crypto: arm/aes - replace scalar AES cipher

This replaces the scalar AES cipher that originates in the OpenSSL project
with a new implementation that is ~15% (*) faster (on modern cores), and
reuses the lookup tables and the key schedule generation routines from the
generic C implementation (which is usually compiled in anyway due to
networking and other subsystems depending on it).

Note that the bit sliced NEON code for AES still depends on the scalar cipher
that this patch replaces, so it is not removed entirely yet.

* On Cortex-A57, the performance increases from 17.0 to 14.9 cycles per byte
  for 128-bit keys.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

5 files changed, 256 insertions, 119 deletions

diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 2f3339f015d3..f1de658c3c8f 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -62,33 +62,15 @@ config CRYPTO_SHA512_ARM
 	  using optimized ARM assembler and NEON, when available.
 
 config CRYPTO_AES_ARM
-	tristate "AES cipher algorithms (ARM-asm)"
-	depends on ARM
+	tristate "Scalar AES cipher for ARM"
 	select CRYPTO_ALGAPI
 	select CRYPTO_AES
 	help
 	  Use optimized AES assembler routines for ARM platforms.
 
-	  AES cipher algorithms (FIPS-197). AES uses the Rijndael
-	  algorithm.
-
-	  Rijndael appears to be consistently a very good performer in
-	  both hardware and software across a wide range of computing
-	  environments regardless of its use in feedback or non-feedback
-	  modes. Its key setup time is excellent, and its key agility is
-	  good. Rijndael's very low memory requirements make it very well
-	  suited for restricted-space environments, in which it also
-	  demonstrates excellent performance. Rijndael's operations are
-	  among the easiest to defend against power and timing attacks.
-
-	  The AES specifies three key sizes: 128, 192 and 256 bits
-
-	  See <http://csrc.nist.gov/encryption/aes/> for more information.
-
 config CRYPTO_AES_ARM_BS
 	tristate "Bit sliced AES using NEON instructions"
 	depends on KERNEL_MODE_NEON
-	select CRYPTO_AES_ARM
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_SIMD
 	help
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 8d74e55eacd4..8f5de2db701c 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -27,8 +27,8 @@ $(warning $(ce-obj-y) $(ce-obj-m))
 endif
 endif
 
-aes-arm-y	:= aes-armv4.o aes_glue.o
-aes-arm-bs-y	:= aesbs-core.o aesbs-glue.o
+aes-arm-y	:= aes-cipher-core.o aes-cipher-glue.o
+aes-arm-bs-y	:= aes-armv4.o aesbs-core.o aesbs-glue.o
 sha1-arm-y	:= sha1-armv4-large.o sha1_glue.o
 sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
 sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S
new file mode 100644
index 000000000000..b04261e1e068
--- /dev/null
+++ b/arch/arm/crypto/aes-cipher-core.S
@@ -0,0 +1,179 @@
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd.
+ * Author: Ard Biesheuvel <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.
+ */
+
+#include <linux/linkage.h>
+
+	.text
+	.align		5
+
+	rk		.req	r0
+	rounds		.req	r1
+	in		.req	r2
+	out		.req	r3
+	tt		.req	ip
+
+	t0		.req	lr
+	t1		.req	r2
+	t2		.req	r3
+
+	.macro		__select, out, in, idx
+	.if		__LINUX_ARM_ARCH__ < 7
+	and		\out, \in, #0xff << (8 * \idx)
+	.else
+	ubfx		\out, \in, #(8 * \idx), #8
+	.endif
+	.endm
+
+	.macro		__load, out, in, idx
+	.if		__LINUX_ARM_ARCH__ < 7 && \idx > 0
+	ldr		\out, [tt, \in, lsr #(8 * \idx) - 2]
+	.else
+	ldr		\out, [tt, \in, lsl #2]
+	.endif
+	.endm
+
+	.macro		__hround, out0, out1, in0, in1, in2, in3, t3, t4, enc
+	__select	\out0, \in0, 0
+	__select	t0, \in1, 1
+	__load		\out0, \out0, 0
+	__load		t0, t0, 1
+
+	.if		\enc
+	__select	\out1, \in1, 0
+	__select	t1, \in2, 1
+	.else
+	__select	\out1, \in3, 0
+	__select	t1, \in0, 1
+	.endif
+	__load		\out1, \out1, 0
+	__select	t2, \in2, 2
+	__load		t1, t1, 1
+	__load		t2, t2, 2
+
+	eor		\out0, \out0, t0, ror #24
+
+	__select	t0, \in3, 3
+	.if		\enc
+	__select	\t3, \in3, 2
+	__select	\t4, \in0, 3
+	.else
+	__select	\t3, \in1, 2
+	__select	\t4, \in2, 3
+	.endif
+	__load		\t3, \t3, 2
+	__load		t0, t0, 3
+	__load		\t4, \t4, 3
+
+	eor		\out1, \out1, t1, ror #24
+	eor		\out0, \out0, t2, ror #16
+	ldm		rk!, {t1, t2}
+	eor		\out1, \out1, \t3, ror #16
+	eor		\out0, \out0, t0, ror #8
+	eor		\out1, \out1, \t4, ror #8
+	eor		\out0, \out0, t1
+	eor		\out1, \out1, t2
+	.endm
+
+	.macro		fround, out0, out1, out2, out3, in0, in1, in2, in3
+	__hround	\out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1
+	__hround	\out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1
+	.endm
+
+	.macro		iround, out0, out1, out2, out3, in0, in1, in2, in3
+	__hround	\out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0
+	__hround	\out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0
+	.endm
+
+	.macro		__rev, out, in
+	.if		__LINUX_ARM_ARCH__ < 6
+	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
+	.else
+	rev		\out, \in
+	.endif
+	.endm
+
+	.macro		__adrl, out, sym, c
+	.if		__LINUX_ARM_ARCH__ < 7
+	ldr\c		\out, =\sym
+	.else
+	movw\c		\out, #:lower16:\sym
+	movt\c		\out, #:upper16:\sym
+	.endif
+	.endm
+
+	.macro		do_crypt, round, ttab, ltab
+	push		{r3-r11, lr}
+
+	ldr		r4, [in]
+	ldr		r5, [in, #4]
+	ldr		r6, [in, #8]
+	ldr		r7, [in, #12]
+
+	ldm		rk!, {r8-r11}
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	__rev		r4, r4
+	__rev		r5, r5
+	__rev		r6, r6
+	__rev		r7, r7
+#endif
+
+	eor		r4, r4, r8
+	eor		r5, r5, r9
+	eor		r6, r6, r10
+	eor		r7, r7, r11
+
+	__adrl		tt, \ttab
+
+	tst		rounds, #2
+	bne		1f
+
+0:	\round		r8, r9, r10, r11, r4, r5, r6, r7
+	\round		r4, r5, r6, r7, r8, r9, r10, r11
+
+1:	subs		rounds, rounds, #4
+	\round		r8, r9, r10, r11, r4, r5, r6, r7
+	__adrl		tt, \ltab, ls
+	\round		r4, r5, r6, r7, r8, r9, r10, r11
+	bhi		0b
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	__rev		r4, r4
+	__rev		r5, r5
+	__rev		r6, r6
+	__rev		r7, r7
+#endif
+
+	ldr		out, [sp]
+
+	str		r4, [out]
+	str		r5, [out, #4]
+	str		r6, [out, #8]
+	str		r7, [out, #12]
+
+	pop		{r3-r11, pc}
+
+	.align		3
+	.ltorg
+	.endm
+
+ENTRY(__aes_arm_encrypt)
+	do_crypt	fround, crypto_ft_tab, crypto_fl_tab
+ENDPROC(__aes_arm_encrypt)
+
+ENTRY(__aes_arm_decrypt)
+	do_crypt	iround, crypto_it_tab, crypto_il_tab
+ENDPROC(__aes_arm_decrypt)
diff --git a/arch/arm/crypto/aes-cipher-glue.c b/arch/arm/crypto/aes-cipher-glue.c
new file mode 100644
index 000000000000..c222f6e072ad
--- /dev/null
+++ b/arch/arm/crypto/aes-cipher-glue.c
@@ -0,0 +1,74 @@
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd.
+ * Author: Ard Biesheuvel <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.
+ */
+
+#include <crypto/aes.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+asmlinkage void __aes_arm_encrypt(u32 *rk, int rounds, const u8 *in, u8 *out);
+EXPORT_SYMBOL(__aes_arm_encrypt);
+
+asmlinkage void __aes_arm_decrypt(u32 *rk, int rounds, const u8 *in, u8 *out);
+EXPORT_SYMBOL(__aes_arm_decrypt);
+
+static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int rounds = 6 + ctx->key_length / 4;
+
+	__aes_arm_encrypt(ctx->key_enc, rounds, in, out);
+}
+
+static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int rounds = 6 + ctx->key_length / 4;
+
+	__aes_arm_decrypt(ctx->key_dec, rounds, in, out);
+}
+
+static struct crypto_alg aes_alg = {
+	.cra_name			= "aes",
+	.cra_driver_name		= "aes-arm",
+	.cra_priority			= 200,
+	.cra_flags			= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize			= AES_BLOCK_SIZE,
+	.cra_ctxsize			= sizeof(struct crypto_aes_ctx),
+	.cra_module			= THIS_MODULE,
+
+	.cra_cipher.cia_min_keysize	= AES_MIN_KEY_SIZE,
+	.cra_cipher.cia_max_keysize	= AES_MAX_KEY_SIZE,
+	.cra_cipher.cia_setkey		= crypto_aes_set_key,
+	.cra_cipher.cia_encrypt		= aes_encrypt,
+	.cra_cipher.cia_decrypt		= aes_decrypt,
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	.cra_alignmask			= 3,
+#endif
+};
+
+static int __init aes_init(void)
+{
+	return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_fini(void)
+{
+	crypto_unregister_alg(&aes_alg);
+}
+
+module_init(aes_init);
+module_exit(aes_fini);
+
+MODULE_DESCRIPTION("Scalar AES cipher for ARM");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/arch/arm/crypto/aes_glue.c b/arch/arm/crypto/aes_glue.c
deleted file mode 100644
index 0409b8f89782..000000000000
--- a/arch/arm/crypto/aes_glue.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * Glue Code for the asm optimized version of the AES Cipher Algorithm
- */
-
-#include <linux/module.h>
-#include <linux/crypto.h>
-#include <crypto/aes.h>
-
-#include "aes_glue.h"
-
-EXPORT_SYMBOL(AES_encrypt);
-EXPORT_SYMBOL(AES_decrypt);
-EXPORT_SYMBOL(private_AES_set_encrypt_key);
-EXPORT_SYMBOL(private_AES_set_decrypt_key);
-
-static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
-{
-	struct AES_CTX *ctx = crypto_tfm_ctx(tfm);
-	AES_encrypt(src, dst, &ctx->enc_key);
-}
-
-static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
-{
-	struct AES_CTX *ctx = crypto_tfm_ctx(tfm);
-	AES_decrypt(src, dst, &ctx->dec_key);
-}
-
-static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
-		unsigned int key_len)
-{
-	struct AES_CTX *ctx = crypto_tfm_ctx(tfm);
-
-	switch (key_len) {
-	case AES_KEYSIZE_128:
-		key_len = 128;
-		break;
-	case AES_KEYSIZE_192:
-		key_len = 192;
-		break;
-	case AES_KEYSIZE_256:
-		key_len = 256;
-		break;
-	default:
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
-
-	if (private_AES_set_encrypt_key(in_key, key_len, &ctx->enc_key) == -1) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
-	/* private_AES_set_decrypt_key expects an encryption key as input */
-	ctx->dec_key = ctx->enc_key;
-	if (private_AES_set_decrypt_key(in_key, key_len, &ctx->dec_key) == -1) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static struct crypto_alg aes_alg = {
-	.cra_name		= "aes",
-	.cra_driver_name	= "aes-asm",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct AES_CTX),
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(aes_alg.cra_list),
-	.cra_u	= {
-		.cipher	= {
-			.cia_min_keysize	= AES_MIN_KEY_SIZE,
-			.cia_max_keysize	= AES_MAX_KEY_SIZE,
-			.cia_setkey		= aes_set_key,
-			.cia_encrypt		= aes_encrypt,
-			.cia_decrypt		= aes_decrypt
-		}
-	}
-};
-
-static int __init aes_init(void)
-{
-	return crypto_register_alg(&aes_alg);
-}
-
-static void __exit aes_fini(void)
-{
-	crypto_unregister_alg(&aes_alg);
-}
-
-module_init(aes_init);
-module_exit(aes_fini);
-
-MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm (ASM)");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_CRYPTO("aes");
-MODULE_ALIAS_CRYPTO("aes-asm");
-MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");