Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto update from Herbert Xu:
 "Here is the crypto update for 3.20:

   - Added 192/256-bit key support to aesni GCM.
   - Added MIPS OCTEON MD5 support.
   - Fixed hwrng starvation and race conditions.
   - Added note that memzero_explicit is not a subsitute for memset.
   - Added user-space interface for crypto_rng.
   - Misc fixes"

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (71 commits)
  crypto: tcrypt - do not allocate iv on stack for aead speed tests
  crypto: testmgr - limit IV copy length in aead tests
  crypto: tcrypt - fix buflen reminder calculation
  crypto: testmgr - mark rfc4106(gcm(aes)) as fips_allowed
  crypto: caam - fix resource clean-up on error path for caam_jr_init
  crypto: caam - pair irq map and dispose in the same function
  crypto: ccp - terminate ccp_support array with empty element
  crypto: caam - remove unused local variable
  crypto: caam - remove dead code
  crypto: caam - don't emit ICV check failures to dmesg
  hwrng: virtio - drop extra empty line
  crypto: replace scatterwalk_sg_next with sg_next
  crypto: atmel - Free memory in error path
  crypto: doc - remove colons in comments
  crypto: seqiv - Ensure that IV size is at least 8 bytes
  crypto: cts - Weed out non-CBC algorithms
  MAINTAINERS: add linux-crypto to hw random
  crypto: cts - Remove bogus use of seqiv
  crypto: qat - don't need qat_auth_state struct
  crypto: algif_rng - fix sparse non static symbol warning
  ...

15 files changed, 595 insertions, 184 deletions

diff --git a/arch/mips/cavium-octeon/Makefile b/arch/mips/cavium-octeon/Makefile
index 42f5f1a4b40a..69a8a8dabc2b 100644
--- a/arch/mips/cavium-octeon/Makefile
+++ b/arch/mips/cavium-octeon/Makefile
@@ -16,6 +16,7 @@ obj-y := cpu.o setup.o octeon-platform.o octeon-irq.o csrc-octeon.o
 obj-y += dma-octeon.o
 obj-y += octeon-memcpy.o
 obj-y += executive/
+obj-y += crypto/
 
 obj-$(CONFIG_MTD)		      += flash_setup.o
 obj-$(CONFIG_SMP)		      += smp.o
diff --git a/arch/mips/cavium-octeon/crypto/Makefile b/arch/mips/cavium-octeon/crypto/Makefile
new file mode 100644
index 000000000000..a74f76d85a2f
--- /dev/null
+++ b/arch/mips/cavium-octeon/crypto/Makefile
@@ -0,0 +1,7 @@
+#
+# OCTEON-specific crypto modules.
+#
+
+obj-y += octeon-crypto.o
+
+obj-$(CONFIG_CRYPTO_MD5_OCTEON) += octeon-md5.o
diff --git a/arch/mips/cavium-octeon/crypto/octeon-crypto.c b/arch/mips/cavium-octeon/crypto/octeon-crypto.c
new file mode 100644
index 000000000000..7c82ff463b65
--- /dev/null
+++ b/arch/mips/cavium-octeon/crypto/octeon-crypto.c
@@ -0,0 +1,66 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2004-2012 Cavium Networks
+ */
+
+#include <asm/cop2.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+
+#include "octeon-crypto.h"
+
+/**
+ * Enable access to Octeon's COP2 crypto hardware for kernel use. Wrap any
+ * crypto operations in calls to octeon_crypto_enable/disable in order to make
+ * sure the state of COP2 isn't corrupted if userspace is also performing
+ * hardware crypto operations. Allocate the state parameter on the stack.
+ * Preemption must be disabled to prevent context switches.
+ *
+ * @state: Pointer to state structure to store current COP2 state in.
+ *
+ * Returns: Flags to be passed to octeon_crypto_disable()
+ */
+unsigned long octeon_crypto_enable(struct octeon_cop2_state *state)
+{
+	int status;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	status = read_c0_status();
+	write_c0_status(status | ST0_CU2);
+	if (KSTK_STATUS(current) & ST0_CU2) {
+		octeon_cop2_save(&(current->thread.cp2));
+		KSTK_STATUS(current) &= ~ST0_CU2;
+		status &= ~ST0_CU2;
+	} else if (status & ST0_CU2) {
+		octeon_cop2_save(state);
+	}
+	local_irq_restore(flags);
+	return status & ST0_CU2;
+}
+EXPORT_SYMBOL_GPL(octeon_crypto_enable);
+
+/**
+ * Disable access to Octeon's COP2 crypto hardware in the kernel. This must be
+ * called after an octeon_crypto_enable() before any context switch or return to
+ * userspace.
+ *
+ * @state:	Pointer to COP2 state to restore
+ * @flags:	Return value from octeon_crypto_enable()
+ */
+void octeon_crypto_disable(struct octeon_cop2_state *state,
+			   unsigned long crypto_flags)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if (crypto_flags & ST0_CU2)
+		octeon_cop2_restore(state);
+	else
+		write_c0_status(read_c0_status() & ~ST0_CU2);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(octeon_crypto_disable);
diff --git a/arch/mips/cavium-octeon/crypto/octeon-crypto.h b/arch/mips/cavium-octeon/crypto/octeon-crypto.h
new file mode 100644
index 000000000000..e2a4aece9c24
--- /dev/null
+++ b/arch/mips/cavium-octeon/crypto/octeon-crypto.h
@@ -0,0 +1,75 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012-2013 Cavium Inc., All Rights Reserved.
+ *
+ * MD5 instruction definitions added by Aaro Koskinen <aaro.koskinen@iki.fi>.
+ *
+ */
+#ifndef __LINUX_OCTEON_CRYPTO_H
+#define __LINUX_OCTEON_CRYPTO_H
+
+#include <linux/sched.h>
+#include <asm/mipsregs.h>
+
+#define OCTEON_CR_OPCODE_PRIORITY 300
+
+extern unsigned long octeon_crypto_enable(struct octeon_cop2_state *state);
+extern void octeon_crypto_disable(struct octeon_cop2_state *state,
+				  unsigned long flags);
+
+/*
+ * Macros needed to implement MD5:
+ */
+
+/*
+ * The index can be 0-1.
+ */
+#define write_octeon_64bit_hash_dword(value, index)	\
+do {							\
+	__asm__ __volatile__ (				\
+	"dmtc2 %[rt],0x0048+" STR(index)		\
+	:						\
+	: [rt] "d" (value));				\
+} while (0)
+
+/*
+ * The index can be 0-1.
+ */
+#define read_octeon_64bit_hash_dword(index)		\
+({							\
+	u64 __value;					\
+							\
+	__asm__ __volatile__ (				\
+	"dmfc2 %[rt],0x0048+" STR(index)		\
+	: [rt] "=d" (__value)				\
+	: );						\
+							\
+	__value;					\
+})
+
+/*
+ * The index can be 0-6.
+ */
+#define write_octeon_64bit_block_dword(value, index)	\
+do {							\
+	__asm__ __volatile__ (				\
+	"dmtc2 %[rt],0x0040+" STR(index)		\
+	:						\
+	: [rt] "d" (value));				\
+} while (0)
+
+/*
+ * The value is the final block dword (64-bit).
+ */
+#define octeon_md5_start(value)				\
+do {							\
+	__asm__ __volatile__ (				\
+	"dmtc2 %[rt],0x4047"				\
+	:						\
+	: [rt] "d" (value));				\
+} while (0)
+
+#endif /* __LINUX_OCTEON_CRYPTO_H */
diff --git a/arch/mips/cavium-octeon/crypto/octeon-md5.c b/arch/mips/cavium-octeon/crypto/octeon-md5.c
new file mode 100644
index 000000000000..b909881ba6c1
--- /dev/null
+++ b/arch/mips/cavium-octeon/crypto/octeon-md5.c
@@ -0,0 +1,216 @@
+/*
+ * Cryptographic API.
+ *
+ * MD5 Message Digest Algorithm (RFC1321).
+ *
+ * Adapted for OCTEON by Aaro Koskinen <aaro.koskinen@iki.fi>.
+ *
+ * Based on crypto/md5.c, which is:
+ *
+ * Derived from cryptoapi implementation, originally based on the
+ * public domain implementation written by Colin Plumb in 1993.
+ *
+ * Copyright (c) Cryptoapi developers.
+ * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <crypto/md5.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <asm/byteorder.h>
+#include <linux/cryptohash.h>
+#include <asm/octeon/octeon.h>
+#include <crypto/internal/hash.h>
+
+#include "octeon-crypto.h"
+
+/*
+ * We pass everything as 64-bit. OCTEON can handle misaligned data.
+ */
+
+static void octeon_md5_store_hash(struct md5_state *ctx)
+{
+	u64 *hash = (u64 *)ctx->hash;
+
+	write_octeon_64bit_hash_dword(hash[0], 0);
+	write_octeon_64bit_hash_dword(hash[1], 1);
+}
+
+static void octeon_md5_read_hash(struct md5_state *ctx)
+{
+	u64 *hash = (u64 *)ctx->hash;
+
+	hash[0] = read_octeon_64bit_hash_dword(0);
+	hash[1] = read_octeon_64bit_hash_dword(1);
+}
+
+static void octeon_md5_transform(const void *_block)
+{
+	const u64 *block = _block;
+
+	write_octeon_64bit_block_dword(block[0], 0);
+	write_octeon_64bit_block_dword(block[1], 1);
+	write_octeon_64bit_block_dword(block[2], 2);
+	write_octeon_64bit_block_dword(block[3], 3);
+	write_octeon_64bit_block_dword(block[4], 4);
+	write_octeon_64bit_block_dword(block[5], 5);
+	write_octeon_64bit_block_dword(block[6], 6);
+	octeon_md5_start(block[7]);
+}
+
+static int octeon_md5_init(struct shash_desc *desc)
+{
+	struct md5_state *mctx = shash_desc_ctx(desc);
+
+	mctx->hash[0] = cpu_to_le32(0x67452301);
+	mctx->hash[1] = cpu_to_le32(0xefcdab89);
+	mctx->hash[2] = cpu_to_le32(0x98badcfe);
+	mctx->hash[3] = cpu_to_le32(0x10325476);
+	mctx->byte_count = 0;
+
+	return 0;
+}
+
+static int octeon_md5_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len)
+{
+	struct md5_state *mctx = shash_desc_ctx(desc);
+	const u32 avail = sizeof(mctx->block) - (mctx->byte_count & 0x3f);
+	struct octeon_cop2_state state;
+	unsigned long flags;
+
+	mctx->byte_count += len;
+
+	if (avail > len) {
+		memcpy((char *)mctx->block + (sizeof(mctx->block) - avail),
+		       data, len);
+		return 0;
+	}
+
+	memcpy((char *)mctx->block + (sizeof(mctx->block) - avail), data,
+	       avail);
+
+	local_bh_disable();
+	preempt_disable();
+	flags = octeon_crypto_enable(&state);
+	octeon_md5_store_hash(mctx);
+
+	octeon_md5_transform(mctx->block);
+	data += avail;
+	len -= avail;
+
+	while (len >= sizeof(mctx->block)) {
+		octeon_md5_transform(data);
+		data += sizeof(mctx->block);
+		len -= sizeof(mctx->block);
+	}
+
+	octeon_md5_read_hash(mctx);
+	octeon_crypto_disable(&state, flags);
+	preempt_enable();
+	local_bh_enable();
+
+	memcpy(mctx->block, data, len);
+
+	return 0;
+}
+
+static int octeon_md5_final(struct shash_desc *desc, u8 *out)
+{
+	struct md5_state *mctx = shash_desc_ctx(desc);
+	const unsigned int offset = mctx->byte_count & 0x3f;
+	char *p = (char *)mctx->block + offset;
+	int padding = 56 - (offset + 1);
+	struct octeon_cop2_state state;
+	unsigned long flags;
+
+	*p++ = 0x80;
+
+	local_bh_disable();
+	preempt_disable();
+	flags = octeon_crypto_enable(&state);
+	octeon_md5_store_hash(mctx);
+
+	if (padding < 0) {
+		memset(p, 0x00, padding + sizeof(u64));
+		octeon_md5_transform(mctx->block);
+		p = (char *)mctx->block;
+		padding = 56;
+	}
+
+	memset(p, 0, padding);
+	mctx->block[14] = cpu_to_le32(mctx->byte_count << 3);
+	mctx->block[15] = cpu_to_le32(mctx->byte_count >> 29);
+	octeon_md5_transform(mctx->block);
+
+	octeon_md5_read_hash(mctx);
+	octeon_crypto_disable(&state, flags);
+	preempt_enable();
+	local_bh_enable();
+
+	memcpy(out, mctx->hash, sizeof(mctx->hash));
+	memset(mctx, 0, sizeof(*mctx));
+
+	return 0;
+}
+
+static int octeon_md5_export(struct shash_desc *desc, void *out)
+{
+	struct md5_state *ctx = shash_desc_ctx(desc);
+
+	memcpy(out, ctx, sizeof(*ctx));
+	return 0;
+}
+
+static int octeon_md5_import(struct shash_desc *desc, const void *in)
+{
+	struct md5_state *ctx = shash_desc_ctx(desc);
+
+	memcpy(ctx, in, sizeof(*ctx));
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.digestsize	=	MD5_DIGEST_SIZE,
+	.init		=	octeon_md5_init,
+	.update		=	octeon_md5_update,
+	.final		=	octeon_md5_final,
+	.export		=	octeon_md5_export,
+	.import		=	octeon_md5_import,
+	.descsize	=	sizeof(struct md5_state),
+	.statesize	=	sizeof(struct md5_state),
+	.base		=	{
+		.cra_name	=	"md5",
+		.cra_driver_name=	"octeon-md5",
+		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static int __init md5_mod_init(void)
+{
+	if (!octeon_has_crypto())
+		return -ENOTSUPP;
+	return crypto_register_shash(&alg);
+}
+
+static void __exit md5_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(md5_mod_init);
+module_exit(md5_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MD5 Message Digest Algorithm (OCTEON)");
+MODULE_AUTHOR("Aaro Koskinen <aaro.koskinen@iki.fi>");
diff --git a/arch/mips/cavium-octeon/executive/octeon-model.c b/arch/mips/cavium-octeon/executive/octeon-model.c
index e15b049b3bd7..b2104bd9ab3b 100644
--- a/arch/mips/cavium-octeon/executive/octeon-model.c
+++ b/arch/mips/cavium-octeon/executive/octeon-model.c
@@ -27,6 +27,9 @@
 
 #include <asm/octeon/octeon.h>
 
+enum octeon_feature_bits __octeon_feature_bits __read_mostly;
+EXPORT_SYMBOL_GPL(__octeon_feature_bits);
+
 /**
  * Read a byte of fuse data
  * @byte_addr:	 address to read
@@ -103,6 +106,9 @@ static const char *__init octeon_model_get_string_buffer(uint32_t chip_id,
 	else
 		suffix = "NSP";
 
+	if (!fus_dat2.s.nocrypto)
+		__octeon_feature_bits |= OCTEON_HAS_CRYPTO;
+
 	/*
 	 * Assume pass number is encoded using <5:3><2:0>. Exceptions
 	 * will be fixed later.
diff --git a/arch/mips/include/asm/octeon/octeon-feature.h b/arch/mips/include/asm/octeon/octeon-feature.h
index c4fe81f47f53..8ebd3f579b84 100644
--- a/arch/mips/include/asm/octeon/octeon-feature.h
+++ b/arch/mips/include/asm/octeon/octeon-feature.h
@@ -46,8 +46,6 @@ enum octeon_feature {
 	OCTEON_FEATURE_SAAD,
 	/* Does this Octeon support the ZIP offload engine? */
 	OCTEON_FEATURE_ZIP,
-	/* Does this Octeon support crypto acceleration using COP2? */
-	OCTEON_FEATURE_CRYPTO,
 	OCTEON_FEATURE_DORM_CRYPTO,
 	/* Does this Octeon support PCI express? */
 	OCTEON_FEATURE_PCIE,
@@ -86,6 +84,21 @@ enum octeon_feature {
 	OCTEON_MAX_FEATURE
 };
 
+enum octeon_feature_bits {
+	OCTEON_HAS_CRYPTO = 0x0001,	/* Crypto acceleration using COP2 */
+};
+extern enum octeon_feature_bits __octeon_feature_bits;
+
+/**
+ * octeon_has_crypto() - Check if this OCTEON has crypto acceleration support.
+ *
+ * Returns: Non-zero if the feature exists. Zero if the feature does not exist.
+ */
+static inline int octeon_has_crypto(void)
+{
+	return __octeon_feature_bits & OCTEON_HAS_CRYPTO;
+}
+
 /**
  * Determine if the current Octeon supports a specific feature. These
  * checks have been optimized to be fairly quick, but they should still
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index d781f9e66884..6dfefd2d5cdf 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -44,11 +44,6 @@ extern int octeon_get_boot_num_arguments(void);
 extern const char *octeon_get_boot_argument(int arg);
 extern void octeon_hal_setup_reserved32(void);
 extern void octeon_user_io_init(void);
-struct octeon_cop2_state;
-extern unsigned long octeon_crypto_enable(struct octeon_cop2_state *state);
-extern void octeon_crypto_disable(struct octeon_cop2_state *state,
-				  unsigned long flags);
-extern asmlinkage void octeon_cop2_restore(struct octeon_cop2_state *task);
 
 extern void octeon_init_cvmcount(void);
 extern void octeon_setup_delays(void);
diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c
index 705408766ab0..2e48eb8813ff 100644
--- a/arch/sparc/crypto/aes_glue.c
+++ b/arch/sparc/crypto/aes_glue.c
@@ -497,7 +497,7 @@ module_init(aes_sparc64_mod_init);
 module_exit(aes_sparc64_mod_fini);
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("AES Secure Hash Algorithm, sparc64 aes opcode accelerated");
+MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, sparc64 aes opcode accelerated");
 
 MODULE_ALIAS_CRYPTO("aes");
 
diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c
index 641f55cb61c3..6bf2479a12fb 100644
--- a/arch/sparc/crypto/camellia_glue.c
+++ b/arch/sparc/crypto/camellia_glue.c
@@ -322,6 +322,6 @@ module_exit(camellia_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, sparc64 camellia opcode accelerated");
 
-MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("camellia");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c
index d11500972994..dd6a34fa6e19 100644
--- a/arch/sparc/crypto/des_glue.c
+++ b/arch/sparc/crypto/des_glue.c
@@ -533,5 +533,6 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms, sparc64 des opcode accelerated");
 
 MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des3_ede");
 
 #include "crop_devid.c"
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index 64c7ff5f72a9..b688731d7ede 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -183,7 +183,7 @@ module_init(md5_sparc64_mod_init);
 module_exit(md5_sparc64_mod_fini);
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("MD5 Secure Hash Algorithm, sparc64 md5 opcode accelerated");
+MODULE_DESCRIPTION("MD5 Message Digest Algorithm, sparc64 md5 opcode accelerated");
 
 MODULE_ALIAS_CRYPTO("md5");
 
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 477e9d75149b..6bd2c6c95373 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -32,12 +32,23 @@
 #include <linux/linkage.h>
 #include <asm/inst.h>
 
+/*
+ * The following macros are used to move an (un)aligned 16 byte value to/from
+ * an XMM register.  This can done for either FP or integer values, for FP use
+ * movaps (move aligned packed single) or integer use movdqa (move double quad
+ * aligned).  It doesn't make a performance difference which instruction is used
+ * since Nehalem (original Core i7) was released.  However, the movaps is a byte
+ * shorter, so that is the one we'll use for now. (same for unaligned).
+ */
+#define MOVADQ	movaps
+#define MOVUDQ	movups
+
 #ifdef __x86_64__
+
 .data
 .align 16
 .Lgf128mul_x_ble_mask:
 	.octa 0x00000000000000010000000000000087
-
 POLY:   .octa 0xC2000000000000000000000000000001
 TWOONE: .octa 0x00000001000000000000000000000001
 
@@ -89,6 +100,7 @@ enc:        .octa 0x2
 #define arg8 STACK_OFFSET+16(%r14)
 #define arg9 STACK_OFFSET+24(%r14)
 #define arg10 STACK_OFFSET+32(%r14)
+#define keysize 2*15*16(%arg1)
 #endif
 
 
@@ -213,10 +225,12 @@ enc:        .octa 0x2
 
 .macro INITIAL_BLOCKS_DEC num_initial_blocks TMP1 TMP2 TMP3 TMP4 TMP5 XMM0 XMM1 \
 XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation
+        MOVADQ     SHUF_MASK(%rip), %xmm14
 	mov	   arg7, %r10           # %r10 = AAD
 	mov	   arg8, %r12           # %r12 = aadLen
 	mov	   %r12, %r11
 	pxor	   %xmm\i, %xmm\i
+
 _get_AAD_loop\num_initial_blocks\operation:
 	movd	   (%r10), \TMP1
 	pslldq	   $12, \TMP1
@@ -225,16 +239,18 @@ _get_AAD_loop\num_initial_blocks\operation:
 	add	   $4, %r10
 	sub	   $4, %r12
 	jne	   _get_AAD_loop\num_initial_blocks\operation
+
 	cmp	   $16, %r11
 	je	   _get_AAD_loop2_done\num_initial_blocks\operation
+
 	mov	   $16, %r12
 _get_AAD_loop2\num_initial_blocks\operation:
 	psrldq	   $4, %xmm\i
 	sub	   $4, %r12
 	cmp	   %r11, %r12
 	jne	   _get_AAD_loop2\num_initial_blocks\operation
+
 _get_AAD_loop2_done\num_initial_blocks\operation:
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
 
 	xor	   %r11, %r11 # initialise the data pointer offset as zero
@@ -243,59 +259,34 @@ _get_AAD_loop2_done\num_initial_blocks\operation:
 
 	mov	   %arg5, %rax                      # %rax = *Y0
 	movdqu	   (%rax), \XMM0                    # XMM0 = Y0
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM   %xmm14, \XMM0
 
 .if (\i == 5) || (\i == 6) || (\i == 7)
+	MOVADQ		ONE(%RIP),\TMP1
+	MOVADQ		(%arg1),\TMP2
 .irpc index, \i_seq
-	paddd	   ONE(%rip), \XMM0                 # INCR Y0
+	paddd	   \TMP1, \XMM0                 # INCR Y0
 	movdqa	   \XMM0, %xmm\index
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM   %xmm14, %xmm\index      # perform a 16 byte swap
-
-.endr
-.irpc index, \i_seq
-	pxor	   16*0(%arg1), %xmm\index
-.endr
-.irpc index, \i_seq
-	movaps 0x10(%rdi), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 1
-.endr
-.irpc index, \i_seq
-	movaps 0x20(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x30(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x40(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x50(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x60(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
+	pxor	   \TMP2, %xmm\index
 .endr
-.irpc index, \i_seq
-	movaps 0x70(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x80(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x90(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
+	lea	0x10(%arg1),%r10
+	mov	keysize,%eax
+	shr	$2,%eax				# 128->4, 192->6, 256->8
+	add	$5,%eax			      # 128->9, 192->11, 256->13
+
+aes_loop_initial_dec\num_initial_blocks:
+	MOVADQ	(%r10),\TMP1
+.irpc	index, \i_seq
+	AESENC	\TMP1, %xmm\index
 .endr
+	add	$16,%r10
+	sub	$1,%eax
+	jnz	aes_loop_initial_dec\num_initial_blocks
+
+	MOVADQ	(%r10), \TMP1
 .irpc index, \i_seq
-	movaps 0xa0(%arg1), \TMP1
-	AESENCLAST \TMP1, %xmm\index         # Round 10
+	AESENCLAST \TMP1, %xmm\index         # Last Round
 .endr
 .irpc index, \i_seq
 	movdqu	   (%arg3 , %r11, 1), \TMP1
@@ -305,10 +296,8 @@ _get_AAD_loop2_done\num_initial_blocks\operation:
 	add	   $16, %r11
 
 	movdqa     \TMP1, %xmm\index
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM	   %xmm14, %xmm\index
-
-		# prepare plaintext/ciphertext for GHASH computation
+                # prepare plaintext/ciphertext for GHASH computation
 .endr
 .endif
 	GHASH_MUL  %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
@@ -338,30 +327,28 @@ _get_AAD_loop2_done\num_initial_blocks\operation:
 * Precomputations for HashKey parallel with encryption of first 4 blocks.
 * Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
 */
-	paddd	   ONE(%rip), \XMM0              # INCR Y0
-	movdqa	   \XMM0, \XMM1
-        movdqa     SHUF_MASK(%rip), %xmm14
+	MOVADQ	   ONE(%rip), \TMP1
+	paddd	   \TMP1, \XMM0              # INCR Y0
+	MOVADQ	   \XMM0, \XMM1
 	PSHUFB_XMM  %xmm14, \XMM1        # perform a 16 byte swap
 
-	paddd	   ONE(%rip), \XMM0              # INCR Y0
-	movdqa	   \XMM0, \XMM2
-        movdqa     SHUF_MASK(%rip), %xmm14
+	paddd	   \TMP1, \XMM0              # INCR Y0
+	MOVADQ	   \XMM0, \XMM2
 	PSHUFB_XMM  %xmm14, \XMM2        # perform a 16 byte swap
 
-	paddd	   ONE(%rip), \XMM0              # INCR Y0
-	movdqa	   \XMM0, \XMM3
-        movdqa     SHUF_MASK(%rip), %xmm14
+	paddd	   \TMP1, \XMM0              # INCR Y0
+	MOVADQ	   \XMM0, \XMM3
 	PSHUFB_XMM %xmm14, \XMM3        # perform a 16 byte swap
 
-	paddd	   ONE(%rip), \XMM0              # INCR Y0
-	movdqa	   \XMM0, \XMM4
-        movdqa     SHUF_MASK(%rip), %xmm14
+	paddd	   \TMP1, \XMM0              # INCR Y0
+	MOVADQ	   \XMM0, \XMM4
 	PSHUFB_XMM %xmm14, \XMM4        # perform a 16 byte swap
 
-	pxor	   16*0(%arg1), \XMM1
-	pxor	   16*0(%arg1), \XMM2
-	pxor	   16*0(%arg1), \XMM3
-	pxor	   16*0(%arg1), \XMM4
+	MOVADQ	   0(%arg1),\TMP1
+	pxor	   \TMP1, \XMM1
+	pxor	   \TMP1, \XMM2
+	pxor	   \TMP1, \XMM3
+	pxor	   \TMP1, \XMM4
 	movdqa	   \TMP3, \TMP5
 	pshufd	   $78, \TMP3, \TMP1
 	pxor	   \TMP3, \TMP1
@@ -399,7 +386,23 @@ _get_AAD_loop2_done\num_initial_blocks\operation:
 	pshufd	   $78, \TMP5, \TMP1
 	pxor	   \TMP5, \TMP1
 	movdqa	   \TMP1, HashKey_4_k(%rsp)
-	movaps 0xa0(%arg1), \TMP2
+	lea	   0xa0(%arg1),%r10
+	mov	   keysize,%eax
+	shr	   $2,%eax			# 128->4, 192->6, 256->8
+	sub	   $4,%eax			# 128->0, 192->2, 256->4
+	jz	   aes_loop_pre_dec_done\num_initial_blocks
+
+aes_loop_pre_dec\num_initial_blocks:
+	MOVADQ	   (%r10),\TMP2
+.irpc	index, 1234
+	AESENC	   \TMP2, %xmm\index
+.endr
+	add	   $16,%r10
+	sub	   $1,%eax
+	jnz	   aes_loop_pre_dec\num_initial_blocks
+
+aes_loop_pre_dec_done\num_initial_blocks:
+	MOVADQ	   (%r10), \TMP2
 	AESENCLAST \TMP2, \XMM1
 	AESENCLAST \TMP2, \XMM2
 	AESENCLAST \TMP2, \XMM3
@@ -421,15 +424,11 @@ _get_AAD_loop2_done\num_initial_blocks\operation:
 	movdqu	   \XMM4, 16*3(%arg2 , %r11 , 1)
 	movdqa     \TMP1, \XMM4
 	add	   $64, %r11
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap
 	pxor	   \XMMDst, \XMM1
 # combine GHASHed value with the corresponding ciphertext
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM %xmm14, \XMM2 # perform a 16 byte swap
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap
 
 _initial_blocks_done\num_initial_blocks\operation:
@@ -451,6 +450,7 @@ _initial_blocks_done\num_initial_blocks\operation:
 
 .macro INITIAL_BLOCKS_ENC num_initial_blocks TMP1 TMP2 TMP3 TMP4 TMP5 XMM0 XMM1 \
 XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation
+        MOVADQ     SHUF_MASK(%rip), %xmm14
 	mov	   arg7, %r10           # %r10 = AAD
 	mov	   arg8, %r12           # %r12 = aadLen
 	mov	   %r12, %r11
@@ -472,7 +472,6 @@ _get_AAD_loop2\num_initial_blocks\operation:
 	cmp	   %r11, %r12
 	jne	   _get_AAD_loop2\num_initial_blocks\operation
 _get_AAD_loop2_done\num_initial_blocks\operation:
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
 
 	xor	   %r11, %r11 # initialise the data pointer offset as zero
@@ -481,59 +480,35 @@ _get_AAD_loop2_done\num_initial_blocks\operation:
 
 	mov	   %arg5, %rax                      # %rax = *Y0
 	movdqu	   (%rax), \XMM0                    # XMM0 = Y0
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM   %xmm14, \XMM0
 
 .if (\i == 5) || (\i == 6) || (\i == 7)
-.irpc index, \i_seq
-	paddd	   ONE(%rip), \XMM0                 # INCR Y0
-	movdqa	   \XMM0, %xmm\index
-        movdqa     SHUF_MASK(%rip), %xmm14
-	PSHUFB_XMM   %xmm14, %xmm\index      # perform a 16 byte swap
 
-.endr
-.irpc index, \i_seq
-	pxor	   16*0(%arg1), %xmm\index
-.endr
-.irpc index, \i_seq
-	movaps 0x10(%rdi), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 1
-.endr
-.irpc index, \i_seq
-	movaps 0x20(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
+	MOVADQ		ONE(%RIP),\TMP1
+	MOVADQ		0(%arg1),\TMP2
 .irpc index, \i_seq
-	movaps 0x30(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
+	paddd		\TMP1, \XMM0                 # INCR Y0
+	MOVADQ		\XMM0, %xmm\index
+	PSHUFB_XMM	%xmm14, %xmm\index      # perform a 16 byte swap
+	pxor		\TMP2, %xmm\index
 .endr
-.irpc index, \i_seq
-	movaps 0x40(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x50(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x60(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x70(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x80(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
-.endr
-.irpc index, \i_seq
-	movaps 0x90(%arg1), \TMP1
-	AESENC     \TMP1, %xmm\index          # Round 2
+	lea	0x10(%arg1),%r10
+	mov	keysize,%eax
+	shr	$2,%eax				# 128->4, 192->6, 256->8
+	add	$5,%eax			      # 128->9, 192->11, 256->13
+
+aes_loop_initial_enc\num_initial_blocks:
+	MOVADQ	(%r10),\TMP1
+.irpc	index, \i_seq
+	AESENC	\TMP1, %xmm\index
 .endr
+	add	$16,%r10
+	sub	$1,%eax
+	jnz	aes_loop_initial_enc\num_initial_blocks
+
+	MOVADQ	(%r10), \TMP1
 .irpc index, \i_seq
-	movaps 0xa0(%arg1), \TMP1
-	AESENCLAST \TMP1, %xmm\index         # Round 10
+	AESENCLAST \TMP1, %xmm\index         # Last Round
 .endr
 .irpc index, \i_seq
 	movdqu	   (%arg3 , %r11, 1), \TMP1
@@ -541,8 +516,6 @@ _get_AAD_loop2_done\num_initial_blocks\operation:
 	movdqu	   %xmm\index, (%arg2 , %r11, 1)
 	# write back plaintext/ciphertext for num_initial_blocks
 	add	   $16, %r11
-
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM	   %xmm14, %xmm\index
 
 		# prepare plaintext/ciphertext for GHASH computation
@@ -575,30 +548,28 @@ _get_AAD_loop2_done\num_initial_blocks\operation:
 * Precomputations for HashKey parallel with encryption of first 4 blocks.
 * Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
 */
-	paddd	   ONE(%rip), \XMM0              # INCR Y0
-	movdqa	   \XMM0, \XMM1
-        movdqa     SHUF_MASK(%rip), %xmm14
+	MOVADQ	   ONE(%RIP),\TMP1
+	paddd	   \TMP1, \XMM0              # INCR Y0
+	MOVADQ	   \XMM0, \XMM1
 	PSHUFB_XMM  %xmm14, \XMM1        # perform a 16 byte swap
 
-	paddd	   ONE(%rip), \XMM0              # INCR Y0
-	movdqa	   \XMM0, \XMM2
-        movdqa     SHUF_MASK(%rip), %xmm14
+	paddd	   \TMP1, \XMM0              # INCR Y0
+	MOVADQ	   \XMM0, \XMM2
 	PSHUFB_XMM  %xmm14, \XMM2        # perform a 16 byte swap
 
-	paddd	   ONE(%rip), \XMM0              # INCR Y0
-	movdqa	   \XMM0, \XMM3
-        movdqa     SHUF_MASK(%rip), %xmm14
+	paddd	   \TMP1, \XMM0              # INCR Y0
+	MOVADQ	   \XMM0, \XMM3
 	PSHUFB_XMM %xmm14, \XMM3        # perform a 16 byte swap
 
-	paddd	   ONE(%rip), \XMM0              # INCR Y0
-	movdqa	   \XMM0, \XMM4
-        movdqa     SHUF_MASK(%rip), %xmm14
+	paddd	   \TMP1, \XMM0              # INCR Y0
+	MOVADQ	   \XMM0, \XMM4
 	PSHUFB_XMM %xmm14, \XMM4        # perform a 16 byte swap
 
-	pxor	   16*0(%arg1), \XMM1
-	pxor	   16*0(%arg1), \XMM2
-	pxor	   16*0(%arg1), \XMM3
-	pxor	   16*0(%arg1), \XMM4
+	MOVADQ	   0(%arg1),\TMP1
+	pxor	   \TMP1, \XMM1
+	pxor	   \TMP1, \XMM2
+	pxor	   \TMP1, \XMM3
+	pxor	   \TMP1, \XMM4
 	movdqa	   \TMP3, \TMP5
 	pshufd	   $78, \TMP3, \TMP1
 	pxor	   \TMP3, \TMP1
@@ -636,7 +607,23 @@ _get_AAD_loop2_done\num_initial_blocks\operation:
 	pshufd	   $78, \TMP5, \TMP1
 	pxor	   \TMP5, \TMP1
 	movdqa	   \TMP1, HashKey_4_k(%rsp)
-	movaps 0xa0(%arg1), \TMP2
+	lea	   0xa0(%arg1),%r10
+	mov	   keysize,%eax
+	shr	   $2,%eax			# 128->4, 192->6, 256->8
+	sub	   $4,%eax			# 128->0, 192->2, 256->4
+	jz	   aes_loop_pre_enc_done\num_initial_blocks
+
+aes_loop_pre_enc\num_initial_blocks:
+	MOVADQ	   (%r10),\TMP2
+.irpc	index, 1234
+	AESENC	   \TMP2, %xmm\index
+.endr
+	add	   $16,%r10
+	sub	   $1,%eax
+	jnz	   aes_loop_pre_enc\num_initial_blocks
+
+aes_loop_pre_enc_done\num_initial_blocks:
+	MOVADQ	   (%r10), \TMP2
 	AESENCLAST \TMP2, \XMM1
 	AESENCLAST \TMP2, \XMM2
 	AESENCLAST \TMP2, \XMM3
@@ -655,15 +642,11 @@ _get_AAD_loop2_done\num_initial_blocks\operation:
 	movdqu     \XMM4, 16*3(%arg2 , %r11 , 1)
 
 	add	   $64, %r11
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap
 	pxor	   \XMMDst, \XMM1
 # combine GHASHed value with the corresponding ciphertext
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM %xmm14, \XMM2 # perform a 16 byte swap
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap
-        movdqa     SHUF_MASK(%rip), %xmm14
 	PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap
 
 _initial_blocks_done\num_initial_blocks\operation:
@@ -794,7 +777,23 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	AESENC	  \TMP3, \XMM3
 	AESENC	  \TMP3, \XMM4
 	PCLMULQDQ 0x00, \TMP5, \XMM8          # XMM8 = a0*b0
-	movaps 0xa0(%arg1), \TMP3
+	lea	  0xa0(%arg1),%r10
+	mov	  keysize,%eax
+	shr	  $2,%eax			# 128->4, 192->6, 256->8
+	sub	  $4,%eax			# 128->0, 192->2, 256->4
+	jz	  aes_loop_par_enc_done
+
+aes_loop_par_enc:
+	MOVADQ	  (%r10),\TMP3
+.irpc	index, 1234
+	AESENC	  \TMP3, %xmm\index
+.endr
+	add	  $16,%r10
+	sub	  $1,%eax
+	jnz	  aes_loop_par_enc
+
+aes_loop_par_enc_done:
+	MOVADQ	  (%r10), \TMP3
 	AESENCLAST \TMP3, \XMM1           # Round 10
 	AESENCLAST \TMP3, \XMM2
 	AESENCLAST \TMP3, \XMM3
@@ -986,8 +985,24 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	AESENC	  \TMP3, \XMM3
 	AESENC	  \TMP3, \XMM4
 	PCLMULQDQ 0x00, \TMP5, \XMM8          # XMM8 = a0*b0
-	movaps 0xa0(%arg1), \TMP3
-	AESENCLAST \TMP3, \XMM1           # Round 10
+	lea	  0xa0(%arg1),%r10
+	mov	  keysize,%eax
+	shr	  $2,%eax		        # 128->4, 192->6, 256->8
+	sub	  $4,%eax			# 128->0, 192->2, 256->4
+	jz	  aes_loop_par_dec_done
+
+aes_loop_par_dec:
+	MOVADQ	  (%r10),\TMP3
+.irpc	index, 1234
+	AESENC	  \TMP3, %xmm\index
+.endr
+	add	  $16,%r10
+	sub	  $1,%eax
+	jnz	  aes_loop_par_dec
+
+aes_loop_par_dec_done:
+	MOVADQ	  (%r10), \TMP3
+	AESENCLAST \TMP3, \XMM1           # last round
 	AESENCLAST \TMP3, \XMM2
 	AESENCLAST \TMP3, \XMM3
 	AESENCLAST \TMP3, \XMM4
@@ -1155,33 +1170,29 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	pxor      \TMP6, \XMMDst            # reduced result is in XMMDst
 .endm
 
-/* Encryption of a single block done*/
-.macro ENCRYPT_SINGLE_BLOCK XMM0 TMP1
 
-	pxor	(%arg1), \XMM0
-        movaps 16(%arg1), \TMP1
-	AESENC	\TMP1, \XMM0
-        movaps 32(%arg1), \TMP1
-	AESENC	\TMP1, \XMM0
-        movaps 48(%arg1), \TMP1
-	AESENC	\TMP1, \XMM0
-        movaps 64(%arg1), \TMP1
-	AESENC	\TMP1, \XMM0
-        movaps 80(%arg1), \TMP1
-	AESENC	\TMP1, \XMM0
-        movaps 96(%arg1), \TMP1
-	AESENC	\TMP1, \XMM0
-        movaps 112(%arg1), \TMP1
-	AESENC	\TMP1, \XMM0
-        movaps 128(%arg1), \TMP1
-	AESENC	\TMP1, \XMM0
-        movaps 144(%arg1), \TMP1
-	AESENC	\TMP1, \XMM0
-        movaps 160(%arg1), \TMP1
-	AESENCLAST	\TMP1, \XMM0
-.endm
+/* Encryption of a single block
+* uses eax & r10
+*/
 
+.macro ENCRYPT_SINGLE_BLOCK XMM0 TMP1
 
+	pxor		(%arg1), \XMM0
+	mov		keysize,%eax
+	shr		$2,%eax			# 128->4, 192->6, 256->8
+	add		$5,%eax			# 128->9, 192->11, 256->13
+	lea		16(%arg1), %r10	  # get first expanded key address
+
+_esb_loop_\@:
+	MOVADQ		(%r10),\TMP1
+	AESENC		\TMP1,\XMM0
+	add		$16,%r10
+	sub		$1,%eax
+	jnz		_esb_loop_\@
+
+	MOVADQ		(%r10),\TMP1
+	AESENCLAST	\TMP1,\XMM0
+.endm
 /*****************************************************************************
 * void aesni_gcm_dec(void *aes_ctx,    // AES Key schedule. Starts on a 16 byte boundary.
 *                   u8 *out,           // Plaintext output. Encrypt in-place is allowed.
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index ae855f4f64b7..947c6bf52c33 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -43,6 +43,7 @@
 #include <asm/crypto/glue_helper.h>
 #endif
 
+
 /* This data is stored at the end of the crypto_tfm struct.
  * It's a type of per "session" data storage location.
  * This needs to be 16 byte aligned.
@@ -182,7 +183,8 @@ static void aesni_gcm_enc_avx(void *ctx, u8 *out,
 			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len)
 {
-	if (plaintext_len < AVX_GEN2_OPTSIZE) {
+        struct crypto_aes_ctx *aes_ctx = (struct crypto_aes_ctx*)ctx;
+	if ((plaintext_len < AVX_GEN2_OPTSIZE) || (aes_ctx-> key_length != AES_KEYSIZE_128)){
 		aesni_gcm_enc(ctx, out, in, plaintext_len, iv, hash_subkey, aad,
 				aad_len, auth_tag, auth_tag_len);
 	} else {
@@ -197,7 +199,8 @@ static void aesni_gcm_dec_avx(void *ctx, u8 *out,
 			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len)
 {
-	if (ciphertext_len < AVX_GEN2_OPTSIZE) {
+        struct crypto_aes_ctx *aes_ctx = (struct crypto_aes_ctx*)ctx;
+	if ((ciphertext_len < AVX_GEN2_OPTSIZE) || (aes_ctx-> key_length != AES_KEYSIZE_128)) {
 		aesni_gcm_dec(ctx, out, in, ciphertext_len, iv, hash_subkey, aad,
 				aad_len, auth_tag, auth_tag_len);
 	} else {
@@ -231,7 +234,8 @@ static void aesni_gcm_enc_avx2(void *ctx, u8 *out,
 			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len)
 {
-	if (plaintext_len < AVX_GEN2_OPTSIZE) {
+       struct crypto_aes_ctx *aes_ctx = (struct crypto_aes_ctx*)ctx;
+	if ((plaintext_len < AVX_GEN2_OPTSIZE) || (aes_ctx-> key_length != AES_KEYSIZE_128)) {
 		aesni_gcm_enc(ctx, out, in, plaintext_len, iv, hash_subkey, aad,
 				aad_len, auth_tag, auth_tag_len);
 	} else if (plaintext_len < AVX_GEN4_OPTSIZE) {
@@ -250,7 +254,8 @@ static void aesni_gcm_dec_avx2(void *ctx, u8 *out,
 			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len)
 {
-	if (ciphertext_len < AVX_GEN2_OPTSIZE) {
+       struct crypto_aes_ctx *aes_ctx = (struct crypto_aes_ctx*)ctx;
+	if ((ciphertext_len < AVX_GEN2_OPTSIZE) || (aes_ctx-> key_length != AES_KEYSIZE_128)) {
 		aesni_gcm_dec(ctx, out, in, ciphertext_len, iv, hash_subkey,
 				aad, aad_len, auth_tag, auth_tag_len);
 	} else if (ciphertext_len < AVX_GEN4_OPTSIZE) {
@@ -511,7 +516,7 @@ static int ctr_crypt(struct blkcipher_desc *desc,
 	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
 		aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr,
-				  nbytes & AES_BLOCK_MASK, walk.iv);
+			              nbytes & AES_BLOCK_MASK, walk.iv);
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
@@ -902,7 +907,8 @@ static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key,
 	}
 	/*Account for 4 byte nonce at the end.*/
 	key_len -= 4;
-	if (key_len != AES_KEYSIZE_128) {
+	if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 &&
+	    key_len != AES_KEYSIZE_256) {
 		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
@@ -1013,6 +1019,7 @@ static int __driver_rfc4106_encrypt(struct aead_request *req)
 	__be32 counter = cpu_to_be32(1);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+	u32 key_len = ctx->aes_key_expanded.key_length;
 	void *aes_ctx = &(ctx->aes_key_expanded);
 	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
 	u8 iv_tab[16+AESNI_ALIGN];
@@ -1027,6 +1034,13 @@ static int __driver_rfc4106_encrypt(struct aead_request *req)
 	/* to 8 or 12 bytes */
 	if (unlikely(req->assoclen != 8 && req->assoclen != 12))
 		return -EINVAL;
+	if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16))
+	        return -EINVAL;
+	if (unlikely(key_len != AES_KEYSIZE_128 &&
+	             key_len != AES_KEYSIZE_192 &&
+	             key_len != AES_KEYSIZE_256))
+	        return -EINVAL;
+
 	/* IV below built */
 	for (i = 0; i < 4; i++)
 		*(iv+i) = ctx->nonce[i];
@@ -1091,6 +1105,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 	int retval = 0;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+	u32 key_len = ctx->aes_key_expanded.key_length;
 	void *aes_ctx = &(ctx->aes_key_expanded);
 	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
 	u8 iv_and_authTag[32+AESNI_ALIGN];
@@ -1104,6 +1119,13 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 	if (unlikely((req->cryptlen < auth_tag_len) ||
 		(req->assoclen != 8 && req->assoclen != 12)))
 		return -EINVAL;
+	if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16))
+	        return -EINVAL;
+	if (unlikely(key_len != AES_KEYSIZE_128 &&
+	             key_len != AES_KEYSIZE_192 &&
+	             key_len != AES_KEYSIZE_256))
+	        return -EINVAL;
+
 	/* Assuming we are supporting rfc4106 64-bit extended */
 	/* sequence numbers We need to have the AAD length */
 	/* equal to 8 or 12 bytes */
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
index 38a14f818ef1..d6fc59aaaadf 100644
--- a/arch/x86/crypto/des3_ede_glue.c
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -504,6 +504,4 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Triple DES EDE Cipher Algorithm, asm optimized");
 MODULE_ALIAS_CRYPTO("des3_ede");
 MODULE_ALIAS_CRYPTO("des3_ede-asm");
-MODULE_ALIAS_CRYPTO("des");
-MODULE_ALIAS_CRYPTO("des-asm");
 MODULE_AUTHOR("Jussi Kivilinna <jussi.kivilinna@iki.fi>");