crypto: qat - move temp buffers off the stack

Arnd reports that with Kees's latest VLA patches applied, the HMAC
handling in the QAT driver uses a worst case estimate of 160 bytes
for the SHA blocksize, allowing the compiler to determine the size
of the stack frame at compile time and throw a warning:

  drivers/crypto/qat/qat_common/qat_algs.c: In function 'qat_alg_do_precomputes':
  drivers/crypto/qat/qat_common/qat_algs.c:257:1: error: the frame size
  of 1112 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]

Given that this worst case estimate is only 32 bytes larger than the
actual block size of SHA-512, the use of a VLA here was hiding the
excessive size of the stack frame from the compiler, and so we should
try to move these buffers off the stack.

So move the ipad/opad buffers and the various SHA state descriptors
into the tfm context struct. Since qat_alg_do_precomputes() is only
called in the context of a setkey() operation, this should be safe.
Using SHA512_BLOCK_SIZE for the size of the ipad/opad buffers allows
them to be used by SHA-1/SHA-256 as well.

Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

drivers/crypto/qat/qat_common/qat_algs.c

@@ -113,6 +113,13 @@ struct qat_alg_aead_ctx {
 	struct crypto_shash *hash_tfm;
 	enum icp_qat_hw_auth_algo qat_hash_alg;
 	struct qat_crypto_instance *inst;
+	union {
+		struct sha1_state sha1;
+		struct sha256_state sha256;
+		struct sha512_state sha512;
+	};
+	char ipad[SHA512_BLOCK_SIZE]; /* sufficient for SHA-1/SHA-256 as well */
+	char opad[SHA512_BLOCK_SIZE];
 };
 
 struct qat_alg_ablkcipher_ctx {
@@ -148,41 +155,32 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 				  unsigned int auth_keylen)
 {
 	SHASH_DESC_ON_STACK(shash, ctx->hash_tfm);
-	struct sha1_state sha1;
-	struct sha256_state sha256;
-	struct sha512_state sha512;
 	int block_size = crypto_shash_blocksize(ctx->hash_tfm);
 	int digest_size = crypto_shash_digestsize(ctx->hash_tfm);
-	char ipad[MAX_ALGAPI_BLOCKSIZE];
-	char opad[MAX_ALGAPI_BLOCKSIZE];
 	__be32 *hash_state_out;
 	__be64 *hash512_state_out;
 	int i, offset;
 
-	memset(ipad, 0, block_size);
-	memset(opad, 0, block_size);
+	memset(ctx->ipad, 0, block_size);
+	memset(ctx->opad, 0, block_size);
 	shash->tfm = ctx->hash_tfm;
 	shash->flags = 0x0;
 
-	if (WARN_ON(block_size > sizeof(ipad) ||
-		    sizeof(ipad) != sizeof(opad)))
-		return -EINVAL;
-
 	if (auth_keylen > block_size) {
 		int ret = crypto_shash_digest(shash, auth_key,
-					      auth_keylen, ipad);
+					      auth_keylen, ctx->ipad);
 		if (ret)
 			return ret;
 
-		memcpy(opad, ipad, digest_size);
+		memcpy(ctx->opad, ctx->ipad, digest_size);
 	} else {
-		memcpy(ipad, auth_key, auth_keylen);
-		memcpy(opad, auth_key, auth_keylen);
+		memcpy(ctx->ipad, auth_key, auth_keylen);
+		memcpy(ctx->opad, auth_key, auth_keylen);
 	}
 
 	for (i = 0; i < block_size; i++) {
-		char *ipad_ptr = ipad + i;
-		char *opad_ptr = opad + i;
+		char *ipad_ptr = ctx->ipad + i;
+		char *opad_ptr = ctx->opad + i;
 		*ipad_ptr ^= HMAC_IPAD_VALUE;
 		*opad_ptr ^= HMAC_OPAD_VALUE;
 	}
@@ -190,7 +188,7 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 	if (crypto_shash_init(shash))
 		return -EFAULT;
 
-	if (crypto_shash_update(shash, ipad, block_size))
+	if (crypto_shash_update(shash, ctx->ipad, block_size))
 		return -EFAULT;
 
 	hash_state_out = (__be32 *)hash->sha.state1;
@@ -198,22 +196,22 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 
 	switch (ctx->qat_hash_alg) {
 	case ICP_QAT_HW_AUTH_ALGO_SHA1:
-		if (crypto_shash_export(shash, &sha1))
+		if (crypto_shash_export(shash, &ctx->sha1))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
-			*hash_state_out = cpu_to_be32(*(sha1.state + i));
+			*hash_state_out = cpu_to_be32(ctx->sha1.state[i]);
 		break;
 	case ICP_QAT_HW_AUTH_ALGO_SHA256:
-		if (crypto_shash_export(shash, &sha256))
+		if (crypto_shash_export(shash, &ctx->sha256))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
-			*hash_state_out = cpu_to_be32(*(sha256.state + i));
+			*hash_state_out = cpu_to_be32(ctx->sha256.state[i]);
 		break;
 	case ICP_QAT_HW_AUTH_ALGO_SHA512:
-		if (crypto_shash_export(shash, &sha512))
+		if (crypto_shash_export(shash, &ctx->sha512))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 3; i++, hash512_state_out++)
-			*hash512_state_out = cpu_to_be64(*(sha512.state + i));
+			*hash512_state_out = cpu_to_be64(ctx->sha512.state[i]);
 		break;
 	default:
 		return -EFAULT;
@@ -222,7 +220,7 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 	if (crypto_shash_init(shash))
 		return -EFAULT;
 
-	if (crypto_shash_update(shash, opad, block_size))
+	if (crypto_shash_update(shash, ctx->opad, block_size))
 		return -EFAULT;
 
 	offset = round_up(qat_get_inter_state_size(ctx->qat_hash_alg), 8);
@@ -231,28 +229,28 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 
 	switch (ctx->qat_hash_alg) {
 	case ICP_QAT_HW_AUTH_ALGO_SHA1:
-		if (crypto_shash_export(shash, &sha1))
+		if (crypto_shash_export(shash, &ctx->sha1))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
-			*hash_state_out = cpu_to_be32(*(sha1.state + i));
+			*hash_state_out = cpu_to_be32(ctx->sha1.state[i]);
 		break;
 	case ICP_QAT_HW_AUTH_ALGO_SHA256:
-		if (crypto_shash_export(shash, &sha256))
+		if (crypto_shash_export(shash, &ctx->sha256))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
-			*hash_state_out = cpu_to_be32(*(sha256.state + i));
+			*hash_state_out = cpu_to_be32(ctx->sha256.state[i]);
 		break;
 	case ICP_QAT_HW_AUTH_ALGO_SHA512:
-		if (crypto_shash_export(shash, &sha512))
+		if (crypto_shash_export(shash, &ctx->sha512))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 3; i++, hash512_state_out++)
-			*hash512_state_out = cpu_to_be64(*(sha512.state + i));
+			*hash512_state_out = cpu_to_be64(ctx->sha512.state[i]);
 		break;
 	default:
 		return -EFAULT;
 	}
-	memzero_explicit(ipad, block_size);
-	memzero_explicit(opad, block_size);
+	memzero_explicit(ctx->ipad, block_size);
+	memzero_explicit(ctx->opad, block_size);
 	return 0;
 }