Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "API:
   - Add library interfaces of certain crypto algorithms for WireGuard
   - Remove the obsolete ablkcipher and blkcipher interfaces
   - Move add_early_randomness() out of rng_mutex

  Algorithms:
   - Add blake2b shash algorithm
   - Add blake2s shash algorithm
   - Add curve25519 kpp algorithm
   - Implement 4 way interleave in arm64/gcm-ce
   - Implement ciphertext stealing in powerpc/spe-xts
   - Add Eric Biggers's scalar accelerated ChaCha code for ARM
   - Add accelerated 32r2 code from Zinc for MIPS
   - Add OpenSSL/CRYPTOGRAMS poly1305 implementation for ARM and MIPS

  Drivers:
   - Fix entropy reading failures in ks-sa
   - Add support for sam9x60 in atmel
   - Add crypto accelerator for amlogic GXL
   - Add sun8i-ce Crypto Engine
   - Add sun8i-ss cryptographic offloader
   - Add a host of algorithms to inside-secure
   - Add NPCM RNG driver
   - add HiSilicon HPRE accelerator
   - Add HiSilicon TRNG driver"

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (285 commits)
  crypto: vmx - Avoid weird build failures
  crypto: lib/chacha20poly1305 - use chacha20_crypt()
  crypto: x86/chacha - only unregister algorithms if registered
  crypto: chacha_generic - remove unnecessary setkey() functions
  crypto: amlogic - enable working on big endian kernel
  crypto: sun8i-ce - enable working on big endian
  crypto: mips/chacha - select CRYPTO_SKCIPHER, not CRYPTO_BLKCIPHER
  hwrng: ks-sa - Enable COMPILE_TEST
  crypto: essiv - remove redundant null pointer check before kfree
  crypto: atmel-aes - Change data type for "lastc" buffer
  crypto: atmel-tdes - Set the IV after {en,de}crypt
  crypto: sun4i-ss - fix big endian issues
  crypto: sun4i-ss - hide the Invalid keylen message
  crypto: sun4i-ss - use crypto_ahash_digestsize
  crypto: sun4i-ss - remove dependency on not 64BIT
  crypto: sun4i-ss - Fix 64-bit size_t warnings on sun4i-ss-hash.c
  MAINTAINERS: Add maintainer for HiSilicon SEC V2 driver
  crypto: hisilicon - add DebugFS for HiSilicon SEC
  Documentation: add DebugFS doc for HiSilicon SEC
  crypto: hisilicon - add SRIOV for HiSilicon SEC
  ...

16 files changed, 5719 insertions, 255 deletions

diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 84a5ade1e865..63659880eeb3 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -155,6 +155,12 @@
 		pwms = <&pwm9 0 26316 0>; /* 38000 Hz */
 	};
 
+	rom_rng: rng {
+		compatible = "nokia,n900-rom-rng";
+		clocks = <&rng_ick>;
+		clock-names = "ick";
+	};
+
 	/* controlled (enabled/disabled) directly by bcm2048 and wl1251 */
 	vctcxo: vctcxo {
 		compatible = "fixed-clock";
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..3f0c057aa050
--- /dev/null
+++ b/arch/arm/crypto/chacha-glue.c
@@ -0,0 +1,343 @@
+// 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;
+
+	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);
+		}
+
+		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)
+{
+	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