crypto: arm64/aes - implement support for XTS ciphertext stealing

Add the missing support for ciphertext stealing in the implementation
of AES-XTS, which is part of the XTS specification but was omitted up
until now due to lack of a need for it.

The asm helpers are updated so they can deal with any input size, as
long as the last full block and the final partial block are presented
at the same time. The glue code is updated so that the common case of
operating on a sector or page is mostly as before. When CTS is needed,
the walk is split up into two pieces, unless the entire input is covered
by a single step.

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

1 files changed, 114 insertions, 12 deletions

diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index e78f69b81dfc..23ee7c85c0b7 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -90,10 +90,10 @@ asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[],
 				int rounds, int blocks, u8 ctr[]);
 
 asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u32 const rk1[],
-				int rounds, int blocks, u32 const rk2[], u8 iv[],
+				int rounds, int bytes, u32 const rk2[], u8 iv[],
 				int first);
 asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u32 const rk1[],
-				int rounds, int blocks, u32 const rk2[], u8 iv[],
+				int rounds, int bytes, u32 const rk2[], u8 iv[],
 				int first);
 
 asmlinkage void aes_essiv_cbc_encrypt(u8 out[], u8 const in[], u32 const rk1[],
@@ -527,21 +527,71 @@ static int __maybe_unused xts_encrypt(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int err, first, rounds = 6 + ctx->key1.key_length / 4;
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct scatterlist *src, *dst;
 	struct skcipher_walk walk;
-	unsigned int blocks;
+
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
 
 	err = skcipher_walk_virt(&walk, req, false);
 
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
+		int xts_blocks = DIV_ROUND_UP(req->cryptlen,
+					      AES_BLOCK_SIZE) - 2;
+
+		skcipher_walk_abort(&walk);
+
+		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,
+					   xts_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+		req = &subreq;
+		err = skcipher_walk_virt(&walk, req, false);
+	} else {
+		tail = 0;
+	}
+
+	for (first = 1; walk.nbytes >= AES_BLOCK_SIZE; first = 0) {
+		int nbytes = walk.nbytes;
+
+		if (walk.nbytes < walk.total)
+			nbytes &= ~(AES_BLOCK_SIZE - 1);
+
 		kernel_neon_begin();
 		aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				ctx->key1.key_enc, rounds, blocks,
+				ctx->key1.key_enc, rounds, nbytes,
 				ctx->key2.key_enc, walk.iv, first);
 		kernel_neon_end();
-		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
-	return err;
+	if (err || likely(!tail))
+		return err;
+
+	dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+	if (req->dst != req->src)
+		dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+
+	skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+	kernel_neon_begin();
+	aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+			ctx->key1.key_enc, rounds, walk.nbytes,
+			ctx->key2.key_enc, walk.iv, first);
+	kernel_neon_end();
+
+	return skcipher_walk_done(&walk, 0);
 }
 
 static int __maybe_unused xts_decrypt(struct skcipher_request *req)
@@ -549,21 +599,72 @@ static int __maybe_unused xts_decrypt(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int err, first, rounds = 6 + ctx->key1.key_length / 4;
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct scatterlist *src, *dst;
 	struct skcipher_walk walk;
-	unsigned int blocks;
+
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
 
 	err = skcipher_walk_virt(&walk, req, false);
 
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
+		int xts_blocks = DIV_ROUND_UP(req->cryptlen,
+					      AES_BLOCK_SIZE) - 2;
+
+		skcipher_walk_abort(&walk);
+
+		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,
+					   xts_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+		req = &subreq;
+		err = skcipher_walk_virt(&walk, req, false);
+	} else {
+		tail = 0;
+	}
+
+	for (first = 1; walk.nbytes >= AES_BLOCK_SIZE; first = 0) {
+		int nbytes = walk.nbytes;
+
+		if (walk.nbytes < walk.total)
+			nbytes &= ~(AES_BLOCK_SIZE - 1);
+
 		kernel_neon_begin();
 		aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				ctx->key1.key_dec, rounds, blocks,
+				ctx->key1.key_dec, rounds, nbytes,
 				ctx->key2.key_enc, walk.iv, first);
 		kernel_neon_end();
-		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
-	return err;
+	if (err || likely(!tail))
+		return err;
+
+	dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+	if (req->dst != req->src)
+		dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+
+	skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+
+	kernel_neon_begin();
+	aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+			ctx->key1.key_dec, rounds, walk.nbytes,
+			ctx->key2.key_enc, walk.iv, first);
+	kernel_neon_end();
+
+	return skcipher_walk_done(&walk, 0);
 }
 
 static struct skcipher_alg aes_algs[] = { {
@@ -644,6 +745,7 @@ static struct skcipher_alg aes_algs[] = { {
 	.min_keysize	= 2 * AES_MIN_KEY_SIZE,
 	.max_keysize	= 2 * AES_MAX_KEY_SIZE,
 	.ivsize		= AES_BLOCK_SIZE,
+	.walksize	= 2 * AES_BLOCK_SIZE,
 	.setkey		= xts_set_key,
 	.encrypt	= xts_encrypt,
 	.decrypt	= xts_decrypt,