From af5034e8e4a5838fc77e476c1a91822e449d5869 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 30 Dec 2019 21:19:38 -0600
Subject: crypto: remove propagation of CRYPTO_TFM_RES_* flags

The CRYPTO_TFM_RES_* flags were apparently meant as a way to make the
->setkey() functions provide more information about errors.  But these
flags weren't actually being used or tested, and in many cases they
weren't being set correctly anyway.  So they've now been removed.

Also, if someone ever actually needs to start better distinguishing
->setkey() errors (which is somewhat unlikely, as this has been unneeded
for a long time), we'd be much better off just defining different return
values, like -EINVAL if the key is invalid for the algorithm vs.
-EKEYREJECTED if the key was rejected by a policy like "no weak keys".
That would be much simpler, less error-prone, and easier to test.

So just remove CRYPTO_TFM_RES_MASK and all the unneeded logic that
propagates these flags around.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/adiantum.c | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'crypto/adiantum.c')

diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index aded26092268..30cffb45b88f 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -135,9 +135,6 @@ static int adiantum_setkey(struct crypto_skcipher *tfm, const u8 *key,
 				  crypto_skcipher_get_flags(tfm) &
 				  CRYPTO_TFM_REQ_MASK);
 	err = crypto_skcipher_setkey(tctx->streamcipher, key, keylen);
-	crypto_skcipher_set_flags(tfm,
-				crypto_skcipher_get_flags(tctx->streamcipher) &
-				CRYPTO_TFM_RES_MASK);
 	if (err)
 		return err;
 
@@ -167,9 +164,6 @@ static int adiantum_setkey(struct crypto_skcipher *tfm, const u8 *key,
 				CRYPTO_TFM_REQ_MASK);
 	err = crypto_cipher_setkey(tctx->blockcipher, keyp,
 				   BLOCKCIPHER_KEY_SIZE);
-	crypto_skcipher_set_flags(tfm,
-				  crypto_cipher_get_flags(tctx->blockcipher) &
-				  CRYPTO_TFM_RES_MASK);
 	if (err)
 		goto out;
 	keyp += BLOCKCIPHER_KEY_SIZE;
@@ -182,8 +176,6 @@ static int adiantum_setkey(struct crypto_skcipher *tfm, const u8 *key,
 	crypto_shash_set_flags(tctx->hash, crypto_skcipher_get_flags(tfm) &
 					   CRYPTO_TFM_REQ_MASK);
 	err = crypto_shash_setkey(tctx->hash, keyp, NHPOLY1305_KEY_SIZE);
-	crypto_skcipher_set_flags(tfm, crypto_shash_get_flags(tctx->hash) &
-				       CRYPTO_TFM_RES_MASK);
 	keyp += NHPOLY1305_KEY_SIZE;
 	WARN_ON(keyp != &data->derived_keys[ARRAY_SIZE(data->derived_keys)]);
 out:
-- 
cgit v1.2.3


From b9f76dddb1f9f70e008b982381bbc9a67c9b8c66 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 2 Jan 2020 19:58:45 -0800
Subject: crypto: skcipher - pass instance to crypto_grab_skcipher()

Initializing a crypto_skcipher_spawn currently requires:

1. Set spawn->base.inst to point to the instance.
2. Call crypto_grab_skcipher().

But there's no reason for these steps to be separate, and in fact this
unneeded complication has caused at least one bug, the one fixed by
commit 6db43410179b ("crypto: adiantum - initialize crypto_spawn::inst")

So just make crypto_grab_skcipher() take the instance as an argument.

To keep the function calls from getting too unwieldy due to this extra
argument, also introduce a 'mask' variable into the affected places
which weren't already using one.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/adiantum.c                  | 11 ++++++-----
 crypto/authenc.c                   | 12 ++++++------
 crypto/authencesn.c                | 12 ++++++------
 crypto/ccm.c                       |  9 +++++----
 crypto/chacha20poly1305.c          | 13 ++++++-------
 crypto/cryptd.c                    |  4 ++--
 crypto/ctr.c                       |  4 ++--
 crypto/cts.c                       |  9 +++++----
 crypto/essiv.c                     | 13 +++++--------
 crypto/gcm.c                       | 13 ++++++-------
 crypto/lrw.c                       | 15 ++++++++-------
 crypto/skcipher.c                  |  4 +++-
 crypto/xts.c                       |  9 +++++----
 include/crypto/internal/skcipher.h | 11 +++--------
 14 files changed, 68 insertions(+), 71 deletions(-)

(limited to 'crypto/adiantum.c')

diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index 30cffb45b88f..567071464fab 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -493,6 +493,7 @@ static bool adiantum_supported_algorithms(struct skcipher_alg *streamcipher_alg,
 static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
+	u32 mask;
 	const char *streamcipher_name;
 	const char *blockcipher_name;
 	const char *nhpoly1305_name;
@@ -511,6 +512,8 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
 	if ((algt->type ^ CRYPTO_ALG_TYPE_SKCIPHER) & algt->mask)
 		return -EINVAL;
 
+	mask = crypto_requires_sync(algt->type, algt->mask);
+
 	streamcipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(streamcipher_name))
 		return PTR_ERR(streamcipher_name);
@@ -531,11 +534,9 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
 	ictx = skcipher_instance_ctx(inst);
 
 	/* Stream cipher, e.g. "xchacha12" */
-	crypto_set_skcipher_spawn(&ictx->streamcipher_spawn,
-				  skcipher_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ictx->streamcipher_spawn, streamcipher_name,
-				   0, crypto_requires_sync(algt->type,
-							   algt->mask));
+	err = crypto_grab_skcipher(&ictx->streamcipher_spawn,
+				   skcipher_crypto_instance(inst),
+				   streamcipher_name, 0, mask);
 	if (err)
 		goto out_free_inst;
 	streamcipher_alg = crypto_spawn_skcipher_alg(&ictx->streamcipher_spawn);
diff --git a/crypto/authenc.c b/crypto/authenc.c
index 15aaddd34171..e31bcec58564 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -373,6 +373,7 @@ static int crypto_authenc_create(struct crypto_template *tmpl,
 				 struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
+	u32 mask;
 	struct aead_instance *inst;
 	struct hash_alg_common *auth;
 	struct crypto_alg *auth_base;
@@ -388,9 +389,10 @@ static int crypto_authenc_create(struct crypto_template *tmpl,
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
 		return -EINVAL;
 
+	mask = crypto_requires_sync(algt->type, algt->mask);
+
 	auth = ahash_attr_alg(tb[1], CRYPTO_ALG_TYPE_HASH,
-			      CRYPTO_ALG_TYPE_AHASH_MASK |
-			      crypto_requires_sync(algt->type, algt->mask));
+			      CRYPTO_ALG_TYPE_AHASH_MASK | mask);
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
@@ -413,10 +415,8 @@ static int crypto_authenc_create(struct crypto_template *tmpl,
 	if (err)
 		goto err_free_inst;
 
-	crypto_set_skcipher_spawn(&ctx->enc, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->enc, enc_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher(&ctx->enc, aead_crypto_instance(inst),
+				   enc_name, 0, mask);
 	if (err)
 		goto err_drop_auth;
 
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index fc81324ce881..83bda7f905bb 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -391,6 +391,7 @@ static int crypto_authenc_esn_create(struct crypto_template *tmpl,
 				     struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
+	u32 mask;
 	struct aead_instance *inst;
 	struct hash_alg_common *auth;
 	struct crypto_alg *auth_base;
@@ -406,9 +407,10 @@ static int crypto_authenc_esn_create(struct crypto_template *tmpl,
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
 		return -EINVAL;
 
+	mask = crypto_requires_sync(algt->type, algt->mask);
+
 	auth = ahash_attr_alg(tb[1], CRYPTO_ALG_TYPE_HASH,
-			      CRYPTO_ALG_TYPE_AHASH_MASK |
-			      crypto_requires_sync(algt->type, algt->mask));
+			      CRYPTO_ALG_TYPE_AHASH_MASK | mask);
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
@@ -431,10 +433,8 @@ static int crypto_authenc_esn_create(struct crypto_template *tmpl,
 	if (err)
 		goto err_free_inst;
 
-	crypto_set_skcipher_spawn(&ctx->enc, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->enc, enc_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher(&ctx->enc, aead_crypto_instance(inst),
+				   enc_name, 0, mask);
 	if (err)
 		goto err_drop_auth;
 
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 44104524e95a..4414f0ddfe5a 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -450,6 +450,7 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
 				    const char *mac_name)
 {
 	struct crypto_attr_type *algt;
+	u32 mask;
 	struct aead_instance *inst;
 	struct skcipher_alg *ctr;
 	struct crypto_alg *mac_alg;
@@ -464,6 +465,8 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
 		return -EINVAL;
 
+	mask = crypto_requires_sync(algt->type, algt->mask);
+
 	mac_alg = crypto_find_alg(mac_name, &crypto_ahash_type,
 				  CRYPTO_ALG_TYPE_HASH,
 				  CRYPTO_ALG_TYPE_AHASH_MASK |
@@ -488,10 +491,8 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
 	if (err)
 		goto err_free_inst;
 
-	crypto_set_skcipher_spawn(&ictx->ctr, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ictx->ctr, ctr_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher(&ictx->ctr, aead_crypto_instance(inst),
+				   ctr_name, 0, mask);
 	if (err)
 		goto err_drop_mac;
 
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
index 88cbdaba43b8..09d5a34ab339 100644
--- a/crypto/chacha20poly1305.c
+++ b/crypto/chacha20poly1305.c
@@ -558,6 +558,7 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 			     const char *name, unsigned int ivsize)
 {
 	struct crypto_attr_type *algt;
+	u32 mask;
 	struct aead_instance *inst;
 	struct skcipher_alg *chacha;
 	struct crypto_alg *poly;
@@ -576,6 +577,8 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
 		return -EINVAL;
 
+	mask = crypto_requires_sync(algt->type, algt->mask);
+
 	chacha_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(chacha_name))
 		return PTR_ERR(chacha_name);
@@ -585,9 +588,7 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 
 	poly = crypto_find_alg(poly_name, &crypto_ahash_type,
 			       CRYPTO_ALG_TYPE_HASH,
-			       CRYPTO_ALG_TYPE_AHASH_MASK |
-			       crypto_requires_sync(algt->type,
-						    algt->mask));
+			       CRYPTO_ALG_TYPE_AHASH_MASK | mask);
 	if (IS_ERR(poly))
 		return PTR_ERR(poly);
 	poly_hash = __crypto_hash_alg_common(poly);
@@ -608,10 +609,8 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 	if (err)
 		goto err_free_inst;
 
-	crypto_set_skcipher_spawn(&ctx->chacha, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->chacha, chacha_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher(&ctx->chacha, aead_crypto_instance(inst),
+				   chacha_name, 0, mask);
 	if (err)
 		goto err_drop_poly;
 
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index cd94243a1605..a0fe10624cfd 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -416,8 +416,8 @@ static int cryptd_create_skcipher(struct crypto_template *tmpl,
 	ctx = skcipher_instance_ctx(inst);
 	ctx->queue = queue;
 
-	crypto_set_skcipher_spawn(&ctx->spawn, skcipher_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->spawn, name, type, mask);
+	err = crypto_grab_skcipher(&ctx->spawn, skcipher_crypto_instance(inst),
+				   name, type, mask);
 	if (err)
 		goto out_free_inst;
 
diff --git a/crypto/ctr.c b/crypto/ctr.c
index b63b19de68a9..a8feab621c6c 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -286,8 +286,8 @@ static int crypto_rfc3686_create(struct crypto_template *tmpl,
 
 	spawn = skcipher_instance_ctx(inst);
 
-	crypto_set_skcipher_spawn(spawn, skcipher_crypto_instance(inst));
-	err = crypto_grab_skcipher(spawn, cipher_name, 0, mask);
+	err = crypto_grab_skcipher(spawn, skcipher_crypto_instance(inst),
+				   cipher_name, 0, mask);
 	if (err)
 		goto err_free_inst;
 
diff --git a/crypto/cts.c b/crypto/cts.c
index a0bb994f8b11..48188adc8e91 100644
--- a/crypto/cts.c
+++ b/crypto/cts.c
@@ -328,6 +328,7 @@ static int crypto_cts_create(struct crypto_template *tmpl, struct rtattr **tb)
 	struct crypto_attr_type *algt;
 	struct skcipher_alg *alg;
 	const char *cipher_name;
+	u32 mask;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
@@ -337,6 +338,8 @@ static int crypto_cts_create(struct crypto_template *tmpl, struct rtattr **tb)
 	if ((algt->type ^ CRYPTO_ALG_TYPE_SKCIPHER) & algt->mask)
 		return -EINVAL;
 
+	mask = crypto_requires_sync(algt->type, algt->mask);
+
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
 		return PTR_ERR(cipher_name);
@@ -347,10 +350,8 @@ static int crypto_cts_create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	spawn = skcipher_instance_ctx(inst);
 
-	crypto_set_skcipher_spawn(spawn, skcipher_crypto_instance(inst));
-	err = crypto_grab_skcipher(spawn, cipher_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher(spawn, skcipher_crypto_instance(inst),
+				   cipher_name, 0, mask);
 	if (err)
 		goto err_free_inst;
 
diff --git a/crypto/essiv.c b/crypto/essiv.c
index 61d9000ae4ad..0e45f5b4f67f 100644
--- a/crypto/essiv.c
+++ b/crypto/essiv.c
@@ -452,6 +452,7 @@ static int essiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 	struct shash_alg *hash_alg;
 	int ivsize;
 	u32 type;
+	u32 mask;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
@@ -467,6 +468,7 @@ static int essiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 		return PTR_ERR(shash_name);
 
 	type = algt->type & algt->mask;
+	mask = crypto_requires_sync(algt->type, algt->mask);
 
 	switch (type) {
 	case CRYPTO_ALG_TYPE_SKCIPHER:
@@ -479,11 +481,8 @@ static int essiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 		ictx = crypto_instance_ctx(inst);
 
 		/* Symmetric cipher, e.g., "cbc(aes)" */
-		crypto_set_skcipher_spawn(&ictx->u.skcipher_spawn, inst);
-		err = crypto_grab_skcipher(&ictx->u.skcipher_spawn,
-					   inner_cipher_name, 0,
-					   crypto_requires_sync(algt->type,
-								algt->mask));
+		err = crypto_grab_skcipher(&ictx->u.skcipher_spawn, inst,
+					   inner_cipher_name, 0, mask);
 		if (err)
 			goto out_free_inst;
 		skcipher_alg = crypto_spawn_skcipher_alg(&ictx->u.skcipher_spawn);
@@ -503,9 +502,7 @@ static int essiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 		/* AEAD cipher, e.g., "authenc(hmac(sha256),cbc(aes))" */
 		crypto_set_aead_spawn(&ictx->u.aead_spawn, inst);
 		err = crypto_grab_aead(&ictx->u.aead_spawn,
-				       inner_cipher_name, 0,
-				       crypto_requires_sync(algt->type,
-							    algt->mask));
+				       inner_cipher_name, 0, mask);
 		if (err)
 			goto out_free_inst;
 		aead_alg = crypto_spawn_aead_alg(&ictx->u.aead_spawn);
diff --git a/crypto/gcm.c b/crypto/gcm.c
index 7041cb1b6fd5..887f472734b6 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -580,6 +580,7 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 				    const char *ghash_name)
 {
 	struct crypto_attr_type *algt;
+	u32 mask;
 	struct aead_instance *inst;
 	struct skcipher_alg *ctr;
 	struct crypto_alg *ghash_alg;
@@ -594,11 +595,11 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
 		return -EINVAL;
 
+	mask = crypto_requires_sync(algt->type, algt->mask);
+
 	ghash_alg = crypto_find_alg(ghash_name, &crypto_ahash_type,
 				    CRYPTO_ALG_TYPE_HASH,
-				    CRYPTO_ALG_TYPE_AHASH_MASK |
-				    crypto_requires_sync(algt->type,
-							 algt->mask));
+				    CRYPTO_ALG_TYPE_AHASH_MASK | mask);
 	if (IS_ERR(ghash_alg))
 		return PTR_ERR(ghash_alg);
 
@@ -620,10 +621,8 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 	    ghash->digestsize != 16)
 		goto err_drop_ghash;
 
-	crypto_set_skcipher_spawn(&ctx->ctr, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->ctr, ctr_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher(&ctx->ctr, aead_crypto_instance(inst),
+				   ctr_name, 0, mask);
 	if (err)
 		goto err_drop_ghash;
 
diff --git a/crypto/lrw.c b/crypto/lrw.c
index 8ebd79276c78..63c485c0d8a6 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -301,6 +301,7 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	struct skcipher_alg *alg;
 	const char *cipher_name;
 	char ecb_name[CRYPTO_MAX_ALG_NAME];
+	u32 mask;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
@@ -310,6 +311,8 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	if ((algt->type ^ CRYPTO_ALG_TYPE_SKCIPHER) & algt->mask)
 		return -EINVAL;
 
+	mask = crypto_requires_sync(algt->type, algt->mask);
+
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
 		return PTR_ERR(cipher_name);
@@ -320,19 +323,17 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	spawn = skcipher_instance_ctx(inst);
 
-	crypto_set_skcipher_spawn(spawn, skcipher_crypto_instance(inst));
-	err = crypto_grab_skcipher(spawn, cipher_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher(spawn, skcipher_crypto_instance(inst),
+				   cipher_name, 0, mask);
 	if (err == -ENOENT) {
 		err = -ENAMETOOLONG;
 		if (snprintf(ecb_name, CRYPTO_MAX_ALG_NAME, "ecb(%s)",
 			     cipher_name) >= CRYPTO_MAX_ALG_NAME)
 			goto err_free_inst;
 
-		err = crypto_grab_skcipher(spawn, ecb_name, 0,
-					   crypto_requires_sync(algt->type,
-								algt->mask));
+		err = crypto_grab_skcipher(spawn,
+					   skcipher_crypto_instance(inst),
+					   ecb_name, 0, mask);
 	}
 
 	if (err)
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 89137a197fc8..8759d473a154 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -747,8 +747,10 @@ static const struct crypto_type crypto_skcipher_type = {
 };
 
 int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn,
-			  const char *name, u32 type, u32 mask)
+			 struct crypto_instance *inst,
+			 const char *name, u32 type, u32 mask)
 {
+	spawn->base.inst = inst;
 	spawn->base.frontend = &crypto_skcipher_type;
 	return crypto_grab_spawn(&spawn->base, name, type, mask);
 }
diff --git a/crypto/xts.c b/crypto/xts.c
index 19d55489e78b..29efa15f1495 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -355,20 +355,21 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	ctx = skcipher_instance_ctx(inst);
 
-	crypto_set_skcipher_spawn(&ctx->spawn, skcipher_crypto_instance(inst));
-
 	mask = crypto_requires_off(algt->type, algt->mask,
 				   CRYPTO_ALG_NEED_FALLBACK |
 				   CRYPTO_ALG_ASYNC);
 
-	err = crypto_grab_skcipher(&ctx->spawn, cipher_name, 0, mask);
+	err = crypto_grab_skcipher(&ctx->spawn, skcipher_crypto_instance(inst),
+				   cipher_name, 0, mask);
 	if (err == -ENOENT) {
 		err = -ENAMETOOLONG;
 		if (snprintf(ctx->name, CRYPTO_MAX_ALG_NAME, "ecb(%s)",
 			     cipher_name) >= CRYPTO_MAX_ALG_NAME)
 			goto err_free_inst;
 
-		err = crypto_grab_skcipher(&ctx->spawn, ctx->name, 0, mask);
+		err = crypto_grab_skcipher(&ctx->spawn,
+					   skcipher_crypto_instance(inst),
+					   ctx->name, 0, mask);
 	}
 
 	if (err)
diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h
index df4fdeaa13f3..e387424f6247 100644
--- a/include/crypto/internal/skcipher.h
+++ b/include/crypto/internal/skcipher.h
@@ -88,14 +88,9 @@ static inline void skcipher_request_complete(struct skcipher_request *req, int e
 	req->base.complete(&req->base, err);
 }
 
-static inline void crypto_set_skcipher_spawn(
-	struct crypto_skcipher_spawn *spawn, struct crypto_instance *inst)
-{
-	crypto_set_spawn(&spawn->base, inst);
-}
-
-int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, const char *name,
-			 u32 type, u32 mask);
+int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn,
+			 struct crypto_instance *inst,
+			 const char *name, u32 type, u32 mask);
 
 static inline void crypto_drop_skcipher(struct crypto_skcipher_spawn *spawn)
 {
-- 
cgit v1.2.3


From de95c9574108ec304083ed574304ab3b60b4167c Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 2 Jan 2020 19:58:48 -0800
Subject: crypto: algapi - pass instance to crypto_grab_spawn()

Currently, crypto_spawn::inst is first used temporarily to pass the
instance to crypto_grab_spawn().  Then crypto_init_spawn() overwrites it
with crypto_spawn::next, which shares the same union.  Finally,
crypto_spawn::inst is set again when the instance is registered.

Make this less convoluted by just passing the instance as an argument to
crypto_grab_spawn() instead.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/adiantum.c       |  6 +++---
 crypto/aead.c           |  3 +--
 crypto/akcipher.c       |  3 +--
 crypto/algapi.c         |  6 +++---
 crypto/skcipher.c       |  3 +--
 include/crypto/algapi.h | 10 ++--------
 6 files changed, 11 insertions(+), 20 deletions(-)

(limited to 'crypto/adiantum.c')

diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index 567071464fab..76a41881ee8c 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -542,9 +542,9 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
 	streamcipher_alg = crypto_spawn_skcipher_alg(&ictx->streamcipher_spawn);
 
 	/* Block cipher, e.g. "aes" */
-	crypto_set_spawn(&ictx->blockcipher_spawn,
-			 skcipher_crypto_instance(inst));
-	err = crypto_grab_spawn(&ictx->blockcipher_spawn, blockcipher_name,
+	err = crypto_grab_spawn(&ictx->blockcipher_spawn,
+				skcipher_crypto_instance(inst),
+				blockcipher_name,
 				CRYPTO_ALG_TYPE_CIPHER, CRYPTO_ALG_TYPE_MASK);
 	if (err)
 		goto out_drop_streamcipher;
diff --git a/crypto/aead.c b/crypto/aead.c
index c7135e00b8ea..02a0db076d7e 100644
--- a/crypto/aead.c
+++ b/crypto/aead.c
@@ -211,9 +211,8 @@ int crypto_grab_aead(struct crypto_aead_spawn *spawn,
 		     struct crypto_instance *inst,
 		     const char *name, u32 type, u32 mask)
 {
-	spawn->base.inst = inst;
 	spawn->base.frontend = &crypto_aead_type;
-	return crypto_grab_spawn(&spawn->base, name, type, mask);
+	return crypto_grab_spawn(&spawn->base, inst, name, type, mask);
 }
 EXPORT_SYMBOL_GPL(crypto_grab_aead);
 
diff --git a/crypto/akcipher.c b/crypto/akcipher.c
index 84ccf9b02bbe..eeed6c151d2f 100644
--- a/crypto/akcipher.c
+++ b/crypto/akcipher.c
@@ -94,9 +94,8 @@ int crypto_grab_akcipher(struct crypto_akcipher_spawn *spawn,
 			 struct crypto_instance *inst,
 			 const char *name, u32 type, u32 mask)
 {
-	spawn->base.inst = inst;
 	spawn->base.frontend = &crypto_akcipher_type;
-	return crypto_grab_spawn(&spawn->base, name, type, mask);
+	return crypto_grab_spawn(&spawn->base, inst, name, type, mask);
 }
 EXPORT_SYMBOL_GPL(crypto_grab_akcipher);
 
diff --git a/crypto/algapi.c b/crypto/algapi.c
index a5223c5f2275..a25ce02918f8 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -714,8 +714,8 @@ out:
 }
 EXPORT_SYMBOL_GPL(crypto_init_spawn2);
 
-int crypto_grab_spawn(struct crypto_spawn *spawn, const char *name,
-		      u32 type, u32 mask)
+int crypto_grab_spawn(struct crypto_spawn *spawn, struct crypto_instance *inst,
+		      const char *name, u32 type, u32 mask)
 {
 	struct crypto_alg *alg;
 	int err;
@@ -729,7 +729,7 @@ int crypto_grab_spawn(struct crypto_spawn *spawn, const char *name,
 		return PTR_ERR(alg);
 
 	spawn->dropref = true;
-	err = crypto_init_spawn(spawn, alg, spawn->inst, mask);
+	err = crypto_init_spawn(spawn, alg, inst, mask);
 	if (err)
 		crypto_mod_put(alg);
 	return err;
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 8759d473a154..15c033c960f7 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -750,9 +750,8 @@ int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn,
 			 struct crypto_instance *inst,
 			 const char *name, u32 type, u32 mask)
 {
-	spawn->base.inst = inst;
 	spawn->base.frontend = &crypto_skcipher_type;
-	return crypto_grab_spawn(&spawn->base, name, type, mask);
+	return crypto_grab_spawn(&spawn->base, inst, name, type, mask);
 }
 EXPORT_SYMBOL_GPL(crypto_grab_skcipher);
 
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 5022cada4fc6..2779c8d34ba9 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -116,20 +116,14 @@ int crypto_init_spawn(struct crypto_spawn *spawn, struct crypto_alg *alg,
 int crypto_init_spawn2(struct crypto_spawn *spawn, struct crypto_alg *alg,
 		       struct crypto_instance *inst,
 		       const struct crypto_type *frontend);
-int crypto_grab_spawn(struct crypto_spawn *spawn, const char *name,
-		      u32 type, u32 mask);
+int crypto_grab_spawn(struct crypto_spawn *spawn, struct crypto_instance *inst,
+		      const char *name, u32 type, u32 mask);
 
 void crypto_drop_spawn(struct crypto_spawn *spawn);
 struct crypto_tfm *crypto_spawn_tfm(struct crypto_spawn *spawn, u32 type,
 				    u32 mask);
 void *crypto_spawn_tfm2(struct crypto_spawn *spawn);
 
-static inline void crypto_set_spawn(struct crypto_spawn *spawn,
-				    struct crypto_instance *inst)
-{
-	spawn->inst = inst;
-}
-
 struct crypto_attr_type *crypto_get_attr_type(struct rtattr **tb);
 int crypto_check_attr_type(struct rtattr **tb, u32 type);
 const char *crypto_attr_alg_name(struct rtattr *rta);
-- 
cgit v1.2.3


From ba44840747bdd60095881830af0d75f0e5017c99 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 2 Jan 2020 19:58:52 -0800
Subject: crypto: adiantum - use crypto_grab_{cipher,shash} and simplify error
 paths

Make the adiantum template use the new functions crypto_grab_cipher()
and crypto_grab_shash() to initialize its cipher and shash spawns.

This is needed to make all spawns be initialized in a consistent way.

Also simplify the error handling by taking advantage of crypto_drop_*()
now accepting (as a no-op) spawns that haven't been initialized yet, and
by taking advantage of crypto_grab_*() now handling ERR_PTR() names.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/adiantum.c | 85 ++++++++++++++++---------------------------------------
 1 file changed, 25 insertions(+), 60 deletions(-)

(limited to 'crypto/adiantum.c')

diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index 76a41881ee8c..5b8aa14ccb55 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -39,8 +39,6 @@
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
 
-#include "internal.h"
-
 /*
  * Size of right-hand part of input data, in bytes; also the size of the block
  * cipher's block size and the hash function's output.
@@ -64,7 +62,7 @@
 
 struct adiantum_instance_ctx {
 	struct crypto_skcipher_spawn streamcipher_spawn;
-	struct crypto_spawn blockcipher_spawn;
+	struct crypto_cipher_spawn blockcipher_spawn;
 	struct crypto_shash_spawn hash_spawn;
 };
 
@@ -410,7 +408,7 @@ static int adiantum_init_tfm(struct crypto_skcipher *tfm)
 	if (IS_ERR(streamcipher))
 		return PTR_ERR(streamcipher);
 
-	blockcipher = crypto_spawn_cipher(&ictx->blockcipher_spawn);
+	blockcipher = crypto_spawn_cipher(&ictx->blockcipher_spawn.base);
 	if (IS_ERR(blockcipher)) {
 		err = PTR_ERR(blockcipher);
 		goto err_free_streamcipher;
@@ -461,7 +459,7 @@ static void adiantum_free_instance(struct skcipher_instance *inst)
 	struct adiantum_instance_ctx *ictx = skcipher_instance_ctx(inst);
 
 	crypto_drop_skcipher(&ictx->streamcipher_spawn);
-	crypto_drop_spawn(&ictx->blockcipher_spawn);
+	crypto_drop_cipher(&ictx->blockcipher_spawn);
 	crypto_drop_shash(&ictx->hash_spawn);
 	kfree(inst);
 }
@@ -494,14 +492,11 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
 	u32 mask;
-	const char *streamcipher_name;
-	const char *blockcipher_name;
 	const char *nhpoly1305_name;
 	struct skcipher_instance *inst;
 	struct adiantum_instance_ctx *ictx;
 	struct skcipher_alg *streamcipher_alg;
 	struct crypto_alg *blockcipher_alg;
-	struct crypto_alg *_hash_alg;
 	struct shash_alg *hash_alg;
 	int err;
 
@@ -514,20 +509,6 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	mask = crypto_requires_sync(algt->type, algt->mask);
 
-	streamcipher_name = crypto_attr_alg_name(tb[1]);
-	if (IS_ERR(streamcipher_name))
-		return PTR_ERR(streamcipher_name);
-
-	blockcipher_name = crypto_attr_alg_name(tb[2]);
-	if (IS_ERR(blockcipher_name))
-		return PTR_ERR(blockcipher_name);
-
-	nhpoly1305_name = crypto_attr_alg_name(tb[3]);
-	if (nhpoly1305_name == ERR_PTR(-ENOENT))
-		nhpoly1305_name = "nhpoly1305";
-	if (IS_ERR(nhpoly1305_name))
-		return PTR_ERR(nhpoly1305_name);
-
 	inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL);
 	if (!inst)
 		return -ENOMEM;
@@ -536,33 +517,29 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
 	/* Stream cipher, e.g. "xchacha12" */
 	err = crypto_grab_skcipher(&ictx->streamcipher_spawn,
 				   skcipher_crypto_instance(inst),
-				   streamcipher_name, 0, mask);
+				   crypto_attr_alg_name(tb[1]), 0, mask);
 	if (err)
-		goto out_free_inst;
+		goto err_free_inst;
 	streamcipher_alg = crypto_spawn_skcipher_alg(&ictx->streamcipher_spawn);
 
 	/* Block cipher, e.g. "aes" */
-	err = crypto_grab_spawn(&ictx->blockcipher_spawn,
-				skcipher_crypto_instance(inst),
-				blockcipher_name,
-				CRYPTO_ALG_TYPE_CIPHER, CRYPTO_ALG_TYPE_MASK);
+	err = crypto_grab_cipher(&ictx->blockcipher_spawn,
+				 skcipher_crypto_instance(inst),
+				 crypto_attr_alg_name(tb[2]), 0, mask);
 	if (err)
-		goto out_drop_streamcipher;
-	blockcipher_alg = ictx->blockcipher_spawn.alg;
+		goto err_free_inst;
+	blockcipher_alg = crypto_spawn_cipher_alg(&ictx->blockcipher_spawn);
 
 	/* NHPoly1305 ε-∆U hash function */
-	_hash_alg = crypto_alg_mod_lookup(nhpoly1305_name,
-					  CRYPTO_ALG_TYPE_SHASH,
-					  CRYPTO_ALG_TYPE_MASK);
-	if (IS_ERR(_hash_alg)) {
-		err = PTR_ERR(_hash_alg);
-		goto out_drop_blockcipher;
-	}
-	hash_alg = __crypto_shash_alg(_hash_alg);
-	err = crypto_init_shash_spawn(&ictx->hash_spawn, hash_alg,
-				      skcipher_crypto_instance(inst));
+	nhpoly1305_name = crypto_attr_alg_name(tb[3]);
+	if (nhpoly1305_name == ERR_PTR(-ENOENT))
+		nhpoly1305_name = "nhpoly1305";
+	err = crypto_grab_shash(&ictx->hash_spawn,
+				skcipher_crypto_instance(inst),
+				nhpoly1305_name, 0, mask);
 	if (err)
-		goto out_put_hash;
+		goto err_free_inst;
+	hash_alg = crypto_spawn_shash_alg(&ictx->hash_spawn);
 
 	/* Check the set of algorithms */
 	if (!adiantum_supported_algorithms(streamcipher_alg, blockcipher_alg,
@@ -571,7 +548,7 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
 			streamcipher_alg->base.cra_name,
 			blockcipher_alg->cra_name, hash_alg->base.cra_name);
 		err = -EINVAL;
-		goto out_drop_hash;
+		goto err_free_inst;
 	}
 
 	/* Instance fields */
@@ -580,13 +557,13 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
 	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
 		     "adiantum(%s,%s)", streamcipher_alg->base.cra_name,
 		     blockcipher_alg->cra_name) >= CRYPTO_MAX_ALG_NAME)
-		goto out_drop_hash;
+		goto err_free_inst;
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "adiantum(%s,%s,%s)",
 		     streamcipher_alg->base.cra_driver_name,
 		     blockcipher_alg->cra_driver_name,
 		     hash_alg->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
-		goto out_drop_hash;
+		goto err_free_inst;
 
 	inst->alg.base.cra_flags = streamcipher_alg->base.cra_flags &
 				   CRYPTO_ALG_ASYNC;
@@ -616,22 +593,10 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb)
 	inst->free = adiantum_free_instance;
 
 	err = skcipher_register_instance(tmpl, inst);
-	if (err)
-		goto out_drop_hash;
-
-	crypto_mod_put(_hash_alg);
-	return 0;
-
-out_drop_hash:
-	crypto_drop_shash(&ictx->hash_spawn);
-out_put_hash:
-	crypto_mod_put(_hash_alg);
-out_drop_blockcipher:
-	crypto_drop_spawn(&ictx->blockcipher_spawn);
-out_drop_streamcipher:
-	crypto_drop_skcipher(&ictx->streamcipher_spawn);
-out_free_inst:
-	kfree(inst);
+	if (err) {
+err_free_inst:
+		adiantum_free_instance(inst);
+	}
 	return err;
 }
 
-- 
cgit v1.2.3


From d5ed3b65f7012a6592809f7f928f3e3660df8fd9 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 2 Jan 2020 19:59:05 -0800
Subject: crypto: cipher - make crypto_spawn_cipher() take a
 crypto_cipher_spawn

Now that all users of single-block cipher spawns have been converted to
use 'struct crypto_cipher_spawn' rather than the less specifically typed
'struct crypto_spawn', make crypto_spawn_cipher() take a pointer to a
'struct crypto_cipher_spawn' rather than a 'struct crypto_spawn'.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/adiantum.c       | 2 +-
 crypto/ccm.c            | 2 +-
 crypto/cmac.c           | 2 +-
 crypto/skcipher.c       | 2 +-
 crypto/vmac.c           | 2 +-
 crypto/xcbc.c           | 2 +-
 include/crypto/algapi.h | 4 ++--
 7 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'crypto/adiantum.c')

diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index 5b8aa14ccb55..4d7a6cac82ed 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -408,7 +408,7 @@ static int adiantum_init_tfm(struct crypto_skcipher *tfm)
 	if (IS_ERR(streamcipher))
 		return PTR_ERR(streamcipher);
 
-	blockcipher = crypto_spawn_cipher(&ictx->blockcipher_spawn.base);
+	blockcipher = crypto_spawn_cipher(&ictx->blockcipher_spawn);
 	if (IS_ERR(blockcipher)) {
 		err = PTR_ERR(blockcipher);
 		goto err_free_streamcipher;
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 411c3973b95c..f4abaefd9df5 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -866,7 +866,7 @@ static int cbcmac_init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_cipher *cipher;
 	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
+	struct crypto_cipher_spawn *spawn = crypto_instance_ctx(inst);
 	struct cbcmac_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	cipher = crypto_spawn_cipher(spawn);
diff --git a/crypto/cmac.c b/crypto/cmac.c
index c6bf78b5321a..58dc644416bb 100644
--- a/crypto/cmac.c
+++ b/crypto/cmac.c
@@ -201,7 +201,7 @@ static int cmac_init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_cipher *cipher;
 	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
+	struct crypto_cipher_spawn *spawn = crypto_instance_ctx(inst);
 	struct cmac_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	cipher = crypto_spawn_cipher(spawn);
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 950ff1438131..42add1e0814f 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -887,7 +887,7 @@ static int skcipher_setkey_simple(struct crypto_skcipher *tfm, const u8 *key,
 static int skcipher_init_tfm_simple(struct crypto_skcipher *tfm)
 {
 	struct skcipher_instance *inst = skcipher_alg_instance(tfm);
-	struct crypto_spawn *spawn = skcipher_instance_ctx(inst);
+	struct crypto_cipher_spawn *spawn = skcipher_instance_ctx(inst);
 	struct skcipher_ctx_simple *ctx = crypto_skcipher_ctx(tfm);
 	struct crypto_cipher *cipher;
 
diff --git a/crypto/vmac.c b/crypto/vmac.c
index 9b000aaa20a8..28358a6aef9f 100644
--- a/crypto/vmac.c
+++ b/crypto/vmac.c
@@ -596,7 +596,7 @@ static int vmac_final(struct shash_desc *desc, u8 *out)
 static int vmac_init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
-	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
+	struct crypto_cipher_spawn *spawn = crypto_instance_ctx(inst);
 	struct vmac_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 	struct crypto_cipher *cipher;
 
diff --git a/crypto/xcbc.c b/crypto/xcbc.c
index 9b97fa511f10..9265e00ea663 100644
--- a/crypto/xcbc.c
+++ b/crypto/xcbc.c
@@ -167,7 +167,7 @@ static int xcbc_init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_cipher *cipher;
 	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
+	struct crypto_cipher_spawn *spawn = crypto_instance_ctx(inst);
 	struct xcbc_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	cipher = crypto_spawn_cipher(spawn);
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 7705387f9459..bbf85a854a42 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -234,12 +234,12 @@ static inline struct crypto_alg *crypto_spawn_cipher_alg(
 }
 
 static inline struct crypto_cipher *crypto_spawn_cipher(
-	struct crypto_spawn *spawn)
+	struct crypto_cipher_spawn *spawn)
 {
 	u32 type = CRYPTO_ALG_TYPE_CIPHER;
 	u32 mask = CRYPTO_ALG_TYPE_MASK;
 
-	return __crypto_cipher_cast(crypto_spawn_tfm(spawn, type, mask));
+	return __crypto_cipher_cast(crypto_spawn_tfm(&spawn->base, type, mask));
 }
 
 static inline struct cipher_alg *crypto_cipher_alg(struct crypto_cipher *tfm)
-- 
cgit v1.2.3


From 1c08a104360f3e18f4ee6346c21cc3923efb952e Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sun, 5 Jan 2020 22:40:46 -0500
Subject: crypto: poly1305 - add new 32 and 64-bit generic versions

These two C implementations from Zinc -- a 32x32 one and a 64x64 one,
depending on the platform -- come from Andrew Moon's public domain
poly1305-donna portable code, modified for usage in the kernel. The
precomputation in the 32-bit version and the use of 64x64 multiplies in
the 64-bit version make these perform better than the code it replaces.
Moon's code is also very widespread and has received many eyeballs of
scrutiny.

There's a bit of interference between the x86 implementation, which
relies on internal details of the old scalar implementation. In the next
commit, the x86 implementation will be replaced with a faster one that
doesn't rely on this, so none of this matters much. But for now, to keep
this passing the tests, we inline the bits of the old implementation
that the x86 implementation relied on. Also, since we now support a
slightly larger key space, via the union, some offsets had to be fixed
up.

Nonce calculation was folded in with the emit function, to take
advantage of 64x64 arithmetic. However, Adiantum appeared to rely on no
nonce handling in emit, so this path was conditionalized. We also
introduced a new struct, poly1305_core_key, to represent the precise
amount of space that particular implementation uses.

Testing with kbench9000, depending on the CPU, the update function for
the 32x32 version has been improved by 4%-7%, and for the 64x64 by
19%-30%. The 32x32 gains are small, but I think there's great value in
having a parallel implementation to the 64x64 one so that the two can be
compared side-by-side as nice stand-alone units.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/x86/crypto/poly1305-avx2-x86_64.S |  20 +--
 arch/x86/crypto/poly1305_glue.c        | 215 +++++++++++++++++++++++++++++++--
 crypto/adiantum.c                      |   4 +-
 crypto/nhpoly1305.c                    |   2 +-
 crypto/poly1305_generic.c              |  25 +++-
 include/crypto/internal/poly1305.h     |  45 ++-----
 include/crypto/nhpoly1305.h            |   4 +-
 include/crypto/poly1305.h              |  26 +++-
 lib/crypto/Makefile                    |   4 +-
 lib/crypto/poly1305-donna32.c          | 204 +++++++++++++++++++++++++++++++
 lib/crypto/poly1305-donna64.c          | 185 ++++++++++++++++++++++++++++
 lib/crypto/poly1305.c                  | 169 ++------------------------
 12 files changed, 675 insertions(+), 228 deletions(-)
 create mode 100644 lib/crypto/poly1305-donna32.c
 create mode 100644 lib/crypto/poly1305-donna64.c

(limited to 'crypto/adiantum.c')

diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S
index d6063feda9da..8f56989ea599 100644
--- a/arch/x86/crypto/poly1305-avx2-x86_64.S
+++ b/arch/x86/crypto/poly1305-avx2-x86_64.S
@@ -34,16 +34,16 @@ ORMASK:	.octa 0x00000000010000000000000001000000
 #define u2 0x08(%r8)
 #define u3 0x0c(%r8)
 #define u4 0x10(%r8)
-#define w0 0x14(%r8)
-#define w1 0x18(%r8)
-#define w2 0x1c(%r8)
-#define w3 0x20(%r8)
-#define w4 0x24(%r8)
-#define y0 0x28(%r8)
-#define y1 0x2c(%r8)
-#define y2 0x30(%r8)
-#define y3 0x34(%r8)
-#define y4 0x38(%r8)
+#define w0 0x18(%r8)
+#define w1 0x1c(%r8)
+#define w2 0x20(%r8)
+#define w3 0x24(%r8)
+#define w4 0x28(%r8)
+#define y0 0x30(%r8)
+#define y1 0x34(%r8)
+#define y2 0x38(%r8)
+#define y3 0x3c(%r8)
+#define y4 0x40(%r8)
 #define m %rsi
 #define hc0 %ymm0
 #define hc1 %ymm1
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 0cc4537e6617..edb7113e36f3 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -25,6 +25,21 @@ asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r,
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_simd);
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2);
 
+static inline u64 mlt(u64 a, u64 b)
+{
+	return a * b;
+}
+
+static inline u32 sr(u64 v, u_char n)
+{
+	return v >> n;
+}
+
+static inline u32 and(u32 v, u32 mask)
+{
+	return v & mask;
+}
+
 static void poly1305_simd_mult(u32 *a, const u32 *b)
 {
 	u8 m[POLY1305_BLOCK_SIZE];
@@ -36,6 +51,168 @@ static void poly1305_simd_mult(u32 *a, const u32 *b)
 	poly1305_block_sse2(a, m, b, 1);
 }
 
+static void poly1305_integer_setkey(struct poly1305_key *key, const u8 *raw_key)
+{
+	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
+	key->r[0] = (get_unaligned_le32(raw_key +  0) >> 0) & 0x3ffffff;
+	key->r[1] = (get_unaligned_le32(raw_key +  3) >> 2) & 0x3ffff03;
+	key->r[2] = (get_unaligned_le32(raw_key +  6) >> 4) & 0x3ffc0ff;
+	key->r[3] = (get_unaligned_le32(raw_key +  9) >> 6) & 0x3f03fff;
+	key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff;
+}
+
+static void poly1305_integer_blocks(struct poly1305_state *state,
+				    const struct poly1305_key *key,
+				    const void *src,
+				    unsigned int nblocks, u32 hibit)
+{
+	u32 r0, r1, r2, r3, r4;
+	u32 s1, s2, s3, s4;
+	u32 h0, h1, h2, h3, h4;
+	u64 d0, d1, d2, d3, d4;
+
+	if (!nblocks)
+		return;
+
+	r0 = key->r[0];
+	r1 = key->r[1];
+	r2 = key->r[2];
+	r3 = key->r[3];
+	r4 = key->r[4];
+
+	s1 = r1 * 5;
+	s2 = r2 * 5;
+	s3 = r3 * 5;
+	s4 = r4 * 5;
+
+	h0 = state->h[0];
+	h1 = state->h[1];
+	h2 = state->h[2];
+	h3 = state->h[3];
+	h4 = state->h[4];
+
+	do {
+		/* h += m[i] */
+		h0 += (get_unaligned_le32(src +  0) >> 0) & 0x3ffffff;
+		h1 += (get_unaligned_le32(src +  3) >> 2) & 0x3ffffff;
+		h2 += (get_unaligned_le32(src +  6) >> 4) & 0x3ffffff;
+		h3 += (get_unaligned_le32(src +  9) >> 6) & 0x3ffffff;
+		h4 += (get_unaligned_le32(src + 12) >> 8) | (hibit << 24);
+
+		/* h *= r */
+		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) +
+		     mlt(h3, s2) + mlt(h4, s1);
+		d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) +
+		     mlt(h3, s3) + mlt(h4, s2);
+		d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) +
+		     mlt(h3, s4) + mlt(h4, s3);
+		d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) +
+		     mlt(h3, r0) + mlt(h4, s4);
+		d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) +
+		     mlt(h3, r1) + mlt(h4, r0);
+
+		/* (partial) h %= p */
+		d1 += sr(d0, 26);     h0 = and(d0, 0x3ffffff);
+		d2 += sr(d1, 26);     h1 = and(d1, 0x3ffffff);
+		d3 += sr(d2, 26);     h2 = and(d2, 0x3ffffff);
+		d4 += sr(d3, 26);     h3 = and(d3, 0x3ffffff);
+		h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff);
+		h1 += h0 >> 26;       h0 = h0 & 0x3ffffff;
+
+		src += POLY1305_BLOCK_SIZE;
+	} while (--nblocks);
+
+	state->h[0] = h0;
+	state->h[1] = h1;
+	state->h[2] = h2;
+	state->h[3] = h3;
+	state->h[4] = h4;
+}
+
+static void poly1305_integer_emit(const struct poly1305_state *state, void *dst)
+{
+	u32 h0, h1, h2, h3, h4;
+	u32 g0, g1, g2, g3, g4;
+	u32 mask;
+
+	/* fully carry h */
+	h0 = state->h[0];
+	h1 = state->h[1];
+	h2 = state->h[2];
+	h3 = state->h[3];
+	h4 = state->h[4];
+
+	h2 += (h1 >> 26);     h1 = h1 & 0x3ffffff;
+	h3 += (h2 >> 26);     h2 = h2 & 0x3ffffff;
+	h4 += (h3 >> 26);     h3 = h3 & 0x3ffffff;
+	h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff;
+	h1 += (h0 >> 26);     h0 = h0 & 0x3ffffff;
+
+	/* compute h + -p */
+	g0 = h0 + 5;
+	g1 = h1 + (g0 >> 26);             g0 &= 0x3ffffff;
+	g2 = h2 + (g1 >> 26);             g1 &= 0x3ffffff;
+	g3 = h3 + (g2 >> 26);             g2 &= 0x3ffffff;
+	g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff;
+
+	/* select h if h < p, or h + -p if h >= p */
+	mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1;
+	g0 &= mask;
+	g1 &= mask;
+	g2 &= mask;
+	g3 &= mask;
+	g4 &= mask;
+	mask = ~mask;
+	h0 = (h0 & mask) | g0;
+	h1 = (h1 & mask) | g1;
+	h2 = (h2 & mask) | g2;
+	h3 = (h3 & mask) | g3;
+	h4 = (h4 & mask) | g4;
+
+	/* h = h % (2^128) */
+	put_unaligned_le32((h0 >>  0) | (h1 << 26), dst +  0);
+	put_unaligned_le32((h1 >>  6) | (h2 << 20), dst +  4);
+	put_unaligned_le32((h2 >> 12) | (h3 << 14), dst +  8);
+	put_unaligned_le32((h3 >> 18) | (h4 <<  8), dst + 12);
+}
+
+void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key)
+{
+	poly1305_integer_setkey(desc->opaque_r, key);
+	desc->s[0] = get_unaligned_le32(key + 16);
+	desc->s[1] = get_unaligned_le32(key + 20);
+	desc->s[2] = get_unaligned_le32(key + 24);
+	desc->s[3] = get_unaligned_le32(key + 28);
+	poly1305_core_init(&desc->h);
+	desc->buflen = 0;
+	desc->sset = true;
+	desc->rset = 1;
+}
+EXPORT_SYMBOL_GPL(poly1305_init_arch);
+
+static unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
+					       const u8 *src, unsigned int srclen)
+{
+	if (!dctx->sset) {
+		if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
+			poly1305_integer_setkey(dctx->r, src);
+			src += POLY1305_BLOCK_SIZE;
+			srclen -= POLY1305_BLOCK_SIZE;
+			dctx->rset = 1;
+		}
+		if (srclen >= POLY1305_BLOCK_SIZE) {
+			dctx->s[0] = get_unaligned_le32(src +  0);
+			dctx->s[1] = get_unaligned_le32(src +  4);
+			dctx->s[2] = get_unaligned_le32(src +  8);
+			dctx->s[3] = get_unaligned_le32(src + 12);
+			src += POLY1305_BLOCK_SIZE;
+			srclen -= POLY1305_BLOCK_SIZE;
+			dctx->sset = true;
+		}
+	}
+	return srclen;
+}
+
 static unsigned int poly1305_scalar_blocks(struct poly1305_desc_ctx *dctx,
 					   const u8 *src, unsigned int srclen)
 {
@@ -47,8 +224,8 @@ static unsigned int poly1305_scalar_blocks(struct poly1305_desc_ctx *dctx,
 		srclen = datalen;
 	}
 	if (srclen >= POLY1305_BLOCK_SIZE) {
-		poly1305_core_blocks(&dctx->h, dctx->r, src,
-				     srclen / POLY1305_BLOCK_SIZE, 1);
+		poly1305_integer_blocks(&dctx->h, dctx->opaque_r, src,
+					srclen / POLY1305_BLOCK_SIZE, 1);
 		srclen %= POLY1305_BLOCK_SIZE;
 	}
 	return srclen;
@@ -105,12 +282,6 @@ static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx,
 	return srclen;
 }
 
-void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key)
-{
-	poly1305_init_generic(desc, key);
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
 void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
 			  unsigned int srclen)
 {
@@ -158,9 +329,31 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
 }
 EXPORT_SYMBOL(poly1305_update_arch);
 
-void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *digest)
+void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *dst)
 {
-	poly1305_final_generic(desc, digest);
+	__le32 digest[4];
+	u64 f = 0;
+
+	if (unlikely(desc->buflen)) {
+		desc->buf[desc->buflen++] = 1;
+		memset(desc->buf + desc->buflen, 0,
+		       POLY1305_BLOCK_SIZE - desc->buflen);
+		poly1305_integer_blocks(&desc->h, desc->opaque_r, desc->buf, 1, 0);
+	}
+
+	poly1305_integer_emit(&desc->h, digest);
+
+	/* mac = (h + s) % (2^128) */
+	f = (f >> 32) + le32_to_cpu(digest[0]) + desc->s[0];
+	put_unaligned_le32(f, dst + 0);
+	f = (f >> 32) + le32_to_cpu(digest[1]) + desc->s[1];
+	put_unaligned_le32(f, dst + 4);
+	f = (f >> 32) + le32_to_cpu(digest[2]) + desc->s[2];
+	put_unaligned_le32(f, dst + 8);
+	f = (f >> 32) + le32_to_cpu(digest[3]) + desc->s[3];
+	put_unaligned_le32(f, dst + 12);
+
+	*desc = (struct poly1305_desc_ctx){};
 }
 EXPORT_SYMBOL(poly1305_final_arch);
 
@@ -183,7 +376,7 @@ static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
 	if (unlikely(!dctx->sset))
 		return -ENOKEY;
 
-	poly1305_final_generic(dctx, dst);
+	poly1305_final_arch(dctx, dst);
 	return 0;
 }
 
diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index 4d7a6cac82ed..53d5e705a425 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -70,7 +70,7 @@ struct adiantum_tfm_ctx {
 	struct crypto_skcipher *streamcipher;
 	struct crypto_cipher *blockcipher;
 	struct crypto_shash *hash;
-	struct poly1305_key header_hash_key;
+	struct poly1305_core_key header_hash_key;
 };
 
 struct adiantum_request_ctx {
@@ -239,7 +239,7 @@ static void adiantum_hash_header(struct skcipher_request *req)
 	poly1305_core_blocks(&state, &tctx->header_hash_key, req->iv,
 			     TWEAK_SIZE / POLY1305_BLOCK_SIZE, 1);
 
-	poly1305_core_emit(&state, &rctx->header_hash);
+	poly1305_core_emit(&state, NULL, &rctx->header_hash);
 }
 
 /* Hash the left-hand part (the "bulk") of the message using NHPoly1305 */
diff --git a/crypto/nhpoly1305.c b/crypto/nhpoly1305.c
index f6b6a52092b4..8a3006c3b51b 100644
--- a/crypto/nhpoly1305.c
+++ b/crypto/nhpoly1305.c
@@ -210,7 +210,7 @@ int crypto_nhpoly1305_final_helper(struct shash_desc *desc, u8 *dst, nh_t nh_fn)
 	if (state->nh_remaining)
 		process_nh_hash_value(state, key);
 
-	poly1305_core_emit(&state->poly_state, dst);
+	poly1305_core_emit(&state->poly_state, NULL, dst);
 	return 0;
 }
 EXPORT_SYMBOL(crypto_nhpoly1305_final_helper);
diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index 21edbd8c99fb..94af47eb6fa6 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -31,6 +31,29 @@ static int crypto_poly1305_init(struct shash_desc *desc)
 	return 0;
 }
 
+static unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
+					       const u8 *src, unsigned int srclen)
+{
+	if (!dctx->sset) {
+		if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
+			poly1305_core_setkey(&dctx->core_r, src);
+			src += POLY1305_BLOCK_SIZE;
+			srclen -= POLY1305_BLOCK_SIZE;
+			dctx->rset = 2;
+		}
+		if (srclen >= POLY1305_BLOCK_SIZE) {
+			dctx->s[0] = get_unaligned_le32(src +  0);
+			dctx->s[1] = get_unaligned_le32(src +  4);
+			dctx->s[2] = get_unaligned_le32(src +  8);
+			dctx->s[3] = get_unaligned_le32(src + 12);
+			src += POLY1305_BLOCK_SIZE;
+			srclen -= POLY1305_BLOCK_SIZE;
+			dctx->sset = true;
+		}
+	}
+	return srclen;
+}
+
 static void poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
 			    unsigned int srclen)
 {
@@ -42,7 +65,7 @@ static void poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
 		srclen = datalen;
 	}
 
-	poly1305_core_blocks(&dctx->h, dctx->r, src,
+	poly1305_core_blocks(&dctx->h, &dctx->core_r, src,
 			     srclen / POLY1305_BLOCK_SIZE, 1);
 }
 
diff --git a/include/crypto/internal/poly1305.h b/include/crypto/internal/poly1305.h
index 479b0cab2a1a..064e52ca5248 100644
--- a/include/crypto/internal/poly1305.h
+++ b/include/crypto/internal/poly1305.h
@@ -11,48 +11,23 @@
 #include <crypto/poly1305.h>
 
 /*
- * Poly1305 core functions.  These implement the ε-almost-∆-universal hash
- * function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce
- * ("s key") at the end.  They also only support block-aligned inputs.
+ * Poly1305 core functions.  These only accept whole blocks; the caller must
+ * handle any needed block buffering and padding.  'hibit' must be 1 for any
+ * full blocks, or 0 for the final block if it had to be padded.  If 'nonce' is
+ * non-NULL, then it's added at the end to compute the Poly1305 MAC.  Otherwise,
+ * only the ε-almost-∆-universal hash function (not the full MAC) is computed.
  */
-void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key);
+
+void poly1305_core_setkey(struct poly1305_core_key *key, const u8 *raw_key);
 static inline void poly1305_core_init(struct poly1305_state *state)
 {
 	*state = (struct poly1305_state){};
 }
 
 void poly1305_core_blocks(struct poly1305_state *state,
-			  const struct poly1305_key *key, const void *src,
+			  const struct poly1305_core_key *key, const void *src,
 			  unsigned int nblocks, u32 hibit);
-void poly1305_core_emit(const struct poly1305_state *state, void *dst);
-
-/*
- * Poly1305 requires a unique key for each tag, which implies that we can't set
- * it on the tfm that gets accessed by multiple users simultaneously. Instead we
- * expect the key as the first 32 bytes in the update() call.
- */
-static inline
-unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
-					const u8 *src, unsigned int srclen)
-{
-	if (!dctx->sset) {
-		if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
-			poly1305_core_setkey(dctx->r, src);
-			src += POLY1305_BLOCK_SIZE;
-			srclen -= POLY1305_BLOCK_SIZE;
-			dctx->rset = 1;
-		}
-		if (srclen >= POLY1305_BLOCK_SIZE) {
-			dctx->s[0] = get_unaligned_le32(src +  0);
-			dctx->s[1] = get_unaligned_le32(src +  4);
-			dctx->s[2] = get_unaligned_le32(src +  8);
-			dctx->s[3] = get_unaligned_le32(src + 12);
-			src += POLY1305_BLOCK_SIZE;
-			srclen -= POLY1305_BLOCK_SIZE;
-			dctx->sset = true;
-		}
-	}
-	return srclen;
-}
+void poly1305_core_emit(const struct poly1305_state *state, const u32 nonce[4],
+			void *dst);
 
 #endif
diff --git a/include/crypto/nhpoly1305.h b/include/crypto/nhpoly1305.h
index 53c04423c582..306925fea190 100644
--- a/include/crypto/nhpoly1305.h
+++ b/include/crypto/nhpoly1305.h
@@ -7,7 +7,7 @@
 #define _NHPOLY1305_H
 
 #include <crypto/hash.h>
-#include <crypto/poly1305.h>
+#include <crypto/internal/poly1305.h>
 
 /* NH parameterization: */
 
@@ -33,7 +33,7 @@
 #define NHPOLY1305_KEY_SIZE	(POLY1305_BLOCK_SIZE + NH_KEY_BYTES)
 
 struct nhpoly1305_key {
-	struct poly1305_key poly_key;
+	struct poly1305_core_key poly_key;
 	u32 nh_key[NH_KEY_WORDS];
 };
 
diff --git a/include/crypto/poly1305.h b/include/crypto/poly1305.h
index 74c6e1cd73ee..f1f67fc749cf 100644
--- a/include/crypto/poly1305.h
+++ b/include/crypto/poly1305.h
@@ -13,12 +13,29 @@
 #define POLY1305_KEY_SIZE	32
 #define POLY1305_DIGEST_SIZE	16
 
+/* The poly1305_key and poly1305_state types are mostly opaque and
+ * implementation-defined. Limbs might be in base 2^64 or base 2^26, or
+ * different yet. The union type provided keeps these 64-bit aligned for the
+ * case in which this is implemented using 64x64 multiplies.
+ */
+
 struct poly1305_key {
-	u32 r[5];	/* key, base 2^26 */
+	union {
+		u32 r[5];
+		u64 r64[3];
+	};
+};
+
+struct poly1305_core_key {
+	struct poly1305_key key;
+	struct poly1305_key precomputed_s;
 };
 
 struct poly1305_state {
-	u32 h[5];	/* accumulator, base 2^26 */
+	union {
+		u32 h[5];
+		u64 h64[3];
+	};
 };
 
 struct poly1305_desc_ctx {
@@ -35,7 +52,10 @@ struct poly1305_desc_ctx {
 	/* accumulator */
 	struct poly1305_state h;
 	/* key */
-	struct poly1305_key r[CONFIG_CRYPTO_LIB_POLY1305_RSIZE];
+	union {
+		struct poly1305_key opaque_r[CONFIG_CRYPTO_LIB_POLY1305_RSIZE];
+		struct poly1305_core_key core_r;
+	};
 };
 
 void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key);
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index f97f9b941110..6ecaf83a5a9a 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -28,7 +28,9 @@ obj-$(CONFIG_CRYPTO_LIB_DES)			+= libdes.o
 libdes-y					:= des.o
 
 obj-$(CONFIG_CRYPTO_LIB_POLY1305_GENERIC)	+= libpoly1305.o
-libpoly1305-y					:= poly1305.o
+libpoly1305-y					:= poly1305-donna32.o
+libpoly1305-$(CONFIG_ARCH_SUPPORTS_INT128)	:= poly1305-donna64.o
+libpoly1305-y					+= poly1305.o
 
 obj-$(CONFIG_CRYPTO_LIB_SHA256)			+= libsha256.o
 libsha256-y					:= sha256.o
diff --git a/lib/crypto/poly1305-donna32.c b/lib/crypto/poly1305-donna32.c
new file mode 100644
index 000000000000..3cc77d94390b
--- /dev/null
+++ b/lib/crypto/poly1305-donna32.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This is based in part on Andrew Moon's poly1305-donna, which is in the
+ * public domain.
+ */
+
+#include <linux/kernel.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/poly1305.h>
+
+void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16])
+{
+	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
+	key->key.r[0] = (get_unaligned_le32(&raw_key[0])) & 0x3ffffff;
+	key->key.r[1] = (get_unaligned_le32(&raw_key[3]) >> 2) & 0x3ffff03;
+	key->key.r[2] = (get_unaligned_le32(&raw_key[6]) >> 4) & 0x3ffc0ff;
+	key->key.r[3] = (get_unaligned_le32(&raw_key[9]) >> 6) & 0x3f03fff;
+	key->key.r[4] = (get_unaligned_le32(&raw_key[12]) >> 8) & 0x00fffff;
+
+	/* s = 5*r */
+	key->precomputed_s.r[0] = key->key.r[1] * 5;
+	key->precomputed_s.r[1] = key->key.r[2] * 5;
+	key->precomputed_s.r[2] = key->key.r[3] * 5;
+	key->precomputed_s.r[3] = key->key.r[4] * 5;
+}
+EXPORT_SYMBOL(poly1305_core_setkey);
+
+void poly1305_core_blocks(struct poly1305_state *state,
+			  const struct poly1305_core_key *key, const void *src,
+			  unsigned int nblocks, u32 hibit)
+{
+	const u8 *input = src;
+	u32 r0, r1, r2, r3, r4;
+	u32 s1, s2, s3, s4;
+	u32 h0, h1, h2, h3, h4;
+	u64 d0, d1, d2, d3, d4;
+	u32 c;
+
+	if (!nblocks)
+		return;
+
+	hibit <<= 24;
+
+	r0 = key->key.r[0];
+	r1 = key->key.r[1];
+	r2 = key->key.r[2];
+	r3 = key->key.r[3];
+	r4 = key->key.r[4];
+
+	s1 = key->precomputed_s.r[0];
+	s2 = key->precomputed_s.r[1];
+	s3 = key->precomputed_s.r[2];
+	s4 = key->precomputed_s.r[3];
+
+	h0 = state->h[0];
+	h1 = state->h[1];
+	h2 = state->h[2];
+	h3 = state->h[3];
+	h4 = state->h[4];
+
+	do {
+		/* h += m[i] */
+		h0 += (get_unaligned_le32(&input[0])) & 0x3ffffff;
+		h1 += (get_unaligned_le32(&input[3]) >> 2) & 0x3ffffff;
+		h2 += (get_unaligned_le32(&input[6]) >> 4) & 0x3ffffff;
+		h3 += (get_unaligned_le32(&input[9]) >> 6) & 0x3ffffff;
+		h4 += (get_unaligned_le32(&input[12]) >> 8) | hibit;
+
+		/* h *= r */
+		d0 = ((u64)h0 * r0) + ((u64)h1 * s4) +
+		     ((u64)h2 * s3) + ((u64)h3 * s2) +
+		     ((u64)h4 * s1);
+		d1 = ((u64)h0 * r1) + ((u64)h1 * r0) +
+		     ((u64)h2 * s4) + ((u64)h3 * s3) +
+		     ((u64)h4 * s2);
+		d2 = ((u64)h0 * r2) + ((u64)h1 * r1) +
+		     ((u64)h2 * r0) + ((u64)h3 * s4) +
+		     ((u64)h4 * s3);
+		d3 = ((u64)h0 * r3) + ((u64)h1 * r2) +
+		     ((u64)h2 * r1) + ((u64)h3 * r0) +
+		     ((u64)h4 * s4);
+		d4 = ((u64)h0 * r4) + ((u64)h1 * r3) +
+		     ((u64)h2 * r2) + ((u64)h3 * r1) +
+		     ((u64)h4 * r0);
+
+		/* (partial) h %= p */
+		c = (u32)(d0 >> 26);
+		h0 = (u32)d0 & 0x3ffffff;
+		d1 += c;
+		c = (u32)(d1 >> 26);
+		h1 = (u32)d1 & 0x3ffffff;
+		d2 += c;
+		c = (u32)(d2 >> 26);
+		h2 = (u32)d2 & 0x3ffffff;
+		d3 += c;
+		c = (u32)(d3 >> 26);
+		h3 = (u32)d3 & 0x3ffffff;
+		d4 += c;
+		c = (u32)(d4 >> 26);
+		h4 = (u32)d4 & 0x3ffffff;
+		h0 += c * 5;
+		c = (h0 >> 26);
+		h0 = h0 & 0x3ffffff;
+		h1 += c;
+
+		input += POLY1305_BLOCK_SIZE;
+	} while (--nblocks);
+
+	state->h[0] = h0;
+	state->h[1] = h1;
+	state->h[2] = h2;
+	state->h[3] = h3;
+	state->h[4] = h4;
+}
+EXPORT_SYMBOL(poly1305_core_blocks);
+
+void poly1305_core_emit(const struct poly1305_state *state, const u32 nonce[4],
+			void *dst)
+{
+	u8 *mac = dst;
+	u32 h0, h1, h2, h3, h4, c;
+	u32 g0, g1, g2, g3, g4;
+	u64 f;
+	u32 mask;
+
+	/* fully carry h */
+	h0 = state->h[0];
+	h1 = state->h[1];
+	h2 = state->h[2];
+	h3 = state->h[3];
+	h4 = state->h[4];
+
+	c = h1 >> 26;
+	h1 = h1 & 0x3ffffff;
+	h2 += c;
+	c = h2 >> 26;
+	h2 = h2 & 0x3ffffff;
+	h3 += c;
+	c = h3 >> 26;
+	h3 = h3 & 0x3ffffff;
+	h4 += c;
+	c = h4 >> 26;
+	h4 = h4 & 0x3ffffff;
+	h0 += c * 5;
+	c = h0 >> 26;
+	h0 = h0 & 0x3ffffff;
+	h1 += c;
+
+	/* compute h + -p */
+	g0 = h0 + 5;
+	c = g0 >> 26;
+	g0 &= 0x3ffffff;
+	g1 = h1 + c;
+	c = g1 >> 26;
+	g1 &= 0x3ffffff;
+	g2 = h2 + c;
+	c = g2 >> 26;
+	g2 &= 0x3ffffff;
+	g3 = h3 + c;
+	c = g3 >> 26;
+	g3 &= 0x3ffffff;
+	g4 = h4 + c - (1UL << 26);
+
+	/* select h if h < p, or h + -p if h >= p */
+	mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1;
+	g0 &= mask;
+	g1 &= mask;
+	g2 &= mask;
+	g3 &= mask;
+	g4 &= mask;
+	mask = ~mask;
+
+	h0 = (h0 & mask) | g0;
+	h1 = (h1 & mask) | g1;
+	h2 = (h2 & mask) | g2;
+	h3 = (h3 & mask) | g3;
+	h4 = (h4 & mask) | g4;
+
+	/* h = h % (2^128) */
+	h0 = ((h0) | (h1 << 26)) & 0xffffffff;
+	h1 = ((h1 >> 6) | (h2 << 20)) & 0xffffffff;
+	h2 = ((h2 >> 12) | (h3 << 14)) & 0xffffffff;
+	h3 = ((h3 >> 18) | (h4 << 8)) & 0xffffffff;
+
+	if (likely(nonce)) {
+		/* mac = (h + nonce) % (2^128) */
+		f = (u64)h0 + nonce[0];
+		h0 = (u32)f;
+		f = (u64)h1 + nonce[1] + (f >> 32);
+		h1 = (u32)f;
+		f = (u64)h2 + nonce[2] + (f >> 32);
+		h2 = (u32)f;
+		f = (u64)h3 + nonce[3] + (f >> 32);
+		h3 = (u32)f;
+	}
+
+	put_unaligned_le32(h0, &mac[0]);
+	put_unaligned_le32(h1, &mac[4]);
+	put_unaligned_le32(h2, &mac[8]);
+	put_unaligned_le32(h3, &mac[12]);
+}
+EXPORT_SYMBOL(poly1305_core_emit);
diff --git a/lib/crypto/poly1305-donna64.c b/lib/crypto/poly1305-donna64.c
new file mode 100644
index 000000000000..6ae181bb4345
--- /dev/null
+++ b/lib/crypto/poly1305-donna64.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This is based in part on Andrew Moon's poly1305-donna, which is in the
+ * public domain.
+ */
+
+#include <linux/kernel.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/poly1305.h>
+
+typedef __uint128_t u128;
+
+void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16])
+{
+	u64 t0, t1;
+
+	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
+	t0 = get_unaligned_le64(&raw_key[0]);
+	t1 = get_unaligned_le64(&raw_key[8]);
+
+	key->key.r64[0] = t0 & 0xffc0fffffffULL;
+	key->key.r64[1] = ((t0 >> 44) | (t1 << 20)) & 0xfffffc0ffffULL;
+	key->key.r64[2] = ((t1 >> 24)) & 0x00ffffffc0fULL;
+
+	/* s = 20*r */
+	key->precomputed_s.r64[0] = key->key.r64[1] * 20;
+	key->precomputed_s.r64[1] = key->key.r64[2] * 20;
+}
+EXPORT_SYMBOL(poly1305_core_setkey);
+
+void poly1305_core_blocks(struct poly1305_state *state,
+			  const struct poly1305_core_key *key, const void *src,
+			  unsigned int nblocks, u32 hibit)
+{
+	const u8 *input = src;
+	u64 hibit64;
+	u64 r0, r1, r2;
+	u64 s1, s2;
+	u64 h0, h1, h2;
+	u64 c;
+	u128 d0, d1, d2, d;
+
+	if (!nblocks)
+		return;
+
+	hibit64 = ((u64)hibit) << 40;
+
+	r0 = key->key.r64[0];
+	r1 = key->key.r64[1];
+	r2 = key->key.r64[2];
+
+	h0 = state->h64[0];
+	h1 = state->h64[1];
+	h2 = state->h64[2];
+
+	s1 = key->precomputed_s.r64[0];
+	s2 = key->precomputed_s.r64[1];
+
+	do {
+		u64 t0, t1;
+
+		/* h += m[i] */
+		t0 = get_unaligned_le64(&input[0]);
+		t1 = get_unaligned_le64(&input[8]);
+
+		h0 += t0 & 0xfffffffffffULL;
+		h1 += ((t0 >> 44) | (t1 << 20)) & 0xfffffffffffULL;
+		h2 += (((t1 >> 24)) & 0x3ffffffffffULL) | hibit64;
+
+		/* h *= r */
+		d0 = (u128)h0 * r0;
+		d = (u128)h1 * s2;
+		d0 += d;
+		d = (u128)h2 * s1;
+		d0 += d;
+		d1 = (u128)h0 * r1;
+		d = (u128)h1 * r0;
+		d1 += d;
+		d = (u128)h2 * s2;
+		d1 += d;
+		d2 = (u128)h0 * r2;
+		d = (u128)h1 * r1;
+		d2 += d;
+		d = (u128)h2 * r0;
+		d2 += d;
+
+		/* (partial) h %= p */
+		c = (u64)(d0 >> 44);
+		h0 = (u64)d0 & 0xfffffffffffULL;
+		d1 += c;
+		c = (u64)(d1 >> 44);
+		h1 = (u64)d1 & 0xfffffffffffULL;
+		d2 += c;
+		c = (u64)(d2 >> 42);
+		h2 = (u64)d2 & 0x3ffffffffffULL;
+		h0 += c * 5;
+		c = h0 >> 44;
+		h0 = h0 & 0xfffffffffffULL;
+		h1 += c;
+
+		input += POLY1305_BLOCK_SIZE;
+	} while (--nblocks);
+
+	state->h64[0] = h0;
+	state->h64[1] = h1;
+	state->h64[2] = h2;
+}
+EXPORT_SYMBOL(poly1305_core_blocks);
+
+void poly1305_core_emit(const struct poly1305_state *state, const u32 nonce[4],
+			void *dst)
+{
+	u8 *mac = dst;
+	u64 h0, h1, h2, c;
+	u64 g0, g1, g2;
+	u64 t0, t1;
+
+	/* fully carry h */
+	h0 = state->h64[0];
+	h1 = state->h64[1];
+	h2 = state->h64[2];
+
+	c = h1 >> 44;
+	h1 &= 0xfffffffffffULL;
+	h2 += c;
+	c = h2 >> 42;
+	h2 &= 0x3ffffffffffULL;
+	h0 += c * 5;
+	c = h0 >> 44;
+	h0 &= 0xfffffffffffULL;
+	h1 += c;
+	c = h1 >> 44;
+	h1 &= 0xfffffffffffULL;
+	h2 += c;
+	c = h2 >> 42;
+	h2 &= 0x3ffffffffffULL;
+	h0 += c * 5;
+	c = h0 >> 44;
+	h0 &= 0xfffffffffffULL;
+	h1 += c;
+
+	/* compute h + -p */
+	g0 = h0 + 5;
+	c  = g0 >> 44;
+	g0 &= 0xfffffffffffULL;
+	g1 = h1 + c;
+	c  = g1 >> 44;
+	g1 &= 0xfffffffffffULL;
+	g2 = h2 + c - (1ULL << 42);
+
+	/* select h if h < p, or h + -p if h >= p */
+	c = (g2 >> ((sizeof(u64) * 8) - 1)) - 1;
+	g0 &= c;
+	g1 &= c;
+	g2 &= c;
+	c  = ~c;
+	h0 = (h0 & c) | g0;
+	h1 = (h1 & c) | g1;
+	h2 = (h2 & c) | g2;
+
+	if (likely(nonce)) {
+		/* h = (h + nonce) */
+		t0 = ((u64)nonce[1] << 32) | nonce[0];
+		t1 = ((u64)nonce[3] << 32) | nonce[2];
+
+		h0 += t0 & 0xfffffffffffULL;
+		c = h0 >> 44;
+		h0 &= 0xfffffffffffULL;
+		h1 += (((t0 >> 44) | (t1 << 20)) & 0xfffffffffffULL) + c;
+		c = h1 >> 44;
+		h1 &= 0xfffffffffffULL;
+		h2 += (((t1 >> 24)) & 0x3ffffffffffULL) + c;
+		h2 &= 0x3ffffffffffULL;
+	}
+
+	/* mac = h % (2^128) */
+	h0 = h0 | (h1 << 44);
+	h1 = (h1 >> 20) | (h2 << 24);
+
+	put_unaligned_le64(h0, &mac[0]);
+	put_unaligned_le64(h1, &mac[8]);
+}
+EXPORT_SYMBOL(poly1305_core_emit);
diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c
index 32ec293c65ae..9d2d14df0fee 100644
--- a/lib/crypto/poly1305.c
+++ b/lib/crypto/poly1305.c
@@ -12,151 +12,9 @@
 #include <linux/module.h>
 #include <asm/unaligned.h>
 
-static inline u64 mlt(u64 a, u64 b)
-{
-	return a * b;
-}
-
-static inline u32 sr(u64 v, u_char n)
-{
-	return v >> n;
-}
-
-static inline u32 and(u32 v, u32 mask)
-{
-	return v & mask;
-}
-
-void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key)
-{
-	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
-	key->r[0] = (get_unaligned_le32(raw_key +  0) >> 0) & 0x3ffffff;
-	key->r[1] = (get_unaligned_le32(raw_key +  3) >> 2) & 0x3ffff03;
-	key->r[2] = (get_unaligned_le32(raw_key +  6) >> 4) & 0x3ffc0ff;
-	key->r[3] = (get_unaligned_le32(raw_key +  9) >> 6) & 0x3f03fff;
-	key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff;
-}
-EXPORT_SYMBOL_GPL(poly1305_core_setkey);
-
-void poly1305_core_blocks(struct poly1305_state *state,
-			  const struct poly1305_key *key, const void *src,
-			  unsigned int nblocks, u32 hibit)
-{
-	u32 r0, r1, r2, r3, r4;
-	u32 s1, s2, s3, s4;
-	u32 h0, h1, h2, h3, h4;
-	u64 d0, d1, d2, d3, d4;
-
-	if (!nblocks)
-		return;
-
-	r0 = key->r[0];
-	r1 = key->r[1];
-	r2 = key->r[2];
-	r3 = key->r[3];
-	r4 = key->r[4];
-
-	s1 = r1 * 5;
-	s2 = r2 * 5;
-	s3 = r3 * 5;
-	s4 = r4 * 5;
-
-	h0 = state->h[0];
-	h1 = state->h[1];
-	h2 = state->h[2];
-	h3 = state->h[3];
-	h4 = state->h[4];
-
-	do {
-		/* h += m[i] */
-		h0 += (get_unaligned_le32(src +  0) >> 0) & 0x3ffffff;
-		h1 += (get_unaligned_le32(src +  3) >> 2) & 0x3ffffff;
-		h2 += (get_unaligned_le32(src +  6) >> 4) & 0x3ffffff;
-		h3 += (get_unaligned_le32(src +  9) >> 6) & 0x3ffffff;
-		h4 += (get_unaligned_le32(src + 12) >> 8) | (hibit << 24);
-
-		/* h *= r */
-		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) +
-		     mlt(h3, s2) + mlt(h4, s1);
-		d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) +
-		     mlt(h3, s3) + mlt(h4, s2);
-		d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) +
-		     mlt(h3, s4) + mlt(h4, s3);
-		d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) +
-		     mlt(h3, r0) + mlt(h4, s4);
-		d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) +
-		     mlt(h3, r1) + mlt(h4, r0);
-
-		/* (partial) h %= p */
-		d1 += sr(d0, 26);     h0 = and(d0, 0x3ffffff);
-		d2 += sr(d1, 26);     h1 = and(d1, 0x3ffffff);
-		d3 += sr(d2, 26);     h2 = and(d2, 0x3ffffff);
-		d4 += sr(d3, 26);     h3 = and(d3, 0x3ffffff);
-		h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff);
-		h1 += h0 >> 26;       h0 = h0 & 0x3ffffff;
-
-		src += POLY1305_BLOCK_SIZE;
-	} while (--nblocks);
-
-	state->h[0] = h0;
-	state->h[1] = h1;
-	state->h[2] = h2;
-	state->h[3] = h3;
-	state->h[4] = h4;
-}
-EXPORT_SYMBOL_GPL(poly1305_core_blocks);
-
-void poly1305_core_emit(const struct poly1305_state *state, void *dst)
-{
-	u32 h0, h1, h2, h3, h4;
-	u32 g0, g1, g2, g3, g4;
-	u32 mask;
-
-	/* fully carry h */
-	h0 = state->h[0];
-	h1 = state->h[1];
-	h2 = state->h[2];
-	h3 = state->h[3];
-	h4 = state->h[4];
-
-	h2 += (h1 >> 26);     h1 = h1 & 0x3ffffff;
-	h3 += (h2 >> 26);     h2 = h2 & 0x3ffffff;
-	h4 += (h3 >> 26);     h3 = h3 & 0x3ffffff;
-	h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff;
-	h1 += (h0 >> 26);     h0 = h0 & 0x3ffffff;
-
-	/* compute h + -p */
-	g0 = h0 + 5;
-	g1 = h1 + (g0 >> 26);             g0 &= 0x3ffffff;
-	g2 = h2 + (g1 >> 26);             g1 &= 0x3ffffff;
-	g3 = h3 + (g2 >> 26);             g2 &= 0x3ffffff;
-	g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff;
-
-	/* select h if h < p, or h + -p if h >= p */
-	mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1;
-	g0 &= mask;
-	g1 &= mask;
-	g2 &= mask;
-	g3 &= mask;
-	g4 &= mask;
-	mask = ~mask;
-	h0 = (h0 & mask) | g0;
-	h1 = (h1 & mask) | g1;
-	h2 = (h2 & mask) | g2;
-	h3 = (h3 & mask) | g3;
-	h4 = (h4 & mask) | g4;
-
-	/* h = h % (2^128) */
-	put_unaligned_le32((h0 >>  0) | (h1 << 26), dst +  0);
-	put_unaligned_le32((h1 >>  6) | (h2 << 20), dst +  4);
-	put_unaligned_le32((h2 >> 12) | (h3 << 14), dst +  8);
-	put_unaligned_le32((h3 >> 18) | (h4 <<  8), dst + 12);
-}
-EXPORT_SYMBOL_GPL(poly1305_core_emit);
-
 void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key)
 {
-	poly1305_core_setkey(desc->r, key);
+	poly1305_core_setkey(&desc->core_r, key);
 	desc->s[0] = get_unaligned_le32(key + 16);
 	desc->s[1] = get_unaligned_le32(key + 20);
 	desc->s[2] = get_unaligned_le32(key + 24);
@@ -164,7 +22,7 @@ void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key)
 	poly1305_core_init(&desc->h);
 	desc->buflen = 0;
 	desc->sset = true;
-	desc->rset = 1;
+	desc->rset = 2;
 }
 EXPORT_SYMBOL_GPL(poly1305_init_generic);
 
@@ -181,13 +39,14 @@ void poly1305_update_generic(struct poly1305_desc_ctx *desc, const u8 *src,
 		desc->buflen += bytes;
 
 		if (desc->buflen == POLY1305_BLOCK_SIZE) {
-			poly1305_core_blocks(&desc->h, desc->r, desc->buf, 1, 1);
+			poly1305_core_blocks(&desc->h, &desc->core_r, desc->buf,
+					     1, 1);
 			desc->buflen = 0;
 		}
 	}
 
 	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
-		poly1305_core_blocks(&desc->h, desc->r, src,
+		poly1305_core_blocks(&desc->h, &desc->core_r, src,
 				     nbytes / POLY1305_BLOCK_SIZE, 1);
 		src += nbytes - (nbytes % POLY1305_BLOCK_SIZE);
 		nbytes %= POLY1305_BLOCK_SIZE;
@@ -202,28 +61,14 @@ EXPORT_SYMBOL_GPL(poly1305_update_generic);
 
 void poly1305_final_generic(struct poly1305_desc_ctx *desc, u8 *dst)
 {
-	__le32 digest[4];
-	u64 f = 0;
-
 	if (unlikely(desc->buflen)) {
 		desc->buf[desc->buflen++] = 1;
 		memset(desc->buf + desc->buflen, 0,
 		       POLY1305_BLOCK_SIZE - desc->buflen);
-		poly1305_core_blocks(&desc->h, desc->r, desc->buf, 1, 0);
+		poly1305_core_blocks(&desc->h, &desc->core_r, desc->buf, 1, 0);
 	}
 
-	poly1305_core_emit(&desc->h, digest);
-
-	/* mac = (h + s) % (2^128) */
-	f = (f >> 32) + le32_to_cpu(digest[0]) + desc->s[0];
-	put_unaligned_le32(f, dst + 0);
-	f = (f >> 32) + le32_to_cpu(digest[1]) + desc->s[1];
-	put_unaligned_le32(f, dst + 4);
-	f = (f >> 32) + le32_to_cpu(digest[2]) + desc->s[2];
-	put_unaligned_le32(f, dst + 8);
-	f = (f >> 32) + le32_to_cpu(digest[3]) + desc->s[3];
-	put_unaligned_le32(f, dst + 12);
-
+	poly1305_core_emit(&desc->h, desc->s, dst);
 	*desc = (struct poly1305_desc_ctx){};
 }
 EXPORT_SYMBOL_GPL(poly1305_final_generic);
-- 
cgit v1.2.3