1 files changed, 109 insertions, 205 deletions

diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index fb507d569922..d496effb0a5b 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -16,6 +16,7 @@
 #include <linux/module.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)");
@@ -34,7 +35,7 @@ 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 iv[], u8 final[]);
+				  int rounds, int blocks, u8 iv[]);
 
 asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
 				  int rounds, int blocks, u8 iv[]);
@@ -46,6 +47,8 @@ asmlinkage void neon_aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[],
 				     int rounds, int blocks);
 asmlinkage void neon_aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[],
 				     int rounds, int blocks, u8 iv[]);
+asmlinkage void neon_aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[],
+				     int rounds, int bytes, u8 ctr[]);
 asmlinkage void neon_aes_xts_encrypt(u8 out[], u8 const in[],
 				     u32 const rk1[], int rounds, int bytes,
 				     u32 const rk2[], u8 iv[], int first);
@@ -58,16 +61,11 @@ struct aesbs_ctx {
 	int	rounds;
 } __aligned(AES_BLOCK_SIZE);
 
-struct aesbs_cbc_ctx {
+struct aesbs_cbc_ctr_ctx {
 	struct aesbs_ctx	key;
 	u32			enc[AES_MAX_KEYLENGTH_U32];
 };
 
-struct aesbs_ctr_ctx {
-	struct aesbs_ctx	key;		/* must be first member */
-	struct crypto_aes_ctx	fallback;
-};
-
 struct aesbs_xts_ctx {
 	struct aesbs_ctx	key;
 	u32			twkey[AES_MAX_KEYLENGTH_U32];
@@ -87,9 +85,8 @@ static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 
 	ctx->rounds = 6 + key_len / 4;
 
-	kernel_neon_begin();
-	aesbs_convert_key(ctx->rk, rk.key_enc, ctx->rounds);
-	kernel_neon_end();
+	scoped_ksimd()
+		aesbs_convert_key(ctx->rk, rk.key_enc, ctx->rounds);
 
 	return 0;
 }
@@ -112,10 +109,9 @@ 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();
+		scoped_ksimd()
+			fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk,
+			   ctx->rounds, blocks);
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
@@ -133,10 +129,10 @@ static int ecb_decrypt(struct skcipher_request *req)
 	return __ecb_crypt(req, aesbs_ecb_decrypt);
 }
 
-static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+static int aesbs_cbc_ctr_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
-	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct crypto_aes_ctx rk;
 	int err;
 
@@ -148,9 +144,8 @@ static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 
 	memcpy(ctx->enc, rk.key_enc, sizeof(ctx->enc));
 
-	kernel_neon_begin();
-	aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds);
-	kernel_neon_end();
+	scoped_ksimd()
+		aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds);
 	memzero_explicit(&rk, sizeof(rk));
 
 	return 0;
@@ -159,7 +154,7 @@ static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 static int cbc_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct skcipher_walk walk;
 	int err;
 
@@ -169,11 +164,11 @@ static int cbc_encrypt(struct skcipher_request *req)
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
 		/* fall back to the non-bitsliced NEON implementation */
-		kernel_neon_begin();
-		neon_aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				     ctx->enc, ctx->key.rounds, blocks,
-				     walk.iv);
-		kernel_neon_end();
+		scoped_ksimd()
+			neon_aes_cbc_encrypt(walk.dst.virt.addr,
+					     walk.src.virt.addr,
+					     ctx->enc, ctx->key.rounds, blocks,
+					     walk.iv);
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
@@ -182,7 +177,7 @@ static int cbc_encrypt(struct skcipher_request *req)
 static int cbc_decrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct skcipher_walk walk;
 	int err;
 
@@ -195,11 +190,10 @@ 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();
+		scoped_ksimd()
+			aesbs_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+					  ctx->key.rk, ctx->key.rounds, blocks,
+					  walk.iv);
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
@@ -207,62 +201,48 @@ static int cbc_decrypt(struct skcipher_request *req)
 	return err;
 }
 
-static int aesbs_ctr_setkey_sync(struct crypto_skcipher *tfm, const u8 *in_key,
-				 unsigned int key_len)
-{
-	struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err;
-
-	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, ctx->fallback.key_enc, ctx->key.rounds);
-	kernel_neon_end();
-
-	return 0;
-}
-
 static int ctr_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct skcipher_walk walk;
-	u8 buf[AES_BLOCK_SIZE];
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, false);
 
 	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;
+		int blocks = (walk.nbytes / AES_BLOCK_SIZE) & ~7;
+		int nbytes = walk.nbytes % (8 * AES_BLOCK_SIZE);
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+
+		scoped_ksimd() {
+			if (blocks >= 8) {
+				aesbs_ctr_encrypt(dst, src, ctx->key.rk,
+						  ctx->key.rounds, blocks,
+						  walk.iv);
+				dst += blocks * AES_BLOCK_SIZE;
+				src += blocks * AES_BLOCK_SIZE;
+			}
+			if (nbytes && walk.nbytes == walk.total) {
+				u8 buf[AES_BLOCK_SIZE];
+				u8 *d = dst;
+
+				if (unlikely(nbytes < AES_BLOCK_SIZE))
+					src = dst = memcpy(buf + sizeof(buf) -
+							   nbytes, src, nbytes);
+
+				neon_aes_ctr_encrypt(dst, src, ctx->enc,
+						     ctx->key.rounds, nbytes,
+						     walk.iv);
+
+				if (unlikely(nbytes < AES_BLOCK_SIZE))
+					memcpy(d, dst, nbytes);
+
+				nbytes = 0;
+			}
 		}
-
-		kernel_neon_begin();
-		aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				  ctx->rk, ctx->rounds, blocks, walk.iv, final);
-		kernel_neon_end();
-
-		if (final) {
-			u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
-			u8 *src = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
-
-			crypto_xor_cpy(dst, src, final,
-				       walk.total % AES_BLOCK_SIZE);
-
-			err = skcipher_walk_done(&walk, 0);
-			break;
-		}
-		err = skcipher_walk_done(&walk,
-					 walk.nbytes - blocks * AES_BLOCK_SIZE);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 	return err;
 }
@@ -292,29 +272,6 @@ static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 	return aesbs_setkey(tfm, in_key, key_len);
 }
 
-static void ctr_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
-{
-	struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
-	unsigned long flags;
-
-	/*
-	 * Temporarily disable interrupts to avoid races where
-	 * cachelines are evicted when the CPU is interrupted
-	 * to do something else.
-	 */
-	local_irq_save(flags);
-	aes_encrypt(&ctx->fallback, dst, src);
-	local_irq_restore(flags);
-}
-
-static int ctr_encrypt_sync(struct skcipher_request *req)
-{
-	if (!crypto_simd_usable())
-		return crypto_ctr_encrypt_walk(req, ctr_encrypt_one);
-
-	return ctr_encrypt(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[]))
@@ -328,7 +285,8 @@ static int __xts_crypt(struct skcipher_request *req, bool encrypt,
 	struct skcipher_walk walk;
 	int nbytes, err;
 	int first = 1;
-	u8 *out, *in;
+	const u8 *in;
+	u8 *out;
 
 	if (req->cryptlen < AES_BLOCK_SIZE)
 		return -EINVAL;
@@ -355,36 +313,38 @@ static int __xts_crypt(struct skcipher_request *req, bool encrypt,
 		return err;
 
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
-		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
-
-		if (walk.nbytes < walk.total || walk.nbytes % AES_BLOCK_SIZE)
-			blocks = round_down(blocks,
-					    walk.stride / AES_BLOCK_SIZE);
-
+		int blocks = (walk.nbytes / AES_BLOCK_SIZE) & ~7;
 		out = walk.dst.virt.addr;
 		in = walk.src.virt.addr;
 		nbytes = walk.nbytes;
 
-		kernel_neon_begin();
-		if (likely(blocks > 6)) { /* plain NEON is faster otherwise */
-			if (first)
-				neon_aes_ecb_encrypt(walk.iv, walk.iv,
-						     ctx->twkey,
-						     ctx->key.rounds, 1);
-			first = 0;
-
-			fn(out, in, ctx->key.rk, ctx->key.rounds, blocks,
-			   walk.iv);
-
-			out += blocks * AES_BLOCK_SIZE;
-			in += blocks * AES_BLOCK_SIZE;
-			nbytes -= blocks * AES_BLOCK_SIZE;
+		scoped_ksimd() {
+			if (blocks >= 8) {
+				if (first == 1)
+					neon_aes_ecb_encrypt(walk.iv, walk.iv,
+							     ctx->twkey,
+							     ctx->key.rounds, 1);
+				first = 2;
+
+				fn(out, in, ctx->key.rk, ctx->key.rounds, blocks,
+				   walk.iv);
+
+				out += blocks * AES_BLOCK_SIZE;
+				in += blocks * AES_BLOCK_SIZE;
+				nbytes -= blocks * AES_BLOCK_SIZE;
+			}
+			if (walk.nbytes == walk.total && nbytes > 0) {
+				if (encrypt)
+					neon_aes_xts_encrypt(out, in, ctx->cts.key_enc,
+							     ctx->key.rounds, nbytes,
+							     ctx->twkey, walk.iv, first);
+				else
+					neon_aes_xts_decrypt(out, in, ctx->cts.key_dec,
+							     ctx->key.rounds, nbytes,
+							     ctx->twkey, walk.iv, first);
+				nbytes = first = 0;
+			}
 		}
-
-		if (walk.nbytes == walk.total && nbytes > 0)
-			goto xts_tail;
-
-		kernel_neon_end();
 		err = skcipher_walk_done(&walk, nbytes);
 	}
 
@@ -407,15 +367,16 @@ static int __xts_crypt(struct skcipher_request *req, bool encrypt,
 	in = walk.src.virt.addr;
 	nbytes = walk.nbytes;
 
-	kernel_neon_begin();
-xts_tail:
-	if (encrypt)
-		neon_aes_xts_encrypt(out, in, ctx->cts.key_enc, ctx->key.rounds,
-				     nbytes, ctx->twkey, walk.iv, first ?: 2);
-	else
-		neon_aes_xts_decrypt(out, in, ctx->cts.key_dec, ctx->key.rounds,
-				     nbytes, ctx->twkey, walk.iv, first ?: 2);
-	kernel_neon_end();
+	scoped_ksimd() {
+		if (encrypt)
+			neon_aes_xts_encrypt(out, in, ctx->cts.key_enc,
+					     ctx->key.rounds, nbytes, ctx->twkey,
+					     walk.iv, first);
+		else
+			neon_aes_xts_decrypt(out, in, ctx->cts.key_dec,
+					     ctx->key.rounds, nbytes, ctx->twkey,
+					     walk.iv, first);
+	}
 
 	return skcipher_walk_done(&walk, 0);
 }
@@ -431,13 +392,12 @@ static int xts_decrypt(struct skcipher_request *req)
 }
 
 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,
@@ -446,62 +406,43 @@ 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_ctxsize	= sizeof(struct aesbs_cbc_ctr_ctx),
 	.base.cra_module	= THIS_MODULE,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
 	.walksize		= 8 * AES_BLOCK_SIZE,
 	.ivsize			= AES_BLOCK_SIZE,
-	.setkey			= aesbs_cbc_setkey,
+	.setkey			= aesbs_cbc_ctr_setkey,
 	.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_ctxsize	= sizeof(struct aesbs_cbc_ctr_ctx),
 	.base.cra_module	= THIS_MODULE,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
 	.chunksize		= AES_BLOCK_SIZE,
 	.walksize		= 8 * AES_BLOCK_SIZE,
 	.ivsize			= AES_BLOCK_SIZE,
-	.setkey			= aesbs_setkey,
+	.setkey			= aesbs_cbc_ctr_setkey,
 	.encrypt		= ctr_encrypt,
 	.decrypt		= ctr_encrypt,
 }, {
-	.base.cra_name		= "ctr(aes)",
-	.base.cra_driver_name	= "ctr-aes-neonbs",
-	.base.cra_priority	= 250 - 1,
-	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct aesbs_ctr_ctx),
-	.base.cra_module	= THIS_MODULE,
-
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.chunksize		= AES_BLOCK_SIZE,
-	.walksize		= 8 * AES_BLOCK_SIZE,
-	.ivsize			= AES_BLOCK_SIZE,
-	.setkey			= aesbs_ctr_setkey_sync,
-	.encrypt		= ctr_encrypt_sync,
-	.decrypt		= ctr_encrypt_sync,
-}, {
-	.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,
 
 	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
 	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
@@ -512,54 +453,17 @@ 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 (!cpu_have_named_feature(ASIMD))
 		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));
 }
 
 module_init(aes_init);