crypto: aesni - implement support for cts(cbc(aes))

Follow the same approach as the arm64 driver for implementing a version
of AES-NI in CBC mode that supports ciphertext stealing. This results in
a ~2x speed increase for relatively short inputs (less than 256 bytes),
which is relevant given that AES-CBC with ciphertext stealing is used
for filename encryption in the fscrypt layer. For larger inputs, the
speedup is still significant (~25% on decryption, ~6% on encryption)

Tested-by: Eric Biggers <ebiggers@google.com> # x86_64
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 133 insertions, 0 deletions

diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index ad8a7188a2bf..96bdc1584215 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -93,6 +93,10 @@ asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv);
 asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv);
+asmlinkage void aesni_cts_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out,
+				  const u8 *in, unsigned int len, u8 *iv);
+asmlinkage void aesni_cts_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
+				  const u8 *in, unsigned int len, u8 *iv);
 
 #define AVX_GEN2_OPTSIZE 640
 #define AVX_GEN4_OPTSIZE 4096
@@ -454,6 +458,118 @@ static int cbc_decrypt(struct skcipher_request *req)
 	return err;
 }
 
+static int cts_cbc_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
+	int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+	struct scatterlist *src = req->src, *dst = req->dst;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct skcipher_walk walk;
+	int err;
+
+	skcipher_request_set_tfm(&subreq, tfm);
+	skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
+				      NULL, NULL);
+
+	if (req->cryptlen <= AES_BLOCK_SIZE) {
+		if (req->cryptlen < AES_BLOCK_SIZE)
+			return -EINVAL;
+		cbc_blocks = 1;
+	}
+
+	if (cbc_blocks > 0) {
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   cbc_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+
+		err = cbc_encrypt(&subreq);
+		if (err)
+			return err;
+
+		if (req->cryptlen == AES_BLOCK_SIZE)
+			return 0;
+
+		dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
+		if (req->dst != req->src)
+			dst = scatterwalk_ffwd(sg_dst, req->dst,
+					       subreq.cryptlen);
+	}
+
+	/* handle ciphertext stealing */
+	skcipher_request_set_crypt(&subreq, src, dst,
+				   req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+	kernel_fpu_begin();
+	aesni_cts_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+			  walk.nbytes, walk.iv);
+	kernel_fpu_end();
+
+	return skcipher_walk_done(&walk, 0);
+}
+
+static int cts_cbc_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
+	int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+	struct scatterlist *src = req->src, *dst = req->dst;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct skcipher_walk walk;
+	int err;
+
+	skcipher_request_set_tfm(&subreq, tfm);
+	skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
+				      NULL, NULL);
+
+	if (req->cryptlen <= AES_BLOCK_SIZE) {
+		if (req->cryptlen < AES_BLOCK_SIZE)
+			return -EINVAL;
+		cbc_blocks = 1;
+	}
+
+	if (cbc_blocks > 0) {
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   cbc_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+
+		err = cbc_decrypt(&subreq);
+		if (err)
+			return err;
+
+		if (req->cryptlen == AES_BLOCK_SIZE)
+			return 0;
+
+		dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
+		if (req->dst != req->src)
+			dst = scatterwalk_ffwd(sg_dst, req->dst,
+					       subreq.cryptlen);
+	}
+
+	/* handle ciphertext stealing */
+	skcipher_request_set_crypt(&subreq, src, dst,
+				   req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+	kernel_fpu_begin();
+	aesni_cts_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+			  walk.nbytes, walk.iv);
+	kernel_fpu_end();
+
+	return skcipher_walk_done(&walk, 0);
+}
+
 #ifdef CONFIG_X86_64
 static void ctr_crypt_final(struct crypto_aes_ctx *ctx,
 			    struct skcipher_walk *walk)
@@ -928,6 +1044,23 @@ static struct skcipher_alg aesni_skciphers[] = {
 		.setkey		= aesni_skcipher_setkey,
 		.encrypt	= cbc_encrypt,
 		.decrypt	= cbc_decrypt,
+	}, {
+		.base = {
+			.cra_name		= "__cts(cbc(aes))",
+			.cra_driver_name	= "__cts-cbc-aes-aesni",
+			.cra_priority		= 400,
+			.cra_flags		= CRYPTO_ALG_INTERNAL,
+			.cra_blocksize		= AES_BLOCK_SIZE,
+			.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
+			.cra_module		= THIS_MODULE,
+		},
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.walksize	= 2 * AES_BLOCK_SIZE,
+		.setkey		= aesni_skcipher_setkey,
+		.encrypt	= cts_cbc_encrypt,
+		.decrypt	= cts_cbc_decrypt,
 #ifdef CONFIG_X86_64
 	}, {
 		.base = {