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

Pull crypto updates from Herbert Xu:
 "API:
   - Add support for allocating transforms on a specific NUMA Node
   - Introduce the flag CRYPTO_ALG_ALLOCATES_MEMORY for storage users

  Algorithms:
   - Drop PMULL based ghash on arm64
   - Fixes for building with clang on x86
   - Add sha256 helper that does the digest in one go
   - Add SP800-56A rev 3 validation checks to dh

  Drivers:
   - Permit users to specify NUMA node in hisilicon/zip
   - Add support for i.MX6 in imx-rngc
   - Add sa2ul crypto driver
   - Add BA431 hwrng driver
   - Add Ingenic JZ4780 and X1000 hwrng driver
   - Spread IRQ affinity in inside-secure and marvell/cesa"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (157 commits)
  crypto: sa2ul - Fix inconsistent IS_ERR and PTR_ERR
  hwrng: core - remove redundant initialization of variable ret
  crypto: x86/curve25519 - Remove unused carry variables
  crypto: ingenic - Add hardware RNG for Ingenic JZ4780 and X1000
  dt-bindings: RNG: Add Ingenic RNG bindings.
  crypto: caam/qi2 - add module alias
  crypto: caam - add more RNG hw error codes
  crypto: caam/jr - remove incorrect reference to caam_jr_register()
  crypto: caam - silence .setkey in case of bad key length
  crypto: caam/qi2 - create ahash shared descriptors only once
  crypto: caam/qi2 - fix error reporting for caam_hash_alloc
  crypto: caam - remove deadcode on 32-bit platforms
  crypto: ccp - use generic power management
  crypto: xts - Replace memcpy() invocation with simple assignment
  crypto: marvell/cesa - irq balance
  crypto: inside-secure - irq balance
  crypto: ecc - SP800-56A rev 3 local public key validation
  crypto: dh - SP800-56A rev 3 local public key validation
  crypto: dh - check validity of Z before export
  lib/mpi: Add mpi_sub_ui()
  ...

19 files changed, 551 insertions, 815 deletions

diff --git a/arch/arm/crypto/crc32-ce-core.S b/arch/arm/crypto/crc32-ce-core.S
index 5cbd4a6fedad..3f13a76b9066 100644
--- a/arch/arm/crypto/crc32-ce-core.S
+++ b/arch/arm/crypto/crc32-ce-core.S
@@ -39,7 +39,7 @@
  * CRC32 polynomial:0x04c11db7(BE)/0xEDB88320(LE)
  * PCLMULQDQ is a new instruction in Intel SSE4.2, the reference can be found
  * at:
- * http://www.intel.com/products/processor/manuals/
+ * https://www.intel.com/products/processor/manuals/
  * Intel(R) 64 and IA-32 Architectures Software Developer's Manual
  * Volume 2B: Instruction Set Reference, N-Z
  *
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index a00fd329255f..f13401f3e669 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -16,6 +16,7 @@
 #include <crypto/gf128mul.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
+#include <linux/jump_label.h>
 #include <linux/module.h>
 
 MODULE_DESCRIPTION("GHASH hash function using ARMv8 Crypto Extensions");
@@ -27,12 +28,8 @@ MODULE_ALIAS_CRYPTO("ghash");
 #define GHASH_DIGEST_SIZE	16
 
 struct ghash_key {
-	u64	h[2];
-	u64	h2[2];
-	u64	h3[2];
-	u64	h4[2];
-
 	be128	k;
+	u64	h[][2];
 };
 
 struct ghash_desc_ctx {
@@ -46,16 +43,12 @@ struct ghash_async_ctx {
 };
 
 asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
-				       struct ghash_key const *k,
-				       const char *head);
+				       u64 const h[][2], const char *head);
 
 asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
-				      struct ghash_key const *k,
-				      const char *head);
+				      u64 const h[][2], const char *head);
 
-static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src,
-				  struct ghash_key const *k,
-				  const char *head);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_p64);
 
 static int ghash_init(struct shash_desc *desc)
 {
@@ -70,7 +63,10 @@ static void ghash_do_update(int blocks, u64 dg[], const char *src,
 {
 	if (likely(crypto_simd_usable())) {
 		kernel_neon_begin();
-		pmull_ghash_update(blocks, dg, src, key, head);
+		if (static_branch_likely(&use_p64))
+			pmull_ghash_update_p64(blocks, dg, src, key->h, head);
+		else
+			pmull_ghash_update_p8(blocks, dg, src, key->h, head);
 		kernel_neon_end();
 	} else {
 		be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
@@ -161,25 +157,26 @@ static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *inkey, unsigned int keylen)
 {
 	struct ghash_key *key = crypto_shash_ctx(tfm);
-	be128 h;
 
 	if (keylen != GHASH_BLOCK_SIZE)
 		return -EINVAL;
 
 	/* needed for the fallback */
 	memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
-	ghash_reflect(key->h, &key->k);
+	ghash_reflect(key->h[0], &key->k);
 
-	h = key->k;
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h2, &h);
+	if (static_branch_likely(&use_p64)) {
+		be128 h = key->k;
 
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h3, &h);
+		gf128mul_lle(&h, &key->k);
+		ghash_reflect(key->h[1], &h);
 
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h4, &h);
+		gf128mul_lle(&h, &key->k);
+		ghash_reflect(key->h[2], &h);
 
+		gf128mul_lle(&h, &key->k);
+		ghash_reflect(key->h[3], &h);
+	}
 	return 0;
 }
 
@@ -195,7 +192,7 @@ static struct shash_alg ghash_alg = {
 	.base.cra_driver_name	= "ghash-ce-sync",
 	.base.cra_priority	= 300 - 1,
 	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct ghash_key),
+	.base.cra_ctxsize	= sizeof(struct ghash_key) + sizeof(u64[2]),
 	.base.cra_module	= THIS_MODULE,
 };
 
@@ -354,10 +351,10 @@ static int __init ghash_ce_mod_init(void)
 	if (!(elf_hwcap & HWCAP_NEON))
 		return -ENODEV;
 
-	if (elf_hwcap2 & HWCAP2_PMULL)
-		pmull_ghash_update = pmull_ghash_update_p64;
-	else
-		pmull_ghash_update = pmull_ghash_update_p8;
+	if (elf_hwcap2 & HWCAP2_PMULL) {
+		ghash_alg.base.cra_ctxsize += 3 * sizeof(u64[2]);
+		static_branch_enable(&use_p64);
+	}
 
 	err = crypto_register_shash(&ghash_alg);
 	if (err)
diff --git a/arch/arm/crypto/sha1-armv4-large.S b/arch/arm/crypto/sha1-armv4-large.S
index f82cd8cf5a09..1c8b685149f2 100644
--- a/arch/arm/crypto/sha1-armv4-large.S
+++ b/arch/arm/crypto/sha1-armv4-large.S
@@ -13,7 +13,7 @@
 @ Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
 @ project. The module is, however, dual licensed under OpenSSL and
 @ CRYPTOGAMS licenses depending on where you obtain it. For further
-@ details see http://www.openssl.org/~appro/cryptogams/.
+@ details see https://www.openssl.org/~appro/cryptogams/.
 @ ====================================================================
 
 @ sha1_block procedure for ARMv4.
diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl
index a03cf4dfb781..9f96ff48e4a8 100644
--- a/arch/arm/crypto/sha256-armv4.pl
+++ b/arch/arm/crypto/sha256-armv4.pl
@@ -13,7 +13,7 @@
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 # project. The module is, however, dual licensed under OpenSSL and
 # CRYPTOGAMS licenses depending on where you obtain it. For further
-# details see http://www.openssl.org/~appro/cryptogams/.
+# details see https://www.openssl.org/~appro/cryptogams/.
 # ====================================================================
 
 # SHA256 block procedure for ARMv4. May 2007.
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
index 054aae0edfce..ea04b2ab0c33 100644
--- a/arch/arm/crypto/sha256-core.S_shipped
+++ b/arch/arm/crypto/sha256-core.S_shipped
@@ -12,7 +12,7 @@
 @ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 @ project. The module is, however, dual licensed under OpenSSL and
 @ CRYPTOGAMS licenses depending on where you obtain it. For further
-@ details see http://www.openssl.org/~appro/cryptogams/.
+@ details see https://www.openssl.org/~appro/cryptogams/.
 @ ====================================================================
 
 @ SHA256 block procedure for ARMv4. May 2007.
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
index 788c17b56ecc..69df68981acd 100644
--- a/arch/arm/crypto/sha512-armv4.pl
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -13,7 +13,7 @@
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 # project. The module is, however, dual licensed under OpenSSL and
 # CRYPTOGAMS licenses depending on where you obtain it. For further
-# details see http://www.openssl.org/~appro/cryptogams/.
+# details see https://www.openssl.org/~appro/cryptogams/.
 # ====================================================================
 
 # SHA512 block procedure for ARMv4. September 2007.
@@ -43,7 +43,7 @@
 # terms it's 22.6 cycles per byte, which is disappointing result.
 # Technical writers asserted that 3-way S4 pipeline can sustain
 # multiple NEON instructions per cycle, but dual NEON issue could
-# not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+# not be observed, see https://www.openssl.org/~appro/Snapdragon-S4.html
 # for further details. On side note Cortex-A15 processes one byte in
 # 16 cycles.
 
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
index 710ea309769e..cb147db5cbfe 100644
--- a/arch/arm/crypto/sha512-core.S_shipped
+++ b/arch/arm/crypto/sha512-core.S_shipped
@@ -12,7 +12,7 @@
 @ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 @ project. The module is, however, dual licensed under OpenSSL and
 @ CRYPTOGAMS licenses depending on where you obtain it. For further
-@ details see http://www.openssl.org/~appro/cryptogams/.
+@ details see https://www.openssl.org/~appro/cryptogams/.
 @ ====================================================================
 
 @ SHA512 block procedure for ARMv4. September 2007.
@@ -42,7 +42,7 @@
 @ terms it's 22.6 cycles per byte, which is disappointing result.
 @ Technical writers asserted that 3-way S4 pipeline can sustain
 @ multiple NEON instructions per cycle, but dual NEON issue could
-@ not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+@ not be observed, see https://www.openssl.org/~appro/Snapdragon-S4.html
 @ for further details. On side note Cortex-A15 processes one byte in
 @ 16 cycles.
 
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 22831d3b7f62..da1034867aaa 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -31,12 +31,8 @@ MODULE_ALIAS_CRYPTO("ghash");
 #define GCM_IV_SIZE		12
 
 struct ghash_key {
-	u64			h[2];
-	u64			h2[2];
-	u64			h3[2];
-	u64			h4[2];
-
 	be128			k;
+	u64			h[][2];
 };
 
 struct ghash_desc_ctx {
@@ -51,22 +47,18 @@ struct gcm_aes_ctx {
 };
 
 asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
-				       struct ghash_key const *k,
-				       const char *head);
+				       u64 const h[][2], const char *head);
 
 asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
-				      struct ghash_key const *k,
-				      const char *head);
+				      u64 const h[][2], const char *head);
 
 asmlinkage void pmull_gcm_encrypt(int bytes, u8 dst[], const u8 src[],
-				  struct ghash_key const *k, u64 dg[],
-				  u8 ctr[], u32 const rk[], int rounds,
-				  u8 tag[]);
+				  u64 const h[][2], u64 dg[], u8 ctr[],
+				  u32 const rk[], int rounds, u8 tag[]);
 
 asmlinkage void pmull_gcm_decrypt(int bytes, u8 dst[], const u8 src[],
-				  struct ghash_key const *k, u64 dg[],
-				  u8 ctr[], u32 const rk[], int rounds,
-				  u8 tag[]);
+				  u64 const h[][2], u64 dg[], u8 ctr[],
+				  u32 const rk[], int rounds, u8 tag[]);
 
 static int ghash_init(struct shash_desc *desc)
 {
@@ -77,48 +69,51 @@ static int ghash_init(struct shash_desc *desc)
 }
 
 static void ghash_do_update(int blocks, u64 dg[], const char *src,
-			    struct ghash_key *key, const char *head,
-			    void (*simd_update)(int blocks, u64 dg[],
-						const char *src,
-						struct ghash_key const *k,
-						const char *head))
+			    struct ghash_key *key, const char *head)
 {
-	if (likely(crypto_simd_usable() && simd_update)) {
-		kernel_neon_begin();
-		simd_update(blocks, dg, src, key, head);
-		kernel_neon_end();
-	} else {
-		be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
+	be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
 
-		do {
-			const u8 *in = src;
-
-			if (head) {
-				in = head;
-				blocks++;
-				head = NULL;
-			} else {
-				src += GHASH_BLOCK_SIZE;
-			}
+	do {
+		const u8 *in = src;
+
+		if (head) {
+			in = head;
+			blocks++;
+			head = NULL;
+		} else {
+			src += GHASH_BLOCK_SIZE;
+		}
 
-			crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
-			gf128mul_lle(&dst, &key->k);
-		} while (--blocks);
+		crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
+		gf128mul_lle(&dst, &key->k);
+	} while (--blocks);
 
-		dg[0] = be64_to_cpu(dst.b);
-		dg[1] = be64_to_cpu(dst.a);
+	dg[0] = be64_to_cpu(dst.b);
+	dg[1] = be64_to_cpu(dst.a);
+}
+
+static __always_inline
+void ghash_do_simd_update(int blocks, u64 dg[], const char *src,
+			  struct ghash_key *key, const char *head,
+			  void (*simd_update)(int blocks, u64 dg[],
+					      const char *src,
+					      u64 const h[][2],
+					      const char *head))
+{
+	if (likely(crypto_simd_usable())) {
+		kernel_neon_begin();
+		simd_update(blocks, dg, src, key->h, head);
+		kernel_neon_end();
+	} else {
+		ghash_do_update(blocks, dg, src, key, head);
 	}
 }
 
 /* avoid hogging the CPU for too long */
 #define MAX_BLOCKS	(SZ_64K / GHASH_BLOCK_SIZE)
 
-static int __ghash_update(struct shash_desc *desc, const u8 *src,
-			  unsigned int len,
-			  void (*simd_update)(int blocks, u64 dg[],
-					      const char *src,
-					      struct ghash_key const *k,
-					      const char *head))
+static int ghash_update(struct shash_desc *desc, const u8 *src,
+			unsigned int len)
 {
 	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
@@ -143,9 +138,9 @@ static int __ghash_update(struct shash_desc *desc, const u8 *src,
 		do {
 			int chunk = min(blocks, MAX_BLOCKS);
 
-			ghash_do_update(chunk, ctx->digest, src, key,
-					partial ? ctx->buf : NULL,
-					simd_update);
+			ghash_do_simd_update(chunk, ctx->digest, src, key,
+					     partial ? ctx->buf : NULL,
+					     pmull_ghash_update_p8);
 
 			blocks -= chunk;
 			src += chunk * GHASH_BLOCK_SIZE;
@@ -157,39 +152,7 @@ static int __ghash_update(struct shash_desc *desc, const u8 *src,
 	return 0;
 }
 
-static int ghash_update_p8(struct shash_desc *desc, const u8 *src,
-			   unsigned int len)
-{
-	return __ghash_update(desc, src, len, pmull_ghash_update_p8);
-}
-
-static int ghash_update_p64(struct shash_desc *desc, const u8 *src,
-			    unsigned int len)
-{
-	return __ghash_update(desc, src, len, pmull_ghash_update_p64);
-}
-
-static int ghash_final_p8(struct shash_desc *desc, u8 *dst)
-{
-	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
-	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
-
-	if (partial) {
-		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
-
-		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
-
-		ghash_do_update(1, ctx->digest, ctx->buf, key, NULL,
-				pmull_ghash_update_p8);
-	}
-	put_unaligned_be64(ctx->digest[1], dst);
-	put_unaligned_be64(ctx->digest[0], dst + 8);
-
-	*ctx = (struct ghash_desc_ctx){};
-	return 0;
-}
-
-static int ghash_final_p64(struct shash_desc *desc, u8 *dst)
+static int ghash_final(struct shash_desc *desc, u8 *dst)
 {
 	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
@@ -199,8 +162,8 @@ static int ghash_final_p64(struct shash_desc *desc, u8 *dst)
 
 		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
 
-		ghash_do_update(1, ctx->digest, ctx->buf, key, NULL,
-				pmull_ghash_update_p64);
+		ghash_do_simd_update(1, ctx->digest, ctx->buf, key, NULL,
+				     pmull_ghash_update_p8);
 	}
 	put_unaligned_be64(ctx->digest[1], dst);
 	put_unaligned_be64(ctx->digest[0], dst + 8);
@@ -220,29 +183,6 @@ static void ghash_reflect(u64 h[], const be128 *k)
 		h[1] ^= 0xc200000000000000UL;
 }
 
-static int __ghash_setkey(struct ghash_key *key,
-			  const u8 *inkey, unsigned int keylen)
-{
-	be128 h;
-
-	/* needed for the fallback */
-	memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
-
-	ghash_reflect(key->h, &key->k);
-
-	h = key->k;
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h2, &h);
-
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h3, &h);
-
-	gf128mul_lle(&h, &key->k);
-	ghash_reflect(key->h4, &h);
-
-	return 0;
-}
-
 static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *inkey, unsigned int keylen)
 {
@@ -251,38 +191,28 @@ static int ghash_setkey(struct crypto_shash *tfm,
 	if (keylen != GHASH_BLOCK_SIZE)
 		return -EINVAL;
 
-	return __ghash_setkey(key, inkey, keylen);
+	/* needed for the fallback */
+	memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
+
+	ghash_reflect(key->h[0], &key->k);
+	return 0;
 }
 
-static struct shash_alg ghash_alg[] = {{
+static struct shash_alg ghash_alg = {
 	.base.cra_name		= "ghash",
 	.base.cra_driver_name	= "ghash-neon",
 	.base.cra_priority	= 150,
 	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct ghash_key),
-	.base.cra_module	= THIS_MODULE,
-
-	.digestsize		= GHASH_DIGEST_SIZE,
-	.init			= ghash_init,
-	.update			= ghash_update_p8,
-	.final			= ghash_final_p8,
-	.setkey			= ghash_setkey,
-	.descsize		= sizeof(struct ghash_desc_ctx),
-}, {
-	.base.cra_name		= "ghash",
-	.base.cra_driver_name	= "ghash-ce",
-	.base.cra_priority	= 200,
-	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct ghash_key),
+	.base.cra_ctxsize	= sizeof(struct ghash_key) + sizeof(u64[2]),
 	.base.cra_module	= THIS_MODULE,
 
 	.digestsize		= GHASH_DIGEST_SIZE,
 	.init			= ghash_init,
-	.update			= ghash_update_p64,
-	.final			= ghash_final_p64,
+	.update			= ghash_update,
+	.final			= ghash_final,
 	.setkey			= ghash_setkey,
 	.descsize		= sizeof(struct ghash_desc_ctx),
-}};
+};
 
 static int num_rounds(struct crypto_aes_ctx *ctx)
 {
@@ -301,6 +231,7 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
 {
 	struct gcm_aes_ctx *ctx = crypto_aead_ctx(tfm);
 	u8 key[GHASH_BLOCK_SIZE];
+	be128 h;
 	int ret;
 
 	ret = aes_expandkey(&ctx->aes_key, inkey, keylen);
@@ -309,7 +240,22 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
 
 	aes_encrypt(&ctx->aes_key, key, (u8[AES_BLOCK_SIZE]){});
 
-	return __ghash_setkey(&ctx->ghash_key, key, sizeof(be128));
+	/* needed for the fallback */
+	memcpy(&ctx->ghash_key.k, key, GHASH_BLOCK_SIZE);
+
+	ghash_reflect(ctx->ghash_key.h[0], &ctx->ghash_key.k);
+
+	h = ctx->ghash_key.k;
+	gf128mul_lle(&h, &ctx->ghash_key.k);
+	ghash_reflect(ctx->ghash_key.h[1], &h);
+
+	gf128mul_lle(&h, &ctx->ghash_key.k);
+	ghash_reflect(ctx->ghash_key.h[2], &h);
+
+	gf128mul_lle(&h, &ctx->ghash_key.k);
+	ghash_reflect(ctx->ghash_key.h[3], &h);
+
+	return 0;
 }
 
 static int gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
@@ -341,9 +287,9 @@ static void gcm_update_mac(u64 dg[], const u8 *src, int count, u8 buf[],
 	if (count >= GHASH_BLOCK_SIZE || *buf_count == GHASH_BLOCK_SIZE) {
 		int blocks = count / GHASH_BLOCK_SIZE;
 
-		ghash_do_update(blocks, dg, src, &ctx->ghash_key,
-				*buf_count ? buf : NULL,
-				pmull_ghash_update_p64);
+		ghash_do_simd_update(blocks, dg, src, &ctx->ghash_key,
+				     *buf_count ? buf : NULL,
+				     pmull_ghash_update_p64);
 
 		src += blocks * GHASH_BLOCK_SIZE;
 		count %= GHASH_BLOCK_SIZE;
@@ -387,8 +333,8 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[])
 
 	if (buf_count) {
 		memset(&buf[buf_count], 0, GHASH_BLOCK_SIZE - buf_count);
-		ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL,
-				pmull_ghash_update_p64);
+		ghash_do_simd_update(1, dg, buf, &ctx->ghash_key, NULL,
+				     pmull_ghash_update_p64);
 	}
 }
 
@@ -433,8 +379,8 @@ static int gcm_encrypt(struct aead_request *req)
 			}
 
 			kernel_neon_begin();
-			pmull_gcm_encrypt(nbytes, dst, src, &ctx->ghash_key, dg,
-					  iv, ctx->aes_key.key_enc, nrounds,
+			pmull_gcm_encrypt(nbytes, dst, src, ctx->ghash_key.h,
+					  dg, iv, ctx->aes_key.key_enc, nrounds,
 					  tag);
 			kernel_neon_end();
 
@@ -464,7 +410,7 @@ static int gcm_encrypt(struct aead_request *req)
 			} while (--remaining > 0);
 
 			ghash_do_update(blocks, dg, walk.dst.virt.addr,
-					&ctx->ghash_key, NULL, NULL);
+					&ctx->ghash_key, NULL);
 
 			err = skcipher_walk_done(&walk,
 						 walk.nbytes % AES_BLOCK_SIZE);
@@ -483,7 +429,7 @@ static int gcm_encrypt(struct aead_request *req)
 
 		tag = (u8 *)&lengths;
 		ghash_do_update(1, dg, tag, &ctx->ghash_key,
-				walk.nbytes ? buf : NULL, NULL);
+				walk.nbytes ? buf : NULL);
 
 		if (walk.nbytes)
 			err = skcipher_walk_done(&walk, 0);
@@ -547,8 +493,8 @@ static int gcm_decrypt(struct aead_request *req)
 			}
 
 			kernel_neon_begin();
-			pmull_gcm_decrypt(nbytes, dst, src, &ctx->ghash_key, dg,
-					  iv, ctx->aes_key.key_enc, nrounds,
+			pmull_gcm_decrypt(nbytes, dst, src, ctx->ghash_key.h,
+					  dg, iv, ctx->aes_key.key_enc, nrounds,
 					  tag);
 			kernel_neon_end();
 
@@ -568,7 +514,7 @@ static int gcm_decrypt(struct aead_request *req)
 			u8 *dst = walk.dst.virt.addr;
 
 			ghash_do_update(blocks, dg, walk.src.virt.addr,
-					&ctx->ghash_key, NULL, NULL);
+					&ctx->ghash_key, NULL);
 
 			do {
 				aes_encrypt(&ctx->aes_key, buf, iv);
@@ -591,7 +537,7 @@ static int gcm_decrypt(struct aead_request *req)
 
 		tag = (u8 *)&lengths;
 		ghash_do_update(1, dg, tag, &ctx->ghash_key,
-				walk.nbytes ? buf : NULL, NULL);
+				walk.nbytes ? buf : NULL);
 
 		if (walk.nbytes) {
 			aes_encrypt(&ctx->aes_key, buf, iv);
@@ -635,43 +581,28 @@ static struct aead_alg gcm_aes_alg = {
 	.base.cra_driver_name	= "gcm-aes-ce",
 	.base.cra_priority	= 300,
 	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct gcm_aes_ctx),
+	.base.cra_ctxsize	= sizeof(struct gcm_aes_ctx) +
+				  4 * sizeof(u64[2]),
 	.base.cra_module	= THIS_MODULE,
 };
 
 static int __init ghash_ce_mod_init(void)
 {
-	int ret;
-
 	if (!cpu_have_named_feature(ASIMD))
 		return -ENODEV;
 
 	if (cpu_have_named_feature(PMULL))
-		ret = crypto_register_shashes(ghash_alg,
-					      ARRAY_SIZE(ghash_alg));
-	else
-		/* only register the first array element */
-		ret = crypto_register_shash(ghash_alg);
+		return crypto_register_aead(&gcm_aes_alg);
 
-	if (ret)
-		return ret;
-
-	if (cpu_have_named_feature(PMULL)) {
-		ret = crypto_register_aead(&gcm_aes_alg);
-		if (ret)
-			crypto_unregister_shashes(ghash_alg,
-						  ARRAY_SIZE(ghash_alg));
-	}
-	return ret;
+	return crypto_register_shash(&ghash_alg);
 }
 
 static void __exit ghash_ce_mod_exit(void)
 {
 	if (cpu_have_named_feature(PMULL))
-		crypto_unregister_shashes(ghash_alg, ARRAY_SIZE(ghash_alg));
+		crypto_unregister_aead(&gcm_aes_alg);
 	else
-		crypto_unregister_shash(ghash_alg);
-	crypto_unregister_aead(&gcm_aes_alg);
+		crypto_unregister_shash(&ghash_alg);
 }
 
 static const struct cpu_feature ghash_cpu_feature[] = {
diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c
index 286bc8ecf15b..ca2547df9652 100644
--- a/arch/sparc/crypto/sha256_glue.c
+++ b/arch/sparc/crypto/sha256_glue.c
@@ -156,7 +156,7 @@ static int sha256_sparc64_import(struct shash_desc *desc, const void *in)
 	return 0;
 }
 
-static struct shash_alg sha256 = {
+static struct shash_alg sha256_alg = {
 	.digestsize	=	SHA256_DIGEST_SIZE,
 	.init		=	sha256_sparc64_init,
 	.update		=	sha256_sparc64_update,
@@ -174,7 +174,7 @@ static struct shash_alg sha256 = {
 	}
 };
 
-static struct shash_alg sha224 = {
+static struct shash_alg sha224_alg = {
 	.digestsize	=	SHA224_DIGEST_SIZE,
 	.init		=	sha224_sparc64_init,
 	.update		=	sha256_sparc64_update,
@@ -206,13 +206,13 @@ static bool __init sparc64_has_sha256_opcode(void)
 static int __init sha256_sparc64_mod_init(void)
 {
 	if (sparc64_has_sha256_opcode()) {
-		int ret = crypto_register_shash(&sha224);
+		int ret = crypto_register_shash(&sha224_alg);
 		if (ret < 0)
 			return ret;
 
-		ret = crypto_register_shash(&sha256);
+		ret = crypto_register_shash(&sha256_alg);
 		if (ret < 0) {
-			crypto_unregister_shash(&sha224);
+			crypto_unregister_shash(&sha224_alg);
 			return ret;
 		}
 
@@ -225,8 +225,8 @@ static int __init sha256_sparc64_mod_init(void)
 
 static void __exit sha256_sparc64_mod_fini(void)
 {
-	crypto_unregister_shash(&sha224);
-	crypto_unregister_shash(&sha256);
+	crypto_unregister_shash(&sha224_alg);
+	crypto_unregister_shash(&sha256_alg);
 }
 
 module_init(sha256_sparc64_mod_init);
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index ec437db1fa54..3f0fc7dd87d7 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -63,7 +63,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/inst.h>
 
 #define VMOVDQ		vmovdqu
 
@@ -127,10 +126,6 @@ ddq_add_8:
 
 /* generate a unique variable for ddq_add_x */
 
-.macro setddq n
-	var_ddq_add = ddq_add_\n
-.endm
-
 /* generate a unique variable for xmm register */
 .macro setxdata n
 	var_xdata = %xmm\n
@@ -140,9 +135,7 @@ ddq_add_8:
 
 .macro club name, id
 .altmacro
-	.if \name == DDQ_DATA
-		setddq %\id
-	.elseif \name == XDATA
+	.if \name == XDATA
 		setxdata %\id
 	.endif
 .noaltmacro
@@ -165,9 +158,8 @@ ddq_add_8:
 
 	.set i, 1
 	.rept (by - 1)
-		club DDQ_DATA, i
 		club XDATA, i
-		vpaddq	var_ddq_add(%rip), xcounter, var_xdata
+		vpaddq	(ddq_add_1 + 16 * (i - 1))(%rip), xcounter, var_xdata
 		vptest	ddq_low_msk(%rip), var_xdata
 		jnz 1f
 		vpaddq	ddq_high_add_1(%rip), var_xdata, var_xdata
@@ -180,8 +172,7 @@ ddq_add_8:
 	vmovdqa	1*16(p_keys), xkeyA
 
 	vpxor	xkey0, xdata0, xdata0
-	club DDQ_DATA, by
-	vpaddq	var_ddq_add(%rip), xcounter, xcounter
+	vpaddq	(ddq_add_1 + 16 * (by - 1))(%rip), xcounter, xcounter
 	vptest	ddq_low_msk(%rip), xcounter
 	jnz	1f
 	vpaddq	ddq_high_add_1(%rip), xcounter, xcounter
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 54e7d15dbd0d..1852b19a73a0 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -26,7 +26,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/inst.h>
 #include <asm/frame.h>
 #include <asm/nospec-branch.h>
 
@@ -201,7 +200,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	mov	\SUBKEY, %r12
 	movdqu	(%r12), \TMP3
 	movdqa	SHUF_MASK(%rip), \TMP2
-	PSHUFB_XMM \TMP2, \TMP3
+	pshufb	\TMP2, \TMP3
 
 	# precompute HashKey<<1 mod poly from the HashKey (required for GHASH)
 
@@ -263,10 +262,10 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	movdqu %xmm0, OrigIV(%arg2) # ctx_data.orig_IV = iv
 
 	movdqa  SHUF_MASK(%rip), %xmm2
-	PSHUFB_XMM %xmm2, %xmm0
+	pshufb %xmm2, %xmm0
 	movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv
 
-	PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
+	PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7
 	movdqu HashKey(%arg2), %xmm13
 
 	CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \
@@ -347,7 +346,7 @@ _zero_cipher_left_\@:
 	paddd ONE(%rip), %xmm0                # INCR CNT to get Yn
 	movdqu %xmm0, CurCount(%arg2)
 	movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10, %xmm0
+	pshufb %xmm10, %xmm0
 
 	ENCRYPT_SINGLE_BLOCK	%xmm0, %xmm1        # Encrypt(K, Yn)
 	movdqu %xmm0, PBlockEncKey(%arg2)
@@ -377,7 +376,7 @@ _large_enough_update_\@:
 	# get the appropriate shuffle mask
 	movdqu	(%r12), %xmm2
 	# shift right 16-r13 bytes
-	PSHUFB_XMM  %xmm2, %xmm1
+	pshufb  %xmm2, %xmm1
 
 _data_read_\@:
 	lea ALL_F+16(%rip), %r12
@@ -393,12 +392,12 @@ _data_read_\@:
 .ifc \operation, dec
 	pand    %xmm1, %xmm2
 	movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10 ,%xmm2
+	pshufb %xmm10 ,%xmm2
 
 	pxor %xmm2, %xmm8
 .else
 	movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10,%xmm0
+	pshufb %xmm10,%xmm0
 
 	pxor	%xmm0, %xmm8
 .endif
@@ -408,17 +407,17 @@ _data_read_\@:
 	# GHASH computation for the last <16 byte block
 	movdqa SHUF_MASK(%rip), %xmm10
 	# shuffle xmm0 back to output as ciphertext
-	PSHUFB_XMM %xmm10, %xmm0
+	pshufb %xmm10, %xmm0
 .endif
 
 	# Output %r13 bytes
-	MOVQ_R64_XMM %xmm0, %rax
+	movq %xmm0, %rax
 	cmp $8, %r13
 	jle _less_than_8_bytes_left_\@
 	mov %rax, (%arg3 , %r11, 1)
 	add $8, %r11
 	psrldq $8, %xmm0
-	MOVQ_R64_XMM %xmm0, %rax
+	movq %xmm0, %rax
 	sub $8, %r13
 _less_than_8_bytes_left_\@:
 	mov %al,  (%arg3, %r11, 1)
@@ -449,7 +448,7 @@ _partial_done\@:
 	movd	%r12d, %xmm15		  # len(A) in %xmm15
 	mov InLen(%arg2), %r12
 	shl     $3, %r12                  # len(C) in bits (*128)
-	MOVQ_R64_XMM    %r12, %xmm1
+	movq    %r12, %xmm1
 
 	pslldq	$8, %xmm15		  # %xmm15 = len(A)||0x0000000000000000
 	pxor	%xmm1, %xmm15		  # %xmm15 = len(A)||len(C)
@@ -457,7 +456,7 @@ _partial_done\@:
 	GHASH_MUL	%xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
 	# final GHASH computation
 	movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10, %xmm8
+	pshufb %xmm10, %xmm8
 
 	movdqu OrigIV(%arg2), %xmm0       # %xmm0 = Y0
 	ENCRYPT_SINGLE_BLOCK	%xmm0,  %xmm1	  # E(K, Y0)
@@ -470,7 +469,7 @@ _return_T_\@:
 	cmp	$8, %r11
 	jl	_T_4_\@
 _T_8_\@:
-	MOVQ_R64_XMM	%xmm0, %rax
+	movq	%xmm0, %rax
 	mov	%rax, (%r10)
 	add	$8, %r10
 	sub	$8, %r11
@@ -518,9 +517,9 @@ _return_T_done_\@:
 	pshufd	  $78, \HK, \TMP3
 	pxor	  \GH, \TMP2            # TMP2 = a1+a0
 	pxor	  \HK, \TMP3            # TMP3 = b1+b0
-	PCLMULQDQ 0x11, \HK, \TMP1     # TMP1 = a1*b1
-	PCLMULQDQ 0x00, \HK, \GH       # GH = a0*b0
-	PCLMULQDQ 0x00, \TMP3, \TMP2   # TMP2 = (a0+a1)*(b1+b0)
+	p