@@ -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 += $(LIBGCC)
new file mode 100644
@@ -0,0 +1,13 @@
+#
+# linux/arch/arm64/crypto/Makefile
+#
+# Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
+
+CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
new file mode 100644
@@ -0,0 +1,257 @@
+/*
+ * linux/arch/arm64/crypto/aes-ce-cipher.c
+ *
+ * Copyright (C) 2013 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.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <crypto/aes.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL");
+
+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_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ kernel_neon_begin_partial(4);
+
+ __asm__(" ld1 {v0.16b}, [%[in]] ;"
+ " cmp %[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ " b 2f ;"
+ "0: ld1 {v2.2d-v3.2d}, [%[key]], #32 ;"
+ "1: aese v0.16b, v2.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ "2: aese v0.16b, v3.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ "3: ld1 {v1.2d-v3.2d}, [%[key]], #48 ;"
+ " subs %[rounds], %[rounds], #3 ;"
+ " aese v0.16b, v1.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ " bpl 1b ;"
+ " aese v0.16b, v2.16b ;"
+ " eor v0.16b, v0.16b, v3.16b ;"
+ " st1 {v0.16b}, [%[out]] ;"
+ : :
+ [out] "r"(dst),
+ [in] "r"(src),
+ [rounds] "r"(num_rounds(ctx) - 2),
+ [key] "r"(ctx->key_enc)
+ : "cc", "memory");
+
+ kernel_neon_end();
+}
+
+static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ kernel_neon_begin_partial(4);
+
+ __asm__(" ld1 {v0.16b}, [%[in]] ;"
+ " cmp %[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ " b 2f ;"
+ "0: ld1 {v2.2d-v3.2d}, [%[key]], #32 ;"
+ "1: aesd v0.16b, v2.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ "2: aesd v0.16b, v3.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ "3: ld1 {v1.2d-v3.2d}, [%[key]], #48 ;"
+ " subs %[rounds], %[rounds], #3 ;"
+ " aesd v0.16b, v1.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ " bpl 1b ;"
+ " aesd v0.16b, v2.16b ;"
+ " eor v0.16b, v0.16b, v3.16b ;"
+ " st1 {v0.16b}, [%[out]] ;"
+ : :
+ [out] "r"(dst),
+ [in] "r"(src),
+ [rounds] "r"(num_rounds(ctx) - 2),
+ [key] "r"(ctx->key_dec)
+ : "cc", "memory");
+
+ kernel_neon_end();
+}
+
+
+static void aes_cipher_enc_interleave(struct crypto_tfm *tfm, u8 dst[],
+ u8 const src[])
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ kernel_neon_begin_partial(7);
+
+ __asm__(" ld1 {v0.16b-v3.16b}, [%[in]] ;"
+ " cmp %[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " ld1 {v6.2d}, [%[key]], #16 ;"
+ " b 2f ;"
+ "0: ld1 {v5.2d-v6.2d}, [%[key]], #32 ;"
+ "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: 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 {v4.2d-v6.2d}, [%[key]], #48 ;"
+ " 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 ;"
+ " 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] "r"(dst),
+ [in] "r"(src),
+ [rounds] "r"(num_rounds(ctx) - 2),
+ [key] "r"(ctx->key_enc)
+ : "cc", "memory");
+
+ kernel_neon_end();
+}
+
+static void aes_cipher_dec_interleave(struct crypto_tfm *tfm, u8 dst[],
+ u8 const src[])
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ kernel_neon_begin_partial(7);
+
+ __asm__(" ld1 {v0.16b-v3.16b}, [%[in]] ;"
+ " cmp %[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " ld1 {v6.2d}, [%[key]], #16 ;"
+ " b 2f ;"
+ "0: ld1 {v5.2d-v6.2d}, [%[key]], #32 ;"
+ "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: 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 {v4.2d-v6.2d}, [%[key]], #48 ;"
+ " 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 ;"
+ " 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] "r"(dst),
+ [in] "r"(src),
+ [rounds] "r"(num_rounds(ctx) - 2),
+ [key] "r"(ctx->key_dec)
+ : "cc", "memory");
+
+ kernel_neon_end();
+}
+
+static struct crypto_alg aes_alg = {
+ .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,
+ .cia_interleave = 4,
+ .cia_enc_interleave = aes_cipher_enc_interleave,
+ .cia_dec_interleave = aes_cipher_dec_interleave,
+ }
+};
+
+static int __init aes_mod_init(void)
+{
+ if (!(elf_hwcap & HWCAP_AES))
+ return -ENODEV;
+ return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+ crypto_unregister_alg(&aes_alg);
+}
+
+module_init(aes_mod_init);
+module_exit(aes_mod_exit);
@@ -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
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- arch/arm64/Makefile | 1 + arch/arm64/crypto/Makefile | 13 ++ arch/arm64/crypto/aes-ce-cipher.c | 257 ++++++++++++++++++++++++++++++++++++++ crypto/Kconfig | 6 + 4 files changed, 277 insertions(+) create mode 100644 arch/arm64/crypto/Makefile create mode 100644 arch/arm64/crypto/aes-ce-cipher.c