crypto: arm/curve25519 - wire up NEON implementation

This ports the SUPERCOP implementation for usage in kernel space. In
addition to the usual header, macro, and style changes required for
kernel space, it makes a few small changes to the code:

  - The stack alignment is relaxed to 16 bytes.
  - Superfluous mov statements have been removed.
  - ldr for constants has been replaced with movw.
  - ldreq has been replaced with moveq.
  - The str epilogue has been made more idiomatic.
  - SIMD registers are not pushed and popped at the beginning and end.
  - The prologue and epilogue have been made idiomatic.
  - A hole has been removed from the stack, saving 32 bytes.
  - We write-back the base register whenever possible for vld1.8.
  - Some multiplications have been reordered for better A7 performance.

There are more opportunities for cleanup, since this code is from qhasm,
which doesn't always do the most opportune thing. But even prior to
extensive hand optimizations, this code delivers significant performance
improvements (given in get_cycles() per call):

		      ----------- -------------
	             | generic C | this commit |
	 ------------ ----------- -------------
	| Cortex-A7  |     49136 |       22395 |
	 ------------ ----------- -------------
	| Cortex-A17 |     17326 |        4983 |
	 ------------ ----------- -------------
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
[ardb: - move to arch/arm/crypto
       - wire into lib/crypto framework
       - implement crypto API KPP hooks ]
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm/crypto/Kconfig

@@ -142,4 +142,10 @@ config CRYPTO_NHPOLY1305_NEON
 	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

arch/arm/crypto/Makefile

@@ -12,6 +12,7 @@ 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
 
 obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -38,6 +39,7 @@ 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    $@

arch/arm/crypto/curve25519-glue.c

+// 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 crypto_register_kpp(&curve25519_alg);
+	}
+	return 0;
+}
+
+static void __exit mod_exit(void)
+{
+	if (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");