Signed-off-by: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>
---
arch/arm64/Makefile | 1 +
arch/arm64/crypto/Makefile | 13 ++
arch/arm64/crypto/aes-ce-cipher.c | 382 ++++++++++++++++++++++++++++++++++++++
crypto/Kconfig | 6 +
4 files changed, 402 insertions(+)
create mode 100644 arch/arm64/crypto/Makefile
create mode 100644 arch/arm64/crypto/aes-ce-cipher.c
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 2fceb71ac3b7..8185a913c5ed 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -45,6 +45,7 @@ export TEXT_OFFSET GZFLAGS
core-y += arch/arm64/kernel/ arch/arm64/mm/
core-$(CONFIG_KVM) += arch/arm64/kvm/
core-$(CONFIG_XEN) += arch/arm64/xen/
+core-$(CONFIG_CRYPTO) += arch/arm64/crypto/
libs-y := arch/arm64/lib/ $(libs-y)
libs-y += $(LIBGCC)
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
new file mode 100644
index 000000000000..ac58945c50b3
--- /dev/null
+++ b/arch/arm64/crypto/Makefile
@@ -0,0 +1,13 @@
+#
+# linux/arch/arm64/crypto/Makefile
+#
+# Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@xxxxxxxxxx>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
+
+CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
new file mode 100644
index 000000000000..e2015aae4e86
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -0,0 +1,382 @@
+/*
+ * linux/arch/arm64/crypto/aes-ce-cipher.c
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@xxxxxxxxxx>
+ *
+ * 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 <asm/hwcap.h>
+#include <asm/neon.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>");
+MODULE_LICENSE("GPL");
+
+struct aes_vec {
+ u8 __attribute__((vector_size(16))) v;
+};
+
+struct aes_vec4 {
+ u8 __attribute__((vector_size(16))) v[4];
+};
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+ /*
+ * # of rounds specified by AES:
+ * 128 bit key 10 rounds
+ * 192 bit key 12 rounds
+ * 256 bit key 14 rounds
+ * => n byte key => 6 + (n/4) rounds
+ */
+ return 6 + ctx->key_length / 4;
+}
+
+static void aes_encrypt(struct crypto_aes_ctx *ctx,
+ struct aes_vec *dst, struct aes_vec const *src)
+{
+ void *d1;
+ int d2;
+
+ __asm__(" ld1 {v0.16b}, %[in] ;"
+ " ld1 {v1.2d}, [%[key]] ;"
+ " cmp %[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " mov v3.16b, v1.16b ;"
+ " b 2f ;"
+ "0: mov v2.16b, v1.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ "1: aese v0.16b, v2.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ "2: ld1 {v1.2d}, [%[key]], #16 ;"
+ " aese v0.16b, v3.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ "3: ld1 {v2.2d}, [%[key]], #16 ;"
+ " subs %[rounds], %[rounds], #3 ;"
+ " aese v0.16b, v1.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ " bpl 1b ;"
+ " aese v0.16b, v2.16b ;"
+ " eor v0.16b, v0.16b, v3.16b ;"
+ " st1 {v0.16b}, %[out] ;"
+
+ : [out] "=m"(*dst),
+ "=r"(d1), "=r"(d2) /* dummies */
+ : [in] "m"(*src),
+ [key] "1"(ctx->key_enc),
+ [rounds] "2"(num_rounds(ctx) - 2)
+ : "cc");
+}
+
+static void aes_decrypt(struct crypto_aes_ctx *ctx,
+ struct aes_vec *dst, struct aes_vec const *src)
+{
+ void *d1;
+ int d2;
+
+ __asm__(" ld1 {v0.16b}, %[in] ;"
+ " ld1 {v1.2d}, [%[key]] ;"
+ " cmp %[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " mov v3.16b, v1.16b ;"
+ " b 2f ;"
+ "0: mov v2.16b, v1.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ "1: aesd v0.16b, v2.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ "2: ld1 {v1.2d}, [%[key]], #16 ;"
+ " aesd v0.16b, v3.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ "3: ld1 {v2.2d}, [%[key]], #16 ;"
+ " subs %[rounds], %[rounds], #3 ;"
+ " aesd v0.16b, v1.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ " bpl 1b ;"
+ " aese v0.16b, v2.16b ;"
+ " eor v0.16b, v0.16b, v3.16b ;"
+ " st1 {v0.16b}, %[out] ;"
+
+ : [out] "=m"(*dst),
+ "=r"(d1), "=r"(d2) /* dummies */
+ : [in] "m"(*src),
+ [key] "1"(ctx->key_dec),
+ [rounds] "2"(num_rounds(ctx) - 2)
+ : "cc");
+}
+
+static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+ kernel_neon_begin_partial(4);
+ aes_encrypt(crypto_tfm_ctx(tfm),
+ (struct aes_vec *)dst, (struct aes_vec *)src);
+ kernel_neon_end();
+}
+
+static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+ kernel_neon_begin_partial(4);
+ aes_decrypt(crypto_tfm_ctx(tfm),
+ (struct aes_vec *)dst, (struct aes_vec *)src);
+ kernel_neon_end();
+}
+
+static void aes_encrypt_4x(struct crypto_aes_ctx *ctx,
+ struct aes_vec4 *dst, struct aes_vec4 const *src)
+{
+ void *d1;
+ int d2;
+
+ __asm__(" ld1 {v0.16b-v3.16b}, %[in] ;"
+ " ld1 {v4.2d}, [%[key]] ;"
+ " cmp %[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " mov v6.16b, v4.16b ;"
+ " b 2f ;"
+ "0: mov v5.16b, v4.16b ;"
+ " ld1 {v6.2d}, [%[key]], #16 ;"
+ "1: aese v0.16b, v5.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ " aese v1.16b, v5.16b ;"
+ " aesmc v1.16b, v1.16b ;"
+ " aese v2.16b, v5.16b ;"
+ " aesmc v2.16b, v2.16b ;"
+ " aese v3.16b, v5.16b ;"
+ " aesmc v3.16b, v3.16b ;"
+ "2: ld1 {v4.2d}, [%[key]], #16 ;"
+ " aese v0.16b, v6.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ " aese v1.16b, v6.16b ;"
+ " aesmc v1.16b, v1.16b ;"
+ " aese v2.16b, v6.16b ;"
+ " aesmc v2.16b, v2.16b ;"
+ " aese v3.16b, v6.16b ;"
+ " aesmc v3.16b, v3.16b ;"
+ "3: ld1 {v5.2d}, [%[key]], #16 ;"
+ " subs %[rounds], %[rounds], #3 ;"
+ " aese v0.16b, v4.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ " aese v1.16b, v4.16b ;"
+ " aesmc v1.16b, v1.16b ;"
+ " aese v2.16b, v4.16b ;"
+ " aesmc v2.16b, v2.16b ;"
+ " aese v3.16b, v4.16b ;"
+ " aesmc v3.16b, v3.16b ;"
+ " ld1 {v6.2d}, [%[key]], #16 ;"
+ " bpl 1b ;"
+ " aese v0.16b, v5.16b ;"
+ " aese v1.16b, v5.16b ;"
+ " aese v2.16b, v5.16b ;"
+ " aese v3.16b, v5.16b ;"
+ " eor v0.16b, v0.16b, v6.16b ;"
+ " eor v1.16b, v1.16b, v6.16b ;"
+ " eor v2.16b, v2.16b, v6.16b ;"
+ " eor v3.16b, v3.16b, v6.16b ;"
+ " st1 {v0.16b-v3.16b}, %[out] ;"
+
+ : [out] "=m"(*dst),
+ "=r"(d1), "=r"(d2) /* dummies */
+ : [in] "m"(*src),
+ [key] "1"(ctx->key_dec),
+ [rounds] "2"(num_rounds(ctx) - 2)
+ : "cc");
+}
+
+static void aes_decrypt_4x(struct crypto_aes_ctx *ctx,
+ struct aes_vec4 *dst, struct aes_vec4 const *src)
+{
+ void *d1;
+ int d2;
+
+ __asm__(" ld1 {v0.16b-v3.16b}, %[in] ;"
+ " ld1 {v4.2d}, [%[key]], #16 ;"
+ " cmp %[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " mov v6.16b, v4.16b ;"
+ " b 2f ;"
+ "0: mov v5.16b, v4.16b ;"
+ " ld1 {v6.2d}, [%[key]], #16 ;"
+ "1: aesd v0.16b, v5.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ " aesd v1.16b, v5.16b ;"
+ " aesimc v1.16b, v1.16b ;"
+ " aesd v2.16b, v5.16b ;"
+ " aesimc v2.16b, v2.16b ;"
+ " aesd v3.16b, v5.16b ;"
+ " aesimc v3.16b, v3.16b ;"
+ "2: ld1 {v4.2d}, [%[key]], #16 ;"
+ " aesd v0.16b, v6.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ " aesd v1.16b, v6.16b ;"
+ " aesimc v1.16b, v1.16b ;"
+ " aesd v2.16b, v6.16b ;"
+ " aesimc v2.16b, v2.16b ;"
+ " aesd v3.16b, v6.16b ;"
+ " aesimc v3.16b, v3.16b ;"
+ "3: ld1 {v5.2d}, [%[key]], #16 ;"
+ " subs %[rounds], %[rounds], #3 ;"
+ " aesd v0.16b, v4.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ " aesd v1.16b, v4.16b ;"
+ " aesimc v1.16b, v1.16b ;"
+ " aesd v2.16b, v4.16b ;"
+ " aesimc v2.16b, v2.16b ;"
+ " aesd v3.16b, v4.16b ;"
+ " aesimc v3.16b, v3.16b ;"
+ " ld1 {v6.2d}, [%[key]], #16 ;"
+ " bpl 1b ;"
+ " aesd v0.16b, v5.16b ;"
+ " aesd v1.16b, v5.16b ;"
+ " aesd v2.16b, v5.16b ;"
+ " aesd v3.16b, v5.16b ;"
+ " eor v0.16b, v0.16b, v6.16b ;"
+ " eor v1.16b, v1.16b, v6.16b ;"
+ " eor v2.16b, v2.16b, v6.16b ;"
+ " eor v3.16b, v3.16b, v6.16b ;"
+ " st1 {v0.16b-v3.16b}, %[out] ;"
+
+ : [out] "=m"(*dst),
+ "=r"(d1), "=r"(d2) /* dummies */
+ : [in] "m"(*src),
+ [key] "1"(ctx->key_dec),
+ [rounds] "2"(num_rounds(ctx) - 2)
+ : "cc");
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ struct blkcipher_walk walk;
+ int err;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, 4 * AES_BLOCK_SIZE);
+
+ kernel_neon_begin_partial(7);
+
+ do {
+ u8 *out = walk.dst.virt.addr;
+ u8 *in = walk.src.virt.addr;
+ int bl;
+
+ for (bl = walk.nbytes / AES_BLOCK_SIZE; bl >= 4; bl -= 4) {
+ aes_encrypt_4x(ctx, (struct aes_vec4 *)out,
+ (struct aes_vec4 *)in);
+ out += 4 * AES_BLOCK_SIZE;
+ in += 4 * AES_BLOCK_SIZE;
+ }
+ while (bl--) {
+ aes_encrypt(ctx, (struct aes_vec *)out,
+ (struct aes_vec *)in);
+ out += AES_BLOCK_SIZE;
+ in += AES_BLOCK_SIZE;
+ }
+ err = blkcipher_walk_done(desc, &walk, 0);
+ } while (walk.nbytes);
+
+ kernel_neon_end();
+
+ return err;
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ struct blkcipher_walk walk;
+ int err;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, 4 * AES_BLOCK_SIZE);
+
+ kernel_neon_begin_partial(7);
+
+ do {
+ u8 *out = walk.dst.virt.addr;
+ u8 *in = walk.src.virt.addr;
+ int bl;
+
+ for (bl = walk.nbytes / AES_BLOCK_SIZE; bl >= 4; bl -= 4) {
+ aes_decrypt_4x(ctx, (struct aes_vec4 *)out,
+ (struct aes_vec4 *)in);
+ out += 4 * AES_BLOCK_SIZE;
+ in += 4 * AES_BLOCK_SIZE;
+ }
+ while (bl--) {
+ aes_decrypt(ctx, (struct aes_vec *)out,
+ (struct aes_vec *)in);
+ out += AES_BLOCK_SIZE;
+ in += AES_BLOCK_SIZE;
+ }
+ err = blkcipher_walk_done(desc, &walk, 0);
+ } while (walk.nbytes);
+
+ kernel_neon_end();
+
+ return err;
+}
+
+static struct crypto_alg aes_algs[] = { {
+ .cra_name = "aes",
+ .cra_driver_name = "aes-ce",
+ .cra_priority = 300,
+ .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,
+ .cia_max_keysize = AES_MAX_KEY_SIZE,
+ .cia_setkey = crypto_aes_set_key,
+ .cia_encrypt = aes_cipher_encrypt,
+ .cia_decrypt = aes_cipher_decrypt,
+ }
+}, {
+ .cra_name = "ecb(aes)",
+ .cra_driver_name = "ecb-aes-ce",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = crypto_aes_set_key,
+ .encrypt = ecb_encrypt,
+ .decrypt = ecb_decrypt,
+ }
+} };
+
+static int __init aes_mod_init(void)
+{
+ if (!(elf_hwcap & HWCAP_AES))
+ return -ENODEV;
+ return crypto_register_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static void __exit aes_mod_exit(void)
+{
+ crypto_unregister_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+module_init(aes_mod_init);
+module_exit(aes_mod_exit);
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 7bcb70d216e1..f1d98bc346b6 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -791,6 +791,12 @@ config CRYPTO_AES_ARM_BS
This implementation does not rely on any lookup tables so it is
believed to be invulnerable to cache timing attacks.
+config CRYPTO_AES_ARM64_CE
+ tristate "Synchronous AES cipher using ARMv8 Crypto Extensions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_ALGAPI
+ select CRYPTO_AES
+
config CRYPTO_ANUBIS
tristate "Anubis cipher algorithm"
select CRYPTO_ALGAPI
--
1.8.3.2
--
To unsubscribe from this list: send the line "unsubscribe linux-crypto" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
