1 files changed, 129 insertions, 154 deletions

diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index c76377961444..df5afe601e4a 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -1,22 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Bit sliced AES using NEON instructions
  *
  * Copyright (C) 2017 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/neon.h>
+#include <asm/simd.h>
 #include <crypto/aes.h>
-#include <crypto/cbc.h>
-#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
 #include <crypto/xts.h>
 #include <linux/module.h>
+#include "aes-cipher.h"
 
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_DESCRIPTION("Bit sliced AES using NEON instructions");
 MODULE_LICENSE("GPL v2");
 
 MODULE_ALIAS_CRYPTO("ecb(aes)");
@@ -35,12 +34,12 @@ asmlinkage void aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
 				  int rounds, int blocks, u8 iv[]);
 
 asmlinkage void aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
-				  int rounds, int blocks, u8 ctr[], u8 final[]);
+				  int rounds, int blocks, u8 ctr[]);
 
 asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
-				  int rounds, int blocks, u8 iv[]);
+				  int rounds, int blocks, u8 iv[], int);
 asmlinkage void aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[],
-				  int rounds, int blocks, u8 iv[]);
+				  int rounds, int blocks, u8 iv[], int);
 
 struct aesbs_ctx {
 	int	rounds;
@@ -49,12 +48,13 @@ struct aesbs_ctx {
 
 struct aesbs_cbc_ctx {
 	struct aesbs_ctx	key;
-	struct crypto_cipher	*enc_tfm;
+	struct crypto_aes_ctx	fallback;
 };
 
 struct aesbs_xts_ctx {
 	struct aesbs_ctx	key;
-	struct crypto_cipher	*tweak_tfm;
+	struct crypto_aes_ctx	fallback;
+	struct crypto_aes_ctx	tweak_key;
 };
 
 static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
@@ -64,7 +64,7 @@ static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 	struct crypto_aes_ctx rk;
 	int err;
 
-	err = crypto_aes_expand_key(&rk, in_key, key_len);
+	err = aes_expandkey(&rk, in_key, key_len);
 	if (err)
 		return err;
 
@@ -86,9 +86,8 @@ static int __ecb_crypt(struct skcipher_request *req,
 	struct skcipher_walk walk;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
@@ -96,12 +95,13 @@ static int __ecb_crypt(struct skcipher_request *req,
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
 
+		kernel_neon_begin();
 		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk,
 		   ctx->rounds, blocks);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -120,32 +120,49 @@ static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
 	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct crypto_aes_ctx rk;
 	int err;
 
-	err = crypto_aes_expand_key(&rk, in_key, key_len);
+	err = aes_expandkey(&ctx->fallback, in_key, key_len);
 	if (err)
 		return err;
 
 	ctx->key.rounds = 6 + key_len / 4;
 
 	kernel_neon_begin();
-	aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds);
+	aesbs_convert_key(ctx->key.rk, ctx->fallback.key_enc, ctx->key.rounds);
 	kernel_neon_end();
 
-	return crypto_cipher_setkey(ctx->enc_tfm, in_key, key_len);
-}
-
-static void cbc_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
-{
-	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	crypto_cipher_encrypt_one(ctx->enc_tfm, dst, src);
+	return 0;
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	return crypto_cbc_encrypt_walk(req, cbc_encrypt_one);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+		u8 *prev = walk.iv;
+
+		do {
+			crypto_xor_cpy(dst, src, prev, AES_BLOCK_SIZE);
+			__aes_arm_encrypt(ctx->fallback.key_enc,
+					  ctx->key.rounds, dst, dst);
+			prev = dst;
+			src += AES_BLOCK_SIZE;
+			dst += AES_BLOCK_SIZE;
+			nbytes -= AES_BLOCK_SIZE;
+		} while (nbytes >= AES_BLOCK_SIZE);
+		memcpy(walk.iv, prev, AES_BLOCK_SIZE);
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+	return err;
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
@@ -155,9 +172,8 @@ static int cbc_decrypt(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
@@ -165,34 +181,18 @@ static int cbc_decrypt(struct skcipher_request *req)
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
 
+		kernel_neon_begin();
 		aesbs_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				  ctx->key.rk, ctx->key.rounds, blocks,
 				  walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
 
-static int cbc_init(struct crypto_tfm *tfm)
-{
-	struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	ctx->enc_tfm = crypto_alloc_cipher("aes", 0, 0);
-	if (IS_ERR(ctx->enc_tfm))
-		return PTR_ERR(ctx->enc_tfm);
-	return 0;
-}
-
-static void cbc_exit(struct crypto_tfm *tfm)
-{
-	struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	crypto_free_cipher(ctx->enc_tfm);
-}
-
 static int ctr_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -201,37 +201,29 @@ static int ctr_encrypt(struct skcipher_request *req)
 	u8 buf[AES_BLOCK_SIZE];
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while (walk.nbytes > 0) {
-		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
-		u8 *final = (walk.total % AES_BLOCK_SIZE) ? buf : NULL;
-
-		if (walk.nbytes < walk.total) {
-			blocks = round_down(blocks,
-					    walk.stride / AES_BLOCK_SIZE);
-			final = NULL;
-		}
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+		unsigned int bytes = walk.nbytes;
 
-		aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				  ctx->rk, ctx->rounds, blocks, walk.iv, final);
+		if (unlikely(bytes < AES_BLOCK_SIZE))
+			src = dst = memcpy(buf + sizeof(buf) - bytes,
+					   src, bytes);
+		else if (walk.nbytes < walk.total)
+			bytes &= ~(8 * AES_BLOCK_SIZE - 1);
 
-		if (final) {
-			u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
-			u8 *src = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+		kernel_neon_begin();
+		aesbs_ctr_encrypt(dst, src, ctx->rk, ctx->rounds, bytes, walk.iv);
+		kernel_neon_end();
 
-			if (dst != src)
-				memcpy(dst, src, walk.total % AES_BLOCK_SIZE);
-			crypto_xor(dst, final, walk.total % AES_BLOCK_SIZE);
+		if (unlikely(bytes < AES_BLOCK_SIZE))
+			memcpy(walk.dst.virt.addr,
+			       buf + sizeof(buf) - bytes, bytes);
 
-			err = skcipher_walk_done(&walk, 0);
-			break;
-		}
-		err = skcipher_walk_done(&walk,
-					 walk.nbytes - blocks * AES_BLOCK_SIZE);
+		err = skcipher_walk_done(&walk, walk.nbytes - bytes);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -247,79 +239,106 @@ static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 		return err;
 
 	key_len /= 2;
-	err = crypto_cipher_setkey(ctx->tweak_tfm, in_key + key_len, key_len);
+	err = aes_expandkey(&ctx->fallback, in_key, key_len);
+	if (err)
+		return err;
+	err = aes_expandkey(&ctx->tweak_key, in_key + key_len, key_len);
 	if (err)
 		return err;
 
 	return aesbs_setkey(tfm, in_key, key_len);
 }
 
-static int xts_init(struct crypto_tfm *tfm)
-{
-	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	ctx->tweak_tfm = crypto_alloc_cipher("aes", 0, 0);
-	if (IS_ERR(ctx->tweak_tfm))
-		return PTR_ERR(ctx->tweak_tfm);
-	return 0;
-}
-
-static void xts_exit(struct crypto_tfm *tfm)
-{
-	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	crypto_free_cipher(ctx->tweak_tfm);
-}
-
-static int __xts_crypt(struct skcipher_request *req,
+static int __xts_crypt(struct skcipher_request *req, bool encrypt,
 		       void (*fn)(u8 out[], u8 const in[], u8 const rk[],
-				  int rounds, int blocks, u8 iv[]))
+				  int rounds, int blocks, u8 iv[], int))
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	const int rounds = ctx->key.rounds;
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	struct skcipher_request subreq;
+	u8 buf[2 * AES_BLOCK_SIZE];
 	struct skcipher_walk walk;
 	int err;
 
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	if (unlikely(tail)) {
+		skcipher_request_set_tfm(&subreq, tfm);
+		skcipher_request_set_callback(&subreq,
+					      skcipher_request_flags(req),
+					      NULL, NULL);
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   req->cryptlen - tail, req->iv);
+		req = &subreq;
+	}
+
 	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
-	crypto_cipher_encrypt_one(ctx->tweak_tfm, walk.iv, walk.iv);
+	__aes_arm_encrypt(ctx->tweak_key.key_enc, rounds, walk.iv, walk.iv);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+		int reorder_last_tweak = !encrypt && tail > 0;
 
-		if (walk.nbytes < walk.total)
+		if (walk.nbytes < walk.total) {
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
+			reorder_last_tweak = 0;
+		}
 
+		kernel_neon_begin();
 		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->key.rk,
-		   ctx->key.rounds, blocks, walk.iv);
+		   rounds, blocks, walk.iv, reorder_last_tweak);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
-	return err;
+	if (err || likely(!tail))
+		return err;
+
+	/* handle ciphertext stealing */
+	scatterwalk_map_and_copy(buf, req->dst, req->cryptlen - AES_BLOCK_SIZE,
+				 AES_BLOCK_SIZE, 0);
+	memcpy(buf + AES_BLOCK_SIZE, buf, tail);
+	scatterwalk_map_and_copy(buf, req->src, req->cryptlen, tail, 0);
+
+	crypto_xor(buf, req->iv, AES_BLOCK_SIZE);
+
+	if (encrypt)
+		__aes_arm_encrypt(ctx->fallback.key_enc, rounds, buf, buf);
+	else
+		__aes_arm_decrypt(ctx->fallback.key_dec, rounds, buf, buf);
+
+	crypto_xor(buf, req->iv, AES_BLOCK_SIZE);
+
+	scatterwalk_map_and_copy(buf, req->dst, req->cryptlen - AES_BLOCK_SIZE,
+				 AES_BLOCK_SIZE + tail, 1);
+	return 0;
 }
 
 static int xts_encrypt(struct skcipher_request *req)
 {
-	return __xts_crypt(req, aesbs_xts_encrypt);
+	return __xts_crypt(req, true, aesbs_xts_encrypt);
 }
 
 static int xts_decrypt(struct skcipher_request *req)
 {
-	return __xts_crypt(req, aesbs_xts_decrypt);
+	return __xts_crypt(req, false, aesbs_xts_decrypt);
 }
 
 static struct skcipher_alg aes_algs[] = { {
-	.base.cra_name		= "__ecb(aes)",
-	.base.cra_driver_name	= "__ecb-aes-neonbs",
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "ecb-aes-neonbs",
 	.base.cra_priority	= 250,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct aesbs_ctx),
 	.base.cra_module	= THIS_MODULE,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
@@ -328,15 +347,12 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= ecb_encrypt,
 	.decrypt		= ecb_decrypt,
 }, {
-	.base.cra_name		= "__cbc(aes)",
-	.base.cra_driver_name	= "__cbc-aes-neonbs",
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "cbc-aes-neonbs",
 	.base.cra_priority	= 250,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct aesbs_cbc_ctx),
 	.base.cra_module	= THIS_MODULE,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
-	.base.cra_init		= cbc_init,
-	.base.cra_exit		= cbc_exit,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
@@ -346,13 +362,12 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= cbc_encrypt,
 	.decrypt		= cbc_decrypt,
 }, {
-	.base.cra_name		= "__ctr(aes)",
-	.base.cra_driver_name	= "__ctr-aes-neonbs",
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "ctr-aes-neonbs",
 	.base.cra_priority	= 250,
 	.base.cra_blocksize	= 1,
 	.base.cra_ctxsize	= sizeof(struct aesbs_ctx),
 	.base.cra_module	= THIS_MODULE,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
@@ -363,15 +378,12 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= ctr_encrypt,
 	.decrypt		= ctr_encrypt,
 }, {
-	.base.cra_name		= "__xts(aes)",
-	.base.cra_driver_name	= "__xts-aes-neonbs",
+	.base.cra_name		= "xts(aes)",
+	.base.cra_driver_name	= "xts-aes-neonbs",
 	.base.cra_priority	= 250,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct aesbs_xts_ctx),
 	.base.cra_module	= THIS_MODULE,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
-	.base.cra_init		= xts_init,
-	.base.cra_exit		= xts_exit,
 
 	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
 	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
@@ -382,55 +394,18 @@ static struct skcipher_alg aes_algs[] = { {
 	.decrypt		= xts_decrypt,
 } };
 
-static struct simd_skcipher_alg *aes_simd_algs[ARRAY_SIZE(aes_algs)];
-
 static void aes_exit(void)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(aes_simd_algs); i++)
-		if (aes_simd_algs[i])
-			simd_skcipher_free(aes_simd_algs[i]);
-
 	crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
 }
 
 static int __init aes_init(void)
 {
-	struct simd_skcipher_alg *simd;
-	const char *basename;
-	const char *algname;
-	const char *drvname;
-	int err;
-	int i;
-
 	if (!(elf_hwcap & HWCAP_NEON))
 		return -ENODEV;
 
-	err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
-	if (err)
-		return err;
-
-	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
-		if (!(aes_algs[i].base.cra_flags & CRYPTO_ALG_INTERNAL))
-			continue;
-
-		algname = aes_algs[i].base.cra_name + 2;
-		drvname = aes_algs[i].base.cra_driver_name + 2;
-		basename = aes_algs[i].base.cra_driver_name;
-		simd = simd_skcipher_create_compat(algname, drvname, basename);
-		err = PTR_ERR(simd);
-		if (IS_ERR(simd))
-			goto unregister_simds;
-
-		aes_simd_algs[i] = simd;
-	}
-	return 0;
-
-unregister_simds:
-	aes_exit();
-	return err;
+	return crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
 }
 
-late_initcall(aes_init);
+module_init(aes_init);
 module_exit(aes_exit);