
+	vsub.i64	q1, q1, q8
+	vshr.s64	q3, q3, #25
+	vadd.i64	q0, q0, q7
+	vadd.i64	q5, q5, q3
+	vshl.i64	q3, q3, #25
+	vadd.i64	q6, q5, q11
+	vadd.i64	q0, q0, q13
+	vshl.i64	q7, q13, #25
+	vadd.i64	q8, q0, q11
+	vsub.i64	q3, q12, q3
+	vshr.s64	q6, q6, #26
+	vsub.i64	q7, q10, q7
+	vtrn.32		d2, d6
+	vshr.s64	q8, q8, #26
+	vtrn.32		d3, d7
+	vadd.i64	q3, q9, q6
+	vst1.8		d2, [r2, : 64]
+	vshl.i64	q6, q6, #26
+	vst1.8		d3, [r4, : 64]
+	vadd.i64	q1, q4, q8
+	vtrn.32		d4, d14
+	vshl.i64	q4, q8, #26
+	vtrn.32		d5, d15
+	vsub.i64	q5, q5, q6
+	add		r2, r2, #16
+	vsub.i64	q0, q0, q4
+	vst1.8		d4, [r2, : 64]
+	add		r4, r4, #16
+	vst1.8		d5, [r4, : 64]
+	vtrn.32		d10, d6
+	vtrn.32		d11, d7
+	sub		r2, r2, #8
+	sub		r4, r4, #8
+	vtrn.32		d0, d2
+	vtrn.32		d1, d3
+	vst1.8		d10, [r2, : 64]
+	vst1.8		d11, [r4, : 64]
+	sub		r2, r2, #24
+	sub		r4, r4, #24
+	vst1.8		d0, [r2, : 64]
+	vst1.8		d1, [r4, : 64]
+	add		r2, r3, #288
+	add		r4, r3, #336
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vsub.i32	q0, q0, q1
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d4-d5}, [r4, : 128]!
+	vsub.i32	q1, q1, q2
+	add		r5, r3, #240
+	vld1.8		{d4}, [r2, : 64]
+	vld1.8		{d6}, [r4, : 64]
+	vsub.i32	q2, q2, q3
+	vst1.8		{d0-d1}, [r5, : 128]!
+	vst1.8		{d2-d3}, [r5, : 128]!
+	vst1.8		d4, [r5, : 64]
+	add		r2, r3, #144
+	add		r4, r3, #96
+	add		r5, r3, #144
+	add		r6, r3, #192
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vsub.i32	q2, q0, q1
+	vadd.i32	q0, q0, q1
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vsub.i32	q4, q1, q3
+	vadd.i32	q1, q1, q3
+	vld1.8		{d6}, [r2, : 64]
+	vld1.8		{d10}, [r4, : 64]
+	vsub.i32	q6, q3, q5
+	vadd.i32	q3, q3, q5
+	vst1.8		{d4-d5}, [r5, : 128]!
+	vst1.8		{d0-d1}, [r6, : 128]!
+	vst1.8		{d8-d9}, [r5, : 128]!
+	vst1.8		{d2-d3}, [r6, : 128]!
+	vst1.8		d12, [r5, : 64]
+	vst1.8		d6, [r6, : 64]
+	add		r2, r3, #0
+	add		r4, r3, #240
+	vld1.8		{d0-d1}, [r4, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vld1.8		{d4}, [r4, : 64]
+	add		r4, r3, #336
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vtrn.32		q0, q3
+	vld1.8		{d8-d9}, [r4, : 128]!
+	vshl.i32	q5, q0, #4
+	vtrn.32		q1, q4
+	vshl.i32	q6, q3, #4
+	vadd.i32	q5, q5, q0
+	vadd.i32	q6, q6, q3
+	vshl.i32	q7, q1, #4
+	vld1.8		{d5}, [r4, : 64]
+	vshl.i32	q8, q4, #4
+	vtrn.32		d4, d5
+	vadd.i32	q7, q7, q1
+	vadd.i32	q8, q8, q4
+	vld1.8		{d18-d19}, [r2, : 128]!
+	vshl.i32	q10, q2, #4
+	vld1.8		{d22-d23}, [r2, : 128]!
+	vadd.i32	q10, q10, q2
+	vld1.8		{d24}, [r2, : 64]
+	vadd.i32	q5, q5, q0
+	add		r2, r3, #288
+	vld1.8		{d26-d27}, [r2, : 128]!
+	vadd.i32	q6, q6, q3
+	vld1.8		{d28-d29}, [r2, : 128]!
+	vadd.i32	q8, q8, q4
+	vld1.8		{d25}, [r2, : 64]
+	vadd.i32	q10, q10, q2
+	vtrn.32		q9, q13
+	vadd.i32	q7, q7, q1
+	vadd.i32	q5, q5, q0
+	vtrn.32		q11, q14
+	vadd.i32	q6, q6, q3
+	add		r2, sp, #528
+	vadd.i32	q10, q10, q2
+	vtrn.32		d24, d25
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q6, q13, #1
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vshl.i32	q10, q14, #1
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q15, q12, #1
+	vadd.i32	q8, q8, q4
+	vext.32		d10, d31, d30, #0
+	vadd.i32	q7, q7, q1
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vmull.s32	q8, d18, d5
+	vmlal.s32	q8, d26, d4
+	vmlal.s32	q8, d19, d9
+	vmlal.s32	q8, d27, d3
+	vmlal.s32	q8, d22, d8
+	vmlal.s32	q8, d28, d2
+	vmlal.s32	q8, d23, d7
+	vmlal.s32	q8, d29, d1
+	vmlal.s32	q8, d24, d6
+	vmlal.s32	q8, d25, d0
+	vst1.8		{d14-d15}, [r2, : 128]!
+	vmull.s32	q2, d18, d4
+	vmlal.s32	q2, d12, d9
+	vmlal.s32	q2, d13, d8
+	vmlal.s32	q2, d19, d3
+	vmlal.s32	q2, d22, d2
+	vmlal.s32	q2, d23, d1
+	vmlal.s32	q2, d24, d0
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vmull.s32	q7, d18, d9
+	vmlal.s32	q7, d26, d3
+	vmlal.s32	q7, d19, d8
+	vmlal.s32	q7, d27, d2
+	vmlal.s32	q7, d22, d7
+	vmlal.s32	q7, d28, d1
+	vmlal.s32	q7, d23, d6
+	vmlal.s32	q7, d29, d0
+	vst1.8		{d10-d11}, [r2, : 128]!
+	vmull.s32	q5, d18, d3
+	vmlal.s32	q5, d19, d2
+	vmlal.s32	q5, d22, d1
+	vmlal.s32	q5, d23, d0
+	vmlal.s32	q5, d12, d8
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vmull.s32	q4, d18, d8
+	vmlal.s32	q4, d26, d2
+	vmlal.s32	q4, d19, d7
+	vmlal.s32	q4, d27, d1
+	vmlal.s32	q4, d22, d6
+	vmlal.s32	q4, d28, d0
+	vmull.s32	q8, d18, d7
+	vmlal.s32	q8, d26, d1
+	vmlal.s32	q8, d19, d6
+	vmlal.s32	q8, d27, d0
+	add		r2, sp, #544
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q7, d24, d21
+	vmlal.s32	q7, d25, d20
+	vmlal.s32	q4, d23, d21
+	vmlal.s32	q4, d29, d20
+	vmlal.s32	q8, d22, d21
+	vmlal.s32	q8, d28, d20
+	vmlal.s32	q5, d24, d20
+	vst1.8		{d14-d15}, [r2, : 128]
+	vmull.s32	q7, d18, d6
+	vmlal.s32	q7, d26, d0
+	add		r2, sp, #624
+	vld1.8		{d30-d31}, [r2, : 128]
+	vmlal.s32	q2, d30, d21
+	vmlal.s32	q7, d19, d21
+	vmlal.s32	q7, d27, d20
+	add		r2, sp, #592
+	vld1.8		{d26-d27}, [r2, : 128]
+	vmlal.s32	q4, d25, d27
+	vmlal.s32	q8, d29, d27
+	vmlal.s32	q8, d25, d26
+	vmlal.s32	q7, d28, d27
+	vmlal.s32	q7, d29, d26
+	add		r2, sp, #576
+	vld1.8		{d28-d29}, [r2, : 128]
+	vmlal.s32	q4, d24, d29
+	vmlal.s32	q8, d23, d29
+	vmlal.s32	q8, d24, d28
+	vmlal.s32	q7, d22, d29
+	vmlal.s32	q7, d23, d28
+	vst1.8		{d8-d9}, [r2, : 128]
+	add		r2, sp, #528
+	vld1.8		{d8-d9}, [r2, : 128]
+	vmlal.s32	q7, d24, d9
+	vmlal.s32	q7, d25, d31
+	vmull.s32	q1, d18, d2
+	vmlal.s32	q1, d19, d1
+	vmlal.s32	q1, d22, d0
+	vmlal.s32	q1, d24, d27
+	vmlal.s32	q1, d23, d20
+	vmlal.s32	q1, d12, d7
+	vmlal.s32	q1, d13, d6
+	vmull.s32	q6, d18, d1
+	vmlal.s32	q6, d19, d0
+	vmlal.s32	q6, d23, d27
+	vmlal.s32	q6, d22, d20
+	vmlal.s32	q6, d24, d26
+	vmull.s32	q0, d18, d0
+	vmlal.s32	q0, d22, d27
+	vmlal.s32	q0, d23, d26
+	vmlal.s32	q0, d24, d31
+	vmlal.s32	q0, d19, d20
+	add		r2, sp, #608
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q2, d18, d7
+	vmlal.s32	q5, d18, d6
+	vmlal.s32	q1, d18, d21
+	vmlal.s32	q0, d18, d28
+	vmlal.s32	q6, d18, d29
+	vmlal.s32	q2, d19, d6
+	vmlal.s32	q5, d19, d21
+	vmlal.s32	q1, d19, d29
+	vmlal.s32	q0, d19, d9
+	vmlal.s32	q6, d19, d28
+	add		r2, sp, #560
+	vld1.8		{d18-d19}, [r2, : 128]
+	add		r2, sp, #480
+	vld1.8		{d22-d23}, [r2, : 128]
+	vmlal.s32	q5, d19, d7
+	vmlal.s32	q0, d18, d21
+	vmlal.s32	q0, d19, d29
+	vmlal.s32	q6, d18, d6
+	add		r2, sp, #496
+	vld1.8		{d6-d7}, [r2, : 128]
+	vmlal.s32	q6, d19, d21
+	add		r2, sp, #544
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q0, d30, d8
+	add		r2, sp, #640
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q5, d30, d29
+	add		r2, sp, #576
+	vld1.8		{d24-d25}, [r2, : 128]
+	vmlal.s32	q1, d30, d28
+	vadd.i64	q13, q0, q11
+	vadd.i64	q14, q5, q11
+	vmlal.s32	q6, d30, d9
+	vshr.s64	q4, q13, #26
+	vshr.s64	q13, q14, #26
+	vadd.i64	q7, q7, q4
+	vshl.i64	q4, q4, #26
+	vadd.i64	q14, q7, q3
+	vadd.i64	q9, q9, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q15, q9, q3
+	vsub.i64	q0, q0, q4
+	vshr.s64	q4, q14, #25
+	vsub.i64	q5, q5, q13
+	vshr.s64	q13, q15, #25
+	vadd.i64	q6, q6, q4
+	vshl.i64	q4, q4, #25
+	vadd.i64	q14, q6, q11
+	vadd.i64	q2, q2, q13
+	vsub.i64	q4, q7, q4
+	vshr.s64	q7, q14, #26
+	vshl.i64	q13, q13, #25
+	vadd.i64	q14, q2, q11
+	vadd.i64	q8, q8, q7
+	vshl.i64	q7, q7, #26
+	vadd.i64	q15, q8, q3
+	vsub.i64	q9, q9, q13
+	vshr.s64	q13, q14, #26
+	vsub.i64	q6, q6, q7
+	vshr.s64	q7, q15, #25
+	vadd.i64	q10, q10, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q14, q10, q3
+	vadd.i64	q1, q1, q7
+	add		r2, r3, #288
+	vshl.i64	q7, q7, #25
+	add		r4, r3, #96
+	vadd.i64	q15, q1, q11
+	add		r2, r2, #8
+	vsub.i64	q2, q2, q13
+	add		r4, r4, #8
+	vshr.s64	q13, q14, #25
+	vsub.i64	q7, q8, q7
+	vshr.s64	q8, q15, #26
+	vadd.i64	q14, q13, q13
+	vadd.i64	q12, q12, q8
+	vtrn.32		d12, d14
+	vshl.i64	q8, q8, #26
+	vtrn.32		d13, d15
+	vadd.i64	q3, q12, q3
+	vadd.i64	q0, q0, q14
+	vst1.8		d12, [r2, : 64]!
+	vshl.i64	q7, q13, #4
+	vst1.8		d13, [r4, : 64]!
+	vsub.i64	q1, q1, q8
+	vshr.s64	q3, q3, #25
+	vadd.i64	q0, q0, q7
+	vadd.i64	q5, q5, q3
+	vshl.i64	q3, q3, #25
+	vadd.i64	q6, q5, q11
+	vadd.i64	q0, q0, q13
+	vshl.i64	q7, q13, #25
+	vadd.i64	q8, q0, q11
+	vsub.i64	q3, q12, q3
+	vshr.s64	q6, q6, #26
+	vsub.i64	q7, q10, q7
+	vtrn.32		d2, d6
+	vshr.s64	q8, q8, #26
+	vtrn.32		d3, d7
+	vadd.i64	q3, q9, q6
+	vst1.8		d2, [r2, : 64]
+	vshl.i64	q6, q6, #26
+	vst1.8		d3, [r4, : 64]
+	vadd.i64	q1, q4, q8
+	vtrn.32		d4, d14
+	vshl.i64	q4, q8, #26
+	vtrn.32		d5, d15
+	vsub.i64	q5, q5, q6
+	add		r2, r2, #16
+	vsub.i64	q0, q0, q4
+	vst1.8		d4, [r2, : 64]
+	add		r4, r4, #16
+	vst1.8		d5, [r4, : 64]
+	vtrn.32		d10, d6
+	vtrn.32		d11, d7
+	sub		r2, r2, #8
+	sub		r4, r4, #8
+	vtrn.32		d0, d2
+	vtrn.32		d1, d3
+	vst1.8		d10, [r2, : 64]
+	vst1.8		d11, [r4, : 64]
+	sub		r2, r2, #24
+	sub		r4, r4, #24
+	vst1.8		d0, [r2, : 64]
+	vst1.8		d1, [r4, : 64]
+	add		r2, sp, #512
+	add		r4, r3, #144
+	add		r5, r3, #192
+	vld1.8		{d0-d1}, [r2, : 128]
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vld1.8		{d4-d5}, [r5, : 128]!
+	vzip.i32	q1, q2
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vld1.8		{d8-d9}, [r5, : 128]!
+	vshl.i32	q5, q1, #1
+	vzip.i32	q3, q4
+	vshl.i32	q6, q2, #1
+	vld1.8		{d14}, [r4, : 64]
+	vshl.i32	q8, q3, #1
+	vld1.8		{d15}, [r5, : 64]
+	vshl.i32	q9, q4, #1
+	vmul.i32	d21, d7, d1
+	vtrn.32		d14, d15
+	vmul.i32	q11, q4, q0
+	vmul.i32	q0, q7, q0
+	vmull.s32	q12, d2, d2
+	vmlal.s32	q12, d11, d1
+	vmlal.s32	q12, d12, d0
+	vmlal.s32	q12, d13, d23
+	vmlal.s32	q12, d16, d22
+	vmlal.s32	q12, d7, d21
+	vmull.s32	q10, d2, d11
+	vmlal.s32	q10, d4, d1
+	vmlal.s32	q10, d13, d0
+	vmlal.s32	q10, d6, d23
+	vmlal.s32	q10, d17, d22
+	vmull.s32	q13, d10, d4
+	vmlal.s32	q13, d11, d3
+	vmlal.s32	q13, d13, d1
+	vmlal.s32	q13, d16, d0
+	vmlal.s32	q13, d17, d23
+	vmlal.s32	q13, d8, d22
+	vmull.s32	q1, d10, d5
+	vmlal.s32	q1, d11, d4
+	vmlal.s32	q1, d6, d1
+	vmlal.s32	q1, d17, d0
+	vmlal.s32	q1, d8, d23
+	vmull.s32	q14, d10, d6
+	vmlal.s32	q14, d11, d13
+	vmlal.s32	q14, d4, d4
+	vmlal.s32	q14, d17, d1
+	vmlal.s32	q14, d18, d0
+	vmlal.s32	q14, d9, d23
+	vmull.s32	q11, d10, d7
+	vmlal.s32	q11, d11, d6
+	vmlal.s32	q11, d12, d5
+	vmlal.s32	q11, d8, d1
+	vmlal.s32	q11, d19, d0
+	vmull.s32	q15, d10, d8
+	vmlal.s32	q15, d11, d17
+	vmlal.s32	q15, d12, d6
+	vmlal.s32	q15, d13, d5
+	vmlal.s32	q15, d19, d1
+	vmlal.s32	q15, d14, d0
+	vmull.s32	q2, d10, d9
+	vmlal.s32	q2, d11, d8
+	vmlal.s32	q2, d12, d7
+	vmlal.s32	q2, d13, d6
+	vmlal.s32	q2, d14, d1
+	vmull.s32	q0, d15, d1
+	vmlal.s32	q0, d10, d14
+	vmlal.s32	q0, d11, d19
+	vmlal.s32	q0, d12, d8
+	vmlal.s32	q0, d13, d17
+	vmlal.s32	q0, d6, d6
+	add		r2, sp, #480
+	vld1.8		{d18-d19}, [r2, : 128]!
+	vmull.s32	q3, d16, d7
+	vmlal.s32	q3, d10, d15
+	vmlal.s32	q3, d11, d14
+	vmlal.s32	q3, d12, d9
+	vmlal.s32	q3, d13, d8
+	vld1.8		{d8-d9}, [r2, : 128]
+	vadd.i64	q5, q12, q9
+	vadd.i64	q6, q15, q9
+	vshr.s64	q5, q5, #26
+	vshr.s64	q6, q6, #26
+	vadd.i64	q7, q10, q5
+	vshl.i64	q5, q5, #26
+	vadd.i64	q8, q7, q4
+	vadd.i64	q2, q2, q6
+	vshl.i64	q6, q6, #26
+	vadd.i64	q10, q2, q4
+	vsub.i64	q5, q12, q5
+	vshr.s64	q8, q8, #25
+	vsub.i64	q6, q15, q6
+	vshr.s64	q10, q10, #25
+	vadd.i64	q12, q13, q8
+	vshl.i64	q8, q8, #25
+	vadd.i64	q13, q12, q9
+	vadd.i64	q0, q0, q10
+	vsub.i64	q7, q7, q8
+	vshr.s64	q8, q13, #26
+	vshl.i64	q10, q10, #25
+	vadd.i64	q13, q0, q9
+	vadd.i64	q1, q1, q8
+	vshl.i64	q8, q8, #26
+	vadd.i64	q15, q1, q4
+	vsub.i64	q2, q2, q10
+	vshr.s64	q10, q13, #26
+	vsub.i64	q8, q12, q8
+	vshr.s64	q12, q15, #25
+	vadd.i64	q3, q3, q10
+	vshl.i64	q10, q10, #26
+	vadd.i64	q13, q3, q4
+	vadd.i64	q14, q14, q12
+	add		r2, r3, #144
+	vshl.i64	q12, q12, #25
+	add		r4, r3, #192
+	vadd.i64	q15, q14, q9
+	add		r2, r2, #8
+	vsub.i64	q0, q0, q10
+	add		r4, r4, #8
+	vshr.s64	q10, q13, #25
+	vsub.i64	q1, q1, q12
+	vshr.s64	q12, q15, #26
+	vadd.i64	q13, q10, q10
+	vadd.i64	q11, q11, q12
+	vtrn.32		d16, d2
+	vshl.i64	q12, q12, #26
+	vtrn.32		d17, d3
+	vadd.i64	q1, q11, q4
+	vadd.i64	q4, q5, q13
+	vst1.8		d16, [r2, : 64]!
+	vshl.i64	q5, q10, #4
+	vst1.8		d17, [r4, : 64]!
+	vsub.i64	q8, q14, q12
+	vshr.s64	q1, q1, #25
+	vadd.i64	q4, q4, q5
+	vadd.i64	q5, q6, q1
+	vshl.i64	q1, q1, #25
+	vadd.i64	q6, q5, q9
+	vadd.i64	q4, q4, q10
+	vshl.i64	q10, q10, #25
+	vadd.i64	q9, q4, q9
+	vsub.i64	q1, q11, q1
+	vshr.s64	q6, q6, #26
+	vsub.i64	q3, q3, q10
+	vtrn.32		d16, d2
+	vshr.s64	q9, q9, #26
+	vtrn.32		d17, d3
+	vadd.i64	q1, q2, q6
+	vst1.8		d16, [r2, : 64]
+	vshl.i64	q2, q6, #26
+	vst1.8		d17, [r4, : 64]
+	vadd.i64	q6, q7, q9
+	vtrn.32		d0, d6
+	vshl.i64	q7, q9, #26
+	vtrn.32		d1, d7
+	vsub.i64	q2, q5, q2
+	add		r2, r2, #16
+	vsub.i64	q3, q4, q7
+	vst1.8		d0, [r2, : 64]
+	add		r4, r4, #16
+	vst1.8		d1, [r4, : 64]
+	vtrn.32		d4, d2
+	vtrn.32		d5, d3
+	sub		r2, r2, #8
+	sub		r4, r4, #8
+	vtrn.32		d6, d12
+	vtrn.32		d7, d13
+	vst1.8		d4, [r2, : 64]
+	vst1.8		d5, [r4, : 64]
+	sub		r2, r2, #24
+	sub		r4, r4, #24
+	vst1.8		d6, [r2, : 64]
+	vst1.8		d7, [r4, : 64]
+	add		r2, r3, #336
+	add		r4, r3, #288
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vadd.i32	q0, q0, q1
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d4-d5}, [r4, : 128]!
+	vadd.i32	q1, q1, q2
+	add		r5, r3, #288
+	vld1.8		{d4}, [r2, : 64]
+	vld1.8		{d6}, [r4, : 64]
+	vadd.i32	q2, q2, q3
+	vst1.8		{d0-d1}, [r5, : 128]!
+	vst1.8		{d2-d3}, [r5, : 128]!
+	vst1.8		d4, [r5, : 64]
+	add		r2, r3, #48
+	add		r4, r3, #144
+	vld1.8		{d0-d1}, [r4, : 128]!
+	vld1.8		{d2-d3}, [r4, : 128]!
+	vld1.8		{d4}, [r4, : 64]
+	add		r4, r3, #288
+	vld1.8		{d6-d7}, [r4, : 128]!
+	vtrn.32		q0, q3
+	vld1.8		{d8-d9}, [r4, : 128]!
+	vshl.i32	q5, q0, #4
+	vtrn.32		q1, q4
+	vshl.i32	q6, q3, #4
+	vadd.i32	q5, q5, q0
+	vadd.i32	q6, q6, q3
+	vshl.i32	q7, q1, #4
+	vld1.8		{d5}, [r4, : 64]
+	vshl.i32	q8, q4, #4
+	vtrn.32		d4, d5
+	vadd.i32	q7, q7, q1
+	vadd.i32	q8, q8, q4
+	vld1.8		{d18-d19}, [r2, : 128]!
+	vshl.i32	q10, q2, #4
+	vld1.8		{d22-d23}, [r2, : 128]!
+	vadd.i32	q10, q10, q2
+	vld1.8		{d24}, [r2, : 64]
+	vadd.i32	q5, q5, q0
+	add		r2, r3, #240
+	vld1.8		{d26-d27}, [r2, : 128]!
+	vadd.i32	q6, q6, q3
+	vld1.8		{d28-d29}, [r2, : 128]!
+	vadd.i32	q8, q8, q4
+	vld1.8		{d25}, [r2, : 64]
+	vadd.i32	q10, q10, q2
+	vtrn.32		q9, q13
+	vadd.i32	q7, q7, q1
+	vadd.i32	q5, q5, q0
+	vtrn.32		q11, q14
+	vadd.i32	q6, q6, q3
+	add		r2, sp, #528
+	vadd.i32	q10, q10, q2
+	vtrn.32		d24, d25
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q6, q13, #1
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vshl.i32	q10, q14, #1
+	vst1.8		{d12-d13}, [r2, : 128]!
+	vshl.i32	q15, q12, #1
+	vadd.i32	q8, q8, q4
+	vext.32		d10, d31, d30, #0
+	vadd.i32	q7, q7, q1
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vmull.s32	q8, d18, d5
+	vmlal.s32	q8, d26, d4
+	vmlal.s32	q8, d19, d9
+	vmlal.s32	q8, d27, d3
+	vmlal.s32	q8, d22, d8
+	vmlal.s32	q8, d28, d2
+	vmlal.s32	q8, d23, d7
+	vmlal.s32	q8, d29, d1
+	vmlal.s32	q8, d24, d6
+	vmlal.s32	q8, d25, d0
+	vst1.8		{d14-d15}, [r2, : 128]!
+	vmull.s32	q2, d18, d4
+	vmlal.s32	q2, d12, d9
+	vmlal.s32	q2, d13, d8
+	vmlal.s32	q2, d19, d3
+	vmlal.s32	q2, d22, d2
+	vmlal.s32	q2, d23, d1
+	vmlal.s32	q2, d24, d0
+	vst1.8		{d20-d21}, [r2, : 128]!
+	vmull.s32	q7, d18, d9
+	vmlal.s32	q7, d26, d3
+	vmlal.s32	q7, d19, d8
+	vmlal.s32	q7, d27, d2
+	vmlal.s32	q7, d22, d7
+	vmlal.s32	q7, d28, d1
+	vmlal.s32	q7, d23, d6
+	vmlal.s32	q7, d29, d0
+	vst1.8		{d10-d11}, [r2, : 128]!
+	vmull.s32	q5, d18, d3
+	vmlal.s32	q5, d19, d2
+	vmlal.s32	q5, d22, d1
+	vmlal.s32	q5, d23, d0
+	vmlal.s32	q5, d12, d8
+	vst1.8		{d16-d17}, [r2, : 128]!
+	vmull.s32	q4, d18, d8
+	vmlal.s32	q4, d26, d2
+	vmlal.s32	q4, d19, d7
+	vmlal.s32	q4, d27, d1
+	vmlal.s32	q4, d22, d6
+	vmlal.s32	q4, d28, d0
+	vmull.s32	q8, d18, d7
+	vmlal.s32	q8, d26, d1
+	vmlal.s32	q8, d19, d6
+	vmlal.s32	q8, d27, d0
+	add		r2, sp, #544
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q7, d24, d21
+	vmlal.s32	q7, d25, d20
+	vmlal.s32	q4, d23, d21
+	vmlal.s32	q4, d29, d20
+	vmlal.s32	q8, d22, d21
+	vmlal.s32	q8, d28, d20
+	vmlal.s32	q5, d24, d20
+	vst1.8		{d14-d15}, [r2, : 128]
+	vmull.s32	q7, d18, d6
+	vmlal.s32	q7, d26, d0
+	add		r2, sp, #624
+	vld1.8		{d30-d31}, [r2, : 128]
+	vmlal.s32	q2, d30, d21
+	vmlal.s32	q7, d19, d21
+	vmlal.s32	q7, d27, d20
+	add		r2, sp, #592
+	vld1.8		{d26-d27}, [r2, : 128]
+	vmlal.s32	q4, d25, d27
+	vmlal.s32	q8, d29, d27
+	vmlal.s32	q8, d25, d26
+	vmlal.s32	q7, d28, d27
+	vmlal.s32	q7, d29, d26
+	add		r2, sp, #576
+	vld1.8		{d28-d29}, [r2, : 128]
+	vmlal.s32	q4, d24, d29
+	vmlal.s32	q8, d23, d29
+	vmlal.s32	q8, d24, d28
+	vmlal.s32	q7, d22, d29
+	vmlal.s32	q7, d23, d28
+	vst1.8		{d8-d9}, [r2, : 128]
+	add		r2, sp, #528
+	vld1.8		{d8-d9}, [r2, : 128]
+	vmlal.s32	q7, d24, d9
+	vmlal.s32	q7, d25, d31
+	vmull.s32	q1, d18, d2
+	vmlal.s32	q1, d19, d1
+	vmlal.s32	q1, d22, d0
+	vmlal.s32	q1, d24, d27
+	vmlal.s32	q1, d23, d20
+	vmlal.s32	q1, d12, d7
+	vmlal.s32	q1, d13, d6
+	vmull.s32	q6, d18, d1
+	vmlal.s32	q6, d19, d0
+	vmlal.s32	q6, d23, d27
+	vmlal.s32	q6, d22, d20
+	vmlal.s32	q6, d24, d26
+	vmull.s32	q0, d18, d0
+	vmlal.s32	q0, d22, d27
+	vmlal.s32	q0, d23, d26
+	vmlal.s32	q0, d24, d31
+	vmlal.s32	q0, d19, d20
+	add		r2, sp, #608
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q2, d18, d7
+	vmlal.s32	q5, d18, d6
+	vmlal.s32	q1, d18, d21
+	vmlal.s32	q0, d18, d28
+	vmlal.s32	q6, d18, d29
+	vmlal.s32	q2, d19, d6
+	vmlal.s32	q5, d19, d21
+	vmlal.s32	q1, d19, d29
+	vmlal.s32	q0, d19, d9
+	vmlal.s32	q6, d19, d28
+	add		r2, sp, #560
+	vld1.8		{d18-d19}, [r2, : 128]
+	add		r2, sp, #480
+	vld1.8		{d22-d23}, [r2, : 128]
+	vmlal.s32	q5, d19, d7
+	vmlal.s32	q0, d18, d21
+	vmlal.s32	q0, d19, d29
+	vmlal.s32	q6, d18, d6
+	add		r2, sp, #496
+	vld1.8		{d6-d7}, [r2, : 128]
+	vmlal.s32	q6, d19, d21
+	add		r2, sp, #544
+	vld1.8		{d18-d19}, [r2, : 128]
+	vmlal.s32	q0, d30, d8
+	add		r2, sp, #640
+	vld1.8		{d20-d21}, [r2, : 128]
+	vmlal.s32	q5, d30, d29
+	add		r2, sp, #576
+	vld1.8		{d24-d25}, [r2, : 128]
+	vmlal.s32	q1, d30, d28
+	vadd.i64	q13, q0, q11
+	vadd.i64	q14, q5, q11
+	vmlal.s32	q6, d30, d9
+	vshr.s64	q4, q13, #26
+	vshr.s64	q13, q14, #26
+	vadd.i64	q7, q7, q4
+	vshl.i64	q4, q4, #26
+	vadd.i64	q14, q7, q3
+	vadd.i64	q9, q9, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q15, q9, q3
+	vsub.i64	q0, q0, q4
+	vshr.s64	q4, q14, #25
+	vsub.i64	q5, q5, q13
+	vshr.s64	q13, q15, #25
+	vadd.i64	q6, q6, q4
+	vshl.i64	q4, q4, #25
+	vadd.i64	q14, q6, q11
+	vadd.i64	q2, q2, q13
+	vsub.i64	q4, q7, q4
+	vshr.s64	q7, q14, #26
+	vshl.i64	q13, q13, #25
+	vadd.i64	q14, q2, q11
+	vadd.i64	q8, q8, q7
+	vshl.i64	q7, q7, #26
+	vadd.i64	q15, q8, q3
+	vsub.i64	q9, q9, q13
+	vshr.s64	q13, q14, #26
+	vsub.i64	q6, q6, q7
+	vshr.s64	q7, q15, #25
+	vadd.i64	q10, q10, q13
+	vshl.i64	q13, q13, #26
+	vadd.i64	q14, q10, q3
+	vadd.i64	q1, q1, q7
+	add		r2, r3, #240
+	vshl.i64	q7, q7, #25
+	add		r4, r3, #144
+	vadd.i64	q15, q1, q11
+	add		r2, r2, #8
+	vsub.i64	q2, q2, q13
+	add		r4, r4, #8
+	vshr.s64	q13, q14, #25
+	vsub.i64	q7, q8, q7
+	vshr.s64	q8, q15, #26
+	vadd.i64	q14, q13, q13
+	vadd.i64	q12, q12, q8
+	vtrn.32		d12, d14
+	vshl.i64	q8, q8, #26
+	vtrn.32		d13, d15
+	vadd.i64	q3, q12, q3
+	vadd.i64	q0, q0, q14
+	vst1.8		d12, [r2, : 64]!
+	vshl.i64	q7, q13, #4
+	vst1.8		d13, [r4, : 64]!
+	vsub.i64	q1, q1, q8
+	vshr.s64	q3, q3, #25
+	vadd.i64	q0, q0, q7
+	vadd.i64	q5, q5, q3
+	vshl.i64	q3, q3, #25
+	vadd.i64	q6, q5, q11
+	vadd.i64	q0, q0, q13
+	vshl.i64	q7, q13, #25
+	vadd.i64	q8, q0, q11
+	vsub.i64	q3, q12, q3
+	vshr.s64	q6, q6, #26
+	vsub.i64	q7, q10, q7
+	vtrn.32		d2, d6
+	vshr.s64	q8, q8, #26
+	vtrn.32		d3, d7
+	vadd.i64	q3, q9, q6
+	vst1.8		d2, [r2, : 64]
+	vshl.i64	q6, q6, #26
+	vst1.8		d3, [r4, : 64]
+	vadd.i64	q1, q4, q8
+	vtrn.32		d4, d14
+	vshl.i64	q4, q8, #26
+	vtrn.32		d5, d15
+	vsub.i64	q5, q5, q6
+	add		r2, r2, #16
+	vsub.i64	q0, q0, q4
+	vst1.8		d4, [r2, : 64]
+	add		r4, r4, #16
+	vst1.8		d5, [r4, : 64]
+	vtrn.32		d10, d6
+	vtrn.32		d11, d7
+	sub		r2, r2, #8
+	sub		r4, r4, #8
+	vtrn.32		d0, d2
+	vtrn.32		d1, d3
+	vst1.8		d10, [r2, : 64]
+	vst1.8		d11, [r4, : 64]
+	sub		r2, r2, #24
+	sub		r4, r4, #24
+	vst1.8		d0, [r2, : 64]
+	vst1.8		d1, [r4, : 64]
+	ldr		r2, [sp, #456]
+	ldr		r4, [sp, #460]
+	subs		r5, r2, #1
+	bge		.Lmainloop
+	add		r1, r3, #144
+	add		r2, r3, #336
+	vld1.8		{d0-d1}, [r1, : 128]!
+	vld1.8		{d2-d3}, [r1, : 128]!
+	vld1.8		{d4}, [r1, : 64]
+	vst1.8		{d0-d1}, [r2, : 128]!
+	vst1.8		{d2-d3}, [r2, : 128]!
+	vst1.8		d4, [r2, : 64]
+	movw		r1, #0
+.Linvertloop:
+	add		r2, r3, #144
+	movw		r4, #0
+	movw		r5, #2
+	cmp		r1, #1
+	moveq		r5, #1
+	addeq		r2, r3, #336
+	addeq		r4, r3, #48
+	cmp		r1, #2
+	moveq		r5, #1
+	addeq		r2, r3, #48
+	cmp		r1, #3
+	moveq		r5, #5
+	addeq		r4, r3, #336
+	cmp		r1, #4
+	moveq		r5, #10
+	cmp		r1, #5
+	moveq		r5, #20
+	cmp		r1, #6
+	moveq		r5, #10
+	addeq		r2, r3, #336
+	addeq		r4, r3, #336
+	cmp		r1, #7
+	moveq		r5, #50
+	cmp		r1, #8
+	moveq		r5, #100
+	cmp		r1, #9
+	moveq		r5, #50
+	addeq		r2, r3, #336
+	cmp		r1, #10
+	moveq		r5, #5
+	addeq		r2, r3, #48
+	cmp		r1, #11
+	moveq		r5, #0
+	addeq		r2, r3, #96
+	add		r6, r3, #144
+	add		r7, r3, #288
+	vld1.8		{d0-d1}, [r6, : 128]!
+	vld1.8		{d2-d3}, [r6, : 128]!
+	vld1.8		{d4}, [r6, : 64]
+	vst1.8		{d0-d1}, [r7, : 128]!
+	vst1.8		{d2-d3}, [r7, : 128]!
+	vst1.8		d4, [r7, : 64]
+	cmp		r5, #0
+	beq		.Lskipsquaringloop
+.Lsquaringloop:
+	add		r6, r3, #288
+	add		r7, r3, #288
+	add		r8, r3, #288
+	vmov.i32	q0, #19
+	vmov.i32	q1, #0
+	vmov.i32	q2, #1
+	vzip.i32	q1, q2
+	vld1.8		{d4-d5}, [r7, : 128]!
+	vld1.8		{d6-d7}, [r7, : 128]!
+	vld1.8		{d9}, [r7, : 64]
+	vld1.8		{d10-d11}, [r6, : 128]!
+	add		r7, sp, #384
+	vld1.8		{d12-d13}, [r6, : 128]!
+	vmul.i32	q7, q2, q0
+	vld1.8		{d8}, [r6, : 64]
+	vext.32		d17, d11, d10, #1
+	vmul.i32	q9, q3, q0
+	vext.32		d16, d10, d8, #1
+	vshl.u32	q10, q5, q1
+	vext.32		d22, d14, d4, #1
+	vext.32		d24, d18, d6, #1
+	vshl.u32	q13, q6, q1
+	vshl.u32	d28, d8, d2
+	vrev64.i32	d22, d22
+	vmul.i32	d1, d9, d1
+	vrev64.i32	d24, d24
+	vext.32		d29, d8, d13, #1
+	vext.32		d0, d1, d9, #1
+	vrev64.i32	d0, d0
+	vext.32		d2, d9, d1, #1
+	vext.32		d23, d15, d5, #1
+	vmull.s32	q4, d20, d4
+	vrev64.i32	d23, d23
+	vmlal.s32	q4, d21, d1
+	vrev64.i32	d2, d2
+	vmlal.s32	q4, d26, d19
+	vext.32		d3, d5, d15, #1
+	vmlal.s32	q4, d27, d18
+	vrev64.i32	d3, d3
+	vmlal.s32	q4, d28, d15
+	vext.32		d14, d12, d11, #1
+	vmull.s32	q5, d16, d23
+	vext.32		d15, d13, d12, #1
+	vmlal.s32	q5, d17, d4
+	vst1.8		d8, [r7, : 64]!
+	vmlal.s32	q5, d14, d1
+	vext.32		d12, d9, d8, #0
+	vmlal.s32	q5, d15, d19
+	vmov.i64	d13, #0
+	vmlal.s32	q5, d29, d18
+	vext.32		d25, d19, d7, #1
+	vmlal.s32	q6, d20, d5
+	vrev64.i32	d25, d25
+	vmlal.s32	q6, d21, d4
+	vst1.8		d11, [r7, : 64]!
+	vmlal.s32	q6, d26, d1
+	vext.32		d9, d10, d10, #0
+	vmlal.s32	q6, d27, d19
+	vmov.i64	d8, #0
+	vmlal.s32	q6, d28, d18
+	vmlal.s32	q4, d16, d24
+	vmlal.s32	q4, d17, d5
+	vmlal.s32	q4, d14, d4
+	vst1.8		d12, [r7, : 64]!
+	vmlal.s32	q4, d15, d1
+	vext.32		d10, d13, d12, #0
+	vmlal.s32	q4, d29, d19
+	vmov.i64	d11, #0
+	vmlal.s32	q5, d20, d6
+	vmlal.s32	q5, d21, d5
+	vmlal.s32	q5, d26, d4
+	vext.32		d13, d8, d8, #0
+	vmlal.s32	q5, d27, d1
+	vmov.i64	d12, #0
+	vmlal.s32	q5, d28, d19
+	vst1.8		d9, [r7, : 64]!
+	vmlal.s32	q6, d16, d25
+	vmlal.s32	q6, d17, d6
+	vst1.8		d10, [r7, : 64]
+	vmlal.s32	q6, d14, d5
+	vext.32		d8, d11, d10, #0
+	vmlal.s32	q6, d15, d4
+	vmov.i64	d9, #0
+	vmlal.s32	q6, d29, d1
+	vmlal.s32	q4, d20, d7
+	vmlal.s32	q4, d21, d6
+	vmlal.s32	q4, d26, d5
+	vext.32		d11, d12, d12, #0
+	vmlal.s32	q4, d27, d4
+	vmov.i64	d10, #0
+	vmlal.s32	q4, d28, d1
+	vmlal.s32	q5, d16, d0
+	sub		r6, r7, #32
+	vmlal.s32	q5, d17, d7
+	vmlal.s32	q5, d14, d6
+	vext.32		d30, d9, d8, #0
+	vmlal.s32	q5, d15, d5
+	vld1.8		{d31}, [r6, : 64]!
+	vmlal.s32	q5, d29, d4
+	vmlal.s32	q15, d20, d0
+	vext.32		d0, d6, d18, #1
+	vmlal.s32	q15, d21, d25
+	vrev64.i32	d0, d0
+	vmlal.s32	q15, d26, d24
+	vext.32		d1, d7, d19, #1
+	vext.32		d7, d10, d10, #0
+	vmlal.s32	q15, d27, d23
+	vrev64.i32	d1, d1
+	vld1.8		{d6}, [r6, : 64]
+	vmlal.s32	q15, d28, d22
+	vmlal.s32	q3, d16, d4
+	add		r6, r6, #24
+	vmlal.s32	q3, d17, d2
+	vext.32		d4, d31, d30, #0
+	vmov		d17, d11
+	vmlal.s32	q3, d14, d1
+	vext.32		d11, d13, d13, #0
+	vext.32		d13, d30, d30, #0
+	vmlal.s32	q3, d15, d0
+	vext.32		d1, d8, d8, #0
+	vmlal.s32	q3, d29, d3
+	vld1.8		{d5}, [r6, : 64]
+	sub		r6, r6, #16
+	vext.32		d10, d6, d6, #0
+	vmov.i32	q1, #0xffffffff
+	vshl.i64	q4, q1, #25
+	add		r7, sp, #480
+	vld1.8		{d14-d15}, [r7, : 128]
+	vadd.i64	q9, q2, q7
+	vshl.i64	q1, q1, #26
+	vshr.s64	q10, q9, #26
+	vld1.8		{d0}, [r6, : 64]!
+	vadd.i64	q5, q5, q10
+	vand		q9, q9, q1
+	vld1.8		{d16}, [r6, : 64]!
+	add		r6, sp, #496
+	vld1.8		{d20-d21}, [r6, : 128]
+	vadd.i64	q11, q5, q10
+	vsub.i64	q2, q2, q9
+	vshr.s64	q9, q11, #25
+	vext.32		d12, d5, d4, #0
+	vand		q11, q11, q4
+	vadd.i64	q0, q0, q9
+	vmov		d19, d7
+	vadd.i64	q3, q0, q7
+	vsub.i64	q5, q5, q11
+	vshr.s64	q11, q3, #26
+	vext.32		d18, d11, d10, #0
+	vand		q3, q3, q1
+	vadd.i64	q8, q8, q11
+	vadd.i64	q11, q8, q10
+	vsub.i64	q0, q0, q3
+	vshr.s64	q3, q11, #25
+	vand		q11, q11, q4
+	vadd.i64	q3, q6, q3
+	vadd.i64	q6, q3, q7
+	vsub.i64	q8, q8, q11
+	vshr.s64	q11, q6, #26
+	vand		q6, q6, q1
+	vadd.i64	q9, q9, q11
+	vadd.i64	d25, d19, d21
+	vsub.i64	q3, q3, q6
+	vshr.s64	d23, d25, #25
+	vand		q4, q12, q4
+	vadd.i64	d21, d23, d23
+	vshl.i64	d25, d23, #4
+	vadd.i64	d21, d21, d23
+	vadd.i64	d25, d25, d21
+	vadd.i64	d4, d4, d25
+	vzip.i32	q0, q8
+	vadd.i64	d12, d4, d14
+	add		r6, r8, #8
+	vst1.8		d0, [r6, : 64]
+	vsub.i64	d19, d19, d9
+	add		r6, r6, #16
+	vst1.8		d16, [r6, : 64]
+	vshr.s64	d22, d12, #26
+	vand		q0, q6, q1
+	vadd.i64	d10, d10, d22
+	vzip.i32	q3, q9
+	vsub.i64	d4, d4, d0
+	sub		r6, r6, #8
+	vst1.8		d6, [r6, : 64]
+	add		r6, r6, #16
+	vst1.8		d18, [r6, : 64]
+	vzip.i32	q2, q5
+	sub		r6, r6, #32
+	vst1.8		d4, [r6, : 64]
+	subs		r5, r5, #1
+	bhi		.Lsquaringloop
+.Lskipsquaringloop:
+	mov		r2, r2
+	add		r5, r3, #288
+	add		r6, r3, #144
+	vmov.i32	q0, #19
+	vmov.i32	q1, #0
+	vmov.i32	q2, #1
+	vzip.i32	q1, q2
+	vld1.8		{d4-d5}, [r5, : 128]!
+	vld1.8		{d6-d7}, [r5, : 128]!
+	vld1.8		{d9}, [r5, : 64]
+	vld1.8		{d10-d11}, [r2, : 128]!
+	add		r5, sp, #384
+	vld1.8		{d12-d13}, [r2, : 128]!
+	vmul.i32	q7, q2, q0
+	vld1.8		{d8}, [r2, : 64]
+	vext.32		d17, d11, d10, #1
+	vmul.i32	q9, q3, q0
+	vext.32		d16, d10, d8, #1
+	vshl.u32	q10, q5, q1
+	vext.32		d22, d14, d4, #1
+	vext.32		d24, d18, d6, #1
+	vshl.u32	q13, q6, q1
+	vshl.u32	d28, d8, d2
+	vrev64.i32	d22, d22
+	vmul.i32	d1, d9, d1
+	vrev64.i32	d24, d24
+	vext.32		d29, d8, d13, #1
+	vext.32		d0, d1, d9, #1
+	vrev64.i32	d0, d0
+	vext.32		d2, d9, d1, #1
+	vext.32		d23, d15, d5, #1
+	vmull.s32	q4, d20, d4
+	vrev64.i32	d23, d23
+	vmlal.s32	q4, d21, d1
+	vrev64.i32	d2, d2
+	vmlal.s32	q4, d26, d19
+	vext.32		d3, d5, d15, #1
+	vmlal.s32	q4, d27, d18
+	vrev64.i32	d3, d3
+	vmlal.s32	q4, d28, d15
+	vext.32		d14, d12, d11, #1
+	vmull.s32	q5, d16, d23
+	vext.32		d15, d13, d12, #1
+	vmlal.s32	q5, d17, d4
+	vst1.8		d8, [r5, : 64]!
+	vmlal.s32	q5, d14, d1
+	vext.32		d12, d9, d8, #0
+	vmlal.s32	q5, d15, d19
+	vmov.i64	d13, #0
+	vmlal.s32	q5, d29, d18
+	vext.32		d25, d19, d7, #1
+	vmlal.s32	q6, d20, d5
+	vrev64.i32	d25, d25
+	vmlal.s32	q6, d21, d4
+	vst1.8		d11, [r5, : 64]!
+	vmlal.s32	q6, d26, d1
+	vext.32		d9, d10, d10, #0
+	vmlal.s32	q6, d27, d19
+	vmov.i64	d8, #0
+	vmlal.s32	q6, d28, d18
+	vmlal.s32	q4, d16, d24
+	vmlal.s32	q4, d17, d5
+	vmlal.s32	q4, d14, d4
+	vst1.8		d12, [r5, : 64]!
+	vmlal.s32	q4, d15, d1
+	vext.32		d10, d13, d12, #0
+	vmlal.s32	q4, d29, d19
+	vmov.i64	d11, #0
+	vmlal.s32	q5, d20, d6
+	vmlal.s32	q5, d21, d5
+	vmlal.s32	q5, d26, d4
+	vext.32		d13, d8, d8, #0
+	vmlal.s32	q5, d27, d1
+	vmov.i64	d12, #0
+	vmlal.s32	q5, d28, d19
+	vst1.8		d9, [r5, : 64]!
+	vmlal.s32	q6, d16, d25
+	vmlal.s32	q6, d17, d6
+	vst1.8		d10, [r5, : 64]
+	vmlal.s32	q6, d14, d5
+	vext.32		d8, d11, d10, #0
+	vmlal.s32	q6, d15, d4
+	vmov.i64	d9, #0
+	vmlal.s32	q6, d29, d1
+	vmlal.s32	q4, d20, d7
+	vmlal.s32	q4, d21, d6
+	vmlal.s32	q4, d26, d5
+	vext.32		d11, d12, d12, #0
+	vmlal.s32	q4, d27, d4
+	vmov.i64	d10, #0
+	vmlal.s32	q4, d28, d1
+	vmlal.s32	q5, d16, d0
+	sub		r2, r5, #32
+	vmlal.s32	q5, d17, d7
+	vmlal.s32	q5, d14, d6
+	vext.32		d30, d9, d8, #0
+	vmlal.s32	q5, d15, d5
+	vld1.8		{d31}, [r2, : 64]!
+	vmlal.s32	q5, d29, d4
+	vmlal.s32	q15, d20, d0
+	vext.32		d0, d6, d18, #1
+	vmlal.s32	q15, d21, d25
+	vrev64.i32	d0, d0
+	vmlal.s32	q15, d26, d24
+	vext.32		d1, d7, d19, #1
+	vext.32		d7, d10, d10, #0
+	vmlal.s32	q15, d27, d23
+	vrev64.i32	d1, d1
+	vld1.8		{d6}, [r2, : 64]
+	vmlal.s32	q15, d28, d22
+	vmlal.s32	q3, d16, d4
+	add		r2, r2, #24
+	vmlal.s32	q3, d17, d2
+	vext.32		d4, d31, d30, #0
+	vmov		d17, d11
+	vmlal.s32	q3, d14, d1
+	vext.32		d11, d13, d13, #0
+	vext.32		d13, d30, d30, #0
+	vmlal.s32	q3, d15, d0
+	vext.32		d1, d8, d8, #0
+	vmlal.s32	q3, d29, d3
+	vld1.8		{d5}, [r2, : 64]
+	sub		r2, r2, #16
+	vext.32		d10, d6, d6, #0
+	vmov.i32	q1, #0xffffffff
+	vshl.i64	q4, q1, #25
+	add		r5, sp, #480
+	vld1.8		{d14-d15}, [r5, : 128]
+	vadd.i64	q9, q2, q7
+	vshl.i64	q1, q1, #26
+	vshr.s64	q10, q9, #26
+	vld1.8		{d0}, [r2, : 64]!
+	vadd.i64	q5, q5, q10
+	vand		q9, q9, q1
+	vld1.8		{d16}, [r2, : 64]!
+	add		r2, sp, #496
+	vld1.8		{d20-d21}, [r2, : 128]
+	vadd.i64	q11, q5, q10
+	vsub.i64	q2, q2, q9
+	vshr.s64	q9, q11, #25
+	vext.32		d12, d5, d4, #0
+	vand		q11, q11, q4
+	vadd.i64	q0, q0, q9
+	vmov		d19, d7
+	vadd.i64	q3, q0, q7
+	vsub.i64	q5, q5, q11
+	vshr.s64	q11, q3, #26
+	vext.32		d18, d11, d10, #0
+	vand		q3, q3, q1
+	vadd.i64	q8, q8, q11
+	vadd.i64	q11, q8, q10
+	vsub.i64	q0, q0, q3
+	vshr.s64	q3, q11, #25
+	vand		q11, q11, q4
+	vadd.i64	q3, q6, q3
+	vadd.i64	q6, q3, q7
+	vsub.i64	q8, q8, q11
+	vshr.s64	q11, q6, #26
+	vand		q6, q6, q1
+	vadd.i64	q9, q9, q11
+	vadd.i64	d25, d19, d21
+	vsub.i64	q3, q3, q6
+	vshr.s64	d23, d25, #25
+	vand		q4, q12, q4
+	vadd.i64	d21, d23, d23
+	vshl.i64	d25, d23, #4
+	vadd.i64	d21, d21, d23
+	vadd.i64	d25, d25, d21
+	vadd.i64	d4, d4, d25
+	vzip.i32	q0, q8
+	vadd.i64	d12, d4, d14
+	add		r2, r6, #8
+	vst1.8		d0, [r2, : 64]
+	vsub.i64	d19, d19, d9
+	add		r2, r2, #16
+	vst1.8		d16, [r2, : 64]
+	vshr.s64	d22, d12, #26
+	vand		q0, q6, q1
+	vadd.i64	d10, d10, d22
+	vzip.i32	q3, q9
+	vsub.i64	d4, d4, d0
+	sub		r2, r2, #8
+	vst1.8		d6, [r2, : 64]
+	add		r2, r2, #16
+	vst1.8		d18, [r2, : 64]
+	vzip.i32	q2, q5
+	sub		r2, r2, #32
+	vst1.8		d4, [r2, : 64]
+	cmp		r4, #0
+	beq		.Lskippostcopy
+	add		r2, r3, #144
+	mov		r4, r4
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d4}, [r2, : 64]
+	vst1.8		{d0-d1}, [r4, : 128]!
+	vst1.8		{d2-d3}, [r4, : 128]!
+	vst1.8		d4, [r4, : 64]
+.Lskippostcopy:
+	cmp		r1, #1
+	bne		.Lskipfinalcopy
+	add		r2, r3, #288
+	add		r4, r3, #144
+	vld1.8		{d0-d1}, [r2, : 128]!
+	vld1.8		{d2-d3}, [r2, : 128]!
+	vld1.8		{d4}, [r2, : 64]
+	vst1.8		{d0-d1}, [r4, : 128]!
+	vst1.8		{d2-d3}, [r4, : 128]!
+	vst1.8		d4, [r4, : 64]
+.Lskipfinalcopy:
+	add		r1, r1, #1
+	cmp		r1, #12
+	blo		.Linvertloop
+	add		r1, r3, #144
+	ldr		r2, [r1], #4
+	ldr		r3, [r1], #4
+	ldr		r4, [r1], #4
+	ldr		r5, [r1], #4
+	ldr		r6, [r1], #4
+	ldr		r7, [r1], #4
+	ldr		r8, [r1], #4
+	ldr		r9, [r1], #4
+	ldr		r10, [r1], #4
+	ldr		r1, [r1]
+	add		r11, r1, r1, LSL #4
+	add		r11, r11, r1, LSL #1
+	add		r11, r11, #16777216
+	mov		r11, r11, ASR #25
+	add		r11, r11, r2
+	mov		r11, r11, ASR #26
+	add		r11, r11, r3
+	mov		r11, r11, ASR #25
+	add		r11, r11, r4
+	mov		r11, r11, ASR #26
+	add		r11, r11, r5
+	mov		r11, r11, ASR #25
+	add		r11, r11, r6
+	mov		r11, r11, ASR #26
+	add		r11, r11, r7
+	mov		r11, r11, ASR #25
+	add		r11, r11, r8
+	mov		r11, r11, ASR #26
+	add		r11, r11, r9
+	mov		r11, r11, ASR #25
+	add		r11, r11, r10
+	mov		r11, r11, ASR #26
+	add		r11, r11, r1
+	mov		r11, r11, ASR #25
+	add		r2, r2, r11
+	add		r2, r2, r11, LSL #1
+	add		r2, r2, r11, LSL #4
+	mov		r11, r2, ASR #26
+	add		r3, r3, r11
+	sub		r2, r2, r11, LSL #26
+	mov		r11, r3, ASR #25
+	add		r4, r4, r11
+	sub		r3, r3, r11, LSL #25
+	mov		r11, r4, ASR #26
+	add		r5, r5, r11
+	sub		r4, r4, r11, LSL #26
+	mov		r11, r5, ASR #25
+	add		r6, r6, r11
+	sub		r5, r5, r11, LSL #25
+	mov		r11, r6, ASR #26
+	add		r7, r7, r11
+	sub		r6, r6, r11, LSL #26
+	mov		r11, r7, ASR #25
+	add		r8, r8, r11
+	sub		r7, r7, r11, LSL #25
+	mov		r11, r8, ASR #26
+	add		r9, r9, r11
+	sub		r8, r8, r11, LSL #26
+	mov		r11, r9, ASR #25
+	add		r10, r10, r11
+	sub		r9, r9, r11, LSL #25
+	mov		r11, r10, ASR #26
+	add		r1, r1, r11
+	sub		r10, r10, r11, LSL #26
+	mov		r11, r1, ASR #25
+	sub		r1, r1, r11, LSL #25
+	add		r2, r2, r3, LSL #26
+	mov		r3, r3, LSR #6
+	add		r3, r3, r4, LSL #19
+	mov		r4, r4, LSR #13
+	add		r4, r4, r5, LSL #13
+	mov		r5, r5, LSR #19
+	add		r5, r5, r6, LSL #6
+	add		r6, r7, r8, LSL #25
+	mov		r7, r8, LSR #7
+	add		r7, r7, r9, LSL #19
+	mov		r8, r9, LSR #13
+	add		r8, r8, r10, LSL #12
+	mov		r9, r10, LSR #20
+	add		r1, r9, r1, LSL #6
+	str		r2, [r0]
+	str		r3, [r0, #4]
+	str		r4, [r0, #8]
+	str		r5, [r0, #12]
+	str		r6, [r0, #16]
+	str		r7, [r0, #20]
+	str		r8, [r0, #24]
+	str		r1, [r0, #28]
+	movw		r0, #0
+	mov		sp, ip
+	pop		{r4-r11, pc}
+ENDPROC(curve25519_neon)
diff --git a/arch/arm/crypto/curve25519-glue.c b/arch/arm/crypto/curve25519-glue.c
new file mode 100644
index 000000000000..f3f42cf3b893
--- /dev/null
+++ b/arch/arm/crypto/curve25519-glue.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * Based on public domain code from Daniel J. Bernstein and Peter Schwabe. This
+ * began from SUPERCOP's curve25519/neon2/scalarmult.s, but has subsequently been
+ * manually reworked for use in kernel space.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/internal/simd.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <crypto/curve25519.h>
+
+asmlinkage void curve25519_neon(u8 mypublic[CURVE25519_KEY_SIZE],
+				const u8 secret[CURVE25519_KEY_SIZE],
+				const u8 basepoint[CURVE25519_KEY_SIZE]);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void curve25519_arch(u8 out[CURVE25519_KEY_SIZE],
+		     const u8 scalar[CURVE25519_KEY_SIZE],
+		     const u8 point[CURVE25519_KEY_SIZE])
+{
+	if (static_branch_likely(&have_neon) && crypto_simd_usable()) {
+		kernel_neon_begin();
+		curve25519_neon(out, scalar, point);
+		kernel_neon_end();
+	} else {
+		curve25519_generic(out, scalar, point);
+	}
+}
+EXPORT_SYMBOL(curve25519_arch);
+
+static int curve25519_set_secret(struct crypto_kpp *tfm, const void *buf,
+				 unsigned int len)
+{
+	u8 *secret = kpp_tfm_ctx(tfm);
+
+	if (!len)
+		curve25519_generate_secret(secret);
+	else if (len == CURVE25519_KEY_SIZE &&
+		 crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE))
+		memcpy(secret, buf, CURVE25519_KEY_SIZE);
+	else
+		return -EINVAL;
+	return 0;
+}
+
+static int curve25519_compute_value(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	const u8 *secret = kpp_tfm_ctx(tfm);
+	u8 public_key[CURVE25519_KEY_SIZE];
+	u8 buf[CURVE25519_KEY_SIZE];
+	int copied, nbytes;
+	u8 const *bp;
+
+	if (req->src) {
+		copied = sg_copy_to_buffer(req->src,
+					   sg_nents_for_len(req->src,
+							    CURVE25519_KEY_SIZE),
+					   public_key, CURVE25519_KEY_SIZE);
+		if (copied != CURVE25519_KEY_SIZE)
+			return -EINVAL;
+		bp = public_key;
+	} else {
+		bp = curve25519_base_point;
+	}
+
+	curve25519_arch(buf, secret, bp);
+
+	/* might want less than we've got */
+	nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+								nbytes),
+				     buf, nbytes);
+	if (copied != nbytes)
+		return -EINVAL;
+	return 0;
+}
+
+static unsigned int curve25519_max_size(struct crypto_kpp *tfm)
+{
+	return CURVE25519_KEY_SIZE;
+}
+
+static struct kpp_alg curve25519_alg = {
+	.base.cra_name		= "curve25519",
+	.base.cra_driver_name	= "curve25519-neon",
+	.base.cra_priority	= 200,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_ctxsize	= CURVE25519_KEY_SIZE,
+
+	.set_secret		= curve25519_set_secret,
+	.generate_public_key	= curve25519_compute_value,
+	.compute_shared_secret	= curve25519_compute_value,
+	.max_size		= curve25519_max_size,
+};
+
+static int __init mod_init(void)
+{
+	if (elf_hwcap & HWCAP_NEON) {
+		static_branch_enable(&have_neon);
+		return IS_REACHABLE(CONFIG_CRYPTO_KPP) ?
+			crypto_register_kpp(&curve25519_alg) : 0;
+	}
+	return 0;
+}
+
+static void __exit mod_exit(void)
+{
+	if (IS_REACHABLE(CONFIG_CRYPTO_KPP) && elf_hwcap & HWCAP_NEON)
+		crypto_unregister_kpp(&curve25519_alg);
+}
+
+module_init(mod_init);
+module_exit(mod_exit);
+
+MODULE_ALIAS_CRYPTO("curve25519");
+MODULE_ALIAS_CRYPTO("curve25519-neon");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/crypto/ghash-ce-core.S b/arch/arm/crypto/ghash-ce-core.S
index c47fe81abcb0..534c9647726d 100644
--- a/arch/arm/crypto/ghash-ce-core.S
+++ b/arch/arm/crypto/ghash-ce-core.S
@@ -88,6 +88,7 @@
 	T3_H		.req	d17
 
 	.text
+	.arch		armv8-a
 	.fpu		crypto-neon-fp-armv8
 
 	.macro		__pmull_p64, rd, rn, rm, b1, b2, b3, b4
diff --git a/arch/arm/crypto/poly1305-armv4.pl b/arch/arm/crypto/poly1305-armv4.pl
new file mode 100644
index 000000000000..6d79498d3115
--- /dev/null
+++ b/arch/arm/crypto/poly1305-armv4.pl
@@ -0,0 +1,1236 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause
+#
+# ====================================================================
+# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL
+# project.
+# ====================================================================
+#
+#			IALU(*)/gcc-4.4		NEON
+#
+# ARM11xx(ARMv6)	7.78/+100%		-
+# Cortex-A5		6.35/+130%		3.00
+# Cortex-A8		6.25/+115%		2.36
+# Cortex-A9		5.10/+95%		2.55
+# Cortex-A15		3.85/+85%		1.25(**)
+# Snapdragon S4		5.70/+100%		1.48(**)
+#
+# (*)	this is for -march=armv6, i.e. with bunch of ldrb loading data;
+# (**)	these are trade-off results, they can be improved by ~8% but at
+#	the cost of 15/12% regression on Cortex-A5/A7, it's even possible
+#	to improve Cortex-A9 result, but then A5/A7 loose more than 20%;
+
+$flavour = shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
+
+($ctx,$inp,$len,$padbit)=map("r$_",(0..3));
+
+$code.=<<___;
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
+# define poly1305_init   poly1305_init_arm
+# define poly1305_blocks poly1305_blocks_arm
+# define poly1305_emit   poly1305_emit_arm
+.globl	poly1305_blocks_neon
+#endif
+
+#if defined(__thumb2__)
+.syntax	unified
+.thumb
+#else
+.code	32
+#endif
+
+.text
+
+.globl	poly1305_emit
+.globl	poly1305_blocks
+.globl	poly1305_init
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+.Lpoly1305_init:
+	stmdb	sp!,{r4-r11}
+
+	eor	r3,r3,r3
+	cmp	$inp,#0
+	str	r3,[$ctx,#0]		@ zero hash value
+	str	r3,[$ctx,#4]
+	str	r3,[$ctx,#8]
+	str	r3,[$ctx,#12]
+	str	r3,[$ctx,#16]
+	str	r3,[$ctx,#36]		@ clear is_base2_26
+	add	$ctx,$ctx,#20
+
+#ifdef	__thumb2__
+	it	eq
+#endif
+	moveq	r0,#0
+	beq	.Lno_key
+
+#if	__ARM_MAX_ARCH__>=7
+	mov	r3,#-1
+	str	r3,[$ctx,#28]		@ impossible key power value
+# ifndef __KERNEL__
+	adr	r11,.Lpoly1305_init
+	ldr	r12,.LOPENSSL_armcap
+# endif
+#endif
+	ldrb	r4,[$inp,#0]
+	mov	r10,#0x0fffffff
+	ldrb	r5,[$inp,#1]
+	and	r3,r10,#-4		@ 0x0ffffffc
+	ldrb	r6,[$inp,#2]
+	ldrb	r7,[$inp,#3]
+	orr	r4,r4,r5,lsl#8
+	ldrb	r5,[$inp,#4]
+	orr	r4,r4,r6,lsl#16
+	ldrb	r6,[$inp,#5]
+	orr	r4,r4,r7,lsl#24
+	ldrb	r7,[$inp,#6]
+	and	r4,r4,r10
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+# if !defined(_WIN32)
+	ldr	r12,[r11,r12]		@ OPENSSL_armcap_P
+# endif
+# if defined(__APPLE__) || defined(_WIN32)
+	ldr	r12,[r12]
+# endif
+#endif
+	ldrb	r8,[$inp,#7]
+	orr	r5,r5,r6,lsl#8
+	ldrb	r6,[$inp,#8]
+	orr	r5,r5,r7,lsl#16
+	ldrb	r7,[$inp,#9]
+	orr	r5,r5,r8,lsl#24
+	ldrb	r8,[$inp,#10]
+	and	r5,r5,r3
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	tst	r12,#ARMV7_NEON		@ check for NEON
+# ifdef	__thumb2__
+	adr	r9,.Lpoly1305_blocks_neon
+	adr	r11,.Lpoly1305_blocks
+	it	ne
+	movne	r11,r9
+	adr	r12,.Lpoly1305_emit
+	orr	r11,r11,#1		@ thumb-ify addresses
+	orr	r12,r12,#1
+# else
+	add	r12,r11,#(.Lpoly1305_emit-.Lpoly1305_init)
+	ite	eq
+	addeq	r11,r11,#(.Lpoly1305_blocks-.Lpoly1305_init)
+	addne	r11,r11,#(.Lpoly1305_blocks_neon-.Lpoly1305_init)
+# endif
+#endif
+	ldrb	r9,[$inp,#11]
+	orr	r6,r6,r7,lsl#8
+	ldrb	r7,[$inp,#12]
+	orr	r6,r6,r8,lsl#16
+	ldrb	r8,[$inp,#13]
+	orr	r6,r6,r9,lsl#24
+	ldrb	r9,[$inp,#14]
+	and	r6,r6,r3
+
+	ldrb	r10,[$inp,#15]
+	orr	r7,r7,r8,lsl#8
+	str	r4,[$ctx,#0]
+	orr	r7,r7,r9,lsl#16
+	str	r5,[$ctx,#4]
+	orr	r7,r7,r10,lsl#24
+	str	r6,[$ctx,#8]
+	and	r7,r7,r3
+	str	r7,[$ctx,#12]
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	stmia	r2,{r11,r12}		@ fill functions table
+	mov	r0,#1
+#else
+	mov	r0,#0
+#endif
+.Lno_key:
+	ldmia	sp!,{r4-r11}
+#if	__ARM_ARCH__>=5
+	ret				@ bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_init,.-poly1305_init
+___
+{
+my ($h0,$h1,$h2,$h3,$h4,$r0,$r1,$r2,$r3)=map("r$_",(4..12));
+my ($s1,$s2,$s3)=($r1,$r2,$r3);
+
+$code.=<<___;
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+.Lpoly1305_blocks:
+	stmdb	sp!,{r3-r11,lr}
+
+	ands	$len,$len,#-16
+	beq	.Lno_data
+
+	add	$len,$len,$inp		@ end pointer
+	sub	sp,sp,#32
+
+#if __ARM_ARCH__<7
+	ldmia	$ctx,{$h0-$r3}		@ load context
+	add	$ctx,$ctx,#20
+	str	$len,[sp,#16]		@ offload stuff
+	str	$ctx,[sp,#12]
+#else
+	ldr	lr,[$ctx,#36]		@ is_base2_26
+	ldmia	$ctx!,{$h0-$h4}		@ load hash value
+	str	$len,[sp,#16]		@ offload stuff
+	str	$ctx,[sp,#12]
+
+	adds	$r0,$h0,$h1,lsl#26	@ base 2^26 -> base 2^32
+	mov	$r1,$h1,lsr#6
+	adcs	$r1,$r1,$h2,lsl#20
+	mov	$r2,$h2,lsr#12
+	adcs	$r2,$r2,$h3,lsl#14
+	mov	$r3,$h3,lsr#18
+	adcs	$r3,$r3,$h4,lsl#8
+	mov	$len,#0
+	teq	lr,#0
+	str	$len,[$ctx,#16]		@ clear is_base2_26
+	adc	$len,$len,$h4,lsr#24
+
+	itttt	ne
+	movne	$h0,$r0			@ choose between radixes
+	movne	$h1,$r1
+	movne	$h2,$r2
+	movne	$h3,$r3
+	ldmia	$ctx,{$r0-$r3}		@ load key
+	it	ne
+	movne	$h4,$len
+#endif
+
+	mov	lr,$inp
+	cmp	$padbit,#0
+	str	$r1,[sp,#20]
+	str	$r2,[sp,#24]
+	str	$r3,[sp,#28]
+	b	.Loop
+
+.align	4
+.Loop:
+#if __ARM_ARCH__<7
+	ldrb	r0,[lr],#16		@ load input
+# ifdef	__thumb2__
+	it	hi
+# endif
+	addhi	$h4,$h4,#1		@ 1<<128
+	ldrb	r1,[lr,#-15]
+	ldrb	r2,[lr,#-14]
+	ldrb	r3,[lr,#-13]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-12]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-11]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-10]
+	adds	$h0,$h0,r3		@ accumulate input
+
+	ldrb	r3,[lr,#-9]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-8]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-7]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-6]
+	adcs	$h1,$h1,r3
+
+	ldrb	r3,[lr,#-5]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-4]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-3]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-2]
+	adcs	$h2,$h2,r3
+
+	ldrb	r3,[lr,#-1]
+	orr	r1,r0,r1,lsl#8
+	str	lr,[sp,#8]		@ offload input pointer
+	orr	r2,r1,r2,lsl#16
+	add	$s1,$r1,$r1,lsr#2
+	orr	r3,r2,r3,lsl#24
+#else
+	ldr	r0,[lr],#16		@ load input
+	it	hi
+	addhi	$h4,$h4,#1		@ padbit
+	ldr	r1,[lr,#-12]
+	ldr	r2,[lr,#-8]
+	ldr	r3,[lr,#-4]
+# ifdef	__ARMEB__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+# endif
+	adds	$h0,$h0,r0		@ accumulate input
+	str	lr,[sp,#8]		@ offload input pointer
+	adcs	$h1,$h1,r1
+	add	$s1,$r1,$r1,lsr#2
+	adcs	$h2,$h2,r2
+#endif
+	add	$s2,$r2,$r2,lsr#2
+	adcs	$h3,$h3,r3
+	add	$s3,$r3,$r3,lsr#2
+
+	umull	r2,r3,$h1,$r0
+	 adc	$h4,$h4,#0
+	umull	r0,r1,$h0,$r0
+	umlal	r2,r3,$h4,$s1
+	umlal	r0,r1,$h3,$s1
+	ldr	$r1,[sp,#20]		@ reload $r1
+	umlal	r2,r3,$h2,$s3
+	umlal	r0,r1,$h1,$s3
+	umlal	r2,r3,$h3,$s2
+	umlal	r0,r1,$h2,$s2
+	umlal	r2,r3,$h0,$r1
+	str	r0,[sp,#0]		@ future $h0
+	 mul	r0,$s2,$h4
+	ldr	$r2,[sp,#24]		@ reload $r2
+	adds	r2,r2,r1		@ d1+=d0>>32
+	 eor	r1,r1,r1
+	adc	lr,r3,#0		@ future $h2
+	str	r2,[sp,#4]		@ future $h1
+
+	mul	r2,$s3,$h4
+	eor	r3,r3,r3
+	umlal	r0,r1,$h3,$s3
+	ldr	$r3,[sp,#28]		@ reload $r3
+	umlal	r2,r3,$h3,$r0
+	umlal	r0,r1,$h2,$r0
+	umlal	r2,r3,$h2,$r1
+	umlal	r0,r1,$h1,$r1
+	umlal	r2,r3,$h1,$r2
+	umlal	r0,r1,$h0,$r2
+	umlal	r2,r3,$h0,$r3
+	ldr	$h0,[sp,#0]
+	mul	$h4,$r0,$h4
+	ldr	$h1,[sp,#4]
+
+	adds	$h2,lr,r0		@ d2+=d1>>32
+	ldr	lr,[sp,#8]		@ reload input pointer
+	adc	r1,r1,#0
+	adds	$h3,r2,r1		@ d3+=d2>>32
+	ldr	r0,[sp,#16]		@ reload end pointer
+	adc	r3,r3,#0
+	add	$h4,$h4,r3		@ h4+=d3>>32
+
+	and	r1,$h4,#-4
+	and	$h4,$h4,#3
+	add	r1,r1,r1,lsr#2		@ *=5
+	adds	$h0,$h0,r1
+	adcs	$h1,$h1,#0
+	adcs	$h2,$h2,#0
+	adcs	$h3,$h3,#0
+	adc	$h4,$h4,#0
+
+	cmp	r0,lr			@ done yet?
+	bhi	.Loop
+
+	ldr	$ctx,[sp,#12]
+	add	sp,sp,#32
+	stmdb	$ctx,{$h0-$h4}		@ store the result
+
+.Lno_data:
+#if	__ARM_ARCH__>=5
+	ldmia	sp!,{r3-r11,pc}
+#else
+	ldmia	sp!,{r3-r11,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_blocks,.-poly1305_blocks
+___
+}
+{
+my ($ctx,$mac,$nonce)=map("r$_",(0..2));
+my ($h0,$h1,$h2,$h3,$h4,$g0,$g1,$g2,$g3)=map("r$_",(3..11));
+my $g4=$ctx;
+
+$code.=<<___;
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+.Lpoly1305_emit:
+	stmdb	sp!,{r4-r11}
+
+	ldmia	$ctx,{$h0-$h4}
+
+#if __ARM_ARCH__>=7
+	ldr	ip,[$ctx,#36]		@ is_base2_26
+
+	adds	$g0,$h0,$h1,lsl#26	@ base 2^26 -> base 2^32
+	mov	$g1,$h1,lsr#6
+	adcs	$g1,$g1,$h2,lsl#20
+	mov	$g2,$h2,lsr#12
+	adcs	$g2,$g2,$h3,lsl#14
+	mov	$g3,$h3,lsr#18
+	adcs	$g3,$g3,$h4,lsl#8
+	mov	$g4,#0
+	adc	$g4,$g4,$h4,lsr#24
+
+	tst	ip,ip
+	itttt	ne
+	movne	$h0,$g0
+	movne	$h1,$g1
+	movne	$h2,$g2
+	movne	$h3,$g3
+	it	ne
+	movne	$h4,$g4
+#endif
+
+	adds	$g0,$h0,#5		@ compare to modulus
+	adcs	$g1,$h1,#0
+	adcs	$g2,$h2,#0
+	adcs	$g3,$h3,#0
+	adc	$g4,$h4,#0
+	tst	$g4,#4			@ did it carry/borrow?
+
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h0,$g0
+	ldr	$g0,[$nonce,#0]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h1,$g1
+	ldr	$g1,[$nonce,#4]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h2,$g2
+	ldr	$g2,[$nonce,#8]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h3,$g3
+	ldr	$g3,[$nonce,#12]
+
+	adds	$h0,$h0,$g0
+	adcs	$h1,$h1,$g1
+	adcs	$h2,$h2,$g2
+	adc	$h3,$h3,$g3
+
+#if __ARM_ARCH__>=7
+# ifdef __ARMEB__
+	rev	$h0,$h0
+	rev	$h1,$h1
+	rev	$h2,$h2
+	rev	$h3,$h3
+# endif
+	str	$h0,[$mac,#0]
+	str	$h1,[$mac,#4]
+	str	$h2,[$mac,#8]
+	str	$h3,[$mac,#12]
+#else
+	strb	$h0,[$mac,#0]
+	mov	$h0,$h0,lsr#8
+	strb	$h1,[$mac,#4]
+	mov	$h1,$h1,lsr#8
+	strb	$h2,[$mac,#8]
+	mov	$h2,$h2,lsr#8
+	strb	$h3,[$mac,#12]
+	mov	$h3,$h3,lsr#8
+
+	strb	$h0,[$mac,#1]
+	mov	$h0,$h0,lsr#8
+	strb	$h1,[$mac,#5]
+	mov	$h1,$h1,lsr#8
+	strb	$h2,[$mac,#9]
+	mov	$h2,$h2,lsr#8
+	strb	$h3,[$mac,#13]
+	mov	$h3,$h3,lsr#8
+
+	strb	$h0,[$mac,#2]
+	mov	$h0,$h0,lsr#8
+	strb	$h1,[$mac,#6]
+	mov	$h1,$h1,lsr#8
+	strb	$h2,[$mac,#10]
+	mov	$h2,$h2,lsr#8
+	strb	$h3,[$mac,#14]
+	mov	$h3,$h3,lsr#8
+
+	strb	$h0,[$mac,#3]
+	strb	$h1,[$mac,#7]
+	strb	$h2,[$mac,#11]
+	strb	$h3,[$mac,#15]
+#endif
+	ldmia	sp!,{r4-r11}
+#if	__ARM_ARCH__>=5
+	ret				@ bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_emit,.-poly1305_emit
+___
+{
+my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("d$_",(0..9));
+my ($D0,$D1,$D2,$D3,$D4, $H0,$H1,$H2,$H3,$H4) = map("q$_",(5..14));
+my ($T0,$T1,$MASK) = map("q$_",(15,4,0));
+
+my ($in2,$zeros,$tbl0,$tbl1) = map("r$_",(4..7));
+
+$code.=<<___;
+#if	__ARM_MAX_ARCH__>=7
+.fpu	neon
+
+.type	poly1305_init_neon,%function
+.align	5
+poly1305_init_neon:
+.Lpoly1305_init_neon:
+	ldr	r3,[$ctx,#48]		@ first table element
+	cmp	r3,#-1			@ is value impossible?
+	bne	.Lno_init_neon
+
+	ldr	r4,[$ctx,#20]		@ load key base 2^32
+	ldr	r5,[$ctx,#24]
+	ldr	r6,[$ctx,#28]
+	ldr	r7,[$ctx,#32]
+
+	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
+	mov	r3,r4,lsr#26
+	mov	r4,r5,lsr#20
+	orr	r3,r3,r5,lsl#6
+	mov	r5,r6,lsr#14
+	orr	r4,r4,r6,lsl#12
+	mov	r6,r7,lsr#8
+	orr	r5,r5,r7,lsl#18
+	and	r3,r3,#0x03ffffff
+	and	r4,r4,#0x03ffffff
+	and	r5,r5,#0x03ffffff
+
+	vdup.32	$R0,r2			@ r^1 in both lanes
+	add	r2,r3,r3,lsl#2		@ *5
+	vdup.32	$R1,r3
+	add	r3,r4,r4,lsl#2
+	vdup.32	$S1,r2
+	vdup.32	$R2,r4
+	add	r4,r5,r5,lsl#2
+	vdup.32	$S2,r3
+	vdup.32	$R3,r5
+	add	r5,r6,r6,lsl#2
+	vdup.32	$S3,r4
+	vdup.32	$R4,r6
+	vdup.32	$S4,r5
+
+	mov	$zeros,#2		@ counter
+
+.Lsquare_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
+	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
+	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
+	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
+
+	vmull.u32	$D0,$R0,${R0}[1]
+	vmull.u32	$D1,$R1,${R0}[1]
+	vmull.u32	$D2,$R2,${R0}[1]
+	vmull.u32	$D3,$R3,${R0}[1]
+	vmull.u32	$D4,$R4,${R0}[1]
+
+	vmlal.u32	$D0,$R4,${S1}[1]
+	vmlal.u32	$D1,$R0,${R1}[1]
+	vmlal.u32	$D2,$R1,${R1}[1]
+	vmlal.u32	$D3,$R2,${R1}[1]
+	vmlal.u32	$D4,$R3,${R1}[1]
+
+	vmlal.u32	$D0,$R3,${S2}[1]
+	vmlal.u32	$D1,$R4,${S2}[1]
+	vmlal.u32	$D3,$R1,${R2}[1]
+	vmlal.u32	$D2,$R0,${R2}[1]
+	vmlal.u32	$D4,$R2,${R2}[1]
+
+	vmlal.u32	$D0,$R2,${S3}[1]
+	vmlal.u32	$D3,$R0,${R3}[1]
+	vmlal.u32	$D1,$R3,${S3}[1]
+	vmlal.u32	$D2,$R4,${S3}[1]
+	vmlal.u32	$D4,$R1,${R3}[1]
+
+	vmlal.u32	$D3,$R4,${S4}[1]
+	vmlal.u32	$D0,$R1,${S4}[1]
+	vmlal.u32	$D1,$R2,${S4}[1]
+	vmlal.u32	$D2,$R3,${S4}[1]
+	vmlal.u32	$D4,$R0,${R4}[1]
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	@ and P. Schwabe
+	@
+	@ H0>>+H1>>+H2>>+H3>>+H4
+	@ H3>>+H4>>*5+H0>>+H1
+	@
+	@ Trivia.
+	@
+	@ Result of multiplication of n-bit number by m-bit number is
+	@ n+m bits wide. However! Even though 2^n is a n+1-bit number,
+	@ m-bit number multiplied by 2^n is still n+m bits wide.
+	@
+	@ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
+	@ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
+	@ one is n+1 bits wide.
+	@
+	@ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
+	@ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
+	@ can be 27. However! In cases when their width exceeds 26 bits
+	@ they are limited by 2^26+2^6. This in turn means that *sum*
+	@ of the products with these values can still be viewed as sum
+	@ of 52-bit numbers as long as the amount of addends is not a
+	@ power of 2. For example,
+	@
+	@ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
+	@
+	@ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
+	@ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
+	@ 8 * (2^52) or 2^55. However, the value is then multiplied by
+	@ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
+	@ which is less than 32 * (2^52) or 2^57. And when processing
+	@ data we are looking at triple as many addends...
+	@
+	@ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
+	@ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
+	@ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
+	@ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
+	@ instruction accepts 2x32-bit input and writes 2x64-bit result.
+	@ This means that result of reduction have to be compressed upon
+	@ loop wrap-around. This can be done in the process of reduction
+	@ to minimize amount of instructions [as well as amount of
+	@ 128-bit instructions, which benefits low-end processors], but
+	@ one has to watch for H2 (which is narrower than H0) and 5*H4
+	@ not being wider than 58 bits, so that result of right shift
+	@ by 26 bits fits in 32 bits. This is also useful on x86,
+	@ because it allows to use paddd in place for paddq, which
+	@ benefits Atom, where paddq is ridiculously slow.
+
+	vshr.u64	$T0,$D3,#26
+	vmovn.i64	$D3#lo,$D3
+	 vshr.u64	$T1,$D0,#26
+	 vmovn.i64	$D0#lo,$D0
+	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
+	vbic.i32	$D3#lo,#0xfc000000	@ &=0x03ffffff
+	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
+	 vbic.i32	$D0#lo,#0xfc000000
+
+	vshrn.u64	$T0#lo,$D4,#26
+	vmovn.i64	$D4#lo,$D4
+	 vshr.u64	$T1,$D1,#26
+	 vmovn.i64	$D1#lo,$D1
+	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
+	vbic.i32	$D4#lo,#0xfc000000
+	 vbic.i32	$D1#lo,#0xfc000000
+
+	vadd.i32	$D0#lo,$D0#lo,$T0#lo
+	vshl.u32	$T0#lo,$T0#lo,#2
+	 vshrn.u64	$T1#lo,$D2,#26
+	 vmovn.i64	$D2#lo,$D2
+	vadd.i32	$D0#lo,$D0#lo,$T0#lo	@ h4 -> h0
+	 vadd.i32	$D3#lo,$D3#lo,$T1#lo	@ h2 -> h3
+	 vbic.i32	$D2#lo,#0xfc000000
+
+	vshr.u32	$T0#lo,$D0#lo,#26
+	vbic.i32	$D0#lo,#0xfc000000
+	 vshr.u32	$T1#lo,$D3#lo,#26
+	 vbic.i32	$D3#lo,#0xfc000000
+	vadd.i32	$D1#lo,$D1#lo,$T0#lo	@ h0 -> h1
+	 vadd.i32	$D4#lo,$D4#lo,$T1#lo	@ h3 -> h4
+
+	subs		$zeros,$zeros,#1
+	beq		.Lsquare_break_neon
+
+	add		$tbl0,$ctx,#(48+0*9*4)
+	add		$tbl1,$ctx,#(48+1*9*4)
+
+	vtrn.32		$R0,$D0#lo		@ r^2:r^1
+	vtrn.32		$R2,$D2#lo
+	vtrn.32		$R3,$D3#lo
+	vtrn.32		$R1,$D1#lo
+	vtrn.32		$R4,$D4#lo
+
+	vshl.u32	$S2,$R2,#2		@ *5
+	vshl.u32	$S3,$R3,#2
+	vshl.u32	$S1,$R1,#2
+	vshl.u32	$S4,$R4,#2
+	vadd.i32	$S2,$S2,$R2
+	vadd.i32	$S1,$S1,$R1
+	vadd.i32	$S3,$S3,$R3
+	vadd.i32	$S4,$S4,$R4
+
+	vst4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
+	vst4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
+	vst4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vst4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vst1.32		{${S4}[0]},[$tbl0,:32]
+	vst1.32		{${S4}[1]},[$tbl1,:32]
+
+	b		.Lsquare_neon
+
+.align	4
+.Lsquare_break_neon:
+	add		$tbl0,$ctx,#(48+2*4*9)
+	add		$tbl1,$ctx,#(48+3*4*9)
+
+	vmov		$R0,$D0#lo		@ r^4:r^3
+	vshl.u32	$S1,$D1#lo,#2		@ *5
+	vmov		$R1,$D1#lo
+	vshl.u32	$S2,$D2#lo,#2
+	vmov		$R2,$D2#lo
+	vshl.u32	$S3,$D3#lo,#2
+	vmov		$R3,$D3#lo
+	vshl.u32	$S4,$D4#lo,#2
+	vmov		$R4,$D4#lo
+	vadd.i32	$S1,$S1,$D1#lo
+	vadd.i32	$S2,$S2,$D2#lo
+	vadd.i32	$S3,$S3,$D3#lo
+	vadd.i32	$S4,$S4,$D4#lo
+
+	vst4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
+	vst4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
+	vst4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vst4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vst1.32		{${S4}[0]},[$tbl0]
+	vst1.32		{${S4}[1]},[$tbl1]
+
+.Lno_init_neon:
+	ret				@ bx	lr
+.size	poly1305_init_neon,.-poly1305_init_neon
+
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+	ldr	ip,[$ctx,#36]		@ is_base2_26
+
+	cmp	$len,#64
+	blo	.Lpoly1305_blocks
+
+	stmdb	sp!,{r4-r7}
+	vstmdb	sp!,{d8-d15}		@ ABI specification says so
+
+	tst	ip,ip			@ is_base2_26?
+	bne	.Lbase2_26_neon
+
+	stmdb	sp!,{r1-r3,lr}
+	bl	.Lpoly1305_init_neon
+
+	ldr	r4,[$ctx,#0]		@ load hash value base 2^32
+	ldr	r5,[$ctx,#4]
+	ldr	r6,[$ctx,#8]
+	ldr	r7,[$ctx,#12]
+	ldr	ip,[$ctx,#16]
+
+	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
+	mov	r3,r4,lsr#26
+	 veor	$D0#lo,$D0#lo,$D0#lo
+	mov	r4,r5,lsr#20
+	orr	r3,r3,r5,lsl#6
+	 veor	$D1#lo,$D1#lo,$D1#lo
+	mov	r5,r6,lsr#14
+	orr	r4,r4,r6,lsl#12
+	 veor	$D2#lo,$D2#lo,$D2#lo
+	mov	r6,r7,lsr#8
+	orr	r5,r5,r7,lsl#18
+	 veor	$D3#lo,$D3#lo,$D3#lo
+	and	r3,r3,#0x03ffffff
+	orr	r6,r6,ip,lsl#24
+	 veor	$D4#lo,$D4#lo,$D4#lo
+	and	r4,r4,#0x03ffffff
+	mov	r1,#1
+	and	r5,r5,#0x03ffffff
+	str	r1,[$ctx,#36]		@ set is_base2_26
+
+	vmov.32	$D0#lo[0],r2
+	vmov.32	$D1#lo[0],r3
+	vmov.32	$D2#lo[0],r4
+	vmov.32	$D3#lo[0],r5
+	vmov.32	$D4#lo[0],r6
+	adr	$zeros,.Lzeros
+
+	ldmia	sp!,{r1-r3,lr}
+	b	.Lhash_loaded
+
+.align	4
+.Lbase2_26_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ load hash value
+
+	veor		$D0#lo,$D0#lo,$D0#lo
+	veor		$D1#lo,$D1#lo,$D1#lo
+	veor		$D2#lo,$D2#lo,$D2#lo
+	veor		$D3#lo,$D3#lo,$D3#lo
+	veor		$D4#lo,$D4#lo,$D4#lo
+	vld4.32		{$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
+	adr		$zeros,.Lzeros
+	vld1.32		{$D4#lo[0]},[$ctx]
+	sub		$ctx,$ctx,#16		@ rewind
+
+.Lhash_loaded:
+	add		$in2,$inp,#32
+	mov		$padbit,$padbit,lsl#24
+	tst		$len,#31
+	beq		.Leven
+
+	vld4.32		{$H0#lo[0],$H1#lo[0],$H2#lo[0],$H3#lo[0]},[$inp]!
+	vmov.32		$H4#lo[0],$padbit
+	sub		$len,$len,#16
+	add		$in2,$inp,#32
+
+# ifdef	__ARMEB__
+	vrev32.8	$H0,$H0
+	vrev32.8	$H3,$H3
+	vrev32.8	$H1,$H1
+	vrev32.8	$H2,$H2
+# endif
+	vsri.u32	$H4#lo,$H3#lo,#8	@ base 2^32 -> base 2^26
+	vshl.u32	$H3#lo,$H3#lo,#18
+
+	vsri.u32	$H3#lo,$H2#lo,#14
+	vshl.u32	$H2#lo,$H2#lo,#12
+	vadd.i32	$H4#hi,$H4#lo,$D4#lo	@ add hash value and move to #hi
+
+	vbic.i32	$H3#lo,#0xfc000000
+	vsri.u32	$H2#lo,$H1#lo,#20
+	vshl.u32	$H1#lo,$H1#lo,#6
+
+	vbic.i32	$H2#lo,#0xfc000000
+	vsri.u32	$H1#lo,$H0#lo,#26
+	vadd.i32	$H3#hi,$H3#lo,$D3#lo
+
+	vbic.i32	$H0#lo,#0xfc000000
+	vbic.i32	$H1#lo,#0xfc000000
+	vadd.i32	$H2#hi,$H2#lo,$D2#lo
+
+	vadd.i32	$H0#hi,$H0#lo,$D0#lo
+	vadd.i32	$H1#hi,$H1#lo,$D1#lo
+
+	mov		$tbl1,$zeros
+	add		$tbl0,$ctx,#48
+
+	cmp		$len,$len
+	b		.Long_tail
+
+.align	4
+.Leven:
+	subs		$len,$len,#64
+	it		lo
+	movlo		$in2,$zeros
+
+	vmov.i32	$H4,#1<<24		@ padbit, yes, always
+	vld4.32		{$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp]	@ inp[0:1]
+	add		$inp,$inp,#64
+	vld4.32		{$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2]	@ inp[2:3] (or 0)
+	add		$in2,$in2,#64
+	itt		hi
+	addhi		$tbl1,$ctx,#(48+1*9*4)
+	addhi		$tbl0,$ctx,#(48+3*9*4)
+
+# ifdef	__ARMEB__
+	vrev32.8	$H0,$H0
+	vrev32.8	$H3,$H3
+	vrev32.8	$H1,$H1
+	vrev32.8	$H2,$H2
+# endif
+	vsri.u32	$H4,$H3,#8		@ base 2^32 -> base 2^26
+	vshl.u32	$H3,$H3,#18
+
+	vsri.u32	$H3,$H2,#14
+	vshl.u32	$H2,$H2,#12
+
+	vbic.i32	$H3,#0xfc000000
+	vsri.u32	$H2,$H1,#20
+	vshl.u32	$H1,$H1,#6
+
+	vbic.i32	$H2,#0xfc000000
+	vsri.u32	$H1,$H0,#26
+
+	vbic.i32	$H0,#0xfc000000
+	vbic.i32	$H1,#0xfc000000
+
+	bls		.Lskip_loop
+
+	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^2
+	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^4
+	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	b		.Loop_neon
+
+.align	5
+.Loop_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+	@   \___________________/
+	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+	@   \___________________/ \____________________/
+	@
+	@ Note that we start with inp[2:3]*r^2. This is because it
+	@ doesn't depend on reduction in previous iteration.
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
+	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
+	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
+	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
+	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ inp[2:3]*r^2
+
+	vadd.i32	$H2#lo,$H2#lo,$D2#lo	@ accumulate inp[0:1]
+	vmull.u32	$D2,$H2#hi,${R0}[1]
+	vadd.i32	$H0#lo,$H0#lo,$D0#lo
+	vmull.u32	$D0,$H0#hi,${R0}[1]
+	vadd.i32	$H3#lo,$H3#lo,$D3#lo
+	vmull.u32	$D3,$H3#hi,${R0}[1]
+	vmlal.u32	$D2,$H1#hi,${R1}[1]
+	vadd.i32	$H1#lo,$H1#lo,$D1#lo
+	vmull.u32	$D1,$H1#hi,${R0}[1]
+
+	vadd.i32	$H4#lo,$H4#lo,$D4#lo
+	vmull.u32	$D4,$H4#hi,${R0}[1]
+	subs		$len,$len,#64
+	vmlal.u32	$D0,$H4#hi,${S1}[1]
+	it		lo
+	movlo		$in2,$zeros
+	vmlal.u32	$D3,$H2#hi,${R1}[1]
+	vld1.32		${S4}[1],[$tbl1,:32]
+	vmlal.u32	$D1,$H0#hi,${R1}[1]
+	vmlal.u32	$D4,$H3#hi,${R1}[1]
+
+	vmlal.u32	$D0,$H3#hi,${S2}[1]
+	vmlal.u32	$D3,$H1#hi,${R2}[1]
+	vmlal.u32	$D4,$H2#hi,${R2}[1]
+	vmlal.u32	$D1,$H4#hi,${S2}[1]
+	vmlal.u32	$D2,$H0#hi,${R2}[1]
+
+	vmlal.u32	$D3,$H0#hi,${R3}[1]
+	vmlal.u32	$D0,$H2#hi,${S3}[1]
+	vmlal.u32	$D4,$H1#hi,${R3}[1]
+	vmlal.u32	$D1,$H3#hi,${S3}[1]
+	vmlal.u32	$D2,$H4#hi,${S3}[1]
+
+	vmlal.u32	$D3,$H4#hi,${S4}[1]
+	vmlal.u32	$D0,$H1#hi,${S4}[1]
+	vmlal.u32	$D4,$H0#hi,${R4}[1]
+	vmlal.u32	$D1,$H2#hi,${S4}[1]
+	vmlal.u32	$D2,$H3#hi,${S4}[1]
+
+	vld4.32		{$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2]	@ inp[2:3] (or 0)
+	add		$in2,$in2,#64
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ (hash+inp[0:1])*r^4 and accumulate
+
+	vmlal.u32	$D3,$H3#lo,${R0}[0]
+	vmlal.u32	$D0,$H0#lo,${R0}[0]
+	vmlal.u32	$D4,$H4#lo,${R0}[0]
+	vmlal.u32	$D1,$H1#lo,${R0}[0]
+	vmlal.u32	$D2,$H2#lo,${R0}[0]
+	vld1.32		${S4}[0],[$tbl0,:32]
+
+	vmlal.u32	$D3,$H2#lo,${R1}[0]
+	vmlal.u32	$D0,$H4#lo,${S1}[0]
+	vmlal.u32	$D4,$H3#lo,${R1}[0]
+	vmlal.u32	$D1,$H0#lo,${R1}[0]
+	vmlal.u32	$D2,$H1#lo,${R1}[0]
+
+	vmlal.u32	$D3,$H1#lo,${R2}[0]
+	vmlal.u32	$D0,$H3#lo,${S2}[0]
+	vmlal.u32	$D4,$H2#lo,${R2}[0]
+	vmlal.u32	$D1,$H4#lo,${S2}[0]
+	vmlal.u32	$D2,$H0#lo,${R2}[0]
+
+	vmlal.u32	$D3,$H0#lo,${R3}[0]
+	vmlal.u32	$D0,$H2#lo,${S3}[0]
+	vmlal.u32	$D4,$H1#lo,${R3}[0]
+	vmlal.u32	$D1,$H3#lo,${S3}[0]
+	vmlal.u32	$D3,$H4#lo,${S4}[0]
+
+	vmlal.u32	$D2,$H4#lo,${S3}[0]
+	vmlal.u32	$D0,$H1#lo,${S4}[0]
+	vmlal.u32	$D4,$H0#lo,${R4}[0]
+	vmov.i32	$H4,#1<<24		@ padbit, yes, always
+	vmlal.u32	$D1,$H2#lo,${S4}[0]
+	vmlal.u32	$D2,$H3#lo,${S4}[0]
+
+	vld4.32		{$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp]	@ inp[0:1]
+	add		$inp,$inp,#64
+# ifdef	__ARMEB__
+	vrev32.8	$H0,$H0
+	vrev32.8	$H1,$H1
+	vrev32.8	$H2,$H2
+	vrev32.8	$H3,$H3
+# endif
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction interleaved with base 2^32 -> base 2^26 of
+	@ inp[0:3] previously loaded to $H0-$H3 and smashed to $H0-$H4.
+
+	vshr.u64	$T0,$D3,#26
+	vmovn.i64	$D3#lo,$D3
+	 vshr.u64	$T1,$D0,#26
+	 vmovn.i64	$D0#lo,$D0
+	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
+	vbic.i32	$D3#lo,#0xfc000000
+	  vsri.u32	$H4,$H3,#8		@ base 2^32 -> base 2^26
+	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
+	  vshl.u32	$H3,$H3,#18
+	 vbic.i32	$D0#lo,#0xfc000000
+
+	vshrn.u64	$T0#lo,$D4,#26
+	vmovn.i64	$D4#lo,$D4
+	 vshr.u64	$T1,$D1,#26
+	 vmovn.i64	$D1#lo,$D1
+	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
+	  vsri.u32	$H3,$H2,#14
+	vbic.i32	$D4#lo,#0xfc000000
+	  vshl.u32	$H2,$H2,#12
+	 vbic.i32	$D1#lo,#0xfc000000
+
+	vadd.i32	$D0#lo,$D0#lo,$T0#lo
+	vshl.u32	$T0#lo,$T0#lo,#2
+	  vbic.i32	$H3,#0xfc000000
+	 vshrn.u64	$T1#lo,$D2,#26
+	 vmovn.i64	$D2#lo,$D2
+	vaddl.u32	$D0,$D0#lo,$T0#lo	@ h4 -> h0 [widen for a sec]
+	  vsri.u32	$H2,$H1,#20
+	 vadd.i32	$D3#lo,$D3#lo,$T1#lo	@ h2 -> h3
+	  vshl.u32	$H1,$H1,#6
+	 vbic.i32	$D2#lo,#0xfc000000
+	  vbic.i32	$H2,#0xfc000000
+
+	vshrn.u64	$T0#lo,$D0,#26		@ re-narrow
+	vmovn.i64	$D0#lo,$D0
+	  vsri.u32	$H1,$H0,#26
+	  vbic.i32	$H0,#0xfc000000
+	 vshr.u32	$T1#lo,$D3#lo,#26
+	 vbic.i32	$D3#lo,#0xfc000000
+	vbic.i32	$D0#lo,#0xfc000000
+	vadd.i32	$D1#lo,$D1#lo,$T0#lo	@ h0 -> h1
+	 vadd.i32	$D4#lo,$D4#lo,$T1#lo	@ h3 -> h4
+	  vbic.i32	$H1,#0xfc000000
+
+	bhi		.Loop_neon
+
+.Lskip_loop:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	add		$tbl1,$ctx,#(48+0*9*4)
+	add		$tbl0,$ctx,#(48+1*9*4)
+	adds		$len,$len,#32
+	it		ne
+	movne		$len,#0
+	bne		.Long_tail
+
+	vadd.i32	$H2#hi,$H2#lo,$D2#lo	@ add hash value and move to #hi
+	vadd.i32	$H0#hi,$H0#lo,$D0#lo
+	vadd.i32	$H3#hi,$H3#lo,$D3#lo
+	vadd.i32	$H1#hi,$H1#lo,$D1#lo
+	vadd.i32	$H4#hi,$H4#lo,$D4#lo
+
+.Long_tail:
+	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^1
+	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^2
+
+	vadd.i32	$H2#lo,$H2#lo,$D2#lo	@ can be redundant
+	vmull.u32	$D2,$H2#hi,$R0
+	vadd.i32	$H0#lo,$H0#lo,$D0#lo
+	vmull.u32	$D0,$H0#hi,$R0
+	vadd.i32	$H3#lo,$H3#lo,$D3#lo
+	vmull.u32	$D3,$H3#hi,$R0
+	vadd.i32	$H1#lo,$H1#lo,$D1#lo
+	vmull.u32	$D1,$H1#hi,$R0
+	vadd.i32	$H4#lo,$H4#lo,$D4#lo
+	vmull.u32	$D4,$H4#hi,$R0
+
+	vmlal.u32	$D0,$H4#hi,$S1
+	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vmlal.u32	$D3,$H2#hi,$R1
+	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vmlal.u32	$D1,$H0#hi,$R1
+	vmlal.u32	$D4,$H3#hi,$R1
+	vmlal.u32	$D2,$H1#hi,$R1
+
+	vmlal.u32	$D3,$H1#hi,$R2
+	vld1.32		${S4}[1],[$tbl1,:32]
+	vmlal.u32	$D0,$H3#hi,$S2
+	vld1.32		${S4}[0],[$tbl0,:32]
+	vmlal.u32	$D4,$H2#hi,$R2
+	vmlal.u32	$D1,$H4#hi,$S2
+	vmlal.u32	$D2,$H0#hi,$R2
+
+	vmlal.u32	$D3,$H0#hi,$R3
+	 it		ne
+	 addne		$tbl1,$ctx,#(48+2*9*4)
+	vmlal.u32	$D0,$H2#hi,$S3
+	 it		ne
+	 addne		$tbl0,$ctx,#(48+3*9*4)
+	vmlal.u32	$D4,$H1#hi,$R3
+	vmlal.u32	$D1,$H3#hi,$S3
+	vmlal.u32	$D2,$H4#hi,$S3
+
+	vmlal.u32	$D3,$H4#hi,$S4
+	 vorn		$MASK,$MASK,$MASK	@ all-ones, can be redundant
+	vmlal.u32	$D0,$H1#hi,$S4
+	 vshr.u64	$MASK,$MASK,#38
+	vmlal.u32	$D4,$H0#hi,$R4
+	vmlal.u32	$D1,$H2#hi,$S4
+	vmlal.u32	$D2,$H3#hi,$S4
+
+	beq		.Lshort_tail
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^3
+	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^4
+
+	vmlal.u32	$D2,$H2#lo,$R0
+	vmlal.u32	$D0,$H0#lo,$R0
+	vmlal.u32	$D3,$H3#lo,$R0
+	vmlal.u32	$D1,$H1#lo,$R0
+	vmlal.u32	$D4,$H4#lo,$R0
+
+	vmlal.u32	$D0,$H4#lo,$S1
+	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vmlal.u32	$D3,$H2#lo,$R1
+	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vmlal.u32	$D1,$H0#lo,$R1
+	vmlal.u32	$D4,$H3#lo,$R1
+	vmlal.u32	$D2,$H1#lo,$R1
+
+	vmlal.u32	$D3,$H1#lo,$R2
+	vld1.32		${S4}[1],[$tbl1,:32]
+	vmlal.u32	$D0,$H3#lo,$S2
+	vld1.32		${S4}[0],[$tbl0,:32]
+	vmlal.u32	$D4,$H2#lo,$R2
+	vmlal.u32	$D1,$H4#lo,$S2
+	vmlal.u32	$D2,$H0#lo,$R2
+
+	vmlal.u32	$D3,$H0#lo,$R3
+	vmlal.u32	$D0,$H2#lo,$S3
+	vmlal.u32	$D4,$H1#lo,$R3
+	vmlal.u32	$D1,$H3#lo,$S3
+	vmlal.u32	$D2,$H4#lo,$S3
+
+	vmlal.u32	$D3,$H4#lo,$S4
+	 vorn		$MASK,$MASK,$MASK	@ all-ones
+	vmlal.u32	$D0,$H1#lo,$S4
+	 vshr.u64	$MASK,$MASK,#38
+	vmlal.u32	$D4,$H0#lo,$R4
+	vmlal.u32	$D1,$H2#lo,$S4
+	vmlal.u32	$D2,$H3#lo,$S4
+
+.Lshort_tail:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ horizontal addition
+
+	vadd.i64	$D3#lo,$D3#lo,$D3#hi
+	vadd.i64	$D0#lo,$D0#lo,$D0#hi
+	vadd.i64	$D4#lo,$D4#lo,$D4#hi
+	vadd.i64	$D1#lo,$D1#lo,$D1#hi
+	vadd.i64	$D2#lo,$D2#lo,$D2#hi
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction, but without narrowing
+
+	vshr.u64	$T0,$D3,#26
+	vand.i64	$D3,$D3,$MASK
+	 vshr.u64	$T1,$D0,#26
+	 vand.i64	$D0,$D0,$MASK
+	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
+	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
+
+	vshr.u64	$T0,$D4,#26
+	vand.i64	$D4,$D4,$MASK
+	 vshr.u64	$T1,$D1,#26
+	 vand.i64	$D1,$D1,$MASK
+	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
+
+	vadd.i64	$D0,$D0,$T0
+	vshl.u64	$T0,$T0,#2
+	 vshr.u64	$T1,$D2,#26
+	 vand.i64	$D2,$D2,$MASK
+	vadd.i64	$D0,$D0,$T0		@ h4 -> h0
+	 vadd.i64	$D3,$D3,$T1		@ h2 -> h3
+
+	vshr.u64	$T0,$D0,#26
+	vand.i64	$D0,$D0,$MASK
+	 vshr.u64	$T1,$D3,#26
+	 vand.i64	$D3,$D3,$MASK
+	vadd.i64	$D1,$D1,$T0		@ h0 -> h1
+	 vadd.i64	$D4,$D4,$T1		@ h3 -> h4
+
+	cmp		$len,#0
+	bne		.Leven
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ store hash value
+
+	vst4.32		{$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
+	vst1.32		{$D4#lo[0]},[$ctx]
+
+	vldmia	sp!,{d8-d15}			@ epilogue
+	ldmia	sp!,{r4-r7}
+	ret					@ bx	lr
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+#ifndef	__KERNEL__
+.LOPENSSL_armcap:
+# ifdef	_WIN32
+.word	OPENSSL_armcap_P
+# else
+.word	OPENSSL_armcap_P-.Lpoly1305_init
+# endif
+.comm	OPENSSL_armcap_P,4,4
+.hidden	OPENSSL_armcap_P
+#endif
+#endif
+___
+}	}
+$code.=<<___;
+.asciz	"Poly1305 for ARMv4/NEON, CRYPTOGAMS by \@dot-asm"
+.align	2
+___
+
+foreach (split("\n",$code)) {
+	s/\`([^\`]*)\`/eval $1/geo;
+
+	s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo	or
+	s/\bret\b/bx	lr/go						or
+	s/\bbx\s+lr\b/.word\t0xe12fff1e/go;	# make it possible to compile with -march=armv4
+
+	print $_,"\n";
+}
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/poly1305-core.S_shipped b/arch/arm/crypto/poly1305-core.S_shipped
new file mode 100644
index 000000000000..37b71d990293
--- /dev/null
+++ b/arch/arm/crypto/poly1305-core.S_shipped
@@ -0,0 +1,1158 @@
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
+# define poly1305_init   poly1305_init_arm
+# define poly1305_blocks poly1305_blocks_arm
+# define poly1305_emit   poly1305_emit_arm
+.globl	poly1305_blocks_neon
+#endif
+
+#if defined(__thumb2__)
+.syntax	unified
+.thumb
+#else
+.code	32
+#endif
+
+.text
+
+.globl	poly1305_emit
+.globl	poly1305_blocks
+.globl	poly1305_init
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+.Lpoly1305_init:
+	stmdb	sp!,{r4-r11}
+
+	eor	r3,r3,r3
+	cmp	r1,#0
+	str	r3,[r0,#0]		@ zero hash value
+	str	r3,[r0,#4]
+	str	r3,[r0,#8]
+	str	r3,[r0,#12]
+	str	r3,[r0,#16]
+	str	r3,[r0,#36]		@ clear is_base2_26
+	add	r0,r0,#20
+
+#ifdef	__thumb2__
+	it	eq
+#endif
+	moveq	r0,#0
+	beq	.Lno_key
+
+#if	__ARM_MAX_ARCH__>=7
+	mov	r3,#-1
+	str	r3,[r0,#28]		@ impossible key power value
+# ifndef __KERNEL__
+	adr	r11,.Lpoly1305_init
+	ldr	r12,.LOPENSSL_armcap
+# endif
+#endif
+	ldrb	r4,[r1,#0]
+	mov	r10,#0x0fffffff
+	ldrb	r5,[r1,#1]
+	and	r3,r10,#-4		@ 0x0ffffffc
+	ldrb	r6,[r1,#2]
+	ldrb	r7,[r1,#3]
+	orr	r4,r4,r5,lsl#8
+	ldrb	r5,[r1,#4]
+	orr	r4,r4,r6,lsl#16
+	ldrb	r6,[r1,#5]
+	orr	r4,r4,r7,lsl#24
+	ldrb	r7,[r1,#6]
+	and	r4,r4,r10
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+# if !defined(_WIN32)
+	ldr	r12,[r11,r12]		@ OPENSSL_armcap_P
+# endif
+# if defined(__APPLE__) || defined(_WIN32)
+	ldr	r12,[r12]
+# endif
+#endif
+	ldrb	r8,[r1,#7]
+	orr	r5,r5,r6,lsl#8
+	ldrb	r6,[r1,#8]
+	orr	r5,r5,r7,lsl#16
+	ldrb	r7,[r1,#9]
+	orr	r5,r5,r8,lsl#24
+	ldrb	r8,[r1,#10]
+	and	r5,r5,r3
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	tst	r12,#ARMV7_NEON		@ check for NEON
+# ifdef	__thumb2__
+	adr	r9,.Lpoly1305_blocks_neon
+	adr	r11,.Lpoly1305_blocks
+	it	ne
+	movne	r11,r9
+	adr	r12,.Lpoly1305_emit
+	orr	r11,r11,#1		@ thumb-ify addresses
+	orr	r12,r12,#1
+# else
+	add	r12,r11,#(.Lpoly1305_emit-.Lpoly1305_init)
+	ite	eq
+	addeq	r11,r11,#(.Lpoly1305_blocks-.Lpoly1305_init)
+	addne	r11,r11,#(.Lpoly1305_blocks_neon-.Lpoly1305_init)
+# endif
+#endif
+	ldrb	r9,[r1,#11]
+	orr	r6,r6,r7,lsl#8
+	ldrb	r7,[r1,#12]
+	orr	r6,r6,r8,lsl#16
+	ldrb	r8,[r1,#13]
+	orr	r6,r6,r9,lsl#24
+	ldrb	r9,[r1,#14]
+	and	r6,r6,r3
+
+	ldrb	r10,[r1,#15]
+	orr	r7,r7,r8,lsl#8
+	str	r4,[r0,#0]
+	orr	r7,r7,r9,lsl#16
+	str	r5,[r0,#4]
+	orr	r7,r7,r10,lsl#24
+	str	r6,[r0,#8]
+	and	r7,r7,r3
+	str	r7,[r0,#12]
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	stmia	r2,{r11,r12}		@ fill functions table
+	mov	r0,#1
+#else
+	mov	r0,#0
+#endif
+.Lno_key:
+	ldmia	sp!,{r4-r11}
+#if	__ARM_ARCH__>=5
+	bx	lr				@ bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_init,.-poly1305_init
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+.Lpoly1305_blocks:
+	stmdb	sp!,{r3-r11,lr}
+
+	ands	r2,r2,#-16
+	beq	.Lno_data
+
+	add	r2,r2,r1		@ end pointer
+	sub	sp,sp,#32
+
+#if __ARM_ARCH__<7
+	ldmia	r0,{r4-r12}		@ load context
+	add	r0,r0,#20
+	str	r2,[sp,#16]		@ offload stuff
+	str	r0,[sp,#12]
+#else
+	ldr	lr,[r0,#36]		@ is_base2_26
+	ldmia	r0!,{r4-r8}		@ load hash value
+	str	r2,[sp,#16]		@ offload stuff
+	str	r0,[sp,#12]
+
+	adds	r9,r4,r5,lsl#26	@ base 2^26 -> base 2^32
+	mov	r10,r5,lsr#6
+	adcs	r10,r10,r6,lsl#20
+	mov	r11,r6,lsr#12
+	adcs	r11,r11,r7,lsl#14
+	mov	r12,r7,lsr#18
+	adcs	r12,r12,r8,lsl#8
+	mov	r2,#0
+	teq	lr,#0
+	str	r2,[r0,#16]		@ clear is_base2_26
+	adc	r2,r2,r8,lsr#24
+
+	itttt	ne
+	movne	r4,r9			@ choose between radixes
+	movne	r5,r10
+	movne	r6,r11
+	movne	r7,r12
+	ldmia	r0,{r9-r12}		@ load key
+	it	ne
+	movne	r8,r2
+#endif
+
+	mov	lr,r1
+	cmp	r3,#0
+	str	r10,[sp,#20]
+	str	r11,[sp,#24]
+	str	r12,[sp,#28]
+	b	.Loop
+
+.align	4
+.Loop:
+#if __ARM_ARCH__<7
+	ldrb	r0,[lr],#16		@ load input
+# ifdef	__thumb2__
+	it	hi
+# endif
+	addhi	r8,r8,#1		@ 1<<128
+	ldrb	r1,[lr,#-15]
+	ldrb	r2,[lr,#-14]
+	ldrb	r3,[lr,#-13]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-12]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-11]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-10]
+	adds	r4,r4,r3		@ accumulate input
+
+	ldrb	r3,[lr,#-9]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-8]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-7]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-6]
+	adcs	r5,r5,r3
+
+	ldrb	r3,[lr,#-5]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-4]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-3]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-2]
+	adcs	r6,r6,r3
+
+	ldrb	r3,[lr,#-1]
+	orr	r1,r0,r1,lsl#8
+	str	lr,[sp,#8]		@ offload input pointer
+	orr	r2,r1,r2,lsl#16
+	add	r10,r10,r10,lsr#2
+	orr	r3,r2,r3,lsl#24
+#else
+	ldr	r0,[lr],#16		@ load input
+	it	hi
+	addhi	r8,r8,#1		@ padbit
+	ldr	r1,[lr,#-12]
+	ldr	r2,[lr,#-8]
+	ldr	r3,[lr,#-4]
+# ifdef	__ARMEB__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+# endif
+	adds	r4,r4,r0		@ accumulate input
+	str	lr,[sp,#8]		@ offload input pointer
+	adcs	r5,r5,r1
+	add	r10,r10,r10,lsr#2
+	adcs	r6,r6,r2
+#endif
+	add	r11,r11,r11,lsr#2
+	adcs	r7,r7,r3
+	add	r12,r12,r12,lsr#2
+
+	umull	r2,r3,r5,r9
+	 adc	r8,r8,#0
+	umull	r0,r1,r4,r9
+	umlal	r2,r3,r8,r10
+	umlal	r0,r1,r7,r10
+	ldr	r10,[sp,#20]		@ reload r10
+	umlal	r2,r3,r6,r12
+	umlal	r0,r1,r5,r12
+	umlal	r2,r3,r7,r11
+	umlal	r0,r1,r6,r11
+	umlal	r2,r3,r4,r10
+	str	r0,[sp,#0]		@ future r4
+	 mul	r0,r11,r8
+	ldr	r11,[sp,#24]		@ reload r11
+	adds	r2,r2,r1		@ d1+=d0>>32
+	 eor	r1,r1,r1
+	adc	lr,r3,#0		@ future r6
+	str	r2,[sp,#4]		@ future r5
+
+	mul	r2,r12,r8
+	eor	r3,r3,r3
+	umlal	r0,r1,r7,r12
+	ldr	r12,[sp,#28]		@ reload r12
+	umlal	r2,r3,r7,r9
+	umlal	r0,r1,r6,r9
+	umlal	r2,r3,r6,r10
+	umlal	r0,r1,r5,r10
+	umlal	r2,r3,r5,r11
+	umlal	r0,r1,r4,r11
+	umlal	r2,r3,r4,r12
+	ldr	r4,[sp,#0]
+	mul	r8,r9,r8
+	ldr	r5,[sp,#4]
+
+	adds	r6,lr,r0		@ d2+=d1>>32
+	ldr	lr,[sp,#8]		@ reload input pointer
+	adc	r1,r1,#0
+	adds	r7,r2,r1		@ d3+=d2>>32
+	ldr	r0,[sp,#16]		@ reload end pointer
+	adc	r3,r3,#0
+	add	r8,r8,r3		@ h4+=d3>>32
+
+	and	r1,r8,#-4
+	and	r8,r8,#3
+	add	r1,r1,r1,lsr#2		@ *=5
+	adds	r4,r4,r1
+	adcs	r5,r5,#0
+	adcs	r6,r6,#0
+	adcs	r7,r7,#0
+	adc	r8,r8,#0
+
+	cmp	r0,lr			@ done yet?
+	bhi	.Loop
+
+	ldr	r0,[sp,#12]
+	add	sp,sp,#32
+	stmdb	r0,{r4-r8}		@ store the result
+
+.Lno_data:
+#if	__ARM_ARCH__>=5
+	ldmia	sp!,{r3-r11,pc}
+#else
+	ldmia	sp!,{r3-r11,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_blocks,.-poly1305_blocks
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+.Lpoly1305_emit:
+	stmdb	sp!,{r4-r11}
+
+	ldmia	r0,{r3-r7}
+
+#if __ARM_ARCH__>=7
+	ldr	ip,[r0,#36]		@ is_base2_26
+
+	adds	r8,r3,r4,lsl#26	@ base 2^26 -> base 2^32
+	mov	r9,r4,lsr#6
+	adcs	r9,r9,r5,lsl#20
+	mov	r10,r5,lsr#12
+	adcs	r10,r10,r6,lsl#14
+	mov	r11,r6,lsr#18
+	adcs	r11,r11,r7,lsl#8
+	mov	r0,#0
+	adc	r0,r0,r7,lsr#24
+
+	tst	ip,ip
+	itttt	ne
+	movne	r3,r8
+	movne	r4,r9
+	movne	r5,r10
+	movne	r6,r11
+	it	ne
+	movne	r7,r0
+#endif
+
+	adds	r8,r3,#5		@ compare to modulus
+	adcs	r9,r4,#0
+	adcs	r10,r5,#0
+	adcs	r11,r6,#0
+	adc	r0,r7,#0
+	tst	r0,#4			@ did it carry/borrow?
+
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	r3,r8
+	ldr	r8,[r2,#0]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	r4,r9
+	ldr	r9,[r2,#4]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	r5,r10
+	ldr	r10,[r2,#8]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	r6,r11
+	ldr	r11,[r2,#12]
+
+	adds	r3,r3,r8
+	adcs	r4,r4,r9
+	adcs	r5,r5,r10
+	adc	r6,r6,r11
+
+#if __ARM_ARCH__>=7
+# ifdef __ARMEB__
+	rev	r3,r3
+	rev	r4,r4
+	rev	r5,r5
+	rev	r6,r6
+# endif
+	str	r3,[r1,#0]
+	str	r4,[r1,#4]
+	str	r5,[r1,#8]
+	str	r6,[r1,#12]
+#else
+	strb	r3,[r1,#0]
+	mov	r3,r3,lsr#8
+	strb	r4,[r1,#4]
+	mov	r4,r4,lsr#8
+	strb	r5,[r1,#8]
+	mov	r5,r5,lsr#8
+	strb	r6,[r1,#12]
+	mov	r6,r6,lsr#8
+
+	strb	r3,[r1,#1]
+	mov	r3,r3,lsr#8
+	strb	r4,[r1,#5]
+	mov	r4,r4,lsr#8
+	strb	r5,[r1,#9]
+	mov	r5,r5,lsr#8
+	strb	r6,[r1,#13]
+	mov	r6,r6,lsr#8
+
+	strb	r3,[r1,#2]
+	mov	r3,r3,lsr#8
+	strb	r4,[r1,#6]
+	mov	r4,r4,lsr#8
+	strb	r5,[r1,#10]
+	mov	r5,r5,lsr#8
+	strb	r6,[r1,#14]
+	mov	r6,r6,lsr#8
+
+	strb	r3,[r1,#3]
+	strb	r4,[r1,#7]
+	strb	r5,[r1,#11]
+	strb	r6,[r1,#15]
+#endif
+	ldmia	sp!,{r4-r11}
+#if	__ARM_ARCH__>=5
+	bx	lr				@ bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_emit,.-poly1305_emit
+#if	__ARM_MAX_ARCH__>=7
+.fpu	neon
+
+.type	poly1305_init_neon,%function
+.align	5
+poly1305_init_neon:
+.Lpoly1305_init_neon:
+	ldr	r3,[r0,#48]		@ first table element
+	cmp	r3,#-1			@ is value impossible?
+	bne	.Lno_init_neon
+
+	ldr	r4,[r0,#20]		@ load key base 2^32
+	ldr	r5,[r0,#24]
+	ldr	r6,[r0,#28]
+	ldr	r7,[r0,#32]
+
+	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
+	mov	r3,r4,lsr#26
+	mov	r4,r5,lsr#20
+	orr	r3,r3,r5,lsl#6
+	mov	r5,r6,lsr#14
+	orr	r4,r4,r6,lsl#12
+	mov	r6,r7,lsr#8
+	orr	r5,r5,r7,lsl#18
+	and	r3,r3,#0x03ffffff
+	and	r4,r4,#0x03ffffff
+	and	r5,r5,#0x03ffffff
+
+	vdup.32	d0,r2			@ r^1 in both lanes
+	add	r2,r3,r3,lsl#2		@ *5
+	vdup.32	d1,r3
+	add	r3,r4,r4,lsl#2
+	vdup.32	d2,r2
+	vdup.32	d3,r4
+	add	r4,r5,r5,lsl#2
+	vdup.32	d4,r3
+	vdup.32	d5,r5
+	add	r5,r6,r6,lsl#2
+	vdup.32	d6,r4
+	vdup.32	d7,r6
+	vdup.32	d8,r5
+
+	mov	r5,#2		@ counter
+
+.Lsquare_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
+	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
+	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
+	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
+
+	vmull.u32	q5,d0,d0[1]
+	vmull.u32	q6,d1,d0[1]
+	vmull.u32	q7,d3,d0[1]
+	vmull.u32	q8,d5,d0[1]
+	vmull.u32	q9,d7,d0[1]
+
+	vmlal.u32	q5,d7,d2[1]
+	vmlal.u32	q6,d0,d1[1]
+	vmlal.u32	q7,d1,d1[1]
+	vmlal.u32	q8,d3,d1[1]
+	vmlal.u32	q9,d5,d1[1]
+
+	vmlal.u32	q5,d5,d4[1]
+	vmlal.u32	q6,d7,d4[1]
+	vmlal.u32	q8,d1,d3[1]
+	vmlal.u32	q7,d0,d3[1]
+	vmlal.u32	q9,d3,d3[1]
+
+	vmlal.u32	q5,d3,d6[1]
+	vmlal.u32	q8,d0,d5[1]
+	vmlal.u32	q6,d5,d6[1]
+	vmlal.u32	q7,d7,d6[1]
+	vmlal.u32	q9,d1,d5[1]
+
+	vmlal.u32	q8,d7,d8[1]
+	vmlal.u32	q5,d1,d8[1]
+	vmlal.u32	q6,d3,d8[1]
+	vmlal.u32	q7,d5,d8[1]
+	vmlal.u32	q9,d0,d7[1]
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	@ and P. Schwabe
+	@
+	@ H0>>+H1>>+H2>>+H3>>+H4
+	@ H3>>+H4>>*5+H0>>+H1
+	@
+	@ Trivia.
+	@
+	@ Result of multiplication of n-bit number by m-bit number is
+	@ n+m bits wide. However! Even though 2^n is a n+1-bit number,
+	@ m-bit number multiplied by 2^n is still n+m bits wide.
+	@
+	@ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
+	@ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
+	@ one is n+1 bits wide.
+	@
+	@ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
+	@ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
+	@ can be 27. However! In cases when their width exceeds 26 bits
+	@ they are limited by 2^26+2^6. This in turn means that *sum*
+	@ of the products with these values can still be viewed as sum
+	@ of 52-bit numbers as long as the amount of addends is not a
+	@ power of 2. For example,
+	@
+	@ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
+	@
+	@ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
+	@ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
+	@ 8 * (2^52) or 2^55. However, the value is then multiplied by
+	@ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
+	@ which is less than 32 * (2^52) or 2^57. And when processing
+	@ data we are looking at triple as many addends...
+	@
+	@ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
+	@ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
+	@ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
+	@ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
+	@ instruction accepts 2x32-bit input and writes 2x64-bit result.
+	@ This means that result of reduction have to be compressed upon
+	@ loop wrap-around. This can be done in the process of reduction
+	@ to minimize amount of instructions [as well as amount of
+	@ 128-bit instructions, which benefits low-end processors], but
+	@ one has to watch for H2 (which is narrower than H0) and 5*H4
+	@ not being wider than 58 bits, so that result of right shift
+	@ by 26 bits fits in 32 bits. This is also useful on x86,
+	@ because it allows to use paddd in place for paddq, which
+	@ benefits Atom, where paddq is ridiculously slow.
+
+	vshr.u64	q15,q8,#26
+	vmovn.i64	d16,q8
+	 vshr.u64	q4,q5,#26
+	 vmovn.i64	d10,q5
+	vadd.i64	q9,q9,q15		@ h3 -> h4
+	vbic.i32	d16,#0xfc000000	@ &=0x03ffffff
+	 vadd.i64	q6,q6,q4		@ h0 -> h1
+	 vbic.i32	d10,#0xfc000000
+
+	vshrn.u64	d30,q9,#26
+	vmovn.i64	d18,q9
+	 vshr.u64	q4,q6,#26
+	 vmovn.i64	d12,q6
+	 vadd.i64	q7,q7,q4		@ h1 -> h2
+	vbic.i32	d18,#0xfc000000
+	 vbic.i32	d12,#0xfc000000
+
+	vadd.i32	d10,d10,d30
+	vshl.u32	d30,d30,#2
+	 vshrn.u64	d8,q7,#26
+	 vmovn.i64	d14,q7
+	vadd.i32	d10,d10,d30	@ h4 -> h0
+	 vadd.i32	d16,d16,d8	@ h2 -> h3
+	 vbic.i32	d14,#0xfc000000
+
+	vshr.u32	d30,d10,#26
+	vbic.i32	d10,#0xfc000000
+	 vshr.u32	d8,d16,#26
+	 vbic.i32	d16,#0xfc000000
+	vadd.i32	d12,d12,d30	@ h0 -> h1
+	 vadd.i32	d18,d18,d8	@ h3 -> h4
+
+	subs		r5,r5,#1
+	beq		.Lsquare_break_neon
+
+	add		r6,r0,#(48+0*9*4)
+	add		r7,r0,#(48+1*9*4)
+
+	vtrn.32		d0,d10		@ r^2:r^1
+	vtrn.32		d3,d14
+	vtrn.32		d5,d16
+	vtrn.32		d1,d12
+	vtrn.32		d7,d18
+
+	vshl.u32	d4,d3,#2		@ *5
+	vshl.u32	d6,d5,#2
+	vshl.u32	d2,d1,#2
+	vshl.u32	d8,d7,#2
+	vadd.i32	d4,d4,d3
+	vadd.i32	d2,d2,d1
+	vadd.i32	d6,d6,d5
+	vadd.i32	d8,d8,d7
+
+	vst4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!
+	vst4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!
+	vst4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
+	vst4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
+	vst1.32		{d8[0]},[r6,:32]
+	vst1.32		{d8[1]},[r7,:32]
+
+	b		.Lsquare_neon
+
+.align	4
+.Lsquare_break_neon:
+	add		r6,r0,#(48+2*4*9)
+	add		r7,r0,#(48+3*4*9)
+
+	vmov		d0,d10		@ r^4:r^3
+	vshl.u32	d2,d12,#2		@ *5
+	vmov		d1,d12
+	vshl.u32	d4,d14,#2
+	vmov		d3,d14
+	vshl.u32	d6,d16,#2
+	vmov		d5,d16
+	vshl.u32	d8,d18,#2
+	vmov		d7,d18
+	vadd.i32	d2,d2,d12
+	vadd.i32	d4,d4,d14
+	vadd.i32	d6,d6,d16
+	vadd.i32	d8,d8,d18
+
+	vst4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!
+	vst4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!
+	vst4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
+	vst4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
+	vst1.32		{d8[0]},[r6]
+	vst1.32		{d8[1]},[r7]
+
+.Lno_init_neon:
+	bx	lr				@ bx	lr
+.size	poly1305_init_neon,.-poly1305_init_neon
+
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+	ldr	ip,[r0,#36]		@ is_base2_26
+
+	cmp	r2,#64
+	blo	.Lpoly1305_blocks
+
+	stmdb	sp!,{r4-r7}
+	vstmdb	sp!,{d8-d15}		@ ABI specification says so
+
+	tst	ip,ip			@ is_base2_26?
+	bne	.Lbase2_26_neon
+
+	stmdb	sp!,{r1-r3,lr}
+	bl	.Lpoly1305_init_neon
+
+	ldr	r4,[r0,#0]		@ load hash value base 2^32
+	ldr	r5,[r0,#4]
+	ldr	r6,[r0,#8]
+	ldr	r7,[r0,#12]
+	ldr	ip,[r0,#16]
+
+	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
+	mov	r3,r4,lsr#26
+	 veor	d10,d10,d10
+	mov	r4,r5,lsr#20
+	orr	r3,r3,r5,lsl#6
+	 veor	d12,d12,d12
+	mov	r5,r6,lsr#14
+	orr	r4,r4,r6,lsl#12
+	 veor	d14,d14,d14
+	mov	r6,r7,lsr#8
+	orr	r5,r5,r7,lsl#18
+	 veor	d16,d16,d16
+	and	r3,r3,#0x03ffffff
+	orr	r6,r6,ip,lsl#24
+	 veor	d18,d18,d18
+	and	r4,r4,#0x03ffffff
+	mov	r1,#1
+	and	r5,r5,#0x03ffffff
+	str	r1,[r0,#36]		@ set is_base2_26
+
+	vmov.32	d10[0],r2
+	vmov.32	d12[0],r3
+	vmov.32	d14[0],r4
+	vmov.32	d16[0],r5
+	vmov.32	d18[0],r6
+	adr	r5,.Lzeros
+
+	ldmia	sp!,{r1-r3,lr}
+	b	.Lhash_loaded
+
+.align	4
+.Lbase2_26_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ load hash value
+
+	veor		d10,d10,d10
+	veor		d12,d12,d12
+	veor		d14,d14,d14
+	veor		d16,d16,d16
+	veor		d18,d18,d18
+	vld4.32		{d10[0],d12[0],d14[0],d16[0]},[r0]!
+	adr		r5,.Lzeros
+	vld1.32		{d18[0]},[r0]
+	sub		r0,r0,#16		@ rewind
+
+.Lhash_loaded:
+	add		r4,r1,#32
+	mov		r3,r3,lsl#24
+	tst		r2,#31
+	beq		.Leven
+
+	vld4.32		{d20[0],d22[0],d24[0],d26[0]},[r1]!
+	vmov.32		d28[0],r3
+	sub		r2,r2,#16
+	add		r4,r1,#32
+
+# ifdef	__ARMEB__
+	vrev32.8	q10,q10
+	vrev32.8	q13,q13
+	vrev32.8	q11,q11
+	vrev32.8	q12,q12
+# endif
+	vsri.u32	d28,d26,#8	@ base 2^32 -> base 2^26
+	vshl.u32	d26,d26,#18
+
+	vsri.u32	d26,d24,#14
+	vshl.u32	d24,d24,#12
+	vadd.i32	d29,d28,d18	@ add hash value and move to #hi
+
+	vbic.i32	d26,#0xfc000000
+	vsri.u32	d24,d22,#20
+	vshl.u32	d22,d22,#6
+
+	vbic.i32	d24,#0xfc000000
+	vsri.u32	d22,d20,#26
+	vadd.i32	d27,d26,d16
+
+	vbic.i32	d20,#0xfc000000
+	vbic.i32	d22,#0xfc000000
+	vadd.i32	d25,d24,d14
+
+	vadd.i32	d21,d20,d10
+	vadd.i32	d23,d22,d12
+
+	mov		r7,r5
+	add		r6,r0,#48
+
+	cmp		r2,r2
+	b		.Long_tail
+
+.align	4
+.Leven:
+	subs		r2,r2,#64
+	it		lo
+	movlo		r4,r5
+
+	vmov.i32	q14,#1<<24		@ padbit, yes, always
+	vld4.32		{d20,d22,d24,d26},[r1]	@ inp[0:1]
+	add		r1,r1,#64
+	vld4.32		{d21,d23,d25,d27},[r4]	@ inp[2:3] (or 0)
+	add		r4,r4,#64
+	itt		hi
+	addhi		r7,r0,#(48+1*9*4)
+	addhi		r6,r0,#(48+3*9*4)
+
+# ifdef	__ARMEB__
+	vrev32.8	q10,q10
+	vrev32.8	q13,q13
+	vrev32.8	q11,q11
+	vrev32.8	q12,q12
+# endif
+	vsri.u32	q14,q13,#8		@ base 2^32 -> base 2^26
+	vshl.u32	q13,q13,#18
+
+	vsri.u32	q13,q12,#14
+	vshl.u32	q12,q12,#12
+
+	vbic.i32	q13,#0xfc000000
+	vsri.u32	q12,q11,#20
+	vshl.u32	q11,q11,#6
+
+	vbic.i32	q12,#0xfc000000
+	vsri.u32	q11,q10,#26
+
+	vbic.i32	q10,#0xfc000000
+	vbic.i32	q11,#0xfc000000
+
+	bls		.Lskip_loop
+
+	vld4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!	@ load r^2
+	vld4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!	@ load r^4
+	vld4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
+	vld4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
+	b		.Loop_neon
+
+.align	5
+.Loop_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+	@   ___________________/
+	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+	@   ___________________/ ____________________/
+	@
+	@ Note that we start with inp[2:3]*r^2. This is because it
+	@ doesn't depend on reduction in previous iteration.
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
+	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
+	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
+	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
+	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ inp[2:3]*r^2
+
+	vadd.i32	d24,d24,d14	@ accumulate inp[0:1]
+	vmull.u32	q7,d25,d0[1]
+	vadd.i32	d20,d20,d10
+	vmull.u32	q5,d21,d0[1]
+	vadd.i32	d26,d26,d16
+	vmull.u32	q8,d27,d0[1]
+	vmlal.u32	q7,d23,d1[1]
+	vadd.i32	d22,d22,d12
+	vmull.u32	q6,d23,d0[1]
+
+	vadd.i32	d28,d28,d18
+	vmull.u32	q9,d29,d0[1]
+	subs		r2,r2,#64
+	vmlal.u32	q5,d29,d2[1]
+	it		lo
+	movlo		r4,r5
+	vmlal.u32	q8,d25,d1[1]
+	vld1.32		d8[1],[r7,:32]
+	vmlal.u32	q6,d21,d1[1]
+	vmlal.u32	q9,d27,d1[1]
+
+	vmlal.u32	q5,d27,d4[1]
+	vmlal.u32	q8,d23,d3[1]
+	vmlal.u32	q9,d25,d3[1]
+	vmlal.u32	q6,d29,d4[1]
+	vmlal.u32	q7,d21,d3[1]
+
+	vmlal.u32	q8,d21,d5[1]
+	vmlal.u32	q5,d25,d6[1]
+	vmlal.u32	q9,d23,d5[1]
+	vmlal.u32	q6,d27,d6[1]
+	vmlal.u32	q7,d29,d6[1]
+
+	vmlal.u32	q8,d29,d8[1]
+	vmlal.u32	q5,d23,d8[1]
+	vmlal.u32	q9,d21,d7[1]
+	vmlal.u32	q6,d25,d8[1]
+	vmlal.u32	q7,d27,d8[1]
+
+	vld4.32		{d21,d23,d25,d27},[r4]	@ inp[2:3] (or 0)
+	add		r4,r4,#64
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ (hash+inp[0:1])*r^4 and accumulate
+
+	vmlal.u32	q8,d26,d0[0]
+	vmlal.u32	q5,d20,d0[0]
+	vmlal.u32	q9,d28,d0[0]
+	vmlal.u32	q6,d22,d0[0]
+	vmlal.u32	q7,d24,d0[0]
+	vld1.32		d8[0],[r6,:32]
+
+	vmlal.u32	q8,d24,d1[0]
+	vmlal.u32	q5,d28,d2[0]
+	vmlal.u32	q9,d26,d1[0]
+	vmlal.u32	q6,d20,d1[0]
+	vmlal.u32	q7,d22,d1[0]
+
+	vmlal.u32	q8,d22,d3[0]
+	vmlal.u32	q5,d26,d4[0]
+	vmlal.u32	q9,d24,d3[0]
+	vmlal.u32	q6,d28,d4[0]
+	vmlal.u32	q7,d20,d3[0]
+
+	vmlal.u32	q8,d20,d5[0]
+	vmlal.u32	q5,d24,d6[0]
+	vmlal.u32	q9,d22,d5[0]
+	vmlal.u32	q6,d26,d6[0]
+	vmlal.u32	q8,d28,d8[0]
+
+	vmlal.u32	q7,d28,d6[0]
+	vmlal.u32	q5,d22,d8[0]
+	vmlal.u32	q9,d20,d7[0]
+	vmov.i32	q14,#1<<24		@ padbit, yes, always
+	vmlal.u32	q6,d24,d8[0]
+	vmlal.u32	q7,d26,d8[0]
+
+	vld4.32		{d20,d22,d24,d26},[r1]	@ inp[0:1]
+	add		r1,r1,#64
+# ifdef	__ARMEB__
+	vrev32.8	q10,q10
+	vrev32.8	q11,q11
+	vrev32.8	q12,q12
+	vrev32.8	q13,q13
+# endif
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction interleaved with base 2^32 -> base 2^26 of
+	@ inp[0:3] previously loaded to q10-q13 and smashed to q10-q14.
+
+	vshr.u64	q15,q8,#26
+	vmovn.i64	d16,q8
+	 vshr.u64	q4,q5,#26
+	 vmovn.i64	d10,q5
+	vadd.i64	q9,q9,q15		@ h3 -> h4
+	vbic.i32	d16,#0xfc000000
+	  vsri.u32	q14,q13,#8		@ base 2^32 -> base 2^26
+	 vadd.i64	q6,q6,q4		@ h0 -> h1
+	  vshl.u32	q13,q13,#18
+	 vbic.i32	d10,#0xfc000000
+
+	vshrn.u64	d30,q9,#26
+	vmovn.i64	d18,q9
+	 vshr.u64	q4,q6,#26
+	 vmovn.i64	d12,q6
+	 vadd.i64	q7,q7,q4		@ h1 -> h2
+	  vsri.u32	q13,q12,#14
+	vbic.i32	d18,#0xfc000000
+	  vshl.u32	q12,q12,#12
+	 vbic.i32	d12,#0xfc000000
+
+	vadd.i32	d10,d10,d30
+	vshl.u32	d30,d30,#2
+	  vbic.i32	q13,#0xfc000000
+	 vshrn.u64	d8,q7,#26
+	 vmovn.i64	d14,q7
+	vaddl.u32	q5,d10,d30	@ h4 -> h0 [widen for a sec]
+	  vsri.u32	q12,q11,#20
+	 vadd.i32	d16,d16,d8	@ h2 -> h3
+	  vshl.u32	q11,q11,#6
+	 vbic.i32	d14,#0xfc000000
+	  vbic.i32	q12,#0xfc000000
+
+	vshrn.u64	d30,q5,#26		@ re-narrow
+	vmovn.i64	d10,q5
+	  vsri.u32	q11,q10,#26
+	  vbic.i32	q10,#0xfc000000
+	 vshr.u32	d8,d16,#26
+	 vbic.i32	d16,#0xfc000000
+	vbic.i32	d10,#0xfc000000
+	vadd.i32	d12,d12,d30	@ h0 -> h1
+	 vadd.i32	d18,d18,d8	@ h3 -> h4
+	  vbic.i32	q11,#0xfc000000
+
+	bhi		.Loop_neon
+
+.Lskip_loop:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	add		r7,r0,#(48+0*9*4)
+	add		r6,r0,#(48+1*9*4)
+	adds		r2,r2,#32
+	it		ne
+	movne		r2,#0
+	bne		.Long_tail
+
+	vadd.i32	d25,d24,d14	@ add hash value and move to #hi
+	vadd.i32	d21,d20,d10
+	vadd.i32	d27,d26,d16
+	vadd.i32	d23,d22,d12
+	vadd.i32	d29,d28,d18
+
+.Long_tail:
+	vld4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!	@ load r^1
+	vld4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!	@ load r^2
+
+	vadd.i32	d24,d24,d14	@ can be redundant
+	vmull.u32	q7,d25,d0
+	vadd.i32	d20,d20,d10
+	vmull.u32	q5,d21,d0
+	vadd.i32	d26,d26,d16
+	vmull.u32	q8,d27,d0
+	vadd.i32	d22,d22,d12
+	vmull.u32	q6,d23,d0
+	vadd.i32	d28,d28,d18
+	vmull.u32	q9,d29,d0
+
+	vmlal.u32	q5,d29,d2
+	vld4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
+	vmlal.u32	q8,d25,d1
+	vld4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
+	vmlal.u32	q6,d21,d1
+	vmlal.u32	q9,d27,d1
+	vmlal.u32	q7,d23,d1
+
+	vmlal.u32	q8,d23,d3
+	vld1.32		d8[1],[r7,:32]
+	vmlal.u32	q5,d27,d4
+	vld1.32		d8[0],[r6,:32]
+	vmlal.u32	q9,d25,d3
+	vmlal.u32	q6,d29,d4
+	vmlal.u32	q7,d21,d3
+
+	vmlal.u32	q8,d21,d5
+	 it		ne
+	 addne		r7,r0,#(48+2*9*4)
+	vmlal.u32	q5,d25,d6
+	 it		ne
+	 addne		r6,r0,#(48+3*9*4)
+	vmlal.u32	q9,d23,d5
+	vmlal.u32	q6,d27,d6
+	vmlal.u32	q7,d29,d6
+
+	vmlal.u32	q8,d29,d8
+	 vorn		q0,q0,q0	@ all-ones, can be redundant
+	vmlal.u32	q5,d23,d8
+	 vshr.u64	q0,q0,#38
+	vmlal.u32	q9,d21,d7
+	vmlal.u32	q6,d25,d8
+	vmlal.u32	q7,d27,d8
+
+	beq		.Lshort_tail
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	vld4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!	@ load r^3
+	vld4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!	@ load r^4
+
+	vmlal.u32	q7,d24,d0
+	vmlal.u32	q5,d20,d0
+	vmlal.u32	q8,d26,d0
+	vmlal.u32	q6,d22,d0
+	vmlal.u32	q9,d28,d0
+
+	vmlal.u32	q5,d28,d2
+	vld4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
+	vmlal.u32	q8,d24,d1
+	vld4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
+	vmlal.u32	q6,d20,d1
+	vmlal.u32	q9,d26,d1
+	vmlal.u32	q7,d22,d1
+
+	vmlal.u32	q8,d22,d3
+	vld1.32		d8[1],[r7,:32]
+	vmlal.u32	q5,d26,d4
+	vld1.32		d8[0],[r6,:32]
+	vmlal.u32	q9,d24,d3
+	vmlal.u32	q6,d28,d4
+	vmlal.u32	q7,d20,d3
+
+	vmlal.u32	q8,d20,d5
+	vmlal.u32	q5,d24,d6
+	vmlal.u32	q9,d22,d5
+	vmlal.u32	q6,d26,d6
+	vmlal.u32	q7,d28,d6
+
+	vmlal.u32	q8,d28,d8
+	 vorn		q0,q0,q0	@ all-ones
+	vmlal.u32	q5,d22,d8
+	 vshr.u64	q0,q0,#38
+	vmlal.u32	q9,d20,d7
+	vmlal.u32	q6,d24,d8
+	vmlal.u32	q7,d26,d8
+
+.Lshort_tail:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ horizontal addition
+
+	vadd.i64	d16,d16,d17
+	vadd.i64	d10,d10,d11
+	vadd.i64	d18,d18,d19
+	vadd.i64	d12,d12,d13
+	vadd.i64	d14,d14,d15
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction, but without narrowing
+
+	vshr.u64	q15,q8,#26
+	vand.i64	q8,q8,q0
+	 vshr.u64	q4,q5,#26
+	 vand.i64	q5,q5,q0
+	vadd.i64	q9,q9,q15		@ h3 -> h4
+	 vadd.i64	q6,q6,q4		@ h0 -> h1
+
+	vshr.u64	q15,q9,#26
+	vand.i64	q9,q9,q0
+	 vshr.u64	q4,q6,#26
+	 vand.i64	q6,q6,q0
+	 vadd.i64	q7,q7,q4		@ h1 -> h2
+
+	vadd.i64	q5,q5,q15
+	vshl.u64	q15,q15,#2
+	 vshr.u64	q4,q7,#26
+	 vand.i64	q7,q7,q0
+	vadd.i64	q5,q5,q15		@ h4 -> h0
+	 vadd.i64	q8,q8,q4		@ h2 -> h3
+
+	vshr.u64	q15,q5,#26
+	vand.i64	q5,q5,q0
+	 vshr.u64	q4,q8,#26
+	 vand.i64	q8,q8,q0
+	vadd.i64	q6,q6,q15		@ h0 -> h1
+	 vadd.i64	q9,q9,q4		@ h3 -> h4
+
+	cmp		r2,#0
+	bne		.Leven
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ store hash value
+
+	vst4.32		{d10[0],d12[0],d14[0],d16[0]},[r0]!
+	vst1.32		{d18[0]},[r0]
+
+	vldmia	sp!,{d8-d15}			@ epilogue
+	ldmia	sp!,{r4-r7}
+	bx	lr					@ bx	lr
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+#ifndef	__KERNEL__
+.LOPENSSL_armcap:
+# ifdef	_WIN32
+.word	OPENSSL_armcap_P
+# else
+.word	OPENSSL_armcap_P-.Lpoly1305_init
+# endif
+.comm	OPENSSL_armcap_P,4,4
+.hidden	OPENSSL_armcap_P
+#endif
+#endif
+.asciz	"Poly1305 for ARMv4/NEON, CRYPTOGAMS by @dot-asm"
+.align	2
diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
new file mode 100644
index 000000000000..abe3f2d587dc
--- /dev/null
+++ b/arch/arm/crypto/poly1305-glue.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for ARM
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
+#include <crypto/internal/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/jump_label.h>
+#include <linux/module.h>
+
+void poly1305_init_arm(void *state, const u8 *key);
+void poly1305_blocks_arm(void *state, const u8 *src, u32 len, u32 hibit);
+void poly1305_emit_arm(void *state, __le32 *digest, const u32 *nonce);
+
+void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit)
+{
+}
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
+{
+	poly1305_init_arm(&dctx->h, key);
+	dctx->s[0] = get_unaligned_le32(key + 16);
+	dctx->s[1] = get_unaligned_le32(key + 20);
+	dctx->s[2] = get_unaligned_le32(key + 24);
+	dctx->s[3] = get_unaligned_le32(key + 28);
+	dctx->buflen = 0;
+}
+EXPORT_SYMBOL(poly1305_init_arch);
+
+static int arm_poly1305_init(struct shash_desc *desc)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	dctx->buflen = 0;
+	dctx->rset = 0;
+	dctx->sset = false;
+
+	return 0;
+}
+
+static void arm_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
+				 u32 len, u32 hibit, bool do_neon)
+{
+	if (unlikely(!dctx->sset)) {
+		if (!dctx->rset) {
+			poly1305_init_arm(&dctx->h, src);
+			src += POLY1305_BLOCK_SIZE;
+			len -= POLY1305_BLOCK_SIZE;
+			dctx->rset = 1;
+		}
+		if (len >= POLY1305_BLOCK_SIZE) {
+			dctx->s[0] = get_unaligned_le32(src +  0);
+			dctx->s[1] = get_unaligned_le32(src +  4);
+			dctx->s[2] = get_unaligned_le32(src +  8);
+			dctx->s[3] = get_unaligned_le32(src + 12);
+			src += POLY1305_BLOCK_SIZE;
+			len -= POLY1305_BLOCK_SIZE;
+			dctx->sset = true;
+		}
+		if (len < POLY1305_BLOCK_SIZE)
+			return;
+	}
+
+	len &= ~(POLY1305_BLOCK_SIZE - 1);
+
+	if (static_branch_likely(&have_neon) && likely(do_neon))
+		poly1305_blocks_neon(&dctx->h, src, len, hibit);
+	else
+		poly1305_blocks_arm(&dctx->h, src, len, hibit);
+}
+
+static void arm_poly1305_do_update(struct poly1305_desc_ctx *dctx,
+				    const u8 *src, u32 len, bool do_neon)
+{
+	if (unlikely(dctx->buflen)) {
+		u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		len -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			arm_poly1305_blocks(dctx, dctx->buf,
+					    POLY1305_BLOCK_SIZE, 1, false);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(len >= POLY1305_BLOCK_SIZE)) {
+		arm_poly1305_blocks(dctx, src, len, 1, do_neon);
+		src += round_down(len, POLY1305_BLOCK_SIZE);
+		len %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(len)) {
+		dctx->buflen = len;
+		memcpy(dctx->buf, src, len);
+	}
+}
+
+static int arm_poly1305_update(struct shash_desc *desc,
+			       const u8 *src, unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	arm_poly1305_do_update(dctx, src, srclen, false);
+	return 0;
+}
+
+static int __maybe_unused arm_poly1305_update_neon(struct shash_desc *desc,
+						   const u8 *src,
+						   unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+	bool do_neon = crypto_simd_usable() && srclen > 128;
+
+	if (static_branch_likely(&have_neon) && do_neon)
+		kernel_neon_begin();
+	arm_poly1305_do_update(dctx, src, srclen, do_neon);
+	if (static_branch_likely(&have_neon) && do_neon)
+		kernel_neon_end();
+	return 0;
+}
+
+void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
+			  unsigned int nbytes)
+{
+	bool do_neon = IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+		       crypto_simd_usable();
+
+	if (unlikely(dctx->buflen)) {
+		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		nbytes -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_blocks_arm(&dctx->h, dctx->buf,
+					    POLY1305_BLOCK_SIZE, 1);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
+		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
+
+		if (static_branch_likely(&have_neon) && do_neon) {
+			kernel_neon_begin();
+			poly1305_blocks_neon(&dctx->h, src, len, 1);
+			kernel_neon_end();
+		} else {
+			poly1305_blocks_arm(&dctx->h, src, len, 1);
+		}
+		src += len;
+		nbytes %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(nbytes)) {
+		dctx->buflen = nbytes;
+		memcpy(dctx->buf, src, nbytes);
+	}
+}
+EXPORT_SYMBOL(poly1305_update_arch);
+
+void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
+{
+	__le32 digest[4];
+	u64 f = 0;
+
+	if (unlikely(dctx->buflen)) {
+		dctx->buf[dctx->buflen++] = 1;
+		memset(dctx->buf + dctx->buflen, 0,
+		       POLY1305_BLOCK_SIZE - dctx->buflen);
+		poly1305_blocks_arm(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+	}
+
+	poly1305_emit_arm(&dctx->h, digest, dctx->s);
+
+	/* mac = (h + s) % (2^128) */
+	f = (f >> 32) + le32_to_cpu(digest[0]);
+	put_unaligned_le32(f, dst);
+	f = (f >> 32) + le32_to_cpu(digest[1]);
+	put_unaligned_le32(f, dst + 4);
+	f = (f >> 32) + le32_to_cpu(digest[2]);
+	put_unaligned_le32(f, dst + 8);
+	f = (f >> 32) + le32_to_cpu(digest[3]);
+	put_unaligned_le32(f, dst + 12);
+
+	*dctx = (struct poly1305_desc_ctx){};
+}
+EXPORT_SYMBOL(poly1305_final_arch);
+
+static int arm_poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (unlikely(!dctx->sset))
+		return -ENOKEY;
+
+	poly1305_final_arch(dctx, dst);
+	return 0;
+}
+
+static struct shash_alg arm_poly1305_algs[] = {{
+	.init			= arm_poly1305_init,
+	.update			= arm_poly1305_update,
+	.final			= arm_poly1305_final,
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.descsize		= sizeof(struct poly1305_desc_ctx),
+
+	.base.cra_name		= "poly1305",
+	.base.cra_driver_name	= "poly1305-arm",
+	.base.cra_priority	= 150,
+	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+#ifdef CONFIG_KERNEL_MODE_NEON
+}, {
+	.init			= arm_poly1305_init,
+	.update			= arm_poly1305_update_neon,
+	.final			= arm_poly1305_final,
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.descsize		= sizeof(struct poly1305_desc_ctx),
+
+	.base.cra_name		= "poly1305",
+	.base.cra_driver_name	= "poly1305-neon",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+#endif
+}};
+
+static int __init arm_poly1305_mod_init(void)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+	    (elf_hwcap & HWCAP_NEON))
+		static_branch_enable(&have_neon);
+	else if (IS_REACHABLE(CONFIG_CRYPTO_HASH))
+		/* register only the first entry */
+		return crypto_register_shash(&arm_poly1305_algs[0]);
+
+	return IS_REACHABLE(CONFIG_CRYPTO_HASH) ?
+		crypto_register_shashes(arm_poly1305_algs,
+					ARRAY_SIZE(arm_poly1305_algs)) : 0;
+}
+
+static void __exit arm_poly1305_mod_exit(void)
+{
+	if (!IS_REACHABLE(CONFIG_CRYPTO_HASH))
+		return;
+	if (!static_branch_likely(&have_neon)) {
+		crypto_unregister_shash(&arm_poly1305_algs[0]);
+		return;
+	}
+	crypto_unregister_shashes(arm_poly1305_algs,
+				  ARRAY_SIZE(arm_poly1305_algs));
+}
+
+module_init(arm_poly1305_mod_init);
+module_exit(arm_poly1305_mod_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-arm");
+MODULE_ALIAS_CRYPTO("poly1305-neon");
diff --git a/arch/arm/crypto/sha1-ce-core.S b/arch/arm/crypto/sha1-ce-core.S
index 49a74a441aec..8a702e051738 100644
--- a/arch/arm/crypto/sha1-ce-core.S
+++ b/arch/arm/crypto/sha1-ce-core.S
@@ -10,6 +10,7 @@
 #include <asm/assembler.h>
 
 	.text
+	.arch		armv8-a
 	.fpu		crypto-neon-fp-armv8
 
 	k0		.req	q0
diff --git a/arch/arm/crypto/sha2-ce-core.S b/arch/arm/crypto/sha2-ce-core.S
index 4ad517577e23..b6369d2440a1 100644
--- a/arch/arm/crypto/sha2-ce-core.S
+++ b/arch/arm/crypto/sha2-ce-core.S
@@ -10,6 +10,7 @@
 #include <asm/assembler.h>
 
 	.text
+	.arch		armv8-a
 	.fpu		crypto-neon-fp-armv8
 
 	k0		.req	q7