Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto update from Herbert Xu:
 "API:
   - Add support for AEAD in simd
   - Add fuzz testing to testmgr
   - Add panic_on_fail module parameter to testmgr
   - Use per-CPU struct instead multiple variables in scompress
   - Change verify API for akcipher

  Algorithms:
   - Convert x86 AEAD algorithms over to simd
   - Forbid 2-key 3DES in FIPS mode
   - Add EC-RDSA (GOST 34.10) algorithm

  Drivers:
   - Set output IV with ctr-aes in crypto4xx
   - Set output IV in rockchip
   - Fix potential length overflow with hashing in sun4i-ss
   - Fix computation error with ctr in vmx
   - Add SM4 protected keys support in ccree
   - Remove long-broken mxc-scc driver
   - Add rfc4106(gcm(aes)) cipher support in cavium/nitrox"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (179 commits)
  crypto: ccree - use a proper le32 type for le32 val
  crypto: ccree - remove set but not used variable 'du_size'
  crypto: ccree - Make cc_sec_disable static
  crypto: ccree - fix spelling mistake "protedcted" -> "protected"
  crypto: caam/qi2 - generate hash keys in-place
  crypto: caam/qi2 - fix DMA mapping of stack memory
  crypto: caam/qi2 - fix zero-length buffer DMA mapping
  crypto: stm32/cryp - update to return iv_out
  crypto: stm32/cryp - remove request mutex protection
  crypto: stm32/cryp - add weak key check for DES
  crypto: atmel - remove set but not used variable 'alg_name'
  crypto: picoxcell - Use dev_get_drvdata()
  crypto: crypto4xx - get rid of redundant using_sd variable
  crypto: crypto4xx - use sync skcipher for fallback
  crypto: crypto4xx - fix cfb and ofb "overran dst buffer" issues
  crypto: crypto4xx - fix ctr-aes missing output IV
  crypto: ecrdsa - select ASN1 and OID_REGISTRY for EC-RDSA
  crypto: ux500 - use ccflags-y instead of CFLAGS_<basename>.o
  crypto: ccree - handle tee fips error during power management resume
  crypto: ccree - add function to handle cryptocell tee fips error
  ...

Documentation/crypto/api-samples.rst

@@ -133,7 +133,6 @@ Code Example For Use of Operational State Memory With SHASH
         if (!sdesc)
             return ERR_PTR(-ENOMEM);
         sdesc->shash.tfm = alg;
-        sdesc->shash.flags = 0x0;
         return sdesc;
     }
 

arch/arm/crypto/aes-neonbs-glue.c

@@ -278,6 +278,8 @@ static int __xts_crypt(struct skcipher_request *req,
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	crypto_cipher_encrypt_one(ctx->tweak_tfm, walk.iv, walk.iv);
 

arch/arm/crypto/chacha-neon-glue.c

@@ -21,6 +21,7 @@
 
 #include <crypto/algapi.h>
 #include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -93,7 +94,7 @@ static int chacha_neon(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_chacha_crypt(req);
 
 	return chacha_neon_stream_xor(req, ctx, req->iv);
@@ -107,7 +108,7 @@ static int xchacha_neon(struct skcipher_request *req)
 	u32 state[16];
 	u8 real_iv[16];
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_xchacha_crypt(req);
 
 	crypto_chacha_init(state, ctx, req->iv);

arch/arm/crypto/crc32-ce-glue.c

@@ -16,6 +16,7 @@
 #include <linux/string.h>
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 
 #include <asm/hwcap.h>
 #include <asm/neon.h>
@@ -113,7 +114,7 @@ static int crc32_pmull_update(struct shash_desc *desc, const u8 *data,
 	u32 *crc = shash_desc_ctx(desc);
 	unsigned int l;
 
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		if ((u32)data % SCALE_F) {
 			l = min_t(u32, length, SCALE_F - ((u32)data % SCALE_F));
 
@@ -147,7 +148,7 @@ static int crc32c_pmull_update(struct shash_desc *desc, const u8 *data,
 	u32 *crc = shash_desc_ctx(desc);
 	unsigned int l;
 
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		if ((u32)data % SCALE_F) {
 			l = min_t(u32, length, SCALE_F - ((u32)data % SCALE_F));
 

arch/arm/crypto/crct10dif-ce-glue.c

@@ -15,6 +15,7 @@
 #include <linux/string.h>
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 
 #include <asm/neon.h>
 #include <asm/simd.h>
@@ -36,7 +37,7 @@ static int crct10dif_update(struct shash_desc *desc, const u8 *data,
 {
 	u16 *crc = shash_desc_ctx(desc);
 
-	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) {
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
 		kernel_neon_begin();
 		*crc = crc_t10dif_pmull(*crc, data, length);
 		kernel_neon_end();

arch/arm/crypto/ghash-ce-glue.c

@@ -14,6 +14,7 @@
 #include <asm/unaligned.h>
 #include <crypto/cryptd.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/gf128mul.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
@@ -185,7 +186,6 @@ static int ghash_async_init(struct ahash_request *req)
 	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
 	desc->tfm = child;
-	desc->flags = req->base.flags;
 	return crypto_shash_init(desc);
 }
 
@@ -196,7 +196,7 @@ static int ghash_async_update(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -214,7 +214,7 @@ static int ghash_async_final(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -232,7 +232,7 @@ static int ghash_async_digest(struct ahash_request *req)
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -242,7 +242,6 @@ static int ghash_async_digest(struct ahash_request *req)
 		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
 		desc->tfm = child;
-		desc->flags = req->base.flags;
 		return shash_ahash_digest(req, desc);
 	}
 }
@@ -255,7 +254,6 @@ static int ghash_async_import(struct ahash_request *req, const void *in)
 	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
 
 	desc->tfm = cryptd_ahash_child(ctx->cryptd_tfm);
-	desc->flags = req->base.flags;
 
 	return crypto_shash_import(desc, in);
 }

arch/arm/crypto/nhpoly1305-neon-glue.c

@@ -9,6 +9,7 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
 
@@ -25,7 +26,7 @@ static void _nh_neon(const u32 *key, const u8 *message, size_t message_len,
 static int nhpoly1305_neon_update(struct shash_desc *desc,
 				  const u8 *src, unsigned int srclen)
 {
-	if (srclen < 64 || !may_use_simd())
+	if (srclen < 64 || !crypto_simd_usable())
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {

arch/arm/crypto/sha1-ce-glue.c

@@ -9,6 +9,7 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
 #include <linux/cpufeature.h>
@@ -33,7 +34,7 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
 		return sha1_update_arm(desc, data, len);
 
@@ -47,7 +48,7 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 			 unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return sha1_finup_arm(desc, data, len, out);
 
 	kernel_neon_begin();

arch/arm/crypto/sha1_neon_glue.c

@@ -19,6 +19,7 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -39,7 +40,7 @@ static int sha1_neon_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
 		return sha1_update_arm(desc, data, len);
 
@@ -54,7 +55,7 @@ static int sha1_neon_update(struct shash_desc *desc, const u8 *data,
 static int sha1_neon_finup(struct shash_desc *desc, const u8 *data,
 			   unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return sha1_finup_arm(desc, data, len, out);
 
 	kernel_neon_begin();

arch/arm/crypto/sha2-ce-glue.c

@@ -9,6 +9,7 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
 #include <linux/cpufeature.h>
@@ -34,7 +35,7 @@ static int sha2_ce_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
 		return crypto_sha256_arm_update(desc, data, len);
 
@@ -49,7 +50,7 @@ static int sha2_ce_update(struct shash_desc *desc, const u8 *data,
 static int sha2_ce_finup(struct shash_desc *desc, const u8 *data,
 			 unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sha256_arm_finup(desc, data, len, out);
 
 	kernel_neon_begin();

arch/arm/crypto/sha256_neon_glue.c

@@ -15,6 +15,7 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -34,7 +35,7 @@ static int sha256_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
 		return crypto_sha256_arm_update(desc, data, len);
 
@@ -49,7 +50,7 @@ static int sha256_update(struct shash_desc *desc, const u8 *data,
 static int sha256_finup(struct shash_desc *desc, const u8 *data,
 			unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sha256_arm_finup(desc, data, len, out);
 
 	kernel_neon_begin();

arch/arm/crypto/sha512-neon-glue.c

@@ -9,6 +9,7 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha512_base.h>
 #include <linux/crypto.h>
@@ -30,7 +31,7 @@ static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
 		return sha512_arm_update(desc, data, len);
 
@@ -45,7 +46,7 @@ static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
 static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
 			     unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return sha512_arm_finup(desc, data, len, out);
 
 	kernel_neon_begin();

arch/arm64/crypto/aes-ce-ccm-glue.c

@@ -14,6 +14,7 @@
 #include <crypto/aes.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/module.h>
 
@@ -109,7 +110,7 @@ static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
 static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[],
 			   u32 abytes, u32 *macp)
 {
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		kernel_neon_begin();
 		ce_aes_ccm_auth_data(mac, in, abytes, macp, key->key_enc,
 				     num_rounds(key));
@@ -255,7 +256,7 @@ static int ccm_encrypt(struct aead_request *req)
 
 	err = skcipher_walk_aead_encrypt(&walk, req, false);
 
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		while (walk.nbytes) {
 			u32 tail = walk.nbytes % AES_BLOCK_SIZE;
 
@@ -313,7 +314,7 @@ static int ccm_decrypt(struct aead_request *req)
 
 	err = skcipher_walk_aead_decrypt(&walk, req, false);
 
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		while (walk.nbytes) {
 			u32 tail = walk.nbytes % AES_BLOCK_SIZE;
 

arch/arm64/crypto/aes-ce-glue.c

@@ -12,6 +12,7 @@
 #include <asm/simd.h>
 #include <asm/unaligned.h>
 #include <crypto/aes.h>
+#include <crypto/internal/simd.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
@@ -52,7 +53,7 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		__aes_arm64_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
 		return;
 	}
@@ -66,7 +67,7 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		__aes_arm64_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
 		return;
 	}

arch/arm64/crypto/aes-glue.c

@@ -405,7 +405,7 @@ static int ctr_encrypt_sync(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return aes_ctr_encrypt_fallback(ctx, req);
 
 	return ctr_encrypt(req);
@@ -642,7 +642,7 @@ static void mac_do_update(struct crypto_aes_ctx *ctx, u8 const in[], int blocks,
 {
 	int rounds = 6 + ctx->key_length / 4;
 
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		kernel_neon_begin();
 		aes_mac_update(in, ctx->key_enc, rounds, blocks, dg, enc_before,
 			       enc_after);
@@ -707,7 +707,7 @@ static int cbcmac_final(struct shash_desc *desc, u8 *out)
 	struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	mac_do_update(&tctx->key, NULL, 0, ctx->dg, 1, 0);
+	mac_do_update(&tctx->key, NULL, 0, ctx->dg, (ctx->len != 0), 0);
 
 	memcpy(out, ctx->dg, AES_BLOCK_SIZE);
 

arch/arm64/crypto/aes-neonbs-glue.c

@@ -288,7 +288,7 @@ static int ctr_encrypt_sync(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return aes_ctr_encrypt_fallback(&ctx->fallback, req);
 
 	return ctr_encrypt(req);
@@ -304,6 +304,8 @@ static int __xts_crypt(struct skcipher_request *req,
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
 
 	kernel_neon_begin();
 	neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey, ctx->key.rounds, 1);

arch/arm64/crypto/chacha-neon-glue.c

@@ -21,6 +21,7 @@
 
 #include <crypto/algapi.h>
 #include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -90,7 +91,7 @@ static int chacha_neon(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_chacha_crypt(req);
 
 	return chacha_neon_stream_xor(req, ctx, req->iv);
@@ -104,7 +105,7 @@ static int xchacha_neon(struct skcipher_request *req)
 	u32 state[16];
 	u8 real_iv[16];
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_xchacha_crypt(req);
 
 	crypto_chacha_init(state, ctx, req->iv);

arch/arm64/crypto/crct10dif-ce-glue.c

@@ -16,6 +16,7 @@
 #include <linux/string.h>
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 
 #include <asm/neon.h>
 #include <asm/simd.h>
@@ -38,7 +39,7 @@ static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data,
 {
 	u16 *crc = shash_desc_ctx(desc);
 
-	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) {
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
 		kernel_neon_begin();
 		*crc = crc_t10dif_pmull_p8(*crc, data, length);
 		kernel_neon_end();
@@ -54,7 +55,7 @@ static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data,
 {
 	u16 *crc = shash_desc_ctx(desc);
 
-	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) {
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
 		kernel_neon_begin();
 		*crc = crc_t10dif_pmull_p64(*crc, data, length);
 		kernel_neon_end();

arch/arm64/crypto/ghash-ce-glue.c

@@ -17,6 +17,7 @@
 #include <crypto/gf128mul.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/cpufeature.h>
@@ -89,7 +90,7 @@ static void ghash_do_update(int blocks, u64 dg[], const char *src,
 						struct ghash_key const *k,
 						const char *head))
 {
-	if (likely(may_use_simd())) {
+	if (likely(crypto_simd_usable())) {
 		kernel_neon_begin();
 		simd_update(blocks, dg, src, key, head);
 		kernel_neon_end();
@@ -441,7 +442,7 @@ static int gcm_encrypt(struct aead_request *req)
 
 	err = skcipher_walk_aead_encrypt(&walk, req, false);
 
-	if (likely(may_use_simd() && walk.total >= 2 * AES_BLOCK_SIZE)) {
+	if (likely(crypto_simd_usable() && walk.total >= 2 * AES_BLOCK_SIZE)) {
 		u32 const *rk = NULL;
 
 		kernel_neon_begin();
@@ -473,9 +474,11 @@ static int gcm_encrypt(struct aead_request *req)
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
-			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			const int blocks =
+				walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 			u8 *dst = walk.dst.virt.addr;
 			u8 *src = walk.src.virt.addr;
+			int remaining = blocks;
 
 			do {
 				__aes_arm64_encrypt(ctx->aes_key.key_enc,
@@ -485,9 +488,9 @@ static int gcm_encrypt(struct aead_request *req)
 
 				dst += AES_BLOCK_SIZE;
 				src += AES_BLOCK_SIZE;
-			} while (--blocks > 0);
+			} while (--remaining > 0);
 
-			ghash_do_update(walk.nbytes / AES_BLOCK_SIZE, dg,
+			ghash_do_update(blocks, dg,
 					walk.dst.virt.addr, &ctx->ghash_key,
 					NULL, pmull_ghash_update_p64);
 
@@ -563,7 +566,7 @@ static int gcm_decrypt(struct aead_request *req)
 
 	err = skcipher_walk_aead_decrypt(&walk, req, false);
 
-	if (likely(may_use_simd() && walk.total >= 2 * AES_BLOCK_SIZE)) {
+	if (likely(crypto_simd_usable() && walk.total >= 2 * AES_BLOCK_SIZE)) {
 		u32 const *rk = NULL;
 
 		kernel_neon_begin();
@@ -609,7 +612,7 @@ static int gcm_decrypt(struct aead_request *req)
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
-			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 			u8 *dst = walk.dst.virt.addr;
 			u8 *src = walk.src.virt.addr;
 

arch/arm64/crypto/nhpoly1305-neon-glue.c

@@ -9,6 +9,7 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
 
@@ -25,7 +26,7 @@ static void _nh_neon(const u32 *key, const u8 *message, size_t message_len,
 static int nhpoly1305_neon_update(struct shash_desc *desc,
 				  const u8 *src, unsigned int srclen)
 {
-	if (srclen < 64 || !may_use_simd())
+	if (srclen < 64 || !crypto_simd_usable())
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {