From:   Eric Biggers <ebiggers@kernel.org>
To:     linux-crypto@vger.kernel.org,
        Herbert Xu <herbert@gondor.apana.org.au>
Cc:     linux-kernel@vger.kernel.org,
        "Jason A . Donenfeld" <Jason@zx2c4.com>, stable@vger.kernel.org,
        Ondrej Mosnacek <omosnace@redhat.com>
Subject: [RFC/RFT PATCH 04/15] crypto: x86/morus - fix handling chunked inputs and MAY_SLEEP
Date:   Wed, 23 Jan 2019 14:49:15 -0800
Message-Id: <20190123224926.250525-5-ebiggers@kernel.org>
In-Reply-To: <20190123224926.250525-1-ebiggers@kernel.org>
References: <20190123224926.250525-1-ebiggers@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-crypto-owner@vger.kernel.org
Precedence: bulk

From: Eric Biggers <ebiggers@google.com>

The x86 MORUS implementations all fail the improved AEAD tests because
they produce the wrong result with some data layouts.  Also, when the
MAY_SLEEP flag is given, they can sleep in the skcipher_walk_*()
functions while preemption is disabled by kernel_fpu_begin().

Fix these bugs.

Fixes: 56e8e57fc3a7 ("crypto: morus - Add common SIMD glue code for MORUS")
Cc: <stable@vger.kernel.org> # v4.18+
Cc: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 arch/x86/crypto/morus1280_glue.c | 40 +++++++++++++-------------------
 arch/x86/crypto/morus640_glue.c  | 39 ++++++++++++-------------------
 2 files changed, 31 insertions(+), 48 deletions(-)

diff --git a/arch/x86/crypto/morus1280_glue.c b/arch/x86/crypto/morus1280_glue.c
index 0dccdda1eb3a..7e600f8bcdad 100644
--- a/arch/x86/crypto/morus1280_glue.c
+++ b/arch/x86/crypto/morus1280_glue.c
@@ -85,31 +85,20 @@ static void crypto_morus1280_glue_process_ad(
 
 static void crypto_morus1280_glue_process_crypt(struct morus1280_state *state,
 						struct morus1280_ops ops,
-						struct aead_request *req)
+						struct skcipher_walk *walk)
 {
-	struct skcipher_walk walk;
-	u8 *cursor_src, *cursor_dst;
-	unsigned int chunksize, base;
-
-	ops.skcipher_walk_init(&walk, req, false);
-
-	while (walk.nbytes) {
-		cursor_src = walk.src.virt.addr;
-		cursor_dst = walk.dst.virt.addr;
-		chunksize = walk.nbytes;
-
-		ops.crypt_blocks(state, cursor_src, cursor_dst, chunksize);
-
-		base = chunksize & ~(MORUS1280_BLOCK_SIZE - 1);
-		cursor_src += base;
-		cursor_dst += base;
-		chunksize &= MORUS1280_BLOCK_SIZE - 1;
-
-		if (chunksize > 0)
-			ops.crypt_tail(state, cursor_src, cursor_dst,
-				       chunksize);
+	while (walk->nbytes >= MORUS1280_BLOCK_SIZE) {
+		ops.crypt_blocks(state, walk->src.virt.addr,
+				 walk->dst.virt.addr,
+				 round_down(walk->nbytes,
+					    MORUS1280_BLOCK_SIZE));
+		skcipher_walk_done(walk, walk->nbytes % MORUS1280_BLOCK_SIZE);
+	}
 
-		skcipher_walk_done(&walk, 0);
+	if (walk->nbytes) {
+		ops.crypt_tail(state, walk->src.virt.addr, walk->dst.virt.addr,
+			       walk->nbytes);
+		skcipher_walk_done(walk, 0);
 	}
 }
 
@@ -147,12 +136,15 @@ static void crypto_morus1280_glue_crypt(struct aead_request *req,
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct morus1280_ctx *ctx = crypto_aead_ctx(tfm);
 	struct morus1280_state state;
+	struct skcipher_walk walk;
+
+	ops.skcipher_walk_init(&walk, req, true);
 
 	kernel_fpu_begin();
 
 	ctx->ops->init(&state, &ctx->key, req->iv);
 	crypto_morus1280_glue_process_ad(&state, ctx->ops, req->src, req->assoclen);
-	crypto_morus1280_glue_process_crypt(&state, ops, req);
+	crypto_morus1280_glue_process_crypt(&state, ops, &walk);
 	ctx->ops->final(&state, tag_xor, req->assoclen, cryptlen);
 
 	kernel_fpu_end();
diff --git a/arch/x86/crypto/morus640_glue.c b/arch/x86/crypto/morus640_glue.c
index 7b58fe4d9bd1..cb3a81732016 100644
--- a/arch/x86/crypto/morus640_glue.c
+++ b/arch/x86/crypto/morus640_glue.c
@@ -85,31 +85,19 @@ static void crypto_morus640_glue_process_ad(
 
 static void crypto_morus640_glue_process_crypt(struct morus640_state *state,
 					       struct morus640_ops ops,
-					       struct aead_request *req)
+					       struct skcipher_walk *walk)
 {
-	struct skcipher_walk walk;
-	u8 *cursor_src, *cursor_dst;
-	unsigned int chunksize, base;
-
-	ops.skcipher_walk_init(&walk, req, false);
-
-	while (walk.nbytes) {
-		cursor_src = walk.src.virt.addr;
-		cursor_dst = walk.dst.virt.addr;
-		chunksize = walk.nbytes;
-
-		ops.crypt_blocks(state, cursor_src, cursor_dst, chunksize);
-
-		base = chunksize & ~(MORUS640_BLOCK_SIZE - 1);
-		cursor_src += base;
-		cursor_dst += base;
-		chunksize &= MORUS640_BLOCK_SIZE - 1;
-
-		if (chunksize > 0)
-			ops.crypt_tail(state, cursor_src, cursor_dst,
-				       chunksize);
+	while (walk->nbytes >= MORUS640_BLOCK_SIZE) {
+		ops.crypt_blocks(state, walk->src.virt.addr,
+				 walk->dst.virt.addr,
+				 round_down(walk->nbytes, MORUS640_BLOCK_SIZE));
+		skcipher_walk_done(walk, walk->nbytes % MORUS640_BLOCK_SIZE);
+	}
 
-		skcipher_walk_done(&walk, 0);
+	if (walk->nbytes) {
+		ops.crypt_tail(state, walk->src.virt.addr, walk->dst.virt.addr,
+			       walk->nbytes);
+		skcipher_walk_done(walk, 0);
 	}
 }
 
@@ -143,12 +131,15 @@ static void crypto_morus640_glue_crypt(struct aead_request *req,
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct morus640_ctx *ctx = crypto_aead_ctx(tfm);
 	struct morus640_state state;
+	struct skcipher_walk walk;
+
+	ops.skcipher_walk_init(&walk, req, true);
 
 	kernel_fpu_begin();
 
 	ctx->ops->init(&state, &ctx->key, req->iv);
 	crypto_morus640_glue_process_ad(&state, ctx->ops, req->src, req->assoclen);
-	crypto_morus640_glue_process_crypt(&state, ops, req);
+	crypto_morus640_glue_process_crypt(&state, ops, &walk);
 	ctx->ops->final(&state, tag_xor, req->assoclen, cryptlen);
 
 	kernel_fpu_end();
-- 
2.20.1.321.g9e740568ce-goog