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 AEAD support to crypto engine - allow batch registration in simd Algorithms: - add CFB mode - add speck block cipher - add sm4 block cipher - new test case for crct10dif - improve scheduling latency on ARM - scatter/gather support to gcm in aesni - convert x86 crypto algorithms to skcihper Drivers: - hmac(sha224/sha256) support in inside-secure - aes gcm/ccm support in stm32 - stm32mp1 support in stm32 - ccree driver from staging tree - gcm support over QI in caam - add ks-sa hwrng driver" * 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (212 commits) crypto: ccree - remove unused enums crypto: ahash - Fix early termination in hash walk crypto: brcm - explicitly cast cipher to hash type crypto: talitos - don't leak pointers to authenc keys crypto: qat - don't leak pointers to authenc keys crypto: picoxcell - don't leak pointers to authenc keys crypto: ixp4xx - don't leak pointers to authenc keys crypto: chelsio - don't leak pointers to authenc keys crypto: caam/qi - don't leak pointers to authenc keys crypto: caam - don't leak pointers to authenc keys crypto: lrw - Free rctx->ext with kzfree crypto: talitos - fix IPsec cipher in length crypto: Deduplicate le32_to_cpu_array() and cpu_to_le32_array() crypto: doc - clarify hash callbacks state machine crypto: api - Keep failed instances alive crypto: api - Make crypto_alg_lookup static crypto: api - Remove unused crypto_type lookup function crypto: chelsio - Remove declaration of static function from header crypto: inside-secure - hmac(sha224) support crypto: inside-secure - hmac(sha256) support ..
author: Linus Torvalds <torvalds@linux-foundation.org> 2018-04-04 17:11:08 -0700
committer: Linus Torvalds <torvalds@linux-foundation.org> 2018-04-04 17:11:08 -0700
commit: 9eb31227cbccd3a37da0f42604f1ab5fc556bc53 (patch)
tree: 9aa467e620e002bf01cecdd98e3908e0cc3e7221
parent: 527cd20771888443b5d8707debe98f62c7a1f596 (diff)
parent: f444ec106407d600f17fa1a4bd14f84577401dec (diff)
download: linux-9eb31227cbccd3a37da0f42604f1ab5fc556bc53.tar.bz2
183 files changed, 22264 insertions, 7763 deletions
diff --git a/Documentation/crypto/crypto_engine.rst b/Documentation/crypto/crypto_engine.rst
new file mode 100644
index 000000000000..8272ac92a14f
--- /dev/null
+++ b/Documentation/crypto/crypto_engine.rst
@@ -0,0 +1,48 @@
+=============
+CRYPTO ENGINE
+=============
+
+Overview
+--------
+The crypto engine API (CE), is a crypto queue manager.
+
+Requirement
+-----------
+You have to put at start of your tfm_ctx the struct crypto_engine_ctx
+struct your_tfm_ctx {
+        struct crypto_engine_ctx enginectx;
+        ...
+};
+Why: Since CE manage only crypto_async_request, it cannot know the underlying
+request_type and so have access only on the TFM.
+So using container_of for accessing __ctx is impossible.
+Furthermore, the crypto engine cannot know the "struct your_tfm_ctx",
+so it must assume that crypto_engine_ctx is at start of it.
+
+Order of operations
+-------------------
+You have to obtain a struct crypto_engine via crypto_engine_alloc_init().
+And start it via crypto_engine_start().
+
+Before transferring any request, you have to fill the enginectx.
+- prepare_request: (taking a function pointer) If you need to do some processing before doing the request
+- unprepare_request: (taking a function pointer) Undoing what's done in prepare_request
+- do_one_request: (taking a function pointer) Do encryption for current request
+
+Note: that those three functions get the crypto_async_request associated with the received request.
+So your need to get the original request via container_of(areq, struct yourrequesttype_request, base);
+
+When your driver receive a crypto_request, you have to transfer it to
+the cryptoengine via one of:
+- crypto_transfer_ablkcipher_request_to_engine()
+- crypto_transfer_aead_request_to_engine()
+- crypto_transfer_akcipher_request_to_engine()
+- crypto_transfer_hash_request_to_engine()
+- crypto_transfer_skcipher_request_to_engine()
+
+At the end of the request process, a call to one of the following function is needed:
+- crypto_finalize_ablkcipher_request
+- crypto_finalize_aead_request
+- crypto_finalize_akcipher_request
+- crypto_finalize_hash_request
+- crypto_finalize_skcipher_request
diff --git a/Documentation/crypto/devel-algos.rst b/Documentation/crypto/devel-algos.rst
index 66f50d32dcec..c45c6f400dbd 100644
--- a/Documentation/crypto/devel-algos.rst
+++ b/Documentation/crypto/devel-algos.rst
@@ -236,6 +236,14 @@ when used from another part of the kernel.
                                |
                                '---------------> HASH2
 
+Note that it is perfectly legal to "abandon" a request object:
+- call .init() and then (as many times) .update()
+- _not_ call any of .final(), .finup() or .export() at any point in future
+
+In other words implementations should mind the resource allocation and clean-up.
+No resources related to request objects should remain allocated after a call
+to .init() or .update(), since there might be no chance to free them.
+
 
 Specifics Of Asynchronous HASH Transformation
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt b/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
index cec8d5d74e26..c2598ab27f2e 100644
--- a/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
+++ b/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
@@ -1,7 +1,8 @@
 Arm TrustZone CryptoCell cryptographic engine
 
 Required properties:
-- compatible: Should be "arm,cryptocell-712-ree".
+- compatible: Should be one of: "arm,cryptocell-712-ree",
+  "arm,cryptocell-710-ree" or "arm,cryptocell-630p-ree".
 - reg: Base physical address of the engine and length of memory mapped region.
 - interrupts: Interrupt number for the device.
 
diff --git a/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt b/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
index 30c3ce6b502e..5dba55cdfa63 100644
--- a/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
+++ b/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
@@ -8,7 +8,11 @@ Required properties:
 - interrupt-names: Should be "ring0", "ring1", "ring2", "ring3", "eip", "mem".
 
 Optional properties:
-- clocks: Reference to the crypto engine clock.
+- clocks: Reference to the crypto engine clocks, the second clock is
+          needed for the Armada 7K/8K SoCs.
+- clock-names: mandatory if there is a second clock, in this case the
+               name must be "core" for the first clock and "reg" for
+               the second one.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/rng/imx-rngc.txt b/Documentation/devicetree/bindings/rng/imx-rng.txt
index 93c7174a7bed..405c2b00ccb0 100644
--- a/Documentation/devicetree/bindings/rng/imx-rngc.txt
+++ b/Documentation/devicetree/bindings/rng/imx-rng.txt
@@ -1,15 +1,14 @@
-Freescale RNGC (Random Number Generator Version C)
-
-The driver also supports version B, which is mostly compatible
-to version C.
+Freescale RNGA/RNGB/RNGC (Random Number Generator Versions A, B and C)
 
 Required properties:
 - compatible : should be one of
+               "fsl,imx21-rnga"
+               "fsl,imx31-rnga" (backward compatible with "fsl,imx21-rnga")
                "fsl,imx25-rngb"
                "fsl,imx35-rngc"
 - reg : offset and length of the register set of this block
-- interrupts : the interrupt number for the RNGC block
-- clocks : the RNGC clk source
+- interrupts : the interrupt number for the RNG block
+- clocks : the RNG clk source
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/rng/ks-sa-rng.txt b/Documentation/devicetree/bindings/rng/ks-sa-rng.txt
new file mode 100644
index 000000000000..b7a65b487901
--- /dev/null
+++ b/Documentation/devicetree/bindings/rng/ks-sa-rng.txt
@@ -0,0 +1,21 @@
+Keystone SoC Hardware Random Number Generator(HWRNG) Module
+
+On Keystone SoCs HWRNG module is a submodule of the Security Accelerator.
+
+- compatible: should be "ti,keystone-rng"
+- ti,syscon-sa-cfg: phandle to syscon node of the SA configuration registers.
+		    This registers are shared between hwrng and crypto drivers.
+- clocks: phandle to the reference clocks for the subsystem
+- clock-names: functional clock name. Should be set to "fck"
+- reg: HWRNG module register space
+
+Example:
+/* K2HK */
+
+rng@24000 {
+	compatible = "ti,keystone-rng";
+	ti,syscon-sa-cfg = <&sa_config>;
+	clocks = <&clksa>;
+	clock-names = "fck";
+	reg = <0x24000 0x1000>;
+};
diff --git a/Documentation/devicetree/bindings/rng/omap_rng.txt b/Documentation/devicetree/bindings/rng/omap_rng.txt
index 9cf7876ab434..ea434ce50f36 100644
--- a/Documentation/devicetree/bindings/rng/omap_rng.txt
+++ b/Documentation/devicetree/bindings/rng/omap_rng.txt
@@ -13,7 +13,12 @@ Required properties:
 - interrupts : the interrupt number for the RNG module.
 		Used for "ti,omap4-rng" and "inside-secure,safexcel-eip76"
 - clocks: the trng clock source. Only mandatory for the
-  "inside-secure,safexcel-eip76" compatible.
+  "inside-secure,safexcel-eip76" compatible, the second clock is
+  needed for the Armada 7K/8K SoCs
+- clock-names: mandatory if there is a second clock, in this case the
+  name must be "core" for the first clock and "reg" for the second
+  one
+
 
 Example:
 /* AM335x */
diff --git a/Documentation/devicetree/bindings/rng/st,stm32-rng.txt b/Documentation/devicetree/bindings/rng/st,stm32-rng.txt
index 47f04176f93b..1dfa7d51e006 100644
--- a/Documentation/devicetree/bindings/rng/st,stm32-rng.txt
+++ b/Documentation/devicetree/bindings/rng/st,stm32-rng.txt
@@ -11,6 +11,10 @@ Required properties:
 - interrupts : The designated IRQ line for the RNG
 - clocks : The clock needed to enable the RNG
 
+Optional properties:
+- resets : The reset to properly start RNG
+- clock-error-detect : Enable the clock detection management
+
 Example:
 
 	rng: rng@50060800 {
diff --git a/MAINTAINERS b/MAINTAINERS
index 2328eed6aea9..9d42bb8bb120 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3252,12 +3252,11 @@ F:	drivers/net/ieee802154/cc2520.c
 F:	include/linux/spi/cc2520.h
 F:	Documentation/devicetree/bindings/net/ieee802154/cc2520.txt
 
-CCREE ARM TRUSTZONE CRYPTOCELL 700 REE DRIVER
+CCREE ARM TRUSTZONE CRYPTOCELL REE DRIVER
 M:	Gilad Ben-Yossef <gilad@benyossef.com>
 L:	linux-crypto@vger.kernel.org
-L:	driverdev-devel@linuxdriverproject.org
 S:	Supported
-F:	drivers/staging/ccree/
+F:	drivers/crypto/ccree/
 W:	https://developer.arm.com/products/system-ip/trustzone-cryptocell/cryptocell-700-family
 
 CEC FRAMEWORK
@@ -6962,7 +6961,7 @@ F:	drivers/input/input-mt.c
 K:	\b(ABS|SYN)_MT_
 
 INSIDE SECURE CRYPTO DRIVER
-M:	Antoine Tenart <antoine.tenart@free-electrons.com>
+M:	Antoine Tenart <antoine.tenart@bootlin.com>
 F:	drivers/crypto/inside-secure/
 S:	Maintained
 L:	linux-crypto@vger.kernel.org
@@ -7200,6 +7199,14 @@ L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/hw/i40iw/
 
+INTEL SHA MULTIBUFFER DRIVER
+M:	Megha Dey <megha.dey@linux.intel.com>
+R:	Tim Chen <tim.c.chen@linux.intel.com>
+L:	linux-crypto@vger.kernel.org
+S:	Supported
+F:	arch/x86/crypto/sha*-mb
+F:	crypto/mcryptd.c
+
 INTEL TELEMETRY DRIVER
 M:	Souvik Kumar Chakravarty <souvik.k.chakravarty@intel.com>
 L:	platform-driver-x86@vger.kernel.org
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index b8e69fe282b8..925d1364727a 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -121,4 +121,10 @@ config CRYPTO_CHACHA20_NEON
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_CHACHA20
 
+config CRYPTO_SPECK_NEON
+	tristate "NEON accelerated Speck cipher algorithms"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_SPECK
+
 endif
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 30ef8e291271..3304e671918d 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha20-neon.o
+obj-$(CONFIG_CRYPTO_SPECK_NEON) += speck-neon.o
 
 ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -53,7 +54,9 @@ ghash-arm-ce-y	:= ghash-ce-core.o ghash-ce-glue.o
 crct10dif-arm-ce-y	:= crct10dif-ce-core.o crct10dif-ce-glue.o
 crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o
 chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o
+speck-neon-y := speck-neon-core.o speck-neon-glue.o
 
+ifdef REGENERATE_ARM_CRYPTO
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)
 
@@ -62,5 +65,6 @@ $(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
 
 $(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
 	$(call cmd,perl)
+endif
 
 .PRECIOUS: $(obj)/sha256-core.S $(obj)/sha512-core.S
diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S
index 54b384084637..184d6c2d15d5 100644
--- a/arch/arm/crypto/aes-cipher-core.S
+++ b/arch/arm/crypto/aes-cipher-core.S
@@ -174,6 +174,16 @@
 	.ltorg
 	.endm
 
+ENTRY(__aes_arm_encrypt)
+	do_crypt	fround, crypto_ft_tab, crypto_ft_tab + 1, 2
+ENDPROC(__aes_arm_encrypt)
+
+	.align		5
+ENTRY(__aes_arm_decrypt)
+	do_crypt	iround, crypto_it_tab, __aes_arm_inverse_sbox, 0
+ENDPROC(__aes_arm_decrypt)
+
+	.section	".rodata", "a"
 	.align		L1_CACHE_SHIFT
 	.type		__aes_arm_inverse_sbox, %object
 __aes_arm_inverse_sbox:
@@ -210,12 +220,3 @@ __aes_arm_inverse_sbox:
 	.byte		0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
 	.byte		0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
 	.size		__aes_arm_inverse_sbox, . - __aes_arm_inverse_sbox
-
-ENTRY(__aes_arm_encrypt)
-	do_crypt	fround, crypto_ft_tab, crypto_ft_tab + 1, 2
-ENDPROC(__aes_arm_encrypt)
-
-	.align		5
-ENTRY(__aes_arm_decrypt)
-	do_crypt	iround, crypto_it_tab, __aes_arm_inverse_sbox, 0
-ENDPROC(__aes_arm_decrypt)
diff --git a/arch/arm/crypto/speck-neon-core.S b/arch/arm/crypto/speck-neon-core.S
new file mode 100644
index 000000000000..3c1e203e53b9
--- /dev/null
+++ b/arch/arm/crypto/speck-neon-core.S
@@ -0,0 +1,432 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
+ *
+ * Copyright (c) 2018 Google, Inc
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+	.text
+	.fpu		neon
+
+	// arguments
+	ROUND_KEYS	.req	r0	// const {u64,u32} *round_keys
+	NROUNDS		.req	r1	// int nrounds
+	DST		.req	r2	// void *dst
+	SRC		.req	r3	// const void *src
+	NBYTES		.req	r4	// unsigned int nbytes
+	TWEAK		.req	r5	// void *tweak
+
+	// registers which hold the data being encrypted/decrypted
+	X0		.req	q0
+	X0_L		.req	d0
+	X0_H		.req	d1
+	Y0		.req	q1
+	Y0_H		.req	d3
+	X1		.req	q2
+	X1_L		.req	d4
+	X1_H		.req	d5
+	Y1		.req	q3
+	Y1_H		.req	d7
+	X2		.req	q4
+	X2_L		.req	d8
+	X2_H		.req	d9
+	Y2		.req	q5
+	Y2_H		.req	d11
+	X3		.req	q6
+	X3_L		.req	d12
+	X3_H		.req	d13
+	Y3		.req	q7
+	Y3_H		.req	d15
+
+	// the round key, duplicated in all lanes
+	ROUND_KEY	.req	q8
+	ROUND_KEY_L	.req	d16
+	ROUND_KEY_H	.req	d17
+
+	// index vector for vtbl-based 8-bit rotates
+	ROTATE_TABLE	.req	d18
+
+	// multiplication table for updating XTS tweaks
+	GF128MUL_TABLE	.req	d19
+	GF64MUL_TABLE	.req	d19
+
+	// current XTS tweak value(s)
+	TWEAKV		.req	q10
+	TWEAKV_L	.req	d20
+	TWEAKV_H	.req	d21
+
+	TMP0		.req	q12
+	TMP0_L		.req	d24
+	TMP0_H		.req	d25
+	TMP1		.req	q13
+	TMP2		.req	q14
+	TMP3		.req	q15
+
+	.align		4
+.Lror64_8_table:
+	.byte		1, 2, 3, 4, 5, 6, 7, 0
+.Lror32_8_table:
+	.byte		1, 2, 3, 0, 5, 6, 7, 4
+.Lrol64_8_table:
+	.byte		7, 0, 1, 2, 3, 4, 5, 6
+.Lrol32_8_table:
+	.byte		3, 0, 1, 2, 7, 4, 5, 6
+.Lgf128mul_table:
+	.byte		0, 0x87
+	.fill		14
+.Lgf64mul_table:
+	.byte		0, 0x1b, (0x1b << 1), (0x1b << 1) ^ 0x1b
+	.fill		12
+
+/*
+ * _speck_round_128bytes() - Speck encryption round on 128 bytes at a time
+ *
+ * Do one Speck encryption round on the 128 bytes (8 blocks for Speck128, 16 for
+ * Speck64) stored in X0-X3 and Y0-Y3, using the round key stored in all lanes
+ * of ROUND_KEY.  'n' is the lane size: 64 for Speck128, or 32 for Speck64.
+ *
+ * The 8-bit rotates are implemented using vtbl instead of vshr + vsli because
+ * the vtbl approach is faster on some processors and the same speed on others.
+ */
+.macro _speck_round_128bytes	n
+
+	// x = ror(x, 8)
+	vtbl.8		X0_L, {X0_L}, ROTATE_TABLE
+	vtbl.8		X0_H, {X0_H}, ROTATE_TABLE
+	vtbl.8		X1_L, {X1_L}, ROTATE_TABLE
+	vtbl.8		X1_H, {X1_H}, ROTATE_TABLE
+	vtbl.8		X2_L, {X2_L}, ROTATE_TABLE
+	vtbl.8		X2_H, {X2_H}, ROTATE_TABLE
+	vtbl.8		X3_L, {X3_L}, ROTATE_TABLE
+	vtbl.8		X3_H, {X3_H}, ROTATE_TABLE
+
+	// x += y
+	vadd.u\n	X0, Y0
+	vadd.u\n	X1, Y1
+	vadd.u\n	X2, Y2
+	vadd.u\n	X3, Y3
+
+	// x ^= k
+	veor		X0, ROUND_KEY
+	veor		X1, ROUND_KEY
+	veor		X2, ROUND_KEY
+	veor		X3, ROUND_KEY
+
+	// y = rol(y, 3)
+	vshl.u\n	TMP0, Y0, #3
+	vshl.u\n	TMP1, Y1, #3
+	vshl.u\n	TMP2, Y2, #3
+	vshl.u\n	TMP3, Y3, #3
+	vsri.u\n	TMP0, Y0, #(\n - 3)
+	vsri.u\n	TMP1, Y1, #(\n - 3)
+	vsri.u\n	TMP2, Y2, #(\n - 3)
+	vsri.u\n	TMP3, Y3, #(\n - 3)
+
+	// y ^= x
+	veor		Y0, TMP0, X0
+	veor		Y1, TMP1, X1
+	veor		Y2, TMP2, X2
+	veor		Y3, TMP3, X3
+.endm
+
+/*
+ * _speck_unround_128bytes() - Speck decryption round on 128 bytes at a time
+ *
+ * This is the inverse of _speck_round_128bytes().
+ */
+.macro _speck_unround_128bytes	n
+
+	// y ^= x
+	veor		TMP0, Y0, X0
+	veor		TMP1, Y1, X1
+	veor		TMP2, Y2, X2
+	veor		TMP3, Y3, X3
+
+	// y = ror(y, 3)
+	vshr.u\n	Y0, TMP0, #3
+	vshr.u\n	Y1, TMP1, #3
+	vshr.u\n	Y2, TMP2, #3
+	vshr.u\n	Y3, TMP3, #3
+	vsli.u\n	Y0, TMP0, #(\n - 3)
+	vsli.u\n	Y1, TMP1, #(\n - 3)
+	vsli.u\n	Y2, TMP2, #(\n - 3)
+	vsli.u\n	Y3, TMP3, #(\n - 3)
+
+	// x ^= k
+	veor		X0, ROUND_KEY
+	veor		X1, ROUND_KEY
+	veor		X2, ROUND_KEY
+	veor		X3, ROUND_KEY
+
+	// x -= y
+	vsub.u\n	X0, Y0
+	vsub.u\n	X1, Y1
+	vsub.u\n	X2, Y2
+	vsub.u\n	X3, Y3
+
+	// x = rol(x, 8);
+	vtbl.8		X0_L, {X0_L}, ROTATE_TABLE
+	vtbl.8		X0_H, {X0_H}, ROTATE_TABLE
+	vtbl.8		X1_L, {X1_L}, ROTATE_TABLE
+	vtbl.8		X1_H, {X1_H}, ROTATE_TABLE
+	vtbl.8		X2_L, {X2_L}, ROTATE_TABLE
+	vtbl.8		X2_H, {X2_H}, ROTATE_TABLE
+	vtbl.8		X3_L, {X3_L}, ROTATE_TABLE
+	vtbl.8		X3_H, {X3_H}, ROTATE_TABLE
+.endm
+
+.macro _xts128_precrypt_one	dst_reg, tweak_buf, tmp
+
+	// Load the next source block
+	vld1.8		{\dst_reg}, [SRC]!
+
+	// Save the current tweak in the tweak buffer
+	vst1.8		{TWEAKV}, [\tweak_buf:128]!
+
+	// XOR the next source block with the current tweak
+	veor		\dst_reg, TWEAKV
+
+	/*
+	 * Calculate the next tweak by multiplying the current one by x,
+	 * modulo p(x) = x^128 + x^7 + x^2 + x + 1.
+	 */
+	vshr.u64	\tmp, TWEAKV, #63
+	vshl.u64	TWEAKV, #1
+	veor		TWEAKV_H, \tmp\()_L
+	vtbl.8		\tmp\()_H, {GF128MUL_TABLE}, \tmp\()_H
+	veor		TWEAKV_L, \tmp\()_H
+.endm
+
+.macro _xts64_precrypt_two	dst_reg, tweak_buf, tmp
+
+	// Load the next two source blocks
+	vld1.8		{\dst_reg}, [SRC]!
+
+	// Save the current two tweaks in the tweak buffer
+	vst1.8		{TWEAKV}, [\tweak_buf:128]!
+
+	// XOR the next two source blocks with the current two tweaks
+	veor		\dst_reg, TWEAKV
+
+	/*
+	 * Calculate the next two tweaks by multiplying the current ones by x^2,
+	 * modulo p(x) = x^64 + x^4 + x^3 + x + 1.
+	 */
+	vshr.u64	\tmp, TWEAKV, #62
+	vshl.u64	TWEAKV, #2
+	vtbl.8		\tmp\()_L, {GF64MUL_TABLE}, \tmp\()_L
+	vtbl.8		\tmp\()_H, {GF64MUL_TABLE}, \tmp\()_H
+	veor		TWEAKV, \tmp
+.endm
+
+/*
+ * _speck_xts_crypt() - Speck-XTS encryption/decryption
+ *
+ * Encrypt or decrypt NBYTES bytes of data from the SRC buffer to the DST buffer
+ * using Speck-XTS, specifically the variant with a block size of '2n' and round
+ * count given by NROUNDS.  The expanded round keys are given in ROUND_KEYS, and
+ * the current XTS tweak value is given in TWEAK.  It's assumed that NBYTES is a
+ * nonzero multiple of 128.
+ */
+.macro _speck_xts_crypt	n, decrypting
+	push		{r4-r7}
+	mov		r7, sp
+
+	/*
+	 * The first four parameters were passed in registers r0-r3.  Load the
+	 * additional parameters, which were passed on the stack.
+	 */
+	ldr		NBYTES, [sp, #16]
+	ldr		TWEAK, [sp, #20]
+
+	/*
+	 * If decrypting, modify the ROUND_KEYS parameter to point to the last
+	 * round key rather than the first, since for decryption the round keys
+	 * are used in reverse order.
+	 */
+.if \decrypting
+.if \n == 64
+	add		ROUND_KEYS, ROUND_KEYS, NROUNDS, lsl #3
+	sub		ROUND_KEYS, #8
+.else
+	add		ROUND_KEYS, ROUND_KEYS, NROUNDS, lsl #2
+	sub		ROUND_KEYS, #4
+.endif
+.endif
+
+	// Load the index vector for vtbl-based 8-bit rotates
+.if \decrypting
+	ldr		r12, =.Lrol\n\()_8_table
+.else
+	ldr		r12, =.Lror\n\()_8_table
+.endif
+	vld1.8		{ROTATE_TABLE}, [r12:64]
+
+	// One-time XTS preparation
+
+	/*
+	 * Allocate stack space to store 128 bytes worth of tweaks.  For
+	 * performance, this space is aligned to a 16-byte boundary so that we
+	 * can use the load/store instructions that declare 16-byte alignment.
+	 */
+	sub		sp, #128
+	bic		sp, #0xf
+
+.if \n == 64
+	// Load first tweak
+	vld1.8		{TWEAKV}, [TWEAK]
+
+	// Load GF(2^128) multiplication table
+	ldr		r12, =.Lgf128mul_table
+	vld1.8		{GF128MUL_TABLE}, [r12:64]
+.else
+	// Load first tweak
+	vld1.8		{TWEAKV_L}, [TWEAK]
+
+	// Load GF(2^64) multiplication table
+	ldr		r12, =.Lgf64mul_table
+	vld1.8		{GF64MUL_TABLE}, [r12:64]
+
+	// Calculate second tweak, packing it together with the first
+	vshr.u64	TMP0_L, TWEAKV_L, #63
+	vtbl.u8		TMP0_L, {GF64MUL_TABLE}, TMP0_L
+	vshl.u64	TWEAKV_H, TWEAKV_L, #1
+	veor		TWEAKV_H, TMP0_L
+.endif
+
+.Lnext_128bytes_\@:
+
+	/*
+	 * Load the source blocks into {X,Y}[0-3], XOR them with their XTS tweak
+	 * values, and save the tweaks on the stack for later.  Then
+	 * de-interleave the 'x' and 'y' elements of each block, i.e. make it so
+	 * that the X[0-3] registers contain only the second halves of blocks,
+	 * and the Y[0-3] registers contain only the first halves of blocks.
+	 * (Speck uses the order (y, x) rather than the more intuitive (x, y).)
+	 */
+	mov		r12, sp
+.if \n == 64
+	_xts128_precrypt_one	X0, r12, TMP0
+	_xts128_precrypt_one	Y0, r12, TMP0
+	_xts128_precrypt_one	X1, r12, TMP0
+	_xts128_precrypt_one	Y1, r12, TMP0
+	_xts128_precrypt_one	X2, r12, TMP0
+	_xts128_precrypt_one	Y2, r12, TMP0
+	_xts128_precrypt_one	X3, r12, TMP0
+	_xts128_precrypt_one	Y3, r12, TMP0
+	vswp		X0_L, Y0_H
+	vswp		X1_L, Y1_H
+	vswp		X2_L, Y2_H
+	vswp		X3_L, Y3_H
+.else
+	_xts64_precrypt_two	X0, r12, TMP0
+	_xts64_precrypt_two	Y0, r12, TMP0
+	_xts64_precrypt_two	X1, r12, TMP0
+	_xts64_precrypt_two	Y1, r12, TMP0
+	_xts64_precrypt_two	X2, r12, TMP0
+	_xts64_precrypt_two	Y2, r12, TMP0
+	_xts64_precrypt_two	X3, r12, TMP0
+	_xts64_precrypt_two	Y3, r12, TMP0
+	vuzp.32		Y0, X0
+	vuzp.32		Y1, X1
+	vuzp.32		Y2, X2
+	vuzp.32		Y3, X3
+.endif
+
+	// Do the cipher rounds
+
+	mov		r12, ROUND_KEYS
+	mov		r6, NROUNDS
+
+.Lnext_round_\@:
+.if \decrypting
+.if \n == 64
+	vld1.64		ROUND_KEY_L, [r12]
+	sub		r12, #8
+	vmov		ROUND_KEY_H, ROUND_KEY_L
+.else
+	vld1.32		{ROUND_KEY_L[],ROUND_KEY_H[]}, [r12]
+	sub		r12, #4
+.endif
+	_speck_unround_128bytes	\n
+.else
+.if \n == 64
+	vld1.64		ROUND_KEY_L, [r12]!
+	vmov		ROUND_KEY_H, ROUND_KEY_L
+.else
+	vld1.32		{ROUND_KEY_L[],ROUND_KEY_H[]}, [r12]!
+.endif
+	_speck_round_128bytes	\n
+.endif
+	subs		r6, r6, #1
+	bne		.Lnext_round_\@
+
+	// Re-interleave the 'x' and 'y' elements of each block
+.if \n == 64
+	vswp		X0_L, Y0_H
+	vswp		X1_L, Y1_H
+	vswp		X2_L, Y2_H
+	vswp		X3_L, Y3_H
+.else
+	vzip.32		Y0, X0
+	vzip.32		Y1, X1
+	vzip.32		Y2, X2
+	vzip.32		Y3, X3
+.endif
+
+	// XOR the encrypted/decrypted blocks with the tweaks we saved earlier
+	mov		r12, sp
+	vld1.8		{TMP0, TMP1}, [r12:128]!
+	vld1.8		{TMP2, TMP3}, [r12:128]!
+	veor		X0, TMP0
+	veor		Y0, TMP1
+	veor		X1, TMP2
+	veor		Y1, TMP3
+	vld1.8		{TMP0, TMP1}, [r12:128]!
+	vld1.8		{TMP2, TMP3}, [r12:128]!
+	veor		X2, TMP0
+	veor		Y2, TMP1
+	veor		X3, TMP2
+	veor		Y3, TMP3
+
+	// Store the ciphertext in the destination buffer
+	vst1.8		{X0, Y0}, [DST]!
+	vst1.8		{X1, Y1}, [DST]!
+	vst1.8		{X2, Y2}, [DST]!
+	vst1.8		{X3, Y3}, [DST]!
+
+	// Continue if there are more 128-byte chunks remaining, else return
+	subs		NBYTES, #128
+	bne		.Lnext_128bytes_\@
+
+	// Store the next tweak
+.if \n == 64
+	vst1.8		{TWEAKV}, [TWEAK]
+.else
+	vst1.8		{TWEAKV_L}, [TWEAK]
+.endif
+
+	mov		sp, r7
+	pop		{r4-r7}
+	bx		lr
+.endm
+
+ENTRY(speck128_xts_encrypt_neon)
+	_speck_xts_crypt	n=64, decrypting=0
+ENDPROC(speck128_xts_encrypt_neon)
+
+ENTRY(speck128_xts_decrypt_neon)
+	_speck_xts_crypt	n=64, decrypting=1
+ENDPROC(speck128_xts_decrypt_neon)
+
+ENTRY(speck64_xts_encrypt_neon)
+	_speck_xts_crypt	n=32, decrypting=0
+ENDPROC(speck64_xts_encrypt_neon)
+
+ENTRY(speck64_xts_decrypt_neon)
+	_speck_xts_crypt	n=32, decrypting=1
+ENDPROC(speck64_xts_decrypt_neon)
diff --git a/arch/arm/crypto/speck-neon-glue.c b/arch/arm/crypto/speck-neon-glue.c
new file mode 100644
index 000000000000..f012c3ea998f
--- /dev/null
+++ b/arch/arm/crypto/speck-neon-glue.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
+ *
+ * Copyright (c) 2018 Google, Inc
+ *
+ * Note: the NIST recommendation for XTS only specifies a 128-bit block size,
+ * but a 64-bit version (needed for Speck64) is fairly straightforward; the math
+ * is just done in GF(2^64) instead of GF(2^128), with the reducing polynomial
+ * x^64 + x^4 + x^3 + x + 1 from the original XEX paper (Rogaway, 2004:
+ * "Efficient Instantiations of Tweakable Blockciphers and Refinements to Modes
+ * OCB and PMAC"), represented as 0x1B.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/algapi.h>
+#include <crypto/gf128mul.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/speck.h>
+#include <crypto/xts.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+/* The assembly functions only handle multiples of 128 bytes */
+#define SPECK_NEON_CHUNK_SIZE	128
+
+/* Speck128 */
+
+struct speck128_xts_tfm_ctx {
+	struct speck128_tfm_ctx main_key;
+	struct speck128_tfm_ctx tweak_key;
+};
+
+asmlinkage void speck128_xts_encrypt_neon(const u64 *round_keys, int nrounds,
+					  void *dst, const void *src,
+					  unsigned int nbytes, void *tweak);
+
+asmlinkage void speck128_xts_decrypt_neon(const u64 *round_keys, int nrounds,
+					  void *dst, const void *src,
+					  unsigned int nbytes, void *tweak);
+
+typedef void (*speck128_crypt_one_t)(const struct speck128_tfm_ctx *,
+				     u8 *, const u8 *);
+typedef void (*speck128_xts_crypt_many_t)(const u64 *, int, void *,
+					  const void *, unsigned int, void *);
+
+static __always_inline int
+__speck128_xts_crypt(struct skcipher_request *req,
+		     speck128_crypt_one_t crypt_one,
+		     speck128_xts_crypt_many_t crypt_many)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct speck128_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	le128 tweak;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	crypto_speck128_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+		u8 *dst = walk.dst.virt.addr;
+		const u8 *src = walk.src.virt.addr;
+
+		if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
+			unsigned int count;
+
+			count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
+			kernel_neon_begin();
+			(*crypt_many)(ctx->main_key.round_keys,
+				      ctx->main_key.nrounds,
+				      dst, src, count, &tweak);
+			kernel_neon_end();
+			dst += count;
+			src += count;
+			nbytes -= count;
+		}
+
+		/* Handle any remainder with generic code */
+		while (nbytes >= sizeof(tweak)) {
+			le128_xor((le128 *)dst, (const le128 *)src, &tweak);
+			(*crypt_one)(&ctx->main_key, dst, dst);
+			le128_xor((le128 *)dst, (const le128 *)dst, &tweak);
+			gf128mul_x_ble(&tweak, &tweak);
+
+			dst += sizeof(tweak);
+			src += sizeof(tweak);
+			nbytes -= sizeof(tweak);
+		}
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+
+static int speck128_xts_encrypt(struct skcipher_request *req)
+{
+	return __speck128_xts_crypt(req, crypto_speck128_encrypt,
+				    speck128_xts_encrypt_neon);
+}
+
+static int speck128_xts_decrypt(struct skcipher_request *req)
+{
+	return __speck128_xts_crypt(req, crypto_speck128_decrypt,
+				    speck128_xts_decrypt_neon);
+}
+
+static int speck128_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			       unsigned int keylen)
+{
+	struct speck128_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = xts_verify_key(tfm, key, keylen);
+	if (err)
+		return err;
+
+	keylen /= 2;
+
+	err = crypto_speck128_setkey(&ctx->main_key, key, keylen);
+	if (err)
+		return err;
+
+	return crypto_speck128_setkey(&ctx->tweak_key, key + keylen, keylen);
+}
+
+/* Speck64 */
+
+struct speck64_xts_tfm_ctx {
+	struct speck64_tfm_ctx main_key;
+	struct speck64_tfm_ctx tweak_key;
+};
+
+asmlinkage void speck64_xts_encrypt_neon(const u32 *round_keys, int nrounds,
+					 void *dst, const void *src,
+					 unsigned int nbytes, void *tweak);
+
+asmlinkage void speck64_xts_decrypt_neon(const u32 *round_keys, int nrounds,
+					 void *dst, const void *src,
+					 unsigned int nbytes, void *tweak);
+
+typedef void (*speck64_crypt_one_t)(const struct speck64_tfm_ctx *,
+				    u8 *, const u8 *);
+typedef void (*speck64_xts_crypt_many_t)(const u32 *, int, void *,
+					 const void *, unsigned int, void *);
+
+static __always_inline int
+__speck64_xts_crypt(struct skcipher_request *req, speck64_crypt_one_t crypt_one,
+		    speck64_xts_crypt_many_t crypt_many)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct speck64_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	__le64 tweak;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	crypto_speck64_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+		u8 *dst = walk.dst.virt.addr;
+		const u8 *src = walk.src.virt.addr;
+
+		if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
+			unsigned int count;
+
+			count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
+			kernel_neon_begin();
+			(*crypt_many)(ctx->main_key.round_keys,
+				      ctx->main_key.nrounds,
+				      dst, src, count, &tweak);
+			kernel_neon_end();
+			dst += count;
+			src += count;
+			nbytes -= count;
+		}
+
+		/* Handle any remainder with generic code */
+		while (nbytes >= sizeof(tweak)) {
+			*(__le64 *)dst = *(__le64 *)src ^ tweak;
+			(*crypt_one)(&ctx->main_key, dst, dst);
+			*(__le64 *)dst ^= tweak;
+			tweak = cpu_to_le64((le64_to_cpu(tweak) << 1) ^
+					    ((tweak & cpu_to_le64(1ULL << 63)) ?
+					     0x1B : 0));
+			dst += sizeof(tweak);
+			src += sizeof(tweak);
+			nbytes -= sizeof(tweak);
+		}
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+
+static int speck64_xts_encrypt(struct skcipher_request *req)
+{
+	return __speck64_xts_crypt(req, crypto_speck64_encrypt,
+				   speck64_xts_encrypt_neon);
+}
+
+static int speck64_xts_decrypt(struct skcipher_request *req)
+{
+	return __speck64_xts_crypt(req, crypto_speck64_decrypt,
+				   speck64_xts_decrypt_neon);
+}
+
+static int speck64_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct speck64_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = xts_verify_key(tfm, key, keylen);
+	if (err)
+		return err;
+
+	keylen /= 2;
+
+	err = crypto_speck64_setkey(&ctx->main_key, key, keylen);
+	if (err)
+		return err;
+
+	return crypto_speck64_setkey(&ctx->tweak_key, key + keylen, keylen);
+}
+
+static struct skcipher_alg speck_algs[] = {
+	{
+		.base.cra_name		= "xts(speck128)",
+		.base.cra_driver_name	= "xts-speck128-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= SPECK128_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct speck128_xts_tfm_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * SPECK128_128_KEY_SIZE,
+		.max_keysize		= 2 * SPECK128_256_KEY_SIZE,
+		.ivsize			= SPECK128_BLOCK_SIZE,
+		.walksize		= SPECK_NEON_CHUNK_SIZE,
+		.setkey			= speck128_xts_setkey,
+		.encrypt		= speck128_xts_encrypt,
+		.decrypt		= speck128_xts_decrypt,
+	}, {
+		.base.cra_name		= "xts(speck64)",
+		.base.cra_driver_name	= "xts-speck64-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= SPECK64_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct speck64_xts_tfm_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * SPECK64_96_KEY_SIZE,
+		.max_keysize		= 2 * SPECK64_128_KEY_SIZE,
+		.ivsize			= SPECK64_BLOCK_SIZE,
+		.walksize		= SPECK_NEON_CHUNK_SIZE,
+		.setkey			= speck64_xts_setkey,
+		.encrypt		= speck64_xts_encrypt,
+		.decrypt		= speck64_xts_decrypt,
+	}
+};
+
+static int __init speck_neon_module_init(void)
+{
+	if (!(elf_hwcap & HWCAP_NEON))
+		return -ENODEV;
+	return crypto_register_skciphers(speck_algs, ARRAY_SIZE(speck_algs));
+}
+
+static void __exit speck_neon_module_exit(void)
+{
+	crypto_unregister_skciphers(speck_algs, ARRAY_SIZE(speck_algs));
+}
+
+module_init(speck_neon_module_init);
+module_exit(speck_neon_module_exit);
+
+MODULE_DESCRIPTION("Speck block cipher (NEON-accelerated)");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("xts(speck128)");
+MODULE_ALIAS_CRYPTO("xts-speck128-neon");
+MODULE_ALIAS_CRYPTO("xts(speck64)");
+MODULE_ALIAS_CRYPTO("xts-speck64-neon");
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 285c36c7b408..cb5a243110c4 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -113,4 +113,10 @@ config CRYPTO_AES_ARM64_BS
 	select CRYPTO_AES_ARM64
 	select CRYPTO_SIMD
 
+config CRYPTO_SPECK_NEON
+	tristate "NEON accelerated Speck cipher algorithms"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_SPECK
+
 endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index cee9b8d9830b..8df9f326f449 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -53,20 +53,21 @@ sha512-arm64-y := sha512-glue.o sha512-core.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha20-neon.o
 chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o
 
+obj-$(CONFIG_CRYPTO_SPECK_NEON) += speck-neon.o
+speck-neon-y := speck-neon-core.o speck-neon-glue.o
+
 obj-$(CONFIG_CRYPTO_AES_ARM64) += aes-arm64.o
 aes-arm64-y := aes-cipher-core.o aes-cipher-glue.o
 
 obj-$(CONFIG_CRYPTO_AES_ARM64_BS) += aes-neon-bs.o
 aes-neon-bs-y := aes-neonbs-core.o aes-neonbs-glue.o
 
-AFLAGS_aes-ce.o		:= -DINTERLEAVE=4
-AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
-
 CFLAGS_aes-glue-ce.o	:= -DUSE_V8_CRYPTO_EXTENSIONS
 
 $(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
+ifdef REGENERATE_ARM64_CRYPTO
 quiet_cmd_perlasm = PERLASM $@
       cmd_perlasm = $(PERL) $(<) void $(@)
 
@@ -75,5 +76,6 @@ $(src)/sha256-core.S_shipped: $(src)/sha512-armv8.pl
 
 $(src)/sha512-core.S_shipped: $(src)/sha512-armv8.pl
 	$(call cmd,perlasm)
+endif
 
 .PRECIOUS: $(obj)/sha256-core.S $(obj)/sha512-core.S
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index a1254036f2b1..68b11aa690e4 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -107,11 +107,13 @@ 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, bool use_neon)
+			   u32 abytes, u32 *macp)
 {
-	if (likely(use_neon)) {
+	if (may_use_simd()) {
+		kernel_neon_begin();
 		ce_aes_ccm_auth_data(mac, in, abytes, macp, key->key_enc,
 				     num_rounds(key));
+		kernel_neon_end();
 	} else {
 		if (*macp > 0 && *macp < AES_BLOCK_SIZE) {
 			int added = min(abytes, AES_BLOCK_SIZE - *macp);
@@ -143,8 +145,7 @@ static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[],
 	}
 }
 
-static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[],
-				   bool use_neon)
+static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
@@ -163,7 +164,7 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[],
 		ltag.len = 6;
 	}
 
-	ccm_update_mac(ctx, mac, (u8 *)&ltag, ltag.len, &macp, use_neon);
+	ccm_update_mac(ctx, mac, (u8 *)&ltag, ltag.len, &macp);
 	scatterwalk_start(&walk, req->src);
 
 	do {
@@ -175,7 +176,7 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[],
 			n = scatterwalk_clamp(&walk, len);
 		}
 		p = scatterwalk_map(&walk);
-		ccm_update_mac(ctx, mac, p, n, &macp, use_neon);
+		ccm_update_mac(ctx, mac, p, n, &macp);
 		len -= n;
 
 		scatterwalk_unmap(p);
@@ -242,43 +243,42 @@ static int ccm_encrypt(struct aead_request *req)
 	u8 __aligned(8) mac[AES_BLOCK_SIZE];
 	u8 buf[AES_BLOCK_SIZE];
 	u32 len = req->cryptlen;
-	bool use_neon = may_use_simd();
 	int err;
 
 	err = ccm_init_mac(req, mac, len);
 	if (err)
 		return err;
 
-	if (likely(use_neon))
-		kernel_neon_begin();
-
 	if (req->assoclen)
-		ccm_calculate_auth_mac(req, mac, use_neon);
+		ccm_calculate_auth_mac(req, mac);
 
 	/* preserve the original iv for the final round */
 	memcpy(buf, req->iv, AES_BLOCK_SIZE);
 
 	err = skcipher_walk_aead_encrypt(&walk, req, true);
 
-	if (likely(use_neon)) {
+	if (may_use_simd()) {
 		while (walk.nbytes) {
 			u32 tail = walk.nbytes % AES_BLOCK_SIZE;
 
 			if (walk.nbytes == walk.total)
 				tail = 0;
 
+			kernel_neon_begin();
 			ce_aes_ccm_encrypt(walk.dst.virt.addr,
 					   walk.src.virt.addr,
 					   walk.nbytes - tail, ctx->key_enc,
 					   num_rounds(ctx), mac, walk.iv);
+			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk, tail);
 		}
-		if (!err)
+		if (!err) {
+			kernel_neon_begin();
 			ce_aes_ccm_final(mac, buf, ctx->key_enc,
 					 num_rounds(ctx));
-
-		kernel_neon_end();
+			kernel_neon_end();
+		}
 	} else {
 		err = ccm_crypt_fallback(&walk, mac, buf, ctx, true);
 	}
@@ -301,43 +301,42 @@ static int ccm_decrypt(struct aead_request *req)
 	u8 __aligned(8) mac[AES_BLOCK_SIZE];
 	u8 buf[AES_BLOCK_SIZE];
 	u32 len = req->cryptlen - authsize;
-	bool use_neon = may_use_simd();
 	int err;
 
 	err = ccm_init_mac(req, mac, len);
 	if (err)
 		return err;
 
-	if (likely(use_neon))
-		kernel_neon_begin();
-
 	if (req->assoclen)
-		ccm_calculate_auth_mac(req, mac, use_neon);
+		ccm_calculate_auth_mac(req, mac);
 
 	/* preserve the original iv for the final round */
 	memcpy(buf, req->iv, AES_BLOCK_SIZE);
 
 	err = skcipher_walk_aead_decrypt(&walk, req, true);
 
-	if (likely(use_neon)) {
+	if (may_use_simd()) {
 		while (walk.nbytes) {
 			u32 tail = walk.nbytes % AES_BLOCK_SIZE;
 
 			if (walk.nbytes == walk.total)
 				tail = 0;
 
+			kernel_neon_begin();
 			ce_aes_ccm_decrypt(walk.dst.virt.addr,
 					   walk.src.virt.addr,
 					   walk.nbytes - tail, ctx->key_enc,
 					   num_rounds(ctx), mac, walk.iv);
+			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk, tail);
 		}
-		if (!err)
+		if (!err) {
+			kernel_neon_begin();
 			ce_aes_ccm_final(mac, buf, ctx->key_enc,
 					 num_rounds(ctx));
-
-		kernel_neon_end();
+			kernel_neon_end();
+		}
 	} else {
 		err = ccm_crypt_fallback(&walk, mac, buf, ctx, false);
 	}
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 2fa850e86aa8..253188fb8cb0 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -64,17 +64,17 @@ MODULE_LICENSE("GPL v2");
 
 /* defined in aes-modes.S */
 asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
-				int rounds, int blocks, int first);
+				int rounds, int blocks);
 asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
-				int rounds, int blocks, int first);
+				int rounds, int blocks);
 
 asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[],
-				int rounds, int blocks, u8 iv[], int first);
+				int rounds, int blocks, u8 iv[]);
 asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
-				int rounds, int blocks, u8 iv[], int first);
+				int rounds, int blocks, u8 iv[]);
 
 asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
-				int rounds, int blocks, u8 ctr[], int first);
+				int rounds, int blocks, u8 ctr[]);
 
 asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[],
 				int rounds, int blocks, u8 const rk2[], u8 iv[],
@@ -133,19 +133,19 @@ static int ecb_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err, first, rounds = 6 + ctx->key_length / 4;
+	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				(u8 *)ctx->key_enc, rounds, blocks, first);
+				(u8 *)ctx->key_enc, rounds, blocks);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -153,19 +153,19 @@ static int ecb_decrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err, first, rounds = 6 + ctx->key_length / 4;
+	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				(u8 *)ctx->key_dec, rounds, blocks, first);
+				(u8 *)ctx->key_dec, rounds, blocks);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -173,20 +173,19 @@ static int cbc_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err, first, rounds = 6 + ctx->key_length / 4;
+	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
-				first);
+				(u8 *)ctx->key_enc, rounds, blocks, walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -194,20 +193,19 @@ static int cbc_decrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err, first, rounds = 6 + ctx->key_length / 4;
+	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				(u8 *)ctx->key_dec, rounds, blocks, walk.iv,
-				first);
+				(u8 *)ctx->key_dec, rounds, blocks, walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -215,20 +213,18 @@ static int ctr_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err, first, rounds = 6 + ctx->key_length / 4;
+	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
 	int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	first = 1;
-	kernel_neon_begin();
 	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
-				first);
+				(u8 *)ctx->key_enc, rounds, blocks, walk.iv);
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
-		first = 0;
+		kernel_neon_end();
 	}
 	if (walk.nbytes) {
 		u8 __aligned(8) tail[AES_BLOCK_SIZE];
@@ -241,12 +237,13 @@ static int ctr_encrypt(struct skcipher_request *req)
 		 */
 		blocks = -1;
 
+		kernel_neon_begin();
 		aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc, rounds,
-				blocks, walk.iv, first);
+				blocks, walk.iv);
+		kernel_neon_end();
 		crypto_xor_cpy(tdst, tsrc, tail, nbytes);
 		err = skcipher_walk_done(&walk, 0);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -270,16 +267,16 @@ static int xts_encrypt(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		kernel_neon_begin();
 		aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key1.key_enc, rounds, blocks,
 				(u8 *)ctx->key2.key_enc, walk.iv, first);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -292,16 +289,16 @@ static int xts_decrypt(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		kernel_neon_begin();
 		aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key1.key_dec, rounds, blocks,
 				(u8 *)ctx->key2.key_enc, walk.iv, first);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -425,7 +422,7 @@ static int cmac_setkey(struct crypto_shash *tfm, const u8 *in_key,
 
 	/* encrypt the zero vector */
 	kernel_neon_begin();
-	aes_ecb_encrypt(ctx->consts, (u8[AES_BLOCK_SIZE]){}, rk, rounds, 1, 1);
+	aes_ecb_encrypt(ctx->consts, (u8[AES_BLOCK_SIZE]){}, rk, rounds, 1);
 	kernel_neon_end();
 
 	cmac_gf128_mul_by_x(consts, consts);
@@ -454,8 +451,8 @@ static int xcbc_setkey(struct crypto_shash *tfm, const u8 *in_key,
 		return err;
 
 	kernel_neon_begin();
-	aes_ecb_encrypt(key, ks[0], rk, rounds, 1, 1);
-	aes_ecb_encrypt(ctx->consts, ks[1], rk, rounds, 2, 0);
+	aes_ecb_encrypt(key, ks[0], rk, rounds, 1);
+	aes_ecb_encrypt(ctx->consts, ks[1], rk, rounds, 2);
 	kernel_neon_end();
 
 	return cbcmac_setkey(tfm, key, sizeof(key));
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index 2674d43d1384..a68412e1e3a4 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -13,127 +13,39 @@
 	.text
 	.align		4
 
-/*
- * There are several ways to instantiate this code:
- * - no interleave, all inline
- * - 2-way interleave, 2x calls out of line (-DINTERLEAVE=2)
- * - 2-way interleave, all inline (-DINTERLEAVE=2 -DINTERLEAVE_INLINE)
- * - 4-way interleave, 4x calls out of line (-DINTERLEAVE=4)
- * - 4-way interleave, all inline (-DINTERLEAVE=4 -DINTERLEAVE_INLINE)
- *
- * Macros imported by this code:
- * - enc_prepare	- setup NEON registers for encryption
- * - dec_prepare	- setup NEON registers for decryption
- * - enc_switch_key	- change to new key after having prepared for encryption
- * - encrypt_block	- encrypt a single block
- * - decrypt block	- decrypt a single block
- * - encrypt_block2x	- encrypt 2 blocks in parallel (if INTERLEAVE == 2)
- * - decrypt_block2x	- decrypt 2 blocks in parallel (if INTERLEAVE == 2)
- * - encrypt_block4x	- encrypt 4 blocks in parallel (if INTERLEAVE == 4)
- * - decrypt_block4x	- decrypt 4 blocks in parallel (if INTERLEAVE == 4)
- */
-
-#if defined(INTERLEAVE) && !defined(INTERLEAVE_INLINE)
-#define FRAME_PUSH	stp x29, x30, [sp,#-16]! ; mov x29, sp
-#define FRAME_POP	ldp x29, x30, [sp],#16
-
-#if INTERLEAVE == 2
-
-aes_encrypt_block2x:
-	encrypt_block2x	v0, v1, w3, x2, x6, w7
-	ret
-ENDPROC(aes_encrypt_block2x)
-
-aes_decrypt_block2x:
-	decrypt_block2x	v0, v1, w3, x2, x6, w7
-	ret
-ENDPROC(aes_decrypt_block2x)
-
-#elif INTERLEAVE == 4
-
 aes_encrypt_block4x:
-	encrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	encrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
 	ret
 ENDPROC(aes_encrypt_block4x)
 
 aes_decrypt_block4x:
-	decrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	decrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
 	ret
 ENDPROC(aes_decrypt_block4x)
 
-#else
-#error INTERLEAVE should equal 2 or 4
-#endif
-
-	.macro		do_encrypt_block2x
-	bl		aes_encrypt_block2x
-	.endm
-
-	.macro		do_decrypt_block2x
-	bl		aes_decrypt_block2x
-	.endm
-
-	.macro		do_encrypt_block4x
-	bl		aes_encrypt_block4x
-	.endm
-
-	.macro		do_decrypt_block4x
-	bl		aes_decrypt_block4x
-	.endm
-
-#else
-#define FRAME_PUSH
-#define FRAME_POP
-
-	.macro		do_encrypt_block2x
-	encrypt_block2x	v0, v1, w3, x2, x6, w7
-	.endm
-
-	.macro		do_decrypt_block2x
-	decrypt_block2x	v0, v1, w3, x2, x6, w7
-	.endm
-
-	.macro		do_encrypt_block4x
-	encrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
-	.endm
-
-	.macro		do_decrypt_block4x
-	decrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
-	.endm
-
-#endif
-
 	/*
 	 * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
-	 *		   int blocks, int first)
+	 *		   int blocks)
 	 * aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
-	 *		   int blocks, int first)
+	 *		   int blocks)
 	 */
 
 AES_ENTRY(aes_ecb_encrypt)
-	FRAME_PUSH
-	cbz		w5, .LecbencloopNx
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
 
 	enc_prepare	w3, x2, x5
 
 .LecbencloopNx:
-#if INTERLEAVE >= 2
-	subs		w4, w4, #INTERLEAVE
+	subs		w4, w4, #4
 	bmi		.Lecbenc1x
-#if INTERLEAVE == 2
-	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 pt blocks */
-	do_encrypt_block2x
-	st1		{v0.16b-v1.16b}, [x0], #32
-#else
 	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
-	do_encrypt_block4x
+	bl		aes_encrypt_block4x
 	st1		{v0.16b-v3.16b}, [x0], #64
-#endif
 	b		.LecbencloopNx
 .Lecbenc1x:
-	adds		w4, w4, #INTERLEAVE
+	adds		w4, w4, #4
 	beq		.Lecbencout
-#endif
 .Lecbencloop:
 	ld1		{v0.16b}, [x1], #16		/* get next pt block */
 	encrypt_block	v0, w3, x2, x5, w6
@@ -141,35 +53,27 @@ AES_ENTRY(aes_ecb_encrypt)
 	subs		w4, w4, #1
 	bne		.Lecbencloop
 .Lecbencout:
-	FRAME_POP
+	ldp		x29, x30, [sp], #16
 	ret
 AES_ENDPROC(aes_ecb_encrypt)
 
 
 AES_ENTRY(aes_ecb_decrypt)
-	FRAME_PUSH
-	cbz		w5, .LecbdecloopNx
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
 
 	dec_prepare	w3, x2, x5
 
 .LecbdecloopNx:
-#if INTERLEAVE >= 2
-	subs		w4, w4, #INTERLEAVE
+	subs		w4, w4, #4
 	bmi		.Lecbdec1x
-#if INTERLEAVE == 2
-	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
-	do_decrypt_block2x
-	st1		{v0.16b-v1.16b}, [x0], #32
-#else
 	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
-	do_decrypt_block4x
+	bl		aes_decrypt_block4x
 	st1		{v0.16b-v3.16b}, [x0], #64
-#endif
 	b		.LecbdecloopNx
 .Lecbdec1x:
-	adds		w4, w4, #INTERLEAVE
+	adds		w4, w4, #4
 	beq		.Lecbdecout
-#endif
 .Lecbdecloop:
 	ld1		{v0.16b}, [x1], #16		/* get next ct block */
 	decrypt_block	v0, w3, x2, x5, w6
@@ -177,62 +81,68 @@ AES_ENTRY(aes_ecb_decrypt)
 	subs		w4, w4, #1
 	bne		.Lecbdecloop
 .Lecbdecout:
-	FRAME_POP
+	ldp		x29, x30, [sp], #16
 	ret
 AES_ENDPROC(aes_ecb_decrypt)
 
 
 	/*
 	 * aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
-	 *		   int blocks, u8 iv[], int first)
+	 *		   int blocks, u8 iv[])
 	 * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
-	 *		   int blocks, u8 iv[], int first)
+	 *		   int blocks, u8 iv[])
 	 */
 
 AES_ENTRY(aes_cbc_encrypt)
-	cbz		w6, .Lcbcencloop
-
-	ld1		{v0.16b}, [x5]			/* get iv */
+	ld1		{v4.16b}, [x5]			/* get iv */
 	enc_prepare	w3, x2, x6
 
-.Lcbcencloop:
-	ld1		{v1.16b}, [x1], #16		/* get next pt block */
-	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with iv */
+.Lcbcencloop4x:
+	subs		w4, w4, #4
+	bmi		.Lcbcenc1x
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	eor		v0.16b, v0.16b, v4.16b		/* ..and xor with iv */
 	encrypt_block	v0, w3, x2, x6, w7
-	st1		{v0.16b}, [x0], #16
+	eor		v1.16b, v1.16b, v0.16b
+	encrypt_block	v1, w3, x2, x6, w7
+	eor		v2.16b, v2.16b, v1.16b
+	encrypt_block	v2, w3, x2, x6, w7
+	eor		v3.16b, v3.16b, v2.16b
+	encrypt_block	v3, w3, x2, x6, w7
+	st1		{v0.16b-v3.16b}, [x0], #64
+	mov		v4.16b, v3.16b
+	b		.Lcbcencloop4x
+.Lcbcenc1x:
+	adds		w4, w4, #4
+	beq		.Lcbcencout
+.Lcbcencloop:
+	ld1		{v0.16b}, [x1], #16		/* get next pt block */
+	eor		v4.16b, v4.16b, v0.16b		/* ..and xor with iv */
+	encrypt_block	v4, w3, x2, x6, w7
+	st1		{v4.16b}, [x0], #16
 	subs		w4, w4, #1
 	bne		.Lcbcencloop
-	st1		{v0.16b}, [x5]			/* return iv */
+.Lcbcencout:
+	st1		{v4.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_encrypt)
 
 
 AES_ENTRY(aes_cbc_decrypt)
-	FRAME_PUSH
-	cbz		w6, .LcbcdecloopNx
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
 
 	ld1		{v7.16b}, [x5]			/* get iv */
 	dec_prepare	w3, x2, x6
 
 .LcbcdecloopNx:
-#if INTERLEAVE >= 2
-	subs		w4, w4, #INTERLEAVE
+	subs		w4, w4, #4
 	bmi		.Lcbcdec1x
-#if INTERLEAVE == 2
-	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
-	mov		v2.16b, v0.16b
-	mov		v3.16b, v1.16b
-	do_decrypt_block2x
-	eor		v0.16b, v0.16b, v7.16b
-	eor		v1.16b, v1.16b, v2.16b
-	mov		v7.16b, v3.16b
-	st1		{v0.16b-v1.16b}, [x0], #32
-#else
 	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
 	mov		v4.16b, v0.16b
 	mov		v5.16b, v1.16b
 	mov		v6.16b, v2.16b
-	do_decrypt_block4x
+	bl		aes_decrypt_block4x
 	sub		x1, x1, #16
 	eor		v0.16b, v0.16b, v7.16b
 	eor		v1.16b, v1.16b, v4.16b
@@ -240,12 +150,10 @@ AES_ENTRY(aes_cbc_decrypt)
 	eor		v2.16b, v2.16b, v5.16b
 	eor		v3.16b, v3.16b, v6.16b
 	st1		{v0.16b-v3.16b}, [x0], #64
-#endif
 	b		.LcbcdecloopNx
 .Lcbcdec1x:
-	adds		w4, w4, #INTERLEAVE
+	adds		w4, w4, #4
 	beq		.Lcbcdecout
-#endif
 .Lcbcdecloop:
 	ld1		{v1.16b}, [x1], #16		/* get next ct block */
 	mov		v0.16b, v1.16b			/* ...and copy to v0 */
@@ -256,49 +164,33 @@ AES_ENTRY(aes_cbc_decrypt)
 	subs		w4, w4, #1
 	bne		.Lcbcdecloop
 .Lcbcdecout:
-	FRAME_POP
 	st1		{v7.16b}, [x5]			/* return iv */
+	ldp		x29, x30, [sp], #16
 	ret
 AES_ENDPROC(aes_cbc_decrypt)
 
 
 	/*
 	 * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
-	 *		   int blocks, u8 ctr[], int first)
+	 *		   int blocks, u8 ctr[])
 	 */
 
 AES_ENTRY(aes_ctr_encrypt)
-	FRAME_PUSH
-	cbz		w6, .Lctrnotfirst	/* 1st time around? */
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
 	enc_prepare	w3, x2, x6
 	ld1		{v4.16b}, [x5]
 
-.Lctrnotfirst:
-	umov		x8, v4.d[1]		/* keep swabbed ctr in reg */
-	rev		x8, x8
-#if INTERLEAVE >= 2
-	cmn		w8, w4			/* 32 bit overflow? */
+	umov		x6, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x6, x6
+	cmn		w6, w4			/* 32 bit overflow? */
 	bcs		.Lctrloop
 .LctrloopNx:
-	subs		w4, w4, #INTERLEAVE
+	subs		w4, w4, #4
 	bmi		.Lctr1x
-#if INTERLEAVE == 2
-	mov		v0.8b, v4.8b
-	mov		v1.8b, v4.8b
-	rev		x7, x8
-	add		x8, x8, #1
-	ins		v0.d[1], x7
-	rev		x7, x8
-	add		x8, x8, #1
-	ins		v1.d[1], x7
-	ld1		{v2.16b-v3.16b}, [x1], #32	/* get 2 input blocks */
-	do_encrypt_block2x
-	eor		v0.16b, v0.16b, v2.16b
-	eor		v1.16b, v1.16b, v3.16b
-	st1		{v0.16b-v1.16b}, [x0], #32
-#else
 	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
-	dup		v7.4s, w8
+	dup		v7.4s, w6
 	mov		v0.16b, v4.16b
 	add		v7.4s, v7.4s, v8.4s
 	mov		v1.16b, v4.16b
@@ -309,29 +201,27 @@ AES_ENTRY(aes_ctr_encrypt)
 	mov		v2.s[3], v8.s[1]
 	mov		v3.s[3], v8.s[2]
 	ld1		{v5.16b-v7.16b}, [x1], #48	/* get 3 input blocks */
-	do_encrypt_block4x
+	bl		aes_encrypt_block4x
 	eor		v0.16b, v5.16b, v0.16b
 	ld1		{v5.16b}, [x1], #16		/* get 1 input block  */
 	eor		v1.16b, v6.16b, v1.16b
 	eor		v2.16b, v7.16b, v2.16b
 	eor		v3.16b, v5.16b, v3.16b
 	st1		{v0.16b-v3.16b}, [x0], #64
-	add		x8, x8, #INTERLEAVE
-#endif
-	rev		x7, x8
+	add		x6, x6, #4
+	rev		x7, x6
 	ins		v4.d[1], x7
 	cbz		w4, .Lctrout
 	b		.LctrloopNx
 .Lctr1x:
-	adds		w4, w4, #INTERLEAVE
+	adds		w4, w4, #4
 	beq		.Lctrout
-#endif
 .Lctrloop:
 	mov		v0.16b, v4.16b
-	encrypt_block	v0, w3, x2, x6, w7
+	encrypt_block	v0, w3, x2, x8, w7
 
-	adds		x8, x8, #1		/* increment BE ctr */
-	rev		x7, x8
+	adds		x6, x6, #1		/* increment BE ctr */
+	rev		x7, x6
 	ins		v4.d[1], x7
 	bcs		.Lctrcarry		/* overflow? */
 
@@ -345,12 +235,12 @@ AES_ENTRY(aes_ctr_encrypt)
 
 .Lctrout:
 	st1		{v4.16b}, [x5]		/* return next CTR value */
-	FRAME_POP
+	ldp		x29, x30, [sp], #16
 	ret
 
 .Lctrtailblock:
 	st1		{v0.16b}, [x0]
-	FRAME_POP
+	ldp		x29, x30, [sp], #16
 	ret
 
 .Lctrcarry:
@@ -384,39 +274,26 @@ CPU_LE(	.quad		1, 0x87		)
 CPU_BE(	.quad		0x87, 1		)
 
 AES_ENTRY(aes_xts_encrypt)
-	FRAME_PUSH
-	cbz		w7, .LxtsencloopNx
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
 
 	ld1		{v4.16b}, [x6]
-	enc_prepare	w3, x5, x6
-	encrypt_block	v4, w3, x5, x6, w7		/* first tweak */
-	enc_switch_key	w3, x2, x6
+	cbz		w7, .Lxtsencnotfirst
+
+	enc_prepare	w3, x5, x8
+	encrypt_block	v4, w3, x5, x8, w7		/* first tweak */
+	enc_switch_key	w3, x2, x8
 	ldr		q7, .Lxts_mul_x
 	b		.LxtsencNx
 
+.Lxtsencnotfirst:
+	enc_prepare	w3, x2, x8
 .LxtsencloopNx:
 	ldr		q7, .Lxts_mul_x
 	next_tweak	v4, v4, v7, v8
 .LxtsencNx:
-#if INTERLEAVE >= 2
-	subs		w4, w4, #INTERLEAVE
+	subs		w4, w4, #4
 	bmi		.Lxtsenc1x
-#if INTERLEAVE == 2
-	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 pt blocks */
-	next_tweak	v5, v4, v7, v8
-	eor		v0.16b, v0.16b, v4.16b
-	eor		v1.16b, v1.16b, v5.16b
-	do_encrypt_block2x
-	eor		v0.16b, v0.16b, v4.16b
-	eor		v1.16b, v1.16b, v5.16b
-	st1		{v0.16b-v1.16b}, [x0], #32
-	cbz		w4, .LxtsencoutNx
-	next_tweak	v4, v5, v7, v8
-	b		.LxtsencNx
-.LxtsencoutNx:
-	mov		v4.16b, v5.16b
-	b		.Lxtsencout
-#else
 	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
 	next_tweak	v5, v4, v7, v8
 	eor		v0.16b, v0.16b, v4.16b
@@ -425,7 +302,7 @@ AES_ENTRY(aes_xts_encrypt)
 	eor		v2.16b, v2.16b, v6.16b
 	next_tweak	v7, v6, v7, v8
 	eor		v3.16b, v3.16b, v7.16b
-	do_encrypt_block4x
+	bl		aes_encrypt_block4x
 	eor		v3.16b, v3.16b, v7.16b
 	eor		v0.16b, v0.16b, v4.16b
 	eor		v1.16b, v1.16b, v5.16b
@@ -434,15 +311,13 @@ AES_ENTRY(aes_xts_encrypt)
 	mov		v4.16b, v7.16b
 	cbz		w4, .Lxtsencout
 	b		.LxtsencloopNx
-#endif
 .Lxtsenc1x:
-	adds		w4, w4, #INTERLEAVE
+	adds		w4, w4, #4
 	beq		.Lxtsencout
-#endif
 .Lxtsencloop:
 	ld1		{v1.16b}, [x1], #16
 	eor		v0.16b, v1.16b, v4.16b
-	encrypt_block	v0, w3, x2, x6, w7
+	encrypt_block	v0, w3, x2, x8, w7
 	eor		v0.16b, v0.16b, v4.16b
 	st1		{v0.16b}, [x0], #16
 	subs		w4, w4, #1
@@ -450,45 +325,33 @@ AES_ENTRY(aes_xts_encrypt)
 	next_tweak	v4, v4, v7, v8
 	b		.Lxtsencloop
 .Lxtsencout:
-	FRAME_POP
+	st1		{v4.16b}, [x6]
+	ldp		x29, x30, [sp], #16
 	ret
 AES_ENDPROC(aes_xts_encrypt)
 
 
 AES_ENTRY(aes_xts_decrypt)
-	FRAME_PUSH
-	cbz		w7, .LxtsdecloopNx
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
 
 	ld1		{v4.16b}, [x6]
-	enc_prepare	w3, x5, x6
-	encrypt_block	v4, w3, x5, x6, w7		/* first tweak */
-	dec_prepare	w3, x2, x6
+	cbz		w7, .Lxtsdecnotfirst
+
+	enc_prepare	w3, x5, x8
+	encrypt_block	v4, w3, x5, x8, w7		/* first tweak */
+	dec_prepare	w3, x2, x8
 	ldr		q7, .Lxts_mul_x
 	b		.LxtsdecNx
 
+.Lxtsdecnotfirst:
+	dec_prepare	w3, x2, x8
 .LxtsdecloopNx:
 	ldr		q7, .Lxts_mul_x
 	next_tweak	v4, v4, v7, v8
 .LxtsdecNx:
-#if INTERLEAVE >= 2
-	subs		w4, w4, #INTERLEAVE
+	subs		w4, w4, #4
 	bmi		.Lxtsdec1x
-#if INTERLEAVE == 2
-	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
-	next_tweak	v5, v4, v7, v8
-	eor		v0.16b, v0.16b, v4.16b
-	eor		v1.16b, v1.16b, v5.16b
-	do_decrypt_block2x
-	eor		v0.16b, v0.16b, v4.16b
-	eor		v1.16b, v1.16b, v5.16b
-	st1		{v0.16b-v1.16b}, [x0], #32
-	cbz		w4, .LxtsdecoutNx
-	next_tweak	v4, v5, v7, v8
-	b		.LxtsdecNx
-.LxtsdecoutNx:
-	mov		v4.16b, v5.16b
-	b		.Lxtsdecout
-#else
 	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
 	next_tweak	v5, v4, v7, v8
 	eor		v0.16b, v0.16b, v4.16b
@@ -497,7 +360,7 @@ AES_ENTRY(aes_xts_decrypt)
 	eor		v2.16b, v2.16b, v6.16b
 	next_tweak	v7, v6, v7, v8
 	eor		v3.16b, v3.16b, v7.16b
-	do_decrypt_block4x
+	bl		aes_decrypt_block4x
 	eor		v3.16b, v3.16b, v7.16b
 	eor		v0.16b, v0.16b, v4.16b
 	eor		v1.16b, v1.16b, v5.16b
@@ -506,15 +369,13 @@ AES_ENTRY(aes_xts_decrypt)
 	mov		v4.16b, v7.16b
 	cbz		w4, .Lxtsdecout
 	b		.LxtsdecloopNx
-#endif
 .Lxtsdec1x:
-	adds		w4, w4, #INTERLEAVE
+	adds		w4, w4, #4
 	beq		.Lxtsdecout
-#endif
 .Lxtsdecloop:
 	ld1		{v1.16b}, [x1], #16
 	eor		v0.16b, v1.16b, v4.16b
-	decrypt_block	v0, w3, x2, x6, w7
+	decrypt_block	v0, w3, x2, x8, w7
 	eor		v0.16b, v0.16b, v4.16b
 	st1		{v0.16b}, [x0], #16
 	subs		w4, w4, #1
@@ -522,7 +383,8 @@ AES_ENTRY(aes_xts_decrypt)
 	next_tweak	v4, v4, v7, v8
 	b		.Lxtsdecloop
 .Lxtsdecout:
-	FRAME_POP
+	st1		{v4.16b}, [x6]
+	ldp		x29, x30, [sp], #16
 	ret
 AES_ENDPROC(aes_xts_decrypt)
 
@@ -533,8 +395,28 @@ AES_ENDPROC(aes_xts_decrypt)
 AES_ENTRY(aes_mac_update)
 	ld1		{v0.16b}, [x4]			/* get dg */
 	enc_prepare	w2, x1, x7
-	cbnz		w5, .Lmacenc
+	cbz		w5, .Lmacloop4x
+
+	encrypt_block	v0, w2, x1, x7, w8
 
+.Lmacloop4x:
+	subs		w3, w3, #4
+	bmi		.Lmac1x
+	ld1		{v1.16b-v4.16b}, [x0], #64	/* get next pt block */
+	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with dg */
+	encrypt_block	v0, w2, x1, x7, w8
+	eor		v0.16b, v0.16b, v2.16b
+	encrypt_block	v0, w2, x1, x7, w8
+	eor		v0.16b, v0.16b, v3.16b
+	encrypt_block	v0, w2, x1, x7, w8
+	eor		v0.16b, v0.16b, v4.16b
+	cmp		w3, wzr
+	csinv		x5, x6, xzr, eq
+	cbz		w5, .Lmacout
+	encrypt_block	v0, w2, x1, x7, w8
+	b		.Lmacloop4x
+.Lmac1x:
+	add		w3, w3, #4
 .Lmacloop:
 	cbz		w3, .Lmacout
 	ld1		{v1.16b}, [x0], #16		/* get next pt block */
@@ -544,7 +426,6 @@ AES_ENTRY(aes_mac_update)
 	csinv		x5, x6, xzr, eq
 	cbz		w5, .Lmacout
 
-.Lmacenc:
 	encrypt_block	v0, w2, x1, x7, w8
 	b		.Lmacloop
 
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index c55d68ccb89f..e7a95a566462 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -46,10 +46,9 @@ asmlinkage void aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[],
 
 /* borrowed from aes-neon-blk.ko */
 asmlinkage void neon_aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[],
-				     int rounds, int blocks, int first);
+				     int rounds, int blocks);
 asmlinkage void neon_aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[],
-				     int rounds, int blocks, u8 iv[],
-				     int first);
+				     int rounds, int blocks, u8 iv[]);
 
 struct aesbs_ctx {
 	u8	rk[13 * (8 * AES_BLOCK_SIZE) + 32];
@@ -100,9 +99,8 @@ static int __ecb_crypt(struct skcipher_request *req,
 	struct skcipher_walk walk;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
@@ -110,12 +108,13 @@ static int __ecb_crypt(struct skcipher_request *req,
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
 
+		kernel_neon_begin();
 		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk,
 		   ctx->rounds, blocks);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -157,22 +156,21 @@ static int cbc_encrypt(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct skcipher_walk walk;
-	int err, first = 1;
+	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
 		/* fall back to the non-bitsliced NEON implementation */
+		kernel_neon_begin();
 		neon_aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				     ctx->enc, ctx->key.rounds, blocks, walk.iv,
-				     first);
+				     ctx->enc, ctx->key.rounds, blocks,
+				     walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
-		first = 0;
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -183,9 +181,8 @@ static int cbc_decrypt(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
@@ -193,13 +190,14 @@ static int cbc_decrypt(struct skcipher_request *req)
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
 
+		kernel_neon_begin();
 		aesbs_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				  ctx->key.rk, ctx->key.rounds, blocks,
 				  walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -231,9 +229,8 @@ static int ctr_encrypt(struct skcipher_request *req)
 	u8 buf[AES_BLOCK_SIZE];
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	while (walk.nbytes > 0) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 		u8 *final = (walk.total % AES_BLOCK_SIZE) ? buf : NULL;
@@ -244,8 +241,10 @@ static int ctr_encrypt(struct skcipher_request *req)
 			final = NULL;
 		}
 
+		kernel_neon_begin();
 		aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				  ctx->rk, ctx->rounds, blocks, walk.iv, final);
+		kernel_neon_end();
 
 		if (final) {
 			u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
@@ -260,8 +259,6 @@ static int ctr_encrypt(struct skcipher_request *req)
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
-
 	return err;
 }
 
@@ -306,12 +303,11 @@ static int __xts_crypt(struct skcipher_request *req,
 	struct skcipher_walk walk;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	kernel_neon_begin();
-
-	neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey,
-			     ctx->key.rounds, 1, 1);
+	neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey, ctx->key.rounds, 1);
+	kernel_neon_end();
 
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -320,13 +316,13 @@ static int __xts_crypt(struct skcipher_request *req,
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
 
+		kernel_neon_begin();
 		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->key.rk,
 		   ctx->key.rounds, blocks, walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
-
 	return err;
 }
 
diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c
index cbdb75d15cd0..727579c93ded 100644
--- a/arch/arm64/crypto/chacha20-neon-glue.c
+++ b/arch/arm64/crypto/chacha20-neon-glue.c
@@ -37,12 +37,19 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src,
 	u8 buf[CHACHA20_BLOCK_SIZE];
 
 	while (bytes >= CHACHA20_BLOCK_SIZE * 4) {
+		kernel_neon_begin();
 		chacha20_4block_xor_neon(state, dst, src);
+		kernel_neon_end();
 		bytes -= CHACHA20_BLOCK_SIZE * 4;
 		src += CHACHA20_BLOCK_SIZE * 4;
 		dst += CHACHA20_BLOCK_SIZE * 4;
 		state[12] += 4;
 	}
+
+	if (!bytes)
+		return;
+
+	kernel_neon_begin();
 	while (bytes >= CHACHA20_BLOCK_SIZE) {
 		chacha20_block_xor_neon(state, dst, src);
 		bytes -= CHACHA20_BLOCK_SIZE;
@@ -55,6 +62,7 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src,
 		chacha20_block_xor_neon(state, buf, buf);
 		memcpy(dst, buf, bytes);
 	}
+	kernel_neon_end();
 }
 
 static int chacha20_neon(struct skcipher_request *req)
@@ -68,11 +76,10 @@ static int chacha20_neon(struct skcipher_request *req)
 	if (!may_use_simd() || req->cryptlen <= CHACHA20_BLOCK_SIZE)
 		return crypto_chacha20_crypt(req);
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	crypto_chacha20_init(state, ctx, walk.iv);
 
-	kernel_neon_begin();
 	while (walk.nbytes > 0) {
 		unsigned int nbytes = walk.nbytes;
 
@@ -83,7 +90,6 @@ static int chacha20_neon(struct skcipher_request *req)
 				nbytes);
 		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
-	kernel_neon_end();
 
 	return err;
 }
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index b064d925fe2a..e8880ccdc71f 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -89,21 +89,32 @@ static struct shash_alg algs[] = { {
 static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
 			      unsigned int len)
 {
-	/*
-	 * Stacking and unstacking a substantial slice of the NEON register
-	 * file may significantly affect performance for small updates when
-	 * executing in interrupt context, so fall back to the scalar code
-	 * in that case.
-	 */
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
 	if (!may_use_simd())
 		return sha256_base_do_update(desc, data, len,
 				(sha256_block_fn *)sha256_block_data_order);
 
-	kernel_neon_begin();
-	sha256_base_do_update(desc, data, len,
-				(sha256_block_fn *)sha256_block_neon);
-	kernel_neon_end();
+	while (len > 0) {
+		unsigned int chunk = len;
+
+		/*
+		 * Don't hog the CPU for the entire time it takes to process all
+		 * input when running on a preemptible kernel, but process the
+		 * data block by block instead.
+		 */
+		if (IS_ENABLED(CONFIG_PREEMPT) &&
+		    chunk + sctx->count % SHA256_BLOCK_SIZE > SHA256_BLOCK_SIZE)
+			chunk = SHA256_BLOCK_SIZE -
+				sctx->count % SHA256_BLOCK_SIZE;
 
+		kernel_neon_begin();
+		sha256_base_do_update(desc, data, chunk,
+				      (sha256_block_fn *)sha256_block_neon);
+		kernel_neon_end();
+		data += chunk;
+		len -= chunk;
+	}
 	return 0;
 }
 
@@ -117,10 +128,9 @@ static int sha256_finup_neon(struct shash_desc *desc, const u8 *data,
 		sha256_base_do_finalize(desc,
 				(sha256_block_fn *)sha256_block_data_order);
 	} else {
-		kernel_neon_begin();
 		if (len)
-			sha256_base_do_update(desc, data, len,
-				(sha256_block_fn *)sha256_block_neon);
+			sha256_update_neon(desc, data, len);
+		kernel_neon_begin();
 		sha256_base_do_finalize(desc,
 				(sha256_block_fn *)sha256_block_neon);
 		kernel_neon_end();
diff --git a/arch/arm64/crypto/speck-neon-core.S b/arch/arm64/crypto/speck-neon-core.S
new file mode 100644
index 000000000000..b14463438b09
--- /dev/null
+++ b/arch/arm64/crypto/speck-neon-core.S
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM64 NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
+ *
+ * Copyright (c) 2018 Google, Inc
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+	.text
+
+	// arguments
+	ROUND_KEYS	.req	x0	// const {u64,u32} *round_keys
+	NROUNDS		.req	w1	// int nrounds
+	NROUNDS_X	.req	x1
+	DST		.req	x2	// void *dst
+	SRC		.req	x3	// const void *src
+	NBYTES		.req	w4	// unsigned int nbytes
+	TWEAK		.req	x5	// void *tweak
+
+	// registers which hold the data being encrypted/decrypted
+	// (underscores avoid a naming collision with ARM64 registers x0-x3)
+	X_0		.req	v0
+	Y_0		.req	v1
+	X_1		.req	v2
+	Y_1		.req	v3
+	X_2		.req	v4
+	Y_2		.req	v5
+	X_3		.req	v6
+	Y_3		.req	v7
+
+	// the round key, duplicated in all lanes
+	ROUND_KEY	.req	v8
+
+	// index vector for tbl-based 8-bit rotates
+	ROTATE_TABLE	.req	v9
+	ROTATE_TABLE_Q	.req	q9
+
+	// temporary registers
+	TMP0		.req	v10
+	TMP1		.req	v11
+	TMP2		.req	v12
+	TMP3		.req	v13
+
+	// multiplication table for updating XTS tweaks
+	GFMUL_TABLE	.req	v14
+	GFMUL_TABLE_Q	.req	q14
+
+	// next XTS tweak value(s)
+	TWEAKV_NEXT	.req	v15
+
+	// XTS tweaks for the blocks currently being encrypted/decrypted
+	TWEAKV0		.req	v16
+	TWEAKV1		.req	v17
+	TWEAKV2		.req	v18
+	TWEAKV3		.req	v19
+	TWEAKV4		.req	v20
+	TWEAKV5		.req	v21
+	TWEAKV6		.req	v22
+	TWEAKV7		.req	v23
+
+	.align		4
+.Lror64_8_table:
+	.octa		0x080f0e0d0c0b0a090007060504030201
+.Lror32_8_table:
+	.octa		0x0c0f0e0d080b0a090407060500030201
+.Lrol64_8_table:
+	.octa		0x0e0d0c0b0a09080f0605040302010007
+.Lrol32_8_table:
+	.octa		0x0e0d0c0f0a09080b0605040702010003
+.Lgf128mul_table:
+	.octa		0x00000000000000870000000000000001
+.Lgf64mul_table:
+	.octa		0x0000000000000000000000002d361b00
+
+/*
+ * _speck_round_128bytes() - Speck encryption round on 128 bytes at a time
+ *
+ * Do one Speck encryption round on the 128 bytes (8 blocks for Speck128, 16 for
+ * Speck64) stored in X0-X3 and Y0-Y3, using the round key stored in all lanes
+ * of ROUND_KEY.  'n' is the lane size: 64 for Speck128, or 32 for Speck64.
+ * 'lanes' is the lane specifier: "2d" for Speck128 or "4s" for Speck64.
+ */
+.macro _speck_round_128bytes	n, lanes
+
+	// x = ror(x, 8)
+	tbl		X_0.16b, {X_0.16b}, ROTATE_TABLE.16b
+	tbl		X_1.16b, {X_1.16b}, ROTATE_TABLE.16b
+	tbl		X_2.16b, {X_2.16b}, ROTATE_TABLE.16b
+	tbl		X_3.16b, {X_3.16b}, ROTATE_TABLE.16b
+
+	// x += y
+	add		X_0.\lanes, X_0.\lanes, Y_0.\lanes
+	add		X_1.\lanes, X_1.\lanes, Y_1.\lanes
+	add		X_2.\lanes, X_2.\lanes, Y_2.\lanes
+	add		X_3.\lanes, X_3.\lanes, Y_3.\lanes
+
+	// x ^= k
+	eor		X_0.16b, X_0.16b, ROUND_KEY.16b
+	eor		X_1.16b, X_1.16b, ROUND_KEY.16b
+	eor		X_2.16b, X_2.16b, ROUND_KEY.16b
+	eor		X_3.16b, X_3.16b, ROUND_KEY.16b
+
+	// y = rol(y, 3)
+	shl		TMP0.\lanes, Y_0.\lanes, #3
+	shl		TMP1.\lanes, Y_1.\lanes, #3
+	shl		TMP2.\lanes, Y_2.\lanes, #3
+	shl		TMP3.\lanes, Y_3.\lanes, #3
+	sri		TMP0.\lanes, Y_0.\lanes, #(\n - 3)
+	sri		TMP1.\lanes, Y_1.\lanes, #(\n - 3)
+	sri		TMP2.\lanes, Y_2.\lanes, #(\n - 3)
+	sri		TMP3.\lanes, Y_3.\lanes, #(\n - 3)
+
+	// y ^= x
+	eor		Y_0.16b, TMP0.16b, X_0.16b
+	eor		Y_1.16b, TMP1.16b, X_1.16b
+	eor		Y_2.16b, TMP2.16b, X_2.16b
+	eor		Y_3.16b, TMP3.16b, X_3.16b
+.endm
+
+/*
+ * _speck_unround_128bytes() - Speck decryption round on 128 bytes at a time
+ *
+ * This is the inverse of _speck_round_128bytes().
+ */
+.macro _speck_unround_128bytes	n, lanes
+
+	// y ^= x
+	eor		TMP0.16b, Y_0.16b, X_0.16b
+	eor		TMP1.16b, Y_1.16b, X_1.16b
+	eor		TMP2.16b, Y_2.16b, X_2.16b
+	eor		TMP3.16b, Y_3.16b, X_3.16b
+
+	// y = ror(y, 3)
+	ushr		Y_0.\lanes, TMP0.\lanes, #3
+	ushr		Y_1.\lanes, TMP1.\lanes, #3
+	ushr		Y_2.\lanes, TMP2.\lanes, #3
+	ushr		Y_3.\lanes, TMP3.\lanes, #3
+	sli		Y_0.\lanes, TMP0.\lanes, #(\n - 3)
+	sli		Y_1.\lanes, TMP1.\lanes, #(\n - 3)
+	sli		Y_2.\lanes, TMP2.\lanes, #(\n - 3)
+	sli		Y_3.\lanes, TMP3.\lanes, #(\n - 3)
+
+	// x ^= k
+	eor		X_0.16b, X_0.16b, ROUND_KEY.16b
+	eor		X_1.16b, X_1.16b, ROUND_KEY.16b
+	eor		X_2.16b, X_2.16b, ROUND_KEY.16b
+	eor		X_3.16b, X_3.16b, ROUND_KEY.16b
+
+	// x -= y
+	sub		X_0.\lanes, X_0.\lanes, Y_0.\lanes
+	sub		X_1.\lanes, X_1.\lanes, Y_1.\lanes
+	sub		X_2.\lanes, X_2.\lanes, Y_2.\lanes
+	sub		X_3.\lanes, X_3.\lanes, Y_3.\lanes
+
+	// x = rol(x, 8)
+	tbl		X_0.16b, {X_0.16b}, ROTATE_TABLE.16b
+	tbl		X_1.16b, {X_1.16b}, ROTATE_TABLE.16b
+	tbl		X_2.16b, {X_2.16b}, ROTATE_TABLE.16b
+	tbl		X_3.16b, {X_3.16b}, ROTATE_TABLE.16b
+.endm
+
+.macro _next_xts_tweak	next, cur, tmp, n
+.if \n == 64
+	/*
+	 * Calculate the next tweak by multiplying the current one by x,
+	 * modulo p(x) = x^128 + x^7 + x^2 + x + 1.
+	 */
+	sshr		\tmp\().2d, \cur\().2d, #63
+	and		\tmp\().16b, \tmp\().16b, GFMUL_TABLE.16b
+	shl		\next\().2d, \cur\().2d, #1
+	ext		\tmp\().16b, \tmp\().16b, \tmp\().16b, #8
+	eor		\next\().16b, \next\().16b, \tmp\().16b
+.else
+	/*
+	 * Calculate the next two tweaks by multiplying the current ones by x^2,
+	 * modulo p(x) = x^64 + x^4 + x^3 + x + 1.
+	 */
+	ushr		\tmp\().2d, \cur\().2d, #62
+	shl		\next\().2d, \cur\().2d, #2
+	tbl		\tmp\().16b, {GFMUL_TABLE.16b}, \tmp\().16b
+	eor		\next\().16b, \next\().16b, \tmp\().16b
+.endif
+.endm
+
+/*
+ * _speck_xts_crypt() - Speck-XTS encryption/decryption
+ *
+ * Encrypt or decrypt NBYTES bytes of data from the SRC buffer to the DST buffer
+ * using Speck-XTS, specifically the variant with a block size of '2n' and round
+ * count given by NROUNDS.  The expanded round keys are given in ROUND_KEYS, and
+ * the current XTS tweak value is given in TWEAK.  It's assumed that NBYTES is a
+ * nonzero multiple of 128.
+ */
+.macro _speck_xts_crypt	n, lanes, decrypting
+
+	/*
+	 * If decrypting, modify the ROUND_KEYS parameter to point to the last
+	 * round key rather than the first, since for decryption the round keys
+	 * are used in reverse order.
+	 */
+.if \decrypting
+	mov		NROUNDS, NROUNDS	/* zero the high 32 bits */
+.if \n == 64
+	add		ROUND_KEYS, ROUND_KEYS, NROUNDS_X, lsl #3
+	sub		ROUND_KEYS, ROUND_KEYS, #8
+.else
+	add		ROUND_KEYS, ROUND_KEYS, NROUNDS_X, lsl #2
+	sub		ROUND_KEYS, ROUND_KEYS, #4
+.endif
+.endif
+
+	// Load the index vector for tbl-based 8-bit rotates
+.if \decrypting
+	ldr		ROTATE_TABLE_Q, .Lrol\n\()_8_table
+.else
+	ldr		ROTATE_TABLE_Q, .Lror\n\()_8_table
+.endif
+
+	// One-time XTS preparation
+.if \n == 64
+	// Load first tweak
+	ld1		{TWEAKV0.16b}, [TWEAK]
+
+	// Load GF(2^128) multiplication table
+	ldr		GFMUL_TABLE_Q, .Lgf128mul_table
+.else
+	// Load first tweak
+	ld1		{TWEAKV0.8b}, [TWEAK]
+
+	// Load GF(2^64) multiplication table
+	ldr		GFMUL_TABLE_Q, .Lgf64mul_table
+
+	// Calculate second tweak, packing it together with the first
+	ushr		TMP0.2d, TWEAKV0.2d, #63
+	shl		TMP1.2d, TWEAKV0.2d, #1
+	tbl		TMP0.8b, {GFMUL_TABLE.16b}, TMP0.8b
+	eor		TMP0.8b, TMP0.8b, TMP1.8b
+	mov		TWEAKV0.d[1], TMP0.d[0]
+.endif
+
+.Lnext_128bytes_\@:
+
+	// Calculate XTS tweaks for next 128 bytes
+	_next_xts_tweak	TWEAKV1, TWEAKV0, TMP0, \n
+	_next_xts_tweak	TWEAKV2, TWEAKV1, TMP0, \n
+	_next_xts_tweak	TWEAKV3, TWEAKV2, TMP0, \n
+	_next_xts_tweak	TWEAKV4, TWEAKV3, TMP0, \n
+	_next_xts_tweak	TWEAKV5, TWEAKV4, TMP0, \n
+	_next_xts_tweak	TWEAKV6, TWEAKV5, TMP0, \n
+	_next_xts_tweak	TWEAKV7, TWEAKV6, TMP0, \n
+	_next_xts_tweak	TWEAKV_NEXT, TWEAKV7, TMP0, \n
+
+	// Load the next source blocks into {X,Y}[0-3]
+	ld1		{X_0.16b-Y_1.16b}, [SRC], #64
+	ld1		{X_2.16b-Y_3.16b}, [SRC], #64
+
+	// XOR the source blocks with their XTS tweaks
+	eor		TMP0.16b, X_0.16b, TWEAKV0.16b
+	eor		Y_0.16b,  Y_0.16b, TWEAKV1.16b
+	eor		TMP1.16b, X_1.16b, TWEAKV2.16b
+	eor		Y_1.16b,  Y_1.16b, TWEAKV3.16b
+	eor		TMP2.16b, X_2.16b, TWEAKV4.16b
+	eor		Y_2.16b,  Y_2.16b, TWEAKV5.16b
+	eor		TMP3.16b, X_3.16b, TWEAKV6.16b
+	eor		Y_3.16b,  Y_3.16b, TWEAKV7.16b
+
+	/*
+	 * De-interleave the 'x' and 'y' elements of each block, i.e. make it so
+	 * that the X[0-3] registers contain only the second halves of blocks,
+	 * and the Y[0-3] registers contain only the first halves of blocks.
+	 * (Speck uses the order (y, x) rather than the more intuitive (x, y).)
+	 */
+	uzp2		X_0.\lanes, TMP0.\lanes, Y_0.\lanes
+	uzp1		Y_0.\lanes, TMP0.\lanes, Y_0.\lanes
+	uzp2		X_1.\lanes, TMP1.\lanes, Y_1.\lanes
+	uzp1		Y_1.\lanes, TMP1.\lanes, Y_1.\lanes
+	uzp2		X_2.\lanes, TMP2.\lanes, Y_2.\lanes
+	uzp1		Y_2.\lanes, TMP2.\lanes, Y_2.\lanes
+	uzp2		X_3.\lanes, TMP3.\lanes, Y_3.\lanes
+	uzp1		Y_3.\lanes, TMP3.\lanes, Y_3.\lanes
+
+	// Do the cipher rounds
+	mov		x6, ROUND_KEYS
+	mov		w7, NROUNDS
+.Lnext_round_\@:
+.if \decrypting
+	ld1r		{ROUND_KEY.\lanes}, [x6]
+	sub		x6, x6, #( \n / 8 )
+	_speck_unround_128bytes	\n, \lanes
+.else
+	ld1r		{ROUND_KEY.\lanes}, [x6], #( \n / 8 )
+	_speck_round_128bytes	\n, \lanes
+.endif
+	subs		w7, w7, #1
+	bne		.Lnext_round_\@
+
+	// Re-interleave the 'x' and 'y' elements of each block
+	zip1		TMP0.\lanes, Y_0.\lanes, X_0.\lanes
+	zip2		Y_0.\lanes,  Y_0.\lanes, X_0.\lanes
+	zip1		TMP1.\lanes, Y_1.\lanes, X_1.\lanes
+	zip2		Y_1.\lanes,  Y_1.\lanes, X_1.\lanes
+	zip1		TMP2.\lanes, Y_2.\lanes, X_2.\lanes
+	zip2		Y_2.\lanes,  Y_2.\lanes, X_2.\lanes
+	zip1		TMP3.\lanes, Y_3.\lanes, X_3.\lanes
+	zip2		Y_3.\lanes,  Y_3.\lanes, X_3.\lanes
+
+	// XOR the encrypted/decrypted blocks with the tweaks calculated earlier
+	eor		X_0.16b, TMP0.16b, TWEAKV0.16b
+	eor		Y_0.16b, Y_0.16b,  TWEAKV1.16b
+	eor		X_1.16b, TMP1.16b, TWEAKV2.16b
+	eor		Y_1.16b, Y_1.16b,  TWEAKV3.16b
+	eor		X_2.16b, TMP2.16b, TWEAKV4.16b
+	eor		Y_2.16b, Y_2.16b,  TWEAKV5.16b
+	eor		X_3.16b, TMP3.16b, TWEAKV6.16b
+	eor		Y_3.16b, Y_3.16b,  TWEAKV7.16b
+	mov		TWEAKV0.16b, TWEAKV_NEXT.16b
+
+	// Store the ciphertext in the destination buffer
+	st1		{X_0.16b-Y_1.16b}, [DST], #64
+	st1		{X_2.16b-Y_3.16b}, [DST], #64
+
+	// Continue if there are more 128-byte chunks remaining
+	subs		NBYTES, NBYTES, #128
+	bne		.Lnext_128bytes_\@
+
+	// Store the next tweak and return
+.if \n == 64
+	st1		{TWEAKV_NEXT.16b}, [TWEAK]
+.else
+	st1		{TWEAKV_NEXT.8b}, [TWEAK]
+.endif
+	ret
+.endm
+
+ENTRY(speck128_xts_encrypt_neon)
+	_speck_xts_crypt	n=64, lanes=2d, decrypting=0
+ENDPROC(speck128_xts_encrypt_neon)
+
+ENTRY(speck128_xts_decrypt_neon)
+	_speck_xts_crypt	n=64, lanes=2d, decrypting=1
+ENDPROC(speck128_xts_decrypt_neon)
+
+ENTRY(speck64_xts_encrypt_neon)
+	_speck_xts_crypt	n=32, lanes=4s, decrypting=0
+ENDPROC(speck64_xts_encrypt_neon)
+
+ENTRY(speck64_xts_decrypt_neon)
+	_speck_xts_crypt	n=32, lanes=4s, decrypting=1
+ENDPROC(speck64_xts_decrypt_neon)
diff --git a/arch/arm64/crypto/speck-neon-glue.c b/arch/arm64/crypto/speck-neon-glue.c
new file mode 100644
index 000000000000..6e233aeb4ff4
--- /dev/null
+++ b/arch/arm64/crypto/speck-neon-glue.c
@@ -0,0 +1,282 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
+ * (64-bit version; based on the 32-bit version)
+ *
+ * Copyright (c) 2018 Google, Inc
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/algapi.h>
+#include <crypto/gf128mul.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/speck.h>
+#include <crypto/xts.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+/* The assembly functions only handle multiples of 128 bytes */
+#define SPECK_NEON_CHUNK_SIZE	128
+
+/* Speck128 */
+
+struct speck128_xts_tfm_ctx {
+	struct speck128_tfm_ctx main_key;
+	struct speck128_tfm_ctx tweak_key;
+};
+
+asmlinkage void speck128_xts_encrypt_neon(const u64 *round_keys, int nrounds,
+					  void *dst, const void *src,
+					  unsigned int nbytes, void *tweak);
+
+asmlinkage void speck128_xts_decrypt_neon(const u64 *round_keys, int nrounds,
+					  void *dst, const void *src,
+					  unsigned int nbytes, void *tweak);
+
+typedef void (*speck128_crypt_one_t)(const struct speck128_tfm_ctx *,
+				     u8 *, const u8 *);
+typedef void (*speck128_xts_crypt_many_t)(const u64 *, int, void *,
+					  const void *, unsigned int, void *);
+
+static __always_inline int
+__speck128_xts_crypt(struct skcipher_request *req,
+		     speck128_crypt_one_t crypt_one,
+		     speck128_xts_crypt_many_t crypt_many)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct speck128_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	le128 tweak;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	crypto_speck128_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+		u8 *dst = walk.dst.virt.addr;
+		const u8 *src = walk.src.virt.addr;
+
+		if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
+			unsigned int count;
+
+			count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
+			kernel_neon_begin();
+			(*crypt_many)(ctx->main_key.round_keys,
+				      ctx->main_key.nrounds,
+				      dst, src, count, &tweak);
+			kernel_neon_end();
+			dst += count;
+			src += count;
+			nbytes -= count;
+		}
+
+		/* Handle any remainder with generic code */
+		while (nbytes >= sizeof(tweak)) {
+			le128_xor((le128 *)dst, (const le128 *)src, &tweak);
+			(*crypt_one)(&ctx->main_key, dst, dst);
+			le128_xor((le128 *)dst, (const le128 *)dst, &tweak);
+			gf128mul_x_ble(&tweak, &tweak);
+
+			dst += sizeof(tweak);
+			src += sizeof(tweak);
+			nbytes -= sizeof(tweak);
+		}
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+
+static int speck128_xts_encrypt(struct skcipher_request *req)
+{
+	return __speck128_xts_crypt(req, crypto_speck128_encrypt,
+				    speck128_xts_encrypt_neon);
+}
+
+static int speck128_xts_decrypt(struct skcipher_request *req)
+{
+	return __speck128_xts_crypt(req, crypto_speck128_decrypt,
+				    speck128_xts_decrypt_neon);
+}
+
+static int speck128_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			       unsigned int keylen)
+{
+	struct speck128_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = xts_verify_key(tfm, key, keylen);
+	if (err)
+		return err;
+
+	keylen /= 2;
+
+	err = crypto_speck128_setkey(&ctx->main_key, key, keylen);
+	if (err)
+		return err;
+
+	return crypto_speck128_setkey(&ctx->tweak_key, key + keylen, keylen);
+}
+
+/* Speck64 */
+
+struct speck64_xts_tfm_ctx {
+	struct speck64_tfm_ctx main_key;
+	struct speck64_tfm_ctx tweak_key;
+};
+
+asmlinkage void speck64_xts_encrypt_neon(const u32 *round_keys, int nrounds,
+					 void *dst, const void *src,
+					 unsigned int nbytes, void *tweak);
+
+asmlinkage void speck64_xts_decrypt_neon(const u32 *round_keys, int nrounds,
+					 void *dst, const void *src,
+					 unsigned int nbytes, void *tweak);
+
+typedef void (*speck64_crypt_one_t)(const struct speck64_tfm_ctx *,
+				    u8 *, const u8 *);
+typedef void (*speck64_xts_crypt_many_t)(const u32 *, int, void *,
+					 const void *, unsigned int, void *);
+
+static __always_inline int
+__speck64_xts_crypt(struct skcipher_request *req, speck64_crypt_one_t crypt_one,
+		    speck64_xts_crypt_many_t crypt_many)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct speck64_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	__le64 tweak;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	crypto_speck64_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+		u8 *dst = walk.dst.virt.addr;
+		const u8 *src = walk.src.virt.addr;
+
+		if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
+			unsigned int count;
+
+			count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
+			kernel_neon_begin();
+			(*crypt_many)(ctx->main_key.round_keys,
+				      ctx->main_key.nrounds,
+				      dst, src, count, &tweak);
+			kernel_neon_end();
+			dst += count;
+			src += count;
+			nbytes -= count;
+		}
+
+		/* Handle any remainder with generic code */
+		while (nbytes >= sizeof(tweak)) {
+			*(__le64 *)dst = *(__le64 *)src ^ tweak;
+			(*crypt_one)(&ctx->main_key, dst, dst);
+			*(__le64 *)dst ^= tweak;
+			tweak = cpu_to_le64((le64_to_cpu(tweak) << 1) ^
+					    ((tweak & cpu_to_le64(1ULL << 63)) ?
+					     0x1B : 0));
+			dst += sizeof(tweak);
+			src += sizeof(tweak);
+			nbytes -= sizeof(tweak);
+		}
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+
+static int speck64_xts_encrypt(struct skcipher_request *req)
+{
+	return __speck64_xts_crypt(req, crypto_speck64_encrypt,
+				   speck64_xts_encrypt_neon);
+}
+
+static int speck64_xts_decrypt(struct skcipher_request *req)
+{
+	return __speck64_xts_crypt(req, crypto_speck64_decrypt,
+				   speck64_xts_decrypt_neon);
+}
+
+static int speck64_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct speck64_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = xts_verify_key(tfm, key, keylen);
+	if (err)
+		return err;
+
+	keylen /= 2;
+
+	err = crypto_speck64_setkey(&ctx->main_key, key, keylen);
+	if (err)
+		return err;
+
+	return crypto_speck64_setkey(&ctx->tweak_key, key + keylen, keylen);
+}
+
+static struct skcipher_alg speck_algs[] = {
+	{
+		.base.cra_name		= "xts(speck128)",
+		.base.cra_driver_name	= "xts-speck128-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= SPECK128_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct speck128_xts_tfm_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * SPECK128_128_KEY_SIZE,
+		.max_keysize		= 2 * SPECK128_256_KEY_SIZE,
+		.ivsize			= SPECK128_BLOCK_SIZE,
+		.walksize		= SPECK_NEON_CHUNK_SIZE,
+		.setkey			= speck128_xts_setkey,
+		.encrypt		= speck128_xts_encrypt,
+		.decrypt		= speck128_xts_decrypt,
+	}, {
+		.base.cra_name		= "xts(speck64)",
+		.base.cra_driver_name	= "xts-speck64-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= SPECK64_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct speck64_xts_tfm_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * SPECK64_96_KEY_SIZE,
+		.max_keysize		= 2 * SPECK64_128_KEY_SIZE,
+		.ivsize			= SPECK64_BLOCK_SIZE,
+		.walksize		= SPECK_NEON_CHUNK_SIZE,
+		.setkey			= speck64_xts_setkey,
+		.encrypt		= speck64_xts_encrypt,
+		.decrypt		= speck64_xts_decrypt,
+	}
+};
+
+static int __init speck_neon_module_init(void)
+{
+	if (!(elf_hwcap & HWCAP_ASIMD))
+		return -ENODEV;
+	return crypto_register_skciphers(speck_algs, ARRAY_SIZE(speck_algs));
+}
+
+static void __exit speck_neon_module_exit(void)
+{
+	crypto_unregister_skciphers(speck_algs, ARRAY_SIZE(speck_algs));
+}
+
+module_init(speck_neon_module_init);
+module_exit(speck_neon_module_exit);
+
+MODULE_DESCRIPTION("Speck block cipher (NEON-accelerated)");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("xts(speck128)");
+MODULE_ALIAS_CRYPTO("xts-speck128-neon");
+MODULE_ALIAS_CRYPTO("xts(speck64)");
+MODULE_ALIAS_CRYPTO("xts-speck64-neon");
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 12e8484a8ee7..e762ef417562 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -94,23 +94,30 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 
 
 #define	STACK_OFFSET    8*3
-#define	HashKey		16*0	// store HashKey <<1 mod poly here
-#define	HashKey_2	16*1	// store HashKey^2 <<1 mod poly here
-#define	HashKey_3	16*2	// store HashKey^3 <<1 mod poly here
-#define	HashKey_4	16*3	// store HashKey^4 <<1 mod poly here
-#define	HashKey_k	16*4	// store XOR of High 64 bits and Low 64
+
+#define AadHash 16*0
+#define AadLen 16*1
+#define InLen (16*1)+8
+#define PBlockEncKey 16*2
+#define OrigIV 16*3
+#define CurCount 16*4
+#define PBlockLen 16*5
+#define	HashKey		16*6	// store HashKey <<1 mod poly here
+#define	HashKey_2	16*7	// store HashKey^2 <<1 mod poly here
+#define	HashKey_3	16*8	// store HashKey^3 <<1 mod poly here
+#define	HashKey_4	16*9	// store HashKey^4 <<1 mod poly here
+#define	HashKey_k	16*10	// store XOR of High 64 bits and Low 64
 				// bits of  HashKey <<1 mod poly here
 				//(for Karatsuba purposes)
-#define	HashKey_2_k	16*5	// store XOR of High 64 bits and Low 64
+#define	HashKey_2_k	16*11	// store XOR of High 64 bits and Low 64
 				// bits of  HashKey^2 <<1 mod poly here
 				// (for Karatsuba purposes)
-#define	HashKey_3_k	16*6	// store XOR of High 64 bits and Low 64
+#define	HashKey_3_k	16*12	// store XOR of High 64 bits and Low 64
 				// bits of  HashKey^3 <<1 mod poly here
 				// (for Karatsuba purposes)
-#define	HashKey_4_k	16*7	// store XOR of High 64 bits and Low 64
+#define	HashKey_4_k	16*13	// store XOR of High 64 bits and Low 64
 				// bits of  HashKey^4 <<1 mod poly here
 				// (for Karatsuba purposes)
-#define	VARIABLE_OFFSET	16*8
 
 #define arg1 rdi
 #define arg2 rsi
@@ -118,10 +125,11 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 #define arg4 rcx
 #define arg5 r8
 #define arg6 r9
-#define arg7 STACK_OFFSET+8(%r14)
-#define arg8 STACK_OFFSET+16(%r14)
-#define arg9 STACK_OFFSET+24(%r14)
-#define arg10 STACK_OFFSET+32(%r14)
+#define arg7 STACK_OFFSET+8(%rsp)
+#define arg8 STACK_OFFSET+16(%rsp)
+#define arg9 STACK_OFFSET+24(%rsp)
+#define arg10 STACK_OFFSET+32(%rsp)
+#define arg11 STACK_OFFSET+40(%rsp)
 #define keysize 2*15*16(%arg1)
 #endif
 
@@ -171,6 +179,332 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 #define TKEYP	T1
 #endif
 
+.macro FUNC_SAVE
+	push	%r12
+	push	%r13
+	push	%r14
+#
+# states of %xmm registers %xmm6:%xmm15 not saved
+# all %xmm registers are clobbered
+#
+.endm
+
+
+.macro FUNC_RESTORE
+	pop	%r14
+	pop	%r13
+	pop	%r12
+.endm
+
+# Precompute hashkeys.
+# Input: Hash subkey.
+# Output: HashKeys stored in gcm_context_data.  Only needs to be called
+# once per key.
+# clobbers r12, and tmp xmm registers.
+.macro PRECOMPUTE SUBKEY TMP1 TMP2 TMP3 TMP4 TMP5 TMP6 TMP7
+	mov	\SUBKEY, %r12
+	movdqu	(%r12), \TMP3
+	movdqa	SHUF_MASK(%rip), \TMP2
+	PSHUFB_XMM \TMP2, \TMP3
+
+	# precompute HashKey<<1 mod poly from the HashKey (required for GHASH)
+
+	movdqa	\TMP3, \TMP2
+	psllq	$1, \TMP3
+	psrlq	$63, \TMP2
+	movdqa	\TMP2, \TMP1
+	pslldq	$8, \TMP2
+	psrldq	$8, \TMP1
+	por	\TMP2, \TMP3
+
+	# reduce HashKey<<1
+
+	pshufd	$0x24, \TMP1, \TMP2
+	pcmpeqd TWOONE(%rip), \TMP2
+	pand	POLY(%rip), \TMP2
+	pxor	\TMP2, \TMP3
+	movdqa	\TMP3, HashKey(%arg2)
+
+	movdqa	   \TMP3, \TMP5
+	pshufd	   $78, \TMP3, \TMP1
+	pxor	   \TMP3, \TMP1
+	movdqa	   \TMP1, HashKey_k(%arg2)
+
+	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
+# TMP5 = HashKey^2<<1 (mod poly)
+	movdqa	   \TMP5, HashKey_2(%arg2)
+# HashKey_2 = HashKey^2<<1 (mod poly)
+	pshufd	   $78, \TMP5, \TMP1
+	pxor	   \TMP5, \TMP1
+	movdqa	   \TMP1, HashKey_2_k(%arg2)
+
+	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
+# TMP5 = HashKey^3<<1 (mod poly)
+	movdqa	   \TMP5, HashKey_3(%arg2)
+	pshufd	   $78, \TMP5, \TMP1
+	pxor	   \TMP5, \TMP1
+	movdqa	   \TMP1, HashKey_3_k(%arg2)
+
+	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
+# TMP5 = HashKey^3<<1 (mod poly)
+	movdqa	   \TMP5, HashKey_4(%arg2)
+	pshufd	   $78, \TMP5, \TMP1
+	pxor	   \TMP5, \TMP1
+	movdqa	   \TMP1, HashKey_4_k(%arg2)
+.endm
+
+# GCM_INIT initializes a gcm_context struct to prepare for encoding/decoding.
+# Clobbers rax, r10-r13 and xmm0-xmm6, %xmm13
+.macro GCM_INIT Iv SUBKEY AAD AADLEN
+	mov \AADLEN, %r11
+	mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length
+	xor %r11, %r11
+	mov %r11, InLen(%arg2) # ctx_data.in_length = 0
+	mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0
+	mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0
+	mov \Iv, %rax
+	movdqu (%rax), %xmm0
+	movdqu %xmm0, OrigIV(%arg2) # ctx_data.orig_IV = iv
+
+	movdqa  SHUF_MASK(%rip), %xmm2
+	PSHUFB_XMM %xmm2, %xmm0
+	movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv
+
+	PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
+	movdqa HashKey(%arg2), %xmm13
+
+	CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \
+	%xmm4, %xmm5, %xmm6
+.endm
+
+# GCM_ENC_DEC Encodes/Decodes given data. Assumes that the passed gcm_context
+# struct has been initialized by GCM_INIT.
+# Requires the input data be at least 1 byte long because of READ_PARTIAL_BLOCK
+# Clobbers rax, r10-r13, and xmm0-xmm15
+.macro GCM_ENC_DEC operation
+	movdqu AadHash(%arg2), %xmm8
+	movdqu HashKey(%arg2), %xmm13
+	add %arg5, InLen(%arg2)
+
+	xor %r11, %r11 # initialise the data pointer offset as zero
+	PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation
+
+	sub %r11, %arg5		# sub partial block data used
+	mov %arg5, %r13		# save the number of bytes
+
+	and $-16, %r13		# %r13 = %r13 - (%r13 mod 16)
+	mov %r13, %r12
+	# Encrypt/Decrypt first few blocks
+
+	and	$(3<<4), %r12
+	jz	_initial_num_blocks_is_0_\@
+	cmp	$(2<<4), %r12
+	jb	_initial_num_blocks_is_1_\@
+	je	_initial_num_blocks_is_2_\@
+_initial_num_blocks_is_3_\@:
+	INITIAL_BLOCKS_ENC_DEC	%xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
+%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 5, 678, \operation
+	sub	$48, %r13
+	jmp	_initial_blocks_\@
+_initial_num_blocks_is_2_\@:
+	INITIAL_BLOCKS_ENC_DEC	%xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
+%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 6, 78, \operation
+	sub	$32, %r13
+	jmp	_initial_blocks_\@
+_initial_num_blocks_is_1_\@:
+	INITIAL_BLOCKS_ENC_DEC	%xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
+%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 7, 8, \operation
+	sub	$16, %r13
+	jmp	_initial_blocks_\@
+_initial_num_blocks_is_0_\@:
+	INITIAL_BLOCKS_ENC_DEC	%xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
+%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 8, 0, \operation
+_initial_blocks_\@:
+
+	# Main loop - Encrypt/Decrypt remaining blocks
+
+	cmp	$0, %r13
+	je	_zero_cipher_left_\@
+	sub	$64, %r13
+	je	_four_cipher_left_\@
+_crypt_by_4_\@:
+	GHASH_4_ENCRYPT_4_PARALLEL_\operation	%xmm9, %xmm10, %xmm11, %xmm12, \
+	%xmm13, %xmm14, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, \
+	%xmm7, %xmm8, enc
+	add	$64, %r11
+	sub	$64, %r13
+	jne	_crypt_by_4_\@
+_four_cipher_left_\@:
+	GHASH_LAST_4	%xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \
+%xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8
+_zero_cipher_left_\@:
+	movdqu %xmm8, AadHash(%arg2)
+	movdqu %xmm0, CurCount(%arg2)
+
+	mov	%arg5, %r13
+	and	$15, %r13			# %r13 = arg5 (mod 16)
+	je	_multiple_of_16_bytes_\@
+
+	mov %r13, PBlockLen(%arg2)
+
+	# Handle the last <16 Byte block separately
+	paddd ONE(%rip), %xmm0                # INCR CNT to get Yn
+	movdqu %xmm0, CurCount(%arg2)
+	movdqa SHUF_MASK(%rip), %xmm10
+	PSHUFB_XMM %xmm10, %xmm0
+
+	ENCRYPT_SINGLE_BLOCK	%xmm0, %xmm1        # Encrypt(K, Yn)
+	movdqu %xmm0, PBlockEncKey(%arg2)
+
+	cmp	$16, %arg5
+	jge _large_enough_update_\@
+
+	lea (%arg4,%r11,1), %r10
+	mov %r13, %r12
+	READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1
+	jmp _data_read_\@
+
+_large_enough_update_\@:
+	sub	$16, %r11
+	add	%r13, %r11
+
+	# receive the last <16 Byte block
+	movdqu	(%arg4, %r11, 1), %xmm1
+
+	sub	%r13, %r11
+	add	$16, %r11
+
+	lea	SHIFT_MASK+16(%rip), %r12
+	# adjust the shuffle mask pointer to be able to shift 16-r13 bytes
+	# (r13 is the number of bytes in plaintext mod 16)
+	sub	%r13, %r12
+	# get the appropriate shuffle mask
+	movdqu	(%r12), %xmm2
+	# shift right 16-r13 bytes
+	PSHUFB_XMM  %xmm2, %xmm1
+
+_data_read_\@:
+	lea ALL_F+16(%rip), %r12
+	sub %r13, %r12
+
+.ifc \operation, dec
+	movdqa  %xmm1, %xmm2
+.endif
+	pxor	%xmm1, %xmm0            # XOR Encrypt(K, Yn)
+	movdqu	(%r12), %xmm1
+	# get the appropriate mask to mask out top 16-r13 bytes of xmm0
+	pand	%xmm1, %xmm0            # mask out top 16-r13 bytes of xmm0
+.ifc \operation, dec
+	pand    %xmm1, %xmm2
+	movdqa SHUF_MASK(%rip), %xmm10
+	PSHUFB_XMM %xmm10 ,%xmm2
+
+	pxor %xmm2, %xmm8
+.else
+	movdqa SHUF_MASK(%rip), %xmm10
+	PSHUFB_XMM %xmm10,%xmm0
+
+	pxor	%xmm0, %xmm8
+.endif
+
+	movdqu %xmm8, AadHash(%arg2)
+.ifc \operation, enc
+	# GHASH computation for the last <16 byte block
+	movdqa SHUF_MASK(%rip), %xmm10
+	# shuffle xmm0 back to output as ciphertext
+	PSHUFB_XMM %xmm10, %xmm0
+.endif
+
+	# Output %r13 bytes
+	MOVQ_R64_XMM %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
+	sub $8, %r13
+_less_than_8_bytes_left_\@:
+	mov %al,  (%arg3, %r11, 1)
+	add $1, %r11
+	shr $8, %rax
+	sub $1, %r13
+	jne _less_than_8_bytes_left_\@
+_multiple_of_16_bytes_\@:
+.endm
+
+# GCM_COMPLETE Finishes update of tag of last partial block
+# Output: Authorization Tag (AUTH_TAG)
+# Clobbers rax, r10-r12, and xmm0, xmm1, xmm5-xmm15
+.macro GCM_COMPLETE AUTHTAG AUTHTAGLEN
+	movdqu AadHash(%arg2), %xmm8
+	movdqu HashKey(%arg2), %xmm13
+
+	mov PBlockLen(%arg2), %r12
+
+	cmp $0, %r12
+	je _partial_done\@
+
+	GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
+
+_partial_done\@:
+	mov AadLen(%arg2), %r12  # %r13 = aadLen (number of bytes)
+	shl	$3, %r12		  # convert into number of bits
+	movd	%r12d, %xmm15		  # len(A) in %xmm15
+	mov InLen(%arg2), %r12
+	shl     $3, %r12                  # len(C) in bits (*128)
+	MOVQ_R64_XMM    %r12, %xmm1
+
+	pslldq	$8, %xmm15		  # %xmm15 = len(A)||0x0000000000000000
+	pxor	%xmm1, %xmm15		  # %xmm15 = len(A)||len(C)
+	pxor	%xmm15, %xmm8
+	GHASH_MUL	%xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
+	# final GHASH computation
+	movdqa SHUF_MASK(%rip), %xmm10
+	PSHUFB_XMM %xmm10, %xmm8
+
+	movdqu OrigIV(%arg2), %xmm0       # %xmm0 = Y0
+	ENCRYPT_SINGLE_BLOCK	%xmm0,  %xmm1	  # E(K, Y0)
+	pxor	%xmm8, %xmm0
+_return_T_\@:
+	mov	\AUTHTAG, %r10                     # %r10 = authTag
+	mov	\AUTHTAGLEN, %r11                    # %r11 = auth_tag_len
+	cmp	$16, %r11
+	je	_T_16_\@
+	cmp	$8, %r11
+	jl	_T_4_\@
+_T_8_\@:
+	MOVQ_R64_XMM	%xmm0, %rax
+	mov	%rax, (%r10)
+	add	$8, %r10
+	sub	$8, %r11
+	psrldq	$8, %xmm0
+	cmp	$0, %r11
+	je	_return_T_done_\@
+_T_4_\@:
+	movd	%xmm0, %eax
+	mov	%eax, (%r10)
+	add	$4, %r10
+	sub	$4, %r11
+	psrldq	$4, %xmm0
+	cmp	$0, %r11
+	je	_return_T_done_\@
+_T_123_\@:
+	movd	%xmm0, %eax
+	cmp	$2, %r11
+	jl	_T_1_\@
+	mov	%ax, (%r10)
+	cmp	$2, %r11
+	je	_return_T_done_\@
+	add	$2, %r10
+	sar	$16, %eax
+_T_1_\@:
+	mov	%al, (%r10)
+	jmp	_return_T_done_\@
+_T_16_\@:
+	movdqu	%xmm0, (%r10)
+_return_T_done_\@:
+.endm
 
 #ifdef __x86_64__
 /* GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0)
@@ -264,232 +598,188 @@ _read_next_byte_lt8_\@:
 _done_read_partial_block_\@:
 .endm
 
-/*
-* if a = number of total plaintext bytes
-* b = floor(a/16)
-* num_initial_blocks = b mod 4
-* encrypt the initial num_initial_blocks blocks and apply ghash on
-* the ciphertext
-* %r10, %r11, %r12, %rax, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9 registers
-* are clobbered
-* arg1, %arg2, %arg3, %r14 are used as a pointer only, not modified
-*/
-
-
-.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, %r11           # %r11 = aadLen
-	pxor	   %xmm\i, %xmm\i
-	pxor       \XMM2, \XMM2
+# CALC_AAD_HASH: Calculates the hash of the data which will not be encrypted.
+# clobbers r10-11, xmm14
+.macro CALC_AAD_HASH HASHKEY AAD AADLEN TMP1 TMP2 TMP3 TMP4 TMP5 \
+	TMP6 TMP7
+	MOVADQ	   SHUF_MASK(%rip), %xmm14
+	mov	   \AAD, %r10		# %r10 = AAD
+	mov	   \AADLEN, %r11		# %r11 = aadLen
+	pxor	   \TMP7, \TMP7
+	pxor	   \TMP6, \TMP6
 
 	cmp	   $16, %r11
-	jl	   _get_AAD_rest\num_initial_blocks\operation
-_get_AAD_blocks\num_initial_blocks\operation:
-	movdqu	   (%r10), %xmm\i
-	PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data
-	pxor	   %xmm\i, \XMM2
-	GHASH_MUL  \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
+	jl	   _get_AAD_rest\@
+_get_AAD_blocks\@:
+	movdqu	   (%r10), \TMP7
+	PSHUFB_XMM   %xmm14, \TMP7 # byte-reflect the AAD data
+	pxor	   \TMP7, \TMP6
+	GHASH_MUL  \TMP6, \HASHKEY, \TMP1, \TMP2, \TMP3, \TMP4, \TMP5
 	add	   $16, %r10
 	sub	   $16, %r11
 	cmp	   $16, %r11
-	jge	   _get_AAD_blocks\num_initial_blocks\operation
+	jge	   _get_AAD_blocks\@
 
-	movdqu	   \XMM2, %xmm\i
+	movdqu	   \TMP6, \TMP7
 
 	/* read the last <16B of AAD */
-_get_AAD_rest\num_initial_blocks\operation:
+_get_AAD_rest\@:
 	cmp	   $0, %r11
-	je	   _get_AAD_done\num_initial_blocks\operation
-
-	READ_PARTIAL_BLOCK %r10, %r11, \TMP1, %xmm\i
-	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
-	pxor	   \XMM2, %xmm\i
-	GHASH_MUL  %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
+	je	   _get_AAD_done\@
 
-_get_AAD_done\num_initial_blocks\operation:
-	xor	   %r11, %r11 # initialise the data pointer offset as zero
-	# start AES for num_initial_blocks blocks
-
-	mov	   %arg5, %rax                      # %rax = *Y0
-	movdqu	   (%rax), \XMM0                    # XMM0 = Y0
-	PSHUFB_XMM   %xmm14, \XMM0
+	READ_PARTIAL_BLOCK %r10, %r11, \TMP1, \TMP7
+	PSHUFB_XMM   %xmm14, \TMP7 # byte-reflect the AAD data
+	pxor	   \TMP6, \TMP7
+	GHASH_MUL  \TMP7, \HASHKEY, \TMP1, \TMP2, \TMP3, \TMP4, \TMP5
+	movdqu \TMP7, \TMP6
 
-.if (\i == 5) || (\i == 6) || (\i == 7)
-	MOVADQ		ONE(%RIP),\TMP1
-	MOVADQ		(%arg1),\TMP2
-.irpc index, \i_seq
-	paddd	   \TMP1, \XMM0                 # INCR Y0
-	movdqa	   \XMM0, %xmm\index
-	PSHUFB_XMM   %xmm14, %xmm\index      # perform a 16 byte swap
-	pxor	   \TMP2, %xmm\index
-.endr
-	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
-	AESENCLAST \TMP1, %xmm\index         # Last Round
-.endr
-.irpc index, \i_seq
-	movdqu	   (%arg3 , %r11, 1), \TMP1
-	pxor	   \TMP1, %xmm\index
-	movdqu	   %xmm\index, (%arg2 , %r11, 1)
-	# write back plaintext/ciphertext for num_initial_blocks
-	add	   $16, %r11
-
-	movdqa     \TMP1, %xmm\index
-	PSHUFB_XMM	   %xmm14, %xmm\index
-                # prepare plaintext/ciphertext for GHASH computation
-.endr
-.endif
-
-        # apply GHASH on num_initial_blocks blocks
+_get_AAD_done\@:
+	movdqu \TMP6, AadHash(%arg2)
+.endm
 
-.if \i == 5
-        pxor       %xmm5, %xmm6
-	GHASH_MUL  %xmm6, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
-        pxor       %xmm6, %xmm7
-	GHASH_MUL  %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
-        pxor       %xmm7, %xmm8
-	GHASH_MUL  %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
-.elseif \i == 6
-        pxor       %xmm6, %xmm7
-	GHASH_MUL  %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
-        pxor       %xmm7, %xmm8
-	GHASH_MUL  %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
-.elseif \i == 7
-        pxor       %xmm7, %xmm8
-	GHASH_MUL  %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
+# PARTIAL_BLOCK: Handles encryption/decryption and the tag partial blocks
+# between update calls.
+# Requires the input data be at least 1 byte long due to READ_PARTIAL_BLOCK
+# Outputs encrypted bytes, and updates hash and partial info in gcm_data_context
+# Clobbers rax, r10, r12, r13, xmm0-6, xmm9-13
+.macro PARTIAL_BLOCK CYPH_PLAIN_OUT PLAIN_CYPH_IN PLAIN_CYPH_LEN DATA_OFFSET \
+	AAD_HASH operation
+	mov 	PBlockLen(%arg2), %r13
+	cmp	$0, %r13
+	je	_partial_block_done_\@	# Leave Macro if no partial blocks
+	# Read in input data without over reading
+	cmp	$16, \PLAIN_CYPH_LEN
+	jl	_fewer_than_16_bytes_\@
+	movups	(\PLAIN_CYPH_IN), %xmm1	# If more than 16 bytes, just fill xmm
+	jmp	_data_read_\@
+
+_fewer_than_16_bytes_\@:
+	lea	(\PLAIN_CYPH_IN, \DATA_OFFSET, 1), %r10
+	mov	\PLAIN_CYPH_LEN, %r12
+	READ_PARTIAL_BLOCK %r10 %r12 %xmm0 %xmm1
+
+	mov PBlockLen(%arg2), %r13
+
+_data_read_\@:				# Finished reading in data
+
+	movdqu	PBlockEncKey(%arg2), %xmm9
+	movdqu	HashKey(%arg2), %xmm13
+
+	lea	SHIFT_MASK(%rip), %r12
+
+	# adjust the shuffle mask pointer to be able to shift r13 bytes
+	# r16-r13 is the number of bytes in plaintext mod 16)
+	add	%r13, %r12
+	movdqu	(%r12), %xmm2		# get the appropriate shuffle mask
+	PSHUFB_XMM %xmm2, %xmm9		# shift right r13 bytes
+
+.ifc \operation, dec
+	movdqa	%xmm1, %xmm3
+	pxor	%xmm1, %xmm9		# Cyphertext XOR E(K, Yn)
+
+	mov	\PLAIN_CYPH_LEN, %r10
+	add	%r13, %r10
+	# Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling
+	sub	$16, %r10
+	# Determine if if partial block is not being filled and
+	# shift mask accordingly
+	jge	_no_extra_mask_1_\@
+	sub	%r10, %r12
+_no_extra_mask_1_\@:
+
+	movdqu	ALL_F-SHIFT_MASK(%r12), %xmm1
+	# get the appropriate mask to mask out bottom r13 bytes of xmm9
+	pand	%xmm1, %xmm9		# mask out bottom r13 bytes of xmm9
+
+	pand	%xmm1, %xmm3
+	movdqa	SHUF_MASK(%rip), %xmm10
+	PSHUFB_XMM	%xmm10, %xmm3
+	PSHUFB_XMM	%xmm2, %xmm3
+	pxor	%xmm3, \AAD_HASH
+
+	cmp	$0, %r10
+	jl	_partial_incomplete_1_\@
+
+	# GHASH computation for the last <16 Byte block
+	GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+	xor	%rax,%rax
+
+	mov	%rax, PBlockLen(%arg2)
+	jmp	_dec_done_\@
+_partial_incomplete_1_\@:
+	add	\PLAIN_CYPH_LEN, PBlockLen(%arg2)
+_dec_done_\@:
+	movdqu	\AAD_HASH, AadHash(%arg2)
+.else
+	pxor	%xmm1, %xmm9			# Plaintext XOR E(K, Yn)
+
+	mov	\PLAIN_CYPH_LEN, %r10
+	add	%r13, %r10
+	# Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling
+	sub	$16, %r10
+	# Determine if if partial block is not being filled and
+	# shift mask accordingly
+	jge	_no_extra_mask_2_\@
+	sub	%r10, %r12
+_no_extra_mask_2_\@:
+
+	movdqu	ALL_F-SHIFT_MASK(%r12), %xmm1
+	# get the appropriate mask to mask out bottom r13 bytes of xmm9
+	pand	%xmm1, %xmm9
+
+	movdqa	SHUF_MASK(%rip), %xmm1
+	PSHUFB_XMM %xmm1, %xmm9
+	PSHUFB_XMM %xmm2, %xmm9
+	pxor	%xmm9, \AAD_HASH
+
+	cmp	$0, %r10
+	jl	_partial_incomplete_2_\@
+
+	# GHASH computation for the last <16 Byte block
+	GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+	xor	%rax,%rax
+
+	mov	%rax, PBlockLen(%arg2)
+	jmp	_encode_done_\@
+_partial_incomplete_2_\@:
+	add	\PLAIN_CYPH_LEN, PBlockLen(%arg2)
+_encode_done_\@:
+	movdqu	\AAD_HASH, AadHash(%arg2)
+
+	movdqa	SHUF_MASK(%rip), %xmm10
+	# shuffle xmm9 back to output as ciphertext
+	PSHUFB_XMM	%xmm10, %xmm9
+	PSHUFB_XMM	%xmm2, %xmm9
 .endif
-	cmp	   $64, %r13
-	jl	_initial_blocks_done\num_initial_blocks\operation
-	# no need for precomputed values
-/*
-*
-* 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
-*/
-	MOVADQ	   ONE(%rip), \TMP1
-	paddd	   \TMP1, \XMM0              # INCR Y0
-	MOVADQ	   \XMM0, \XMM1
-	PSHUFB_XMM  %xmm14, \XMM1        # perform a 16 byte swap
-
-	paddd	   \TMP1, \XMM0              # INCR Y0
-	MOVADQ	   \XMM0, \XMM2
-	PSHUFB_XMM  %xmm14, \XMM2        # perform a 16 byte swap
-
-	paddd	   \TMP1, \XMM0              # INCR Y0
-	MOVADQ	   \XMM0, \XMM3
-	PSHUFB_XMM %xmm14, \XMM3        # perform a 16 byte swap
-
-	paddd	   \TMP1, \XMM0              # INCR Y0
-	MOVADQ	   \XMM0, \XMM4
-	PSHUFB_XMM %xmm14, \XMM4        # perform a 16 byte swap
-
-	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
-	movdqa	   \TMP1, HashKey_k(%rsp)
-	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
-# TMP5 = HashKey^2<<1 (mod poly)
-	movdqa	   \TMP5, HashKey_2(%rsp)
-# HashKey_2 = HashKey^2<<1 (mod poly)
-	pshufd	   $78, \TMP5, \TMP1
-	pxor	   \TMP5, \TMP1
-	movdqa	   \TMP1, HashKey_2_k(%rsp)
-.irpc index, 1234 # do 4 rounds
-	movaps 0x10*\index(%arg1), \TMP1
-	AESENC	   \TMP1, \XMM1
-	AESENC	   \TMP1, \XMM2
-	AESENC	   \TMP1, \XMM3
-	AESENC	   \TMP1, \XMM4
-.endr
-	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
-# TMP5 = HashKey^3<<1 (mod poly)
-	movdqa	   \TMP5, HashKey_3(%rsp)
-	pshufd	   $78, \TMP5, \TMP1
-	pxor	   \TMP5, \TMP1
-	movdqa	   \TMP1, HashKey_3_k(%rsp)
-.irpc index, 56789 # do next 5 rounds
-	movaps 0x10*\index(%arg1), \TMP1
-	AESENC	   \TMP1, \XMM1
-	AESENC	   \TMP1, \XMM2
-	AESENC	   \TMP1, \XMM3
-	AESENC	   \TMP1, \XMM4
-.endr
-	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
-# TMP5 = HashKey^3<<1 (mod poly)
-	movdqa	   \TMP5, HashKey_4(%rsp)
-	pshufd	   $78, \TMP5, \TMP1
-	pxor	   \TMP5, \TMP1
-	movdqa	   \TMP1, HashKey_4_k(%rsp)
-	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
-	AESENCLAST \TMP2, \XMM4
-	movdqu	   16*0(%arg3 , %r11 , 1), \TMP1
-	pxor	   \TMP1, \XMM1
-	movdqu	   \XMM1, 16*0(%arg2 , %r11 , 1)
-	movdqa     \TMP1, \XMM1
-	movdqu	   16*1(%arg3 , %r11 , 1), \TMP1
-	pxor	   \TMP1, \XMM2
-	movdqu	   \XMM2, 16*1(%arg2 , %r11 , 1)
-	movdqa     \TMP1, \XMM2
-	movdqu	   16*2(%arg3 , %r11 , 1), \TMP1
-	pxor	   \TMP1, \XMM3
-	movdqu	   \XMM3, 16*2(%arg2 , %r11 , 1)
-	movdqa     \TMP1, \XMM3
-	movdqu	   16*3(%arg3 , %r11 , 1), \TMP1
-	pxor	   \TMP1, \XMM4
-	movdqu	   \XMM4, 16*3(%arg2 , %r11 , 1)
-	movdqa     \TMP1, \XMM4
-	add	   $64, %r11
-	PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap
-	pxor	   \XMMDst, \XMM1
-# combine GHASHed value with the corresponding ciphertext
-	PSHUFB_XMM %xmm14, \XMM2 # perform a 16 byte swap
-	PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap
-	PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap
-
-_initial_blocks_done\num_initial_blocks\operation:
-
-.endm
+	# output encrypted Bytes
+	cmp	$0, %r10
+	jl	_partial_fill_\@
+	mov	%r13, %r12
+	mov	$16, %r13
+	# Set r13 to be the number of bytes to write out
+	sub	%r12, %r13
+	jmp	_count_set_\@
+_partial_fill_\@:
+	mov	\PLAIN_CYPH_LEN, %r13
+_count_set_\@:
+	movdqa	%xmm9, %xmm0
+	MOVQ_R64_XMM	%xmm0, %rax
+	cmp	$8, %r13
+	jle	_less_than_8_bytes_left_\@
 
+	mov	%rax, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
+	add	$8, \DATA_OFFSET
+	psrldq	$8, %xmm0
+	MOVQ_R64_XMM	%xmm0, %rax
+	sub	$8, %r13
+_less_than_8_bytes_left_\@:
+	movb	%al, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
+	add	$1, \DATA_OFFSET
+	shr	$8, %rax
+	sub	$1, %r13
+	jne	_less_than_8_bytes_left_\@
+_partial_block_done_\@:
+.endm # PARTIAL_BLOCK
 
 /*
 * if a = number of total plaintext bytes
@@ -499,49 +789,19 @@ _initial_blocks_done\num_initial_blocks\operation:
 * the ciphertext
 * %r10, %r11, %r12, %rax, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9 registers
 * are clobbered
-* arg1, %arg2, %arg3, %r14 are used as a pointer only, not modified
+* arg1, %arg2, %arg3 are used as a pointer only, not modified
 */
 
 
-.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, %r11           # %r11 = aadLen
-	pxor	   %xmm\i, %xmm\i
-	pxor	   \XMM2, \XMM2
+.macro INITIAL_BLOCKS_ENC_DEC TMP1 TMP2 TMP3 TMP4 TMP5 XMM0 XMM1 \
+	XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation
+	MOVADQ		SHUF_MASK(%rip), %xmm14
 
-	cmp	   $16, %r11
-	jl	   _get_AAD_rest\num_initial_blocks\operation
-_get_AAD_blocks\num_initial_blocks\operation:
-	movdqu	   (%r10), %xmm\i
-	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
-	pxor	   %xmm\i, \XMM2
-	GHASH_MUL  \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
-	add	   $16, %r10
-	sub	   $16, %r11
-	cmp	   $16, %r11
-	jge	   _get_AAD_blocks\num_initial_blocks\operation
+	movdqu AadHash(%arg2), %xmm\i		    # XMM0 = Y0
 
-	movdqu	   \XMM2, %xmm\i
-
-	/* read the last <16B of AAD */
-_get_AAD_rest\num_initial_blocks\operation:
-	cmp	   $0, %r11
-	je	   _get_AAD_done\num_initial_blocks\operation
-
-	READ_PARTIAL_BLOCK %r10, %r11, \TMP1, %xmm\i
-	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
-	pxor	   \XMM2, %xmm\i
-	GHASH_MUL  %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
-
-_get_AAD_done\num_initial_blocks\operation:
-	xor	   %r11, %r11 # initialise the data pointer offset as zero
 	# start AES for num_initial_blocks blocks
 
-	mov	   %arg5, %rax                      # %rax = *Y0
-	movdqu	   (%rax), \XMM0                    # XMM0 = Y0
-	PSHUFB_XMM   %xmm14, \XMM0
+	movdqu CurCount(%arg2), \XMM0                # XMM0 = Y0
 
 .if (\i == 5) || (\i == 6) || (\i == 7)
 
@@ -549,7 +809,11 @@ _get_AAD_done\num_initial_blocks\operation:
 	MOVADQ		0(%arg1),\TMP2
 .irpc index, \i_seq
 	paddd		\TMP1, \XMM0                 # INCR Y0
+.ifc \operation, dec
+        movdqa     \XMM0, %xmm\index
+.else
 	MOVADQ		\XMM0, %xmm\index
+.endif
 	PSHUFB_XMM	%xmm14, %xmm\index      # perform a 16 byte swap
 	pxor		\TMP2, %xmm\index
 .endr
@@ -558,25 +822,29 @@ _get_AAD_done\num_initial_blocks\operation:
 	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:
+aes_loop_initial_\@:
 	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
+	jnz	aes_loop_initial_\@
 
 	MOVADQ	(%r10), \TMP1
 .irpc index, \i_seq
 	AESENCLAST \TMP1, %xmm\index         # Last Round
 .endr
 .irpc index, \i_seq
-	movdqu	   (%arg3 , %r11, 1), \TMP1
+	movdqu	   (%arg4 , %r11, 1), \TMP1
 	pxor	   \TMP1, %xmm\index
-	movdqu	   %xmm\index, (%arg2 , %r11, 1)
+	movdqu	   %xmm\index, (%arg3 , %r11, 1)
 	# write back plaintext/ciphertext for num_initial_blocks
 	add	   $16, %r11
+
+.ifc \operation, dec
+	movdqa     \TMP1, %xmm\index
+.endif
 	PSHUFB_XMM	   %xmm14, %xmm\index
 
 		# prepare plaintext/ciphertext for GHASH computation
@@ -602,7 +870,7 @@ aes_loop_initial_enc\num_initial_blocks:
 	GHASH_MUL  %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
 .endif
 	cmp	   $64, %r13
-	jl	_initial_blocks_done\num_initial_blocks\operation
+	jl	_initial_blocks_done\@
 	# no need for precomputed values
 /*
 *
@@ -631,17 +899,6 @@ aes_loop_initial_enc\num_initial_blocks:
 	pxor	   \TMP1, \XMM2
 	pxor	   \TMP1, \XMM3
 	pxor	   \TMP1, \XMM4
-	movdqa	   \TMP3, \TMP5
-	pshufd	   $78, \TMP3, \TMP1
-	pxor	   \TMP3, \TMP1
-	movdqa	   \TMP1, HashKey_k(%rsp)
-	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
-# TMP5 = HashKey^2<<1 (mod poly)
-	movdqa	   \TMP5, HashKey_2(%rsp)
-# HashKey_2 = HashKey^2<<1 (mod poly)
-	pshufd	   $78, \TMP5, \TMP1
-	pxor	   \TMP5, \TMP1
-	movdqa	   \TMP1, HashKey_2_k(%rsp)
 .irpc index, 1234 # do 4 rounds
 	movaps 0x10*\index(%arg1), \TMP1
 	AESENC	   \TMP1, \XMM1
@@ -649,12 +906,6 @@ aes_loop_initial_enc\num_initial_blocks:
 	AESENC	   \TMP1, \XMM3
 	AESENC	   \TMP1, \XMM4
 .endr
-	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
-# TMP5 = HashKey^3<<1 (mod poly)
-	movdqa	   \TMP5, HashKey_3(%rsp)
-	pshufd	   $78, \TMP5, \TMP1
-	pxor	   \TMP5, \TMP1
-	movdqa	   \TMP1, HashKey_3_k(%rsp)
 .irpc index, 56789 # do next 5 rounds
 	movaps 0x10*\index(%arg1), \TMP1
 	AESENC	   \TMP1, \XMM1
@@ -662,45 +913,56 @@ aes_loop_initial_enc\num_initial_blocks:
 	AESENC	   \TMP1, \XMM3
 	AESENC	   \TMP1, \XMM4
 .endr
-	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
-# TMP5 = HashKey^3<<1 (mod poly)
-	movdqa	   \TMP5, HashKey_4(%rsp)
-	pshufd	   $78, \TMP5, \TMP1
-	pxor	   \TMP5, \TMP1
-	movdqa	   \TMP1, HashKey_4_k(%rsp)
 	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
+	jz	   aes_loop_pre_done\@
 
-aes_loop_pre_enc\num_initial_blocks:
+aes_loop_pre_\@:
 	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
+	jnz	   aes_loop_pre_\@
 
-aes_loop_pre_enc_done\num_initial_blocks:
+aes_loop_pre_done\@:
 	MOVADQ	   (%r10), \TMP2
 	AESENCLAST \TMP2, \XMM1
 	AESENCLAST \TMP2, \XMM2
 	AESENCLAST \TMP2, \XMM3
 	AESENCLAST \TMP2, \XMM4
-	movdqu	   16*0(%arg3 , %r11 , 1), \TMP1
+	movdqu	   16*0(%arg4 , %r11 , 1), \TMP1
 	pxor	   \TMP1, \XMM1
-	movdqu	   16*1(%arg3 , %r11 , 1), \TMP1
+.ifc \operation, dec
+	movdqu     \XMM1, 16*0(%arg3 , %r11 , 1)
+	movdqa     \TMP1, \XMM1
+.endif
+	movdqu	   16*1(%arg4 , %r11 , 1), \TMP1
 	pxor	   \TMP1, \XMM2
-	movdqu	   16*2(%arg3 , %r11 , 1), \TMP1
+.ifc \operation, dec
+	movdqu     \XMM2, 16*1(%arg3 , %r11 , 1)
+	movdqa     \TMP1, \XMM2
+.endif
+	movdqu	   16*2(%arg4 , %r11 , 1), \TMP1
 	pxor	   \TMP1, \XMM3
-	movdqu	   16*3(%arg3 , %r11 , 1), \TMP1
+.ifc \operation, dec
+	movdqu     \XMM3, 16*2(%arg3 , %r11 , 1)
+	movdqa     \TMP1, \XMM3
+.endif
+	movdqu	   16*3(%arg4 , %r11 , 1), \TMP1
 	pxor	   \TMP1, \XMM4
-	movdqu     \XMM1, 16*0(%arg2 , %r11 , 1)
-	movdqu     \XMM2, 16*1(%arg2 , %r11 , 1)
-	movdqu     \XMM3, 16*2(%arg2 , %r11 , 1)
-	movdqu     \XMM4, 16*3(%arg2 , %r11 , 1)
+.ifc \operation, dec
+	movdqu     \XMM4, 16*3(%arg3 , %r11 , 1)
+	movdqa     \TMP1, \XMM4
+.else
+	movdqu     \XMM1, 16*0(%arg3 , %r11 , 1)
+	movdqu     \XMM2, 16*1(%arg3 , %r11 , 1)
+	movdqu     \XMM3, 16*2(%arg3 , %r11 , 1)
+	movdqu     \XMM4, 16*3(%arg3 , %r11 , 1)
+.endif
 
 	add	   $64, %r11
 	PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap
@@ -710,14 +972,14 @@ aes_loop_pre_enc_done\num_initial_blocks:
 	PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap
 	PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap
 
-_initial_blocks_done\num_initial_blocks\operation:
+_initial_blocks_done\@:
 
 .endm
 
 /*
 * encrypt 4 blocks at a time
 * ghash the 4 previously encrypted ciphertext blocks
-* arg1, %arg2, %arg3 are used as pointers only, not modified
+* arg1, %arg3, %arg4 are used as pointers only, not modified
 * %r11 is the data offset value
 */
 .macro GHASH_4_ENCRYPT_4_PARALLEL_ENC TMP1 TMP2 TMP3 TMP4 TMP5 \
@@ -735,7 +997,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pshufd	  $78, \XMM5, \TMP6
 	pxor	  \XMM5, \TMP6
 	paddd     ONE(%rip), \XMM0		# INCR CNT
-	movdqa	  HashKey_4(%rsp), \TMP5
+	movdqa	  HashKey_4(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP4           # TMP4 = a1*b1
 	movdqa    \XMM0, \XMM1
 	paddd     ONE(%rip), \XMM0		# INCR CNT
@@ -754,7 +1016,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pxor	  (%arg1), \XMM2
 	pxor	  (%arg1), \XMM3
 	pxor	  (%arg1), \XMM4
-	movdqa	  HashKey_4_k(%rsp), \TMP5
+	movdqa	  HashKey_4_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP6           # TMP6 = (a1+a0)*(b1+b0)
 	movaps 0x10(%arg1), \TMP1
 	AESENC	  \TMP1, \XMM1              # Round 1
@@ -769,7 +1031,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM6, \TMP1
 	pshufd	  $78, \XMM6, \TMP2
 	pxor	  \XMM6, \TMP2
-	movdqa	  HashKey_3(%rsp), \TMP5
+	movdqa	  HashKey_3(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1 * b1
 	movaps 0x30(%arg1), \TMP3
 	AESENC    \TMP3, \XMM1              # Round 3
@@ -782,7 +1044,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	AESENC	  \TMP3, \XMM2
 	AESENC	  \TMP3, \XMM3
 	AESENC	  \TMP3, \XMM4
-	movdqa	  HashKey_3_k(%rsp), \TMP5
+	movdqa	  HashKey_3_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x50(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1              # Round 5
@@ -796,7 +1058,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM7, \TMP1
 	pshufd	  $78, \XMM7, \TMP2
 	pxor	  \XMM7, \TMP2
-	movdqa	  HashKey_2(%rsp ), \TMP5
+	movdqa	  HashKey_2(%arg2), \TMP5
 
         # Multiply TMP5 * HashKey using karatsuba
 
@@ -812,7 +1074,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	AESENC	  \TMP3, \XMM2
 	AESENC	  \TMP3, \XMM3
 	AESENC	  \TMP3, \XMM4
-	movdqa	  HashKey_2_k(%rsp), \TMP5
+	movdqa	  HashKey_2_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x80(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1             # Round 8
@@ -830,7 +1092,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM8, \TMP1
 	pshufd	  $78, \XMM8, \TMP2
 	pxor	  \XMM8, \TMP2
-	movdqa	  HashKey(%rsp), \TMP5
+	movdqa	  HashKey(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1          # TMP1 = a1*b1
 	movaps 0x90(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1            # Round 9
@@ -842,37 +1104,37 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	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
+	jz	  aes_loop_par_enc_done\@
 
-aes_loop_par_enc:
+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
+	jnz	  aes_loop_par_enc\@
 
-aes_loop_par_enc_done:
+aes_loop_par_enc_done\@:
 	MOVADQ	  (%r10), \TMP3
 	AESENCLAST \TMP3, \XMM1           # Round 10
 	AESENCLAST \TMP3, \XMM2
 	AESENCLAST \TMP3, \XMM3
 	AESENCLAST \TMP3, \XMM4
-	movdqa    HashKey_k(%rsp), \TMP5
+	movdqa    HashKey_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
-	movdqu	  (%arg3,%r11,1), \TMP3
+	movdqu	  (%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM1                 # Ciphertext/Plaintext XOR EK
-	movdqu	  16(%arg3,%r11,1), \TMP3
+	movdqu	  16(%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM2                 # Ciphertext/Plaintext XOR EK
-	movdqu	  32(%arg3,%r11,1), \TMP3
+	movdqu	  32(%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM3                 # Ciphertext/Plaintext XOR EK
-	movdqu	  48(%arg3,%r11,1), \TMP3
+	movdqu	  48(%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM4                 # Ciphertext/Plaintext XOR EK
-        movdqu    \XMM1, (%arg2,%r11,1)        # Write to the ciphertext buffer
-        movdqu    \XMM2, 16(%arg2,%r11,1)      # Write to the ciphertext buffer
-        movdqu    \XMM3, 32(%arg2,%r11,1)      # Write to the ciphertext buffer
-        movdqu    \XMM4, 48(%arg2,%r11,1)      # Write to the ciphertext buffer
+        movdqu    \XMM1, (%arg3,%r11,1)        # Write to the ciphertext buffer
+        movdqu    \XMM2, 16(%arg3,%r11,1)      # Write to the ciphertext buffer
+        movdqu    \XMM3, 32(%arg3,%r11,1)      # Write to the ciphertext buffer
+        movdqu    \XMM4, 48(%arg3,%r11,1)      # Write to the ciphertext buffer
 	PSHUFB_XMM %xmm15, \XMM1        # perform a 16 byte swap
 	PSHUFB_XMM %xmm15, \XMM2	# perform a 16 byte swap
 	PSHUFB_XMM %xmm15, \XMM3	# perform a 16 byte swap
@@ -925,7 +1187,7 @@ aes_loop_par_enc_done:
 /*
 * decrypt 4 blocks at a time
 * ghash the 4 previously decrypted ciphertext blocks
-* arg1, %arg2, %arg3 are used as pointers only, not modified
+* arg1, %arg3, %arg4 are used as pointers only, not modified
 * %r11 is the data offset value
 */
 .macro GHASH_4_ENCRYPT_4_PARALLEL_DEC TMP1 TMP2 TMP3 TMP4 TMP5 \
@@ -943,7 +1205,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pshufd	  $78, \XMM5, \TMP6
 	pxor	  \XMM5, \TMP6
 	paddd     ONE(%rip), \XMM0		# INCR CNT
-	movdqa	  HashKey_4(%rsp), \TMP5
+	movdqa	  HashKey_4(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP4           # TMP4 = a1*b1
 	movdqa    \XMM0, \XMM1
 	paddd     ONE(%rip), \XMM0		# INCR CNT
@@ -962,7 +1224,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	pxor	  (%arg1), \XMM2
 	pxor	  (%arg1), \XMM3
 	pxor	  (%arg1), \XMM4
-	movdqa	  HashKey_4_k(%rsp), \TMP5
+	movdqa	  HashKey_4_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP6           # TMP6 = (a1+a0)*(b1+b0)
 	movaps 0x10(%arg1), \TMP1
 	AESENC	  \TMP1, \XMM1              # Round 1
@@ -977,7 +1239,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM6, \TMP1
 	pshufd	  $78, \XMM6, \TMP2
 	pxor	  \XMM6, \TMP2
-	movdqa	  HashKey_3(%rsp), \TMP5
+	movdqa	  HashKey_3(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1 * b1
 	movaps 0x30(%arg1), \TMP3
 	AESENC    \TMP3, \XMM1              # Round 3
@@ -990,7 +1252,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	AESENC	  \TMP3, \XMM2
 	AESENC	  \TMP3, \XMM3
 	AESENC	  \TMP3, \XMM4
-	movdqa	  HashKey_3_k(%rsp), \TMP5
+	movdqa	  HashKey_3_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x50(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1              # Round 5
@@ -1004,7 +1266,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM7, \TMP1
 	pshufd	  $78, \XMM7, \TMP2
 	pxor	  \XMM7, \TMP2
-	movdqa	  HashKey_2(%rsp ), \TMP5
+	movdqa	  HashKey_2(%arg2), \TMP5
 
         # Multiply TMP5 * HashKey using karatsuba
 
@@ -1020,7 +1282,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	AESENC	  \TMP3, \XMM2
 	AESENC	  \TMP3, \XMM3
 	AESENC	  \TMP3, \XMM4
-	movdqa	  HashKey_2_k(%rsp), \TMP5
+	movdqa	  HashKey_2_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
 	movaps 0x80(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1             # Round 8
@@ -1038,7 +1300,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	movdqa	  \XMM8, \TMP1
 	pshufd	  $78, \XMM8, \TMP2
 	pxor	  \XMM8, \TMP2
-	movdqa	  HashKey(%rsp), \TMP5
+	movdqa	  HashKey(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1          # TMP1 = a1*b1
 	movaps 0x90(%arg1), \TMP3
 	AESENC	  \TMP3, \XMM1            # Round 9
@@ -1050,40 +1312,40 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 	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
+	jz	  aes_loop_par_dec_done\@
 
-aes_loop_par_dec:
+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
+	jnz	  aes_loop_par_dec\@
 
-aes_loop_par_dec_done:
+aes_loop_par_dec_done\@:
 	MOVADQ	  (%r10), \TMP3
 	AESENCLAST \TMP3, \XMM1           # last round
 	AESENCLAST \TMP3, \XMM2
 	AESENCLAST \TMP3, \XMM3
 	AESENCLAST \TMP3, \XMM4
-	movdqa    HashKey_k(%rsp), \TMP5
+	movdqa    HashKey_k(%arg2), \TMP5
 	PCLMULQDQ 0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
-	movdqu	  (%arg3,%r11,1), \TMP3
+	movdqu	  (%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM1                 # Ciphertext/Plaintext XOR EK
-	movdqu	  \XMM1, (%arg2,%r11,1)        # Write to plaintext buffer
+	movdqu	  \XMM1, (%arg3,%r11,1)        # Write to plaintext buffer
 	movdqa    \TMP3, \XMM1
-	movdqu	  16(%arg3,%r11,1), \TMP3
+	movdqu	  16(%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM2                 # Ciphertext/Plaintext XOR EK
-	movdqu	  \XMM2, 16(%arg2,%r11,1)      # Write to plaintext buffer
+	movdqu	  \XMM2, 16(%arg3,%r11,1)      # Write to plaintext buffer
 	movdqa    \TMP3, \XMM2
-	movdqu	  32(%arg3,%r11,1), \TMP3
+	movdqu	  32(%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM3                 # Ciphertext/Plaintext XOR EK
-	movdqu	  \XMM3, 32(%arg2,%r11,1)      # Write to plaintext buffer
+	movdqu	  \XMM3, 32(%arg3,%r11,1)      # Write to plaintext buffer
 	movdqa    \TMP3, \XMM3
-	movdqu	  48(%arg3,%r11,1), \TMP3
+	movdqu	  48(%arg4,%r11,1), \TMP3
 	pxor	  \TMP3, \XMM4                 # Ciphertext/Plaintext XOR EK
-	movdqu	  \XMM4, 48(%arg2,%r11,1)      # Write to plaintext buffer
+	movdqu	  \XMM4, 48(%arg3,%r11,1)      # Write to plaintext buffer
 	movdqa    \TMP3, \XMM4
 	PSHUFB_XMM %xmm15, \XMM1        # perform a 16 byte swap
 	PSHUFB_XMM %xmm15, \XMM2	# perform a 16 byte swap
@@ -1143,10 +1405,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	movdqa	  \XMM1, \TMP6
 	pshufd	  $78, \XMM1, \TMP2
 	pxor	  \XMM1, \TMP2
-	movdqa	  HashKey_4(%rsp), \TMP5
+	movdqa	  HashKey_4(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP6       # TMP6 = a1*b1
 	PCLMULQDQ 0x00, \TMP5, \XMM1       # XMM1 = a0*b0
-	movdqa	  HashKey_4_k(%rsp), \TMP4
+	movdqa	  HashKey_4_k(%arg2), \TMP4
 	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	movdqa	  \XMM1, \XMMDst
 	movdqa	  \TMP2, \XMM1              # result in TMP6, XMMDst, XMM1
@@ -1156,10 +1418,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	movdqa	  \XMM2, \TMP1
 	pshufd	  $78, \XMM2, \TMP2
 	pxor	  \XMM2, \TMP2
-	movdqa	  HashKey_3(%rsp), \TMP5
+	movdqa	  HashKey_3(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1       # TMP1 = a1*b1
 	PCLMULQDQ 0x00, \TMP5, \XMM2       # XMM2 = a0*b0
-	movdqa	  HashKey_3_k(%rsp), \TMP4
+	movdqa	  HashKey_3_k(%arg2), \TMP4
 	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	pxor	  \TMP1, \TMP6
 	pxor	  \XMM2, \XMMDst
@@ -1171,10 +1433,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	movdqa	  \XMM3, \TMP1
 	pshufd	  $78, \XMM3, \TMP2
 	pxor	  \XMM3, \TMP2
-	movdqa	  HashKey_2(%rsp), \TMP5
+	movdqa	  HashKey_2(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1       # TMP1 = a1*b1
 	PCLMULQDQ 0x00, \TMP5, \XMM3       # XMM3 = a0*b0
-	movdqa	  HashKey_2_k(%rsp), \TMP4
+	movdqa	  HashKey_2_k(%arg2), \TMP4
 	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	pxor	  \TMP1, \TMP6
 	pxor	  \XMM3, \XMMDst
@@ -1184,10 +1446,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 	movdqa	  \XMM4, \TMP1
 	pshufd	  $78, \XMM4, \TMP2
 	pxor	  \XMM4, \TMP2
-	movdqa	  HashKey(%rsp), \TMP5
+	movdqa	  HashKey(%arg2), \TMP5
 	PCLMULQDQ 0x11, \TMP5, \TMP1	    # TMP1 = a1*b1
 	PCLMULQDQ 0x00, \TMP5, \XMM4       # XMM4 = a0*b0
-	movdqa	  HashKey_k(%rsp), \TMP4
+	movdqa	  HashKey_k(%arg2), \TMP4
 	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
 	pxor	  \TMP1, \TMP6
 	pxor	  \XMM4, \XMMDst
@@ -1256,6 +1518,8 @@ _esb_loop_\@:
 .endm
 /*****************************************************************************
 * void aesni_gcm_dec(void *aes_ctx,    // AES Key schedule. Starts on a 16 byte boundary.
+*                   struct gcm_context_data *data
+*                                      // Context data
 *                   u8 *out,           // Plaintext output. Encrypt in-place is allowed.
 *                   const u8 *in,      // Ciphertext input
 *                   u64 plaintext_len, // Length of data in bytes for decryption.
@@ -1333,195 +1597,20 @@ _esb_loop_\@:
 *
 *****************************************************************************/
 ENTRY(aesni_gcm_dec)
-	push	%r12
-	push	%r13
-	push	%r14
-	mov	%rsp, %r14
-/*
-* states of %xmm registers %xmm6:%xmm15 not saved
-* all %xmm registers are clobbered
-*/
-	sub	$VARIABLE_OFFSET, %rsp
-	and	$~63, %rsp                        # align rsp to 64 bytes
-	mov	%arg6, %r12
-	movdqu	(%r12), %xmm13			  # %xmm13 = HashKey
-        movdqa  SHUF_MASK(%rip), %xmm2
-	PSHUFB_XMM %xmm2, %xmm13
-
-
-# Precompute HashKey<<1 (mod poly) from the hash key (required for GHASH)
-
-	movdqa	%xmm13, %xmm2
-	psllq	$1, %xmm13
-	psrlq	$63, %xmm2
-	movdqa	%xmm2, %xmm1
-	pslldq	$8, %xmm2
-	psrldq	$8, %xmm1
-	por	%xmm2, %xmm13
-
-        # Reduction
-
-	pshufd	$0x24, %xmm1, %xmm2
-	pcmpeqd TWOONE(%rip), %xmm2
-	pand	POLY(%rip), %xmm2
-	pxor	%xmm2, %xmm13     # %xmm13 holds the HashKey<<1 (mod poly)
-
-
-        # Decrypt first few blocks
-
-	movdqa %xmm13, HashKey(%rsp)           # store HashKey<<1 (mod poly)
-	mov %arg4, %r13    # save the number of bytes of plaintext/ciphertext
-	and $-16, %r13                      # %r13 = %r13 - (%r13 mod 16)
-	mov %r13, %r12
-	and $(3<<4), %r12
-	jz _initial_num_blocks_is_0_decrypt
-	cmp $(2<<4), %r12
-	jb _initial_num_blocks_is_1_decrypt
-	je _initial_num_blocks_is_2_decrypt
-_initial_num_blocks_is_3_decrypt:
-	INITIAL_BLOCKS_DEC 3, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 5, 678, dec
-	sub	$48, %r13
-	jmp	_initial_blocks_decrypted
-_initial_num_blocks_is_2_decrypt:
-	INITIAL_BLOCKS_DEC	2, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 6, 78, dec
-	sub	$32, %r13
-	jmp	_initial_blocks_decrypted
-_initial_num_blocks_is_1_decrypt:
-	INITIAL_BLOCKS_DEC	1, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 7, 8, dec
-	sub	$16, %r13
-	jmp	_initial_blocks_decrypted
-_initial_num_blocks_is_0_decrypt:
-	INITIAL_BLOCKS_DEC	0, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 8, 0, dec
-_initial_blocks_decrypted:
-	cmp	$0, %r13
-	je	_zero_cipher_left_decrypt
-	sub	$64, %r13
-	je	_four_cipher_left_decrypt
-_decrypt_by_4:
-	GHASH_4_ENCRYPT_4_PARALLEL_DEC	%xmm9, %xmm10, %xmm11, %xmm12, %xmm13, \
-%xmm14, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, dec
-	add	$64, %r11
-	sub	$64, %r13
-	jne	_decrypt_by_4
-_four_cipher_left_decrypt:
-	GHASH_LAST_4	%xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \
-%xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8
-_zero_cipher_left_decrypt:
-	mov	%arg4, %r13
-	and	$15, %r13				# %r13 = arg4 (mod 16)
-	je	_multiple_of_16_bytes_decrypt
-
-        # Handle the last <16 byte block separately
-
-	paddd ONE(%rip), %xmm0         # increment CNT to get Yn
-        movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10, %xmm0
-
-	ENCRYPT_SINGLE_BLOCK  %xmm0, %xmm1    # E(K, Yn)
-
-	lea (%arg3,%r11,1), %r10
-	mov %r13, %r12
-	READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1
-
-	lea ALL_F+16(%rip), %r12
-	sub %r13, %r12
-	movdqa  %xmm1, %xmm2
-	pxor %xmm1, %xmm0            # Ciphertext XOR E(K, Yn)
-	movdqu (%r12), %xmm1
-	# get the appropriate mask to mask out top 16-%r13 bytes of %xmm0
-	pand %xmm1, %xmm0            # mask out top 16-%r13 bytes of %xmm0
-	pand    %xmm1, %xmm2
-        movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10 ,%xmm2
-
-	pxor %xmm2, %xmm8
-	GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
-
-        # output %r13 bytes
-	MOVQ_R64_XMM	%xmm0, %rax
-	cmp	$8, %r13
-	jle	_less_than_8_bytes_left_decrypt
-	mov	%rax, (%arg2 , %r11, 1)
-	add	$8, %r11
-	psrldq	$8, %xmm0
-	MOVQ_R64_XMM	%xmm0, %rax
-	sub	$8, %r13
-_less_than_8_bytes_left_decrypt:
-	mov	%al,  (%arg2, %r11, 1)
-	add	$1, %r11
-	shr	$8, %rax
-	sub	$1, %r13
-	jne	_less_than_8_bytes_left_decrypt
-_multiple_of_16_bytes_decrypt:
-	mov	arg8, %r12		  # %r13 = aadLen (number of bytes)
-	shl	$3, %r12		  # convert into number of bits
-	movd	%r12d, %xmm15		  # len(A) in %xmm15
-	shl	$3, %arg4		  # len(C) in bits (*128)
-	MOVQ_R64_XMM	%arg4, %xmm1
-	pslldq	$8, %xmm15		  # %xmm15 = len(A)||0x0000000000000000
-	pxor	%xmm1, %xmm15		  # %xmm15 = len(A)||len(C)
-	pxor	%xmm15, %xmm8
-	GHASH_MUL	%xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
-	         # final GHASH computation
-        movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10, %xmm8
+	FUNC_SAVE
 
-	mov	%arg5, %rax		  # %rax = *Y0
-	movdqu	(%rax), %xmm0		  # %xmm0 = Y0
-	ENCRYPT_SINGLE_BLOCK	%xmm0,  %xmm1	  # E(K, Y0)
-	pxor	%xmm8, %xmm0
-_return_T_decrypt:
-	mov	arg9, %r10                # %r10 = authTag
-	mov	arg10, %r11               # %r11 = auth_tag_len
-	cmp	$16, %r11
-	je	_T_16_decrypt
-	cmp	$8, %r11
-	jl	_T_4_decrypt
-_T_8_decrypt:
-	MOVQ_R64_XMM	%xmm0, %rax
-	mov	%rax, (%r10)
-	add	$8, %r10
-	sub	$8, %r11
-	psrldq	$8, %xmm0
-	cmp	$0, %r11
-	je	_return_T_done_decrypt
-_T_4_decrypt:
-	movd	%xmm0, %eax
-	mov	%eax, (%r10)
-	add	$4, %r10
-	sub	$4, %r11
-	psrldq	$4, %xmm0
-	cmp	$0, %r11
-	je	_return_T_done_decrypt
-_T_123_decrypt:
-	movd	%xmm0, %eax
-	cmp	$2, %r11
-	jl	_T_1_decrypt
-	mov	%ax, (%r10)
-	cmp	$2, %r11
-	je	_return_T_done_decrypt
-	add	$2, %r10
-	sar	$16, %eax
-_T_1_decrypt:
-	mov	%al, (%r10)
-	jmp	_return_T_done_decrypt
-_T_16_decrypt:
-	movdqu	%xmm0, (%r10)
-_return_T_done_decrypt:
-	mov	%r14, %rsp
-	pop	%r14
-	pop	%r13
-	pop	%r12
+	GCM_INIT %arg6, arg7, arg8, arg9
+	GCM_ENC_DEC dec
+	GCM_COMPLETE arg10, arg11
+	FUNC_RESTORE
 	ret
 ENDPROC(aesni_gcm_dec)
 
 
 /*****************************************************************************
 * void aesni_gcm_enc(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
+*                    struct gcm_context_data *data
+*                                        // Context data
 *                    u8 *out,            // Ciphertext output. Encrypt in-place is allowed.
 *                    const u8 *in,       // Plaintext input
 *                    u64 plaintext_len,  // Length of data in bytes for encryption.
@@ -1596,195 +1685,78 @@ ENDPROC(aesni_gcm_dec)
 * poly = x^128 + x^127 + x^126 + x^121 + 1
 ***************************************************************************/
 ENTRY(aesni_gcm_enc)
-	push	%r12
-	push	%r13
-	push	%r14
-	mov	%rsp, %r14
-#
-# states of %xmm registers %xmm6:%xmm15 not saved
-# all %xmm registers are clobbered
-#
-	sub	$VARIABLE_OFFSET, %rsp
-	and	$~63, %rsp
-	mov	%arg6, %r12
-	movdqu	(%r12), %xmm13
-        movdqa  SHUF_MASK(%rip), %xmm2
-	PSHUFB_XMM %xmm2, %xmm13
-
-
-# precompute HashKey<<1 mod poly from the HashKey (required for GHASH)
-
-	movdqa	%xmm13, %xmm2
-	psllq	$1, %xmm13
-	psrlq	$63, %xmm2
-	movdqa	%xmm2, %xmm1
-	pslldq	$8, %xmm2
-	psrldq	$8, %xmm1
-	por	%xmm2, %xmm13
-
-        # reduce HashKey<<1
-
-	pshufd	$0x24, %xmm1, %xmm2
-	pcmpeqd TWOONE(%rip), %xmm2
-	pand	POLY(%rip), %xmm2
-	pxor	%xmm2, %xmm13
-	movdqa	%xmm13, HashKey(%rsp)
-	mov	%arg4, %r13            # %xmm13 holds HashKey<<1 (mod poly)
-	and	$-16, %r13
-	mov	%r13, %r12
+	FUNC_SAVE
 
-        # Encrypt first few blocks
+	GCM_INIT %arg6, arg7, arg8, arg9
+	GCM_ENC_DEC enc
 
-	and	$(3<<4), %r12
-	jz	_initial_num_blocks_is_0_encrypt
-	cmp	$(2<<4), %r12
-	jb	_initial_num_blocks_is_1_encrypt
-	je	_initial_num_blocks_is_2_encrypt
-_initial_num_blocks_is_3_encrypt:
-	INITIAL_BLOCKS_ENC	3, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 5, 678, enc
-	sub	$48, %r13
-	jmp	_initial_blocks_encrypted
-_initial_num_blocks_is_2_encrypt:
-	INITIAL_BLOCKS_ENC	2, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 6, 78, enc
-	sub	$32, %r13
-	jmp	_initial_blocks_encrypted
-_initial_num_blocks_is_1_encrypt:
-	INITIAL_BLOCKS_ENC	1, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 7, 8, enc
-	sub	$16, %r13
-	jmp	_initial_blocks_encrypted
-_initial_num_blocks_is_0_encrypt:
-	INITIAL_BLOCKS_ENC	0, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 8, 0, enc
-_initial_blocks_encrypted:
-
-        # Main loop - Encrypt remaining blocks
-
-	cmp	$0, %r13
-	je	_zero_cipher_left_encrypt
-	sub	$64, %r13
-	je	_four_cipher_left_encrypt
-_encrypt_by_4_encrypt:
-	GHASH_4_ENCRYPT_4_PARALLEL_ENC	%xmm9, %xmm10, %xmm11, %xmm12, %xmm13, \
-%xmm14, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, enc
-	add	$64, %r11
-	sub	$64, %r13
-	jne	_encrypt_by_4_encrypt
-_four_cipher_left_encrypt:
-	GHASH_LAST_4	%xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \
-%xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8
-_zero_cipher_left_encrypt:
-	mov	%arg4, %r13
-	and	$15, %r13			# %r13 = arg4 (mod 16)
-	je	_multiple_of_16_bytes_encrypt
-
-         # Handle the last <16 Byte block separately
-	paddd ONE(%rip), %xmm0                # INCR CNT to get Yn
-        movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10, %xmm0
-
-	ENCRYPT_SINGLE_BLOCK	%xmm0, %xmm1        # Encrypt(K, Yn)
-
-	lea (%arg3,%r11,1), %r10
-	mov %r13, %r12
-	READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1
-
-	lea ALL_F+16(%rip), %r12
-	sub %r13, %r12
-	pxor	%xmm1, %xmm0            # Plaintext XOR Encrypt(K, Yn)
-	movdqu	(%r12), %xmm1
-	# get the appropriate mask to mask out top 16-r13 bytes of xmm0
-	pand	%xmm1, %xmm0            # mask out top 16-r13 bytes of xmm0
-        movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10,%xmm0
+	GCM_COMPLETE arg10, arg11
+	FUNC_RESTORE
+	ret
+ENDPROC(aesni_gcm_enc)
 
-	pxor	%xmm0, %xmm8
-	GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
-	# GHASH computation for the last <16 byte block
-	movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10, %xmm0
+/*****************************************************************************
+* void aesni_gcm_init(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
+*                     struct gcm_context_data *data,
+*                                         // context data
+*                     u8 *iv,             // Pre-counter block j0: 4 byte salt (from Security Association)
+*                                         // concatenated with 8 byte Initialisation Vector (from IPSec ESP Payload)
+*                                         // concatenated with 0x00000001. 16-byte aligned pointer.
+*                     u8 *hash_subkey,    // H, the Hash sub key input. Data starts on a 16-byte boundary.
+*                     const u8 *aad,      // Additional Authentication Data (AAD)
+*                     u64 aad_len)        // Length of AAD in bytes.
+*/
+ENTRY(aesni_gcm_init)
+	FUNC_SAVE
+	GCM_INIT %arg3, %arg4,%arg5, %arg6
+	FUNC_RESTORE
+	ret
+ENDPROC(aesni_gcm_init)
 
-	# shuffle xmm0 back to output as ciphertext
+/*****************************************************************************
+* void aesni_gcm_enc_update(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
+*                    struct gcm_context_data *data,
+*                                        // context data
+*                    u8 *out,            // Ciphertext output. Encrypt in-place is allowed.
+*                    const u8 *in,       // Plaintext input
+*                    u64 plaintext_len,  // Length of data in bytes for encryption.
+*/
+ENTRY(aesni_gcm_enc_update)
+	FUNC_SAVE
+	GCM_ENC_DEC enc
+	FUNC_RESTORE
+	ret
+ENDPROC(aesni_gcm_enc_update)
 
-        # Output %r13 bytes
-	MOVQ_R64_XMM %xmm0, %rax
-	cmp $8, %r13
-	jle _less_than_8_bytes_left_encrypt
-	mov %rax, (%arg2 , %r11, 1)
-	add $8, %r11
-	psrldq $8, %xmm0
-	MOVQ_R64_XMM %xmm0, %rax
-	sub $8, %r13
-_less_than_8_bytes_left_encrypt:
-	mov %al,  (%arg2, %r11, 1)
-	add $1, %r11
-	shr $8, %rax
-	sub $1, %r13
-	jne _less_than_8_bytes_left_encrypt
-_multiple_of_16_bytes_encrypt:
-	mov	arg8, %r12    # %r12 = addLen (number of bytes)
-	shl	$3, %r12
-	movd	%r12d, %xmm15       # len(A) in %xmm15
-	shl	$3, %arg4               # len(C) in bits (*128)
-	MOVQ_R64_XMM	%arg4, %xmm1
-	pslldq	$8, %xmm15          # %xmm15 = len(A)||0x0000000000000000
-	pxor	%xmm1, %xmm15       # %xmm15 = len(A)||len(C)
-	pxor	%xmm15, %xmm8
-	GHASH_MUL	%xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
-	# final GHASH computation
-        movdqa SHUF_MASK(%rip), %xmm10
-	PSHUFB_XMM %xmm10, %xmm8         # perform a 16 byte swap
+/*****************************************************************************
+* void aesni_gcm_dec_update(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
+*                    struct gcm_context_data *data,
+*                                        // context data
+*                    u8 *out,            // Ciphertext output. Encrypt in-place is allowed.
+*                    const u8 *in,       // Plaintext input
+*                    u64 plaintext_len,  // Length of data in bytes for encryption.
+*/
+ENTRY(aesni_gcm_dec_update)
+	FUNC_SAVE
+	GCM_ENC_DEC dec
+	FUNC_RESTORE
+	ret
+ENDPROC(aesni_gcm_dec_update)
 
-	mov	%arg5, %rax		       # %rax  = *Y0
-	movdqu	(%rax), %xmm0		       # %xmm0 = Y0
-	ENCRYPT_SINGLE_BLOCK	%xmm0, %xmm15         # Encrypt(K, Y0)
-	pxor	%xmm8, %xmm0
-_return_T_encrypt:
-	mov	arg9, %r10                     # %r10 = authTag
-	mov	arg10, %r11                    # %r11 = auth_tag_len
-	cmp	$16, %r11
-	je	_T_16_encrypt
-	cmp	$8, %r11
-	jl	_T_4_encrypt
-_T_8_encrypt:
-	MOVQ_R64_XMM	%xmm0, %rax
-	mov	%rax, (%r10)
-	add	$8, %r10
-	sub	$8, %r11
-	psrldq	$8, %xmm0
-	cmp	$0, %r11
-	je	_return_T_done_encrypt
-_T_4_encrypt:
-	movd	%xmm0, %eax
-	mov	%eax, (%r10)
-	add	$4, %r10
-	sub	$4, %r11
-	psrldq	$4, %xmm0
-	cmp	$0, %r11
-	je	_return_T_done_encrypt
-_T_123_encrypt:
-	movd	%xmm0, %eax
-	cmp	$2, %r11
-	jl	_T_1_encrypt
-	mov	%ax, (%r10)
-	cmp	$2, %r11
-	je	_return_T_done_encrypt
-	add	$2, %r10
-	sar	$16, %eax
-_T_1_encrypt:
-	mov	%al, (%r10)
-	jmp	_return_T_done_encrypt
-_T_16_encrypt:
-	movdqu	%xmm0, (%r10)
-_return_T_done_encrypt:
-	mov	%r14, %rsp
-	pop	%r14
-	pop	%r13
-	pop	%r12
+/*****************************************************************************
+* void aesni_gcm_finalize(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
+*                    struct gcm_context_data *data,
+*                                        // context data
+*                    u8 *auth_tag,       // Authenticated Tag output.
+*                    u64 auth_tag_len);  // Authenticated Tag Length in bytes. Valid values are 16 (most likely),
+*                                        // 12 or 8.
+*/
+ENTRY(aesni_gcm_finalize)
+	FUNC_SAVE
+	GCM_COMPLETE %arg3 %arg4
+	FUNC_RESTORE
 	ret
-ENDPROC(aesni_gcm_enc)
+ENDPROC(aesni_gcm_finalize)
 
 #endif
 
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 34cf1c1f8c98..acbe7e8336d8 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -72,6 +72,21 @@ struct aesni_xts_ctx {
 	u8 raw_crypt_ctx[sizeof(struct crypto_aes_ctx)] AESNI_ALIGN_ATTR;
 };
 
+#define GCM_BLOCK_LEN 16
+
+struct gcm_context_data {
+	/* init, update and finalize context data */
+	u8 aad_hash[GCM_BLOCK_LEN];
+	u64 aad_length;
+	u64 in_length;
+	u8 partial_block_enc_key[GCM_BLOCK_LEN];
+	u8 orig_IV[GCM_BLOCK_LEN];
+	u8 current_counter[GCM_BLOCK_LEN];
+	u64 partial_block_len;
+	u64 unused;
+	u8 hash_keys[GCM_BLOCK_LEN * 8];
+};
+
 asmlinkage int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
 			     unsigned int key_len);
 asmlinkage void aesni_enc(struct crypto_aes_ctx *ctx, u8 *out,
@@ -105,6 +120,7 @@ asmlinkage void aesni_xts_crypt8(struct crypto_aes_ctx *ctx, u8 *out,
 
 /* asmlinkage void aesni_gcm_enc()
  * void *ctx,  AES Key schedule. Starts on a 16 byte boundary.
+ * struct gcm_context_data.  May be uninitialized.
  * u8 *out, Ciphertext output. Encrypt in-place is allowed.
  * const u8 *in, Plaintext input
  * unsigned long plaintext_len, Length of data in bytes for encryption.
@@ -117,13 +133,15 @@ asmlinkage void aesni_xts_crypt8(struct crypto_aes_ctx *ctx, u8 *out,
  * unsigned long auth_tag_len), Authenticated Tag Length in bytes.
  *          Valid values are 16 (most likely), 12 or 8.
  */
-asmlinkage void aesni_gcm_enc(void *ctx, u8 *out,
+asmlinkage void aesni_gcm_enc(void *ctx,
+			struct gcm_context_data *gdata, u8 *out,
 			const u8 *in, unsigned long plaintext_len, u8 *iv,
 			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len);
 
 /* asmlinkage void aesni_gcm_dec()
  * void *ctx, AES Key schedule. Starts on a 16 byte boundary.
+ * struct gcm_context_data.  May be uninitialized.
  * u8 *out, Plaintext output. Decrypt in-place is allowed.
  * const u8 *in, Ciphertext input
  * unsigned long ciphertext_len, Length of data in bytes for decryption.
@@ -137,11 +155,28 @@ asmlinkage void aesni_gcm_enc(void *ctx, u8 *out,
  * unsigned long auth_tag_len) Authenticated Tag Length in bytes.
  * Valid values are 16 (most likely), 12 or 8.
  */
-asmlinkage void aesni_gcm_dec(void *ctx, u8 *out,
+asmlinkage void aesni_gcm_dec(void *ctx,
+			struct gcm_context_data *gdata, u8 *out,
 			const u8 *in, unsigned long ciphertext_len, u8 *iv,
 			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len);
 
+/* Scatter / Gather routines, with args similar to above */
+asmlinkage void aesni_gcm_init(void *ctx,
+			       struct gcm_context_data *gdata,
+			       u8 *iv,
+			       u8 *hash_subkey, const u8 *aad,
+			       unsigned long aad_len);
+asmlinkage void aesni_gcm_enc_update(void *ctx,
+				     struct gcm_context_data *gdata, u8 *out,
+				     const u8 *in, unsigned long plaintext_len);
+asmlinkage void aesni_gcm_dec_update(void *ctx,
+				     struct gcm_context_data *gdata, u8 *out,
+				     const u8 *in,
+				     unsigned long ciphertext_len);
+asmlinkage void aesni_gcm_finalize(void *ctx,
+				   struct gcm_context_data *gdata,
+				   u8 *auth_tag, unsigned long auth_tag_len);
 
 #ifdef CONFIG_AS_AVX
 asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv,
@@ -167,15 +202,17 @@ asmlinkage void aesni_gcm_dec_avx_gen2(void *ctx, u8 *out,
 			const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len);
 
-static void aesni_gcm_enc_avx(void *ctx, u8 *out,
+static void aesni_gcm_enc_avx(void *ctx,
+			struct gcm_context_data *data, u8 *out,
 			const u8 *in, unsigned long plaintext_len, u8 *iv,
 			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len)
 {
         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);
+		aesni_gcm_enc(ctx, data, out, in,
+			plaintext_len, iv, hash_subkey, aad,
+			aad_len, auth_tag, auth_tag_len);
 	} else {
 		aesni_gcm_precomp_avx_gen2(ctx, hash_subkey);
 		aesni_gcm_enc_avx_gen2(ctx, out, in, plaintext_len, iv, aad,
@@ -183,15 +220,17 @@ static void aesni_gcm_enc_avx(void *ctx, u8 *out,
 	}
 }
 
-static void aesni_gcm_dec_avx(void *ctx, u8 *out,
+static void aesni_gcm_dec_avx(void *ctx,
+			struct gcm_context_data *data, u8 *out,
 			const u8 *in, unsigned long ciphertext_len, u8 *iv,
 			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len)
 {
         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);
+		aesni_gcm_dec(ctx, data, out, in,
+			ciphertext_len, iv, hash_subkey, aad,
+			aad_len, auth_tag, auth_tag_len);
 	} else {
 		aesni_gcm_precomp_avx_gen2(ctx, hash_subkey);
 		aesni_gcm_dec_avx_gen2(ctx, out, in, ciphertext_len, iv, aad,
@@ -218,15 +257,17 @@ asmlinkage void aesni_gcm_dec_avx_gen4(void *ctx, u8 *out,
 			const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len);
 
-static void aesni_gcm_enc_avx2(void *ctx, u8 *out,
+static void aesni_gcm_enc_avx2(void *ctx,
+			struct gcm_context_data *data, u8 *out,
 			const u8 *in, unsigned long plaintext_len, u8 *iv,
 			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len)
 {
        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);
+		aesni_gcm_enc(ctx, data, out, in,
+			      plaintext_len, iv, hash_subkey, aad,
+			      aad_len, auth_tag, auth_tag_len);
 	} else if (plaintext_len < AVX_GEN4_OPTSIZE) {
 		aesni_gcm_precomp_avx_gen2(ctx, hash_subkey);
 		aesni_gcm_enc_avx_gen2(ctx, out, in, plaintext_len, iv, aad,
@@ -238,15 +279,17 @@ static void aesni_gcm_enc_avx2(void *ctx, u8 *out,
 	}
 }
 
-static void aesni_gcm_dec_avx2(void *ctx, u8 *out,
+static void aesni_gcm_dec_avx2(void *ctx,
+	struct gcm_context_data *data, u8 *out,
 			const u8 *in, unsigned long ciphertext_len, u8 *iv,
 			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
 			u8 *auth_tag, unsigned long auth_tag_len)
 {
        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);
+		aesni_gcm_dec(ctx, data, out, in,
+			      ciphertext_len, iv, hash_subkey,
+			      aad, aad_len, auth_tag, auth_tag_len);
 	} else if (ciphertext_len < AVX_GEN4_OPTSIZE) {
 		aesni_gcm_precomp_avx_gen2(ctx, hash_subkey);
 		aesni_gcm_dec_avx_gen2(ctx, out, in, ciphertext_len, iv, aad,
@@ -259,15 +302,19 @@ static void aesni_gcm_dec_avx2(void *ctx, u8 *out,
 }
 #endif
 
-static void (*aesni_gcm_enc_tfm)(void *ctx, u8 *out,
-			const u8 *in, unsigned long plaintext_len, u8 *iv,
-			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
-			u8 *auth_tag, unsigned long auth_tag_len);
+static void (*aesni_gcm_enc_tfm)(void *ctx,
+				 struct gcm_context_data *data, u8 *out,
+				 const u8 *in, unsigned long plaintext_len,
+				 u8 *iv, u8 *hash_subkey, const u8 *aad,
+				 unsigned long aad_len, u8 *auth_tag,
+				 unsigned long auth_tag_len);
 
-static void (*aesni_gcm_dec_tfm)(void *ctx, u8 *out,
-			const u8 *in, unsigned long ciphertext_len, u8 *iv,
-			u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
-			u8 *auth_tag, unsigned long auth_tag_len);
+static void (*aesni_gcm_dec_tfm)(void *ctx,
+				 struct gcm_context_data *data, u8 *out,
+				 const u8 *in, unsigned long ciphertext_len,
+				 u8 *iv, u8 *hash_subkey, const u8 *aad,
+				 unsigned long aad_len, u8 *auth_tag,
+				 unsigned long auth_tag_len);
 
 static inline struct
 aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm)
@@ -744,6 +791,127 @@ static int generic_gcmaes_set_authsize(struct crypto_aead *tfm,
 	return 0;
 }
 
+static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req,
+			      unsigned int assoclen, u8 *hash_subkey,
+			      u8 *iv, void *aes_ctx)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
+	struct gcm_context_data data AESNI_ALIGN_ATTR;
+	struct scatter_walk dst_sg_walk = {};
+	unsigned long left = req->cryptlen;
+	unsigned long len, srclen, dstlen;
+	struct scatter_walk assoc_sg_walk;
+	struct scatter_walk src_sg_walk;
+	struct scatterlist src_start[2];
+	struct scatterlist dst_start[2];
+	struct scatterlist *src_sg;
+	struct scatterlist *dst_sg;
+	u8 *src, *dst, *assoc;
+	u8 *assocmem = NULL;
+	u8 authTag[16];
+
+	if (!enc)
+		left -= auth_tag_len;
+
+	/* Linearize assoc, if not already linear */
+	if (req->src->length >= assoclen && req->src->length &&
+		(!PageHighMem(sg_page(req->src)) ||
+			req->src->offset + req->src->length < PAGE_SIZE)) {
+		scatterwalk_start(&assoc_sg_walk, req->src);
+		assoc = scatterwalk_map(&assoc_sg_walk);
+	} else {
+		/* assoc can be any length, so must be on heap */
+		assocmem = kmalloc(assoclen, GFP_ATOMIC);
+		if (unlikely(!assocmem))
+			return -ENOMEM;
+		assoc = assocmem;
+
+		scatterwalk_map_and_copy(assoc, req->src, 0, assoclen, 0);
+	}
+
+	src_sg = scatterwalk_ffwd(src_start, req->src, req->assoclen);
+	scatterwalk_start(&src_sg_walk, src_sg);
+	if (req->src != req->dst) {
+		dst_sg = scatterwalk_ffwd(dst_start, req->dst, req->assoclen);
+		scatterwalk_start(&dst_sg_walk, dst_sg);
+	}
+
+	kernel_fpu_begin();
+	aesni_gcm_init(aes_ctx, &data, iv,
+		hash_subkey, assoc, assoclen);
+	if (req->src != req->dst) {
+		while (left) {
+			src = scatterwalk_map(&src_sg_walk);
+			dst = scatterwalk_map(&dst_sg_walk);
+			srclen = scatterwalk_clamp(&src_sg_walk, left);
+			dstlen = scatterwalk_clamp(&dst_sg_walk, left);
+			len = min(srclen, dstlen);
+			if (len) {
+				if (enc)
+					aesni_gcm_enc_update(aes_ctx, &data,
+							     dst, src, len);
+				else
+					aesni_gcm_dec_update(aes_ctx, &data,
+							     dst, src, len);
+			}
+			left -= len;
+
+			scatterwalk_unmap(src);
+			scatterwalk_unmap(dst);
+			scatterwalk_advance(&src_sg_walk, len);
+			scatterwalk_advance(&dst_sg_walk, len);
+			scatterwalk_done(&src_sg_walk, 0, left);
+			scatterwalk_done(&dst_sg_walk, 1, left);
+		}
+	} else {
+		while (left) {
+			dst = src = scatterwalk_map(&src_sg_walk);
+			len = scatterwalk_clamp(&src_sg_walk, left);
+			if (len) {
+				if (enc)
+					aesni_gcm_enc_update(aes_ctx, &data,
+							     src, src, len);
+				else
+					aesni_gcm_dec_update(aes_ctx, &data,
+							     src, src, len);
+			}
+			left -= len;
+			scatterwalk_unmap(src);
+			scatterwalk_advance(&src_sg_walk, len);
+			scatterwalk_done(&src_sg_walk, 1, left);
+		}
+	}
+	aesni_gcm_finalize(aes_ctx, &data, authTag, auth_tag_len);
+	kernel_fpu_end();
+
+	if (!assocmem)
+		scatterwalk_unmap(assoc);
+	else
+		kfree(assocmem);
+
+	if (!enc) {
+		u8 authTagMsg[16];
+
+		/* Copy out original authTag */
+		scatterwalk_map_and_copy(authTagMsg, req->src,
+					 req->assoclen + req->cryptlen -
+					 auth_tag_len,
+					 auth_tag_len, 0);
+
+		/* Compare generated tag with passed in tag. */
+		return crypto_memneq(authTagMsg, authTag, auth_tag_len) ?
+			-EBADMSG : 0;
+	}
+
+	/* Copy in the authTag */
+	scatterwalk_map_and_copy(authTag, req->dst,
+				 req->assoclen + req->cryptlen,
+				 auth_tag_len, 1);
+
+	return 0;
+}
+
 static int gcmaes_encrypt(struct aead_request *req, unsigned int assoclen,
 			  u8 *hash_subkey, u8 *iv, void *aes_ctx)
 {
@@ -753,7 +921,14 @@ static int gcmaes_encrypt(struct aead_request *req, unsigned int assoclen,
 	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
 	struct scatter_walk src_sg_walk;
 	struct scatter_walk dst_sg_walk = {};
+	struct gcm_context_data data AESNI_ALIGN_ATTR;
 
+	if (((struct crypto_aes_ctx *)aes_ctx)->key_length != AES_KEYSIZE_128 ||
+		aesni_gcm_enc_tfm == aesni_gcm_enc ||
+		req->cryptlen < AVX_GEN2_OPTSIZE) {
+		return gcmaes_crypt_by_sg(true, req, assoclen, hash_subkey, iv,
+					  aes_ctx);
+	}
 	if (sg_is_last(req->src) &&
 	    (!PageHighMem(sg_page(req->src)) ||
 	    req->src->offset + req->src->length <= PAGE_SIZE) &&
@@ -782,7 +957,7 @@ static int gcmaes_encrypt(struct aead_request *req, unsigned int assoclen,
 	}
 
 	kernel_fpu_begin();
-	aesni_gcm_enc_tfm(aes_ctx, dst, src, req->cryptlen, iv,
+	aesni_gcm_enc_tfm(aes_ctx, &data, dst, src, req->cryptlen, iv,
 			  hash_subkey, assoc, assoclen,
 			  dst + req->cryptlen, auth_tag_len);
 	kernel_fpu_end();
@@ -817,8 +992,15 @@ static int gcmaes_decrypt(struct aead_request *req, unsigned int assoclen,
 	u8 authTag[16];
 	struct scatter_walk src_sg_walk;
 	struct scatter_walk dst_sg_walk = {};
+	struct gcm_context_data data AESNI_ALIGN_ATTR;
 	int retval = 0;
 
+	if (((struct crypto_aes_ctx *)aes_ctx)->key_length != AES_KEYSIZE_128 ||
+		aesni_gcm_enc_tfm == aesni_gcm_enc ||
+		req->cryptlen < AVX_GEN2_OPTSIZE) {
+		return gcmaes_crypt_by_sg(false, req, assoclen, hash_subkey, iv,
+					  aes_ctx);
+	}
 	tempCipherLen = (unsigned long)(req->cryptlen - auth_tag_len);
 
 	if (sg_is_last(req->src) &&
@@ -849,7 +1031,7 @@ static int gcmaes_decrypt(struct aead_request *req, unsigned int assoclen,
 
 
 	kernel_fpu_begin();
-	aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv,
+	aesni_gcm_dec_tfm(aes_ctx, &data, dst, src, tempCipherLen, iv,
 			  hash_subkey, assoc, assoclen,
 			  authTag, auth_tag_len);
 	kernel_fpu_end();
diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c
index f9eca34301e2..3e0c07cc9124 100644
--- a/arch/x86/crypto/blowfish_glue.c
+++ b/arch/x86/crypto/blowfish_glue.c
@@ -25,13 +25,13 @@
  *
  */
 
-#include <asm/processor.h>
+#include <crypto/algapi.h>
 #include <crypto/blowfish.h>
+#include <crypto/internal/skcipher.h>
 #include <linux/crypto.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/types.h>
-#include <crypto/algapi.h>
 
 /* regular block cipher functions */
 asmlinkage void __blowfish_enc_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src,
@@ -77,20 +77,28 @@ static void blowfish_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 	blowfish_dec_blk(crypto_tfm_ctx(tfm), dst, src);
 }
 
-static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
+static int blowfish_setkey_skcipher(struct crypto_skcipher *tfm,
+				    const u8 *key, unsigned int keylen)
+{
+	return blowfish_setkey(&tfm->base, key, keylen);
+}
+
+static int ecb_crypt(struct skcipher_request *req,
 		     void (*fn)(struct bf_ctx *, u8 *, const u8 *),
 		     void (*fn_4way)(struct bf_ctx *, u8 *, const u8 *))
 {
-	struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	unsigned int bsize = BF_BLOCK_SIZE;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct bf_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	unsigned int nbytes;
 	int err;
 
-	err = blkcipher_walk_virt(desc, walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk->nbytes)) {
-		u8 *wsrc = walk->src.virt.addr;
-		u8 *wdst = walk->dst.virt.addr;
+	while ((nbytes = walk.nbytes)) {
+		u8 *wsrc = walk.src.virt.addr;
+		u8 *wdst = walk.dst.virt.addr;
 
 		/* Process four block batch */
 		if (nbytes >= bsize * 4) {
@@ -116,34 +124,25 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
 		} while (nbytes >= bsize);
 
 done:
-		err = blkcipher_walk_done(desc, walk, nbytes);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	return err;
 }
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, blowfish_enc_blk, blowfish_enc_blk_4way);
+	return ecb_crypt(req, blowfish_enc_blk, blowfish_enc_blk_4way);
 }
 
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, blowfish_dec_blk, blowfish_dec_blk_4way);
+	return ecb_crypt(req, blowfish_dec_blk, blowfish_dec_blk_4way);
 }
 
-static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
+static unsigned int __cbc_encrypt(struct bf_ctx *ctx,
+				  struct skcipher_walk *walk)
 {
-	struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	unsigned int bsize = BF_BLOCK_SIZE;
 	unsigned int nbytes = walk->nbytes;
 	u64 *src = (u64 *)walk->src.virt.addr;
@@ -164,27 +163,27 @@ static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
 	return nbytes;
 }
 
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct bf_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes)) {
-		nbytes = __cbc_encrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		nbytes = __cbc_encrypt(ctx, &walk);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	return err;
 }
 
-static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
+static unsigned int __cbc_decrypt(struct bf_ctx *ctx,
+				  struct skcipher_walk *walk)
 {
-	struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	unsigned int bsize = BF_BLOCK_SIZE;
 	unsigned int nbytes = walk->nbytes;
 	u64 *src = (u64 *)walk->src.virt.addr;
@@ -245,24 +244,25 @@ done:
 	return nbytes;
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct bf_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes)) {
-		nbytes = __cbc_decrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		nbytes = __cbc_decrypt(ctx, &walk);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	return err;
 }
 
-static void ctr_crypt_final(struct bf_ctx *ctx, struct blkcipher_walk *walk)
+static void ctr_crypt_final(struct bf_ctx *ctx, struct skcipher_walk *walk)
 {
 	u8 *ctrblk = walk->iv;
 	u8 keystream[BF_BLOCK_SIZE];
@@ -276,10 +276,8 @@ static void ctr_crypt_final(struct bf_ctx *ctx, struct blkcipher_walk *walk)
 	crypto_inc(ctrblk, BF_BLOCK_SIZE);
 }
 
-static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
-				struct blkcipher_walk *walk)
+static unsigned int __ctr_crypt(struct bf_ctx *ctx, struct skcipher_walk *walk)
 {
-	struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	unsigned int bsize = BF_BLOCK_SIZE;
 	unsigned int nbytes = walk->nbytes;
 	u64 *src = (u64 *)walk->src.virt.addr;
@@ -332,29 +330,30 @@ done:
 	return nbytes;
 }
 
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct bf_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, BF_BLOCK_SIZE);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes) >= BF_BLOCK_SIZE) {
-		nbytes = __ctr_crypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		nbytes = __ctr_crypt(ctx, &walk);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
-	if (walk.nbytes) {
-		ctr_crypt_final(crypto_blkcipher_ctx(desc->tfm), &walk);
-		err = blkcipher_walk_done(desc, &walk, 0);
+	if (nbytes) {
+		ctr_crypt_final(ctx, &walk);
+		err = skcipher_walk_done(&walk, 0);
 	}
 
 	return err;
 }
 
-static struct crypto_alg bf_algs[4] = { {
+static struct crypto_alg bf_cipher_alg = {
 	.cra_name		= "blowfish",
 	.cra_driver_name	= "blowfish-asm",
 	.cra_priority		= 200,
@@ -372,66 +371,50 @@ static struct crypto_alg bf_algs[4] = { {
 			.cia_decrypt		= blowfish_decrypt,
 		}
 	}
-}, {
-	.cra_name		= "ecb(blowfish)",
-	.cra_driver_name	= "ecb-blowfish-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= BF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct bf_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= BF_MIN_KEY_SIZE,
-			.max_keysize	= BF_MAX_KEY_SIZE,
-			.setkey		= blowfish_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
+};
+
+static struct skcipher_alg bf_skcipher_algs[] = {
+	{
+		.base.cra_name		= "ecb(blowfish)",
+		.base.cra_driver_name	= "ecb-blowfish-asm",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= BF_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct bf_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= BF_MIN_KEY_SIZE,
+		.max_keysize		= BF_MAX_KEY_SIZE,
+		.setkey			= blowfish_setkey_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "cbc(blowfish)",
+		.base.cra_driver_name	= "cbc-blowfish-asm",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= BF_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct bf_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= BF_MIN_KEY_SIZE,
+		.max_keysize		= BF_MAX_KEY_SIZE,
+		.ivsize			= BF_BLOCK_SIZE,
+		.setkey			= blowfish_setkey_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "ctr(blowfish)",
+		.base.cra_driver_name	= "ctr-blowfish-asm",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct bf_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= BF_MIN_KEY_SIZE,
+		.max_keysize		= BF_MAX_KEY_SIZE,
+		.ivsize			= BF_BLOCK_SIZE,
+		.chunksize		= BF_BLOCK_SIZE,
+		.setkey			= blowfish_setkey_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
 	},
-}, {
-	.cra_name		= "cbc(blowfish)",
-	.cra_driver_name	= "cbc-blowfish-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= BF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct bf_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= BF_MIN_KEY_SIZE,
-			.max_keysize	= BF_MAX_KEY_SIZE,
-			.ivsize		= BF_BLOCK_SIZE,
-			.setkey		= blowfish_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(blowfish)",
-	.cra_driver_name	= "ctr-blowfish-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct bf_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= BF_MIN_KEY_SIZE,
-			.max_keysize	= BF_MAX_KEY_SIZE,
-			.ivsize		= BF_BLOCK_SIZE,
-			.setkey		= blowfish_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-} };
+};
 
 static bool is_blacklisted_cpu(void)
 {
@@ -456,6 +439,8 @@ MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
 
 static int __init init(void)
 {
+	int err;
+
 	if (!force && is_blacklisted_cpu()) {
 		printk(KERN_INFO
 			"blowfish-x86_64: performance on this CPU "
@@ -464,12 +449,23 @@ static int __init init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(bf_algs, ARRAY_SIZE(bf_algs));
+	err = crypto_register_alg(&bf_cipher_alg);
+	if (err)
+		return err;
+
+	err = crypto_register_skciphers(bf_skcipher_algs,
+					ARRAY_SIZE(bf_skcipher_algs));
+	if (err)
+		crypto_unregister_alg(&bf_cipher_alg);
+
+	return err;
 }
 
 static void __exit fini(void)
 {
-	crypto_unregister_algs(bf_algs, ARRAY_SIZE(bf_algs));
+	crypto_unregister_alg(&bf_cipher_alg);
+	crypto_unregister_skciphers(bf_skcipher_algs,
+				    ARRAY_SIZE(bf_skcipher_algs));
 }
 
 module_init(init);
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index 60907c139c4e..d4992e458f92 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -10,18 +10,15 @@
  *
  */
 
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/crypto.h>
-#include <linux/err.h>
-#include <crypto/ablk_helper.h>
-#include <crypto/algapi.h>
-#include <crypto/ctr.h>
-#include <crypto/lrw.h>
-#include <crypto/xts.h>
-#include <asm/fpu/api.h>
 #include <asm/crypto/camellia.h>
 #include <asm/crypto/glue_helper.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/simd.h>
+#include <crypto/xts.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/types.h>
 
 #define CAMELLIA_AESNI_PARALLEL_BLOCKS 16
 #define CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS 32
@@ -150,413 +147,120 @@ static const struct common_glue_ctx camellia_dec_xts = {
 	} }
 };
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			   unsigned int keylen)
 {
-	return glue_ecb_crypt_128bit(&camellia_enc, desc, dst, src, nbytes);
+	return __camellia_setkey(crypto_skcipher_ctx(tfm), key, keylen,
+				 &tfm->base.crt_flags);
 }
 
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_crypt_128bit(&camellia_dec, desc, dst, src, nbytes);
+	return glue_ecb_req_128bit(&camellia_enc, req);
 }
 
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(camellia_enc_blk), desc,
-				       dst, src, nbytes);
-}
-
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_cbc_decrypt_128bit(&camellia_dec_cbc, desc, dst, src,
-				       nbytes);
-}
-
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ctr_crypt_128bit(&camellia_ctr, desc, dst, src, nbytes);
-}
-
-static inline bool camellia_fpu_begin(bool fpu_enabled, unsigned int nbytes)
-{
-	return glue_fpu_begin(CAMELLIA_BLOCK_SIZE,
-			      CAMELLIA_AESNI_PARALLEL_BLOCKS, NULL, fpu_enabled,
-			      nbytes);
-}
-
-static inline void camellia_fpu_end(bool fpu_enabled)
-{
-	glue_fpu_end(fpu_enabled);
-}
-
-static int camellia_setkey(struct crypto_tfm *tfm, const u8 *in_key,
-			   unsigned int key_len)
-{
-	return __camellia_setkey(crypto_tfm_ctx(tfm), in_key, key_len,
-				 &tfm->crt_flags);
-}
-
-struct crypt_priv {
-	struct camellia_ctx *ctx;
-	bool fpu_enabled;
-};
-
-static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = camellia_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes >= CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS * bsize) {
-		camellia_ecb_enc_32way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS;
-		nbytes -= bsize * CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS;
-	}
-
-	if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
-		camellia_ecb_enc_16way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
-		nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
-	}
-
-	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
-		camellia_enc_blk_2way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
-		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		camellia_enc_blk(ctx->ctx, srcdst, srcdst);
+	return glue_ecb_req_128bit(&camellia_dec, req);
 }
 
-static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = camellia_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes >= CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS * bsize) {
-		camellia_ecb_dec_32way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS;
-		nbytes -= bsize * CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS;
-	}
-
-	if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
-		camellia_ecb_dec_16way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
-		nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
-	}
-
-	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
-		camellia_dec_blk_2way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
-		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		camellia_dec_blk(ctx->ctx, srcdst, srcdst);
+	return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(camellia_enc_blk),
+					   req);
 }
 
-static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->camellia_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	camellia_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
+	return glue_cbc_decrypt_req_128bit(&camellia_dec_cbc, req);
 }
 
-static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->camellia_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	camellia_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
+	return glue_ctr_req_128bit(&camellia_ctr, req);
 }
 
-static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int xts_encrypt(struct skcipher_request *req)
 {
-	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	return glue_xts_crypt_128bit(&camellia_enc_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(camellia_enc_blk),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
+	return glue_xts_req_128bit(&camellia_enc_xts, req,
+				   XTS_TWEAK_CAST(camellia_enc_blk),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int xts_decrypt(struct skcipher_request *req)
 {
-	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	return glue_xts_crypt_128bit(&camellia_dec_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(camellia_enc_blk),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
+	return glue_xts_req_128bit(&camellia_dec_xts, req,
+				   XTS_TWEAK_CAST(camellia_enc_blk),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-static struct crypto_alg cmll_algs[10] = { {
-	.cra_name		= "__ecb-camellia-aesni-avx2",
-	.cra_driver_name	= "__driver-ecb-camellia-aesni-avx2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.setkey		= camellia_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__cbc-camellia-aesni-avx2",
-	.cra_driver_name	= "__driver-cbc-camellia-aesni-avx2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.setkey		= camellia_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__ctr-camellia-aesni-avx2",
-	.cra_driver_name	= "__driver-ctr-camellia-aesni-avx2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct camellia_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= camellia_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-}, {
-	.cra_name		= "__lrw-camellia-aesni-avx2",
-	.cra_driver_name	= "__driver-lrw-camellia-aesni-avx2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_lrw_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_exit		= lrw_camellia_exit_tfm,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE +
-					  CAMELLIA_BLOCK_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE +
-					  CAMELLIA_BLOCK_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= lrw_camellia_setkey,
-			.encrypt	= lrw_encrypt,
-			.decrypt	= lrw_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__xts-camellia-aesni-avx2",
-	.cra_driver_name	= "__driver-xts-camellia-aesni-avx2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_xts_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE * 2,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE * 2,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= xts_camellia_setkey,
-			.encrypt	= xts_encrypt,
-			.decrypt	= xts_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ecb(camellia)",
-	.cra_driver_name	= "ecb-camellia-aesni-avx2",
-	.cra_priority		= 500,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(camellia)",
-	.cra_driver_name	= "cbc-camellia-aesni-avx2",
-	.cra_priority		= 500,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= __ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(camellia)",
-	.cra_driver_name	= "ctr-camellia-aesni-avx2",
-	.cra_priority		= 500,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_encrypt,
-			.geniv		= "chainiv",
-		},
-	},
-}, {
-	.cra_name		= "lrw(camellia)",
-	.cra_driver_name	= "lrw-camellia-aesni-avx2",
-	.cra_priority		= 500,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE +
-					  CAMELLIA_BLOCK_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE +
-					  CAMELLIA_BLOCK_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "xts(camellia)",
-	.cra_driver_name	= "xts-camellia-aesni-avx2",
-	.cra_priority		= 500,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE * 2,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE * 2,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
+static struct skcipher_alg camellia_algs[] = {
+	{
+		.base.cra_name		= "__ecb(camellia)",
+		.base.cra_driver_name	= "__ecb-camellia-aesni-avx2",
+		.base.cra_priority	= 500,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.setkey			= camellia_setkey,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "__cbc(camellia)",
+		.base.cra_driver_name	= "__cbc-camellia-aesni-avx2",
+		.base.cra_priority	= 500,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.ivsize			= CAMELLIA_BLOCK_SIZE,
+		.setkey			= camellia_setkey,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "__ctr(camellia)",
+		.base.cra_driver_name	= "__ctr-camellia-aesni-avx2",
+		.base.cra_priority	= 500,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.ivsize			= CAMELLIA_BLOCK_SIZE,
+		.chunksize		= CAMELLIA_BLOCK_SIZE,
+		.setkey			= camellia_setkey,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+	}, {
+		.base.cra_name		= "__xts(camellia)",
+		.base.cra_driver_name	= "__xts-camellia-aesni-avx2",
+		.base.cra_priority	= 500,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct camellia_xts_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= 2 * CAMELLIA_MAX_KEY_SIZE,
+		.ivsize			= CAMELLIA_BLOCK_SIZE,
+		.setkey			= xts_camellia_setkey,
+		.encrypt		= xts_encrypt,
+		.decrypt		= xts_decrypt,
 	},
-} };
+};
+
+static struct simd_skcipher_alg *camellia_simd_algs[ARRAY_SIZE(camellia_algs)];
 
 static int __init camellia_aesni_init(void)
 {
@@ -576,12 +280,15 @@ static int __init camellia_aesni_init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(cmll_algs, ARRAY_SIZE(cmll_algs));
+	return simd_register_skciphers_compat(camellia_algs,
+					      ARRAY_SIZE(camellia_algs),
+					      camellia_simd_algs);
 }
 
 static void __exit camellia_aesni_fini(void)
 {
-	crypto_unregister_algs(cmll_algs, ARRAY_SIZE(cmll_algs));
+	simd_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs),
+				  camellia_simd_algs);
 }
 
 module_init(camellia_aesni_init);
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index d96429da88eb..d09f6521466a 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -10,18 +10,15 @@
  *
  */
 
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/crypto.h>
-#include <linux/err.h>
-#include <crypto/ablk_helper.h>
-#include <crypto/algapi.h>
-#include <crypto/ctr.h>
-#include <crypto/lrw.h>
-#include <crypto/xts.h>
-#include <asm/fpu/api.h>
 #include <asm/crypto/camellia.h>
 #include <asm/crypto/glue_helper.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/simd.h>
+#include <crypto/xts.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/types.h>
 
 #define CAMELLIA_AESNI_PARALLEL_BLOCKS 16
 
@@ -154,401 +151,142 @@ static const struct common_glue_ctx camellia_dec_xts = {
 	} }
 };
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&camellia_enc, desc, dst, src, nbytes);
-}
-
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			   unsigned int keylen)
 {
-	return glue_ecb_crypt_128bit(&camellia_dec, desc, dst, src, nbytes);
+	return __camellia_setkey(crypto_skcipher_ctx(tfm), key, keylen,
+				 &tfm->base.crt_flags);
 }
 
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(camellia_enc_blk), desc,
-				       dst, src, nbytes);
+	return glue_ecb_req_128bit(&camellia_enc, req);
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_128bit(&camellia_dec_cbc, desc, dst, src,
-				       nbytes);
+	return glue_ecb_req_128bit(&camellia_dec, req);
 }
 
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_ctr_crypt_128bit(&camellia_ctr, desc, dst, src, nbytes);
+	return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(camellia_enc_blk),
+					   req);
 }
 
-static inline bool camellia_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_fpu_begin(CAMELLIA_BLOCK_SIZE,
-			      CAMELLIA_AESNI_PARALLEL_BLOCKS, NULL, fpu_enabled,
-			      nbytes);
+	return glue_cbc_decrypt_req_128bit(&camellia_dec_cbc, req);
 }
 
-static inline void camellia_fpu_end(bool fpu_enabled)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	glue_fpu_end(fpu_enabled);
+	return glue_ctr_req_128bit(&camellia_ctr, req);
 }
 
-static int camellia_setkey(struct crypto_tfm *tfm, const u8 *in_key,
-			   unsigned int key_len)
+int xts_camellia_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			unsigned int keylen)
 {
-	return __camellia_setkey(crypto_tfm_ctx(tfm), in_key, key_len,
-				 &tfm->crt_flags);
+	struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	u32 *flags = &tfm->base.crt_flags;
+	int err;
+
+	err = xts_verify_key(tfm, key, keylen);
+	if (err)
+		return err;
+
+	/* first half of xts-key is for crypt */
+	err = __camellia_setkey(&ctx->crypt_ctx, key, keylen / 2, flags);
+	if (err)
+		return err;
+
+	/* second half of xts-key is for tweak */
+	return __camellia_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2,
+				flags);
 }
+EXPORT_SYMBOL_GPL(xts_camellia_setkey);
 
-struct crypt_priv {
-	struct camellia_ctx *ctx;
-	bool fpu_enabled;
-};
-
-static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int xts_encrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = camellia_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
-		camellia_ecb_enc_16way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
-		nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
-	}
-
-	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
-		camellia_enc_blk_2way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
-		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
-	}
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		camellia_enc_blk(ctx->ctx, srcdst, srcdst);
+	return glue_xts_req_128bit(&camellia_enc_xts, req,
+				   XTS_TWEAK_CAST(camellia_enc_blk),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int xts_decrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = camellia_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
-		camellia_ecb_dec_16way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
-		nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
-	}
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
-		camellia_dec_blk_2way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
-		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		camellia_dec_blk(ctx->ctx, srcdst, srcdst);
+	return glue_xts_req_128bit(&camellia_dec_xts, req,
+				   XTS_TWEAK_CAST(camellia_enc_blk),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[CAMELLIA_AESNI_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->camellia_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	camellia_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[CAMELLIA_AESNI_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->camellia_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	camellia_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-
-	return glue_xts_crypt_128bit(&camellia_enc_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(camellia_enc_blk),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
-}
-
-static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-
-	return glue_xts_crypt_128bit(&camellia_dec_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(camellia_enc_blk),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
-}
-
-static struct crypto_alg cmll_algs[10] = { {
-	.cra_name		= "__ecb-camellia-aesni",
-	.cra_driver_name	= "__driver-ecb-camellia-aesni",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.setkey		= camellia_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__cbc-camellia-aesni",
-	.cra_driver_name	= "__driver-cbc-camellia-aesni",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.setkey		= camellia_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__ctr-camellia-aesni",
-	.cra_driver_name	= "__driver-ctr-camellia-aesni",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct camellia_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= camellia_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-}, {
-	.cra_name		= "__lrw-camellia-aesni",
-	.cra_driver_name	= "__driver-lrw-camellia-aesni",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_lrw_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_exit		= lrw_camellia_exit_tfm,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE +
-					  CAMELLIA_BLOCK_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE +
-					  CAMELLIA_BLOCK_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= lrw_camellia_setkey,
-			.encrypt	= lrw_encrypt,
-			.decrypt	= lrw_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__xts-camellia-aesni",
-	.cra_driver_name	= "__driver-xts-camellia-aesni",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_xts_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE * 2,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE * 2,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= xts_camellia_setkey,
-			.encrypt	= xts_encrypt,
-			.decrypt	= xts_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ecb(camellia)",
-	.cra_driver_name	= "ecb-camellia-aesni",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(camellia)",
-	.cra_driver_name	= "cbc-camellia-aesni",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= __ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(camellia)",
-	.cra_driver_name	= "ctr-camellia-aesni",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_encrypt,
-			.geniv		= "chainiv",
-		},
-	},
-}, {
-	.cra_name		= "lrw(camellia)",
-	.cra_driver_name	= "lrw-camellia-aesni",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE +
-					  CAMELLIA_BLOCK_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE +
-					  CAMELLIA_BLOCK_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "xts(camellia)",
-	.cra_driver_name	= "xts-camellia-aesni",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE * 2,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE * 2,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
+static struct skcipher_alg camellia_algs[] = {
+	{
+		.base.cra_name		= "__ecb(camellia)",
+		.base.cra_driver_name	= "__ecb-camellia-aesni",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.setkey			= camellia_setkey,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "__cbc(camellia)",
+		.base.cra_driver_name	= "__cbc-camellia-aesni",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.ivsize			= CAMELLIA_BLOCK_SIZE,
+		.setkey			= camellia_setkey,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "__ctr(camellia)",
+		.base.cra_driver_name	= "__ctr-camellia-aesni",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.ivsize			= CAMELLIA_BLOCK_SIZE,
+		.chunksize		= CAMELLIA_BLOCK_SIZE,
+		.setkey			= camellia_setkey,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+	}, {
+		.base.cra_name		= "__xts(camellia)",
+		.base.cra_driver_name	= "__xts-camellia-aesni",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct camellia_xts_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= 2 * CAMELLIA_MAX_KEY_SIZE,
+		.ivsize			= CAMELLIA_BLOCK_SIZE,
+		.setkey			= xts_camellia_setkey,
+		.encrypt		= xts_encrypt,
+		.decrypt		= xts_decrypt,
 	},
-} };
+};
+
+static struct simd_skcipher_alg *camellia_simd_algs[ARRAY_SIZE(camellia_algs)];
 
 static int __init camellia_aesni_init(void)
 {
@@ -567,12 +305,15 @@ static int __init camellia_aesni_init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(cmll_algs, ARRAY_SIZE(cmll_algs));
+	return simd_register_skciphers_compat(camellia_algs,
+					      ARRAY_SIZE(camellia_algs),
+					      camellia_simd_algs);
 }
 
 static void __exit camellia_aesni_fini(void)
 {
-	crypto_unregister_algs(cmll_algs, ARRAY_SIZE(cmll_algs));
+	simd_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs),
+				  camellia_simd_algs);
 }
 
 module_init(camellia_aesni_init);
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index af4840ab2a3d..dcd5e0f71b00 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -23,15 +23,12 @@
  *
  */
 
-#include <asm/processor.h>
 #include <asm/unaligned.h>
 #include <linux/crypto.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <crypto/algapi.h>
-#include <crypto/lrw.h>
-#include <crypto/xts.h>
 #include <asm/crypto/camellia.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -1272,13 +1269,19 @@ int __camellia_setkey(struct camellia_ctx *cctx, const unsigned char *key,
 }
 EXPORT_SYMBOL_GPL(__camellia_setkey);
 
-static int camellia_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+static int camellia_setkey(struct crypto_tfm *tfm, const u8 *key,
 			   unsigned int key_len)
 {
-	return __camellia_setkey(crypto_tfm_ctx(tfm), in_key, key_len,
+	return __camellia_setkey(crypto_tfm_ctx(tfm), key, key_len,
 				 &tfm->crt_flags);
 }
 
+static int camellia_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key,
+				    unsigned int key_len)
+{
+	return camellia_setkey(&tfm->base, key, key_len);
+}
+
 void camellia_decrypt_cbc_2way(void *ctx, u128 *dst, const u128 *src)
 {
 	u128 iv = *src;
@@ -1373,188 +1376,33 @@ static const struct common_glue_ctx camellia_dec_cbc = {
 	} }
 };
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&camellia_enc, desc, dst, src, nbytes);
-}
-
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&camellia_dec, desc, dst, src, nbytes);
-}
-
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(camellia_enc_blk), desc,
-				       dst, src, nbytes);
-}
-
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_cbc_decrypt_128bit(&camellia_dec_cbc, desc, dst, src,
-				       nbytes);
-}
-
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ctr_crypt_128bit(&camellia_ctr, desc, dst, src, nbytes);
-}
-
-static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
-{
-	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
-	struct camellia_ctx *ctx = priv;
-	int i;
-
-	while (nbytes >= 2 * bsize) {
-		camellia_enc_blk_2way(ctx, srcdst, srcdst);
-		srcdst += bsize * 2;
-		nbytes -= bsize * 2;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		camellia_enc_blk(ctx, srcdst, srcdst);
-}
-
-static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
-{
-	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
-	struct camellia_ctx *ctx = priv;
-	int i;
-
-	while (nbytes >= 2 * bsize) {
-		camellia_dec_blk_2way(ctx, srcdst, srcdst);
-		srcdst += bsize * 2;
-		nbytes -= bsize * 2;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		camellia_dec_blk(ctx, srcdst, srcdst);
-}
-
-int lrw_camellia_setkey(struct crypto_tfm *tfm, const u8 *key,
-			unsigned int keylen)
-{
-	struct camellia_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	err = __camellia_setkey(&ctx->camellia_ctx, key,
-				keylen - CAMELLIA_BLOCK_SIZE,
-				&tfm->crt_flags);
-	if (err)
-		return err;
-
-	return lrw_init_table(&ctx->lrw_table,
-			      key + keylen - CAMELLIA_BLOCK_SIZE);
-}
-EXPORT_SYMBOL_GPL(lrw_camellia_setkey);
-
-static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[2 * 4];
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &ctx->camellia_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-
-	return lrw_crypt(desc, dst, src, nbytes, &req);
-}
-
-static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[2 * 4];
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &ctx->camellia_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-
-	return lrw_crypt(desc, dst, src, nbytes, &req);
+	return glue_ecb_req_128bit(&camellia_enc, req);
 }
 
-void lrw_camellia_exit_tfm(struct crypto_tfm *tfm)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	struct camellia_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	lrw_free_table(&ctx->lrw_table);
+	return glue_ecb_req_128bit(&camellia_dec, req);
 }
-EXPORT_SYMBOL_GPL(lrw_camellia_exit_tfm);
 
-int xts_camellia_setkey(struct crypto_tfm *tfm, const u8 *key,
-			unsigned int keylen)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	struct camellia_xts_ctx *ctx = crypto_tfm_ctx(tfm);
-	u32 *flags = &tfm->crt_flags;
-	int err;
-
-	err = xts_check_key(tfm, key, keylen);
-	if (err)
-		return err;
-
-	/* first half of xts-key is for crypt */
-	err = __camellia_setkey(&ctx->crypt_ctx, key, keylen / 2, flags);
-	if (err)
-		return err;
-
-	/* second half of xts-key is for tweak */
-	return __camellia_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2,
-				flags);
+	return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(camellia_enc_blk),
+					   req);
 }
-EXPORT_SYMBOL_GPL(xts_camellia_setkey);
 
-static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	le128 buf[2 * 4];
-	struct xts_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.tweak_ctx = &ctx->tweak_ctx,
-		.tweak_fn = XTS_TWEAK_CAST(camellia_enc_blk),
-		.crypt_ctx = &ctx->crypt_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-
-	return xts_crypt(desc, dst, src, nbytes, &req);
+	return glue_cbc_decrypt_req_128bit(&camellia_dec_cbc, req);
 }
 
-static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	le128 buf[2 * 4];
-	struct xts_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.tweak_ctx = &ctx->tweak_ctx,
-		.tweak_fn = XTS_TWEAK_CAST(camellia_enc_blk),
-		.crypt_ctx = &ctx->crypt_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-
-	return xts_crypt(desc, dst, src, nbytes, &req);
+	return glue_ctr_req_128bit(&camellia_ctr, req);
 }
 
-static struct crypto_alg camellia_algs[6] = { {
+static struct crypto_alg camellia_cipher_alg = {
 	.cra_name		= "camellia",
 	.cra_driver_name	= "camellia-asm",
 	.cra_priority		= 200,
@@ -1572,109 +1420,50 @@ static struct crypto_alg camellia_algs[6] = { {
 			.cia_decrypt	 = camellia_decrypt
 		}
 	}
-}, {
-	.cra_name		= "ecb(camellia)",
-	.cra_driver_name	= "ecb-camellia-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.setkey		= camellia_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(camellia)",
-	.cra_driver_name	= "cbc-camellia-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= camellia_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(camellia)",
-	.cra_driver_name	= "ctr-camellia-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct camellia_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= camellia_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-}, {
-	.cra_name		= "lrw(camellia)",
-	.cra_driver_name	= "lrw-camellia-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_lrw_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_exit		= lrw_camellia_exit_tfm,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE +
-						CAMELLIA_BLOCK_SIZE,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE +
-						CAMELLIA_BLOCK_SIZE,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= lrw_camellia_setkey,
-			.encrypt	= lrw_encrypt,
-			.decrypt	= lrw_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "xts(camellia)",
-	.cra_driver_name	= "xts-camellia-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct camellia_xts_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAMELLIA_MIN_KEY_SIZE * 2,
-			.max_keysize	= CAMELLIA_MAX_KEY_SIZE * 2,
-			.ivsize		= CAMELLIA_BLOCK_SIZE,
-			.setkey		= xts_camellia_setkey,
-			.encrypt	= xts_encrypt,
-			.decrypt	= xts_decrypt,
-		},
-	},
-} };
+};
+
+static struct skcipher_alg camellia_skcipher_algs[] = {
+	{
+		.base.cra_name		= "ecb(camellia)",
+		.base.cra_driver_name	= "ecb-camellia-asm",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.setkey			= camellia_setkey_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "cbc(camellia)",
+		.base.cra_driver_name	= "cbc-camellia-asm",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.ivsize			= CAMELLIA_BLOCK_SIZE,
+		.setkey			= camellia_setkey_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "ctr(camellia)",
+		.base.cra_driver_name	= "ctr-camellia-asm",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAMELLIA_MIN_KEY_SIZE,
+		.max_keysize		= CAMELLIA_MAX_KEY_SIZE,
+		.ivsize			= CAMELLIA_BLOCK_SIZE,
+		.chunksize		= CAMELLIA_BLOCK_SIZE,
+		.setkey			= camellia_setkey_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+	}
+};
 
 static bool is_blacklisted_cpu(void)
 {
@@ -1700,6 +1489,8 @@ MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
 
 static int __init init(void)
 {
+	int err;
+
 	if (!force && is_blacklisted_cpu()) {
 		printk(KERN_INFO
 			"camellia-x86_64: performance on this CPU "
@@ -1708,12 +1499,23 @@ static int __init init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(camellia_algs, ARRAY_SIZE(camellia_algs));
+	err = crypto_register_alg(&camellia_cipher_alg);
+	if (err)
+		return err;
+
+	err = crypto_register_skciphers(camellia_skcipher_algs,
+					ARRAY_SIZE(camellia_skcipher_algs));
+	if (err)
+		crypto_unregister_alg(&camellia_cipher_alg);
+
+	return err;
 }
 
 static void __exit fini(void)
 {
-	crypto_unregister_algs(camellia_algs, ARRAY_SIZE(camellia_algs));
+	crypto_unregister_alg(&camellia_cipher_alg);
+	crypto_unregister_skciphers(camellia_skcipher_algs,
+				    ARRAY_SIZE(camellia_skcipher_algs));
 }
 
 module_init(init);
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index dbea6020ffe7..41034745d6a2 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -21,18 +21,14 @@
  *
  */
 
-#include <linux/module.h>
-#include <linux/hardirq.h>
-#include <linux/types.h>
-#include <linux/crypto.h>
-#include <linux/err.h>
-#include <crypto/ablk_helper.h>
+#include <asm/crypto/glue_helper.h>
 #include <crypto/algapi.h>
 #include <crypto/cast5.h>
-#include <crypto/cryptd.h>
-#include <crypto/ctr.h>
-#include <asm/fpu/api.h>
-#include <asm/crypto/glue_helper.h>
+#include <crypto/internal/simd.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/types.h>
 
 #define CAST5_PARALLEL_BLOCKS 16
 
@@ -45,10 +41,17 @@ asmlinkage void cast5_cbc_dec_16way(struct cast5_ctx *ctx, u8 *dst,
 asmlinkage void cast5_ctr_16way(struct cast5_ctx *ctx, u8 *dst, const u8 *src,
 				__be64 *iv);
 
-static inline bool cast5_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+static int cast5_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	return cast5_setkey(&tfm->base, key, keylen);
+}
+
+static inline bool cast5_fpu_begin(bool fpu_enabled, struct skcipher_walk *walk,
+				   unsigned int nbytes)
 {
 	return glue_fpu_begin(CAST5_BLOCK_SIZE, CAST5_PARALLEL_BLOCKS,
-			      NULL, fpu_enabled, nbytes);
+			      walk, fpu_enabled, nbytes);
 }
 
 static inline void cast5_fpu_end(bool fpu_enabled)
@@ -56,29 +59,28 @@ static inline void cast5_fpu_end(bool fpu_enabled)
 	return glue_fpu_end(fpu_enabled);
 }
 
-static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
-		     bool enc)
+static int ecb_crypt(struct skcipher_request *req, bool enc)
 {
 	bool fpu_enabled = false;
-	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
 	const unsigned int bsize = CAST5_BLOCK_SIZE;
 	unsigned int nbytes;
 	void (*fn)(struct cast5_ctx *ctx, u8 *dst, const u8 *src);
 	int err;
 
-	fn = (enc) ? cast5_ecb_enc_16way : cast5_ecb_dec_16way;
-
-	err = blkcipher_walk_virt(desc, walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk->nbytes)) {
-		u8 *wsrc = walk->src.virt.addr;
-		u8 *wdst = walk->dst.virt.addr;
+	while ((nbytes = walk.nbytes)) {
+		u8 *wsrc = walk.src.virt.addr;
+		u8 *wdst = walk.dst.virt.addr;
 
-		fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+		fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes);
 
 		/* Process multi-block batch */
 		if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
+			fn = (enc) ? cast5_ecb_enc_16way : cast5_ecb_dec_16way;
 			do {
 				fn(ctx, wdst, wsrc);
 
@@ -103,76 +105,58 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
 		} while (nbytes >= bsize);
 
 done:
-		err = blkcipher_walk_done(desc, walk, nbytes);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	cast5_fpu_end(fpu_enabled);
 	return err;
 }
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, true);
+	return ecb_crypt(req, true);
 }
 
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, false);
+	return ecb_crypt(req, false);
 }
 
-static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	const unsigned int bsize = CAST5_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u64 *src = (u64 *)walk->src.virt.addr;
-	u64 *dst = (u64 *)walk->dst.virt.addr;
-	u64 *iv = (u64 *)walk->iv;
-
-	do {
-		*dst = *src ^ *iv;
-		__cast5_encrypt(ctx, (u8 *)dst, (u8 *)dst);
-		iv = dst;
-
-		src += 1;
-		dst += 1;
-		nbytes -= bsize;
-	} while (nbytes >= bsize);
-
-	*(u64 *)walk->iv = *iv;
-	return nbytes;
-}
-
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes)) {
-		nbytes = __cbc_encrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		u64 *src = (u64 *)walk.src.virt.addr;
+		u64 *dst = (u64 *)walk.dst.virt.addr;
+		u64 *iv = (u64 *)walk.iv;
+
+		do {
+			*dst = *src ^ *iv;
+			__cast5_encrypt(ctx, (u8 *)dst, (u8 *)dst);
+			iv = dst;
+			src++;
+			dst++;
+			nbytes -= bsize;
+		} while (nbytes >= bsize);
+
+		*(u64 *)walk.iv = *iv;
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	return err;
 }
 
-static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
+static unsigned int __cbc_decrypt(struct cast5_ctx *ctx,
+				  struct skcipher_walk *walk)
 {
-	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	const unsigned int bsize = CAST5_BLOCK_SIZE;
 	unsigned int nbytes = walk->nbytes;
 	u64 *src = (u64 *)walk->src.virt.addr;
@@ -224,31 +208,29 @@ done:
 	return nbytes;
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm);
 	bool fpu_enabled = false;
-	struct blkcipher_walk walk;
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes)) {
-		fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
-		nbytes = __cbc_decrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes);
+		nbytes = __cbc_decrypt(ctx, &walk);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	cast5_fpu_end(fpu_enabled);
 	return err;
 }
 
-static void ctr_crypt_final(struct blkcipher_desc *desc,
-			    struct blkcipher_walk *walk)
+static void ctr_crypt_final(struct skcipher_walk *walk, struct cast5_ctx *ctx)
 {
-	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	u8 *ctrblk = walk->iv;
 	u8 keystream[CAST5_BLOCK_SIZE];
 	u8 *src = walk->src.virt.addr;
@@ -261,10 +243,9 @@ static void ctr_crypt_final(struct blkcipher_desc *desc,
 	crypto_inc(ctrblk, CAST5_BLOCK_SIZE);
 }
 
-static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
-				struct blkcipher_walk *walk)
+static unsigned int __ctr_crypt(struct skcipher_walk *walk,
+				struct cast5_ctx *ctx)
 {
-	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	const unsigned int bsize = CAST5_BLOCK_SIZE;
 	unsigned int nbytes = walk->nbytes;
 	u64 *src = (u64 *)walk->src.virt.addr;
@@ -307,162 +288,80 @@ done:
 	return nbytes;
 }
 
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
+static int ctr_crypt(struct skcipher_request *req)
 {
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm);
 	bool fpu_enabled = false;
-	struct blkcipher_walk walk;
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, CAST5_BLOCK_SIZE);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) {
-		fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
-		nbytes = __ctr_crypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes);
+		nbytes = __ctr_crypt(&walk, ctx);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	cast5_fpu_end(fpu_enabled);
 
 	if (walk.nbytes) {
-		ctr_crypt_final(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		ctr_crypt_final(&walk, ctx);
+		err = skcipher_walk_done(&walk, 0);
 	}
 
 	return err;
 }
 
+static struct skcipher_alg cast5_algs[] = {
+	{
+		.base.cra_name		= "__ecb(cast5)",
+		.base.cra_driver_name	= "__ecb-cast5-avx",
+		.base.cra_priority	= 200,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAST5_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct cast5_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAST5_MIN_KEY_SIZE,
+		.max_keysize		= CAST5_MAX_KEY_SIZE,
+		.setkey			= cast5_setkey_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "__cbc(cast5)",
+		.base.cra_driver_name	= "__cbc-cast5-avx",
+		.base.cra_priority	= 200,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAST5_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct cast5_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAST5_MIN_KEY_SIZE,
+		.max_keysize		= CAST5_MAX_KEY_SIZE,
+		.ivsize			= CAST5_BLOCK_SIZE,
+		.setkey			= cast5_setkey_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "__ctr(cast5)",
+		.base.cra_driver_name	= "__ctr-cast5-avx",
+		.base.cra_priority	= 200,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct cast5_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAST5_MIN_KEY_SIZE,
+		.max_keysize		= CAST5_MAX_KEY_SIZE,
+		.ivsize			= CAST5_BLOCK_SIZE,
+		.chunksize		= CAST5_BLOCK_SIZE,
+		.setkey			= cast5_setkey_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+	}
+};
 
-static struct crypto_alg cast5_algs[6] = { {
-	.cra_name		= "__ecb-cast5-avx",
-	.cra_driver_name	= "__driver-ecb-cast5-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAST5_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct cast5_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAST5_MIN_KEY_SIZE,
-			.max_keysize	= CAST5_MAX_KEY_SIZE,
-			.setkey		= cast5_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__cbc-cast5-avx",
-	.cra_driver_name	= "__driver-cbc-cast5-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAST5_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct cast5_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAST5_MIN_KEY_SIZE,
-			.max_keysize	= CAST5_MAX_KEY_SIZE,
-			.setkey		= cast5_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__ctr-cast5-avx",
-	.cra_driver_name	= "__driver-ctr-cast5-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct cast5_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAST5_MIN_KEY_SIZE,
-			.max_keysize	= CAST5_MAX_KEY_SIZE,
-			.ivsize		= CAST5_BLOCK_SIZE,
-			.setkey		= cast5_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-}, {
-	.cra_name		= "ecb(cast5)",
-	.cra_driver_name	= "ecb-cast5-avx",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAST5_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAST5_MIN_KEY_SIZE,
-			.max_keysize	= CAST5_MAX_KEY_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(cast5)",
-	.cra_driver_name	= "cbc-cast5-avx",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAST5_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAST5_MIN_KEY_SIZE,
-			.max_keysize	= CAST5_MAX_KEY_SIZE,
-			.ivsize		= CAST5_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= __ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(cast5)",
-	.cra_driver_name	= "ctr-cast5-avx",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAST5_MIN_KEY_SIZE,
-			.max_keysize	= CAST5_MAX_KEY_SIZE,
-			.ivsize		= CAST5_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_encrypt,
-			.geniv		= "chainiv",
-		},
-	},
-} };
+static struct simd_skcipher_alg *cast5_simd_algs[ARRAY_SIZE(cast5_algs)];
 
 static int __init cast5_init(void)
 {
@@ -474,12 +373,15 @@ static int __init cast5_init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(cast5_algs, ARRAY_SIZE(cast5_algs));
+	return simd_register_skciphers_compat(cast5_algs,
+					      ARRAY_SIZE(cast5_algs),
+					      cast5_simd_algs);
 }
 
 static void __exit cast5_exit(void)
 {
-	crypto_unregister_algs(cast5_algs, ARRAY_SIZE(cast5_algs));
+	simd_unregister_skciphers(cast5_algs, ARRAY_SIZE(cast5_algs),
+				  cast5_simd_algs);
 }
 
 module_init(cast5_init);
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 50e684768c55..9fb66b5e94b2 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -24,19 +24,13 @@
  */
 
 #include <linux/module.h>
-#include <linux/hardirq.h>
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
-#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
 #include <crypto/cast6.h>
-#include <crypto/cryptd.h>
-#include <crypto/b128ops.h>
-#include <crypto/ctr.h>
-#include <crypto/lrw.h>
+#include <crypto/internal/simd.h>
 #include <crypto/xts.h>
-#include <asm/fpu/api.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAST6_PARALLEL_BLOCKS 8
@@ -56,6 +50,12 @@ asmlinkage void cast6_xts_enc_8way(struct cast6_ctx *ctx, u8 *dst,
 asmlinkage void cast6_xts_dec_8way(struct cast6_ctx *ctx, u8 *dst,
 				   const u8 *src, le128 *iv);
 
+static int cast6_setkey_skcipher(struct crypto_skcipher *tfm,
+				 const u8 *key, unsigned int keylen)
+{
+	return cast6_setkey(&tfm->base, key, keylen);
+}
+
 static void cast6_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv)
 {
 	glue_xts_crypt_128bit_one(ctx, dst, src, iv,
@@ -157,164 +157,30 @@ static const struct common_glue_ctx cast6_dec_xts = {
 	} }
 };
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&cast6_enc, desc, dst, src, nbytes);
-}
-
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&cast6_dec, desc, dst, src, nbytes);
-}
-
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(__cast6_encrypt), desc,
-				       dst, src, nbytes);
-}
-
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_cbc_decrypt_128bit(&cast6_dec_cbc, desc, dst, src,
-				       nbytes);
-}
-
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ctr_crypt_128bit(&cast6_ctr, desc, dst, src, nbytes);
+	return glue_ecb_req_128bit(&cast6_enc, req);
 }
 
-static inline bool cast6_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_fpu_begin(CAST6_BLOCK_SIZE, CAST6_PARALLEL_BLOCKS,
-			      NULL, fpu_enabled, nbytes);
+	return glue_ecb_req_128bit(&cast6_dec, req);
 }
 
-static inline void cast6_fpu_end(bool fpu_enabled)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	glue_fpu_end(fpu_enabled);
+	return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(__cast6_encrypt),
+					   req);
 }
 
-struct crypt_priv {
-	struct cast6_ctx *ctx;
-	bool fpu_enabled;
-};
-
-static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = CAST6_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes == bsize * CAST6_PARALLEL_BLOCKS) {
-		cast6_ecb_enc_8way(ctx->ctx, srcdst, srcdst);
-		return;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		__cast6_encrypt(ctx->ctx, srcdst, srcdst);
+	return glue_cbc_decrypt_req_128bit(&cast6_dec_cbc, req);
 }
 
-static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = CAST6_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes == bsize * CAST6_PARALLEL_BLOCKS) {
-		cast6_ecb_dec_8way(ctx->ctx, srcdst, srcdst);
-		return;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		__cast6_decrypt(ctx->ctx, srcdst, srcdst);
-}
-
-struct cast6_lrw_ctx {
-	struct lrw_table_ctx lrw_table;
-	struct cast6_ctx cast6_ctx;
-};
-
-static int lrw_cast6_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen)
-{
-	struct cast6_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	err = __cast6_setkey(&ctx->cast6_ctx, key, keylen - CAST6_BLOCK_SIZE,
-			     &tfm->crt_flags);
-	if (err)
-		return err;
-
-	return lrw_init_table(&ctx->lrw_table, key + keylen - CAST6_BLOCK_SIZE);
-}
-
-static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct cast6_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[CAST6_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->cast6_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	cast6_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct cast6_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[CAST6_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->cast6_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	cast6_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static void lrw_exit_tfm(struct crypto_tfm *tfm)
-{
-	struct cast6_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	lrw_free_table(&ctx->lrw_table);
+	return glue_ctr_req_128bit(&cast6_ctr, req);
 }
 
 struct cast6_xts_ctx {
@@ -322,14 +188,14 @@ struct cast6_xts_ctx {
 	struct cast6_ctx crypt_ctx;
 };
 
-static int xts_cast6_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen)
+static int xts_cast6_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			    unsigned int keylen)
 {
-	struct cast6_xts_ctx *ctx = crypto_tfm_ctx(tfm);
-	u32 *flags = &tfm->crt_flags;
+	struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	u32 *flags = &tfm->base.crt_flags;
 	int err;
 
-	err = xts_check_key(tfm, key, keylen);
+	err = xts_verify_key(tfm, key, keylen);
 	if (err)
 		return err;
 
@@ -343,245 +209,87 @@ static int xts_cast6_setkey(struct crypto_tfm *tfm, const u8 *key,
 			      flags);
 }
 
-static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int xts_encrypt(struct skcipher_request *req)
 {
-	struct cast6_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	return glue_xts_crypt_128bit(&cast6_enc_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(__cast6_encrypt),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
+	return glue_xts_req_128bit(&cast6_enc_xts, req,
+				   XTS_TWEAK_CAST(__cast6_encrypt),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int xts_decrypt(struct skcipher_request *req)
 {
-	struct cast6_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	return glue_xts_crypt_128bit(&cast6_dec_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(__cast6_encrypt),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
+	return glue_xts_req_128bit(&cast6_dec_xts, req,
+				   XTS_TWEAK_CAST(__cast6_encrypt),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-static struct crypto_alg cast6_algs[10] = { {
-	.cra_name		= "__ecb-cast6-avx",
-	.cra_driver_name	= "__driver-ecb-cast6-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAST6_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct cast6_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAST6_MIN_KEY_SIZE,
-			.max_keysize	= CAST6_MAX_KEY_SIZE,
-			.setkey		= cast6_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__cbc-cast6-avx",
-	.cra_driver_name	= "__driver-cbc-cast6-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAST6_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct cast6_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAST6_MIN_KEY_SIZE,
-			.max_keysize	= CAST6_MAX_KEY_SIZE,
-			.setkey		= cast6_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__ctr-cast6-avx",
-	.cra_driver_name	= "__driver-ctr-cast6-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct cast6_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAST6_MIN_KEY_SIZE,
-			.max_keysize	= CAST6_MAX_KEY_SIZE,
-			.ivsize		= CAST6_BLOCK_SIZE,
-			.setkey		= cast6_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-}, {
-	.cra_name		= "__lrw-cast6-avx",
-	.cra_driver_name	= "__driver-lrw-cast6-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAST6_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct cast6_lrw_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_exit		= lrw_exit_tfm,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAST6_MIN_KEY_SIZE +
-					  CAST6_BLOCK_SIZE,
-			.max_keysize	= CAST6_MAX_KEY_SIZE +
-					  CAST6_BLOCK_SIZE,
-			.ivsize		= CAST6_BLOCK_SIZE,
-			.setkey		= lrw_cast6_setkey,
-			.encrypt	= lrw_encrypt,
-			.decrypt	= lrw_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__xts-cast6-avx",
-	.cra_driver_name	= "__driver-xts-cast6-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= CAST6_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct cast6_xts_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= CAST6_MIN_KEY_SIZE * 2,
-			.max_keysize	= CAST6_MAX_KEY_SIZE * 2,
-			.ivsize		= CAST6_BLOCK_SIZE,
-			.setkey		= xts_cast6_setkey,
-			.encrypt	= xts_encrypt,
-			.decrypt	= xts_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ecb(cast6)",
-	.cra_driver_name	= "ecb-cast6-avx",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAST6_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAST6_MIN_KEY_SIZE,
-			.max_keysize	= CAST6_MAX_KEY_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(cast6)",
-	.cra_driver_name	= "cbc-cast6-avx",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAST6_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAST6_MIN_KEY_SIZE,
-			.max_keysize	= CAST6_MAX_KEY_SIZE,
-			.ivsize		= CAST6_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= __ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(cast6)",
-	.cra_driver_name	= "ctr-cast6-avx",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAST6_MIN_KEY_SIZE,
-			.max_keysize	= CAST6_MAX_KEY_SIZE,
-			.ivsize		= CAST6_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_encrypt,
-			.geniv		= "chainiv",
-		},
-	},
-}, {
-	.cra_name		= "lrw(cast6)",
-	.cra_driver_name	= "lrw-cast6-avx",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAST6_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAST6_MIN_KEY_SIZE +
-					  CAST6_BLOCK_SIZE,
-			.max_keysize	= CAST6_MAX_KEY_SIZE +
-					  CAST6_BLOCK_SIZE,
-			.ivsize		= CAST6_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "xts(cast6)",
-	.cra_driver_name	= "xts-cast6-avx",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CAST6_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= CAST6_MIN_KEY_SIZE * 2,
-			.max_keysize	= CAST6_MAX_KEY_SIZE * 2,
-			.ivsize		= CAST6_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
+static struct skcipher_alg cast6_algs[] = {
+	{
+		.base.cra_name		= "__ecb(cast6)",
+		.base.cra_driver_name	= "__ecb-cast6-avx",
+		.base.cra_priority	= 200,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAST6_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct cast6_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAST6_MIN_KEY_SIZE,
+		.max_keysize		= CAST6_MAX_KEY_SIZE,
+		.setkey			= cast6_setkey_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "__cbc(cast6)",
+		.base.cra_driver_name	= "__cbc-cast6-avx",
+		.base.cra_priority	= 200,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAST6_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct cast6_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAST6_MIN_KEY_SIZE,
+		.max_keysize		= CAST6_MAX_KEY_SIZE,
+		.ivsize			= CAST6_BLOCK_SIZE,
+		.setkey			= cast6_setkey_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "__ctr(cast6)",
+		.base.cra_driver_name	= "__ctr-cast6-avx",
+		.base.cra_priority	= 200,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct cast6_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= CAST6_MIN_KEY_SIZE,
+		.max_keysize		= CAST6_MAX_KEY_SIZE,
+		.ivsize			= CAST6_BLOCK_SIZE,
+		.chunksize		= CAST6_BLOCK_SIZE,
+		.setkey			= cast6_setkey_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+	}, {
+		.base.cra_name		= "__xts(cast6)",
+		.base.cra_driver_name	= "__xts-cast6-avx",
+		.base.cra_priority	= 200,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= CAST6_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct cast6_xts_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * CAST6_MIN_KEY_SIZE,
+		.max_keysize		= 2 * CAST6_MAX_KEY_SIZE,
+		.ivsize			= CAST6_BLOCK_SIZE,
+		.setkey			= xts_cast6_setkey,
+		.encrypt		= xts_encrypt,
+		.decrypt		= xts_decrypt,
 	},
-} };
+};
+
+static struct simd_skcipher_alg *cast6_simd_algs[ARRAY_SIZE(cast6_algs)];
 
 static int __init cast6_init(void)
 {
@@ -593,12 +301,15 @@ static int __init cast6_init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(cast6_algs, ARRAY_SIZE(cast6_algs));
+	return simd_register_skciphers_compat(cast6_algs,
+					      ARRAY_SIZE(cast6_algs),
+					      cast6_simd_algs);
 }
 
 static void __exit cast6_exit(void)
 {
-	crypto_unregister_algs(cast6_algs, ARRAY_SIZE(cast6_algs));
+	simd_unregister_skciphers(cast6_algs, ARRAY_SIZE(cast6_algs),
+				  cast6_simd_algs);
 }
 
 module_init(cast6_init);
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
index 30c0a37f4882..5c610d4ef9fc 100644
--- a/arch/x86/crypto/des3_ede_glue.c
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -20,13 +20,13 @@
  *
  */
 
-#include <asm/processor.h>
+#include <crypto/algapi.h>
 #include <crypto/des.h>
+#include <crypto/internal/skcipher.h>
 #include <linux/crypto.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/types.h>
-#include <crypto/algapi.h>
 
 struct des3_ede_x86_ctx {
 	u32 enc_expkey[DES3_EDE_EXPKEY_WORDS];
@@ -83,18 +83,18 @@ static void des3_ede_x86_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 	des3_ede_dec_blk(crypto_tfm_ctx(tfm), dst, src);
 }
 
-static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
-		     const u32 *expkey)
+static int ecb_crypt(struct skcipher_request *req, const u32 *expkey)
 {
-	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+	const unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+	struct skcipher_walk walk;
 	unsigned int nbytes;
 	int err;
 
-	err = blkcipher_walk_virt(desc, walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk->nbytes)) {
-		u8 *wsrc = walk->src.virt.addr;
-		u8 *wdst = walk->dst.virt.addr;
+	while ((nbytes = walk.nbytes)) {
+		u8 *wsrc = walk.src.virt.addr;
+		u8 *wdst = walk.dst.virt.addr;
 
 		/* Process four block batch */
 		if (nbytes >= bsize * 3) {
@@ -121,36 +121,31 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
 		} while (nbytes >= bsize);
 
 done:
-		err = blkcipher_walk_done(desc, walk, nbytes);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	return err;
 }
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, ctx->enc_expkey);
+	return ecb_crypt(req, ctx->enc_expkey);
 }
 
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, ctx->dec_expkey);
+	return ecb_crypt(req, ctx->dec_expkey);
 }
 
-static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
+static unsigned int __cbc_encrypt(struct des3_ede_x86_ctx *ctx,
+				  struct skcipher_walk *walk)
 {
-	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
 	unsigned int nbytes = walk->nbytes;
 	u64 *src = (u64 *)walk->src.virt.addr;
@@ -171,27 +166,27 @@ static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
 	return nbytes;
 }
 
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes)) {
-		nbytes = __cbc_encrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		nbytes = __cbc_encrypt(ctx, &walk);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	return err;
 }
 
-static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
+static unsigned int __cbc_decrypt(struct des3_ede_x86_ctx *ctx,
+				  struct skcipher_walk *walk)
 {
-	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
 	unsigned int nbytes = walk->nbytes;
 	u64 *src = (u64 *)walk->src.virt.addr;
@@ -250,25 +245,26 @@ done:
 	return nbytes;
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes)) {
-		nbytes = __cbc_decrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		nbytes = __cbc_decrypt(ctx, &walk);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	return err;
 }
 
 static void ctr_crypt_final(struct des3_ede_x86_ctx *ctx,
-			    struct blkcipher_walk *walk)
+			    struct skcipher_walk *walk)
 {
 	u8 *ctrblk = walk->iv;
 	u8 keystream[DES3_EDE_BLOCK_SIZE];
@@ -282,10 +278,9 @@ static void ctr_crypt_final(struct des3_ede_x86_ctx *ctx,
 	crypto_inc(ctrblk, DES3_EDE_BLOCK_SIZE);
 }
 
-static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
-				struct blkcipher_walk *walk)
+static unsigned int __ctr_crypt(struct des3_ede_x86_ctx *ctx,
+				struct skcipher_walk *walk)
 {
-	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
 	unsigned int nbytes = walk->nbytes;
 	__be64 *src = (__be64 *)walk->src.virt.addr;
@@ -333,23 +328,24 @@ done:
 	return nbytes;
 }
 
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, DES3_EDE_BLOCK_SIZE);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes) >= DES3_EDE_BLOCK_SIZE) {
-		nbytes = __ctr_crypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		nbytes = __ctr_crypt(ctx, &walk);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
-	if (walk.nbytes) {
-		ctr_crypt_final(crypto_blkcipher_ctx(desc->tfm), &walk);
-		err = blkcipher_walk_done(desc, &walk, 0);
+	if (nbytes) {
+		ctr_crypt_final(ctx, &walk);
+		err = skcipher_walk_done(&walk, 0);
 	}
 
 	return err;
@@ -381,7 +377,14 @@ static int des3_ede_x86_setkey(struct crypto_tfm *tfm, const u8 *key,
 	return 0;
 }
 
-static struct crypto_alg des3_ede_algs[4] = { {
+static int des3_ede_x86_setkey_skcipher(struct crypto_skcipher *tfm,
+					const u8 *key,
+					unsigned int keylen)
+{
+	return des3_ede_x86_setkey(&tfm->base, key, keylen);
+}
+
+static struct crypto_alg des3_ede_cipher = {
 	.cra_name		= "des3_ede",
 	.cra_driver_name	= "des3_ede-asm",
 	.cra_priority		= 200,
@@ -399,66 +402,50 @@ static struct crypto_alg des3_ede_algs[4] = { {
 			.cia_decrypt		= des3_ede_x86_decrypt,
 		}
 	}
-}, {
-	.cra_name		= "ecb(des3_ede)",
-	.cra_driver_name	= "ecb-des3_ede-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.setkey		= des3_ede_x86_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(des3_ede)",
-	.cra_driver_name	= "cbc-des3_ede-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.ivsize		= DES3_EDE_BLOCK_SIZE,
-			.setkey		= des3_ede_x86_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(des3_ede)",
-	.cra_driver_name	= "ctr-des3_ede-asm",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= DES3_EDE_KEY_SIZE,
-			.max_keysize	= DES3_EDE_KEY_SIZE,
-			.ivsize		= DES3_EDE_BLOCK_SIZE,
-			.setkey		= des3_ede_x86_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-} };
+};
+
+static struct skcipher_alg des3_ede_skciphers[] = {
+	{
+		.base.cra_name		= "ecb(des3_ede)",
+		.base.cra_driver_name	= "ecb-des3_ede-asm",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct des3_ede_x86_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= DES3_EDE_KEY_SIZE,
+		.max_keysize		= DES3_EDE_KEY_SIZE,
+		.setkey			= des3_ede_x86_setkey_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "cbc(des3_ede)",
+		.base.cra_driver_name	= "cbc-des3_ede-asm",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct des3_ede_x86_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= DES3_EDE_KEY_SIZE,
+		.max_keysize		= DES3_EDE_KEY_SIZE,
+		.ivsize			= DES3_EDE_BLOCK_SIZE,
+		.setkey			= des3_ede_x86_setkey_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "ctr(des3_ede)",
+		.base.cra_driver_name	= "ctr-des3_ede-asm",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct des3_ede_x86_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= DES3_EDE_KEY_SIZE,
+		.max_keysize		= DES3_EDE_KEY_SIZE,
+		.ivsize			= DES3_EDE_BLOCK_SIZE,
+		.chunksize		= DES3_EDE_BLOCK_SIZE,
+		.setkey			= des3_ede_x86_setkey_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+	}
+};
 
 static bool is_blacklisted_cpu(void)
 {
@@ -483,17 +470,30 @@ MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
 
 static int __init des3_ede_x86_init(void)
 {
+	int err;
+
 	if (!force && is_blacklisted_cpu()) {
 		pr_info("des3_ede-x86_64: performance on this CPU would be suboptimal: disabling des3_ede-x86_64.\n");
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(des3_ede_algs, ARRAY_SIZE(des3_ede_algs));
+	err = crypto_register_alg(&des3_ede_cipher);
+	if (err)
+		return err;
+
+	err = crypto_register_skciphers(des3_ede_skciphers,
+					ARRAY_SIZE(des3_ede_skciphers));
+	if (err)
+		crypto_unregister_alg(&des3_ede_cipher);
+
+	return err;
 }
 
 static void __exit des3_ede_x86_fini(void)
 {
-	crypto_unregister_algs(des3_ede_algs, ARRAY_SIZE(des3_ede_algs));
+	crypto_unregister_alg(&des3_ede_cipher);
+	crypto_unregister_skciphers(des3_ede_skciphers,
+				    ARRAY_SIZE(des3_ede_skciphers));
 }
 
 module_init(des3_ede_x86_init);
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
index d61e57960fe0..a78ef99a9981 100644
--- a/arch/x86/crypto/glue_helper.c
+++ b/arch/x86/crypto/glue_helper.c
@@ -29,313 +29,212 @@
 #include <crypto/b128ops.h>
 #include <crypto/gf128mul.h>
 #include <crypto/internal/skcipher.h>
-#include <crypto/lrw.h>
 #include <crypto/xts.h>
 #include <asm/crypto/glue_helper.h>
 
-static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
-				   struct blkcipher_desc *desc,
-				   struct blkcipher_walk *walk)
+int glue_ecb_req_128bit(const struct common_glue_ctx *gctx,
+			struct skcipher_request *req)
 {
-	void *ctx = crypto_blkcipher_ctx(desc->tfm);
+	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
 	const unsigned int bsize = 128 / 8;
-	unsigned int nbytes, i, func_bytes;
+	struct skcipher_walk walk;
 	bool fpu_enabled = false;
+	unsigned int nbytes;
 	int err;
 
-	err = blkcipher_walk_virt(desc, walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((nbytes = walk->nbytes)) {
-		u8 *wsrc = walk->src.virt.addr;
-		u8 *wdst = walk->dst.virt.addr;
+	while ((nbytes = walk.nbytes)) {
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+		unsigned int func_bytes;
+		unsigned int i;
 
 		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					     desc, fpu_enabled, nbytes);
-
+					     &walk, fpu_enabled, nbytes);
 		for (i = 0; i < gctx->num_funcs; i++) {
 			func_bytes = bsize * gctx->funcs[i].num_blocks;
 
-			/* Process multi-block batch */
-			if (nbytes >= func_bytes) {
-				do {
-					gctx->funcs[i].fn_u.ecb(ctx, wdst,
-								wsrc);
+			if (nbytes < func_bytes)
+				continue;
 
-					wsrc += func_bytes;
-					wdst += func_bytes;
-					nbytes -= func_bytes;
-				} while (nbytes >= func_bytes);
+			/* Process multi-block batch */
+			do {
+				gctx->funcs[i].fn_u.ecb(ctx, dst, src);
+				src += func_bytes;
+				dst += func_bytes;
+				nbytes -= func_bytes;
+			} while (nbytes >= func_bytes);
 
-				if (nbytes < bsize)
-					goto done;
-			}
+			if (nbytes < bsize)
+				break;
 		}
-
-done:
-		err = blkcipher_walk_done(desc, walk, nbytes);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	glue_fpu_end(fpu_enabled);
 	return err;
 }
+EXPORT_SYMBOL_GPL(glue_ecb_req_128bit);
 
-int glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
-			  struct blkcipher_desc *desc, struct scatterlist *dst,
-			  struct scatterlist *src, unsigned int nbytes)
+int glue_cbc_encrypt_req_128bit(const common_glue_func_t fn,
+				struct skcipher_request *req)
 {
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return __glue_ecb_crypt_128bit(gctx, desc, &walk);
-}
-EXPORT_SYMBOL_GPL(glue_ecb_crypt_128bit);
-
-static unsigned int __glue_cbc_encrypt_128bit(const common_glue_func_t fn,
-					      struct blkcipher_desc *desc,
-					      struct blkcipher_walk *walk)
-{
-	void *ctx = crypto_blkcipher_ctx(desc->tfm);
+	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
 	const unsigned int bsize = 128 / 8;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 *iv = (u128 *)walk->iv;
-
-	do {
-		u128_xor(dst, src, iv);
-		fn(ctx, (u8 *)dst, (u8 *)dst);
-		iv = dst;
-
-		src += 1;
-		dst += 1;
-		nbytes -= bsize;
-	} while (nbytes >= bsize);
-
-	*(u128 *)walk->iv = *iv;
-	return nbytes;
-}
-
-int glue_cbc_encrypt_128bit(const common_glue_func_t fn,
-			    struct blkcipher_desc *desc,
-			    struct scatterlist *dst,
-			    struct scatterlist *src, unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
+	struct skcipher_walk walk;
+	unsigned int nbytes;
 	int err;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes)) {
-		nbytes = __glue_cbc_encrypt_128bit(fn, desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		const u128 *src = (u128 *)walk.src.virt.addr;
+		u128 *dst = (u128 *)walk.dst.virt.addr;
+		u128 *iv = (u128 *)walk.iv;
+
+		do {
+			u128_xor(dst, src, iv);
+			fn(ctx, (u8 *)dst, (u8 *)dst);
+			iv = dst;
+			src++;
+			dst++;
+			nbytes -= bsize;
+		} while (nbytes >= bsize);
+
+		*(u128 *)walk.iv = *iv;
+		err = skcipher_walk_done(&walk, nbytes);
 	}
-
 	return err;
 }
-EXPORT_SYMBOL_GPL(glue_cbc_encrypt_128bit);
+EXPORT_SYMBOL_GPL(glue_cbc_encrypt_req_128bit);
 
-static unsigned int
-__glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
-			  struct blkcipher_desc *desc,
-			  struct blkcipher_walk *walk)
+int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx,
+				struct skcipher_request *req)
 {
-	void *ctx = crypto_blkcipher_ctx(desc->tfm);
+	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
 	const unsigned int bsize = 128 / 8;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 last_iv;
-	unsigned int num_blocks, func_bytes;
-	unsigned int i;
+	struct skcipher_walk walk;
+	bool fpu_enabled = false;
+	unsigned int nbytes;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
 
-	/* Start of the last block. */
-	src += nbytes / bsize - 1;
-	dst += nbytes / bsize - 1;
+	while ((nbytes = walk.nbytes)) {
+		const u128 *src = walk.src.virt.addr;
+		u128 *dst = walk.dst.virt.addr;
+		unsigned int func_bytes, num_blocks;
+		unsigned int i;
+		u128 last_iv;
 
-	last_iv = *src;
+		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+					     &walk, fpu_enabled, nbytes);
+		/* Start of the last block. */
+		src += nbytes / bsize - 1;
+		dst += nbytes / bsize - 1;
 
-	for (i = 0; i < gctx->num_funcs; i++) {
-		num_blocks = gctx->funcs[i].num_blocks;
-		func_bytes = bsize * num_blocks;
+		last_iv = *src;
 
-		/* Process multi-block batch */
-		if (nbytes >= func_bytes) {
+		for (i = 0; i < gctx->num_funcs; i++) {
+			num_blocks = gctx->funcs[i].num_blocks;
+			func_bytes = bsize * num_blocks;
+
+			if (nbytes < func_bytes)
+				continue;
+
+			/* Process multi-block batch */
 			do {
-				nbytes -= func_bytes - bsize;
 				src -= num_blocks - 1;
 				dst -= num_blocks - 1;
 
 				gctx->funcs[i].fn_u.cbc(ctx, dst, src);
 
-				nbytes -= bsize;
+				nbytes -= func_bytes;
 				if (nbytes < bsize)
 					goto done;
 
-				u128_xor(dst, dst, src - 1);
-				src -= 1;
-				dst -= 1;
+				u128_xor(dst, dst, --src);
+				dst--;
 			} while (nbytes >= func_bytes);
 		}
-	}
-
 done:
-	u128_xor(dst, dst, (u128 *)walk->iv);
-	*(u128 *)walk->iv = last_iv;
-
-	return nbytes;
-}
-
-int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
-			    struct blkcipher_desc *desc,
-			    struct scatterlist *dst,
-			    struct scatterlist *src, unsigned int nbytes)
-{
-	const unsigned int bsize = 128 / 8;
-	bool fpu_enabled = false;
-	struct blkcipher_walk walk;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-
-	while ((nbytes = walk.nbytes)) {
-		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					     desc, fpu_enabled, nbytes);
-		nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		u128_xor(dst, dst, (u128 *)walk.iv);
+		*(u128 *)walk.iv = last_iv;
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	glue_fpu_end(fpu_enabled);
 	return err;
 }
-EXPORT_SYMBOL_GPL(glue_cbc_decrypt_128bit);
+EXPORT_SYMBOL_GPL(glue_cbc_decrypt_req_128bit);
 
-static void glue_ctr_crypt_final_128bit(const common_glue_ctr_func_t fn_ctr,
-					struct blkcipher_desc *desc,
-					struct blkcipher_walk *walk)
+int glue_ctr_req_128bit(const struct common_glue_ctx *gctx,
+			struct skcipher_request *req)
 {
-	void *ctx = crypto_blkcipher_ctx(desc->tfm);
-	u8 *src = (u8 *)walk->src.virt.addr;
-	u8 *dst = (u8 *)walk->dst.virt.addr;
-	unsigned int nbytes = walk->nbytes;
-	le128 ctrblk;
-	u128 tmp;
+	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
+	const unsigned int bsize = 128 / 8;
+	struct skcipher_walk walk;
+	bool fpu_enabled = false;
+	unsigned int nbytes;
+	int err;
 
-	be128_to_le128(&ctrblk, (be128 *)walk->iv);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	memcpy(&tmp, src, nbytes);
-	fn_ctr(ctx, &tmp, &tmp, &ctrblk);
-	memcpy(dst, &tmp, nbytes);
+	while ((nbytes = walk.nbytes) >= bsize) {
+		const u128 *src = walk.src.virt.addr;
+		u128 *dst = walk.dst.virt.addr;
+		unsigned int func_bytes, num_blocks;
+		unsigned int i;
+		le128 ctrblk;
 
-	le128_to_be128((be128 *)walk->iv, &ctrblk);
-}
+		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+					     &walk, fpu_enabled, nbytes);
 
-static unsigned int __glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
-					    struct blkcipher_desc *desc,
-					    struct blkcipher_walk *walk)
-{
-	const unsigned int bsize = 128 / 8;
-	void *ctx = crypto_blkcipher_ctx(desc->tfm);
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	le128 ctrblk;
-	unsigned int num_blocks, func_bytes;
-	unsigned int i;
+		be128_to_le128(&ctrblk, (be128 *)walk.iv);
 
-	be128_to_le128(&ctrblk, (be128 *)walk->iv);
+		for (i = 0; i < gctx->num_funcs; i++) {
+			num_blocks = gctx->funcs[i].num_blocks;
+			func_bytes = bsize * num_blocks;
 
-	/* Process multi-block batch */
-	for (i = 0; i < gctx->num_funcs; i++) {
-		num_blocks = gctx->funcs[i].num_blocks;
-		func_bytes = bsize * num_blocks;
+			if (nbytes < func_bytes)
+				continue;
 
-		if (nbytes >= func_bytes) {
+			/* Process multi-block batch */
 			do {
 				gctx->funcs[i].fn_u.ctr(ctx, dst, src, &ctrblk);
-
 				src += num_blocks;
 				dst += num_blocks;
 				nbytes -= func_bytes;
 			} while (nbytes >= func_bytes);
 
 			if (nbytes < bsize)
-				goto done;
+				break;
 		}
-	}
-
-done:
-	le128_to_be128((be128 *)walk->iv, &ctrblk);
-	return nbytes;
-}
-
-int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
-			  struct blkcipher_desc *desc, struct scatterlist *dst,
-			  struct scatterlist *src, unsigned int nbytes)
-{
-	const unsigned int bsize = 128 / 8;
-	bool fpu_enabled = false;
-	struct blkcipher_walk walk;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, bsize);
 
-	while ((nbytes = walk.nbytes) >= bsize) {
-		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					     desc, fpu_enabled, nbytes);
-		nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		le128_to_be128((be128 *)walk.iv, &ctrblk);
+		err = skcipher_walk_done(&walk, nbytes);
 	}
 
 	glue_fpu_end(fpu_enabled);
 
-	if (walk.nbytes) {
-		glue_ctr_crypt_final_128bit(
-			gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, 0);
-	}
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(glue_ctr_crypt_128bit);
-
-static unsigned int __glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
-					    void *ctx,
-					    struct blkcipher_desc *desc,
-					    struct blkcipher_walk *walk)
-{
-	const unsigned int bsize = 128 / 8;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	unsigned int num_blocks, func_bytes;
-	unsigned int i;
-
-	/* Process multi-block batch */
-	for (i = 0; i < gctx->num_funcs; i++) {
-		num_blocks = gctx->funcs[i].num_blocks;
-		func_bytes = bsize * num_blocks;
-
-		if (nbytes >= func_bytes) {
-			do {
-				gctx->funcs[i].fn_u.xts(ctx, dst, src,
-							(le128 *)walk->iv);
+	if (nbytes) {
+		le128 ctrblk;
+		u128 tmp;
 
-				src += num_blocks;
-				dst += num_blocks;
-				nbytes -= func_bytes;
-			} while (nbytes >= func_bytes);
+		be128_to_le128(&ctrblk, (be128 *)walk.iv);
+		memcpy(&tmp, walk.src.virt.addr, nbytes);
+		gctx->funcs[gctx->num_funcs - 1].fn_u.ctr(ctx, &tmp, &tmp,
+							  &ctrblk);
+		memcpy(walk.dst.virt.addr, &tmp, nbytes);
+		le128_to_be128((be128 *)walk.iv, &ctrblk);
 
-			if (nbytes < bsize)
-				goto done;
-		}
+		err = skcipher_walk_done(&walk, 0);
 	}
 
-done:
-	return nbytes;
+	return err;
 }
+EXPORT_SYMBOL_GPL(glue_ctr_req_128bit);
 
 static unsigned int __glue_xts_req_128bit(const struct common_glue_ctx *gctx,
 					  void *ctx,
@@ -372,46 +271,6 @@ done:
 	return nbytes;
 }
 
-/* for implementations implementing faster XTS IV generator */
-int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
-			  struct blkcipher_desc *desc, struct scatterlist *dst,
-			  struct scatterlist *src, unsigned int nbytes,
-			  void (*tweak_fn)(void *ctx, u8 *dst, const u8 *src),
-			  void *tweak_ctx, void *crypt_ctx)
-{
-	const unsigned int bsize = 128 / 8;
-	bool fpu_enabled = false;
-	struct blkcipher_walk walk;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-
-	err = blkcipher_walk_virt(desc, &walk);
-	nbytes = walk.nbytes;
-	if (!nbytes)
-		return err;
-
-	/* set minimum length to bsize, for tweak_fn */
-	fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-				     desc, fpu_enabled,
-				     nbytes < bsize ? bsize : nbytes);
-
-	/* calculate first value of T */
-	tweak_fn(tweak_ctx, walk.iv, walk.iv);
-
-	while (nbytes) {
-		nbytes = __glue_xts_crypt_128bit(gctx, crypt_ctx, desc, &walk);
-
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-		nbytes = walk.nbytes;
-	}
-
-	glue_fpu_end(fpu_enabled);
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit);
-
 int glue_xts_req_128bit(const struct common_glue_ctx *gctx,
 			struct skcipher_request *req,
 			common_glue_func_t tweak_fn, void *tweak_ctx,
@@ -429,9 +288,9 @@ int glue_xts_req_128bit(const struct common_glue_ctx *gctx,
 		return err;
 
 	/* set minimum length to bsize, for tweak_fn */
-	fpu_enabled = glue_skwalk_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					    &walk, fpu_enabled,
-					    nbytes < bsize ? bsize : nbytes);
+	fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+				     &walk, fpu_enabled,
+				     nbytes < bsize ? bsize : nbytes);
 
 	/* calculate first value of T */
 	tweak_fn(tweak_ctx, walk.iv, walk.iv);
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 870f6d812a2d..03347b16ac9d 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -14,15 +14,12 @@
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
-#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
-#include <crypto/ctr.h>
-#include <crypto/lrw.h>
-#include <crypto/xts.h>
+#include <crypto/internal/simd.h>
 #include <crypto/serpent.h>
-#include <asm/fpu/api.h>
-#include <asm/crypto/serpent-avx.h>
+#include <crypto/xts.h>
 #include <asm/crypto/glue_helper.h>
+#include <asm/crypto/serpent-avx.h>
 
 #define SERPENT_AVX2_PARALLEL_BLOCKS 16
 
@@ -40,6 +37,12 @@ asmlinkage void serpent_xts_enc_16way(struct serpent_ctx *ctx, u8 *dst,
 asmlinkage void serpent_xts_dec_16way(struct serpent_ctx *ctx, u8 *dst,
 				      const u8 *src, le128 *iv);
 
+static int serpent_setkey_skcipher(struct crypto_skcipher *tfm,
+				   const u8 *key, unsigned int keylen)
+{
+	return __serpent_setkey(crypto_skcipher_ctx(tfm), key, keylen);
+}
+
 static const struct common_glue_ctx serpent_enc = {
 	.num_funcs = 3,
 	.fpu_blocks_limit = 8,
@@ -136,403 +139,113 @@ static const struct common_glue_ctx serpent_dec_xts = {
 	} }
 };
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_crypt_128bit(&serpent_enc, desc, dst, src, nbytes);
+	return glue_ecb_req_128bit(&serpent_enc, req);
 }
 
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_crypt_128bit(&serpent_dec, desc, dst, src, nbytes);
+	return glue_ecb_req_128bit(&serpent_dec, req);
 }
 
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(__serpent_encrypt), desc,
-				       dst, src, nbytes);
+	return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(__serpent_encrypt),
+					   req);
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_128bit(&serpent_dec_cbc, desc, dst, src,
-				       nbytes);
+	return glue_cbc_decrypt_req_128bit(&serpent_dec_cbc, req);
 }
 
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	return glue_ctr_crypt_128bit(&serpent_ctr, desc, dst, src, nbytes);
+	return glue_ctr_req_128bit(&serpent_ctr, req);
 }
 
-static inline bool serpent_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+static int xts_encrypt(struct skcipher_request *req)
 {
-	/* since reusing AVX functions, starts using FPU at 8 parallel blocks */
-	return glue_fpu_begin(SERPENT_BLOCK_SIZE, 8, NULL, fpu_enabled, nbytes);
-}
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-static inline void serpent_fpu_end(bool fpu_enabled)
-{
-	glue_fpu_end(fpu_enabled);
+	return glue_xts_req_128bit(&serpent_enc_xts, req,
+				   XTS_TWEAK_CAST(__serpent_encrypt),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-struct crypt_priv {
-	struct serpent_ctx *ctx;
-	bool fpu_enabled;
-};
-
-static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int xts_decrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = SERPENT_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes >= SERPENT_AVX2_PARALLEL_BLOCKS * bsize) {
-		serpent_ecb_enc_16way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * SERPENT_AVX2_PARALLEL_BLOCKS;
-		nbytes -= bsize * SERPENT_AVX2_PARALLEL_BLOCKS;
-	}
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	while (nbytes >= SERPENT_PARALLEL_BLOCKS * bsize) {
-		serpent_ecb_enc_8way_avx(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * SERPENT_PARALLEL_BLOCKS;
-		nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		__serpent_encrypt(ctx->ctx, srcdst, srcdst);
+	return glue_xts_req_128bit(&serpent_dec_xts, req,
+				   XTS_TWEAK_CAST(__serpent_encrypt),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
-{
-	const unsigned int bsize = SERPENT_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes >= SERPENT_AVX2_PARALLEL_BLOCKS * bsize) {
-		serpent_ecb_dec_16way(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * SERPENT_AVX2_PARALLEL_BLOCKS;
-		nbytes -= bsize * SERPENT_AVX2_PARALLEL_BLOCKS;
-	}
-
-	while (nbytes >= SERPENT_PARALLEL_BLOCKS * bsize) {
-		serpent_ecb_dec_8way_avx(ctx->ctx, srcdst, srcdst);
-		srcdst += bsize * SERPENT_PARALLEL_BLOCKS;
-		nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		__serpent_decrypt(ctx->ctx, srcdst, srcdst);
-}
-
-static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[SERPENT_AVX2_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->serpent_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	serpent_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[SERPENT_AVX2_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->serpent_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	serpent_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-
-	return glue_xts_crypt_128bit(&serpent_enc_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(__serpent_encrypt),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
-}
-
-static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-
-	return glue_xts_crypt_128bit(&serpent_dec_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(__serpent_encrypt),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
-}
-
-static struct crypto_alg srp_algs[10] = { {
-	.cra_name		= "__ecb-serpent-avx2",
-	.cra_driver_name	= "__driver-ecb-serpent-avx2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(srp_algs[0].cra_list),
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.setkey		= serpent_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__cbc-serpent-avx2",
-	.cra_driver_name	= "__driver-cbc-serpent-avx2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(srp_algs[1].cra_list),
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.setkey		= serpent_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__ctr-serpent-avx2",
-	.cra_driver_name	= "__driver-ctr-serpent-avx2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct serpent_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(srp_algs[2].cra_list),
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= serpent_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-}, {
-	.cra_name		= "__lrw-serpent-avx2",
-	.cra_driver_name	= "__driver-lrw-serpent-avx2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_lrw_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(srp_algs[3].cra_list),
-	.cra_exit		= lrw_serpent_exit_tfm,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= lrw_serpent_setkey,
-			.encrypt	= lrw_encrypt,
-			.decrypt	= lrw_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__xts-serpent-avx2",
-	.cra_driver_name	= "__driver-xts-serpent-avx2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_xts_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(srp_algs[4].cra_list),
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE * 2,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE * 2,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= xts_serpent_setkey,
-			.encrypt	= xts_encrypt,
-			.decrypt	= xts_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ecb(serpent)",
-	.cra_driver_name	= "ecb-serpent-avx2",
-	.cra_priority		= 600,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(srp_algs[5].cra_list),
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(serpent)",
-	.cra_driver_name	= "cbc-serpent-avx2",
-	.cra_priority		= 600,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(srp_algs[6].cra_list),
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= __ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(serpent)",
-	.cra_driver_name	= "ctr-serpent-avx2",
-	.cra_priority		= 600,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(srp_algs[7].cra_list),
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_encrypt,
-			.geniv		= "chainiv",
-		},
-	},
-}, {
-	.cra_name		= "lrw(serpent)",
-	.cra_driver_name	= "lrw-serpent-avx2",
-	.cra_priority		= 600,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(srp_algs[8].cra_list),
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "xts(serpent)",
-	.cra_driver_name	= "xts-serpent-avx2",
-	.cra_priority		= 600,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_list		= LIST_HEAD_INIT(srp_algs[9].cra_list),
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE * 2,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE * 2,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
+static struct skcipher_alg serpent_algs[] = {
+	{
+		.base.cra_name		= "__ecb(serpent)",
+		.base.cra_driver_name	= "__ecb-serpent-avx2",
+		.base.cra_priority	= 600,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= SERPENT_MAX_KEY_SIZE,
+		.setkey			= serpent_setkey_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "__cbc(serpent)",
+		.base.cra_driver_name	= "__cbc-serpent-avx2",
+		.base.cra_priority	= 600,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= SERPENT_MAX_KEY_SIZE,
+		.ivsize			= SERPENT_BLOCK_SIZE,
+		.setkey			= serpent_setkey_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "__ctr(serpent)",
+		.base.cra_driver_name	= "__ctr-serpent-avx2",
+		.base.cra_priority	= 600,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= SERPENT_MAX_KEY_SIZE,
+		.ivsize			= SERPENT_BLOCK_SIZE,
+		.chunksize		= SERPENT_BLOCK_SIZE,
+		.setkey			= serpent_setkey_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+	}, {
+		.base.cra_name		= "__xts(serpent)",
+		.base.cra_driver_name	= "__xts-serpent-avx2",
+		.base.cra_priority	= 600,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct serpent_xts_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= 2 * SERPENT_MAX_KEY_SIZE,
+		.ivsize			= SERPENT_BLOCK_SIZE,
+		.setkey			= xts_serpent_setkey,
+		.encrypt		= xts_encrypt,
+		.decrypt		= xts_decrypt,
 	},
-} };
+};
+
+static struct simd_skcipher_alg *serpent_simd_algs[ARRAY_SIZE(serpent_algs)];
 
 static int __init init(void)
 {
@@ -548,12 +261,15 @@ static int __init init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(srp_algs, ARRAY_SIZE(srp_algs));
+	return simd_register_skciphers_compat(serpent_algs,
+					      ARRAY_SIZE(serpent_algs),
+					      serpent_simd_algs);
 }
 
 static void __exit fini(void)
 {
-	crypto_unregister_algs(srp_algs, ARRAY_SIZE(srp_algs));
+	simd_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs),
+				  serpent_simd_algs);
 }
 
 module_init(init);
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index 6f778d3daa22..458567ecf76c 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -24,21 +24,15 @@
  */
 
 #include <linux/module.h>
-#include <linux/hardirq.h>
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
-#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
+#include <crypto/internal/simd.h>
 #include <crypto/serpent.h>
-#include <crypto/cryptd.h>
-#include <crypto/b128ops.h>
-#include <crypto/ctr.h>
-#include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/fpu/api.h>
-#include <asm/crypto/serpent-avx.h>
 #include <asm/crypto/glue_helper.h>
+#include <asm/crypto/serpent-avx.h>
 
 /* 8-way parallel cipher functions */
 asmlinkage void serpent_ecb_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst,
@@ -91,6 +85,31 @@ void serpent_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv)
 }
 EXPORT_SYMBOL_GPL(serpent_xts_dec);
 
+static int serpent_setkey_skcipher(struct crypto_skcipher *tfm,
+				   const u8 *key, unsigned int keylen)
+{
+	return __serpent_setkey(crypto_skcipher_ctx(tfm), key, keylen);
+}
+
+int xts_serpent_setkey(struct crypto_skcipher *tfm, const u8 *key,
+		       unsigned int keylen)
+{
+	struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = xts_verify_key(tfm, key, keylen);
+	if (err)
+		return err;
+
+	/* first half of xts-key is for crypt */
+	err = __serpent_setkey(&ctx->crypt_ctx, key, keylen / 2);
+	if (err)
+		return err;
+
+	/* second half of xts-key is for tweak */
+	return __serpent_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2);
+}
+EXPORT_SYMBOL_GPL(xts_serpent_setkey);
 
 static const struct common_glue_ctx serpent_enc = {
 	.num_funcs = 2,
@@ -170,423 +189,113 @@ static const struct common_glue_ctx serpent_dec_xts = {
 	} }
 };
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_crypt_128bit(&serpent_enc, desc, dst, src, nbytes);
+	return glue_ecb_req_128bit(&serpent_enc, req);
 }
 
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_crypt_128bit(&serpent_dec, desc, dst, src, nbytes);
+	return glue_ecb_req_128bit(&serpent_dec, req);
 }
 
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(__serpent_encrypt), desc,
-				     dst, src, nbytes);
+	return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(__serpent_encrypt),
+					   req);
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_128bit(&serpent_dec_cbc, desc, dst, src,
-				       nbytes);
+	return glue_cbc_decrypt_req_128bit(&serpent_dec_cbc, req);
 }
 
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	return glue_ctr_crypt_128bit(&serpent_ctr, desc, dst, src, nbytes);
+	return glue_ctr_req_128bit(&serpent_ctr, req);
 }
 
-static inline bool serpent_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+static int xts_encrypt(struct skcipher_request *req)
 {
-	return glue_fpu_begin(SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS,
-			      NULL, fpu_enabled, nbytes);
-}
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-static inline void serpent_fpu_end(bool fpu_enabled)
-{
-	glue_fpu_end(fpu_enabled);
+	return glue_xts_req_128bit(&serpent_enc_xts, req,
+				   XTS_TWEAK_CAST(__serpent_encrypt),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-struct crypt_priv {
-	struct serpent_ctx *ctx;
-	bool fpu_enabled;
-};
-
-static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
-{
-	const unsigned int bsize = SERPENT_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
-		serpent_ecb_enc_8way_avx(ctx->ctx, srcdst, srcdst);
-		return;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		__serpent_encrypt(ctx->ctx, srcdst, srcdst);
-}
-
-static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int xts_decrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = SERPENT_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
-		serpent_ecb_dec_8way_avx(ctx->ctx, srcdst, srcdst);
-		return;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		__serpent_decrypt(ctx->ctx, srcdst, srcdst);
-}
-
-int lrw_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
-		       unsigned int keylen)
-{
-	struct serpent_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	err = __serpent_setkey(&ctx->serpent_ctx, key, keylen -
-							SERPENT_BLOCK_SIZE);
-	if (err)
-		return err;
-
-	return lrw_init_table(&ctx->lrw_table, key + keylen -
-						SERPENT_BLOCK_SIZE);
-}
-EXPORT_SYMBOL_GPL(lrw_serpent_setkey);
-
-static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[SERPENT_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->serpent_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	serpent_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
+	return glue_xts_req_128bit(&serpent_dec_xts, req,
+				   XTS_TWEAK_CAST(__serpent_encrypt),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[SERPENT_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->serpent_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	serpent_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-void lrw_serpent_exit_tfm(struct crypto_tfm *tfm)
-{
-	struct serpent_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	lrw_free_table(&ctx->lrw_table);
-}
-EXPORT_SYMBOL_GPL(lrw_serpent_exit_tfm);
-
-int xts_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
-		       unsigned int keylen)
-{
-	struct serpent_xts_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	err = xts_check_key(tfm, key, keylen);
-	if (err)
-		return err;
-
-	/* first half of xts-key is for crypt */
-	err = __serpent_setkey(&ctx->crypt_ctx, key, keylen / 2);
-	if (err)
-		return err;
-
-	/* second half of xts-key is for tweak */
-	return __serpent_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2);
-}
-EXPORT_SYMBOL_GPL(xts_serpent_setkey);
-
-static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-
-	return glue_xts_crypt_128bit(&serpent_enc_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(__serpent_encrypt),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
-}
-
-static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-
-	return glue_xts_crypt_128bit(&serpent_dec_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(__serpent_encrypt),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
-}
-
-static struct crypto_alg serpent_algs[10] = { {
-	.cra_name		= "__ecb-serpent-avx",
-	.cra_driver_name	= "__driver-ecb-serpent-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.setkey		= serpent_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__cbc-serpent-avx",
-	.cra_driver_name	= "__driver-cbc-serpent-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.setkey		= serpent_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__ctr-serpent-avx",
-	.cra_driver_name	= "__driver-ctr-serpent-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct serpent_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= serpent_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-}, {
-	.cra_name		= "__lrw-serpent-avx",
-	.cra_driver_name	= "__driver-lrw-serpent-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_lrw_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_exit		= lrw_serpent_exit_tfm,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= lrw_serpent_setkey,
-			.encrypt	= lrw_encrypt,
-			.decrypt	= lrw_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__xts-serpent-avx",
-	.cra_driver_name	= "__driver-xts-serpent-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_xts_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE * 2,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE * 2,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= xts_serpent_setkey,
-			.encrypt	= xts_encrypt,
-			.decrypt	= xts_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ecb(serpent)",
-	.cra_driver_name	= "ecb-serpent-avx",
-	.cra_priority		= 500,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(serpent)",
-	.cra_driver_name	= "cbc-serpent-avx",
-	.cra_priority		= 500,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= __ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(serpent)",
-	.cra_driver_name	= "ctr-serpent-avx",
-	.cra_priority		= 500,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_encrypt,
-			.geniv		= "chainiv",
-		},
-	},
-}, {
-	.cra_name		= "lrw(serpent)",
-	.cra_driver_name	= "lrw-serpent-avx",
-	.cra_priority		= 500,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "xts(serpent)",
-	.cra_driver_name	= "xts-serpent-avx",
-	.cra_priority		= 500,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE * 2,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE * 2,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
+static struct skcipher_alg serpent_algs[] = {
+	{
+		.base.cra_name		= "__ecb(serpent)",
+		.base.cra_driver_name	= "__ecb-serpent-avx",
+		.base.cra_priority	= 500,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= SERPENT_MAX_KEY_SIZE,
+		.setkey			= serpent_setkey_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "__cbc(serpent)",
+		.base.cra_driver_name	= "__cbc-serpent-avx",
+		.base.cra_priority	= 500,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= SERPENT_MAX_KEY_SIZE,
+		.ivsize			= SERPENT_BLOCK_SIZE,
+		.setkey			= serpent_setkey_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "__ctr(serpent)",
+		.base.cra_driver_name	= "__ctr-serpent-avx",
+		.base.cra_priority	= 500,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= SERPENT_MAX_KEY_SIZE,
+		.ivsize			= SERPENT_BLOCK_SIZE,
+		.chunksize		= SERPENT_BLOCK_SIZE,
+		.setkey			= serpent_setkey_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+	}, {
+		.base.cra_name		= "__xts(serpent)",
+		.base.cra_driver_name	= "__xts-serpent-avx",
+		.base.cra_priority	= 500,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct serpent_xts_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= 2 * SERPENT_MAX_KEY_SIZE,
+		.ivsize			= SERPENT_BLOCK_SIZE,
+		.setkey			= xts_serpent_setkey,
+		.encrypt		= xts_encrypt,
+		.decrypt		= xts_decrypt,
 	},
-} };
+};
+
+static struct simd_skcipher_alg *serpent_simd_algs[ARRAY_SIZE(serpent_algs)];
 
 static int __init serpent_init(void)
 {
@@ -598,12 +307,15 @@ static int __init serpent_init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(serpent_algs, ARRAY_SIZE(serpent_algs));
+	return simd_register_skciphers_compat(serpent_algs,
+					      ARRAY_SIZE(serpent_algs),
+					      serpent_simd_algs);
 }
 
 static void __exit serpent_exit(void)
 {
-	crypto_unregister_algs(serpent_algs, ARRAY_SIZE(serpent_algs));
+	simd_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs),
+				  serpent_simd_algs);
 }
 
 module_init(serpent_init);
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index ac0e831943f5..3dafe137596a 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -30,21 +30,22 @@
  */
 
 #include <linux/module.h>
-#include <linux/hardirq.h>
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
-#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
-#include <crypto/serpent.h>
-#include <crypto/cryptd.h>
 #include <crypto/b128ops.h>
-#include <crypto/ctr.h>
-#include <crypto/lrw.h>
-#include <crypto/xts.h>
+#include <crypto/internal/simd.h>
+#include <crypto/serpent.h>
 #include <asm/crypto/serpent-sse2.h>
 #include <asm/crypto/glue_helper.h>
 
+static int serpent_setkey_skcipher(struct crypto_skcipher *tfm,
+				   const u8 *key, unsigned int keylen)
+{
+	return __serpent_setkey(crypto_skcipher_ctx(tfm), key, keylen);
+}
+
 static void serpent_decrypt_cbc_xway(void *ctx, u128 *dst, const u128 *src)
 {
 	u128 ivs[SERPENT_PARALLEL_BLOCKS - 1];
@@ -139,464 +140,79 @@ static const struct common_glue_ctx serpent_dec_cbc = {
 	} }
 };
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&serpent_enc, desc, dst, src, nbytes);
-}
-
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&serpent_dec, desc, dst, src, nbytes);
-}
-
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(__serpent_encrypt), desc,
-				     dst, src, nbytes);
+	return glue_ecb_req_128bit(&serpent_enc, req);
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_128bit(&serpent_dec_cbc, desc, dst, src,
-				       nbytes);
+	return glue_ecb_req_128bit(&serpent_dec, req);
 }
 
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_ctr_crypt_128bit(&serpent_ctr, desc, dst, src, nbytes);
+	return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(__serpent_encrypt),
+					   req);
 }
 
-static inline bool serpent_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_fpu_begin(SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS,
-			      NULL, fpu_enabled, nbytes);
+	return glue_cbc_decrypt_req_128bit(&serpent_dec_cbc, req);
 }
 
-static inline void serpent_fpu_end(bool fpu_enabled)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	glue_fpu_end(fpu_enabled);
+	return glue_ctr_req_128bit(&serpent_ctr, req);
 }
 
-struct crypt_priv {
-	struct serpent_ctx *ctx;
-	bool fpu_enabled;
-};
-
-static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
-{
-	const unsigned int bsize = SERPENT_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
-		serpent_enc_blk_xway(ctx->ctx, srcdst, srcdst);
-		return;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		__serpent_encrypt(ctx->ctx, srcdst, srcdst);
-}
-
-static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
-{
-	const unsigned int bsize = SERPENT_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
-		serpent_dec_blk_xway(ctx->ctx, srcdst, srcdst);
-		return;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		__serpent_decrypt(ctx->ctx, srcdst, srcdst);
-}
-
-struct serpent_lrw_ctx {
-	struct lrw_table_ctx lrw_table;
-	struct serpent_ctx serpent_ctx;
-};
-
-static int lrw_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen)
-{
-	struct serpent_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	err = __serpent_setkey(&ctx->serpent_ctx, key, keylen -
-							SERPENT_BLOCK_SIZE);
-	if (err)
-		return err;
-
-	return lrw_init_table(&ctx->lrw_table, key + keylen -
-						SERPENT_BLOCK_SIZE);
-}
-
-static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[SERPENT_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->serpent_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	serpent_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[SERPENT_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->serpent_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	serpent_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static void lrw_exit_tfm(struct crypto_tfm *tfm)
-{
-	struct serpent_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	lrw_free_table(&ctx->lrw_table);
-}
-
-struct serpent_xts_ctx {
-	struct serpent_ctx tweak_ctx;
-	struct serpent_ctx crypt_ctx;
+static struct skcipher_alg serpent_algs[] = {
+	{
+		.base.cra_name		= "__ecb(serpent)",
+		.base.cra_driver_name	= "__ecb-serpent-sse2",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= SERPENT_MAX_KEY_SIZE,
+		.setkey			= serpent_setkey_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "__cbc(serpent)",
+		.base.cra_driver_name	= "__cbc-serpent-sse2",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= SERPENT_MAX_KEY_SIZE,
+		.ivsize			= SERPENT_BLOCK_SIZE,
+		.setkey			= serpent_setkey_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "__ctr(serpent)",
+		.base.cra_driver_name	= "__ctr-serpent-sse2",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= SERPENT_MIN_KEY_SIZE,
+		.max_keysize		= SERPENT_MAX_KEY_SIZE,
+		.ivsize			= SERPENT_BLOCK_SIZE,
+		.chunksize		= SERPENT_BLOCK_SIZE,
+		.setkey			= serpent_setkey_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+	},
 };
 
-static int xts_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen)
-{
-	struct serpent_xts_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	err = xts_check_key(tfm, key, keylen);
-	if (err)
-		return err;
-
-	/* first half of xts-key is for crypt */
-	err = __serpent_setkey(&ctx->crypt_ctx, key, keylen / 2);
-	if (err)
-		return err;
-
-	/* second half of xts-key is for tweak */
-	return __serpent_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2);
-}
-
-static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	le128 buf[SERPENT_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->crypt_ctx,
-		.fpu_enabled = false,
-	};
-	struct xts_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.tweak_ctx = &ctx->tweak_ctx,
-		.tweak_fn = XTS_TWEAK_CAST(__serpent_encrypt),
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = xts_crypt(desc, dst, src, nbytes, &req);
-	serpent_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	le128 buf[SERPENT_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->crypt_ctx,
-		.fpu_enabled = false,
-	};
-	struct xts_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.tweak_ctx = &ctx->tweak_ctx,
-		.tweak_fn = XTS_TWEAK_CAST(__serpent_encrypt),
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = xts_crypt(desc, dst, src, nbytes, &req);
-	serpent_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static struct crypto_alg serpent_algs[10] = { {
-	.cra_name		= "__ecb-serpent-sse2",
-	.cra_driver_name	= "__driver-ecb-serpent-sse2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.setkey		= serpent_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__cbc-serpent-sse2",
-	.cra_driver_name	= "__driver-cbc-serpent-sse2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.setkey		= serpent_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__ctr-serpent-sse2",
-	.cra_driver_name	= "__driver-ctr-serpent-sse2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct serpent_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= serpent_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-}, {
-	.cra_name		= "__lrw-serpent-sse2",
-	.cra_driver_name	= "__driver-lrw-serpent-sse2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_lrw_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_exit		= lrw_exit_tfm,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= lrw_serpent_setkey,
-			.encrypt	= lrw_encrypt,
-			.decrypt	= lrw_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__xts-serpent-sse2",
-	.cra_driver_name	= "__driver-xts-serpent-sse2",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct serpent_xts_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE * 2,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE * 2,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= xts_serpent_setkey,
-			.encrypt	= xts_encrypt,
-			.decrypt	= xts_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ecb(serpent)",
-	.cra_driver_name	= "ecb-serpent-sse2",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(serpent)",
-	.cra_driver_name	= "cbc-serpent-sse2",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= __ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(serpent)",
-	.cra_driver_name	= "ctr-serpent-sse2",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_encrypt,
-			.geniv		= "chainiv",
-		},
-	},
-}, {
-	.cra_name		= "lrw(serpent)",
-	.cra_driver_name	= "lrw-serpent-sse2",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE +
-					  SERPENT_BLOCK_SIZE,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "xts(serpent)",
-	.cra_driver_name	= "xts-serpent-sse2",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= SERPENT_MIN_KEY_SIZE * 2,
-			.max_keysize	= SERPENT_MAX_KEY_SIZE * 2,
-			.ivsize		= SERPENT_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-} };
+static struct simd_skcipher_alg *serpent_simd_algs[ARRAY_SIZE(serpent_algs)];
 
 static int __init serpent_sse2_init(void)
 {
@@ -605,12 +221,15 @@ static int __init serpent_sse2_init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(serpent_algs, ARRAY_SIZE(serpent_algs));
+	return simd_register_skciphers_compat(serpent_algs,
+					      ARRAY_SIZE(serpent_algs),
+					      serpent_simd_algs);
 }
 
 static void __exit serpent_sse2_exit(void)
 {
-	crypto_unregister_algs(serpent_algs, ARRAY_SIZE(serpent_algs));
+	simd_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs),
+				  serpent_simd_algs);
 }
 
 module_init(serpent_sse2_init);
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb.c b/arch/x86/crypto/sha1-mb/sha1_mb.c
index acf9fdf01671..e17655ffde79 100644
--- a/arch/x86/crypto/sha1-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha1-mb/sha1_mb.c
@@ -106,13 +106,6 @@ static asmlinkage struct job_sha1* (*sha1_job_mgr_flush)
 static asmlinkage struct job_sha1* (*sha1_job_mgr_get_comp_job)
 						(struct sha1_mb_mgr *state);
 
-static inline void sha1_init_digest(uint32_t *digest)
-{
-	static const uint32_t initial_digest[SHA1_DIGEST_LENGTH] = {SHA1_H0,
-					SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 };
-	memcpy(digest, initial_digest, sizeof(initial_digest));
-}
-
 static inline uint32_t sha1_pad(uint8_t padblock[SHA1_BLOCK_SIZE * 2],
 			 uint64_t total_len)
 {
@@ -244,11 +237,8 @@ static struct sha1_hash_ctx *sha1_ctx_mgr_submit(struct sha1_ctx_mgr *mgr,
 					  uint32_t len,
 					  int flags)
 {
-	if (flags & (~HASH_ENTIRE)) {
-		/*
-		 * User should not pass anything other than FIRST, UPDATE, or
-		 * LAST
-		 */
+	if (flags & ~(HASH_UPDATE | HASH_LAST)) {
+		/* User should not pass anything other than UPDATE or LAST */
 		ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
 		return ctx;
 	}
@@ -259,24 +249,12 @@ static struct sha1_hash_ctx *sha1_ctx_mgr_submit(struct sha1_ctx_mgr *mgr,
 		return ctx;
 	}
 
-	if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) {
+	if (ctx->status & HASH_CTX_STS_COMPLETE) {
 		/* Cannot update a finished job. */
 		ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
 		return ctx;
 	}
 
-
-	if (flags & HASH_FIRST) {
-		/* Init digest */
-		sha1_init_digest(ctx->job.result_digest);
-
-		/* Reset byte counter */
-		ctx->total_length = 0;
-
-		/* Clear extra blocks */
-		ctx->partial_block_buffer_length = 0;
-	}
-
 	/*
 	 * If we made it here, there were no errors during this call to
 	 * submit
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h b/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h
index 13590ccf965c..9454bd16f9f8 100644
--- a/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h
@@ -57,11 +57,9 @@
 #include "sha1_mb_mgr.h"
 
 #define HASH_UPDATE          0x00
-#define HASH_FIRST           0x01
-#define HASH_LAST            0x02
-#define HASH_ENTIRE          0x03
-#define HASH_DONE	     0x04
-#define HASH_FINAL	     0x08
+#define HASH_LAST            0x01
+#define HASH_DONE	     0x02
+#define HASH_FINAL	     0x04
 
 #define HASH_CTX_STS_IDLE       0x00
 #define HASH_CTX_STS_PROCESSING 0x01
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c
index 7926a226b120..4c46ac1b6653 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb.c
+++ b/arch/x86/crypto/sha256-mb/sha256_mb.c
@@ -106,14 +106,6 @@ static asmlinkage struct job_sha256* (*sha256_job_mgr_flush)
 static asmlinkage struct job_sha256* (*sha256_job_mgr_get_comp_job)
 			(struct sha256_mb_mgr *state);
 
-inline void sha256_init_digest(uint32_t *digest)
-{
-	static const uint32_t initial_digest[SHA256_DIGEST_LENGTH] = {
-				SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
-				SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7};
-	memcpy(digest, initial_digest, sizeof(initial_digest));
-}
-
 inline uint32_t sha256_pad(uint8_t padblock[SHA256_BLOCK_SIZE * 2],
 			 uint64_t total_len)
 {
@@ -245,10 +237,8 @@ static struct sha256_hash_ctx *sha256_ctx_mgr_submit(struct sha256_ctx_mgr *mgr,
 					  uint32_t len,
 					  int flags)
 {
-	if (flags & (~HASH_ENTIRE)) {
-		/* User should not pass anything other than FIRST, UPDATE
-		 * or LAST
-		 */
+	if (flags & ~(HASH_UPDATE | HASH_LAST)) {
+		/* User should not pass anything other than UPDATE or LAST */
 		ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
 		return ctx;
 	}
@@ -259,23 +249,12 @@ static struct sha256_hash_ctx *sha256_ctx_mgr_submit(struct sha256_ctx_mgr *mgr,
 		return ctx;
 	}
 
-	if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) {
+	if (ctx->status & HASH_CTX_STS_COMPLETE) {
 		/* Cannot update a finished job. */
 		ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
 		return ctx;
 	}
 
-	if (flags & HASH_FIRST) {
-		/* Init digest */
-		sha256_init_digest(ctx->job.result_digest);
-
-		/* Reset byte counter */
-		ctx->total_length = 0;
-
-		/* Clear extra blocks */
-		ctx->partial_block_buffer_length = 0;
-	}
-
 	/* If we made it here, there was no error during this call to submit */
 	ctx->error = HASH_CTX_ERROR_NONE;
 
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h b/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h
index aabb30320af0..7c432543dc7f 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h
@@ -57,11 +57,9 @@
 #include "sha256_mb_mgr.h"
 
 #define HASH_UPDATE          0x00
-#define HASH_FIRST           0x01
-#define HASH_LAST            0x02
-#define HASH_ENTIRE          0x03
-#define HASH_DONE	     0x04
-#define HASH_FINAL	     0x08
+#define HASH_LAST            0x01
+#define HASH_DONE	     0x02
+#define HASH_FINAL	     0x04
 
 #define HASH_CTX_STS_IDLE       0x00
 #define HASH_CTX_STS_PROCESSING 0x01
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
index 458409b7568d..39e2bbdc1836 100644
--- a/arch/x86/crypto/sha512-mb/sha512_mb.c
+++ b/arch/x86/crypto/sha512-mb/sha512_mb.c
@@ -107,15 +107,6 @@ static asmlinkage struct job_sha512* (*sha512_job_mgr_flush)
 static asmlinkage struct job_sha512* (*sha512_job_mgr_get_comp_job)
 						(struct sha512_mb_mgr *state);
 
-inline void sha512_init_digest(uint64_t *digest)
-{
-	static const uint64_t initial_digest[SHA512_DIGEST_LENGTH] = {
-					SHA512_H0, SHA512_H1, SHA512_H2,
-					SHA512_H3, SHA512_H4, SHA512_H5,
-					SHA512_H6, SHA512_H7 };
-	memcpy(digest, initial_digest, sizeof(initial_digest));
-}
-
 inline uint32_t sha512_pad(uint8_t padblock[SHA512_BLOCK_SIZE * 2],
 			 uint64_t total_len)
 {
@@ -263,11 +254,8 @@ static struct sha512_hash_ctx
 
 	mgr = cstate->mgr;
 	spin_lock_irqsave(&cstate->work_lock, irqflags);
-	if (flags & (~HASH_ENTIRE)) {
-		/*
-		 * User should not pass anything other than FIRST, UPDATE, or
-		 * LAST
-		 */
+	if (flags & ~(HASH_UPDATE | HASH_LAST)) {
+		/* User should not pass anything other than UPDATE or LAST */
 		ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
 		goto unlock;
 	}
@@ -278,24 +266,12 @@ static struct sha512_hash_ctx
 		goto unlock;
 	}
 
-	if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) {
+	if (ctx->status & HASH_CTX_STS_COMPLETE) {
 		/* Cannot update a finished job. */
 		ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
 		goto unlock;
 	}
 
-
-	if (flags & HASH_FIRST) {
-		/* Init digest */
-		sha512_init_digest(ctx->job.result_digest);
-
-		/* Reset byte counter */
-		ctx->total_length = 0;
-
-		/* Clear extra blocks */
-		ctx->partial_block_buffer_length = 0;
-	}
-
 	/*
 	 * If we made it here, there were no errors during this call to
 	 * submit
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h b/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h
index e4653f5eec3f..e5c465bd821e 100644
--- a/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h
@@ -57,11 +57,9 @@
 #include "sha512_mb_mgr.h"
 
 #define HASH_UPDATE          0x00
-#define HASH_FIRST           0x01
-#define HASH_LAST            0x02
-#define HASH_ENTIRE          0x03
-#define HASH_DONE            0x04
-#define HASH_FINAL           0x08
+#define HASH_LAST            0x01
+#define HASH_DONE            0x02
+#define HASH_FINAL           0x04
 
 #define HASH_CTX_STS_IDLE       0x00
 #define HASH_CTX_STS_PROCESSING 0x01
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index b7a3904b953c..66d989230d10 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -24,24 +24,15 @@
  */
 
 #include <linux/module.h>
-#include <linux/hardirq.h>
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
-#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
+#include <crypto/internal/simd.h>
 #include <crypto/twofish.h>
-#include <crypto/cryptd.h>
-#include <crypto/b128ops.h>
-#include <crypto/ctr.h>
-#include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/fpu/api.h>
-#include <asm/crypto/twofish.h>
 #include <asm/crypto/glue_helper.h>
-#include <crypto/scatterwalk.h>
-#include <linux/workqueue.h>
-#include <linux/spinlock.h>
+#include <asm/crypto/twofish.h>
 
 #define TWOFISH_PARALLEL_BLOCKS 8
 
@@ -61,6 +52,12 @@ asmlinkage void twofish_xts_enc_8way(struct twofish_ctx *ctx, u8 *dst,
 asmlinkage void twofish_xts_dec_8way(struct twofish_ctx *ctx, u8 *dst,
 				     const u8 *src, le128 *iv);
 
+static int twofish_setkey_skcipher(struct crypto_skcipher *tfm,
+				   const u8 *key, unsigned int keylen)
+{
+	return twofish_setkey(&tfm->base, key, keylen);
+}
+
 static inline void twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
 					const u8 *src)
 {
@@ -79,6 +76,31 @@ static void twofish_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv)
 				  GLUE_FUNC_CAST(twofish_dec_blk));
 }
 
+struct twofish_xts_ctx {
+	struct twofish_ctx tweak_ctx;
+	struct twofish_ctx crypt_ctx;
+};
+
+static int xts_twofish_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	u32 *flags = &tfm->base.crt_flags;
+	int err;
+
+	err = xts_verify_key(tfm, key, keylen);
+	if (err)
+		return err;
+
+	/* first half of xts-key is for crypt */
+	err = __twofish_setkey(&ctx->crypt_ctx, key, keylen / 2, flags);
+	if (err)
+		return err;
+
+	/* second half of xts-key is for tweak */
+	return __twofish_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2,
+				flags);
+}
 
 static const struct common_glue_ctx twofish_enc = {
 	.num_funcs = 3,
@@ -170,389 +192,113 @@ static const struct common_glue_ctx twofish_dec_xts = {
 	} }
 };
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&twofish_enc, desc, dst, src, nbytes);
-}
-
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&twofish_dec, desc, dst, src, nbytes);
-}
-
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(twofish_enc_blk), desc,
-				       dst, src, nbytes);
+	return glue_ecb_req_128bit(&twofish_enc, req);
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_128bit(&twofish_dec_cbc, desc, dst, src,
-				       nbytes);
+	return glue_ecb_req_128bit(&twofish_dec, req);
 }
 
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_ctr_crypt_128bit(&twofish_ctr, desc, dst, src, nbytes);
+	return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(twofish_enc_blk),
+					   req);
 }
 
-static inline bool twofish_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_fpu_begin(TF_BLOCK_SIZE, TWOFISH_PARALLEL_BLOCKS, NULL,
-			      fpu_enabled, nbytes);
+	return glue_cbc_decrypt_req_128bit(&twofish_dec_cbc, req);
 }
 
-static inline void twofish_fpu_end(bool fpu_enabled)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	glue_fpu_end(fpu_enabled);
+	return glue_ctr_req_128bit(&twofish_ctr, req);
 }
 
-struct crypt_priv {
-	struct twofish_ctx *ctx;
-	bool fpu_enabled;
-};
-
-static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int xts_encrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = TF_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = twofish_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes == bsize * TWOFISH_PARALLEL_BLOCKS) {
-		twofish_ecb_enc_8way(ctx->ctx, srcdst, srcdst);
-		return;
-	}
-
-	for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3)
-		twofish_enc_blk_3way(ctx->ctx, srcdst, srcdst);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	nbytes %= bsize * 3;
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		twofish_enc_blk(ctx->ctx, srcdst, srcdst);
+	return glue_xts_req_128bit(&twofish_enc_xts, req,
+				   XTS_TWEAK_CAST(twofish_enc_blk),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int xts_decrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = TF_BLOCK_SIZE;
-	struct crypt_priv *ctx = priv;
-	int i;
-
-	ctx->fpu_enabled = twofish_fpu_begin(ctx->fpu_enabled, nbytes);
-
-	if (nbytes == bsize * TWOFISH_PARALLEL_BLOCKS) {
-		twofish_ecb_dec_8way(ctx->ctx, srcdst, srcdst);
-		return;
-	}
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3)
-		twofish_dec_blk_3way(ctx->ctx, srcdst, srcdst);
-
-	nbytes %= bsize * 3;
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		twofish_dec_blk(ctx->ctx, srcdst, srcdst);
+	return glue_xts_req_128bit(&twofish_dec_xts, req,
+				   XTS_TWEAK_CAST(twofish_enc_blk),
+				   &ctx->tweak_ctx, &ctx->crypt_ctx);
 }
 
-static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct twofish_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[TWOFISH_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->twofish_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	twofish_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct twofish_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[TWOFISH_PARALLEL_BLOCKS];
-	struct crypt_priv crypt_ctx = {
-		.ctx = &ctx->twofish_ctx,
-		.fpu_enabled = false,
-	};
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &crypt_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-	int ret;
-
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	ret = lrw_crypt(desc, dst, src, nbytes, &req);
-	twofish_fpu_end(crypt_ctx.fpu_enabled);
-
-	return ret;
-}
-
-static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-
-	return glue_xts_crypt_128bit(&twofish_enc_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(twofish_enc_blk),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
-}
-
-static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-
-	return glue_xts_crypt_128bit(&twofish_dec_xts, desc, dst, src, nbytes,
-				     XTS_TWEAK_CAST(twofish_enc_blk),
-				     &ctx->tweak_ctx, &ctx->crypt_ctx);
-}
-
-static struct crypto_alg twofish_algs[10] = { {
-	.cra_name		= "__ecb-twofish-avx",
-	.cra_driver_name	= "__driver-ecb-twofish-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct twofish_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE,
-			.setkey		= twofish_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__cbc-twofish-avx",
-	.cra_driver_name	= "__driver-cbc-twofish-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct twofish_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE,
-			.setkey		= twofish_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__ctr-twofish-avx",
-	.cra_driver_name	= "__driver-ctr-twofish-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct twofish_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= twofish_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-}, {
-	.cra_name		= "__lrw-twofish-avx",
-	.cra_driver_name	= "__driver-lrw-twofish-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct twofish_lrw_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_exit		= lrw_twofish_exit_tfm,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE +
-					  TF_BLOCK_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE +
-					  TF_BLOCK_SIZE,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= lrw_twofish_setkey,
-			.encrypt	= lrw_encrypt,
-			.decrypt	= lrw_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "__xts-twofish-avx",
-	.cra_driver_name	= "__driver-xts-twofish-avx",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER |
-				  CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct twofish_xts_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE * 2,
-			.max_keysize	= TF_MAX_KEY_SIZE * 2,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= xts_twofish_setkey,
-			.encrypt	= xts_encrypt,
-			.decrypt	= xts_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ecb(twofish)",
-	.cra_driver_name	= "ecb-twofish-avx",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(twofish)",
-	.cra_driver_name	= "cbc-twofish-avx",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= __ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(twofish)",
-	.cra_driver_name	= "ctr-twofish-avx",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_encrypt,
-			.geniv		= "chainiv",
-		},
-	},
-}, {
-	.cra_name		= "lrw(twofish)",
-	.cra_driver_name	= "lrw-twofish-avx",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE +
-					  TF_BLOCK_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE +
-					  TF_BLOCK_SIZE,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "xts(twofish)",
-	.cra_driver_name	= "xts-twofish-avx",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_helper_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= ablk_init,
-	.cra_exit		= ablk_exit,
-	.cra_u = {
-		.ablkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE * 2,
-			.max_keysize	= TF_MAX_KEY_SIZE * 2,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= ablk_set_key,
-			.encrypt	= ablk_encrypt,
-			.decrypt	= ablk_decrypt,
-		},
+static struct skcipher_alg twofish_algs[] = {
+	{
+		.base.cra_name		= "__ecb(twofish)",
+		.base.cra_driver_name	= "__ecb-twofish-avx",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= TF_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct twofish_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= TF_MIN_KEY_SIZE,
+		.max_keysize		= TF_MAX_KEY_SIZE,
+		.setkey			= twofish_setkey_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "__cbc(twofish)",
+		.base.cra_driver_name	= "__cbc-twofish-avx",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= TF_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct twofish_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= TF_MIN_KEY_SIZE,
+		.max_keysize		= TF_MAX_KEY_SIZE,
+		.ivsize			= TF_BLOCK_SIZE,
+		.setkey			= twofish_setkey_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "__ctr(twofish)",
+		.base.cra_driver_name	= "__ctr-twofish-avx",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct twofish_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= TF_MIN_KEY_SIZE,
+		.max_keysize		= TF_MAX_KEY_SIZE,
+		.ivsize			= TF_BLOCK_SIZE,
+		.chunksize		= TF_BLOCK_SIZE,
+		.setkey			= twofish_setkey_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
+	}, {
+		.base.cra_name		= "__xts(twofish)",
+		.base.cra_driver_name	= "__xts-twofish-avx",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.base.cra_blocksize	= TF_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct twofish_xts_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * TF_MIN_KEY_SIZE,
+		.max_keysize		= 2 * TF_MAX_KEY_SIZE,
+		.ivsize			= TF_BLOCK_SIZE,
+		.setkey			= xts_twofish_setkey,
+		.encrypt		= xts_encrypt,
+		.decrypt		= xts_decrypt,
 	},
-} };
+};
+
+static struct simd_skcipher_alg *twofish_simd_algs[ARRAY_SIZE(twofish_algs)];
 
 static int __init twofish_init(void)
 {
@@ -563,12 +309,15 @@ static int __init twofish_init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(twofish_algs, ARRAY_SIZE(twofish_algs));
+	return simd_register_skciphers_compat(twofish_algs,
+					      ARRAY_SIZE(twofish_algs),
+					      twofish_simd_algs);
 }
 
 static void __exit twofish_exit(void)
 {
-	crypto_unregister_algs(twofish_algs, ARRAY_SIZE(twofish_algs));
+	simd_unregister_skciphers(twofish_algs, ARRAY_SIZE(twofish_algs),
+				  twofish_simd_algs);
 }
 
 module_init(twofish_init);
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 243e90a4b5d9..571485502ec8 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -20,22 +20,26 @@
  *
  */
 
-#include <asm/processor.h>
+#include <asm/crypto/glue_helper.h>
+#include <asm/crypto/twofish.h>
+#include <crypto/algapi.h>
+#include <crypto/b128ops.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/twofish.h>
 #include <linux/crypto.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/types.h>
-#include <crypto/algapi.h>
-#include <crypto/twofish.h>
-#include <crypto/b128ops.h>
-#include <asm/crypto/twofish.h>
-#include <asm/crypto/glue_helper.h>
-#include <crypto/lrw.h>
-#include <crypto/xts.h>
 
 EXPORT_SYMBOL_GPL(__twofish_enc_blk_3way);
 EXPORT_SYMBOL_GPL(twofish_dec_blk_3way);
 
+static int twofish_setkey_skcipher(struct crypto_skcipher *tfm,
+				   const u8 *key, unsigned int keylen)
+{
+	return twofish_setkey(&tfm->base, key, keylen);
+}
+
 static inline void twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
 					const u8 *src)
 {
@@ -151,284 +155,74 @@ static const struct common_glue_ctx twofish_dec_cbc = {
 	} }
 };
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&twofish_enc, desc, dst, src, nbytes);
-}
-
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ecb_crypt_128bit(&twofish_dec, desc, dst, src, nbytes);
-}
-
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(twofish_enc_blk), desc,
-				       dst, src, nbytes);
-}
-
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_cbc_decrypt_128bit(&twofish_dec_cbc, desc, dst, src,
-				       nbytes);
-}
-
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
-{
-	return glue_ctr_crypt_128bit(&twofish_ctr, desc, dst, src, nbytes);
-}
-
-static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+static int ecb_encrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = TF_BLOCK_SIZE;
-	struct twofish_ctx *ctx = priv;
-	int i;
-
-	if (nbytes == 3 * bsize) {
-		twofish_enc_blk_3way(ctx, srcdst, srcdst);
-		return;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		twofish_enc_blk(ctx, srcdst, srcdst);
-}
-
-static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
-{
-	const unsigned int bsize = TF_BLOCK_SIZE;
-	struct twofish_ctx *ctx = priv;
-	int i;
-
-	if (nbytes == 3 * bsize) {
-		twofish_dec_blk_3way(ctx, srcdst, srcdst);
-		return;
-	}
-
-	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
-		twofish_dec_blk(ctx, srcdst, srcdst);
-}
-
-int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
-		       unsigned int keylen)
-{
-	struct twofish_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	err = __twofish_setkey(&ctx->twofish_ctx, key, keylen - TF_BLOCK_SIZE,
-			       &tfm->crt_flags);
-	if (err)
-		return err;
-
-	return lrw_init_table(&ctx->lrw_table, key + keylen - TF_BLOCK_SIZE);
+	return glue_ecb_req_128bit(&twofish_enc, req);
 }
-EXPORT_SYMBOL_GPL(lrw_twofish_setkey);
 
-static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ecb_decrypt(struct skcipher_request *req)
 {
-	struct twofish_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[3];
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &ctx->twofish_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-
-	return lrw_crypt(desc, dst, src, nbytes, &req);
+	return glue_ecb_req_128bit(&twofish_dec, req);
 }
 
-static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int cbc_encrypt(struct skcipher_request *req)
 {
-	struct twofish_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	be128 buf[3];
-	struct lrw_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.table_ctx = &ctx->lrw_table,
-		.crypt_ctx = &ctx->twofish_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-
-	return lrw_crypt(desc, dst, src, nbytes, &req);
+	return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(twofish_enc_blk),
+					   req);
 }
 
-void lrw_twofish_exit_tfm(struct crypto_tfm *tfm)
+static int cbc_decrypt(struct skcipher_request *req)
 {
-	struct twofish_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	lrw_free_table(&ctx->lrw_table);
-}
-EXPORT_SYMBOL_GPL(lrw_twofish_exit_tfm);
-
-int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
-		       unsigned int keylen)
-{
-	struct twofish_xts_ctx *ctx = crypto_tfm_ctx(tfm);
-	u32 *flags = &tfm->crt_flags;
-	int err;
-
-	err = xts_check_key(tfm, key, keylen);
-	if (err)
-		return err;
-
-	/* first half of xts-key is for crypt */
-	err = __twofish_setkey(&ctx->crypt_ctx, key, keylen / 2, flags);
-	if (err)
-		return err;
-
-	/* second half of xts-key is for tweak */
-	return __twofish_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2,
-				flags);
-}
-EXPORT_SYMBOL_GPL(xts_twofish_setkey);
-
-static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	le128 buf[3];
-	struct xts_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.tweak_ctx = &ctx->tweak_ctx,
-		.tweak_fn = XTS_TWEAK_CAST(twofish_enc_blk),
-		.crypt_ctx = &ctx->crypt_ctx,
-		.crypt_fn = encrypt_callback,
-	};
-
-	return xts_crypt(desc, dst, src, nbytes, &req);
+	return glue_cbc_decrypt_req_128bit(&twofish_dec_cbc, req);
 }
 
-static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static int ctr_crypt(struct skcipher_request *req)
 {
-	struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	le128 buf[3];
-	struct xts_crypt_req req = {
-		.tbuf = buf,
-		.tbuflen = sizeof(buf),
-
-		.tweak_ctx = &ctx->tweak_ctx,
-		.tweak_fn = XTS_TWEAK_CAST(twofish_enc_blk),
-		.crypt_ctx = &ctx->crypt_ctx,
-		.crypt_fn = decrypt_callback,
-	};
-
-	return xts_crypt(desc, dst, src, nbytes, &req);
+	return glue_ctr_req_128bit(&twofish_ctr, req);
 }
 
-static struct crypto_alg tf_algs[5] = { {
-	.cra_name		= "ecb(twofish)",
-	.cra_driver_name	= "ecb-twofish-3way",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct twofish_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE,
-			.setkey		= twofish_setkey,
-			.encrypt	= ecb_encrypt,
-			.decrypt	= ecb_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "cbc(twofish)",
-	.cra_driver_name	= "cbc-twofish-3way",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct twofish_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= twofish_setkey,
-			.encrypt	= cbc_encrypt,
-			.decrypt	= cbc_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "ctr(twofish)",
-	.cra_driver_name	= "ctr-twofish-3way",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct twofish_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= twofish_setkey,
-			.encrypt	= ctr_crypt,
-			.decrypt	= ctr_crypt,
-		},
-	},
-}, {
-	.cra_name		= "lrw(twofish)",
-	.cra_driver_name	= "lrw-twofish-3way",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct twofish_lrw_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_exit		= lrw_twofish_exit_tfm,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE + TF_BLOCK_SIZE,
-			.max_keysize	= TF_MAX_KEY_SIZE + TF_BLOCK_SIZE,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= lrw_twofish_setkey,
-			.encrypt	= lrw_encrypt,
-			.decrypt	= lrw_decrypt,
-		},
-	},
-}, {
-	.cra_name		= "xts(twofish)",
-	.cra_driver_name	= "xts-twofish-3way",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-	.cra_blocksize		= TF_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct twofish_xts_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_blkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.blkcipher = {
-			.min_keysize	= TF_MIN_KEY_SIZE * 2,
-			.max_keysize	= TF_MAX_KEY_SIZE * 2,
-			.ivsize		= TF_BLOCK_SIZE,
-			.setkey		= xts_twofish_setkey,
-			.encrypt	= xts_encrypt,
-			.decrypt	= xts_decrypt,
-		},
+static struct skcipher_alg tf_skciphers[] = {
+	{
+		.base.cra_name		= "ecb(twofish)",
+		.base.cra_driver_name	= "ecb-twofish-3way",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= TF_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct twofish_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= TF_MIN_KEY_SIZE,
+		.max_keysize		= TF_MAX_KEY_SIZE,
+		.setkey			= twofish_setkey_skcipher,
+		.encrypt		= ecb_encrypt,
+		.decrypt		= ecb_decrypt,
+	}, {
+		.base.cra_name		= "cbc(twofish)",
+		.base.cra_driver_name	= "cbc-twofish-3way",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= TF_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct twofish_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= TF_MIN_KEY_SIZE,
+		.max_keysize		= TF_MAX_KEY_SIZE,
+		.ivsize			= TF_BLOCK_SIZE,
+		.setkey			= twofish_setkey_skcipher,
+		.encrypt		= cbc_encrypt,
+		.decrypt		= cbc_decrypt,
+	}, {
+		.base.cra_name		= "ctr(twofish)",
+		.base.cra_driver_name	= "ctr-twofish-3way",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct twofish_ctx),
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= TF_MIN_KEY_SIZE,
+		.max_keysize		= TF_MAX_KEY_SIZE,
+		.ivsize			= TF_BLOCK_SIZE,
+		.chunksize		= TF_BLOCK_SIZE,
+		.setkey			= twofish_setkey_skcipher,
+		.encrypt		= ctr_crypt,
+		.decrypt		= ctr_crypt,
 	},
-} };
+};
 
 static bool is_blacklisted_cpu(void)
 {
@@ -478,12 +272,13 @@ static int __init init(void)
 		return -ENODEV;
 	}
 
-	return crypto_register_algs(tf_algs, ARRAY_SIZE(tf_algs));
+	return crypto_register_skciphers(tf_skciphers,
+					 ARRAY_SIZE(tf_skciphers));
 }
 
 static void __exit fini(void)
 {
-	crypto_unregister_algs(tf_algs, ARRAY_SIZE(tf_algs));
+	crypto_unregister_skciphers(tf_skciphers, ARRAY_SIZE(tf_skciphers));
 }
 
 module_init(init);
diff --git a/arch/x86/include/asm/crypto/camellia.h b/arch/x86/include/asm/crypto/camellia.h
index 10f8d590bcfe..a5d86fc0593f 100644
--- a/arch/x86/include/asm/crypto/camellia.h
+++ b/arch/x86/include/asm/crypto/camellia.h
@@ -2,8 +2,9 @@
 #ifndef ASM_X86_CAMELLIA_H
 #define ASM_X86_CAMELLIA_H
 
-#include <linux/kernel.h>
+#include <crypto/b128ops.h>
 #include <linux/crypto.h>
+#include <linux/kernel.h>
 
 #define CAMELLIA_MIN_KEY_SIZE	16
 #define CAMELLIA_MAX_KEY_SIZE	32
@@ -11,16 +12,13 @@
 #define CAMELLIA_TABLE_BYTE_LEN	272
 #define CAMELLIA_PARALLEL_BLOCKS 2
 
+struct crypto_skcipher;
+
 struct camellia_ctx {
 	u64 key_table[CAMELLIA_TABLE_BYTE_LEN / sizeof(u64)];
 	u32 key_length;
 };
 
-struct camellia_lrw_ctx {
-	struct lrw_table_ctx lrw_table;
-	struct camellia_ctx camellia_ctx;
-};
-
 struct camellia_xts_ctx {
 	struct camellia_ctx tweak_ctx;
 	struct camellia_ctx crypt_ctx;
@@ -30,11 +28,7 @@ extern int __camellia_setkey(struct camellia_ctx *cctx,
 			     const unsigned char *key,
 			     unsigned int key_len, u32 *flags);
 
-extern int lrw_camellia_setkey(struct crypto_tfm *tfm, const u8 *key,
-			       unsigned int keylen);
-extern void lrw_camellia_exit_tfm(struct crypto_tfm *tfm);
-
-extern int xts_camellia_setkey(struct crypto_tfm *tfm, const u8 *key,
+extern int xts_camellia_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			       unsigned int keylen);
 
 /* regular block cipher functions */
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
index 553a03de55c3..d1818634ae7e 100644
--- a/arch/x86/include/asm/crypto/glue_helper.h
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -45,7 +45,7 @@ struct common_glue_ctx {
 };
 
 static inline bool glue_fpu_begin(unsigned int bsize, int fpu_blocks_limit,
-				  struct blkcipher_desc *desc,
+				  struct skcipher_walk *walk,
 				  bool fpu_enabled, unsigned int nbytes)
 {
 	if (likely(fpu_blocks_limit < 0))
@@ -61,33 +61,6 @@ static inline bool glue_fpu_begin(unsigned int bsize, int fpu_blocks_limit,
 	if (nbytes < bsize * (unsigned int)fpu_blocks_limit)
 		return false;
 
-	if (desc) {
-		/* prevent sleeping if FPU is in use */
-		desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-	}
-
-	kernel_fpu_begin();
-	return true;
-}
-
-static inline bool glue_skwalk_fpu_begin(unsigned int bsize,
-					 int fpu_blocks_limit,
-					 struct skcipher_walk *walk,
-					 bool fpu_enabled, unsigned int nbytes)
-{
-	if (likely(fpu_blocks_limit < 0))
-		return false;
-
-	if (fpu_enabled)
-		return true;
-
-	/*
-	 * Vector-registers are only used when chunk to be processed is large
-	 * enough, so do not enable FPU until it is necessary.
-	 */
-	if (nbytes < bsize * (unsigned int)fpu_blocks_limit)
-		return false;
-
 	/* prevent sleeping if FPU is in use */
 	skcipher_walk_atomise(walk);
 
@@ -126,41 +99,17 @@ static inline void le128_inc(le128 *i)
 	i->b = cpu_to_le64(b);
 }
 
-extern int glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
-				 struct blkcipher_desc *desc,
-				 struct scatterlist *dst,
-				 struct scatterlist *src, unsigned int nbytes);
-
-extern int glue_cbc_encrypt_128bit(const common_glue_func_t fn,
-				   struct blkcipher_desc *desc,
-				   struct scatterlist *dst,
-				   struct scatterlist *src,
-				   unsigned int nbytes);
-
-extern int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
-				   struct blkcipher_desc *desc,
-				   struct scatterlist *dst,
-				   struct scatterlist *src,
-				   unsigned int nbytes);
-
-extern int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
-				 struct blkcipher_desc *desc,
-				 struct scatterlist *dst,
-				 struct scatterlist *src, unsigned int nbytes);
-
-extern int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
-				 struct blkcipher_desc *desc,
-				 struct scatterlist *dst,
-				 struct scatterlist *src, unsigned int nbytes,
-				 common_glue_func_t tweak_fn, void *tweak_ctx,
-				 void *crypt_ctx);
-
-extern int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
-				 struct blkcipher_desc *desc,
-				 struct scatterlist *dst,
-				 struct scatterlist *src, unsigned int nbytes,
-				 common_glue_func_t tweak_fn, void *tweak_ctx,
-				 void *crypt_ctx);
+extern int glue_ecb_req_128bit(const struct common_glue_ctx *gctx,
+			       struct skcipher_request *req);
+
+extern int glue_cbc_encrypt_req_128bit(const common_glue_func_t fn,
+				       struct skcipher_request *req);
+
+extern int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx,
+				       struct skcipher_request *req);
+
+extern int glue_ctr_req_128bit(const struct common_glue_ctx *gctx,
+			       struct skcipher_request *req);
 
 extern int glue_xts_req_128bit(const struct common_glue_ctx *gctx,
 			       struct skcipher_request *req,
diff --git a/arch/x86/include/asm/crypto/serpent-avx.h b/arch/x86/include/asm/crypto/serpent-avx.h
index c958b7bd0fcb..db7c9cc32234 100644
--- a/arch/x86/include/asm/crypto/serpent-avx.h
+++ b/arch/x86/include/asm/crypto/serpent-avx.h
@@ -2,15 +2,13 @@
 #ifndef ASM_X86_SERPENT_AVX_H
 #define ASM_X86_SERPENT_AVX_H
 
-#include <linux/crypto.h>
+#include <crypto/b128ops.h>
 #include <crypto/serpent.h>
+#include <linux/types.h>
 
-#define SERPENT_PARALLEL_BLOCKS 8
+struct crypto_skcipher;
 
-struct serpent_lrw_ctx {
-	struct lrw_table_ctx lrw_table;
-	struct serpent_ctx serpent_ctx;
-};
+#define SERPENT_PARALLEL_BLOCKS 8
 
 struct serpent_xts_ctx {
 	struct serpent_ctx tweak_ctx;
@@ -38,12 +36,7 @@ extern void __serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src,
 extern void serpent_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv);
 extern void serpent_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv);
 
-extern int lrw_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen);
-
-extern void lrw_serpent_exit_tfm(struct crypto_tfm *tfm);
-
-extern int xts_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
+extern int xts_serpent_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			      unsigned int keylen);
 
 #endif
diff --git a/arch/x86/include/asm/crypto/twofish.h b/arch/x86/include/asm/crypto/twofish.h
index 65bb80adba3e..f618bf272b90 100644
--- a/arch/x86/include/asm/crypto/twofish.h
+++ b/arch/x86/include/asm/crypto/twofish.h
@@ -4,19 +4,8 @@
 
 #include <linux/crypto.h>
 #include <crypto/twofish.h>
-#include <crypto/lrw.h>
 #include <crypto/b128ops.h>
 
-struct twofish_lrw_ctx {
-	struct lrw_table_ctx lrw_table;
-	struct twofish_ctx twofish_ctx;
-};
-
-struct twofish_xts_ctx {
-	struct twofish_ctx tweak_ctx;
-	struct twofish_ctx crypt_ctx;
-};
-
 /* regular block cipher functions from twofish_x86_64 module */
 asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst,
 				const u8 *src);
@@ -36,12 +25,4 @@ extern void twofish_enc_blk_ctr(void *ctx, u128 *dst, const u128 *src,
 extern void twofish_enc_blk_ctr_3way(void *ctx, u128 *dst, const u128 *src,
 				     le128 *iv);
 
-extern int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen);
-
-extern void lrw_twofish_exit_tfm(struct crypto_tfm *tfm);
-
-extern int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen);
-
 #endif /* ASM_X86_TWOFISH_H */
diff --git a/crypto/Kconfig b/crypto/Kconfig
index b75264b09a46..c0dabed5122e 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -245,10 +245,6 @@ config CRYPTO_TEST
 	help
 	  Quick & dirty crypto test module.
 
-config CRYPTO_ABLK_HELPER
-	tristate
-	select CRYPTO_CRYPTD
-
 config CRYPTO_SIMD
 	tristate
 	select CRYPTO_CRYPTD
@@ -324,6 +320,14 @@ config CRYPTO_CBC
 	  CBC: Cipher Block Chaining mode
 	  This block cipher algorithm is required for IPSec.
 
+config CRYPTO_CFB
+	tristate "CFB support"
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_MANAGER
+	help
+	  CFB: Cipher FeedBack mode
+	  This block cipher algorithm is required for TPM2 Cryptography.
+
 config CRYPTO_CTR
 	tristate "CTR support"
 	select CRYPTO_BLKCIPHER
@@ -1114,7 +1118,7 @@ config CRYPTO_BLOWFISH_COMMON
 config CRYPTO_BLOWFISH_X86_64
 	tristate "Blowfish cipher algorithm (x86_64)"
 	depends on X86 && 64BIT
-	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_BLOWFISH_COMMON
 	help
 	  Blowfish cipher algorithm (x86_64), by Bruce Schneier.
@@ -1145,10 +1149,8 @@ config CRYPTO_CAMELLIA_X86_64
 	tristate "Camellia cipher algorithm (x86_64)"
 	depends on X86 && 64BIT
 	depends on CRYPTO
-	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_GLUE_HELPER_X86
-	select CRYPTO_LRW
-	select CRYPTO_XTS
 	help
 	  Camellia cipher algorithm module (x86_64).
 
@@ -1164,12 +1166,10 @@ config CRYPTO_CAMELLIA_AESNI_AVX_X86_64
 	tristate "Camellia cipher algorithm (x86_64/AES-NI/AVX)"
 	depends on X86 && 64BIT
 	depends on CRYPTO
-	select CRYPTO_ALGAPI
-	select CRYPTO_CRYPTD
-	select CRYPTO_ABLK_HELPER
-	select CRYPTO_GLUE_HELPER_X86
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_CAMELLIA_X86_64
-	select CRYPTO_LRW
+	select CRYPTO_GLUE_HELPER_X86
+	select CRYPTO_SIMD
 	select CRYPTO_XTS
 	help
 	  Camellia cipher algorithm module (x86_64/AES-NI/AVX).
@@ -1186,14 +1186,7 @@ config CRYPTO_CAMELLIA_AESNI_AVX2_X86_64
 	tristate "Camellia cipher algorithm (x86_64/AES-NI/AVX2)"
 	depends on X86 && 64BIT
 	depends on CRYPTO
-	select CRYPTO_ALGAPI
-	select CRYPTO_CRYPTD
-	select CRYPTO_ABLK_HELPER
-	select CRYPTO_GLUE_HELPER_X86
-	select CRYPTO_CAMELLIA_X86_64
 	select CRYPTO_CAMELLIA_AESNI_AVX_X86_64
-	select CRYPTO_LRW
-	select CRYPTO_XTS
 	help
 	  Camellia cipher algorithm module (x86_64/AES-NI/AVX2).
 
@@ -1238,11 +1231,10 @@ config CRYPTO_CAST5
 config CRYPTO_CAST5_AVX_X86_64
 	tristate "CAST5 (CAST-128) cipher algorithm (x86_64/AVX)"
 	depends on X86 && 64BIT
-	select CRYPTO_ALGAPI
-	select CRYPTO_CRYPTD
-	select CRYPTO_ABLK_HELPER
-	select CRYPTO_CAST_COMMON
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_CAST5
+	select CRYPTO_CAST_COMMON
+	select CRYPTO_SIMD
 	help
 	  The CAST5 encryption algorithm (synonymous with CAST-128) is
 	  described in RFC2144.
@@ -1261,13 +1253,11 @@ config CRYPTO_CAST6
 config CRYPTO_CAST6_AVX_X86_64
 	tristate "CAST6 (CAST-256) cipher algorithm (x86_64/AVX)"
 	depends on X86 && 64BIT
-	select CRYPTO_ALGAPI
-	select CRYPTO_CRYPTD
-	select CRYPTO_ABLK_HELPER
-	select CRYPTO_GLUE_HELPER_X86
-	select CRYPTO_CAST_COMMON
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_CAST6
-	select CRYPTO_LRW
+	select CRYPTO_CAST_COMMON
+	select CRYPTO_GLUE_HELPER_X86
+	select CRYPTO_SIMD
 	select CRYPTO_XTS
 	help
 	  The CAST6 encryption algorithm (synonymous with CAST-256) is
@@ -1294,7 +1284,7 @@ config CRYPTO_DES_SPARC64
 config CRYPTO_DES3_EDE_X86_64
 	tristate "Triple DES EDE cipher algorithm (x86-64)"
 	depends on X86 && 64BIT
-	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_DES
 	help
 	  Triple DES EDE (FIPS 46-3) algorithm.
@@ -1422,13 +1412,10 @@ config CRYPTO_SERPENT
 config CRYPTO_SERPENT_SSE2_X86_64
 	tristate "Serpent cipher algorithm (x86_64/SSE2)"
 	depends on X86 && 64BIT
-	select CRYPTO_ALGAPI
-	select CRYPTO_CRYPTD
-	select CRYPTO_ABLK_HELPER
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SERPENT
-	select CRYPTO_LRW
-	select CRYPTO_XTS
+	select CRYPTO_SIMD
 	help
 	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
 
@@ -1444,13 +1431,10 @@ config CRYPTO_SERPENT_SSE2_X86_64
 config CRYPTO_SERPENT_SSE2_586
 	tristate "Serpent cipher algorithm (i586/SSE2)"
 	depends on X86 && !64BIT
-	select CRYPTO_ALGAPI
-	select CRYPTO_CRYPTD
-	select CRYPTO_ABLK_HELPER
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SERPENT
-	select CRYPTO_LRW
-	select CRYPTO_XTS
+	select CRYPTO_SIMD
 	help
 	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
 
@@ -1466,12 +1450,10 @@ config CRYPTO_SERPENT_SSE2_586
 config CRYPTO_SERPENT_AVX_X86_64
 	tristate "Serpent cipher algorithm (x86_64/AVX)"
 	depends on X86 && 64BIT
-	select CRYPTO_ALGAPI
-	select CRYPTO_CRYPTD
-	select CRYPTO_ABLK_HELPER
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SERPENT
-	select CRYPTO_LRW
+	select CRYPTO_SIMD
 	select CRYPTO_XTS
 	help
 	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
@@ -1488,14 +1470,7 @@ config CRYPTO_SERPENT_AVX_X86_64
 config CRYPTO_SERPENT_AVX2_X86_64
 	tristate "Serpent cipher algorithm (x86_64/AVX2)"
 	depends on X86 && 64BIT
-	select CRYPTO_ALGAPI
-	select CRYPTO_CRYPTD
-	select CRYPTO_ABLK_HELPER
-	select CRYPTO_GLUE_HELPER_X86
-	select CRYPTO_SERPENT
 	select CRYPTO_SERPENT_AVX_X86_64
-	select CRYPTO_LRW
-	select CRYPTO_XTS
 	help
 	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
 
@@ -1508,6 +1483,45 @@ config CRYPTO_SERPENT_AVX2_X86_64
 	  See also:
 	  <http://www.cl.cam.ac.uk/~rja14/serpent.html>
 
+config CRYPTO_SM4
+	tristate "SM4 cipher algorithm"
+	select CRYPTO_ALGAPI
+	help
+	  SM4 cipher algorithms (OSCCA GB/T 32907-2016).
+
+	  SM4 (GBT.32907-2016) is a cryptographic standard issued by the
+	  Organization of State Commercial Administration of China (OSCCA)
+	  as an authorized cryptographic algorithms for the use within China.
+
+	  SMS4 was originally created for use in protecting wireless
+	  networks, and is mandated in the Chinese National Standard for
+	  Wireless LAN WAPI (Wired Authentication and Privacy Infrastructure)
+	  (GB.15629.11-2003).
+
+	  The latest SM4 standard (GBT.32907-2016) was proposed by OSCCA and
+	  standardized through TC 260 of the Standardization Administration
+	  of the People's Republic of China (SAC).
+
+	  The input, output, and key of SMS4 are each 128 bits.
+
+	  See also: <https://eprint.iacr.org/2008/329.pdf>
+
+	  If unsure, say N.
+
+config CRYPTO_SPECK
+	tristate "Speck cipher algorithm"
+	select CRYPTO_ALGAPI
+	help
+	  Speck is a lightweight block cipher that is tuned for optimal
+	  performance in software (rather than hardware).
+
+	  Speck may not be as secure as AES, and should only be used on systems
+	  where AES is not fast enough.
+
+	  See also: <https://eprint.iacr.org/2013/404.pdf>
+
+	  If unsure, say N.
+
 config CRYPTO_TEA
 	tristate "TEA, XTEA and XETA cipher algorithms"
 	select CRYPTO_ALGAPI
@@ -1581,12 +1595,10 @@ config CRYPTO_TWOFISH_X86_64
 config CRYPTO_TWOFISH_X86_64_3WAY
 	tristate "Twofish cipher algorithm (x86_64, 3-way parallel)"
 	depends on X86 && 64BIT
-	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_TWOFISH_COMMON
 	select CRYPTO_TWOFISH_X86_64
 	select CRYPTO_GLUE_HELPER_X86
-	select CRYPTO_LRW
-	select CRYPTO_XTS
 	help
 	  Twofish cipher algorithm (x86_64, 3-way parallel).
 
@@ -1604,15 +1616,12 @@ config CRYPTO_TWOFISH_X86_64_3WAY
 config CRYPTO_TWOFISH_AVX_X86_64
 	tristate "Twofish cipher algorithm (x86_64/AVX)"
 	depends on X86 && 64BIT
-	select CRYPTO_ALGAPI
-	select CRYPTO_CRYPTD
-	select CRYPTO_ABLK_HELPER
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_GLUE_HELPER_X86
+	select CRYPTO_SIMD
 	select CRYPTO_TWOFISH_COMMON
 	select CRYPTO_TWOFISH_X86_64
 	select CRYPTO_TWOFISH_X86_64_3WAY
-	select CRYPTO_LRW
-	select CRYPTO_XTS
 	help
 	  Twofish cipher algorithm (x86_64/AVX).
 
diff --git a/crypto/Makefile b/crypto/Makefile
index cdbc03b35510..4fc69fe94e6a 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -78,6 +78,7 @@ obj-$(CONFIG_CRYPTO_TGR192) += tgr192.o
 obj-$(CONFIG_CRYPTO_GF128MUL) += gf128mul.o
 obj-$(CONFIG_CRYPTO_ECB) += ecb.o
 obj-$(CONFIG_CRYPTO_CBC) += cbc.o
+obj-$(CONFIG_CRYPTO_CFB) += cfb.o
 obj-$(CONFIG_CRYPTO_PCBC) += pcbc.o
 obj-$(CONFIG_CRYPTO_CTS) += cts.o
 obj-$(CONFIG_CRYPTO_LRW) += lrw.o
@@ -100,6 +101,7 @@ obj-$(CONFIG_CRYPTO_SERPENT) += serpent_generic.o
 CFLAGS_serpent_generic.o := $(call cc-option,-fsched-pressure)  # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149
 obj-$(CONFIG_CRYPTO_AES) += aes_generic.o
 CFLAGS_aes_generic.o := $(call cc-option,-fno-code-hoisting) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83356
+obj-$(CONFIG_CRYPTO_SM4) += sm4_generic.o
 obj-$(CONFIG_CRYPTO_AES_TI) += aes_ti.o
 obj-$(CONFIG_CRYPTO_CAMELLIA) += camellia_generic.o
 obj-$(CONFIG_CRYPTO_CAST_COMMON) += cast_common.o
@@ -110,6 +112,7 @@ obj-$(CONFIG_CRYPTO_TEA) += tea.o
 obj-$(CONFIG_CRYPTO_KHAZAD) += khazad.o
 obj-$(CONFIG_CRYPTO_ANUBIS) += anubis.o
 obj-$(CONFIG_CRYPTO_SEED) += seed.o
+obj-$(CONFIG_CRYPTO_SPECK) += speck.o
 obj-$(CONFIG_CRYPTO_SALSA20) += salsa20_generic.o
 obj-$(CONFIG_CRYPTO_CHACHA20) += chacha20_generic.o
 obj-$(CONFIG_CRYPTO_POLY1305) += poly1305_generic.o
@@ -149,6 +152,5 @@ obj-$(CONFIG_XOR_BLOCKS) += xor.o
 obj-$(CONFIG_ASYNC_CORE) += async_tx/
 obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += asymmetric_keys/
 obj-$(CONFIG_CRYPTO_HASH_INFO) += hash_info.o
-obj-$(CONFIG_CRYPTO_ABLK_HELPER) += ablk_helper.o
 crypto_simd-y := simd.o
 obj-$(CONFIG_CRYPTO_SIMD) += crypto_simd.o
diff --git a/crypto/ablk_helper.c b/crypto/ablk_helper.c
deleted file mode 100644
index 09776bb1360e..000000000000
--- a/crypto/ablk_helper.c
+++ /dev/null
@@ -1,150 +0,0 @@
-/*
- * Shared async block cipher helpers
- *
- * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
- *
- * Based on aesni-intel_glue.c by:
- *  Copyright (C) 2008, Intel Corp.
- *    Author: Huang Ying <ying.huang@intel.com>
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/crypto.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <crypto/algapi.h>
-#include <crypto/cryptd.h>
-#include <crypto/ablk_helper.h>
-#include <asm/simd.h>
-
-int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
-		 unsigned int key_len)
-{
-	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base;
-	int err;
-
-	crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm)
-				    & CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(child, key, key_len);
-	crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child)
-				    & CRYPTO_TFM_RES_MASK);
-	return err;
-}
-EXPORT_SYMBOL_GPL(ablk_set_key);
-
-int __ablk_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct blkcipher_desc desc;
-
-	desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
-	desc.info = req->info;
-	desc.flags = 0;
-
-	return crypto_blkcipher_crt(desc.tfm)->encrypt(
-		&desc, req->dst, req->src, req->nbytes);
-}
-EXPORT_SYMBOL_GPL(__ablk_encrypt);
-
-int ablk_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-
-	if (!may_use_simd() ||
-	    (in_atomic() && cryptd_ablkcipher_queued(ctx->cryptd_tfm))) {
-		struct ablkcipher_request *cryptd_req =
-			ablkcipher_request_ctx(req);
-
-		*cryptd_req = *req;
-		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-
-		return crypto_ablkcipher_encrypt(cryptd_req);
-	} else {
-		return __ablk_encrypt(req);
-	}
-}
-EXPORT_SYMBOL_GPL(ablk_encrypt);
-
-int ablk_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-
-	if (!may_use_simd() ||
-	    (in_atomic() && cryptd_ablkcipher_queued(ctx->cryptd_tfm))) {
-		struct ablkcipher_request *cryptd_req =
-			ablkcipher_request_ctx(req);
-
-		*cryptd_req = *req;
-		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-
-		return crypto_ablkcipher_decrypt(cryptd_req);
-	} else {
-		struct blkcipher_desc desc;
-
-		desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
-		desc.info = req->info;
-		desc.flags = 0;
-
-		return crypto_blkcipher_crt(desc.tfm)->decrypt(
-			&desc, req->dst, req->src, req->nbytes);
-	}
-}
-EXPORT_SYMBOL_GPL(ablk_decrypt);
-
-void ablk_exit(struct crypto_tfm *tfm)
-{
-	struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	cryptd_free_ablkcipher(ctx->cryptd_tfm);
-}
-EXPORT_SYMBOL_GPL(ablk_exit);
-
-int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name)
-{
-	struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct cryptd_ablkcipher *cryptd_tfm;
-
-	cryptd_tfm = cryptd_alloc_ablkcipher(drv_name, CRYPTO_ALG_INTERNAL,
-					     CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	ctx->cryptd_tfm = cryptd_tfm;
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
-		crypto_ablkcipher_reqsize(&cryptd_tfm->base);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(ablk_init_common);
-
-int ablk_init(struct crypto_tfm *tfm)
-{
-	char drv_name[CRYPTO_MAX_ALG_NAME];
-
-	snprintf(drv_name, sizeof(drv_name), "__driver-%s",
-					crypto_tfm_alg_driver_name(tfm));
-
-	return ablk_init_common(tfm, drv_name);
-}
-EXPORT_SYMBOL_GPL(ablk_init);
-
-MODULE_LICENSE("GPL");
diff --git a/crypto/ahash.c b/crypto/ahash.c
index 266fc1d64f61..a64c143165b1 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -92,13 +92,14 @@ int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err)
 
 	if (nbytes && walk->offset & alignmask && !err) {
 		walk->offset = ALIGN(walk->offset, alignmask + 1);
-		walk->data += walk->offset;
-
 		nbytes = min(nbytes,
 			     ((unsigned int)(PAGE_SIZE)) - walk->offset);
 		walk->entrylen -= nbytes;
 
-		return nbytes;
+		if (nbytes) {
+			walk->data += walk->offset;
+			return nbytes;
+		}
 	}
 
 	if (walk->flags & CRYPTO_ALG_ASYNC)
@@ -446,24 +447,12 @@ static int ahash_def_finup(struct ahash_request *req)
 	return ahash_def_finup_finish1(req, err);
 }
 
-static int ahash_no_export(struct ahash_request *req, void *out)
-{
-	return -ENOSYS;
-}
-
-static int ahash_no_import(struct ahash_request *req, const void *in)
-{
-	return -ENOSYS;
-}
-
 static int crypto_ahash_init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_ahash *hash = __crypto_ahash_cast(tfm);
 	struct ahash_alg *alg = crypto_ahash_alg(hash);
 
 	hash->setkey = ahash_nosetkey;
-	hash->export = ahash_no_export;
-	hash->import = ahash_no_import;
 
 	if (tfm->__crt_alg->cra_type != &crypto_ahash_type)
 		return crypto_init_shash_ops_async(tfm);
@@ -473,16 +462,14 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm)
 	hash->final = alg->final;
 	hash->finup = alg->finup ?: ahash_def_finup;
 	hash->digest = alg->digest;
+	hash->export = alg->export;
+	hash->import = alg->import;
 
 	if (alg->setkey) {
 		hash->setkey = alg->setkey;
 		if (!(alg->halg.base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY))
 			crypto_ahash_set_flags(hash, CRYPTO_TFM_NEED_KEY);
 	}
-	if (alg->export)
-		hash->export = alg->export;
-	if (alg->import)
-		hash->import = alg->import;
 
 	return 0;
 }
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 395b082d03a9..2a0271b5f62a 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -543,9 +543,6 @@ int crypto_register_instance(struct crypto_template *tmpl,
 	inst->alg.cra_module = tmpl->module;
 	inst->alg.cra_flags |= CRYPTO_ALG_INSTANCE;
 
-	if (unlikely(!crypto_mod_get(&inst->alg)))
-		return -EAGAIN;
-
 	down_write(&crypto_alg_sem);
 
 	larval = __crypto_register_alg(&inst->alg);
@@ -563,14 +560,9 @@ unlock:
 		goto err;
 
 	crypto_wait_for_test(larval);
-
-	/* Remove instance if test failed */
-	if (!(inst->alg.cra_flags & CRYPTO_ALG_TESTED))
-		crypto_unregister_instance(inst);
 	err = 0;
 
 err:
-	crypto_mod_put(&inst->alg);
 	return err;
 }
 EXPORT_SYMBOL_GPL(crypto_register_instance);
diff --git a/crypto/api.c b/crypto/api.c
index 70a894e52ff3..1d5290c67108 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -193,17 +193,24 @@ static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg)
 	return alg;
 }
 
-struct crypto_alg *crypto_alg_lookup(const char *name, u32 type, u32 mask)
+static struct crypto_alg *crypto_alg_lookup(const char *name, u32 type,
+					    u32 mask)
 {
 	struct crypto_alg *alg;
+	u32 test = 0;
+
+	if (!((type | mask) & CRYPTO_ALG_TESTED))
+		test |= CRYPTO_ALG_TESTED;
 
 	down_read(&crypto_alg_sem);
-	alg = __crypto_alg_lookup(name, type, mask);
+	alg = __crypto_alg_lookup(name, type | test, mask | test);
+	if (!alg && test)
+		alg = __crypto_alg_lookup(name, type, mask) ?
+		      ERR_PTR(-ELIBBAD) : NULL;
 	up_read(&crypto_alg_sem);
 
 	return alg;
 }
-EXPORT_SYMBOL_GPL(crypto_alg_lookup);
 
 static struct crypto_alg *crypto_larval_lookup(const char *name, u32 type,
 					       u32 mask)
@@ -227,10 +234,12 @@ static struct crypto_alg *crypto_larval_lookup(const char *name, u32 type,
 		alg = crypto_alg_lookup(name, type, mask);
 	}
 
-	if (alg)
-		return crypto_is_larval(alg) ? crypto_larval_wait(alg) : alg;
+	if (!IS_ERR_OR_NULL(alg) && crypto_is_larval(alg))
+		alg = crypto_larval_wait(alg);
+	else if (!alg)
+		alg = crypto_larval_add(name, type, mask);
 
-	return crypto_larval_add(name, type, mask);
+	return alg;
 }
 
 int crypto_probing_notify(unsigned long val, void *v)
@@ -253,11 +262,6 @@ struct crypto_alg *crypto_alg_mod_lookup(const char *name, u32 type, u32 mask)
 	struct crypto_alg *larval;
 	int ok;
 
-	if (!((type | mask) & CRYPTO_ALG_TESTED)) {
-		type |= CRYPTO_ALG_TESTED;
-		mask |= CRYPTO_ALG_TESTED;
-	}
-
 	/*
 	 * If the internal flag is set for a cipher, require a caller to
 	 * to invoke the cipher with the internal flag to use that cipher.
@@ -485,20 +489,14 @@ struct crypto_alg *crypto_find_alg(const char *alg_name,
 				   const struct crypto_type *frontend,
 				   u32 type, u32 mask)
 {
-	struct crypto_alg *(*lookup)(const char *name, u32 type, u32 mask) =
-		crypto_alg_mod_lookup;
-
 	if (frontend) {
 		type &= frontend->maskclear;
 		mask &= frontend->maskclear;
 		type |= frontend->type;
 		mask |= frontend->maskset;
-
-		if (frontend->lookup)
-			lookup = frontend->lookup;
 	}
 
-	return lookup(alg_name, type, mask);
+	return crypto_alg_mod_lookup(alg_name, type, mask);
 }
 EXPORT_SYMBOL_GPL(crypto_find_alg);
 
diff --git a/crypto/cfb.c b/crypto/cfb.c
new file mode 100644
index 000000000000..94ee39bed758
--- /dev/null
+++ b/crypto/cfb.c
@@ -0,0 +1,353 @@
+//SPDX-License-Identifier: GPL-2.0
+/*
+ * CFB: Cipher FeedBack mode
+ *
+ * Copyright (c) 2018 James.Bottomley@HansenPartnership.com
+ *
+ * CFB is a stream cipher mode which is layered on to a block
+ * encryption scheme.  It works very much like a one time pad where
+ * the pad is generated initially from the encrypted IV and then
+ * subsequently from the encrypted previous block of ciphertext.  The
+ * pad is XOR'd into the plain text to get the final ciphertext.
+ *
+ * The scheme of CFB is best described by wikipedia:
+ *
+ * https://en.wikipedia.org/wiki/Block_cipher_mode_of_operation#CFB
+ *
+ * Note that since the pad for both encryption and decryption is
+ * generated by an encryption operation, CFB never uses the block
+ * decryption function.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+struct crypto_cfb_ctx {
+	struct crypto_cipher *child;
+};
+
+static unsigned int crypto_cfb_bsize(struct crypto_skcipher *tfm)
+{
+	struct crypto_cfb_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_cipher *child = ctx->child;
+
+	return crypto_cipher_blocksize(child);
+}
+
+static void crypto_cfb_encrypt_one(struct crypto_skcipher *tfm,
+					  const u8 *src, u8 *dst)
+{
+	struct crypto_cfb_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	crypto_cipher_encrypt_one(ctx->child, dst, src);
+}
+
+/* final encrypt and decrypt is the same */
+static void crypto_cfb_final(struct skcipher_walk *walk,
+			     struct crypto_skcipher *tfm)
+{
+	const unsigned int bsize = crypto_cfb_bsize(tfm);
+	const unsigned long alignmask = crypto_skcipher_alignmask(tfm);
+	u8 tmp[bsize + alignmask];
+	u8 *stream = PTR_ALIGN(tmp + 0, alignmask + 1);
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	u8 *iv = walk->iv;
+	unsigned int nbytes = walk->nbytes;
+
+	crypto_cfb_encrypt_one(tfm, iv, stream);
+	crypto_xor_cpy(dst, stream, src, nbytes);
+}
+
+static int crypto_cfb_encrypt_segment(struct skcipher_walk *walk,
+				      struct crypto_skcipher *tfm)
+{
+	const unsigned int bsize = crypto_cfb_bsize(tfm);
+	unsigned int nbytes = walk->nbytes;
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	u8 *iv = walk->iv;
+
+	do {
+		crypto_cfb_encrypt_one(tfm, iv, dst);
+		crypto_xor(dst, src, bsize);
+		memcpy(iv, dst, bsize);
+
+		src += bsize;
+		dst += bsize;
+	} while ((nbytes -= bsize) >= bsize);
+
+	return nbytes;
+}
+
+static int crypto_cfb_encrypt_inplace(struct skcipher_walk *walk,
+				      struct crypto_skcipher *tfm)
+{
+	const unsigned int bsize = crypto_cfb_bsize(tfm);
+	unsigned int nbytes = walk->nbytes;
+	u8 *src = walk->src.virt.addr;
+	u8 *iv = walk->iv;
+	u8 tmp[bsize];
+
+	do {
+		crypto_cfb_encrypt_one(tfm, iv, tmp);
+		crypto_xor(src, tmp, bsize);
+		iv = src;
+
+		src += bsize;
+	} while ((nbytes -= bsize) >= bsize);
+
+	memcpy(walk->iv, iv, bsize);
+
+	return nbytes;
+}
+
+static int crypto_cfb_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_walk walk;
+	unsigned int bsize = crypto_cfb_bsize(tfm);
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while (walk.nbytes >= bsize) {
+		if (walk.src.virt.addr == walk.dst.virt.addr)
+			err = crypto_cfb_encrypt_inplace(&walk, tfm);
+		else
+			err = crypto_cfb_encrypt_segment(&walk, tfm);
+		err = skcipher_walk_done(&walk, err);
+	}
+
+	if (walk.nbytes) {
+		crypto_cfb_final(&walk, tfm);
+		err = skcipher_walk_done(&walk, 0);
+	}
+
+	return err;
+}
+
+static int crypto_cfb_decrypt_segment(struct skcipher_walk *walk,
+				      struct crypto_skcipher *tfm)
+{
+	const unsigned int bsize = crypto_cfb_bsize(tfm);
+	unsigned int nbytes = walk->nbytes;
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	u8 *iv = walk->iv;
+
+	do {
+		crypto_cfb_encrypt_one(tfm, iv, dst);
+		crypto_xor(dst, iv, bsize);
+		iv = src;
+
+		src += bsize;
+		dst += bsize;
+	} while ((nbytes -= bsize) >= bsize);
+
+	memcpy(walk->iv, iv, bsize);
+
+	return nbytes;
+}
+
+static int crypto_cfb_decrypt_inplace(struct skcipher_walk *walk,
+				      struct crypto_skcipher *tfm)
+{
+	const unsigned int bsize = crypto_cfb_bsize(tfm);
+	unsigned int nbytes = walk->nbytes;
+	u8 *src = walk->src.virt.addr;
+	u8 *iv = walk->iv;
+	u8 tmp[bsize];
+
+	do {
+		crypto_cfb_encrypt_one(tfm, iv, tmp);
+		memcpy(iv, src, bsize);
+		crypto_xor(src, tmp, bsize);
+		src += bsize;
+	} while ((nbytes -= bsize) >= bsize);
+
+	memcpy(walk->iv, iv, bsize);
+
+	return nbytes;
+}
+
+static int crypto_cfb_decrypt_blocks(struct skcipher_walk *walk,
+				     struct crypto_skcipher *tfm)
+{
+	if (walk->src.virt.addr == walk->dst.virt.addr)
+		return crypto_cfb_decrypt_inplace(walk, tfm);
+	else
+		return crypto_cfb_decrypt_segment(walk, tfm);
+}
+
+static int crypto_cfb_setkey(struct crypto_skcipher *parent, const u8 *key,
+			     unsigned int keylen)
+{
+	struct crypto_cfb_ctx *ctx = crypto_skcipher_ctx(parent);
+	struct crypto_cipher *child = ctx->child;
+	int err;
+
+	crypto_cipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_cipher_set_flags(child, crypto_skcipher_get_flags(parent) &
+				       CRYPTO_TFM_REQ_MASK);
+	err = crypto_cipher_setkey(child, key, keylen);
+	crypto_skcipher_set_flags(parent, crypto_cipher_get_flags(child) &
+					  CRYPTO_TFM_RES_MASK);
+	return err;
+}
+
+static int crypto_cfb_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_walk walk;
+	const unsigned int bsize = crypto_cfb_bsize(tfm);
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while (walk.nbytes >= bsize) {
+		err = crypto_cfb_decrypt_blocks(&walk, tfm);
+		err = skcipher_walk_done(&walk, err);
+	}
+
+	if (walk.nbytes) {
+		crypto_cfb_final(&walk, tfm);
+		err = skcipher_walk_done(&walk, 0);
+	}
+
+	return err;
+}
+
+static int crypto_cfb_init_tfm(struct crypto_skcipher *tfm)
+{
+	struct skcipher_instance *inst = skcipher_alg_instance(tfm);
+	struct crypto_spawn *spawn = skcipher_instance_ctx(inst);
+	struct crypto_cfb_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_cipher *cipher;
+
+	cipher = crypto_spawn_cipher(spawn);
+	if (IS_ERR(cipher))
+		return PTR_ERR(cipher);
+
+	ctx->child = cipher;
+	return 0;
+}
+
+static void crypto_cfb_exit_tfm(struct crypto_skcipher *tfm)
+{
+	struct crypto_cfb_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	crypto_free_cipher(ctx->child);
+}
+
+static void crypto_cfb_free(struct skcipher_instance *inst)
+{
+	crypto_drop_skcipher(skcipher_instance_ctx(inst));
+	kfree(inst);
+}
+
+static int crypto_cfb_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct skcipher_instance *inst;
+	struct crypto_attr_type *algt;
+	struct crypto_spawn *spawn;
+	struct crypto_alg *alg;
+	u32 mask;
+	int err;
+
+	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SKCIPHER);
+	if (err)
+		return err;
+
+	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	algt = crypto_get_attr_type(tb);
+	err = PTR_ERR(algt);
+	if (IS_ERR(algt))
+		goto err_free_inst;
+
+	mask = CRYPTO_ALG_TYPE_MASK |
+		crypto_requires_off(algt->type, algt->mask,
+				    CRYPTO_ALG_NEED_FALLBACK);
+
+	alg = crypto_get_attr_alg(tb, CRYPTO_ALG_TYPE_CIPHER, mask);
+	err = PTR_ERR(alg);
+	if (IS_ERR(alg))
+		goto err_free_inst;
+
+	spawn = skcipher_instance_ctx(inst);
+	err = crypto_init_spawn(spawn, alg, skcipher_crypto_instance(inst),
+				CRYPTO_ALG_TYPE_MASK);
+	crypto_mod_put(alg);
+	if (err)
+		goto err_free_inst;
+
+	err = crypto_inst_setname(skcipher_crypto_instance(inst), "cfb", alg);
+	if (err)
+		goto err_drop_spawn;
+
+	inst->alg.base.cra_priority = alg->cra_priority;
+	/* we're a stream cipher independend of the crypto cra_blocksize */
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = alg->cra_alignmask;
+
+	inst->alg.ivsize = alg->cra_blocksize;
+	inst->alg.min_keysize = alg->cra_cipher.cia_min_keysize;
+	inst->alg.max_keysize = alg->cra_cipher.cia_max_keysize;
+
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_cfb_ctx);
+
+	inst->alg.init = crypto_cfb_init_tfm;
+	inst->alg.exit = crypto_cfb_exit_tfm;
+
+	inst->alg.setkey = crypto_cfb_setkey;
+	inst->alg.encrypt = crypto_cfb_encrypt;
+	inst->alg.decrypt = crypto_cfb_decrypt;
+
+	inst->free = crypto_cfb_free;
+
+	err = skcipher_register_instance(tmpl, inst);
+	if (err)
+		goto err_drop_spawn;
+
+out:
+	return err;
+
+err_drop_spawn:
+	crypto_drop_spawn(spawn);
+err_free_inst:
+	kfree(inst);
+	goto out;
+}
+
+static struct crypto_template crypto_cfb_tmpl = {
+	.name = "cfb",
+	.create = crypto_cfb_create,
+	.module = THIS_MODULE,
+};
+
+static int __init crypto_cfb_module_init(void)
+{
+	return crypto_register_template(&crypto_cfb_tmpl);
+}
+
+static void __exit crypto_cfb_module_exit(void)
+{
+	crypto_unregister_template(&crypto_cfb_tmpl);
+}
+
+module_init(crypto_cfb_module_init);
+module_exit(crypto_cfb_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("CFB block cipher algorithm");
+MODULE_ALIAS_CRYPTO("cfb");
diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c
index 61e7c4e02fd2..992e8d8dcdd9 100644
--- a/crypto/crypto_engine.c
+++ b/crypto/crypto_engine.c
@@ -15,13 +15,50 @@
 #include <linux/err.h>
 #include <linux/delay.h>
 #include <crypto/engine.h>
-#include <crypto/internal/hash.h>
 #include <uapi/linux/sched/types.h>
 #include "internal.h"
 
 #define CRYPTO_ENGINE_MAX_QLEN 10
 
 /**
+ * crypto_finalize_request - finalize one request if the request is done
+ * @engine: the hardware engine
+ * @req: the request need to be finalized
+ * @err: error number
+ */
+static void crypto_finalize_request(struct crypto_engine *engine,
+			     struct crypto_async_request *req, int err)
+{
+	unsigned long flags;
+	bool finalize_cur_req = false;
+	int ret;
+	struct crypto_engine_ctx *enginectx;
+
+	spin_lock_irqsave(&engine->queue_lock, flags);
+	if (engine->cur_req == req)
+		finalize_cur_req = true;
+	spin_unlock_irqrestore(&engine->queue_lock, flags);
+
+	if (finalize_cur_req) {
+		enginectx = crypto_tfm_ctx(req->tfm);
+		if (engine->cur_req_prepared &&
+		    enginectx->op.unprepare_request) {
+			ret = enginectx->op.unprepare_request(engine, req);
+			if (ret)
+				dev_err(engine->dev, "failed to unprepare request\n");
+		}
+		spin_lock_irqsave(&engine->queue_lock, flags);
+		engine->cur_req = NULL;
+		engine->cur_req_prepared = false;
+		spin_unlock_irqrestore(&engine->queue_lock, flags);
+	}
+
+	req->complete(req, err);
+
+	kthread_queue_work(engine->kworker, &engine->pump_requests);
+}
+
+/**
  * crypto_pump_requests - dequeue one request from engine queue to process
  * @engine: the hardware engine
  * @in_kthread: true if we are in the context of the request pump thread
@@ -34,11 +71,10 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 				 bool in_kthread)
 {
 	struct crypto_async_request *async_req, *backlog;
-	struct ahash_request *hreq;
-	struct ablkcipher_request *breq;
 	unsigned long flags;
 	bool was_busy = false;
-	int ret, rtype;
+	int ret;
+	struct crypto_engine_ctx *enginectx;
 
 	spin_lock_irqsave(&engine->queue_lock, flags);
 
@@ -94,7 +130,6 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 
 	spin_unlock_irqrestore(&engine->queue_lock, flags);
 
-	rtype = crypto_tfm_alg_type(engine->cur_req->tfm);
 	/* Until here we get the request need to be encrypted successfully */
 	if (!was_busy && engine->prepare_crypt_hardware) {
 		ret = engine->prepare_crypt_hardware(engine);
@@ -104,57 +139,31 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 		}
 	}
 
-	switch (rtype) {
-	case CRYPTO_ALG_TYPE_AHASH:
-		hreq = ahash_request_cast(engine->cur_req);
-		if (engine->prepare_hash_request) {
-			ret = engine->prepare_hash_request(engine, hreq);
-			if (ret) {
-				dev_err(engine->dev, "failed to prepare request: %d\n",
-					ret);
-				goto req_err;
-			}
-			engine->cur_req_prepared = true;
-		}
-		ret = engine->hash_one_request(engine, hreq);
-		if (ret) {
-			dev_err(engine->dev, "failed to hash one request from queue\n");
-			goto req_err;
-		}
-		return;
-	case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		breq = ablkcipher_request_cast(engine->cur_req);
-		if (engine->prepare_cipher_request) {
-			ret = engine->prepare_cipher_request(engine, breq);
-			if (ret) {
-				dev_err(engine->dev, "failed to prepare request: %d\n",
-					ret);
-				goto req_err;
-			}
-			engine->cur_req_prepared = true;
-		}
-		ret = engine->cipher_one_request(engine, breq);
+	enginectx = crypto_tfm_ctx(async_req->tfm);
+
+	if (enginectx->op.prepare_request) {
+		ret = enginectx->op.prepare_request(engine, async_req);
 		if (ret) {
-			dev_err(engine->dev, "failed to cipher one request from queue\n");
+			dev_err(engine->dev, "failed to prepare request: %d\n",
+				ret);
 			goto req_err;
 		}
-		return;
-	default:
-		dev_err(engine->dev, "failed to prepare request of unknown type\n");
-		return;
+		engine->cur_req_prepared = true;
+	}
+	if (!enginectx->op.do_one_request) {
+		dev_err(engine->dev, "failed to do request\n");
+		ret = -EINVAL;
+		goto req_err;
 	}
+	ret = enginectx->op.do_one_request(engine, async_req);
+	if (ret) {
+		dev_err(engine->dev, "Failed to do one request from queue: %d\n", ret);
+		goto req_err;
+	}
+	return;
 
 req_err:
-	switch (rtype) {
-	case CRYPTO_ALG_TYPE_AHASH:
-		hreq = ahash_request_cast(engine->cur_req);
-		crypto_finalize_hash_request(engine, hreq, ret);
-		break;
-	case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		breq = ablkcipher_request_cast(engine->cur_req);
-		crypto_finalize_cipher_request(engine, breq, ret);
-		break;
-	}
+	crypto_finalize_request(engine, async_req, ret);
 	return;
 
 out:
@@ -170,13 +179,12 @@ static void crypto_pump_work(struct kthread_work *work)
 }
 
 /**
- * crypto_transfer_cipher_request - transfer the new request into the
- * enginequeue
+ * crypto_transfer_request - transfer the new request into the engine queue
  * @engine: the hardware engine
  * @req: the request need to be listed into the engine queue
  */
-int crypto_transfer_cipher_request(struct crypto_engine *engine,
-				   struct ablkcipher_request *req,
+static int crypto_transfer_request(struct crypto_engine *engine,
+				   struct crypto_async_request *req,
 				   bool need_pump)
 {
 	unsigned long flags;
@@ -189,7 +197,7 @@ int crypto_transfer_cipher_request(struct crypto_engine *engine,
 		return -ESHUTDOWN;
 	}
 
-	ret = ablkcipher_enqueue_request(&engine->queue, req);
+	ret = crypto_enqueue_request(&engine->queue, req);
 
 	if (!engine->busy && need_pump)
 		kthread_queue_work(engine->kworker, &engine->pump_requests);
@@ -197,102 +205,131 @@ int crypto_transfer_cipher_request(struct crypto_engine *engine,
 	spin_unlock_irqrestore(&engine->queue_lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(crypto_transfer_cipher_request);
 
 /**
- * crypto_transfer_cipher_request_to_engine - transfer one request to list
+ * crypto_transfer_request_to_engine - transfer one request to list
  * into the engine queue
  * @engine: the hardware engine
  * @req: the request need to be listed into the engine queue
  */
-int crypto_transfer_cipher_request_to_engine(struct crypto_engine *engine,
-					     struct ablkcipher_request *req)
+static int crypto_transfer_request_to_engine(struct crypto_engine *engine,
+					     struct crypto_async_request *req)
 {
-	return crypto_transfer_cipher_request(engine, req, true);
+	return crypto_transfer_request(engine, req, true);
 }
-EXPORT_SYMBOL_GPL(crypto_transfer_cipher_request_to_engine);
 
 /**
- * crypto_transfer_hash_request - transfer the new request into the
- * enginequeue
+ * crypto_transfer_ablkcipher_request_to_engine - transfer one ablkcipher_request
+ * to list into the engine queue
  * @engine: the hardware engine
  * @req: the request need to be listed into the engine queue
+ * TODO: Remove this function when skcipher conversion is finished
  */
-int crypto_transfer_hash_request(struct crypto_engine *engine,
-				 struct ahash_request *req, bool need_pump)
+int crypto_transfer_ablkcipher_request_to_engine(struct crypto_engine *engine,
+						 struct ablkcipher_request *req)
 {
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&engine->queue_lock, flags);
-
-	if (!engine->running) {
-		spin_unlock_irqrestore(&engine->queue_lock, flags);
-		return -ESHUTDOWN;
-	}
-
-	ret = ahash_enqueue_request(&engine->queue, req);
+	return crypto_transfer_request_to_engine(engine, &req->base);
+}
+EXPORT_SYMBOL_GPL(crypto_transfer_ablkcipher_request_to_engine);
 
-	if (!engine->busy && need_pump)
-		kthread_queue_work(engine->kworker, &engine->pump_requests);
+/**
+ * crypto_transfer_aead_request_to_engine - transfer one aead_request
+ * to list into the engine queue
+ * @engine: the hardware engine
+ * @req: the request need to be listed into the engine queue
+ */
+int crypto_transfer_aead_request_to_engine(struct crypto_engine *engine,
+					   struct aead_request *req)
+{
+	return crypto_transfer_request_to_engine(engine, &req->base);
+}
+EXPORT_SYMBOL_GPL(crypto_transfer_aead_request_to_engine);
 
-	spin_unlock_irqrestore(&engine->queue_lock, flags);
-	return ret;
+/**
+ * crypto_transfer_akcipher_request_to_engine - transfer one akcipher_request
+ * to list into the engine queue
+ * @engine: the hardware engine
+ * @req: the request need to be listed into the engine queue
+ */
+int crypto_transfer_akcipher_request_to_engine(struct crypto_engine *engine,
+					       struct akcipher_request *req)
+{
+	return crypto_transfer_request_to_engine(engine, &req->base);
 }
-EXPORT_SYMBOL_GPL(crypto_transfer_hash_request);
+EXPORT_SYMBOL_GPL(crypto_transfer_akcipher_request_to_engine);
 
 /**
- * crypto_transfer_hash_request_to_engine - transfer one request to list
- * into the engine queue
+ * crypto_transfer_hash_request_to_engine - transfer one ahash_request
+ * to list into the engine queue
  * @engine: the hardware engine
  * @req: the request need to be listed into the engine queue
  */
 int crypto_transfer_hash_request_to_engine(struct crypto_engine *engine,
 					   struct ahash_request *req)
 {
-	return crypto_transfer_hash_request(engine, req, true);
+	return crypto_transfer_request_to_engine(engine, &req->base);
 }
 EXPORT_SYMBOL_GPL(crypto_transfer_hash_request_to_engine);
 
 /**
- * crypto_finalize_cipher_request - finalize one request if the request is done
+ * crypto_transfer_skcipher_request_to_engine - transfer one skcipher_request
+ * to list into the engine queue
+ * @engine: the hardware engine
+ * @req: the request need to be listed into the engine queue
+ */
+int crypto_transfer_skcipher_request_to_engine(struct crypto_engine *engine,
+					       struct skcipher_request *req)
+{
+	return crypto_transfer_request_to_engine(engine, &req->base);
+}
+EXPORT_SYMBOL_GPL(crypto_transfer_skcipher_request_to_engine);
+
+/**
+ * crypto_finalize_ablkcipher_request - finalize one ablkcipher_request if
+ * the request is done
  * @engine: the hardware engine
  * @req: the request need to be finalized
  * @err: error number
+ * TODO: Remove this function when skcipher conversion is finished
  */
-void crypto_finalize_cipher_request(struct crypto_engine *engine,
-				    struct ablkcipher_request *req, int err)
+void crypto_finalize_ablkcipher_request(struct crypto_engine *engine,
+					struct ablkcipher_request *req, int err)
 {
-	unsigned long flags;
-	bool finalize_cur_req = false;
-	int ret;
-
-	spin_lock_irqsave(&engine->queue_lock, flags);
-	if (engine->cur_req == &req->base)
-		finalize_cur_req = true;
-	spin_unlock_irqrestore(&engine->queue_lock, flags);
-
-	if (finalize_cur_req) {
-		if (engine->cur_req_prepared &&
-		    engine->unprepare_cipher_request) {
-			ret = engine->unprepare_cipher_request(engine, req);
-			if (ret)
-				dev_err(engine->dev, "failed to unprepare request\n");
-		}
-		spin_lock_irqsave(&engine->queue_lock, flags);
-		engine->cur_req = NULL;
-		engine->cur_req_prepared = false;
-		spin_unlock_irqrestore(&engine->queue_lock, flags);
-	}
+	return crypto_finalize_request(engine, &req->base, err);
+}
+EXPORT_SYMBOL_GPL(crypto_finalize_ablkcipher_request);
 
-	req->base.complete(&req->base, err);
+/**
+ * crypto_finalize_aead_request - finalize one aead_request if
+ * the request is done
+ * @engine: the hardware engine
+ * @req: the request need to be finalized
+ * @err: error number
+ */
+void crypto_finalize_aead_request(struct crypto_engine *engine,
+				  struct aead_request *req, int err)
+{
+	return crypto_finalize_request(engine, &req->base, err);
+}
+EXPORT_SYMBOL_GPL(crypto_finalize_aead_request);
 
-	kthread_queue_work(engine->kworker, &engine->pump_requests);
+/**
+ * crypto_finalize_akcipher_request - finalize one akcipher_request if
+ * the request is done
+ * @engine: the hardware engine
+ * @req: the request need to be finalized
+ * @err: error number
+ */
+void crypto_finalize_akcipher_request(struct crypto_engine *engine,
+				      struct akcipher_request *req, int err)
+{
+	return crypto_finalize_request(engine, &req->base, err);
 }
-EXPORT_SYMBOL_GPL(crypto_finalize_cipher_request);
+EXPORT_SYMBOL_GPL(crypto_finalize_akcipher_request);
 
 /**
- * crypto_finalize_hash_request - finalize one request if the request is done
+ * crypto_finalize_hash_request - finalize one ahash_request if
+ * the request is done
  * @engine: the hardware engine
  * @req: the request need to be finalized
  * @err: error number
@@ -300,35 +337,25 @@ EXPORT_SYMBOL_GPL(crypto_finalize_cipher_request);
 void crypto_finalize_hash_request(struct crypto_engine *engine,
 				  struct ahash_request *req, int err)
 {
-	unsigned long flags;
-	bool finalize_cur_req = false;
-	int ret;
-
-	spin_lock_irqsave(&engine->queue_lock, flags);
-	if (engine->cur_req == &req->base)
-		finalize_cur_req = true;
-	spin_unlock_irqrestore(&engine->queue_lock, flags);
-
-	if (finalize_cur_req) {
-		if (engine->cur_req_prepared &&
-		    engine->unprepare_hash_request) {
-			ret = engine->unprepare_hash_request(engine, req);
-			if (ret)
-				dev_err(engine->dev, "failed to unprepare request\n");
-		}
-		spin_lock_irqsave(&engine->queue_lock, flags);
-		engine->cur_req = NULL;
-		engine->cur_req_prepared = false;
-		spin_unlock_irqrestore(&engine->queue_lock, flags);
-	}
-
-	req->base.complete(&req->base, err);
-
-	kthread_queue_work(engine->kworker, &engine->pump_requests);
+	return crypto_finalize_request(engine, &req->base, err);
 }
 EXPORT_SYMBOL_GPL(crypto_finalize_hash_request);
 
 /**
+ * crypto_finalize_skcipher_request - finalize one skcipher_request if
+ * the request is done
+ * @engine: the hardware engine
+ * @req: the request need to be finalized
+ * @err: error number
+ */
+void crypto_finalize_skcipher_request(struct crypto_engine *engine,
+				      struct skcipher_request *req, int err)
+{
+	return crypto_finalize_request(engine, &req->base, err);
+}
+EXPORT_SYMBOL_GPL(crypto_finalize_skcipher_request);
+
+/**
  * crypto_engine_start - start the hardware engine
  * @engine: the hardware engine need to be started
  *
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 5c291eedaa70..0e89b5457cab 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -271,7 +271,7 @@ static int crypto_report(struct sk_buff *in_skb, struct nlmsghdr *in_nlh,
 		return -ENOENT;
 
 	err = -ENOMEM;
-	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!skb)
 		goto drop_alg;
 
diff --git a/crypto/ecc.c b/crypto/ecc.c
index 18f32f2a5e1c..9c066b5ac12d 100644
--- a/crypto/ecc.c
+++ b/crypto/ecc.c
@@ -1025,9 +1025,7 @@ int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 {
 	int ret = 0;
 	struct ecc_point *product, *pk;
-	u64 priv[ndigits];
-	u64 rand_z[ndigits];
-	unsigned int nbytes;
+	u64 *priv, *rand_z;
 	const struct ecc_curve *curve = ecc_get_curve(curve_id);
 
 	if (!private_key || !public_key || !curve) {
@@ -1035,14 +1033,22 @@ int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 		goto out;
 	}
 
-	nbytes = ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+	priv = kmalloc_array(ndigits, sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
-	get_random_bytes(rand_z, nbytes);
+	rand_z = kmalloc_array(ndigits, sizeof(*rand_z), GFP_KERNEL);
+	if (!rand_z) {
+		ret = -ENOMEM;
+		goto kfree_out;
+	}
 
 	pk = ecc_alloc_point(ndigits);
 	if (!pk) {
 		ret = -ENOMEM;
-		goto out;
+		goto kfree_out;
 	}
 
 	product = ecc_alloc_point(ndigits);
@@ -1051,6 +1057,8 @@ int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 		goto err_alloc_product;
 	}
 
+	get_random_bytes(rand_z, ndigits << ECC_DIGITS_TO_BYTES_SHIFT);
+
 	ecc_swap_digits(public_key, pk->x, ndigits);
 	ecc_swap_digits(&public_key[ndigits], pk->y, ndigits);
 	ecc_swap_digits(private_key, priv, ndigits);
@@ -1065,6 +1073,9 @@ int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 	ecc_free_point(product);
 err_alloc_product:
 	ecc_free_point(pk);
+kfree_out:
+	kzfree(priv);
+	kzfree(rand_z);
 out:
 	return ret;
 }
diff --git a/crypto/ecdh.c b/crypto/ecdh.c
index 3aca0933ec44..d2ec33f0e098 100644
--- a/crypto/ecdh.c
+++ b/crypto/ecdh.c
@@ -89,12 +89,19 @@ static int ecdh_compute_value(struct kpp_request *req)
 		if (!shared_secret)
 			goto free_pubkey;
 
-		copied = sg_copy_to_buffer(req->src, 1, public_key,
-					   public_key_sz);
-		if (copied != public_key_sz) {
-			ret = -EINVAL;
+		/* from here on it's invalid parameters */
+		ret = -EINVAL;
+
+		/* must have exactly two points to be on the curve */
+		if (public_key_sz != req->src_len)
+			goto free_all;
+
+		copied = sg_copy_to_buffer(req->src,
+					   sg_nents_for_len(req->src,
+							    public_key_sz),
+					   public_key, public_key_sz);
+		if (copied != public_key_sz)
 			goto free_all;
-		}
 
 		ret = crypto_ecdh_shared_secret(ctx->curve_id, ctx->ndigits,
 						ctx->private_key, public_key,
@@ -111,7 +118,11 @@ static int ecdh_compute_value(struct kpp_request *req)
 	if (ret < 0)
 		goto free_all;
 
-	copied = sg_copy_from_buffer(req->dst, 1, buf, nbytes);
+	/* might want less than we've got */
+	nbytes = min_t(size_t, nbytes, req->dst_len);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+								nbytes),
+				     buf, nbytes);
 	if (copied != nbytes)
 		ret = -EINVAL;
 
diff --git a/crypto/internal.h b/crypto/internal.h
index 5ac27fba10e8..9a3f39939fba 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -67,7 +67,6 @@ static inline unsigned int crypto_compress_ctxsize(struct crypto_alg *alg)
 }
 
 struct crypto_alg *crypto_mod_get(struct crypto_alg *alg);
-struct crypto_alg *crypto_alg_lookup(const char *name, u32 type, u32 mask);
 struct crypto_alg *crypto_alg_mod_lookup(const char *name, u32 type, u32 mask);
 
 int crypto_init_cipher_ops(struct crypto_tfm *tfm);
diff --git a/crypto/lrw.c b/crypto/lrw.c
index cbbd7c50ad19..954a7064a179 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -28,13 +28,31 @@
 
 #include <crypto/b128ops.h>
 #include <crypto/gf128mul.h>
-#include <crypto/lrw.h>
 
 #define LRW_BUFFER_SIZE 128u
 
+#define LRW_BLOCK_SIZE 16
+
 struct priv {
 	struct crypto_skcipher *child;
-	struct lrw_table_ctx table;
+
+	/*
+	 * optimizes multiplying a random (non incrementing, as at the
+	 * start of a new sector) value with key2, we could also have
+	 * used 4k optimization tables or no optimization at all. In the
+	 * latter case we would have to store key2 here
+	 */
+	struct gf128mul_64k *table;
+
+	/*
+	 * stores:
+	 *  key2*{ 0,0,...0,0,0,0,1 }, key2*{ 0,0,...0,0,0,1,1 },
+	 *  key2*{ 0,0,...0,0,1,1,1 }, key2*{ 0,0,...0,1,1,1,1 }
+	 *  key2*{ 0,0,...1,1,1,1,1 }, etc
+	 * needed for optimized multiplication of incrementing values
+	 * with key2
+	 */
+	be128 mulinc[128];
 };
 
 struct rctx {
@@ -65,11 +83,25 @@ static inline void setbit128_bbe(void *b, int bit)
 			), b);
 }
 
-int lrw_init_table(struct lrw_table_ctx *ctx, const u8 *tweak)
+static int setkey(struct crypto_skcipher *parent, const u8 *key,
+		  unsigned int keylen)
 {
+	struct priv *ctx = crypto_skcipher_ctx(parent);
+	struct crypto_skcipher *child = ctx->child;
+	int err, bsize = LRW_BLOCK_SIZE;
+	const u8 *tweak = key + keylen - bsize;
 	be128 tmp = { 0 };
 	int i;
 
+	crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(parent) &
+					 CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(child, key, keylen - bsize);
+	crypto_skcipher_set_flags(parent, crypto_skcipher_get_flags(child) &
+					  CRYPTO_TFM_RES_MASK);
+	if (err)
+		return err;
+
 	if (ctx->table)
 		gf128mul_free_64k(ctx->table);
 
@@ -87,34 +119,6 @@ int lrw_init_table(struct lrw_table_ctx *ctx, const u8 *tweak)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(lrw_init_table);
-
-void lrw_free_table(struct lrw_table_ctx *ctx)
-{
-	if (ctx->table)
-		gf128mul_free_64k(ctx->table);
-}
-EXPORT_SYMBOL_GPL(lrw_free_table);
-
-static int setkey(struct crypto_skcipher *parent, const u8 *key,
-		  unsigned int keylen)
-{
-	struct priv *ctx = crypto_skcipher_ctx(parent);
-	struct crypto_skcipher *child = ctx->child;
-	int err, bsize = LRW_BLOCK_SIZE;
-	const u8 *tweak = key + keylen - bsize;
-
-	crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(parent) &
-					 CRYPTO_TFM_REQ_MASK);
-	err = crypto_skcipher_setkey(child, key, keylen - bsize);
-	crypto_skcipher_set_flags(parent, crypto_skcipher_get_flags(child) &
-					  CRYPTO_TFM_RES_MASK);
-	if (err)
-		return err;
-
-	return lrw_init_table(&ctx->table, tweak);
-}
 
 static inline void inc(be128 *iv)
 {
@@ -238,7 +242,7 @@ static int pre_crypt(struct skcipher_request *req)
 			/* T <- I*Key2, using the optimization
 			 * discussed in the specification */
 			be128_xor(&rctx->t, &rctx->t,
-				  &ctx->table.mulinc[get_index128(iv)]);
+				  &ctx->mulinc[get_index128(iv)]);
 			inc(iv);
 		} while ((avail -= bs) >= bs);
 
@@ -301,7 +305,7 @@ static int init_crypt(struct skcipher_request *req, crypto_completion_t done)
 	memcpy(&rctx->t, req->iv, sizeof(rctx->t));
 
 	/* T <- I*Key2 */
-	gf128mul_64k_bbe(&rctx->t, ctx->table.table);
+	gf128mul_64k_bbe(&rctx->t, ctx->table);
 
 	return 0;
 }
@@ -313,7 +317,7 @@ static void exit_crypt(struct skcipher_request *req)
 	rctx->left = 0;
 
 	if (rctx->ext)
-		kfree(rctx->ext);
+		kzfree(rctx->ext);
 }
 
 static int do_encrypt(struct skcipher_request *req, int err)
@@ -416,85 +420,6 @@ static int decrypt(struct skcipher_request *req)
 	return do_decrypt(req, init_crypt(req, decrypt_done));
 }
 
-int lrw_crypt(struct blkcipher_desc *desc, struct scatterlist *sdst,
-	      struct scatterlist *ssrc, unsigned int nbytes,
-	      struct lrw_crypt_req *req)
-{
-	const unsigned int bsize = LRW_BLOCK_SIZE;
-	const unsigned int max_blks = req->tbuflen / bsize;
-	struct lrw_table_ctx *ctx = req->table_ctx;
-	struct blkcipher_walk walk;
-	unsigned int nblocks;
-	be128 *iv, *src, *dst, *t;
-	be128 *t_buf = req->tbuf;
-	int err, i;
-
-	BUG_ON(max_blks < 1);
-
-	blkcipher_walk_init(&walk, sdst, ssrc, nbytes);
-
-	err = blkcipher_walk_virt(desc, &walk);
-	nbytes = walk.nbytes;
-	if (!nbytes)
-		return err;
-
-	nblocks = min(walk.nbytes / bsize, max_blks);
-	src = (be128 *)walk.src.virt.addr;
-	dst = (be128 *)walk.dst.virt.addr;
-
-	/* calculate first value of T */
-	iv = (be128 *)walk.iv;
-	t_buf[0] = *iv;
-
-	/* T <- I*Key2 */
-	gf128mul_64k_bbe(&t_buf[0], ctx->table);
-
-	i = 0;
-	goto first;
-
-	for (;;) {
-		do {
-			for (i = 0; i < nblocks; i++) {
-				/* T <- I*Key2, using the optimization
-				 * discussed in the specification */
-				be128_xor(&t_buf[i], t,
-						&ctx->mulinc[get_index128(iv)]);
-				inc(iv);
-first:
-				t = &t_buf[i];
-
-				/* PP <- T xor P */
-				be128_xor(dst + i, t, src + i);
-			}
-
-			/* CC <- E(Key2,PP) */
-			req->crypt_fn(req->crypt_ctx, (u8 *)dst,
-				      nblocks * bsize);
-
-			/* C <- T xor CC */
-			for (i = 0; i < nblocks; i++)
-				be128_xor(dst + i, dst + i, &t_buf[i]);
-
-			src += nblocks;
-			dst += nblocks;
-			nbytes -= nblocks * bsize;
-			nblocks = min(nbytes / bsize, max_blks);
-		} while (nblocks > 0);
-
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-		nbytes = walk.nbytes;
-		if (!nbytes)
-			break;
-
-		nblocks = min(nbytes / bsize, max_blks);
-		src = (be128 *)walk.src.virt.addr;
-		dst = (be128 *)walk.dst.virt.addr;
-	}
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(lrw_crypt);
-
 static int init_tfm(struct crypto_skcipher *tfm)
 {
 	struct skcipher_instance *inst = skcipher_alg_instance(tfm);
@@ -518,7 +443,8 @@ static void exit_tfm(struct crypto_skcipher *tfm)
 {
 	struct priv *ctx = crypto_skcipher_ctx(tfm);
 
-	lrw_free_table(&ctx->table);
+	if (ctx->table)
+		gf128mul_free_64k(ctx->table);
 	crypto_free_skcipher(ctx->child);
 }
 
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index fe5129d6ff4e..f14152147ce8 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -367,7 +367,7 @@ static void mcryptd_hash_update(struct crypto_async_request *req_async, int err)
 		goto out;
 
 	rctx->out = req->result;
-	err = ahash_mcryptd_update(&rctx->areq);
+	err = crypto_ahash_update(&rctx->areq);
 	if (err) {
 		req->base.complete = rctx->complete;
 		goto out;
@@ -394,7 +394,7 @@ static void mcryptd_hash_final(struct crypto_async_request *req_async, int err)
 		goto out;
 
 	rctx->out = req->result;
-	err = ahash_mcryptd_final(&rctx->areq);
+	err = crypto_ahash_final(&rctx->areq);
 	if (err) {
 		req->base.complete = rctx->complete;
 		goto out;
@@ -420,7 +420,7 @@ static void mcryptd_hash_finup(struct crypto_async_request *req_async, int err)
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
 	rctx->out = req->result;
-	err = ahash_mcryptd_finup(&rctx->areq);
+	err = crypto_ahash_finup(&rctx->areq);
 
 	if (err) {
 		req->base.complete = rctx->complete;
@@ -455,7 +455,7 @@ static void mcryptd_hash_digest(struct crypto_async_request *req_async, int err)
 						rctx->complete, req_async);
 
 	rctx->out = req->result;
-	err = ahash_mcryptd_digest(desc);
+	err = crypto_ahash_init(desc) ?: crypto_ahash_finup(desc);
 
 out:
 	local_bh_disable();
@@ -612,32 +612,6 @@ struct mcryptd_ahash *mcryptd_alloc_ahash(const char *alg_name,
 }
 EXPORT_SYMBOL_GPL(mcryptd_alloc_ahash);
 
-int ahash_mcryptd_digest(struct ahash_request *desc)
-{
-	return crypto_ahash_init(desc) ?: ahash_mcryptd_finup(desc);
-}
-
-int ahash_mcryptd_update(struct ahash_request *desc)
-{
-	/* alignment is to be done by multi-buffer crypto algorithm if needed */
-
-	return crypto_ahash_update(desc);
-}
-
-int ahash_mcryptd_finup(struct ahash_request *desc)
-{
-	/* alignment is to be done by multi-buffer crypto algorithm if needed */
-
-	return crypto_ahash_finup(desc);
-}
-
-int ahash_mcryptd_final(struct ahash_request *desc)
-{
-	/* alignment is to be done by multi-buffer crypto algorithm if needed */
-
-	return crypto_ahash_final(desc);
-}
-
 struct crypto_ahash *mcryptd_ahash_child(struct mcryptd_ahash *tfm)
 {
 	struct mcryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base);
diff --git a/crypto/md4.c b/crypto/md4.c
index 3515af425cc9..810fefb0a007 100644
--- a/crypto/md4.c
+++ b/crypto/md4.c
@@ -64,23 +64,6 @@ static inline u32 H(u32 x, u32 y, u32 z)
 #define ROUND2(a,b,c,d,k,s) (a = lshift(a + G(b,c,d) + k + (u32)0x5A827999,s))
 #define ROUND3(a,b,c,d,k,s) (a = lshift(a + H(b,c,d) + k + (u32)0x6ED9EBA1,s))
 
-/* XXX: this stuff can be optimized */
-static inline void le32_to_cpu_array(u32 *buf, unsigned int words)
-{
-	while (words--) {
-		__le32_to_cpus(buf);
-		buf++;
-	}
-}
-
-static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
-{
-	while (words--) {
-		__cpu_to_le32s(buf);
-		buf++;
-	}
-}
-
 static void md4_transform(u32 *hash, u32 const *in)
 {
 	u32 a, b, c, d;
diff --git a/crypto/md5.c b/crypto/md5.c
index f7ae1a48225b..f776ef43d621 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -32,23 +32,6 @@ const u8 md5_zero_message_hash[MD5_DIGEST_SIZE] = {
 };
 EXPORT_SYMBOL_GPL(md5_zero_message_hash);
 
-/* XXX: this stuff can be optimized */
-static inline void le32_to_cpu_array(u32 *buf, unsigned int words)
-{
-	while (words--) {
-		__le32_to_cpus(buf);
-		buf++;
-	}
-}
-
-static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
-{
-	while (words--) {
-		__cpu_to_le32s(buf);
-		buf++;
-	}
-}
-
 #define F1(x, y, z)	(z ^ (x & (y ^ z)))
 #define F2(x, y, z)	F1(z, x, y)
 #define F3(x, y, z)	(x ^ y ^ z)
diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c
index 2908f93c3e55..9893dbfc1af4 100644
--- a/crypto/rsa-pkcs1pad.c
+++ b/crypto/rsa-pkcs1pad.c
@@ -192,7 +192,7 @@ static int pkcs1pad_encrypt_sign_complete(struct akcipher_request *req, int err)
 	if (likely(!pad_len))
 		goto out;
 
-	out_buf = kzalloc(ctx->key_size, GFP_ATOMIC);
+	out_buf = kzalloc(ctx->key_size, GFP_KERNEL);
 	err = -ENOMEM;
 	if (!out_buf)
 		goto out;
diff --git a/crypto/simd.c b/crypto/simd.c
index 208226d7f908..ea7240be3001 100644
--- a/crypto/simd.c
+++ b/crypto/simd.c
@@ -221,4 +221,54 @@ void simd_skcipher_free(struct simd_skcipher_alg *salg)
 }
 EXPORT_SYMBOL_GPL(simd_skcipher_free);
 
+int simd_register_skciphers_compat(struct skcipher_alg *algs, int count,
+				   struct simd_skcipher_alg **simd_algs)
+{
+	int err;
+	int i;
+	const char *algname;
+	const char *drvname;
+	const char *basename;
+	struct simd_skcipher_alg *simd;
+
+	err = crypto_register_skciphers(algs, count);
+	if (err)
+		return err;
+
+	for (i = 0; i < count; i++) {
+		WARN_ON(strncmp(algs[i].base.cra_name, "__", 2));
+		WARN_ON(strncmp(algs[i].base.cra_driver_name, "__", 2));
+		algname = algs[i].base.cra_name + 2;
+		drvname = algs[i].base.cra_driver_name + 2;
+		basename = algs[i].base.cra_driver_name;
+		simd = simd_skcipher_create_compat(algname, drvname, basename);
+		err = PTR_ERR(simd);
+		if (IS_ERR(simd))
+			goto err_unregister;
+		simd_algs[i] = simd;
+	}
+	return 0;
+
+err_unregister:
+	simd_unregister_skciphers(algs, count, simd_algs);
+	return err;
+}
+EXPORT_SYMBOL_GPL(simd_register_skciphers_compat);
+
+void simd_unregister_skciphers(struct skcipher_alg *algs, int count,
+			       struct simd_skcipher_alg **simd_algs)
+{
+	int i;
+
+	crypto_unregister_skciphers(algs, count);
+
+	for (i = 0; i < count; i++) {
+		if (simd_algs[i]) {
+			simd_skcipher_free(simd_algs[i]);
+			simd_algs[i] = NULL;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(simd_unregister_skciphers);
+
 MODULE_LICENSE("GPL");
diff --git a/crypto/sm4_generic.c b/crypto/sm4_generic.c
new file mode 100644
index 000000000000..f537a2766c55
--- /dev/null
+++ b/crypto/sm4_generic.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * SM4 Cipher Algorithm.
+ *
+ * Copyright (C) 2018 ARM Limited or its affiliates.
+ * All rights reserved.
+ */
+
+#include <crypto/sm4.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/crypto.h>
+#include <asm/byteorder.h>
+#include <asm/unaligned.h>
+
+static const u32 fk[4] = {
+	0xa3b1bac6, 0x56aa3350, 0x677d9197, 0xb27022dc
+};
+
+static const u8 sbox[256] = {
+	0xd6, 0x90, 0xe9, 0xfe, 0xcc, 0xe1, 0x3d, 0xb7,
+	0x16, 0xb6, 0x14, 0xc2, 0x28, 0xfb, 0x2c, 0x05,
+	0x2b, 0x67, 0x9a, 0x76, 0x2a, 0xbe, 0x04, 0xc3,
+	0xaa, 0x44, 0x13, 0x26, 0x49, 0x86, 0x06, 0x99,
+	0x9c, 0x42, 0x50, 0xf4, 0x91, 0xef, 0x98, 0x7a,
+	0x33, 0x54, 0x0b, 0x43, 0xed, 0xcf, 0xac, 0x62,
+	0xe4, 0xb3, 0x1c, 0xa9, 0xc9, 0x08, 0xe8, 0x95,
+	0x80, 0xdf, 0x94, 0xfa, 0x75, 0x8f, 0x3f, 0xa6,
+	0x47, 0x07, 0xa7, 0xfc, 0xf3, 0x73, 0x17, 0xba,
+	0x83, 0x59, 0x3c, 0x19, 0xe6, 0x85, 0x4f, 0xa8,
+	0x68, 0x6b, 0x81, 0xb2, 0x71, 0x64, 0xda, 0x8b,
+	0xf8, 0xeb, 0x0f, 0x4b, 0x70, 0x56, 0x9d, 0x35,
+	0x1e, 0x24, 0x0e, 0x5e, 0x63, 0x58, 0xd1, 0xa2,
+	0x25, 0x22, 0x7c, 0x3b, 0x01, 0x21, 0x78, 0x87,
+	0xd4, 0x00, 0x46, 0x57, 0x9f, 0xd3, 0x27, 0x52,
+	0x4c, 0x36, 0x02, 0xe7, 0xa0, 0xc4, 0xc8, 0x9e,
+	0xea, 0xbf, 0x8a, 0xd2, 0x40, 0xc7, 0x38, 0xb5,
+	0xa3, 0xf7, 0xf2, 0xce, 0xf9, 0x61, 0x15, 0xa1,
+	0xe0, 0xae, 0x5d, 0xa4, 0x9b, 0x34, 0x1a, 0x55,
+	0xad, 0x93, 0x32, 0x30, 0xf5, 0x8c, 0xb1, 0xe3,
+	0x1d, 0xf6, 0xe2, 0x2e, 0x82, 0x66, 0xca, 0x60,
+	0xc0, 0x29, 0x23, 0xab, 0x0d, 0x53, 0x4e, 0x6f,
+	0xd5, 0xdb, 0x37, 0x45, 0xde, 0xfd, 0x8e, 0x2f,
+	0x03, 0xff, 0x6a, 0x72, 0x6d, 0x6c, 0x5b, 0x51,
+	0x8d, 0x1b, 0xaf, 0x92, 0xbb, 0xdd, 0xbc, 0x7f,
+	0x11, 0xd9, 0x5c, 0x41, 0x1f, 0x10, 0x5a, 0xd8,
+	0x0a, 0xc1, 0x31, 0x88, 0xa5, 0xcd, 0x7b, 0xbd,
+	0x2d, 0x74, 0xd0, 0x12, 0xb8, 0xe5, 0xb4, 0xb0,
+	0x89, 0x69, 0x97, 0x4a, 0x0c, 0x96, 0x77, 0x7e,
+	0x65, 0xb9, 0xf1, 0x09, 0xc5, 0x6e, 0xc6, 0x84,
+	0x18, 0xf0, 0x7d, 0xec, 0x3a, 0xdc, 0x4d, 0x20,
+	0x79, 0xee, 0x5f, 0x3e, 0xd7, 0xcb, 0x39, 0x48
+};
+
+static const u32 ck[] = {
+	0x00070e15, 0x1c232a31, 0x383f464d, 0x545b6269,
+	0x70777e85, 0x8c939aa1, 0xa8afb6bd, 0xc4cbd2d9,
+	0xe0e7eef5, 0xfc030a11, 0x181f262d, 0x343b4249,
+	0x50575e65, 0x6c737a81, 0x888f969d, 0xa4abb2b9,
+	0xc0c7ced5, 0xdce3eaf1, 0xf8ff060d, 0x141b2229,
+	0x30373e45, 0x4c535a61, 0x686f767d, 0x848b9299,
+	0xa0a7aeb5, 0xbcc3cad1, 0xd8dfe6ed, 0xf4fb0209,
+	0x10171e25, 0x2c333a41, 0x484f565d, 0x646b7279
+};
+
+static u32 sm4_t_non_lin_sub(u32 x)
+{
+	int i;
+	u8 *b = (u8 *)&x;
+
+	for (i = 0; i < 4; ++i)
+		b[i] = sbox[b[i]];
+
+	return x;
+}
+
+static u32 sm4_key_lin_sub(u32 x)
+{
+	return x ^ rol32(x, 13) ^ rol32(x, 23);
+
+}
+
+static u32 sm4_enc_lin_sub(u32 x)
+{
+	return x ^ rol32(x, 2) ^ rol32(x, 10) ^ rol32(x, 18) ^ rol32(x, 24);
+}
+
+static u32 sm4_key_sub(u32 x)
+{
+	return sm4_key_lin_sub(sm4_t_non_lin_sub(x));
+}
+
+static u32 sm4_enc_sub(u32 x)
+{
+	return sm4_enc_lin_sub(sm4_t_non_lin_sub(x));
+}
+
+static u32 sm4_round(const u32 *x, const u32 rk)
+{
+	return x[0] ^ sm4_enc_sub(x[1] ^ x[2] ^ x[3] ^ rk);
+}
+
+
+/**
+ * crypto_sm4_expand_key - Expands the SM4 key as described in GB/T 32907-2016
+ * @ctx:	The location where the computed key will be stored.
+ * @in_key:	The supplied key.
+ * @key_len:	The length of the supplied key.
+ *
+ * Returns 0 on success. The function fails only if an invalid key size (or
+ * pointer) is supplied.
+ */
+int crypto_sm4_expand_key(struct crypto_sm4_ctx *ctx, const u8 *in_key,
+			  unsigned int key_len)
+{
+	u32 rk[4], t;
+	const u32 *key = (u32 *)in_key;
+	int i;
+
+	if (key_len != SM4_KEY_SIZE)
+		return -EINVAL;
+
+	for (i = 0; i < 4; ++i)
+		rk[i] = get_unaligned_be32(&key[i]) ^ fk[i];
+
+	for (i = 0; i < 32; ++i) {
+		t = rk[0] ^ sm4_key_sub(rk[1] ^ rk[2] ^ rk[3] ^ ck[i]);
+		ctx->rkey_enc[i] = t;
+		rk[0] = rk[1];
+		rk[1] = rk[2];
+		rk[2] = rk[3];
+		rk[3] = t;
+	}
+
+	for (i = 0; i < 32; ++i)
+		ctx->rkey_dec[i] = ctx->rkey_enc[31 - i];
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_sm4_expand_key);
+
+/**
+ * crypto_sm4_set_key - Set the AES key.
+ * @tfm:	The %crypto_tfm that is used in the context.
+ * @in_key:	The input key.
+ * @key_len:	The size of the key.
+ *
+ * Returns 0 on success, on failure the %CRYPTO_TFM_RES_BAD_KEY_LEN flag in tfm
+ * is set. The function uses crypto_sm4_expand_key() to expand the key.
+ * &crypto_sm4_ctx _must_ be the private data embedded in @tfm which is
+ * retrieved with crypto_tfm_ctx().
+ */
+int crypto_sm4_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+		       unsigned int key_len)
+{
+	struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 *flags = &tfm->crt_flags;
+	int ret;
+
+	ret = crypto_sm4_expand_key(ctx, in_key, key_len);
+	if (!ret)
+		return 0;
+
+	*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(crypto_sm4_set_key);
+
+static void sm4_do_crypt(const u32 *rk, u32 *out, const u32 *in)
+{
+	u32 x[4], i, t;
+
+	for (i = 0; i < 4; ++i)
+		x[i] = get_unaligned_be32(&in[i]);
+
+	for (i = 0; i < 32; ++i) {
+		t = sm4_round(x, rk[i]);
+		x[0] = x[1];
+		x[1] = x[2];
+		x[2] = x[3];
+		x[3] = t;
+	}
+
+	for (i = 0; i < 4; ++i)
+		put_unaligned_be32(x[3 - i], &out[i]);
+}
+
+/* encrypt a block of text */
+
+static void sm4_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	sm4_do_crypt(ctx->rkey_enc, (u32 *)out, (u32 *)in);
+}
+
+/* decrypt a block of text */
+
+static void sm4_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	sm4_do_crypt(ctx->rkey_dec, (u32 *)out, (u32 *)in);
+}
+
+static struct crypto_alg sm4_alg = {
+	.cra_name		=	"sm4",
+	.cra_driver_name	=	"sm4-generic",
+	.cra_priority		=	100,
+	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		=	SM4_BLOCK_SIZE,
+	.cra_ctxsize		=	sizeof(struct crypto_sm4_ctx),
+	.cra_module		=	THIS_MODULE,
+	.cra_u			=	{
+		.cipher = {
+			.cia_min_keysize	=	SM4_KEY_SIZE,
+			.cia_max_keysize	=	SM4_KEY_SIZE,
+			.cia_setkey		=	crypto_sm4_set_key,
+			.cia_encrypt		=	sm4_encrypt,
+			.cia_decrypt		=	sm4_decrypt
+		}
+	}
+};
+
+static int __init sm4_init(void)
+{
+	return crypto_register_alg(&sm4_alg);
+}
+
+static void __exit sm4_fini(void)
+{
+	crypto_unregister_alg(&sm4_alg);
+}
+
+module_init(sm4_init);
+module_exit(sm4_fini);
+
+MODULE_DESCRIPTION("SM4 Cipher Algorithm");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sm4");
+MODULE_ALIAS_CRYPTO("sm4-generic");
diff --git a/crypto/speck.c b/crypto/speck.c
new file mode 100644
index 000000000000..58aa9f7f91f7
--- /dev/null
+++ b/crypto/speck.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Speck: a lightweight block cipher
+ *
+ * Copyright (c) 2018 Google, Inc
+ *
+ * Speck has 10 variants, including 5 block sizes.  For now we only implement
+ * the variants Speck128/128, Speck128/192, Speck128/256, Speck64/96, and
+ * Speck64/128.   Speck${B}/${K} denotes the variant with a block size of B bits
+ * and a key size of K bits.  The Speck128 variants are believed to be the most
+ * secure variants, and they use the same block size and key sizes as AES.  The
+ * Speck64 variants are less secure, but on 32-bit processors are usually
+ * faster.  The remaining variants (Speck32, Speck48, and Speck96) are even less
+ * secure and/or not as well suited for implementation on either 32-bit or
+ * 64-bit processors, so are omitted.
+ *
+ * Reference: "The Simon and Speck Families of Lightweight Block Ciphers"
+ * https://eprint.iacr.org/2013/404.pdf
+ *
+ * In a correspondence, the Speck designers have also clarified that the words
+ * should be interpreted in little-endian format, and the words should be
+ * ordered such that the first word of each block is 'y' rather than 'x', and
+ * the first key word (rather than the last) becomes the first round key.
+ */
+
+#include <asm/unaligned.h>
+#include <crypto/speck.h>
+#include <linux/bitops.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+
+/* Speck128 */
+
+static __always_inline void speck128_round(u64 *x, u64 *y, u64 k)
+{
+	*x = ror64(*x, 8);
+	*x += *y;
+	*x ^= k;
+	*y = rol64(*y, 3);
+	*y ^= *x;
+}
+
+static __always_inline void speck128_unround(u64 *x, u64 *y, u64 k)
+{
+	*y ^= *x;
+	*y = ror64(*y, 3);
+	*x ^= k;
+	*x -= *y;
+	*x = rol64(*x, 8);
+}
+
+void crypto_speck128_encrypt(const struct speck128_tfm_ctx *ctx,
+			     u8 *out, const u8 *in)
+{
+	u64 y = get_unaligned_le64(in);
+	u64 x = get_unaligned_le64(in + 8);
+	int i;
+
+	for (i = 0; i < ctx->nrounds; i++)
+		speck128_round(&x, &y, ctx->round_keys[i]);
+
+	put_unaligned_le64(y, out);
+	put_unaligned_le64(x, out + 8);
+}
+EXPORT_SYMBOL_GPL(crypto_speck128_encrypt);
+
+static void speck128_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	crypto_speck128_encrypt(crypto_tfm_ctx(tfm), out, in);
+}
+
+void crypto_speck128_decrypt(const struct speck128_tfm_ctx *ctx,
+			     u8 *out, const u8 *in)
+{
+	u64 y = get_unaligned_le64(in);
+	u64 x = get_unaligned_le64(in + 8);
+	int i;
+
+	for (i = ctx->nrounds - 1; i >= 0; i--)
+		speck128_unround(&x, &y, ctx->round_keys[i]);
+
+	put_unaligned_le64(y, out);
+	put_unaligned_le64(x, out + 8);
+}
+EXPORT_SYMBOL_GPL(crypto_speck128_decrypt);
+
+static void speck128_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	crypto_speck128_decrypt(crypto_tfm_ctx(tfm), out, in);
+}
+
+int crypto_speck128_setkey(struct speck128_tfm_ctx *ctx, const u8 *key,
+			   unsigned int keylen)
+{
+	u64 l[3];
+	u64 k;
+	int i;
+
+	switch (keylen) {
+	case SPECK128_128_KEY_SIZE:
+		k = get_unaligned_le64(key);
+		l[0] = get_unaligned_le64(key + 8);
+		ctx->nrounds = SPECK128_128_NROUNDS;
+		for (i = 0; i < ctx->nrounds; i++) {
+			ctx->round_keys[i] = k;
+			speck128_round(&l[0], &k, i);
+		}
+		break;
+	case SPECK128_192_KEY_SIZE:
+		k = get_unaligned_le64(key);
+		l[0] = get_unaligned_le64(key + 8);
+		l[1] = get_unaligned_le64(key + 16);
+		ctx->nrounds = SPECK128_192_NROUNDS;
+		for (i = 0; i < ctx->nrounds; i++) {
+			ctx->round_keys[i] = k;
+			speck128_round(&l[i % 2], &k, i);
+		}
+		break;
+	case SPECK128_256_KEY_SIZE:
+		k = get_unaligned_le64(key);
+		l[0] = get_unaligned_le64(key + 8);
+		l[1] = get_unaligned_le64(key + 16);
+		l[2] = get_unaligned_le64(key + 24);
+		ctx->nrounds = SPECK128_256_NROUNDS;
+		for (i = 0; i < ctx->nrounds; i++) {
+			ctx->round_keys[i] = k;
+			speck128_round(&l[i % 3], &k, i);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_speck128_setkey);
+
+static int speck128_setkey(struct crypto_tfm *tfm, const u8 *key,
+			   unsigned int keylen)
+{
+	return crypto_speck128_setkey(crypto_tfm_ctx(tfm), key, keylen);
+}
+
+/* Speck64 */
+
+static __always_inline void speck64_round(u32 *x, u32 *y, u32 k)
+{
+	*x = ror32(*x, 8);
+	*x += *y;
+	*x ^= k;
+	*y = rol32(*y, 3);
+	*y ^= *x;
+}
+
+static __always_inline void speck64_unround(u32 *x, u32 *y, u32 k)
+{
+	*y ^= *x;
+	*y = ror32(*y, 3);
+	*x ^= k;
+	*x -= *y;
+	*x = rol32(*x, 8);
+}
+
+void crypto_speck64_encrypt(const struct speck64_tfm_ctx *ctx,
+			    u8 *out, const u8 *in)
+{
+	u32 y = get_unaligned_le32(in);
+	u32 x = get_unaligned_le32(in + 4);
+	int i;
+
+	for (i = 0; i < ctx->nrounds; i++)
+		speck64_round(&x, &y, ctx->round_keys[i]);
+
+	put_unaligned_le32(y, out);
+	put_unaligned_le32(x, out + 4);
+}
+EXPORT_SYMBOL_GPL(crypto_speck64_encrypt);
+
+static void speck64_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	crypto_speck64_encrypt(crypto_tfm_ctx(tfm), out, in);
+}
+
+void crypto_speck64_decrypt(const struct speck64_tfm_ctx *ctx,
+			    u8 *out, const u8 *in)
+{
+	u32 y = get_unaligned_le32(in);
+	u32 x = get_unaligned_le32(in + 4);
+	int i;
+
+	for (i = ctx->nrounds - 1; i >= 0; i--)
+		speck64_unround(&x, &y, ctx->round_keys[i]);
+
+	put_unaligned_le32(y, out);
+	put_unaligned_le32(x, out + 4);
+}
+EXPORT_SYMBOL_GPL(crypto_speck64_decrypt);
+
+static void speck64_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	crypto_speck64_decrypt(crypto_tfm_ctx(tfm), out, in);
+}
+
+int crypto_speck64_setkey(struct speck64_tfm_ctx *ctx, const u8 *key,
+			  unsigned int keylen)
+{
+	u32 l[3];
+	u32 k;
+	int i;
+
+	switch (keylen) {
+	case SPECK64_96_KEY_SIZE:
+		k = get_unaligned_le32(key);
+		l[0] = get_unaligned_le32(key + 4);
+		l[1] = get_unaligned_le32(key + 8);
+		ctx->nrounds = SPECK64_96_NROUNDS;
+		for (i = 0; i < ctx->nrounds; i++) {
+			ctx->round_keys[i] = k;
+			speck64_round(&l[i % 2], &k, i);
+		}
+		break;
+	case SPECK64_128_KEY_SIZE:
+		k = get_unaligned_le32(key);
+		l[0] = get_unaligned_le32(key + 4);
+		l[1] = get_unaligned_le32(key + 8);
+		l[2] = get_unaligned_le32(key + 12);
+		ctx->nrounds = SPECK64_128_NROUNDS;
+		for (i = 0; i < ctx->nrounds; i++) {
+			ctx->round_keys[i] = k;
+			speck64_round(&l[i % 3], &k, i);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_speck64_setkey);
+
+static int speck64_setkey(struct crypto_tfm *tfm, const u8 *key,
+			  unsigned int keylen)
+{
+	return crypto_speck64_setkey(crypto_tfm_ctx(tfm), key, keylen);
+}
+
+/* Algorithm definitions */
+
+static struct crypto_alg speck_algs[] = {
+	{
+		.cra_name		= "speck128",
+		.cra_driver_name	= "speck128-generic",
+		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+		.cra_blocksize		= SPECK128_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct speck128_tfm_ctx),
+		.cra_module		= THIS_MODULE,
+		.cra_u			= {
+			.cipher = {
+				.cia_min_keysize	= SPECK128_128_KEY_SIZE,
+				.cia_max_keysize	= SPECK128_256_KEY_SIZE,
+				.cia_setkey		= speck128_setkey,
+				.cia_encrypt		= speck128_encrypt,
+				.cia_decrypt		= speck128_decrypt
+			}
+		}
+	}, {
+		.cra_name		= "speck64",
+		.cra_driver_name	= "speck64-generic",
+		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+		.cra_blocksize		= SPECK64_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct speck64_tfm_ctx),
+		.cra_module		= THIS_MODULE,
+		.cra_u			= {
+			.cipher = {
+				.cia_min_keysize	= SPECK64_96_KEY_SIZE,
+				.cia_max_keysize	= SPECK64_128_KEY_SIZE,
+				.cia_setkey		= speck64_setkey,
+				.cia_encrypt		= speck64_encrypt,
+				.cia_decrypt		= speck64_decrypt
+			}
+		}
+	}
+};
+
+static int __init speck_module_init(void)
+{
+	return crypto_register_algs(speck_algs, ARRAY_SIZE(speck_algs));
+}
+
+static void __exit speck_module_exit(void)
+{
+	crypto_unregister_algs(speck_algs, ARRAY_SIZE(speck_algs));
+}
+
+module_init(speck_module_init);
+module_exit(speck_module_exit);
+
+MODULE_DESCRIPTION("Speck block cipher (generic)");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("speck128");
+MODULE_ALIAS_CRYPTO("speck128-generic");
+MODULE_ALIAS_CRYPTO("speck64");
+MODULE_ALIAS_CRYPTO("speck64-generic");
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 14213a096fd2..51fe7c8744ae 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -1983,6 +1983,9 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 	case 190:
 		ret += tcrypt_test("authenc(hmac(sha512),cbc(des3_ede))");
 		break;
+	case 191:
+		ret += tcrypt_test("ecb(sm4)");
+		break;
 	case 200:
 		test_cipher_speed("ecb(aes)", ENCRYPT, sec, NULL, 0,
 				speed_template_16_24_32);
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index d5e23a142a04..af4a01c5037b 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -3001,6 +3001,33 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "ecb(sm4)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = __VECS(sm4_enc_tv_template),
+				.dec = __VECS(sm4_dec_tv_template)
+			}
+		}
+	}, {
+		.alg = "ecb(speck128)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = __VECS(speck128_enc_tv_template),
+				.dec = __VECS(speck128_dec_tv_template)
+			}
+		}
+	}, {
+		.alg = "ecb(speck64)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = __VECS(speck64_enc_tv_template),
+				.dec = __VECS(speck64_dec_tv_template)
+			}
+		}
+	}, {
 		.alg = "ecb(tea)",
 		.test = alg_test_skcipher,
 		.suite = {
@@ -3558,6 +3585,24 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "xts(speck128)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = __VECS(speck128_xts_enc_tv_template),
+				.dec = __VECS(speck128_xts_dec_tv_template)
+			}
+		}
+	}, {
+		.alg = "xts(speck64)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = __VECS(speck64_xts_enc_tv_template),
+				.dec = __VECS(speck64_xts_dec_tv_template)
+			}
+		}
+	}, {
 		.alg = "xts(twofish)",
 		.test = alg_test_skcipher,
 		.suite = {
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 6044f6906bd6..004c0a0f8004 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -548,7 +548,7 @@ static const struct akcipher_testvec rsa_tv_template[] = {
 static const struct akcipher_testvec pkcs1pad_rsa_tv_template[] = {
 	{
 	.key =
-	"\x30\x82\x03\x1f\x02\x01\x10\x02\x82\x01\x01\x00\xd7\x1e\x77\x82"
+	"\x30\x82\x03\x1f\x02\x01\x00\x02\x82\x01\x01\x00\xd7\x1e\x77\x82"
 	"\x8c\x92\x31\xe7\x69\x02\xa2\xd5\x5c\x78\xde\xa2\x0c\x8f\xfe\x28"
 	"\x59\x31\xdf\x40\x9c\x60\x61\x06\xb9\x2f\x62\x40\x80\x76\xcb\x67"
 	"\x4a\xb5\x59\x56\x69\x17\x07\xfa\xf9\x4c\xbd\x6c\x37\x7a\x46\x7d"
@@ -597,8 +597,8 @@ static const struct akcipher_testvec pkcs1pad_rsa_tv_template[] = {
 	"\xfe\xf8\x27\x1b\xd6\x55\x60\x5e\x48\xb7\x6d\x9a\xa8\x37\xf9\x7a"
 	"\xde\x1b\xcd\x5d\x1a\x30\xd4\xe9\x9e\x5b\x3c\x15\xf8\x9c\x1f\xda"
 	"\xd1\x86\x48\x55\xce\x83\xee\x8e\x51\xc7\xde\x32\x12\x47\x7d\x46"
-	"\xb8\x35\xdf\x41\x02\x01\x30\x02\x01\x30\x02\x01\x30\x02\x01\x30"
-	"\x02\x01\x30",
+	"\xb8\x35\xdf\x41\x02\x01\x00\x02\x01\x00\x02\x01\x00\x02\x01\x00"
+	"\x02\x01\x00",
 	.key_len = 804,
 	/*
 	 * m is SHA256 hash of following message:
@@ -2044,6 +2044,265 @@ static const struct hash_testvec crct10dif_tv_template[] = {
 		.digest		= (u8 *)(u16 []){ 0x44c6 },
 		.np		= 4,
 		.tap		= { 1, 255, 57, 6 },
+	}, {
+		.plaintext =	"\x6e\x05\x79\x10\xa7\x1b\xb2\x49"
+				"\xe0\x54\xeb\x82\x19\x8d\x24\xbb"
+				"\x2f\xc6\x5d\xf4\x68\xff\x96\x0a"
+				"\xa1\x38\xcf\x43\xda\x71\x08\x7c"
+				"\x13\xaa\x1e\xb5\x4c\xe3\x57\xee"
+				"\x85\x1c\x90\x27\xbe\x32\xc9\x60"
+				"\xf7\x6b\x02\x99\x0d\xa4\x3b\xd2"
+				"\x46\xdd\x74\x0b\x7f\x16\xad\x21"
+				"\xb8\x4f\xe6\x5a\xf1\x88\x1f\x93"
+				"\x2a\xc1\x35\xcc\x63\xfa\x6e\x05"
+				"\x9c\x10\xa7\x3e\xd5\x49\xe0\x77"
+				"\x0e\x82\x19\xb0\x24\xbb\x52\xe9"
+				"\x5d\xf4\x8b\x22\x96\x2d\xc4\x38"
+				"\xcf\x66\xfd\x71\x08\x9f\x13\xaa"
+				"\x41\xd8\x4c\xe3\x7a\x11\x85\x1c"
+				"\xb3\x27\xbe\x55\xec\x60\xf7\x8e"
+				"\x02\x99\x30\xc7\x3b\xd2\x69\x00"
+				"\x74\x0b\xa2\x16\xad\x44\xdb\x4f"
+				"\xe6\x7d\x14\x88\x1f\xb6\x2a\xc1"
+				"\x58\xef\x63\xfa\x91\x05\x9c\x33"
+				"\xca\x3e\xd5\x6c\x03\x77\x0e\xa5"
+				"\x19\xb0\x47\xde\x52\xe9\x80\x17"
+				"\x8b\x22\xb9\x2d\xc4\x5b\xf2\x66"
+				"\xfd\x94\x08\x9f\x36\xcd\x41\xd8"
+				"\x6f\x06\x7a\x11\xa8\x1c\xb3\x4a"
+				"\xe1\x55\xec\x83\x1a\x8e\x25\xbc"
+				"\x30\xc7\x5e\xf5\x69\x00\x97\x0b"
+				"\xa2\x39\xd0\x44\xdb\x72\x09\x7d"
+				"\x14\xab\x1f\xb6\x4d\xe4\x58\xef"
+				"\x86\x1d\x91\x28\xbf\x33\xca\x61"
+				"\xf8\x6c\x03\x9a\x0e\xa5\x3c\xd3"
+				"\x47\xde\x75\x0c\x80\x17\xae\x22"
+				"\xb9\x50\xe7\x5b\xf2\x89\x20\x94"
+				"\x2b\xc2\x36\xcd\x64\xfb\x6f\x06"
+				"\x9d\x11\xa8\x3f\xd6\x4a\xe1\x78"
+				"\x0f\x83\x1a\xb1\x25\xbc\x53\xea"
+				"\x5e\xf5\x8c\x00\x97\x2e\xc5\x39"
+				"\xd0\x67\xfe\x72\x09\xa0\x14\xab"
+				"\x42\xd9\x4d\xe4\x7b\x12\x86\x1d"
+				"\xb4\x28\xbf\x56\xed\x61\xf8\x8f"
+				"\x03\x9a\x31\xc8\x3c\xd3\x6a\x01"
+				"\x75\x0c\xa3\x17\xae\x45\xdc\x50"
+				"\xe7\x7e\x15\x89\x20\xb7\x2b\xc2"
+				"\x59\xf0\x64\xfb\x92\x06\x9d\x34"
+				"\xcb\x3f\xd6\x6d\x04\x78\x0f\xa6"
+				"\x1a\xb1\x48\xdf\x53\xea\x81\x18"
+				"\x8c\x23\xba\x2e\xc5\x5c\xf3\x67"
+				"\xfe\x95\x09\xa0\x37\xce\x42\xd9"
+				"\x70\x07\x7b\x12\xa9\x1d\xb4\x4b"
+				"\xe2\x56\xed\x84\x1b\x8f\x26\xbd"
+				"\x31\xc8\x5f\xf6\x6a\x01\x98\x0c"
+				"\xa3\x3a\xd1\x45\xdc\x73\x0a\x7e"
+				"\x15\xac\x20\xb7\x4e\xe5\x59\xf0"
+				"\x87\x1e\x92\x29\xc0\x34\xcb\x62"
+				"\xf9\x6d\x04\x9b\x0f\xa6\x3d\xd4"
+				"\x48\xdf\x76\x0d\x81\x18\xaf\x23"
+				"\xba\x51\xe8\x5c\xf3\x8a\x21\x95"
+				"\x2c\xc3\x37\xce\x65\xfc\x70\x07"
+				"\x9e\x12\xa9\x40\xd7\x4b\xe2\x79"
+				"\x10\x84\x1b\xb2\x26\xbd\x54\xeb"
+				"\x5f\xf6\x8d\x01\x98\x2f\xc6\x3a"
+				"\xd1\x68\xff\x73\x0a\xa1\x15\xac"
+				"\x43\xda\x4e\xe5\x7c\x13\x87\x1e"
+				"\xb5\x29\xc0\x57\xee\x62\xf9\x90"
+				"\x04\x9b\x32\xc9\x3d\xd4\x6b\x02"
+				"\x76\x0d\xa4\x18\xaf\x46\xdd\x51"
+				"\xe8\x7f\x16\x8a\x21\xb8\x2c\xc3"
+				"\x5a\xf1\x65\xfc\x93\x07\x9e\x35"
+				"\xcc\x40\xd7\x6e\x05\x79\x10\xa7"
+				"\x1b\xb2\x49\xe0\x54\xeb\x82\x19"
+				"\x8d\x24\xbb\x2f\xc6\x5d\xf4\x68"
+				"\xff\x96\x0a\xa1\x38\xcf\x43\xda"
+				"\x71\x08\x7c\x13\xaa\x1e\xb5\x4c"
+				"\xe3\x57\xee\x85\x1c\x90\x27\xbe"
+				"\x32\xc9\x60\xf7\x6b\x02\x99\x0d"
+				"\xa4\x3b\xd2\x46\xdd\x74\x0b\x7f"
+				"\x16\xad\x21\xb8\x4f\xe6\x5a\xf1"
+				"\x88\x1f\x93\x2a\xc1\x35\xcc\x63"
+				"\xfa\x6e\x05\x9c\x10\xa7\x3e\xd5"
+				"\x49\xe0\x77\x0e\x82\x19\xb0\x24"
+				"\xbb\x52\xe9\x5d\xf4\x8b\x22\x96"
+				"\x2d\xc4\x38\xcf\x66\xfd\x71\x08"
+				"\x9f\x13\xaa\x41\xd8\x4c\xe3\x7a"
+				"\x11\x85\x1c\xb3\x27\xbe\x55\xec"
+				"\x60\xf7\x8e\x02\x99\x30\xc7\x3b"
+				"\xd2\x69\x00\x74\x0b\xa2\x16\xad"
+				"\x44\xdb\x4f\xe6\x7d\x14\x88\x1f"
+				"\xb6\x2a\xc1\x58\xef\x63\xfa\x91"
+				"\x05\x9c\x33\xca\x3e\xd5\x6c\x03"
+				"\x77\x0e\xa5\x19\xb0\x47\xde\x52"
+				"\xe9\x80\x17\x8b\x22\xb9\x2d\xc4"
+				"\x5b\xf2\x66\xfd\x94\x08\x9f\x36"
+				"\xcd\x41\xd8\x6f\x06\x7a\x11\xa8"
+				"\x1c\xb3\x4a\xe1\x55\xec\x83\x1a"
+				"\x8e\x25\xbc\x30\xc7\x5e\xf5\x69"
+				"\x00\x97\x0b\xa2\x39\xd0\x44\xdb"
+				"\x72\x09\x7d\x14\xab\x1f\xb6\x4d"
+				"\xe4\x58\xef\x86\x1d\x91\x28\xbf"
+				"\x33\xca\x61\xf8\x6c\x03\x9a\x0e"
+				"\xa5\x3c\xd3\x47\xde\x75\x0c\x80"
+				"\x17\xae\x22\xb9\x50\xe7\x5b\xf2"
+				"\x89\x20\x94\x2b\xc2\x36\xcd\x64"
+				"\xfb\x6f\x06\x9d\x11\xa8\x3f\xd6"
+				"\x4a\xe1\x78\x0f\x83\x1a\xb1\x25"
+				"\xbc\x53\xea\x5e\xf5\x8c\x00\x97"
+				"\x2e\xc5\x39\xd0\x67\xfe\x72\x09"
+				"\xa0\x14\xab\x42\xd9\x4d\xe4\x7b"
+				"\x12\x86\x1d\xb4\x28\xbf\x56\xed"
+				"\x61\xf8\x8f\x03\x9a\x31\xc8\x3c"
+				"\xd3\x6a\x01\x75\x0c\xa3\x17\xae"
+				"\x45\xdc\x50\xe7\x7e\x15\x89\x20"
+				"\xb7\x2b\xc2\x59\xf0\x64\xfb\x92"
+				"\x06\x9d\x34\xcb\x3f\xd6\x6d\x04"
+				"\x78\x0f\xa6\x1a\xb1\x48\xdf\x53"
+				"\xea\x81\x18\x8c\x23\xba\x2e\xc5"
+				"\x5c\xf3\x67\xfe\x95\x09\xa0\x37"
+				"\xce\x42\xd9\x70\x07\x7b\x12\xa9"
+				"\x1d\xb4\x4b\xe2\x56\xed\x84\x1b"
+				"\x8f\x26\xbd\x31\xc8\x5f\xf6\x6a"
+				"\x01\x98\x0c\xa3\x3a\xd1\x45\xdc"
+				"\x73\x0a\x7e\x15\xac\x20\xb7\x4e"
+				"\xe5\x59\xf0\x87\x1e\x92\x29\xc0"
+				"\x34\xcb\x62\xf9\x6d\x04\x9b\x0f"
+				"\xa6\x3d\xd4\x48\xdf\x76\x0d\x81"
+				"\x18\xaf\x23\xba\x51\xe8\x5c\xf3"
+				"\x8a\x21\x95\x2c\xc3\x37\xce\x65"
+				"\xfc\x70\x07\x9e\x12\xa9\x40\xd7"
+				"\x4b\xe2\x79\x10\x84\x1b\xb2\x26"
+				"\xbd\x54\xeb\x5f\xf6\x8d\x01\x98"
+				"\x2f\xc6\x3a\xd1\x68\xff\x73\x0a"
+				"\xa1\x15\xac\x43\xda\x4e\xe5\x7c"
+				"\x13\x87\x1e\xb5\x29\xc0\x57\xee"
+				"\x62\xf9\x90\x04\x9b\x32\xc9\x3d"
+				"\xd4\x6b\x02\x76\x0d\xa4\x18\xaf"
+				"\x46\xdd\x51\xe8\x7f\x16\x8a\x21"
+				"\xb8\x2c\xc3\x5a\xf1\x65\xfc\x93"
+				"\x07\x9e\x35\xcc\x40\xd7\x6e\x05"
+				"\x79\x10\xa7\x1b\xb2\x49\xe0\x54"
+				"\xeb\x82\x19\x8d\x24\xbb\x2f\xc6"
+				"\x5d\xf4\x68\xff\x96\x0a\xa1\x38"
+				"\xcf\x43\xda\x71\x08\x7c\x13\xaa"
+				"\x1e\xb5\x4c\xe3\x57\xee\x85\x1c"
+				"\x90\x27\xbe\x32\xc9\x60\xf7\x6b"
+				"\x02\x99\x0d\xa4\x3b\xd2\x46\xdd"
+				"\x74\x0b\x7f\x16\xad\x21\xb8\x4f"
+				"\xe6\x5a\xf1\x88\x1f\x93\x2a\xc1"
+				"\x35\xcc\x63\xfa\x6e\x05\x9c\x10"
+				"\xa7\x3e\xd5\x49\xe0\x77\x0e\x82"
+				"\x19\xb0\x24\xbb\x52\xe9\x5d\xf4"
+				"\x8b\x22\x96\x2d\xc4\x38\xcf\x66"
+				"\xfd\x71\x08\x9f\x13\xaa\x41\xd8"
+				"\x4c\xe3\x7a\x11\x85\x1c\xb3\x27"
+				"\xbe\x55\xec\x60\xf7\x8e\x02\x99"
+				"\x30\xc7\x3b\xd2\x69\x00\x74\x0b"
+				"\xa2\x16\xad\x44\xdb\x4f\xe6\x7d"
+				"\x14\x88\x1f\xb6\x2a\xc1\x58\xef"
+				"\x63\xfa\x91\x05\x9c\x33\xca\x3e"
+				"\xd5\x6c\x03\x77\x0e\xa5\x19\xb0"
+				"\x47\xde\x52\xe9\x80\x17\x8b\x22"
+				"\xb9\x2d\xc4\x5b\xf2\x66\xfd\x94"
+				"\x08\x9f\x36\xcd\x41\xd8\x6f\x06"
+				"\x7a\x11\xa8\x1c\xb3\x4a\xe1\x55"
+				"\xec\x83\x1a\x8e\x25\xbc\x30\xc7"
+				"\x5e\xf5\x69\x00\x97\x0b\xa2\x39"
+				"\xd0\x44\xdb\x72\x09\x7d\x14\xab"
+				"\x1f\xb6\x4d\xe4\x58\xef\x86\x1d"
+				"\x91\x28\xbf\x33\xca\x61\xf8\x6c"
+				"\x03\x9a\x0e\xa5\x3c\xd3\x47\xde"
+				"\x75\x0c\x80\x17\xae\x22\xb9\x50"
+				"\xe7\x5b\xf2\x89\x20\x94\x2b\xc2"
+				"\x36\xcd\x64\xfb\x6f\x06\x9d\x11"
+				"\xa8\x3f\xd6\x4a\xe1\x78\x0f\x83"
+				"\x1a\xb1\x25\xbc\x53\xea\x5e\xf5"
+				"\x8c\x00\x97\x2e\xc5\x39\xd0\x67"
+				"\xfe\x72\x09\xa0\x14\xab\x42\xd9"
+				"\x4d\xe4\x7b\x12\x86\x1d\xb4\x28"
+				"\xbf\x56\xed\x61\xf8\x8f\x03\x9a"
+				"\x31\xc8\x3c\xd3\x6a\x01\x75\x0c"
+				"\xa3\x17\xae\x45\xdc\x50\xe7\x7e"
+				"\x15\x89\x20\xb7\x2b\xc2\x59\xf0"
+				"\x64\xfb\x92\x06\x9d\x34\xcb\x3f"
+				"\xd6\x6d\x04\x78\x0f\xa6\x1a\xb1"
+				"\x48\xdf\x53\xea\x81\x18\x8c\x23"
+				"\xba\x2e\xc5\x5c\xf3\x67\xfe\x95"
+				"\x09\xa0\x37\xce\x42\xd9\x70\x07"
+				"\x7b\x12\xa9\x1d\xb4\x4b\xe2\x56"
+				"\xed\x84\x1b\x8f\x26\xbd\x31\xc8"
+				"\x5f\xf6\x6a\x01\x98\x0c\xa3\x3a"
+				"\xd1\x45\xdc\x73\x0a\x7e\x15\xac"
+				"\x20\xb7\x4e\xe5\x59\xf0\x87\x1e"
+				"\x92\x29\xc0\x34\xcb\x62\xf9\x6d"
+				"\x04\x9b\x0f\xa6\x3d\xd4\x48\xdf"
+				"\x76\x0d\x81\x18\xaf\x23\xba\x51"
+				"\xe8\x5c\xf3\x8a\x21\x95\x2c\xc3"
+				"\x37\xce\x65\xfc\x70\x07\x9e\x12"
+				"\xa9\x40\xd7\x4b\xe2\x79\x10\x84"
+				"\x1b\xb2\x26\xbd\x54\xeb\x5f\xf6"
+				"\x8d\x01\x98\x2f\xc6\x3a\xd1\x68"
+				"\xff\x73\x0a\xa1\x15\xac\x43\xda"
+				"\x4e\xe5\x7c\x13\x87\x1e\xb5\x29"
+				"\xc0\x57\xee\x62\xf9\x90\x04\x9b"
+				"\x32\xc9\x3d\xd4\x6b\x02\x76\x0d"
+				"\xa4\x18\xaf\x46\xdd\x51\xe8\x7f"
+				"\x16\x8a\x21\xb8\x2c\xc3\x5a\xf1"
+				"\x65\xfc\x93\x07\x9e\x35\xcc\x40"
+				"\xd7\x6e\x05\x79\x10\xa7\x1b\xb2"
+				"\x49\xe0\x54\xeb\x82\x19\x8d\x24"
+				"\xbb\x2f\xc6\x5d\xf4\x68\xff\x96"
+				"\x0a\xa1\x38\xcf\x43\xda\x71\x08"
+				"\x7c\x13\xaa\x1e\xb5\x4c\xe3\x57"
+				"\xee\x85\x1c\x90\x27\xbe\x32\xc9"
+				"\x60\xf7\x6b\x02\x99\x0d\xa4\x3b"
+				"\xd2\x46\xdd\x74\x0b\x7f\x16\xad"
+				"\x21\xb8\x4f\xe6\x5a\xf1\x88\x1f"
+				"\x93\x2a\xc1\x35\xcc\x63\xfa\x6e"
+				"\x05\x9c\x10\xa7\x3e\xd5\x49\xe0"
+				"\x77\x0e\x82\x19\xb0\x24\xbb\x52"
+				"\xe9\x5d\xf4\x8b\x22\x96\x2d\xc4"
+				"\x38\xcf\x66\xfd\x71\x08\x9f\x13"
+				"\xaa\x41\xd8\x4c\xe3\x7a\x11\x85"
+				"\x1c\xb3\x27\xbe\x55\xec\x60\xf7"
+				"\x8e\x02\x99\x30\xc7\x3b\xd2\x69"
+				"\x00\x74\x0b\xa2\x16\xad\x44\xdb"
+				"\x4f\xe6\x7d\x14\x88\x1f\xb6\x2a"
+				"\xc1\x58\xef\x63\xfa\x91\x05\x9c"
+				"\x33\xca\x3e\xd5\x6c\x03\x77\x0e"
+				"\xa5\x19\xb0\x47\xde\x52\xe9\x80"
+				"\x17\x8b\x22\xb9\x2d\xc4\x5b\xf2"
+				"\x66\xfd\x94\x08\x9f\x36\xcd\x41"
+				"\xd8\x6f\x06\x7a\x11\xa8\x1c\xb3"
+				"\x4a\xe1\x55\xec\x83\x1a\x8e\x25"
+				"\xbc\x30\xc7\x5e\xf5\x69\x00\x97"
+				"\x0b\xa2\x39\xd0\x44\xdb\x72\x09"
+				"\x7d\x14\xab\x1f\xb6\x4d\xe4\x58"
+				"\xef\x86\x1d\x91\x28\xbf\x33\xca"
+				"\x61\xf8\x6c\x03\x9a\x0e\xa5\x3c"
+				"\xd3\x47\xde\x75\x0c\x80\x17\xae"
+				"\x22\xb9\x50\xe7\x5b\xf2\x89\x20"
+				"\x94\x2b\xc2\x36\xcd\x64\xfb\x6f"
+				"\x06\x9d\x11\xa8\x3f\xd6\x4a\xe1"
+				"\x78\x0f\x83\x1a\xb1\x25\xbc\x53"
+				"\xea\x5e\xf5\x8c\x00\x97\x2e\xc5"
+				"\x39\xd0\x67\xfe\x72\x09\xa0\x14"
+				"\xab\x42\xd9\x4d\xe4\x7b\x12\x86"
+				"\x1d\xb4\x28\xbf\x56\xed\x61\xf8"
+				"\x8f\x03\x9a\x31\xc8\x3c\xd3\x6a"
+				"\x01\x75\x0c\xa3\x17\xae\x45\xdc"
+				"\x50\xe7\x7e\x15\x89\x20\xb7\x2b"
+				"\xc2\x59\xf0\x64\xfb\x92\x06\x9d"
+				"\x34\xcb\x3f\xd6\x6d\x04\x78\x0f"
+				"\xa6\x1a\xb1\x48\xdf\x53\xea\x81"
+				"\x18\x8c\x23\xba\x2e\xc5\x5c\xf3"
+				"\x67\xfe\x95\x09\xa0\x37\xce\x42"
+				"\xd9\x70\x07\x7b\x12\xa9\x1d\xb4"
+				"\x4b\xe2\x56\xed\x84\x1b\x8f\x26"
+				"\xbd\x31\xc8\x5f\xf6\x6a\x01\x98",
+		.psize = 2048,
+		.digest		= (u8 *)(u16 []){ 0x23ca },
 	}
 };
 
@@ -14323,6 +14582,1623 @@ static const struct cipher_testvec serpent_xts_dec_tv_template[] = {
 	},
 };
 
+/*
+ * SM4 test vector taken from the draft RFC
+ * https://tools.ietf.org/html/draft-crypto-sm4-00#ref-GBT.32907-2016
+ */
+
+static const struct cipher_testvec sm4_enc_tv_template[] = {
+	{ /* SM4 Appendix A: Example Calculations. Example 1. */
+		.key	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
+			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
+		.klen	= 16,
+		.input	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
+			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
+		.ilen	= 16,
+		.result	= "\x68\x1E\xDF\x34\xD2\x06\x96\x5E"
+			  "\x86\xB3\xE9\x4F\x53\x6E\x42\x46",
+		.rlen	= 16,
+	}, { /*
+	      *  SM4 Appendix A: Example Calculations.
+	      *  Last 10 iterations of Example 2.
+	      */
+		.key    = "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
+			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
+		.klen	= 16,
+		.input	= "\x99\x4a\xc3\xe7\xc3\x57\x89\x6a"
+			  "\x81\xfc\xa8\xe\x38\x3e\xef\x80"
+			  "\xb1\x98\xf2\xde\x3f\x4b\xae\xd1"
+			  "\xf0\xf1\x30\x4c\x1\x27\x5a\x8f"
+			  "\x45\xe1\x39\xb7\xae\xff\x1f\x27"
+			  "\xad\x57\x15\xab\x31\x5d\xc\xef"
+			  "\x8c\xc8\x80\xbd\x11\x98\xf3\x7b"
+			  "\xa2\xdd\x14\x20\xf9\xe8\xbb\x82"
+			  "\xf7\x32\xca\x4b\xa8\xf7\xb3\x4d"
+			  "\x27\xd1\xcd\xe6\xb6\x65\x5a\x23"
+			  "\xc2\xf3\x54\x84\x53\xe3\xb9\x20"
+			  "\xa5\x37\x0\xbe\xe7\x7b\x48\xfb"
+			  "\x21\x3d\x9e\x48\x1d\x9e\xf5\xbf"
+			  "\x77\xd5\xb4\x4a\x53\x71\x94\x7a"
+			  "\x88\xa6\x6e\x6\x93\xca\x43\xa5"
+			  "\xc4\xf6\xcd\x53\x4b\x7b\x8e\xfe"
+			  "\xb4\x28\x7c\x42\x29\x32\x5d\x88"
+			  "\xed\xce\x0\x19\xe\x16\x2\x6e"
+			  "\x87\xff\x2c\xac\xe8\xe7\xe9\xbf"
+			  "\x31\x51\xec\x47\xc3\x51\x83\xc1",
+		.ilen	= 160,
+		.result	= "\xb1\x98\xf2\xde\x3f\x4b\xae\xd1"
+			  "\xf0\xf1\x30\x4c\x1\x27\x5a\x8f"
+			  "\x45\xe1\x39\xb7\xae\xff\x1f\x27"
+			  "\xad\x57\x15\xab\x31\x5d\xc\xef"
+			  "\x8c\xc8\x80\xbd\x11\x98\xf3\x7b"
+			  "\xa2\xdd\x14\x20\xf9\xe8\xbb\x82"
+			  "\xf7\x32\xca\x4b\xa8\xf7\xb3\x4d"
+			  "\x27\xd1\xcd\xe6\xb6\x65\x5a\x23"
+			  "\xc2\xf3\x54\x84\x53\xe3\xb9\x20"
+			  "\xa5\x37\x0\xbe\xe7\x7b\x48\xfb"
+			  "\x21\x3d\x9e\x48\x1d\x9e\xf5\xbf"
+			  "\x77\xd5\xb4\x4a\x53\x71\x94\x7a"
+			  "\x88\xa6\x6e\x6\x93\xca\x43\xa5"
+			  "\xc4\xf6\xcd\x53\x4b\x7b\x8e\xfe"
+			  "\xb4\x28\x7c\x42\x29\x32\x5d\x88"
+			  "\xed\xce\x0\x19\xe\x16\x2\x6e"
+			  "\x87\xff\x2c\xac\xe8\xe7\xe9\xbf"
+			  "\x31\x51\xec\x47\xc3\x51\x83\xc1"
+			  "\x59\x52\x98\xc7\xc6\xfd\x27\x1f"
+			  "\x4\x2\xf8\x4\xc3\x3d\x3f\x66",
+		.rlen	= 160
+	}
+};
+
+static const struct cipher_testvec sm4_dec_tv_template[] = {
+	{ /* SM4 Appendix A: Example Calculations. Example 1. */
+		.key	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
+			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
+		.klen	= 16,
+		.input	= "\x68\x1E\xDF\x34\xD2\x06\x96\x5E"
+			  "\x86\xB3\xE9\x4F\x53\x6E\x42\x46",
+		.ilen	= 16,
+		.result	= "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
+			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
+		.rlen	= 16,
+	}, { /*
+	      *  SM4 Appendix A: Example Calculations.
+	      *  Last 10 iterations of Example 2.
+	      */
+		.key    = "\x01\x23\x45\x67\x89\xAB\xCD\xEF"
+			  "\xFE\xDC\xBA\x98\x76\x54\x32\x10",
+		.klen	= 16,
+		.input	= "\xb1\x98\xf2\xde\x3f\x4b\xae\xd1"
+			  "\xf0\xf1\x30\x4c\x1\x27\x5a\x8f"
+			  "\x45\xe1\x39\xb7\xae\xff\x1f\x27"
+			  "\xad\x57\x15\xab\x31\x5d\xc\xef"
+			  "\x8c\xc8\x80\xbd\x11\x98\xf3\x7b"
+			  "\xa2\xdd\x14\x20\xf9\xe8\xbb\x82"
+			  "\xf7\x32\xca\x4b\xa8\xf7\xb3\x4d"
+			  "\x27\xd1\xcd\xe6\xb6\x65\x5a\x23"
+			  "\xc2\xf3\x54\x84\x53\xe3\xb9\x20"
+			  "\xa5\x37\x0\xbe\xe7\x7b\x48\xfb"
+			  "\x21\x3d\x9e\x48\x1d\x9e\xf5\xbf"
+			  "\x77\xd5\xb4\x4a\x53\x71\x94\x7a"
+			  "\x88\xa6\x6e\x6\x93\xca\x43\xa5"
+			  "\xc4\xf6\xcd\x53\x4b\x7b\x8e\xfe"
+			  "\xb4\x28\x7c\x42\x29\x32\x5d\x88"
+			  "\xed\xce\x0\x19\xe\x16\x2\x6e"
+			  "\x87\xff\x2c\xac\xe8\xe7\xe9\xbf"
+			  "\x31\x51\xec\x47\xc3\x51\x83\xc1"
+			  "\x59\x52\x98\xc7\xc6\xfd\x27\x1f"
+			  "\x4\x2\xf8\x4\xc3\x3d\x3f\x66",
+		.ilen	= 160,
+		.result	= "\x99\x4a\xc3\xe7\xc3\x57\x89\x6a"
+			  "\x81\xfc\xa8\xe\x38\x3e\xef\x80"
+			  "\xb1\x98\xf2\xde\x3f\x4b\xae\xd1"
+			  "\xf0\xf1\x30\x4c\x1\x27\x5a\x8f"
+			  "\x45\xe1\x39\xb7\xae\xff\x1f\x27"
+			  "\xad\x57\x15\xab\x31\x5d\xc\xef"
+			  "\x8c\xc8\x80\xbd\x11\x98\xf3\x7b"
+			  "\xa2\xdd\x14\x20\xf9\xe8\xbb\x82"
+			  "\xf7\x32\xca\x4b\xa8\xf7\xb3\x4d"
+			  "\x27\xd1\xcd\xe6\xb6\x65\x5a\x23"
+			  "\xc2\xf3\x54\x84\x53\xe3\xb9\x20"
+			  "\xa5\x37\x0\xbe\xe7\x7b\x48\xfb"
+			  "\x21\x3d\x9e\x48\x1d\x9e\xf5\xbf"
+			  "\x77\xd5\xb4\x4a\x53\x71\x94\x7a"
+			  "\x88\xa6\x6e\x6\x93\xca\x43\xa5"
+			  "\xc4\xf6\xcd\x53\x4b\x7b\x8e\xfe"
+			  "\xb4\x28\x7c\x42\x29\x32\x5d\x88"
+			  "\xed\xce\x0\x19\xe\x16\x2\x6e"
+			  "\x87\xff\x2c\xac\xe8\xe7\xe9\xbf"
+			  "\x31\x51\xec\x47\xc3\x51\x83\xc1",
+		.rlen	= 160
+	}
+};
+
+/*
+ * Speck test vectors taken from the original paper:
+ * "The Simon and Speck Families of Lightweight Block Ciphers"
+ * https://eprint.iacr.org/2013/404.pdf
+ *
+ * Note that the paper does not make byte and word order clear.  But it was
+ * confirmed with the authors that the intended orders are little endian byte
+ * order and (y, x) word order.  Equivalently, the printed test vectors, when
+ * looking at only the bytes (ignoring the whitespace that divides them into
+ * words), are backwards: the left-most byte is actually the one with the
+ * highest memory address, while the right-most byte is actually the one with
+ * the lowest memory address.
+ */
+
+static const struct cipher_testvec speck128_enc_tv_template[] = {
+	{ /* Speck128/128 */
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.klen	= 16,
+		.input	= "\x20\x6d\x61\x64\x65\x20\x69\x74"
+			  "\x20\x65\x71\x75\x69\x76\x61\x6c",
+		.ilen	= 16,
+		.result	= "\x18\x0d\x57\x5c\xdf\xfe\x60\x78"
+			  "\x65\x32\x78\x79\x51\x98\x5d\xa6",
+		.rlen	= 16,
+	}, { /* Speck128/192 */
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17",
+		.klen	= 24,
+		.input	= "\x65\x6e\x74\x20\x74\x6f\x20\x43"
+			  "\x68\x69\x65\x66\x20\x48\x61\x72",
+		.ilen	= 16,
+		.result	= "\x86\x18\x3c\xe0\x5d\x18\xbc\xf9"
+			  "\x66\x55\x13\x13\x3a\xcf\xe4\x1b",
+		.rlen	= 16,
+	}, { /* Speck128/256 */
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
+		.klen	= 32,
+		.input	= "\x70\x6f\x6f\x6e\x65\x72\x2e\x20"
+			  "\x49\x6e\x20\x74\x68\x6f\x73\x65",
+		.ilen	= 16,
+		.result	= "\x43\x8f\x18\x9c\x8d\xb4\xee\x4e"
+			  "\x3e\xf5\xc0\x05\x04\x01\x09\x41",
+		.rlen	= 16,
+	},
+};
+
+static const struct cipher_testvec speck128_dec_tv_template[] = {
+	{ /* Speck128/128 */
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.klen	= 16,
+		.input	= "\x18\x0d\x57\x5c\xdf\xfe\x60\x78"
+			  "\x65\x32\x78\x79\x51\x98\x5d\xa6",
+		.ilen	= 16,
+		.result	= "\x20\x6d\x61\x64\x65\x20\x69\x74"
+			  "\x20\x65\x71\x75\x69\x76\x61\x6c",
+		.rlen	= 16,
+	}, { /* Speck128/192 */
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17",
+		.klen	= 24,
+		.input	= "\x86\x18\x3c\xe0\x5d\x18\xbc\xf9"
+			  "\x66\x55\x13\x13\x3a\xcf\xe4\x1b",
+		.ilen	= 16,
+		.result	= "\x65\x6e\x74\x20\x74\x6f\x20\x43"
+			  "\x68\x69\x65\x66\x20\x48\x61\x72",
+		.rlen	= 16,
+	}, { /* Speck128/256 */
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
+		.klen	= 32,
+		.input	= "\x43\x8f\x18\x9c\x8d\xb4\xee\x4e"
+			  "\x3e\xf5\xc0\x05\x04\x01\x09\x41",
+		.ilen	= 16,
+		.result	= "\x70\x6f\x6f\x6e\x65\x72\x2e\x20"
+			  "\x49\x6e\x20\x74\x68\x6f\x73\x65",
+		.rlen	= 16,
+	},
+};
+
+/*
+ * Speck128-XTS test vectors, taken from the AES-XTS test vectors with the
+ * result recomputed with Speck128 as the cipher
+ */
+
+static const struct cipher_testvec speck128_xts_enc_tv_template[] = {
+	{
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen	= 32,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ilen	= 32,
+		.result	= "\xbe\xa0\xe7\x03\xd7\xfe\xab\x62"
+			  "\x3b\x99\x4a\x64\x74\x77\xac\xed"
+			  "\xd8\xf4\xa6\xcf\xae\xb9\x07\x42"
+			  "\x51\xd9\xb6\x1d\xe0\x5e\xbc\x54",
+		.rlen	= 32,
+	}, {
+		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
+			  "\x11\x11\x11\x11\x11\x11\x11\x11"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22",
+		.klen	= 32,
+		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44",
+		.ilen	= 32,
+		.result	= "\xfb\x53\x81\x75\x6f\x9f\x34\xad"
+			  "\x7e\x01\xed\x7b\xcc\xda\x4e\x4a"
+			  "\xd4\x84\xa4\x53\xd5\x88\x73\x1b"
+			  "\xfd\xcb\xae\x0d\xf3\x04\xee\xe6",
+		.rlen	= 32,
+	}, {
+		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
+			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22",
+		.klen	= 32,
+		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44",
+		.ilen	= 32,
+		.result	= "\x21\x52\x84\x15\xd1\xf7\x21\x55"
+			  "\xd9\x75\x4a\xd3\xc5\xdb\x9f\x7d"
+			  "\xda\x63\xb2\xf1\x82\xb0\x89\x59"
+			  "\x86\xd4\xaa\xaa\xdd\xff\x4f\x92",
+		.rlen	= 32,
+	}, {
+		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
+			  "\x23\x53\x60\x28\x74\x71\x35\x26"
+			  "\x31\x41\x59\x26\x53\x58\x97\x93"
+			  "\x23\x84\x62\x64\x33\x83\x27\x95",
+		.klen	= 32,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
+			  "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
+		.ilen	= 512,
+		.result	= "\x57\xb5\xf8\x71\x6e\x6d\xdd\x82"
+			  "\x53\xd0\xed\x2d\x30\xc1\x20\xef"
+			  "\x70\x67\x5e\xff\x09\x70\xbb\xc1"
+			  "\x3a\x7b\x48\x26\xd9\x0b\xf4\x48"
+			  "\xbe\xce\xb1\xc7\xb2\x67\xc4\xa7"
+			  "\x76\xf8\x36\x30\xb7\xb4\x9a\xd9"
+			  "\xf5\x9d\xd0\x7b\xc1\x06\x96\x44"
+			  "\x19\xc5\x58\x84\x63\xb9\x12\x68"
+			  "\x68\xc7\xaa\x18\x98\xf2\x1f\x5c"
+			  "\x39\xa6\xd8\x32\x2b\xc3\x51\xfd"
+			  "\x74\x79\x2e\xb4\x44\xd7\x69\xc4"
+			  "\xfc\x29\xe6\xed\x26\x1e\xa6\x9d"
+			  "\x1c\xbe\x00\x0e\x7f\x3a\xca\xfb"
+			  "\x6d\x13\x65\xa0\xf9\x31\x12\xe2"
+			  "\x26\xd1\xec\x2b\x0a\x8b\x59\x99"
+			  "\xa7\x49\xa0\x0e\x09\x33\x85\x50"
+			  "\xc3\x23\xca\x7a\xdd\x13\x45\x5f"
+			  "\xde\x4c\xa7\xcb\x00\x8a\x66\x6f"
+			  "\xa2\xb6\xb1\x2e\xe1\xa0\x18\xf6"
+			  "\xad\xf3\xbd\xeb\xc7\xef\x55\x4f"
+			  "\x79\x91\x8d\x36\x13\x7b\xd0\x4a"
+			  "\x6c\x39\xfb\x53\xb8\x6f\x02\x51"
+			  "\xa5\x20\xac\x24\x1c\x73\x59\x73"
+			  "\x58\x61\x3a\x87\x58\xb3\x20\x56"
+			  "\x39\x06\x2b\x4d\xd3\x20\x2b\x89"
+			  "\x3f\xa2\xf0\x96\xeb\x7f\xa4\xcd"
+			  "\x11\xae\xbd\xcb\x3a\xb4\xd9\x91"
+			  "\x09\x35\x71\x50\x65\xac\x92\xe3"
+			  "\x7b\x32\xc0\x7a\xdd\xd4\xc3\x92"
+			  "\x6f\xeb\x79\xde\x6f\xd3\x25\xc9"
+			  "\xcd\x63\xf5\x1e\x7a\x3b\x26\x9d"
+			  "\x77\x04\x80\xa9\xbf\x38\xb5\xbd"
+			  "\xb8\x05\x07\xbd\xfd\xab\x7b\xf8"
+			  "\x2a\x26\xcc\x49\x14\x6d\x55\x01"
+			  "\x06\x94\xd8\xb2\x2d\x53\x83\x1b"
+			  "\x8f\xd4\xdd\x57\x12\x7e\x18\xba"
+			  "\x8e\xe2\x4d\x80\xef\x7e\x6b\x9d"
+			  "\x24\xa9\x60\xa4\x97\x85\x86\x2a"
+			  "\x01\x00\x09\xf1\xcb\x4a\x24\x1c"
+			  "\xd8\xf6\xe6\x5b\xe7\x5d\xf2\xc4"
+			  "\x97\x1c\x10\xc6\x4d\x66\x4f\x98"
+			  "\x87\x30\xac\xd5\xea\x73\x49\x10"
+			  "\x80\xea\xe5\x5f\x4d\x5f\x03\x33"
+			  "\x66\x02\x35\x3d\x60\x06\x36\x4f"
+			  "\x14\x1c\xd8\x07\x1f\x78\xd0\xf8"
+			  "\x4f\x6c\x62\x7c\x15\xa5\x7c\x28"
+			  "\x7c\xcc\xeb\x1f\xd1\x07\x90\x93"
+			  "\x7e\xc2\xa8\x3a\x80\xc0\xf5\x30"
+			  "\xcc\x75\xcf\x16\x26\xa9\x26\x3b"
+			  "\xe7\x68\x2f\x15\x21\x5b\xe4\x00"
+			  "\xbd\x48\x50\xcd\x75\x70\xc4\x62"
+			  "\xbb\x41\xfb\x89\x4a\x88\x3b\x3b"
+			  "\x51\x66\x02\x69\x04\x97\x36\xd4"
+			  "\x75\xae\x0b\xa3\x42\xf8\xca\x79"
+			  "\x8f\x93\xe9\xcc\x38\xbd\xd6\xd2"
+			  "\xf9\x70\x4e\xc3\x6a\x8e\x25\xbd"
+			  "\xea\x15\x5a\xa0\x85\x7e\x81\x0d"
+			  "\x03\xe7\x05\x39\xf5\x05\x26\xee"
+			  "\xec\xaa\x1f\x3d\xc9\x98\x76\x01"
+			  "\x2c\xf4\xfc\xa3\x88\x77\x38\xc4"
+			  "\x50\x65\x50\x6d\x04\x1f\xdf\x5a"
+			  "\xaa\xf2\x01\xa9\xc1\x8d\xee\xca"
+			  "\x47\x26\xef\x39\xb8\xb4\xf2\xd1"
+			  "\xd6\xbb\x1b\x2a\xc1\x34\x14\xcf",
+		.rlen	= 512,
+	}, {
+		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
+			  "\x23\x53\x60\x28\x74\x71\x35\x26"
+			  "\x62\x49\x77\x57\x24\x70\x93\x69"
+			  "\x99\x59\x57\x49\x66\x96\x76\x27"
+			  "\x31\x41\x59\x26\x53\x58\x97\x93"
+			  "\x23\x84\x62\x64\x33\x83\x27\x95"
+			  "\x02\x88\x41\x97\x16\x93\x99\x37"
+			  "\x51\x05\x82\x09\x74\x94\x45\x92",
+		.klen	= 64,
+		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
+			  "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
+		.ilen	= 512,
+		.result	= "\xc5\x85\x2a\x4b\x73\xe4\xf6\xf1"
+			  "\x7e\xf9\xf6\xe9\xa3\x73\x36\xcb"
+			  "\xaa\xb6\x22\xb0\x24\x6e\x3d\x73"
+			  "\x92\x99\xde\xd3\x76\xed\xcd\x63"
+			  "\x64\x3a\x22\x57\xc1\x43\x49\xd4"
+			  "\x79\x36\x31\x19\x62\xae\x10\x7e"
+			  "\x7d\xcf\x7a\xe2\x6b\xce\x27\xfa"
+			  "\xdc\x3d\xd9\x83\xd3\x42\x4c\xe0"
+			  "\x1b\xd6\x1d\x1a\x6f\xd2\x03\x00"
+			  "\xfc\x81\x99\x8a\x14\x62\xf5\x7e"
+			  "\x0d\xe7\x12\xe8\x17\x9d\x0b\xec"
+			  "\xe2\xf7\xc9\xa7\x63\xd1\x79\xb6"
+			  "\x62\x62\x37\xfe\x0a\x4c\x4a\x37"
+			  "\x70\xc7\x5e\x96\x5f\xbc\x8e\x9e"
+			  "\x85\x3c\x4f\x26\x64\x85\xbc\x68"
+			  "\xb0\xe0\x86\x5e\x26\x41\xce\x11"
+			  "\x50\xda\x97\x14\xe9\x9e\xc7\x6d"
+			  "\x3b\xdc\x43\xde\x2b\x27\x69\x7d"
+			  "\xfc\xb0\x28\xbd\x8f\xb1\xc6\x31"
+			  "\x14\x4d\xf0\x74\x37\xfd\x07\x25"
+			  "\x96\x55\xe5\xfc\x9e\x27\x2a\x74"
+			  "\x1b\x83\x4d\x15\x83\xac\x57\xa0"
+			  "\xac\xa5\xd0\x38\xef\x19\x56\x53"
+			  "\x25\x4b\xfc\xce\x04\x23\xe5\x6b"
+			  "\xf6\xc6\x6c\x32\x0b\xb3\x12\xc5"
+			  "\xed\x22\x34\x1c\x5d\xed\x17\x06"
+			  "\x36\xa3\xe6\x77\xb9\x97\x46\xb8"
+			  "\xe9\x3f\x7e\xc7\xbc\x13\x5c\xdc"
+			  "\x6e\x3f\x04\x5e\xd1\x59\xa5\x82"
+			  "\x35\x91\x3d\x1b\xe4\x97\x9f\x92"
+			  "\x1c\x5e\x5f\x6f\x41\xd4\x62\xa1"
+			  "\x8d\x39\xfc\x42\xfb\x38\x80\xb9"
+			  "\x0a\xe3\xcc\x6a\x93\xd9\x7a\xb1"
+			  "\xe9\x69\xaf\x0a\x6b\x75\x38\xa7"
+			  "\xa1\xbf\xf7\xda\x95\x93\x4b\x78"
+			  "\x19\xf5\x94\xf9\xd2\x00\x33\x37"
+			  "\xcf\xf5\x9e\x9c\xf3\xcc\xa6\xee"
+			  "\x42\xb2\x9e\x2c\x5f\x48\x23\x26"
+			  "\x15\x25\x17\x03\x3d\xfe\x2c\xfc"
+			  "\xeb\xba\xda\xe0\x00\x05\xb6\xa6"
+			  "\x07\xb3\xe8\x36\x5b\xec\x5b\xbf"
+			  "\xd6\x5b\x00\x74\xc6\x97\xf1\x6a"
+			  "\x49\xa1\xc3\xfa\x10\x52\xb9\x14"
+			  "\xad\xb7\x73\xf8\x78\x12\xc8\x59"
+			  "\x17\x80\x4c\x57\x39\xf1\x6d\x80"
+			  "\x25\x77\x0f\x5e\x7d\xf0\xaf\x21"
+			  "\xec\xce\xb7\xc8\x02\x8a\xed\x53"
+			  "\x2c\x25\x68\x2e\x1f\x85\x5e\x67"
+			  "\xd1\x07\x7a\x3a\x89\x08\xe0\x34"
+			  "\xdc\xdb\x26\xb4\x6b\x77\xfc\x40"
+			  "\x31\x15\x72\xa0\xf0\x73\xd9\x3b"
+			  "\xd5\xdb\xfe\xfc\x8f\xa9\x44\xa2"
+			  "\x09\x9f\xc6\x33\xe5\xe2\x88\xe8"
+			  "\xf3\xf0\x1a\xf4\xce\x12\x0f\xd6"
+			  "\xf7\x36\xe6\xa4\xf4\x7a\x10\x58"
+			  "\xcc\x1f\x48\x49\x65\x47\x75\xe9"
+			  "\x28\xe1\x65\x7b\xf2\xc4\xb5\x07"
+			  "\xf2\xec\x76\xd8\x8f\x09\xf3\x16"
+			  "\xa1\x51\x89\x3b\xeb\x96\x42\xac"
+			  "\x65\xe0\x67\x63\x29\xdc\xb4\x7d"
+			  "\xf2\x41\x51\x6a\xcb\xde\x3c\xfb"
+			  "\x66\x8d\x13\xca\xe0\x59\x2a\x00"
+			  "\xc9\x53\x4c\xe6\x9e\xe2\x73\xd5"
+			  "\x67\x19\xb2\xbd\x9a\x63\xd7\x5c",
+		.rlen	= 512,
+		.also_non_np = 1,
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
+	}
+};
+
+static const struct cipher_testvec speck128_xts_dec_tv_template[] = {
+	{
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen	= 32,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\xbe\xa0\xe7\x03\xd7\xfe\xab\x62"
+			  "\x3b\x99\x4a\x64\x74\x77\xac\xed"
+			  "\xd8\xf4\xa6\xcf\xae\xb9\x07\x42"
+			  "\x51\xd9\xb6\x1d\xe0\x5e\xbc\x54",
+		.ilen	= 32,
+		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.rlen	= 32,
+	}, {
+		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
+			  "\x11\x11\x11\x11\x11\x11\x11\x11"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22",
+		.klen	= 32,
+		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\xfb\x53\x81\x75\x6f\x9f\x34\xad"
+			  "\x7e\x01\xed\x7b\xcc\xda\x4e\x4a"
+			  "\xd4\x84\xa4\x53\xd5\x88\x73\x1b"
+			  "\xfd\xcb\xae\x0d\xf3\x04\xee\xe6",
+		.ilen	= 32,
+		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44",
+		.rlen	= 32,
+	}, {
+		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
+			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22",
+		.klen	= 32,
+		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x21\x52\x84\x15\xd1\xf7\x21\x55"
+			  "\xd9\x75\x4a\xd3\xc5\xdb\x9f\x7d"
+			  "\xda\x63\xb2\xf1\x82\xb0\x89\x59"
+			  "\x86\xd4\xaa\xaa\xdd\xff\x4f\x92",
+		.ilen	= 32,
+		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44",
+		.rlen	= 32,
+	}, {
+		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
+			  "\x23\x53\x60\x28\x74\x71\x35\x26"
+			  "\x31\x41\x59\x26\x53\x58\x97\x93"
+			  "\x23\x84\x62\x64\x33\x83\x27\x95",
+		.klen	= 32,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x57\xb5\xf8\x71\x6e\x6d\xdd\x82"
+			  "\x53\xd0\xed\x2d\x30\xc1\x20\xef"
+			  "\x70\x67\x5e\xff\x09\x70\xbb\xc1"
+			  "\x3a\x7b\x48\x26\xd9\x0b\xf4\x48"
+			  "\xbe\xce\xb1\xc7\xb2\x67\xc4\xa7"
+			  "\x76\xf8\x36\x30\xb7\xb4\x9a\xd9"
+			  "\xf5\x9d\xd0\x7b\xc1\x06\x96\x44"
+			  "\x19\xc5\x58\x84\x63\xb9\x12\x68"
+			  "\x68\xc7\xaa\x18\x98\xf2\x1f\x5c"
+			  "\x39\xa6\xd8\x32\x2b\xc3\x51\xfd"
+			  "\x74\x79\x2e\xb4\x44\xd7\x69\xc4"
+			  "\xfc\x29\xe6\xed\x26\x1e\xa6\x9d"
+			  "\x1c\xbe\x00\x0e\x7f\x3a\xca\xfb"
+			  "\x6d\x13\x65\xa0\xf9\x31\x12\xe2"
+			  "\x26\xd1\xec\x2b\x0a\x8b\x59\x99"
+			  "\xa7\x49\xa0\x0e\x09\x33\x85\x50"
+			  "\xc3\x23\xca\x7a\xdd\x13\x45\x5f"
+			  "\xde\x4c\xa7\xcb\x00\x8a\x66\x6f"
+			  "\xa2\xb6\xb1\x2e\xe1\xa0\x18\xf6"
+			  "\xad\xf3\xbd\xeb\xc7\xef\x55\x4f"
+			  "\x79\x91\x8d\x36\x13\x7b\xd0\x4a"
+			  "\x6c\x39\xfb\x53\xb8\x6f\x02\x51"
+			  "\xa5\x20\xac\x24\x1c\x73\x59\x73"
+			  "\x58\x61\x3a\x87\x58\xb3\x20\x56"
+			  "\x39\x06\x2b\x4d\xd3\x20\x2b\x89"
+			  "\x3f\xa2\xf0\x96\xeb\x7f\xa4\xcd"
+			  "\x11\xae\xbd\xcb\x3a\xb4\xd9\x91"
+			  "\x09\x35\x71\x50\x65\xac\x92\xe3"
+			  "\x7b\x32\xc0\x7a\xdd\xd4\xc3\x92"
+			  "\x6f\xeb\x79\xde\x6f\xd3\x25\xc9"
+			  "\xcd\x63\xf5\x1e\x7a\x3b\x26\x9d"
+			  "\x77\x04\x80\xa9\xbf\x38\xb5\xbd"
+			  "\xb8\x05\x07\xbd\xfd\xab\x7b\xf8"
+			  "\x2a\x26\xcc\x49\x14\x6d\x55\x01"
+			  "\x06\x94\xd8\xb2\x2d\x53\x83\x1b"
+			  "\x8f\xd4\xdd\x57\x12\x7e\x18\xba"
+			  "\x8e\xe2\x4d\x80\xef\x7e\x6b\x9d"
+			  "\x24\xa9\x60\xa4\x97\x85\x86\x2a"
+			  "\x01\x00\x09\xf1\xcb\x4a\x24\x1c"
+			  "\xd8\xf6\xe6\x5b\xe7\x5d\xf2\xc4"
+			  "\x97\x1c\x10\xc6\x4d\x66\x4f\x98"
+			  "\x87\x30\xac\xd5\xea\x73\x49\x10"
+			  "\x80\xea\xe5\x5f\x4d\x5f\x03\x33"
+			  "\x66\x02\x35\x3d\x60\x06\x36\x4f"
+			  "\x14\x1c\xd8\x07\x1f\x78\xd0\xf8"
+			  "\x4f\x6c\x62\x7c\x15\xa5\x7c\x28"
+			  "\x7c\xcc\xeb\x1f\xd1\x07\x90\x93"
+			  "\x7e\xc2\xa8\x3a\x80\xc0\xf5\x30"
+			  "\xcc\x75\xcf\x16\x26\xa9\x26\x3b"
+			  "\xe7\x68\x2f\x15\x21\x5b\xe4\x00"
+			  "\xbd\x48\x50\xcd\x75\x70\xc4\x62"
+			  "\xbb\x41\xfb\x89\x4a\x88\x3b\x3b"
+			  "\x51\x66\x02\x69\x04\x97\x36\xd4"
+			  "\x75\xae\x0b\xa3\x42\xf8\xca\x79"
+			  "\x8f\x93\xe9\xcc\x38\xbd\xd6\xd2"
+			  "\xf9\x70\x4e\xc3\x6a\x8e\x25\xbd"
+			  "\xea\x15\x5a\xa0\x85\x7e\x81\x0d"
+			  "\x03\xe7\x05\x39\xf5\x05\x26\xee"
+			  "\xec\xaa\x1f\x3d\xc9\x98\x76\x01"
+			  "\x2c\xf4\xfc\xa3\x88\x77\x38\xc4"
+			  "\x50\x65\x50\x6d\x04\x1f\xdf\x5a"
+			  "\xaa\xf2\x01\xa9\xc1\x8d\xee\xca"
+			  "\x47\x26\xef\x39\xb8\xb4\xf2\xd1"
+			  "\xd6\xbb\x1b\x2a\xc1\x34\x14\xcf",
+		.ilen	= 512,
+		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
+			  "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
+		.rlen	= 512,
+	}, {
+		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
+			  "\x23\x53\x60\x28\x74\x71\x35\x26"
+			  "\x62\x49\x77\x57\x24\x70\x93\x69"
+			  "\x99\x59\x57\x49\x66\x96\x76\x27"
+			  "\x31\x41\x59\x26\x53\x58\x97\x93"
+			  "\x23\x84\x62\x64\x33\x83\x27\x95"
+			  "\x02\x88\x41\x97\x16\x93\x99\x37"
+			  "\x51\x05\x82\x09\x74\x94\x45\x92",
+		.klen	= 64,
+		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\xc5\x85\x2a\x4b\x73\xe4\xf6\xf1"
+			  "\x7e\xf9\xf6\xe9\xa3\x73\x36\xcb"
+			  "\xaa\xb6\x22\xb0\x24\x6e\x3d\x73"
+			  "\x92\x99\xde\xd3\x76\xed\xcd\x63"
+			  "\x64\x3a\x22\x57\xc1\x43\x49\xd4"
+			  "\x79\x36\x31\x19\x62\xae\x10\x7e"
+			  "\x7d\xcf\x7a\xe2\x6b\xce\x27\xfa"
+			  "\xdc\x3d\xd9\x83\xd3\x42\x4c\xe0"
+			  "\x1b\xd6\x1d\x1a\x6f\xd2\x03\x00"
+			  "\xfc\x81\x99\x8a\x14\x62\xf5\x7e"
+			  "\x0d\xe7\x12\xe8\x17\x9d\x0b\xec"
+			  "\xe2\xf7\xc9\xa7\x63\xd1\x79\xb6"
+			  "\x62\x62\x37\xfe\x0a\x4c\x4a\x37"
+			  "\x70\xc7\x5e\x96\x5f\xbc\x8e\x9e"
+			  "\x85\x3c\x4f\x26\x64\x85\xbc\x68"
+			  "\xb0\xe0\x86\x5e\x26\x41\xce\x11"
+			  "\x50\xda\x97\x14\xe9\x9e\xc7\x6d"
+			  "\x3b\xdc\x43\xde\x2b\x27\x69\x7d"
+			  "\xfc\xb0\x28\xbd\x8f\xb1\xc6\x31"
+			  "\x14\x4d\xf0\x74\x37\xfd\x07\x25"
+			  "\x96\x55\xe5\xfc\x9e\x27\x2a\x74"
+			  "\x1b\x83\x4d\x15\x83\xac\x57\xa0"
+			  "\xac\xa5\xd0\x38\xef\x19\x56\x53"
+			  "\x25\x4b\xfc\xce\x04\x23\xe5\x6b"
+			  "\xf6\xc6\x6c\x32\x0b\xb3\x12\xc5"
+			  "\xed\x22\x34\x1c\x5d\xed\x17\x06"
+			  "\x36\xa3\xe6\x77\xb9\x97\x46\xb8"
+			  "\xe9\x3f\x7e\xc7\xbc\x13\x5c\xdc"
+			  "\x6e\x3f\x04\x5e\xd1\x59\xa5\x82"
+			  "\x35\x91\x3d\x1b\xe4\x97\x9f\x92"
+			  "\x1c\x5e\x5f\x6f\x41\xd4\x62\xa1"
+			  "\x8d\x39\xfc\x42\xfb\x38\x80\xb9"
+			  "\x0a\xe3\xcc\x6a\x93\xd9\x7a\xb1"
+			  "\xe9\x69\xaf\x0a\x6b\x75\x38\xa7"
+			  "\xa1\xbf\xf7\xda\x95\x93\x4b\x78"
+			  "\x19\xf5\x94\xf9\xd2\x00\x33\x37"
+			  "\xcf\xf5\x9e\x9c\xf3\xcc\xa6\xee"
+			  "\x42\xb2\x9e\x2c\x5f\x48\x23\x26"
+			  "\x15\x25\x17\x03\x3d\xfe\x2c\xfc"
+			  "\xeb\xba\xda\xe0\x00\x05\xb6\xa6"
+			  "\x07\xb3\xe8\x36\x5b\xec\x5b\xbf"
+			  "\xd6\x5b\x00\x74\xc6\x97\xf1\x6a"
+			  "\x49\xa1\xc3\xfa\x10\x52\xb9\x14"
+			  "\xad\xb7\x73\xf8\x78\x12\xc8\x59"
+			  "\x17\x80\x4c\x57\x39\xf1\x6d\x80"
+			  "\x25\x77\x0f\x5e\x7d\xf0\xaf\x21"
+			  "\xec\xce\xb7\xc8\x02\x8a\xed\x53"
+			  "\x2c\x25\x68\x2e\x1f\x85\x5e\x67"
+			  "\xd1\x07\x7a\x3a\x89\x08\xe0\x34"
+			  "\xdc\xdb\x26\xb4\x6b\x77\xfc\x40"
+			  "\x31\x15\x72\xa0\xf0\x73\xd9\x3b"
+			  "\xd5\xdb\xfe\xfc\x8f\xa9\x44\xa2"
+			  "\x09\x9f\xc6\x33\xe5\xe2\x88\xe8"
+			  "\xf3\xf0\x1a\xf4\xce\x12\x0f\xd6"
+			  "\xf7\x36\xe6\xa4\xf4\x7a\x10\x58"
+			  "\xcc\x1f\x48\x49\x65\x47\x75\xe9"
+			  "\x28\xe1\x65\x7b\xf2\xc4\xb5\x07"
+			  "\xf2\xec\x76\xd8\x8f\x09\xf3\x16"
+			  "\xa1\x51\x89\x3b\xeb\x96\x42\xac"
+			  "\x65\xe0\x67\x63\x29\xdc\xb4\x7d"
+			  "\xf2\x41\x51\x6a\xcb\xde\x3c\xfb"
+			  "\x66\x8d\x13\xca\xe0\x59\x2a\x00"
+			  "\xc9\x53\x4c\xe6\x9e\xe2\x73\xd5"
+			  "\x67\x19\xb2\xbd\x9a\x63\xd7\x5c",
+		.ilen	= 512,
+		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
+			  "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
+		.rlen	= 512,
+		.also_non_np = 1,
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
+	}
+};
+
+static const struct cipher_testvec speck64_enc_tv_template[] = {
+	{ /* Speck64/96 */
+		.key	= "\x00\x01\x02\x03\x08\x09\x0a\x0b"
+			  "\x10\x11\x12\x13",
+		.klen	= 12,
+		.input	= "\x65\x61\x6e\x73\x20\x46\x61\x74",
+		.ilen	= 8,
+		.result	= "\x6c\x94\x75\x41\xec\x52\x79\x9f",
+		.rlen	= 8,
+	}, { /* Speck64/128 */
+		.key	= "\x00\x01\x02\x03\x08\x09\x0a\x0b"
+			  "\x10\x11\x12\x13\x18\x19\x1a\x1b",
+		.klen	= 16,
+		.input	= "\x2d\x43\x75\x74\x74\x65\x72\x3b",
+		.ilen	= 8,
+		.result	= "\x8b\x02\x4e\x45\x48\xa5\x6f\x8c",
+		.rlen	= 8,
+	},
+};
+
+static const struct cipher_testvec speck64_dec_tv_template[] = {
+	{ /* Speck64/96 */
+		.key	= "\x00\x01\x02\x03\x08\x09\x0a\x0b"
+			  "\x10\x11\x12\x13",
+		.klen	= 12,
+		.input	= "\x6c\x94\x75\x41\xec\x52\x79\x9f",
+		.ilen	= 8,
+		.result	= "\x65\x61\x6e\x73\x20\x46\x61\x74",
+		.rlen	= 8,
+	}, { /* Speck64/128 */
+		.key	= "\x00\x01\x02\x03\x08\x09\x0a\x0b"
+			  "\x10\x11\x12\x13\x18\x19\x1a\x1b",
+		.klen	= 16,
+		.input	= "\x8b\x02\x4e\x45\x48\xa5\x6f\x8c",
+		.ilen	= 8,
+		.result	= "\x2d\x43\x75\x74\x74\x65\x72\x3b",
+		.rlen	= 8,
+	},
+};
+
+/*
+ * Speck64-XTS test vectors, taken from the AES-XTS test vectors with the result
+ * recomputed with Speck64 as the cipher, and key lengths adjusted
+ */
+
+static const struct cipher_testvec speck64_xts_enc_tv_template[] = {
+	{
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen	= 24,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ilen	= 32,
+		.result	= "\x84\xaf\x54\x07\x19\xd4\x7c\xa6"
+			  "\xe4\xfe\xdf\xc4\x1f\x34\xc3\xc2"
+			  "\x80\xf5\x72\xe7\xcd\xf0\x99\x22"
+			  "\x35\xa7\x2f\x06\xef\xdc\x51\xaa",
+		.rlen	= 32,
+	}, {
+		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
+			  "\x11\x11\x11\x11\x11\x11\x11\x11"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22",
+		.klen	= 24,
+		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44",
+		.ilen	= 32,
+		.result	= "\x12\x56\x73\xcd\x15\x87\xa8\x59"
+			  "\xcf\x84\xae\xd9\x1c\x66\xd6\x9f"
+			  "\xb3\x12\x69\x7e\x36\xeb\x52\xff"
+			  "\x62\xdd\xba\x90\xb3\xe1\xee\x99",
+		.rlen	= 32,
+	}, {
+		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
+			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22",
+		.klen	= 24,
+		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44",
+		.ilen	= 32,
+		.result	= "\x15\x1b\xe4\x2c\xa2\x5a\x2d\x2c"
+			  "\x27\x36\xc0\xbf\x5d\xea\x36\x37"
+			  "\x2d\x1a\x88\xbc\x66\xb5\xd0\x0b"
+			  "\xa1\xbc\x19\xb2\x0f\x3b\x75\x34",
+		.rlen	= 32,
+	}, {
+		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
+			  "\x23\x53\x60\x28\x74\x71\x35\x26"
+			  "\x31\x41\x59\x26\x53\x58\x97\x93",
+		.klen	= 24,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
+			  "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
+		.ilen	= 512,
+		.result	= "\xaf\xa1\x81\xa6\x32\xbb\x15\x8e"
+			  "\xf8\x95\x2e\xd3\xe6\xee\x7e\x09"
+			  "\x0c\x1a\xf5\x02\x97\x8b\xe3\xb3"
+			  "\x11\xc7\x39\x96\xd0\x95\xf4\x56"
+			  "\xf4\xdd\x03\x38\x01\x44\x2c\xcf"
+			  "\x88\xae\x8e\x3c\xcd\xe7\xaa\x66"
+			  "\xfe\x3d\xc6\xfb\x01\x23\x51\x43"
+			  "\xd5\xd2\x13\x86\x94\x34\xe9\x62"
+			  "\xf9\x89\xe3\xd1\x7b\xbe\xf8\xef"
+			  "\x76\x35\x04\x3f\xdb\x23\x9d\x0b"
+			  "\x85\x42\xb9\x02\xd6\xcc\xdb\x96"
+			  "\xa7\x6b\x27\xb6\xd4\x45\x8f\x7d"
+			  "\xae\xd2\x04\xd5\xda\xc1\x7e\x24"
+			  "\x8c\x73\xbe\x48\x7e\xcf\x65\x28"
+			  "\x29\xe5\xbe\x54\x30\xcb\x46\x95"
+			  "\x4f\x2e\x8a\x36\xc8\x27\xc5\xbe"
+			  "\xd0\x1a\xaf\xab\x26\xcd\x9e\x69"
+			  "\xa1\x09\x95\x71\x26\xe9\xc4\xdf"
+			  "\xe6\x31\xc3\x46\xda\xaf\x0b\x41"
+			  "\x1f\xab\xb1\x8e\xd6\xfc\x0b\xb3"
+			  "\x82\xc0\x37\x27\xfc\x91\xa7\x05"
+			  "\xfb\xc5\xdc\x2b\x74\x96\x48\x43"
+			  "\x5d\x9c\x19\x0f\x60\x63\x3a\x1f"
+			  "\x6f\xf0\x03\xbe\x4d\xfd\xc8\x4a"
+			  "\xc6\xa4\x81\x6d\xc3\x12\x2a\x5c"
+			  "\x07\xff\xf3\x72\x74\x48\xb5\x40"
+			  "\x50\xb5\xdd\x90\x43\x31\x18\x15"
+			  "\x7b\xf2\xa6\xdb\x83\xc8\x4b\x4a"
+			  "\x29\x93\x90\x8b\xda\x07\xf0\x35"
+			  "\x6d\x90\x88\x09\x4e\x83\xf5\x5b"
+			  "\x94\x12\xbb\x33\x27\x1d\x3f\x23"
+			  "\x51\xa8\x7c\x07\xa2\xae\x77\xa6"
+			  "\x50\xfd\xcc\xc0\x4f\x80\x7a\x9f"
+			  "\x66\xdd\xcd\x75\x24\x8b\x33\xf7"
+			  "\x20\xdb\x83\x9b\x4f\x11\x63\x6e"
+			  "\xcf\x37\xef\xc9\x11\x01\x5c\x45"
+			  "\x32\x99\x7c\x3c\x9e\x42\x89\xe3"
+			  "\x70\x6d\x15\x9f\xb1\xe6\xb6\x05"
+			  "\xfe\x0c\xb9\x49\x2d\x90\x6d\xcc"
+			  "\x5d\x3f\xc1\xfe\x89\x0a\x2e\x2d"
+			  "\xa0\xa8\x89\x3b\x73\x39\xa5\x94"
+			  "\x4c\xa4\xa6\xbb\xa7\x14\x46\x89"
+			  "\x10\xff\xaf\xef\xca\xdd\x4f\x80"
+			  "\xb3\xdf\x3b\xab\xd4\xe5\x5a\xc7"
+			  "\x33\xca\x00\x8b\x8b\x3f\xea\xec"
+			  "\x68\x8a\xc2\x6d\xfd\xd4\x67\x0f"
+			  "\x22\x31\xe1\x0e\xfe\x5a\x04\xd5"
+			  "\x64\xa3\xf1\x1a\x76\x28\xcc\x35"
+			  "\x36\xa7\x0a\x74\xf7\x1c\x44\x9b"
+			  "\xc7\x1b\x53\x17\x02\xea\xd1\xad"
+			  "\x13\x51\x73\xc0\xa0\xb2\x05\x32"
+			  "\xa8\xa2\x37\x2e\xe1\x7a\x3a\x19"
+			  "\x26\xb4\x6c\x62\x5d\xb3\x1a\x1d"
+			  "\x59\xda\xee\x1a\x22\x18\xda\x0d"
+			  "\x88\x0f\x55\x8b\x72\x62\xfd\xc1"
+			  "\x69\x13\xcd\x0d\x5f\xc1\x09\x52"
+			  "\xee\xd6\xe3\x84\x4d\xee\xf6\x88"
+			  "\xaf\x83\xdc\x76\xf4\xc0\x93\x3f"
+			  "\x4a\x75\x2f\xb0\x0b\x3e\xc4\x54"
+			  "\x7d\x69\x8d\x00\x62\x77\x0d\x14"
+			  "\xbe\x7c\xa6\x7d\xc5\x24\x4f\xf3"
+			  "\x50\xf7\x5f\xf4\xc2\xca\x41\x97"
+			  "\x37\xbe\x75\x74\xcd\xf0\x75\x6e"
+			  "\x25\x23\x94\xbd\xda\x8d\xb0\xd4",
+		.rlen	= 512,
+	}, {
+		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
+			  "\x23\x53\x60\x28\x74\x71\x35\x26"
+			  "\x62\x49\x77\x57\x24\x70\x93\x69"
+			  "\x99\x59\x57\x49\x66\x96\x76\x27",
+		.klen	= 32,
+		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
+			  "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
+		.ilen	= 512,
+		.result	= "\x55\xed\x71\xd3\x02\x8e\x15\x3b"
+			  "\xc6\x71\x29\x2d\x3e\x89\x9f\x59"
+			  "\x68\x6a\xcc\x8a\x56\x97\xf3\x95"
+			  "\x4e\x51\x08\xda\x2a\xf8\x6f\x3c"
+			  "\x78\x16\xea\x80\xdb\x33\x75\x94"
+			  "\xf9\x29\xc4\x2b\x76\x75\x97\xc7"
+			  "\xf2\x98\x2c\xf9\xff\xc8\xd5\x2b"
+			  "\x18\xf1\xaf\xcf\x7c\xc5\x0b\xee"
+			  "\xad\x3c\x76\x7c\xe6\x27\xa2\x2a"
+			  "\xe4\x66\xe1\xab\xa2\x39\xfc\x7c"
+			  "\xf5\xec\x32\x74\xa3\xb8\x03\x88"
+			  "\x52\xfc\x2e\x56\x3f\xa1\xf0\x9f"
+			  "\x84\x5e\x46\xed\x20\x89\xb6\x44"
+			  "\x8d\xd0\xed\x54\x47\x16\xbe\x95"
+			  "\x8a\xb3\x6b\x72\xc4\x32\x52\x13"
+			  "\x1b\xb0\x82\xbe\xac\xf9\x70\xa6"
+			  "\x44\x18\xdd\x8c\x6e\xca\x6e\x45"
+			  "\x8f\x1e\x10\x07\x57\x25\x98\x7b"
+			  "\x17\x8c\x78\xdd\x80\xa7\xd9\xd8"
+			  "\x63\xaf\xb9\x67\x57\xfd\xbc\xdb"
+			  "\x44\xe9\xc5\x65\xd1\xc7\x3b\xff"
+			  "\x20\xa0\x80\x1a\xc3\x9a\xad\x5e"
+			  "\x5d\x3b\xd3\x07\xd9\xf5\xfd\x3d"
+			  "\x4a\x8b\xa8\xd2\x6e\x7a\x51\x65"
+			  "\x6c\x8e\x95\xe0\x45\xc9\x5f\x4a"
+			  "\x09\x3c\x3d\x71\x7f\x0c\x84\x2a"
+			  "\xc8\x48\x52\x1a\xc2\xd5\xd6\x78"
+			  "\x92\x1e\xa0\x90\x2e\xea\xf0\xf3"
+			  "\xdc\x0f\xb1\xaf\x0d\x9b\x06\x2e"
+			  "\x35\x10\x30\x82\x0d\xe7\xc5\x9b"
+			  "\xde\x44\x18\xbd\x9f\xd1\x45\xa9"
+			  "\x7b\x7a\x4a\xad\x35\x65\x27\xca"
+			  "\xb2\xc3\xd4\x9b\x71\x86\x70\xee"
+			  "\xf1\x89\x3b\x85\x4b\x5b\xaa\xaf"
+			  "\xfc\x42\xc8\x31\x59\xbe\x16\x60"
+			  "\x4f\xf9\xfa\x12\xea\xd0\xa7\x14"
+			  "\xf0\x7a\xf3\xd5\x8d\xbd\x81\xef"
+			  "\x52\x7f\x29\x51\x94\x20\x67\x3c"
+			  "\xd1\xaf\x77\x9f\x22\x5a\x4e\x63"
+			  "\xe7\xff\x73\x25\xd1\xdd\x96\x8a"
+			  "\x98\x52\x6d\xf3\xac\x3e\xf2\x18"
+			  "\x6d\xf6\x0a\x29\xa6\x34\x3d\xed"
+			  "\xe3\x27\x0d\x9d\x0a\x02\x44\x7e"
+			  "\x5a\x7e\x67\x0f\x0a\x9e\xd6\xad"
+			  "\x91\xe6\x4d\x81\x8c\x5c\x59\xaa"
+			  "\xfb\xeb\x56\x53\xd2\x7d\x4c\x81"
+			  "\x65\x53\x0f\x41\x11\xbd\x98\x99"
+			  "\xf9\xc6\xfa\x51\x2e\xa3\xdd\x8d"
+			  "\x84\x98\xf9\x34\xed\x33\x2a\x1f"
+			  "\x82\xed\xc1\x73\x98\xd3\x02\xdc"
+			  "\xe6\xc2\x33\x1d\xa2\xb4\xca\x76"
+			  "\x63\x51\x34\x9d\x96\x12\xae\xce"
+			  "\x83\xc9\x76\x5e\xa4\x1b\x53\x37"
+			  "\x17\xd5\xc0\x80\x1d\x62\xf8\x3d"
+			  "\x54\x27\x74\xbb\x10\x86\x57\x46"
+			  "\x68\xe1\xed\x14\xe7\x9d\xfc\x84"
+			  "\x47\xbc\xc2\xf8\x19\x4b\x99\xcf"
+			  "\x7a\xe9\xc4\xb8\x8c\x82\x72\x4d"
+			  "\x7b\x4f\x38\x55\x36\x71\x64\xc1"
+			  "\xfc\x5c\x75\x52\x33\x02\x18\xf8"
+			  "\x17\xe1\x2b\xc2\x43\x39\xbd\x76"
+			  "\x9b\x63\x76\x32\x2f\x19\x72\x10"
+			  "\x9f\x21\x0c\xf1\x66\x50\x7f\xa5"
+			  "\x0d\x1f\x46\xe0\xba\xd3\x2f\x3c",
+		.rlen	= 512,
+		.also_non_np = 1,
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
+	}
+};
+
+static const struct cipher_testvec speck64_xts_dec_tv_template[] = {
+	{
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen	= 24,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x84\xaf\x54\x07\x19\xd4\x7c\xa6"
+			  "\xe4\xfe\xdf\xc4\x1f\x34\xc3\xc2"
+			  "\x80\xf5\x72\xe7\xcd\xf0\x99\x22"
+			  "\x35\xa7\x2f\x06\xef\xdc\x51\xaa",
+		.ilen	= 32,
+		.result	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.rlen	= 32,
+	}, {
+		.key	= "\x11\x11\x11\x11\x11\x11\x11\x11"
+			  "\x11\x11\x11\x11\x11\x11\x11\x11"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22",
+		.klen	= 24,
+		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x12\x56\x73\xcd\x15\x87\xa8\x59"
+			  "\xcf\x84\xae\xd9\x1c\x66\xd6\x9f"
+			  "\xb3\x12\x69\x7e\x36\xeb\x52\xff"
+			  "\x62\xdd\xba\x90\xb3\xe1\xee\x99",
+		.ilen	= 32,
+		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44",
+		.rlen	= 32,
+	}, {
+		.key	= "\xff\xfe\xfd\xfc\xfb\xfa\xf9\xf8"
+			  "\xf7\xf6\xf5\xf4\xf3\xf2\xf1\xf0"
+			  "\x22\x22\x22\x22\x22\x22\x22\x22",
+		.klen	= 24,
+		.iv	= "\x33\x33\x33\x33\x33\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x15\x1b\xe4\x2c\xa2\x5a\x2d\x2c"
+			  "\x27\x36\xc0\xbf\x5d\xea\x36\x37"
+			  "\x2d\x1a\x88\xbc\x66\xb5\xd0\x0b"
+			  "\xa1\xbc\x19\xb2\x0f\x3b\x75\x34",
+		.ilen	= 32,
+		.result	= "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44"
+			  "\x44\x44\x44\x44\x44\x44\x44\x44",
+		.rlen	= 32,
+	}, {
+		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
+			  "\x23\x53\x60\x28\x74\x71\x35\x26"
+			  "\x31\x41\x59\x26\x53\x58\x97\x93",
+		.klen	= 24,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\xaf\xa1\x81\xa6\x32\xbb\x15\x8e"
+			  "\xf8\x95\x2e\xd3\xe6\xee\x7e\x09"
+			  "\x0c\x1a\xf5\x02\x97\x8b\xe3\xb3"
+			  "\x11\xc7\x39\x96\xd0\x95\xf4\x56"
+			  "\xf4\xdd\x03\x38\x01\x44\x2c\xcf"
+			  "\x88\xae\x8e\x3c\xcd\xe7\xaa\x66"
+			  "\xfe\x3d\xc6\xfb\x01\x23\x51\x43"
+			  "\xd5\xd2\x13\x86\x94\x34\xe9\x62"
+			  "\xf9\x89\xe3\xd1\x7b\xbe\xf8\xef"
+			  "\x76\x35\x04\x3f\xdb\x23\x9d\x0b"
+			  "\x85\x42\xb9\x02\xd6\xcc\xdb\x96"
+			  "\xa7\x6b\x27\xb6\xd4\x45\x8f\x7d"
+			  "\xae\xd2\x04\xd5\xda\xc1\x7e\x24"
+			  "\x8c\x73\xbe\x48\x7e\xcf\x65\x28"
+			  "\x29\xe5\xbe\x54\x30\xcb\x46\x95"
+			  "\x4f\x2e\x8a\x36\xc8\x27\xc5\xbe"
+			  "\xd0\x1a\xaf\xab\x26\xcd\x9e\x69"
+			  "\xa1\x09\x95\x71\x26\xe9\xc4\xdf"
+			  "\xe6\x31\xc3\x46\xda\xaf\x0b\x41"
+			  "\x1f\xab\xb1\x8e\xd6\xfc\x0b\xb3"
+			  "\x82\xc0\x37\x27\xfc\x91\xa7\x05"
+			  "\xfb\xc5\xdc\x2b\x74\x96\x48\x43"
+			  "\x5d\x9c\x19\x0f\x60\x63\x3a\x1f"
+			  "\x6f\xf0\x03\xbe\x4d\xfd\xc8\x4a"
+			  "\xc6\xa4\x81\x6d\xc3\x12\x2a\x5c"
+			  "\x07\xff\xf3\x72\x74\x48\xb5\x40"
+			  "\x50\xb5\xdd\x90\x43\x31\x18\x15"
+			  "\x7b\xf2\xa6\xdb\x83\xc8\x4b\x4a"
+			  "\x29\x93\x90\x8b\xda\x07\xf0\x35"
+			  "\x6d\x90\x88\x09\x4e\x83\xf5\x5b"
+			  "\x94\x12\xbb\x33\x27\x1d\x3f\x23"
+			  "\x51\xa8\x7c\x07\xa2\xae\x77\xa6"
+			  "\x50\xfd\xcc\xc0\x4f\x80\x7a\x9f"
+			  "\x66\xdd\xcd\x75\x24\x8b\x33\xf7"
+			  "\x20\xdb\x83\x9b\x4f\x11\x63\x6e"
+			  "\xcf\x37\xef\xc9\x11\x01\x5c\x45"
+			  "\x32\x99\x7c\x3c\x9e\x42\x89\xe3"
+			  "\x70\x6d\x15\x9f\xb1\xe6\xb6\x05"
+			  "\xfe\x0c\xb9\x49\x2d\x90\x6d\xcc"
+			  "\x5d\x3f\xc1\xfe\x89\x0a\x2e\x2d"
+			  "\xa0\xa8\x89\x3b\x73\x39\xa5\x94"
+			  "\x4c\xa4\xa6\xbb\xa7\x14\x46\x89"
+			  "\x10\xff\xaf\xef\xca\xdd\x4f\x80"
+			  "\xb3\xdf\x3b\xab\xd4\xe5\x5a\xc7"
+			  "\x33\xca\x00\x8b\x8b\x3f\xea\xec"
+			  "\x68\x8a\xc2\x6d\xfd\xd4\x67\x0f"
+			  "\x22\x31\xe1\x0e\xfe\x5a\x04\xd5"
+			  "\x64\xa3\xf1\x1a\x76\x28\xcc\x35"
+			  "\x36\xa7\x0a\x74\xf7\x1c\x44\x9b"
+			  "\xc7\x1b\x53\x17\x02\xea\xd1\xad"
+			  "\x13\x51\x73\xc0\xa0\xb2\x05\x32"
+			  "\xa8\xa2\x37\x2e\xe1\x7a\x3a\x19"
+			  "\x26\xb4\x6c\x62\x5d\xb3\x1a\x1d"
+			  "\x59\xda\xee\x1a\x22\x18\xda\x0d"
+			  "\x88\x0f\x55\x8b\x72\x62\xfd\xc1"
+			  "\x69\x13\xcd\x0d\x5f\xc1\x09\x52"
+			  "\xee\xd6\xe3\x84\x4d\xee\xf6\x88"
+			  "\xaf\x83\xdc\x76\xf4\xc0\x93\x3f"
+			  "\x4a\x75\x2f\xb0\x0b\x3e\xc4\x54"
+			  "\x7d\x69\x8d\x00\x62\x77\x0d\x14"
+			  "\xbe\x7c\xa6\x7d\xc5\x24\x4f\xf3"
+			  "\x50\xf7\x5f\xf4\xc2\xca\x41\x97"
+			  "\x37\xbe\x75\x74\xcd\xf0\x75\x6e"
+			  "\x25\x23\x94\xbd\xda\x8d\xb0\xd4",
+		.ilen	= 512,
+		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
+			  "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
+		.rlen	= 512,
+	}, {
+		.key	= "\x27\x18\x28\x18\x28\x45\x90\x45"
+			  "\x23\x53\x60\x28\x74\x71\x35\x26"
+			  "\x62\x49\x77\x57\x24\x70\x93\x69"
+			  "\x99\x59\x57\x49\x66\x96\x76\x27",
+		.klen	= 32,
+		.iv	= "\xff\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x55\xed\x71\xd3\x02\x8e\x15\x3b"
+			  "\xc6\x71\x29\x2d\x3e\x89\x9f\x59"
+			  "\x68\x6a\xcc\x8a\x56\x97\xf3\x95"
+			  "\x4e\x51\x08\xda\x2a\xf8\x6f\x3c"
+			  "\x78\x16\xea\x80\xdb\x33\x75\x94"
+			  "\xf9\x29\xc4\x2b\x76\x75\x97\xc7"
+			  "\xf2\x98\x2c\xf9\xff\xc8\xd5\x2b"
+			  "\x18\xf1\xaf\xcf\x7c\xc5\x0b\xee"
+			  "\xad\x3c\x76\x7c\xe6\x27\xa2\x2a"
+			  "\xe4\x66\xe1\xab\xa2\x39\xfc\x7c"
+			  "\xf5\xec\x32\x74\xa3\xb8\x03\x88"
+			  "\x52\xfc\x2e\x56\x3f\xa1\xf0\x9f"
+			  "\x84\x5e\x46\xed\x20\x89\xb6\x44"
+			  "\x8d\xd0\xed\x54\x47\x16\xbe\x95"
+			  "\x8a\xb3\x6b\x72\xc4\x32\x52\x13"
+			  "\x1b\xb0\x82\xbe\xac\xf9\x70\xa6"
+			  "\x44\x18\xdd\x8c\x6e\xca\x6e\x45"
+			  "\x8f\x1e\x10\x07\x57\x25\x98\x7b"
+			  "\x17\x8c\x78\xdd\x80\xa7\xd9\xd8"
+			  "\x63\xaf\xb9\x67\x57\xfd\xbc\xdb"
+			  "\x44\xe9\xc5\x65\xd1\xc7\x3b\xff"
+			  "\x20\xa0\x80\x1a\xc3\x9a\xad\x5e"
+			  "\x5d\x3b\xd3\x07\xd9\xf5\xfd\x3d"
+			  "\x4a\x8b\xa8\xd2\x6e\x7a\x51\x65"
+			  "\x6c\x8e\x95\xe0\x45\xc9\x5f\x4a"
+			  "\x09\x3c\x3d\x71\x7f\x0c\x84\x2a"
+			  "\xc8\x48\x52\x1a\xc2\xd5\xd6\x78"
+			  "\x92\x1e\xa0\x90\x2e\xea\xf0\xf3"
+			  "\xdc\x0f\xb1\xaf\x0d\x9b\x06\x2e"
+			  "\x35\x10\x30\x82\x0d\xe7\xc5\x9b"
+			  "\xde\x44\x18\xbd\x9f\xd1\x45\xa9"
+			  "\x7b\x7a\x4a\xad\x35\x65\x27\xca"
+			  "\xb2\xc3\xd4\x9b\x71\x86\x70\xee"
+			  "\xf1\x89\x3b\x85\x4b\x5b\xaa\xaf"
+			  "\xfc\x42\xc8\x31\x59\xbe\x16\x60"
+			  "\x4f\xf9\xfa\x12\xea\xd0\xa7\x14"
+			  "\xf0\x7a\xf3\xd5\x8d\xbd\x81\xef"
+			  "\x52\x7f\x29\x51\x94\x20\x67\x3c"
+			  "\xd1\xaf\x77\x9f\x22\x5a\x4e\x63"
+			  "\xe7\xff\x73\x25\xd1\xdd\x96\x8a"
+			  "\x98\x52\x6d\xf3\xac\x3e\xf2\x18"
+			  "\x6d\xf6\x0a\x29\xa6\x34\x3d\xed"
+			  "\xe3\x27\x0d\x9d\x0a\x02\x44\x7e"
+			  "\x5a\x7e\x67\x0f\x0a\x9e\xd6\xad"
+			  "\x91\xe6\x4d\x81\x8c\x5c\x59\xaa"
+			  "\xfb\xeb\x56\x53\xd2\x7d\x4c\x81"
+			  "\x65\x53\x0f\x41\x11\xbd\x98\x99"
+			  "\xf9\xc6\xfa\x51\x2e\xa3\xdd\x8d"
+			  "\x84\x98\xf9\x34\xed\x33\x2a\x1f"
+			  "\x82\xed\xc1\x73\x98\xd3\x02\xdc"
+			  "\xe6\xc2\x33\x1d\xa2\xb4\xca\x76"
+			  "\x63\x51\x34\x9d\x96\x12\xae\xce"
+			  "\x83\xc9\x76\x5e\xa4\x1b\x53\x37"
+			  "\x17\xd5\xc0\x80\x1d\x62\xf8\x3d"
+			  "\x54\x27\x74\xbb\x10\x86\x57\x46"
+			  "\x68\xe1\xed\x14\xe7\x9d\xfc\x84"
+			  "\x47\xbc\xc2\xf8\x19\x4b\x99\xcf"
+			  "\x7a\xe9\xc4\xb8\x8c\x82\x72\x4d"
+			  "\x7b\x4f\x38\x55\x36\x71\x64\xc1"
+			  "\xfc\x5c\x75\x52\x33\x02\x18\xf8"
+			  "\x17\xe1\x2b\xc2\x43\x39\xbd\x76"
+			  "\x9b\x63\x76\x32\x2f\x19\x72\x10"
+			  "\x9f\x21\x0c\xf1\x66\x50\x7f\xa5"
+			  "\x0d\x1f\x46\xe0\xba\xd3\x2f\x3c",
+		.ilen	= 512,
+		.result	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
+			  "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			  "\x10\x11\x12\x13\x14\x15\x16\x17"
+			  "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+			  "\x20\x21\x22\x23\x24\x25\x26\x27"
+			  "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+			  "\x30\x31\x32\x33\x34\x35\x36\x37"
+			  "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+			  "\x40\x41\x42\x43\x44\x45\x46\x47"
+			  "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+			  "\x50\x51\x52\x53\x54\x55\x56\x57"
+			  "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+			  "\x60\x61\x62\x63\x64\x65\x66\x67"
+			  "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+			  "\x70\x71\x72\x73\x74\x75\x76\x77"
+			  "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+			  "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+			  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7"
+			  "\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+			  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
+			  "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+			  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7"
+			  "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+			  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7"
+			  "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
+			  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7"
+			  "\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+			  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7"
+			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
+		.rlen	= 512,
+		.also_non_np = 1,
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
+	}
+};
+
 /* Cast6 test vectors from RFC 2612 */
 static const struct cipher_testvec cast6_enc_tv_template[] = {
 	{
diff --git a/crypto/xts.c b/crypto/xts.c
index f317c48b5e43..12284183bd20 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -357,78 +357,6 @@ static int decrypt(struct skcipher_request *req)
 	return do_decrypt(req, init_crypt(req, decrypt_done));
 }
 
-int xts_crypt(struct blkcipher_desc *desc, struct scatterlist *sdst,
-	      struct scatterlist *ssrc, unsigned int nbytes,
-	      struct xts_crypt_req *req)
-{
-	const unsigned int bsize = XTS_BLOCK_SIZE;
-	const unsigned int max_blks = req->tbuflen / bsize;
-	struct blkcipher_walk walk;
-	unsigned int nblocks;
-	le128 *src, *dst, *t;
-	le128 *t_buf = req->tbuf;
-	int err, i;
-
-	BUG_ON(max_blks < 1);
-
-	blkcipher_walk_init(&walk, sdst, ssrc, nbytes);
-
-	err = blkcipher_walk_virt(desc, &walk);
-	nbytes = walk.nbytes;
-	if (!nbytes)
-		return err;
-
-	nblocks = min(nbytes / bsize, max_blks);
-	src = (le128 *)walk.src.virt.addr;
-	dst = (le128 *)walk.dst.virt.addr;
-
-	/* calculate first value of T */
-	req->tweak_fn(req->tweak_ctx, (u8 *)&t_buf[0], walk.iv);
-
-	i = 0;
-	goto first;
-
-	for (;;) {
-		do {
-			for (i = 0; i < nblocks; i++) {
-				gf128mul_x_ble(&t_buf[i], t);
-first:
-				t = &t_buf[i];
-
-				/* PP <- T xor P */
-				le128_xor(dst + i, t, src + i);
-			}
-
-			/* CC <- E(Key2,PP) */
-			req->crypt_fn(req->crypt_ctx, (u8 *)dst,
-				      nblocks * bsize);
-
-			/* C <- T xor CC */
-			for (i = 0; i < nblocks; i++)
-				le128_xor(dst + i, dst + i, &t_buf[i]);
-
-			src += nblocks;
-			dst += nblocks;
-			nbytes -= nblocks * bsize;
-			nblocks = min(nbytes / bsize, max_blks);
-		} while (nblocks > 0);
-
-		*(le128 *)walk.iv = *t;
-
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-		nbytes = walk.nbytes;
-		if (!nbytes)
-			break;
-
-		nblocks = min(nbytes / bsize, max_blks);
-		src = (le128 *)walk.src.virt.addr;
-		dst = (le128 *)walk.dst.virt.addr;
-	}
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(xts_crypt);
-
 static int init_tfm(struct crypto_skcipher *tfm)
 {
 	struct skcipher_instance *inst = skcipher_alg_instance(tfm);
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index 4d0f571c15f9..d53541e96bee 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -452,3 +452,10 @@ config UML_RANDOM
 	  (check your distro, or download from
 	  http://sourceforge.net/projects/gkernel/).  rngd periodically reads
 	  /dev/hwrng and injects the entropy into /dev/random.
+
+config HW_RANDOM_KEYSTONE
+	depends on ARCH_KEYSTONE
+	default HW_RANDOM
+	tristate "TI Keystone NETCP SA Hardware random number generator"
+	help
+	  This option enables Keystone's hardware random generator.
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index b780370bd4eb..533e913c93d1 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -38,3 +38,4 @@ obj-$(CONFIG_HW_RANDOM_MESON) += meson-rng.o
 obj-$(CONFIG_HW_RANDOM_CAVIUM) += cavium-rng.o cavium-rng-vf.o
 obj-$(CONFIG_HW_RANDOM_MTK)	+= mtk-rng.o
 obj-$(CONFIG_HW_RANDOM_S390) += s390-trng.o
+obj-$(CONFIG_HW_RANDOM_KEYSTONE) += ks-sa-rng.o
diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c
index 7a84cec30c3a..6767d965c36c 100644
--- a/drivers/char/hw_random/bcm2835-rng.c
+++ b/drivers/char/hw_random/bcm2835-rng.c
@@ -163,6 +163,8 @@ static int bcm2835_rng_probe(struct platform_device *pdev)
 
 	/* Clock is optional on most platforms */
 	priv->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
 
 	priv->rng.name = pdev->name;
 	priv->rng.init = bcm2835_rng_init;
diff --git a/drivers/char/hw_random/cavium-rng-vf.c b/drivers/char/hw_random/cavium-rng-vf.c
index dd1007aecb10..2d1352b67168 100644
--- a/drivers/char/hw_random/cavium-rng-vf.c
+++ b/drivers/char/hw_random/cavium-rng-vf.c
@@ -77,7 +77,7 @@ static int cavium_rng_probe_vf(struct	pci_dev		*pdev,
 }
 
 /* Remove the VF */
-void  cavium_rng_remove_vf(struct pci_dev *pdev)
+static void  cavium_rng_remove_vf(struct pci_dev *pdev)
 {
 	struct cavium_rng *rng;
 
diff --git a/drivers/char/hw_random/cavium-rng.c b/drivers/char/hw_random/cavium-rng.c
index a944e0a47f42..63d6e68c24d2 100644
--- a/drivers/char/hw_random/cavium-rng.c
+++ b/drivers/char/hw_random/cavium-rng.c
@@ -62,7 +62,7 @@ static int cavium_rng_probe(struct pci_dev *pdev,
 }
 
 /* Disable VF and RNG Hardware */
-void  cavium_rng_remove(struct pci_dev *pdev)
+static void cavium_rng_remove(struct pci_dev *pdev)
 {
 	struct cavium_rng_pf *rng;
 
diff --git a/drivers/char/hw_random/imx-rngc.c b/drivers/char/hw_random/imx-rngc.c
index eca87249bcff..250123bc4905 100644
--- a/drivers/char/hw_random/imx-rngc.c
+++ b/drivers/char/hw_random/imx-rngc.c
@@ -300,7 +300,7 @@ static int __maybe_unused imx_rngc_resume(struct device *dev)
 	return 0;
 }
 
-SIMPLE_DEV_PM_OPS(imx_rngc_pm_ops, imx_rngc_suspend, imx_rngc_resume);
+static SIMPLE_DEV_PM_OPS(imx_rngc_pm_ops, imx_rngc_suspend, imx_rngc_resume);
 
 static const struct of_device_id imx_rngc_dt_ids[] = {
 	{ .compatible = "fsl,imx25-rngb", .data = NULL, },
diff --git a/drivers/char/hw_random/ks-sa-rng.c b/drivers/char/hw_random/ks-sa-rng.c
new file mode 100644
index 000000000000..62c6696c1dbd
--- /dev/null
+++ b/drivers/char/hw_random/ks-sa-rng.c
@@ -0,0 +1,257 @@
+/*
+ * Random Number Generator driver for the Keystone SOC
+ *
+ * Copyright (C) 2016 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Authors:	Sandeep Nair
+ *		Vitaly Andrianov
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/hw_random.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/pm_runtime.h>
+#include <linux/err.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/delay.h>
+
+#define SA_CMD_STATUS_OFS			0x8
+
+/* TRNG enable control in SA System module*/
+#define SA_CMD_STATUS_REG_TRNG_ENABLE		BIT(3)
+
+/* TRNG start control in TRNG module */
+#define TRNG_CNTL_REG_TRNG_ENABLE		BIT(10)
+
+/* Data ready indicator in STATUS register */
+#define TRNG_STATUS_REG_READY			BIT(0)
+
+/* Data ready clear control in INTACK register */
+#define TRNG_INTACK_REG_READY			BIT(0)
+
+/*
+ * Number of samples taken to gather entropy during startup.
+ * If value is 0, the number of samples is 2^24 else
+ * equals value times 2^8.
+ */
+#define TRNG_DEF_STARTUP_CYCLES			0
+#define TRNG_CNTL_REG_STARTUP_CYCLES_SHIFT	16
+
+/*
+ * Minimum number of samples taken to regenerate entropy
+ * If value is 0, the number of samples is 2^24 else
+ * equals value times 2^6.
+ */
+#define TRNG_DEF_MIN_REFILL_CYCLES		1
+#define TRNG_CFG_REG_MIN_REFILL_CYCLES_SHIFT	0
+
+/*
+ * Maximum number of samples taken to regenerate entropy
+ * If value is 0, the number of samples is 2^24 else
+ * equals value times 2^8.
+ */
+#define TRNG_DEF_MAX_REFILL_CYCLES		0
+#define TRNG_CFG_REG_MAX_REFILL_CYCLES_SHIFT	16
+
+/* Number of CLK input cycles between samples */
+#define TRNG_DEF_CLK_DIV_CYCLES			0
+#define TRNG_CFG_REG_SAMPLE_DIV_SHIFT		8
+
+/* Maximum retries to get rng data */
+#define SA_MAX_RNG_DATA_RETRIES			5
+/* Delay between retries (in usecs) */
+#define SA_RNG_DATA_RETRY_DELAY			5
+
+struct trng_regs {
+	u32	output_l;
+	u32	output_h;
+	u32	status;
+	u32	intmask;
+	u32	intack;
+	u32	control;
+	u32	config;
+};
+
+struct ks_sa_rng {
+	struct device	*dev;
+	struct hwrng	rng;
+	struct clk	*clk;
+	struct regmap	*regmap_cfg;
+	struct trng_regs *reg_rng;
+};
+
+static int ks_sa_rng_init(struct hwrng *rng)
+{
+	u32 value;
+	struct device *dev = (struct device *)rng->priv;
+	struct ks_sa_rng *ks_sa_rng = dev_get_drvdata(dev);
+
+	/* Enable RNG module */
+	regmap_write_bits(ks_sa_rng->regmap_cfg, SA_CMD_STATUS_OFS,
+			  SA_CMD_STATUS_REG_TRNG_ENABLE,
+			  SA_CMD_STATUS_REG_TRNG_ENABLE);
+
+	/* Configure RNG module */
+	writel(0, &ks_sa_rng->reg_rng->control);
+	value = TRNG_DEF_STARTUP_CYCLES << TRNG_CNTL_REG_STARTUP_CYCLES_SHIFT;
+	writel(value, &ks_sa_rng->reg_rng->control);
+
+	value =	(TRNG_DEF_MIN_REFILL_CYCLES <<
+		 TRNG_CFG_REG_MIN_REFILL_CYCLES_SHIFT) |
+		(TRNG_DEF_MAX_REFILL_CYCLES <<
+		 TRNG_CFG_REG_MAX_REFILL_CYCLES_SHIFT) |
+		(TRNG_DEF_CLK_DIV_CYCLES <<
+		 TRNG_CFG_REG_SAMPLE_DIV_SHIFT);
+
+	writel(value, &ks_sa_rng->reg_rng->config);
+
+	/* Disable all interrupts from TRNG */
+	writel(0, &ks_sa_rng->reg_rng->intmask);
+
+	/* Enable RNG */
+	value = readl(&ks_sa_rng->reg_rng->control);
+	value |= TRNG_CNTL_REG_TRNG_ENABLE;
+	writel(value, &ks_sa_rng->reg_rng->control);
+
+	return 0;
+}
+
+static void ks_sa_rng_cleanup(struct hwrng *rng)
+{
+	struct device *dev = (struct device *)rng->priv;
+	struct ks_sa_rng *ks_sa_rng = dev_get_drvdata(dev);
+
+	/* Disable RNG */
+	writel(0, &ks_sa_rng->reg_rng->control);
+	regmap_write_bits(ks_sa_rng->regmap_cfg, SA_CMD_STATUS_OFS,
+			  SA_CMD_STATUS_REG_TRNG_ENABLE, 0);
+}
+
+static int ks_sa_rng_data_read(struct hwrng *rng, u32 *data)
+{
+	struct device *dev = (struct device *)rng->priv;
+	struct ks_sa_rng *ks_sa_rng = dev_get_drvdata(dev);
+
+	/* Read random data */
+	data[0] = readl(&ks_sa_rng->reg_rng->output_l);
+	data[1] = readl(&ks_sa_rng->reg_rng->output_h);
+
+	writel(TRNG_INTACK_REG_READY, &ks_sa_rng->reg_rng->intack);
+
+	return sizeof(u32) * 2;
+}
+
+static int ks_sa_rng_data_present(struct hwrng *rng, int wait)
+{
+	struct device *dev = (struct device *)rng->priv;
+	struct ks_sa_rng *ks_sa_rng = dev_get_drvdata(dev);
+
+	u32	ready;
+	int	j;
+
+	for (j = 0; j < SA_MAX_RNG_DATA_RETRIES; j++) {
+		ready = readl(&ks_sa_rng->reg_rng->status);
+		ready &= TRNG_STATUS_REG_READY;
+
+		if (ready || !wait)
+			break;
+
+		udelay(SA_RNG_DATA_RETRY_DELAY);
+	}
+
+	return ready;
+}
+
+static int ks_sa_rng_probe(struct platform_device *pdev)
+{
+	struct ks_sa_rng	*ks_sa_rng;
+	struct device		*dev = &pdev->dev;
+	int			ret;
+	struct resource		*mem;
+
+	ks_sa_rng = devm_kzalloc(dev, sizeof(*ks_sa_rng), GFP_KERNEL);
+	if (!ks_sa_rng)
+		return -ENOMEM;
+
+	ks_sa_rng->dev = dev;
+	ks_sa_rng->rng = (struct hwrng) {
+		.name = "ks_sa_hwrng",
+		.init = ks_sa_rng_init,
+		.data_read = ks_sa_rng_data_read,
+		.data_present = ks_sa_rng_data_present,
+		.cleanup = ks_sa_rng_cleanup,
+	};
+	ks_sa_rng->rng.priv = (unsigned long)dev;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ks_sa_rng->reg_rng = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(ks_sa_rng->reg_rng))
+		return PTR_ERR(ks_sa_rng->reg_rng);
+
+	ks_sa_rng->regmap_cfg =
+		syscon_regmap_lookup_by_phandle(dev->of_node,
+						"ti,syscon-sa-cfg");
+
+	if (IS_ERR(ks_sa_rng->regmap_cfg)) {
+		dev_err(dev, "syscon_node_to_regmap failed\n");
+		return -EINVAL;
+	}
+
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "Failed to enable SA power-domain\n");
+		pm_runtime_disable(dev);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, ks_sa_rng);
+
+	return devm_hwrng_register(&pdev->dev, &ks_sa_rng->rng);
+}
+
+static int ks_sa_rng_remove(struct platform_device *pdev)
+{
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static const struct of_device_id ks_sa_rng_dt_match[] = {
+	{
+		.compatible = "ti,keystone-rng",
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ks_sa_rng_dt_match);
+
+static struct platform_driver ks_sa_rng_driver = {
+	.driver		= {
+		.name	= "ks-sa-rng",
+		.of_match_table = ks_sa_rng_dt_match,
+	},
+	.probe		= ks_sa_rng_probe,
+	.remove		= ks_sa_rng_remove,
+};
+
+module_platform_driver(ks_sa_rng_driver);
+
+MODULE_DESCRIPTION("Keystone NETCP SA H/W Random Number Generator driver");
+MODULE_AUTHOR("Vitaly Andrianov <vitalya@ti.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/char/hw_random/mxc-rnga.c b/drivers/char/hw_random/mxc-rnga.c
index 467362262651..f83bee513d91 100644
--- a/drivers/char/hw_random/mxc-rnga.c
+++ b/drivers/char/hw_random/mxc-rnga.c
@@ -16,16 +16,13 @@
  * This driver is based on other RNG drivers.
  */
 
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
 #include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/ioport.h>
-#include <linux/platform_device.h>
-#include <linux/hw_random.h>
 #include <linux/delay.h>
+#include <linux/hw_random.h>
 #include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 
 /* RNGA Registers */
 #define RNGA_CONTROL			0x00
@@ -197,10 +194,18 @@ static int __exit mxc_rnga_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id mxc_rnga_of_match[] = {
+	{ .compatible = "fsl,imx21-rnga", },
+	{ .compatible = "fsl,imx31-rnga", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, mxc_rnga_of_match);
+
 static struct platform_driver mxc_rnga_driver = {
 	.driver = {
-		   .name = "mxc_rnga",
-		   },
+		.name = "mxc_rnga",
+		.of_match_table = mxc_rnga_of_match,
+	},
 	.remove = __exit_p(mxc_rnga_remove),
 };
 
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 74d11ae6abe9..b65ff6962899 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -150,6 +150,7 @@ struct omap_rng_dev {
 	const struct omap_rng_pdata	*pdata;
 	struct hwrng rng;
 	struct clk 			*clk;
+	struct clk			*clk_reg;
 };
 
 static inline u32 omap_rng_read(struct omap_rng_dev *priv, u16 reg)
@@ -480,6 +481,19 @@ static int omap_rng_probe(struct platform_device *pdev)
 		}
 	}
 
+	priv->clk_reg = devm_clk_get(&pdev->dev, "reg");
+	if (IS_ERR(priv->clk_reg) && PTR_ERR(priv->clk_reg) == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+	if (!IS_ERR(priv->clk_reg)) {
+		ret = clk_prepare_enable(priv->clk_reg);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"Unable to enable the register clk: %d\n",
+				ret);
+			goto err_register;
+		}
+	}
+
 	ret = (dev->of_node) ? of_get_omap_rng_device_details(priv, pdev) :
 				get_omap_rng_device_details(priv);
 	if (ret)
@@ -499,8 +513,8 @@ err_register:
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
-	if (!IS_ERR(priv->clk))
-		clk_disable_unprepare(priv->clk);
+	clk_disable_unprepare(priv->clk_reg);
+	clk_disable_unprepare(priv->clk);
 err_ioremap:
 	dev_err(dev, "initialization failed.\n");
 	return ret;
@@ -517,8 +531,8 @@ static int omap_rng_remove(struct platform_device *pdev)
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
-	if (!IS_ERR(priv->clk))
-		clk_disable_unprepare(priv->clk);
+	clk_disable_unprepare(priv->clk);
+	clk_disable_unprepare(priv->clk_reg);
 
 	return 0;
 }
diff --git a/drivers/char/hw_random/stm32-rng.c b/drivers/char/hw_random/stm32-rng.c
index 63d84e6f1891..0d2328da3b76 100644
--- a/drivers/char/hw_random/stm32-rng.c
+++ b/drivers/char/hw_random/stm32-rng.c
@@ -16,15 +16,18 @@
 #include <linux/delay.h>
 #include <linux/hw_random.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/pm_runtime.h>
+#include <linux/reset.h>
 #include <linux/slab.h>
 
 #define RNG_CR 0x00
 #define RNG_CR_RNGEN BIT(2)
+#define RNG_CR_CED BIT(5)
 
 #define RNG_SR 0x04
 #define RNG_SR_SEIS BIT(6)
@@ -33,19 +36,12 @@
 
 #define RNG_DR 0x08
 
-/*
- * It takes 40 cycles @ 48MHz to generate each random number (e.g. <1us).
- * At the time of writing STM32 parts max out at ~200MHz meaning a timeout
- * of 500 leaves us a very comfortable margin for error. The loop to which
- * the timeout applies takes at least 4 instructions per iteration so the
- * timeout is enough to take us up to multi-GHz parts!
- */
-#define RNG_TIMEOUT 500
-
 struct stm32_rng_private {
 	struct hwrng rng;
 	void __iomem *base;
 	struct clk *clk;
+	struct reset_control *rst;
+	bool ced;
 };
 
 static int stm32_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
@@ -59,13 +55,16 @@ static int stm32_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
 
 	while (max > sizeof(u32)) {
 		sr = readl_relaxed(priv->base + RNG_SR);
+		/* Manage timeout which is based on timer and take */
+		/* care of initial delay time when enabling rng	*/
 		if (!sr && wait) {
-			unsigned int timeout = RNG_TIMEOUT;
-
-			do {
-				cpu_relax();
-				sr = readl_relaxed(priv->base + RNG_SR);
-			} while (!sr && --timeout);
+			retval = readl_relaxed_poll_timeout_atomic(priv->base
+								   + RNG_SR,
+								   sr, sr,
+								   10, 50000);
+			if (retval)
+				dev_err((struct device *)priv->rng.priv,
+					"%s: timeout %x!\n", __func__, sr);
 		}
 
 		/* If error detected or data not ready... */
@@ -99,7 +98,11 @@ static int stm32_rng_init(struct hwrng *rng)
 	if (err)
 		return err;
 
-	writel_relaxed(RNG_CR_RNGEN, priv->base + RNG_CR);
+	if (priv->ced)
+		writel_relaxed(RNG_CR_RNGEN, priv->base + RNG_CR);
+	else
+		writel_relaxed(RNG_CR_RNGEN | RNG_CR_CED,
+			       priv->base + RNG_CR);
 
 	/* clear error indicators */
 	writel_relaxed(0, priv->base + RNG_SR);
@@ -140,6 +143,15 @@ static int stm32_rng_probe(struct platform_device *ofdev)
 	if (IS_ERR(priv->clk))
 		return PTR_ERR(priv->clk);
 
+	priv->rst = devm_reset_control_get(&ofdev->dev, NULL);
+	if (!IS_ERR(priv->rst)) {
+		reset_control_assert(priv->rst);
+		udelay(2);
+		reset_control_deassert(priv->rst);
+	}
+
+	priv->ced = of_property_read_bool(np, "clock-error-detect");
+
 	dev_set_drvdata(dev, priv);
 
 	priv->rng.name = dev_driver_string(dev),
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 4b741b83e23f..d1ea1a07cecb 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -464,13 +464,6 @@ if CRYPTO_DEV_UX500
 	source "drivers/crypto/ux500/Kconfig"
 endif # if CRYPTO_DEV_UX500
 
-config CRYPTO_DEV_BFIN_CRC
-	tristate "Support for Blackfin CRC hardware"
-	depends on BF60x
-	help
-	  Newer Blackfin processors have CRC hardware. Select this if you
-	  want to use the Blackfin CRC module.
-
 config CRYPTO_DEV_ATMEL_AUTHENC
 	tristate "Support for Atmel IPSEC/SSL hw accelerator"
 	depends on HAS_DMA
@@ -730,4 +723,31 @@ config CRYPTO_DEV_ARTPEC6
 
 	  To compile this driver as a module, choose M here.
 
+config CRYPTO_DEV_CCREE
+	tristate "Support for ARM TrustZone CryptoCell family of security processors"
+	depends on CRYPTO && CRYPTO_HW && OF && HAS_DMA
+	default n
+	select CRYPTO_HASH
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_DES
+	select CRYPTO_AEAD
+	select CRYPTO_AUTHENC
+	select CRYPTO_SHA1
+	select CRYPTO_MD5
+	select CRYPTO_SHA256
+	select CRYPTO_SHA512
+	select CRYPTO_HMAC
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_ECB
+	select CRYPTO_CTR
+	select CRYPTO_XTS
+	help
+	  Say 'Y' to enable a driver for the REE interface of the Arm
+	  TrustZone CryptoCell family of processors. Currently the
+	  CryptoCell 712, 710 and 630 are supported.
+	  Choose this if you wish to use hardware acceleration of
+	  cryptographic operations on the system REE.
+	  If unsure say Y.
+
 endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 2513d13ea2c4..7ae87b4f6c8d 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -3,9 +3,9 @@ obj-$(CONFIG_CRYPTO_DEV_ATMEL_AES) += atmel-aes.o
 obj-$(CONFIG_CRYPTO_DEV_ATMEL_SHA) += atmel-sha.o
 obj-$(CONFIG_CRYPTO_DEV_ATMEL_TDES) += atmel-tdes.o
 obj-$(CONFIG_CRYPTO_DEV_ATMEL_ECC) += atmel-ecc.o
-obj-$(CONFIG_CRYPTO_DEV_BFIN_CRC) += bfin_crc.o
 obj-$(CONFIG_CRYPTO_DEV_CAVIUM_ZIP) += cavium/
 obj-$(CONFIG_CRYPTO_DEV_CCP) += ccp/
+obj-$(CONFIG_CRYPTO_DEV_CCREE) += ccree/
 obj-$(CONFIG_CRYPTO_DEV_CHELSIO) += chelsio/
 obj-$(CONFIG_CRYPTO_DEV_CPT) += cavium/cpt/
 obj-$(CONFIG_CRYPTO_DEV_NITROX) += cavium/nitrox/
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
index 691c6465b71e..801aeab5ab1e 100644
--- a/drivers/crypto/atmel-aes.c
+++ b/drivers/crypto/atmel-aes.c
@@ -2155,7 +2155,7 @@ static int atmel_aes_authenc_setkey(struct crypto_aead *tfm, const u8 *key,
 
 badkey:
 	crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-	memzero_explicit(&key, sizeof(keys));
+	memzero_explicit(&keys, sizeof(keys));
 	return -EINVAL;
 }
 
@@ -2602,16 +2602,13 @@ static struct crypto_platform_data *atmel_aes_of_init(struct platform_device *pd
 	}
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-	if (!pdata) {
-		dev_err(&pdev->dev, "could not allocate memory for pdata\n");
+	if (!pdata)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	pdata->dma_slave = devm_kzalloc(&pdev->dev,
 					sizeof(*(pdata->dma_slave)),
 					GFP_KERNEL);
 	if (!pdata->dma_slave) {
-		dev_err(&pdev->dev, "could not allocate memory for dma_slave\n");
 		devm_kfree(&pdev->dev, pdata);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -2649,7 +2646,6 @@ static int atmel_aes_probe(struct platform_device *pdev)
 
 	aes_dd = devm_kzalloc(&pdev->dev, sizeof(*aes_dd), GFP_KERNEL);
 	if (aes_dd == NULL) {
-		dev_err(dev, "unable to alloc data struct.\n");
 		err = -ENOMEM;
 		goto aes_dd_err;
 	}
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 8874aa5ca0f7..4d43081120db 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -2726,18 +2726,14 @@ static struct crypto_platform_data *atmel_sha_of_init(struct platform_device *pd
 	}
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-	if (!pdata) {
-		dev_err(&pdev->dev, "could not allocate memory for pdata\n");
+	if (!pdata)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	pdata->dma_slave = devm_kzalloc(&pdev->dev,
 					sizeof(*(pdata->dma_slave)),
 					GFP_KERNEL);
-	if (!pdata->dma_slave) {
-		dev_err(&pdev->dev, "could not allocate memory for dma_slave\n");
+	if (!pdata->dma_slave)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	return pdata;
 }
@@ -2758,7 +2754,6 @@ static int atmel_sha_probe(struct platform_device *pdev)
 
 	sha_dd = devm_kzalloc(&pdev->dev, sizeof(*sha_dd), GFP_KERNEL);
 	if (sha_dd == NULL) {
-		dev_err(dev, "unable to alloc data struct.\n");
 		err = -ENOMEM;
 		goto sha_dd_err;
 	}
diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c
index 592124f8382b..97b0423efa7f 100644
--- a/drivers/crypto/atmel-tdes.c
+++ b/drivers/crypto/atmel-tdes.c
@@ -1312,18 +1312,14 @@ static struct crypto_platform_data *atmel_tdes_of_init(struct platform_device *p
 	}
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-	if (!pdata) {
-		dev_err(&pdev->dev, "could not allocate memory for pdata\n");
+	if (!pdata)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	pdata->dma_slave = devm_kzalloc(&pdev->dev,
 					sizeof(*(pdata->dma_slave)),
 					GFP_KERNEL);
-	if (!pdata->dma_slave) {
-		dev_err(&pdev->dev, "could not allocate memory for dma_slave\n");
+	if (!pdata->dma_slave)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	return pdata;
 }
@@ -1344,7 +1340,6 @@ static int atmel_tdes_probe(struct platform_device *pdev)
 
 	tdes_dd = devm_kmalloc(&pdev->dev, sizeof(*tdes_dd), GFP_KERNEL);
 	if (tdes_dd == NULL) {
-		dev_err(dev, "unable to alloc data struct.\n");
 		err = -ENOMEM;
 		goto tdes_dd_err;
 	}
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 2b75f95bbe1b..309c67c7012f 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -818,7 +818,7 @@ static int handle_ahash_req(struct iproc_reqctx_s *rctx)
 
 	/* AES hashing keeps key size in type field, so need to copy it here */
 	if (hash_parms.alg == HASH_ALG_AES)
-		hash_parms.type = cipher_parms.type;
+		hash_parms.type = (enum hash_type)cipher_parms.type;
 	else
 		hash_parms.type = spu->spu_hash_type(rctx->total_sent);
 
@@ -1409,7 +1409,7 @@ static int handle_aead_req(struct iproc_reqctx_s *rctx)
 						rctx->iv_ctr_len);
 
 	if (ctx->auth.alg == HASH_ALG_AES)
-		hash_parms.type = ctx->cipher_type;
+		hash_parms.type = (enum hash_type)ctx->cipher_type;
 
 	/* General case AAD padding (CCM and RFC4543 special cases below) */
 	aead_parms.aad_pad_len = spu->spu_gcm_ccm_pad_len(ctx->cipher.mode,
diff --git a/drivers/crypto/bcm/util.c b/drivers/crypto/bcm/util.c
index d543c010ccd9..a912c6ad3e85 100644
--- a/drivers/crypto/bcm/util.c
+++ b/drivers/crypto/bcm/util.c
@@ -279,7 +279,6 @@ int do_shash(unsigned char *name, unsigned char *result,
 	sdesc = kmalloc(size, GFP_KERNEL);
 	if (!sdesc) {
 		rc = -ENOMEM;
-		pr_err("%s: Memory allocation failure\n", __func__);
 		goto do_shash_err;
 	}
 	sdesc->shash.tfm = hash;
diff --git a/drivers/crypto/bfin_crc.c b/drivers/crypto/bfin_crc.c
deleted file mode 100644
index bfbf8bf77f03..000000000000
--- a/drivers/crypto/bfin_crc.c
+++ /dev/null
@@ -1,743 +0,0 @@
-/*
- * Cryptographic API.
- *
- * Support Blackfin CRC HW acceleration.
- *
- * Copyright 2012 Analog Devices Inc.
- *
- * Licensed under the GPL-2.
- */
-
-#include <linux/err.h>
-#include <linux/device.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/irq.h>
-#include <linux/io.h>
-#include <linux/platform_device.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
-#include <linux/delay.h>
-#include <linux/crypto.h>
-#include <linux/cryptohash.h>
-#include <crypto/scatterwalk.h>
-#include <crypto/algapi.h>
-#include <crypto/hash.h>
-#include <crypto/internal/hash.h>
-#include <asm/unaligned.h>
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-#include <asm/io.h>
-
-#include "bfin_crc.h"
-
-#define CRC_CCRYPTO_QUEUE_LENGTH	5
-
-#define DRIVER_NAME "bfin-hmac-crc"
-#define CHKSUM_DIGEST_SIZE      4
-#define CHKSUM_BLOCK_SIZE       1
-
-#define CRC_MAX_DMA_DESC	100
-
-#define CRC_CRYPTO_STATE_UPDATE		1
-#define CRC_CRYPTO_STATE_FINALUPDATE	2
-#define CRC_CRYPTO_STATE_FINISH		3
-
-struct bfin_crypto_crc {
-	struct list_head	list;
-	struct device		*dev;
-	spinlock_t		lock;
-
-	int			irq;
-	int			dma_ch;
-	u32			poly;
-	struct crc_register	*regs;
-
-	struct ahash_request	*req; /* current request in operation */
-	struct dma_desc_array	*sg_cpu; /* virt addr of sg dma descriptors */
-	dma_addr_t		sg_dma; /* phy addr of sg dma descriptors */
-	u8			*sg_mid_buf;
-	dma_addr_t		sg_mid_dma; /* phy addr of sg mid buffer */
-
-	struct tasklet_struct	done_task;
-	struct crypto_queue	queue; /* waiting requests */
-
-	u8			busy:1; /* crc device in operation flag */
-};
-
-static struct bfin_crypto_crc_list {
-	struct list_head	dev_list;
-	spinlock_t		lock;
-} crc_list;
-
-struct bfin_crypto_crc_reqctx {
-	struct bfin_crypto_crc	*crc;
-
-	unsigned int		total;	/* total request bytes */
-	size_t			sg_buflen; /* bytes for this update */
-	unsigned int		sg_nents;
-	struct scatterlist	*sg; /* sg list head for this update*/
-	struct scatterlist	bufsl[2]; /* chained sg list */
-
-	size_t			bufnext_len;
-	size_t			buflast_len;
-	u8			bufnext[CHKSUM_DIGEST_SIZE]; /* extra bytes for next udpate */
-	u8			buflast[CHKSUM_DIGEST_SIZE]; /* extra bytes from last udpate */
-
-	u8			flag;
-};
-
-struct bfin_crypto_crc_ctx {
-	struct bfin_crypto_crc	*crc;
-	u32			key;
-};
-
-/*
- * get element in scatter list by given index
- */
-static struct scatterlist *sg_get(struct scatterlist *sg_list, unsigned int nents,
-				unsigned int index)
-{
-	struct scatterlist *sg = NULL;
-	int i;
-
-	for_each_sg(sg_list, sg, nents, i)
-		if (i == index)
-			break;
-
-	return sg;
-}
-
-static int bfin_crypto_crc_init_hw(struct bfin_crypto_crc *crc, u32 key)
-{
-	writel(0, &crc->regs->datacntrld);
-	writel(MODE_CALC_CRC << OPMODE_OFFSET, &crc->regs->control);
-	writel(key, &crc->regs->curresult);
-
-	/* setup CRC interrupts */
-	writel(CMPERRI | DCNTEXPI, &crc->regs->status);
-	writel(CMPERRI | DCNTEXPI, &crc->regs->intrenset);
-
-	return 0;
-}
-
-static int bfin_crypto_crc_init(struct ahash_request *req)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct bfin_crypto_crc_ctx *crc_ctx = crypto_ahash_ctx(tfm);
-	struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(req);
-	struct bfin_crypto_crc *crc;
-
-	dev_dbg(ctx->crc->dev, "crc_init\n");
-	spin_lock_bh(&crc_list.lock);
-	list_for_each_entry(crc, &crc_list.dev_list, list) {
-		crc_ctx->crc = crc;
-		break;
-	}
-	spin_unlock_bh(&crc_list.lock);
-
-	if (sg_nents(req->src) > CRC_MAX_DMA_DESC) {
-		dev_dbg(ctx->crc->dev, "init: requested sg list is too big > %d\n",
-			CRC_MAX_DMA_DESC);
-		return -EINVAL;
-	}
-
-	ctx->crc = crc;
-	ctx->bufnext_len = 0;
-	ctx->buflast_len = 0;
-	ctx->sg_buflen = 0;
-	ctx->total = 0;
-	ctx->flag = 0;
-
-	/* init crc results */
-	put_unaligned_le32(crc_ctx->key, req->result);
-
-	dev_dbg(ctx->crc->dev, "init: digest size: %d\n",
-		crypto_ahash_digestsize(tfm));
-
-	return bfin_crypto_crc_init_hw(crc, crc_ctx->key);
-}
-
-static void bfin_crypto_crc_config_dma(struct bfin_crypto_crc *crc)
-{
-	struct scatterlist *sg;
-	struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(crc->req);
-	int i = 0, j = 0;
-	unsigned long dma_config;
-	unsigned int dma_count;
-	unsigned int dma_addr;
-	unsigned int mid_dma_count = 0;
-	int dma_mod;
-
-	dma_map_sg(crc->dev, ctx->sg, ctx->sg_nents, DMA_TO_DEVICE);
-
-	for_each_sg(ctx->sg, sg, ctx->sg_nents, j) {
-		dma_addr = sg_dma_address(sg);
-		/* deduce extra bytes in last sg */
-		if (sg_is_last(sg))
-			dma_count = sg_dma_len(sg) - ctx->bufnext_len;
-		else
-			dma_count = sg_dma_len(sg);
-
-		if (mid_dma_count) {
-			/* Append last middle dma buffer to 4 bytes with first
-			   bytes in current sg buffer. Move addr of current
-			   sg and deduce the length of current sg.
-			 */
-			memcpy(crc->sg_mid_buf +(i << 2) + mid_dma_count,
-				sg_virt(sg),
-				CHKSUM_DIGEST_SIZE - mid_dma_count);
-			dma_addr += CHKSUM_DIGEST_SIZE - mid_dma_count;
-			dma_count -= CHKSUM_DIGEST_SIZE - mid_dma_count;
-
-			dma_config = DMAFLOW_ARRAY | RESTART | NDSIZE_3 |
-				DMAEN | PSIZE_32 | WDSIZE_32;
-
-			/* setup new dma descriptor for next middle dma */
-			crc->sg_cpu[i].start_addr = crc->sg_mid_dma + (i << 2);
-			crc->sg_cpu[i].cfg = dma_config;
-			crc->sg_cpu[i].x_count = 1;
-			crc->sg_cpu[i].x_modify = CHKSUM_DIGEST_SIZE;
-			dev_dbg(crc->dev, "%d: crc_dma: start_addr:0x%lx, "
-				"cfg:0x%x, x_count:0x%x, x_modify:0x%x\n",
-				i, crc->sg_cpu[i].start_addr,
-				crc->sg_cpu[i].cfg, crc->sg_cpu[i].x_count,
-				crc->sg_cpu[i].x_modify);
-			i++;
-		}
-
-		dma_config = DMAFLOW_ARRAY | RESTART | NDSIZE_3 | DMAEN | PSIZE_32;
-		/* chop current sg dma len to multiple of 32 bits */
-		mid_dma_count = dma_count % 4;
-		dma_count &= ~0x3;
-
-		if (dma_addr % 4 == 0) {
-			dma_config |= WDSIZE_32;
-			dma_count >>= 2;
-			dma_mod = 4;
-		} else if (dma_addr % 2 == 0) {
-			dma_config |= WDSIZE_16;
-			dma_count >>= 1;
-			dma_mod = 2;
-		} else {
-			dma_config |= WDSIZE_8;
-			dma_mod = 1;
-		}
-
-		crc->sg_cpu[i].start_addr = dma_addr;
-		crc->sg_cpu[i].cfg = dma_config;
-		crc->sg_cpu[i].x_count = dma_count;
-		crc->sg_cpu[i].x_modify = dma_mod;
-		dev_dbg(crc->dev, "%d: crc_dma: start_addr:0x%lx, "
-			"cfg:0x%x, x_count:0x%x, x_modify:0x%x\n",
-			i, crc->sg_cpu[i].start_addr,
-			crc->sg_cpu[i].cfg, crc->sg_cpu[i].x_count,
-			crc->sg_cpu[i].x_modify);
-		i++;
-
-		if (mid_dma_count) {
-			/* copy extra bytes to next middle dma buffer */
-			memcpy(crc->sg_mid_buf + (i << 2),
-				(u8*)sg_virt(sg) + (dma_count << 2),
-				mid_dma_count);
-		}
-	}
-
-	dma_config = DMAFLOW_ARRAY | RESTART | NDSIZE_3 | DMAEN | PSIZE_32 | WDSIZE_32;
-	/* For final update req, append the buffer for next update as well*/
-	if (ctx->bufnext_len && (ctx->flag == CRC_CRYPTO_STATE_FINALUPDATE ||
-		ctx->flag == CRC_CRYPTO_STATE_FINISH)) {
-		crc->sg_cpu[i].start_addr = dma_map_single(crc->dev, ctx->bufnext,
-						CHKSUM_DIGEST_SIZE, DMA_TO_DEVICE);
-		crc->sg_cpu[i].cfg = dma_config;
-		crc->sg_cpu[i].x_count = 1;
-		crc->sg_cpu[i].x_modify = CHKSUM_DIGEST_SIZE;
-		dev_dbg(crc->dev, "%d: crc_dma: start_addr:0x%lx, "
-			"cfg:0x%x, x_count:0x%x, x_modify:0x%x\n",
-			i, crc->sg_cpu[i].start_addr,
-			crc->sg_cpu[i].cfg, crc->sg_cpu[i].x_count,
-			crc->sg_cpu[i].x_modify);
-		i++;
-	}
-
-	if (i == 0)
-		return;
-
-	/* Set the last descriptor to stop mode */
-	crc->sg_cpu[i - 1].cfg &= ~(DMAFLOW | NDSIZE);
-	crc->sg_cpu[i - 1].cfg |= DI_EN;
-	set_dma_curr_desc_addr(crc->dma_ch, (unsigned long *)crc->sg_dma);
-	set_dma_x_count(crc->dma_ch, 0);
-	set_dma_x_modify(crc->dma_ch, 0);
-	set_dma_config(crc->dma_ch, dma_config);
-}
-
-static int bfin_crypto_crc_handle_queue(struct bfin_crypto_crc *crc,
-				  struct ahash_request *req)
-{
-	struct crypto_async_request *async_req, *backlog;
-	struct bfin_crypto_crc_reqctx *ctx;
-	struct scatterlist *sg;
-	int ret = 0;
-	int nsg, i, j;
-	unsigned int nextlen;
-	unsigned long flags;
-	u32 reg;
-
-	spin_lock_irqsave(&crc->lock, flags);
-	if (req)
-		ret = ahash_enqueue_request(&crc->queue, req);
-	if (crc->busy) {
-		spin_unlock_irqrestore(&crc->lock, flags);
-		return ret;
-	}
-	backlog = crypto_get_backlog(&crc->queue);
-	async_req = crypto_dequeue_request(&crc->queue);
-	if (async_req)
-		crc->busy = 1;
-	spin_unlock_irqrestore(&crc->lock, flags);
-
-	if (!async_req)
-		return ret;
-
-	if (backlog)
-		backlog->complete(backlog, -EINPROGRESS);
-
-	req = ahash_request_cast(async_req);
-	crc->req = req;
-	ctx = ahash_request_ctx(req);
-	ctx->sg = NULL;
-	ctx->sg_buflen = 0;
-	ctx->sg_nents = 0;
-
-	dev_dbg(crc->dev, "handling new req, flag=%u, nbytes: %d\n",
-						ctx->flag, req->nbytes);
-
-	if (ctx->flag == CRC_CRYPTO_STATE_FINISH) {
-		if (ctx->bufnext_len == 0) {
-			crc->busy = 0;
-			return 0;
-		}
-
-		/* Pack last crc update buffer to 32bit */
-		memset(ctx->bufnext + ctx->bufnext_len, 0,
-				CHKSUM_DIGEST_SIZE - ctx->bufnext_len);
-	} else {
-		/* Pack small data which is less than 32bit to buffer for next update. */
-		if (ctx->bufnext_len + req->nbytes < CHKSUM_DIGEST_SIZE) {
-			memcpy(ctx->bufnext + ctx->bufnext_len,
-				sg_virt(req->src), req->nbytes);
-			ctx->bufnext_len += req->nbytes;
-			if (ctx->flag == CRC_CRYPTO_STATE_FINALUPDATE &&
-				ctx->bufnext_len) {
-				goto finish_update;
-			} else {
-				crc->busy = 0;
-				return 0;
-			}
-		}
-
-		if (ctx->bufnext_len) {
-			/* Chain in extra bytes of last update */
-			ctx->buflast_len = ctx->bufnext_len;
-			memcpy(ctx->buflast, ctx->bufnext, ctx->buflast_len);
-
-			nsg = ctx->sg_buflen ? 2 : 1;
-			sg_init_table(ctx->bufsl, nsg);
-			sg_set_buf(ctx->bufsl, ctx->buflast, ctx->buflast_len);
-			if (nsg > 1)
-				sg_chain(ctx->bufsl, nsg, req->src);
-			ctx->sg = ctx->bufsl;
-		} else
-			ctx->sg = req->src;
-
-		/* Chop crc buffer size to multiple of 32 bit */
-		nsg = sg_nents(ctx->sg);
-		ctx->sg_nents = nsg;
-		ctx->sg_buflen = ctx->buflast_len + req->nbytes;
-		ctx->bufnext_len = ctx->sg_buflen % 4;
-		ctx->sg_buflen &= ~0x3;
-
-		if (ctx->bufnext_len) {
-			/* copy extra bytes to buffer for next update */
-			memset(ctx->bufnext, 0, CHKSUM_DIGEST_SIZE);
-			nextlen = ctx->bufnext_len;
-			for (i = nsg - 1; i >= 0; i--) {
-				sg = sg_get(ctx->sg, nsg, i);
-				j = min(nextlen, sg_dma_len(sg));
-				memcpy(ctx->bufnext + nextlen - j,
-					sg_virt(sg) + sg_dma_len(sg) - j, j);
-				if (j == sg_dma_len(sg))
-					ctx->sg_nents--;
-				nextlen -= j;
-				if (nextlen == 0)
-					break;
-			}
-		}
-	}
-
-finish_update:
-	if (ctx->bufnext_len && (ctx->flag == CRC_CRYPTO_STATE_FINALUPDATE ||
-		ctx->flag == CRC_CRYPTO_STATE_FINISH))
-		ctx->sg_buflen += CHKSUM_DIGEST_SIZE;
-
-	/* set CRC data count before start DMA */
-	writel(ctx->sg_buflen >> 2, &crc->regs->datacnt);
-
-	/* setup and enable CRC DMA */
-	bfin_crypto_crc_config_dma(crc);
-
-	/* finally kick off CRC operation */
-	reg = readl(&crc->regs->control);
-	writel(reg | BLKEN, &crc->regs->control);
-
-	return -EINPROGRESS;
-}
-
-static int bfin_crypto_crc_update(struct ahash_request *req)
-{
-	struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(req);
-
-	if (!req->nbytes)
-		return 0;
-
-	dev_dbg(ctx->crc->dev, "crc_update\n");
-	ctx->total += req->nbytes;
-	ctx->flag = CRC_CRYPTO_STATE_UPDATE;
-
-	return bfin_crypto_crc_handle_queue(ctx->crc, req);
-}
-
-static int bfin_crypto_crc_final(struct ahash_request *req)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct bfin_crypto_crc_ctx *crc_ctx = crypto_ahash_ctx(tfm);
-	struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(req);
-
-	dev_dbg(ctx->crc->dev, "crc_final\n");
-	ctx->flag = CRC_CRYPTO_STATE_FINISH;
-	crc_ctx->key = 0;
-
-	return bfin_crypto_crc_handle_queue(ctx->crc, req);
-}
-
-static int bfin_crypto_crc_finup(struct ahash_request *req)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct bfin_crypto_crc_ctx *crc_ctx = crypto_ahash_ctx(tfm);
-	struct bfin_crypto_crc_reqctx *ctx = ahash_request_ctx(req);
-
-	dev_dbg(ctx->crc->dev, "crc_finishupdate\n");
-	ctx->total += req->nbytes;
-	ctx->flag = CRC_CRYPTO_STATE_FINALUPDATE;
-	crc_ctx->key = 0;
-
-	return bfin_crypto_crc_handle_queue(ctx->crc, req);
-}
-
-static int bfin_crypto_crc_digest(struct ahash_request *req)
-{
-	int ret;
-
-	ret = bfin_crypto_crc_init(req);
-	if (ret)
-		return ret;
-
-	return bfin_crypto_crc_finup(req);
-}
-
-static int bfin_crypto_crc_setkey(struct crypto_ahash *tfm, const u8 *key,
-			unsigned int keylen)
-{
-	struct bfin_crypto_crc_ctx *crc_ctx = crypto_ahash_ctx(tfm);
-
-	dev_dbg(crc_ctx->crc->dev, "crc_setkey\n");
-	if (keylen != CHKSUM_DIGEST_SIZE) {
-		crypto_ahash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
-
-	crc_ctx->key = get_unaligned_le32(key);
-
-	return 0;
-}
-
-static int bfin_crypto_crc_cra_init(struct crypto_tfm *tfm)
-{
-	struct bfin_crypto_crc_ctx *crc_ctx = crypto_tfm_ctx(tfm);
-
-	crc_ctx->key = 0;
-	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-				 sizeof(struct bfin_crypto_crc_reqctx));
-
-	return 0;
-}
-
-static void bfin_crypto_crc_cra_exit(struct crypto_tfm *tfm)
-{
-}
-
-static struct ahash_alg algs = {
-	.init		= bfin_crypto_crc_init,
-	.update		= bfin_crypto_crc_update,
-	.final		= bfin_crypto_crc_final,
-	.finup		= bfin_crypto_crc_finup,
-	.digest		= bfin_crypto_crc_digest,
-	.setkey		= bfin_crypto_crc_setkey,
-	.halg.digestsize	= CHKSUM_DIGEST_SIZE,
-	.halg.base	= {
-		.cra_name		= "hmac(crc32)",
-		.cra_driver_name	= DRIVER_NAME,
-		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
-						CRYPTO_ALG_OPTIONAL_KEY,
-		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct bfin_crypto_crc_ctx),
-		.cra_alignmask		= 3,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= bfin_crypto_crc_cra_init,
-		.cra_exit		= bfin_crypto_crc_cra_exit,
-	}
-};
-
-static void bfin_crypto_crc_done_task(unsigned long data)
-{
-	struct bfin_crypto_crc *crc = (struct bfin_crypto_crc *)data;
-
-	bfin_crypto_crc_handle_queue(crc, NULL);
-}
-
-static irqreturn_t bfin_crypto_crc_handler(int irq, void *dev_id)
-{
-	struct bfin_crypto_crc *crc = dev_id;
-	u32 reg;
-
-	if (readl(&crc->regs->status) & DCNTEXP) {
-		writel(DCNTEXP, &crc->regs->status);
-
-		/* prepare results */
-		put_unaligned_le32(readl(&crc->regs->result),
-			crc->req->result);
-
-		reg = readl(&crc->regs->control);
-		writel(reg & ~BLKEN, &crc->regs->control);
-		crc->busy = 0;
-
-		if (crc->req->base.complete)
-			crc->req->base.complete(&crc->req->base, 0);
-
-		tasklet_schedule(&crc->done_task);
-
-		return IRQ_HANDLED;
-	} else
-		return IRQ_NONE;
-}
-
-#ifdef CONFIG_PM
-/**
- *	bfin_crypto_crc_suspend - suspend crc device
- *	@pdev: device being suspended
- *	@state: requested suspend state
- */
-static int bfin_crypto_crc_suspend(struct platform_device *pdev, pm_message_t state)
-{
-	struct bfin_crypto_crc *crc = platform_get_drvdata(pdev);
-	int i = 100000;
-
-	while ((readl(&crc->regs->control) & BLKEN) && --i)
-		cpu_relax();
-
-	if (i == 0)
-		return -EBUSY;
-
-	return 0;
-}
-#else
-# define bfin_crypto_crc_suspend NULL
-#endif
-
-#define bfin_crypto_crc_resume NULL
-
-/**
- *	bfin_crypto_crc_probe - Initialize module
- *
- */
-static int bfin_crypto_crc_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct resource *res;
-	struct bfin_crypto_crc *crc;
-	unsigned int timeout = 100000;
-	int ret;
-
-	crc = devm_kzalloc(dev, sizeof(*crc), GFP_KERNEL);
-	if (!crc) {
-		dev_err(&pdev->dev, "fail to malloc bfin_crypto_crc\n");
-		return -ENOMEM;
-	}
-
-	crc->dev = dev;
-
-	INIT_LIST_HEAD(&crc->list);
-	spin_lock_init(&crc->lock);
-	tasklet_init(&crc->done_task, bfin_crypto_crc_done_task, (unsigned long)crc);
-	crypto_init_queue(&crc->queue, CRC_CCRYPTO_QUEUE_LENGTH);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	crc->regs = devm_ioremap_resource(dev, res);
-	if (IS_ERR((void *)crc->regs)) {
-		dev_err(&pdev->dev, "Cannot map CRC IO\n");
-		return PTR_ERR((void *)crc->regs);
-	}
-
-	crc->irq = platform_get_irq(pdev, 0);
-	if (crc->irq < 0) {
-		dev_err(&pdev->dev, "No CRC DCNTEXP IRQ specified\n");
-		return -ENOENT;
-	}
-
-	ret = devm_request_irq(dev, crc->irq, bfin_crypto_crc_handler,
-			IRQF_SHARED, dev_name(dev), crc);
-	if (ret) {
-		dev_err(&pdev->dev, "Unable to request blackfin crc irq\n");
-		return ret;
-	}
-
-	res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (res == NULL) {
-		dev_err(&pdev->dev, "No CRC DMA channel specified\n");
-		return -ENOENT;
-	}
-	crc->dma_ch = res->start;
-
-	ret = request_dma(crc->dma_ch, dev_name(dev));
-	if (ret) {
-		dev_err(&pdev->dev, "Unable to attach Blackfin CRC DMA channel\n");
-		return ret;
-	}
-
-	crc->sg_cpu = dma_alloc_coherent(&pdev->dev, PAGE_SIZE, &crc->sg_dma, GFP_KERNEL);
-	if (crc->sg_cpu == NULL) {
-		ret = -ENOMEM;
-		goto out_error_dma;
-	}
-	/*
-	 * need at most CRC_MAX_DMA_DESC sg + CRC_MAX_DMA_DESC middle  +
-	 * 1 last + 1 next dma descriptors
-	 */
-	crc->sg_mid_buf = (u8 *)(crc->sg_cpu + ((CRC_MAX_DMA_DESC + 1) << 1));
-	crc->sg_mid_dma = crc->sg_dma + sizeof(struct dma_desc_array)
-			* ((CRC_MAX_DMA_DESC + 1) << 1);
-
-	writel(0, &crc->regs->control);
-	crc->poly = (u32)pdev->dev.platform_data;
-	writel(crc->poly, &crc->regs->poly);
-
-	while (!(readl(&crc->regs->status) & LUTDONE) && (--timeout) > 0)
-		cpu_relax();
-
-	if (timeout == 0)
-		dev_info(&pdev->dev, "init crc poly timeout\n");
-
-	platform_set_drvdata(pdev, crc);
-
-	spin_lock(&crc_list.lock);
-	list_add(&crc->list, &crc_list.dev_list);
-	spin_unlock(&crc_list.lock);
-
-	if (list_is_singular(&crc_list.dev_list)) {
-		ret = crypto_register_ahash(&algs);
-		if (ret) {
-			dev_err(&pdev->dev,
-				"Can't register crypto ahash device\n");
-			goto out_error_dma;
-		}
-	}
-
-	dev_info(&pdev->dev, "initialized\n");
-
-	return 0;
-
-out_error_dma:
-	if (crc->sg_cpu)
-		dma_free_coherent(&pdev->dev, PAGE_SIZE, crc->sg_cpu, crc->sg_dma);
-	free_dma(crc->dma_ch);
-
-	return ret;
-}
-
-/**
- *	bfin_crypto_crc_remove - Initialize module
- *
- */
-static int bfin_crypto_crc_remove(struct platform_device *pdev)
-{
-	struct bfin_crypto_crc *crc = platform_get_drvdata(pdev);
-
-	if (!crc)
-		return -ENODEV;
-
-	spin_lock(&crc_list.lock);
-	list_del(&crc->list);
-	spin_unlock(&crc_list.lock);
-
-	crypto_unregister_ahash(&algs);
-	tasklet_kill(&crc->done_task);
-	free_dma(crc->dma_ch);
-
-	return 0;
-}
-
-static struct platform_driver bfin_crypto_crc_driver = {
-	.probe     = bfin_crypto_crc_probe,
-	.remove    = bfin_crypto_crc_remove,
-	.suspend   = bfin_crypto_crc_suspend,
-	.resume    = bfin_crypto_crc_resume,
-	.driver    = {
-		.name  = DRIVER_NAME,
-	},
-};
-
-/**
- *	bfin_crypto_crc_mod_init - Initialize module
- *
- *	Checks the module params and registers the platform driver.
- *	Real work is in the platform probe function.
- */
-static int __init bfin_crypto_crc_mod_init(void)
-{
-	int ret;
-
-	pr_info("Blackfin hardware CRC crypto driver\n");
-
-	INIT_LIST_HEAD(&crc_list.dev_list);
-	spin_lock_init(&crc_list.lock);
-
-	ret = platform_driver_register(&bfin_crypto_crc_driver);
-	if (ret) {
-		pr_err("unable to register driver\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-/**
- *	bfin_crypto_crc_mod_exit - Deinitialize module
- */
-static void __exit bfin_crypto_crc_mod_exit(void)
-{
-	platform_driver_unregister(&bfin_crypto_crc_driver);
-}
-
-module_init(bfin_crypto_crc_mod_init);
-module_exit(bfin_crypto_crc_mod_exit);
-
-MODULE_AUTHOR("Sonic Zhang <sonic.zhang@analog.com>");
-MODULE_DESCRIPTION("Blackfin CRC hardware crypto driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/bfin_crc.h b/drivers/crypto/bfin_crc.h
deleted file mode 100644
index 786ef746d109..000000000000
--- a/drivers/crypto/bfin_crc.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/*
- * bfin_crc.h - interface to Blackfin CRC controllers
- *
- * Copyright 2012 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later.
- */
-
-#ifndef __BFIN_CRC_H__
-#define __BFIN_CRC_H__
-
-/* Function driver which use hardware crc must initialize the structure */
-struct crc_info {
-	/* Input data address */
-	unsigned char *in_addr;
-	/* Output data address */
-	unsigned char *out_addr;
-	/* Input or output bytes */
-	unsigned long datasize;
-	union {
-	/* CRC to compare with that of input buffer */
-	unsigned long crc_compare;
-	/* Value to compare with input data */
-	unsigned long val_verify;
-	/* Value to fill */
-	unsigned long val_fill;
-	};
-	/* Value to program the 32b CRC Polynomial */
-	unsigned long crc_poly;
-	union {
-	/* CRC calculated from the input data */
-	unsigned long crc_result;
-	/* First failed position to verify input data */
-	unsigned long pos_verify;
-	};
-	/* CRC mirror flags */
-	unsigned int bitmirr:1;
-	unsigned int bytmirr:1;
-	unsigned int w16swp:1;
-	unsigned int fdsel:1;
-	unsigned int rsltmirr:1;
-	unsigned int polymirr:1;
-	unsigned int cmpmirr:1;
-};
-
-/* Userspace interface */
-#define CRC_IOC_MAGIC		'C'
-#define CRC_IOC_CALC_CRC	_IOWR('C', 0x01, unsigned int)
-#define CRC_IOC_MEMCPY_CRC	_IOWR('C', 0x02, unsigned int)
-#define CRC_IOC_VERIFY_VAL	_IOWR('C', 0x03, unsigned int)
-#define CRC_IOC_FILL_VAL	_IOWR('C', 0x04, unsigned int)
-
-
-#ifdef __KERNEL__
-
-#include <linux/types.h>
-#include <linux/spinlock.h>
-
-struct crc_register {
-	u32 control;
-	u32 datacnt;
-	u32 datacntrld;
-	u32 __pad_1[2];
-	u32 compare;
-	u32 fillval;
-	u32 datafifo;
-	u32 intren;
-	u32 intrenset;
-	u32 intrenclr;
-	u32 poly;
-	u32 __pad_2[4];
-	u32 status;
-	u32 datacntcap;
-	u32 __pad_3;
-	u32 result;
-	u32 curresult;
-	u32 __pad_4[3];
-	u32 revid;
-};
-
-/* CRC_STATUS Masks */
-#define CMPERR			0x00000002	/* Compare error */
-#define DCNTEXP			0x00000010	/* datacnt register expired */
-#define IBR			0x00010000	/* Input buffer ready */
-#define OBR			0x00020000	/* Output buffer ready */
-#define IRR			0x00040000	/* Immediate result readt */
-#define LUTDONE			0x00080000	/* Look-up table generation done */
-#define FSTAT			0x00700000	/* FIFO status */
-#define MAX_FIFO		4		/* Max fifo size */
-
-/* CRC_CONTROL Masks */
-#define BLKEN			0x00000001	/* Block enable */
-#define OPMODE			0x000000F0	/* Operation mode */
-#define OPMODE_OFFSET		4		/* Operation mode mask offset*/
-#define MODE_DMACPY_CRC		1		/* MTM CRC compute and compare */
-#define MODE_DATA_FILL		2		/* MTM data fill */
-#define MODE_CALC_CRC		3		/* MSM CRC compute and compare */
-#define MODE_DATA_VERIFY	4		/* MSM data verify */
-#define AUTOCLRZ		0x00000100	/* Auto clear to zero */
-#define AUTOCLRF		0x00000200	/* Auto clear to one */
-#define OBRSTALL		0x00001000	/* Stall on output buffer ready */
-#define IRRSTALL		0x00002000	/* Stall on immediate result ready */
-#define BITMIRR			0x00010000	/* Mirror bits within each byte of 32-bit input data */
-#define BITMIRR_OFFSET		16		/* Mirror bits offset */
-#define BYTMIRR			0x00020000	/* Mirror bytes of 32-bit input data */
-#define BYTMIRR_OFFSET		17		/* Mirror bytes offset */
-#define W16SWP			0x00040000	/* Mirror uppper and lower 16-bit word of 32-bit input data */
-#define W16SWP_OFFSET		18		/* Mirror 16-bit word offset */
-#define FDSEL			0x00080000	/* FIFO is written after input data is mirrored */
-#define FDSEL_OFFSET		19		/* Mirror FIFO offset */
-#define RSLTMIRR		0x00100000	/* CRC result registers are mirrored. */
-#define RSLTMIRR_OFFSET		20		/* Mirror CRC result offset. */
-#define POLYMIRR		0x00200000	/* CRC poly register is mirrored. */
-#define POLYMIRR_OFFSET		21		/* Mirror CRC poly offset. */
-#define CMPMIRR			0x00400000	/* CRC compare register is mirrored. */
-#define CMPMIRR_OFFSET		22		/* Mirror CRC compare offset. */
-
-/* CRC_INTREN Masks */
-#define CMPERRI 		0x02		/* CRC_ERROR_INTR */
-#define DCNTEXPI 		0x10		/* CRC_STATUS_INTR */
-
-#endif
-
-#endif
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 2188235be02d..7207a535942d 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -328,6 +328,7 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 {
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
+	unsigned int ivsize = crypto_aead_ivsize(aead);
 	u32 *desc;
 	int rem_bytes = CAAM_DESC_BYTES_MAX - GCM_DESC_JOB_IO_LEN -
 			ctx->cdata.keylen;
@@ -349,7 +350,7 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	}
 
 	desc = ctx->sh_desc_enc;
-	cnstr_shdsc_gcm_encap(desc, &ctx->cdata, ctx->authsize);
+	cnstr_shdsc_gcm_encap(desc, &ctx->cdata, ivsize, ctx->authsize, false);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
 				   desc_bytes(desc), ctx->dir);
 
@@ -366,7 +367,7 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	}
 
 	desc = ctx->sh_desc_dec;
-	cnstr_shdsc_gcm_decap(desc, &ctx->cdata, ctx->authsize);
+	cnstr_shdsc_gcm_decap(desc, &ctx->cdata, ivsize, ctx->authsize, false);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
 				   desc_bytes(desc), ctx->dir);
 
@@ -387,6 +388,7 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 {
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
+	unsigned int ivsize = crypto_aead_ivsize(aead);
 	u32 *desc;
 	int rem_bytes = CAAM_DESC_BYTES_MAX - GCM_DESC_JOB_IO_LEN -
 			ctx->cdata.keylen;
@@ -408,7 +410,8 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	}
 
 	desc = ctx->sh_desc_enc;
-	cnstr_shdsc_rfc4106_encap(desc, &ctx->cdata, ctx->authsize);
+	cnstr_shdsc_rfc4106_encap(desc, &ctx->cdata, ivsize, ctx->authsize,
+				  false);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
 				   desc_bytes(desc), ctx->dir);
 
@@ -425,7 +428,8 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	}
 
 	desc = ctx->sh_desc_dec;
-	cnstr_shdsc_rfc4106_decap(desc, &ctx->cdata, ctx->authsize);
+	cnstr_shdsc_rfc4106_decap(desc, &ctx->cdata, ivsize, ctx->authsize,
+				  false);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
 				   desc_bytes(desc), ctx->dir);
 
@@ -447,6 +451,7 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 {
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
+	unsigned int ivsize = crypto_aead_ivsize(aead);
 	u32 *desc;
 	int rem_bytes = CAAM_DESC_BYTES_MAX - GCM_DESC_JOB_IO_LEN -
 			ctx->cdata.keylen;
@@ -468,7 +473,8 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	}
 
 	desc = ctx->sh_desc_enc;
-	cnstr_shdsc_rfc4543_encap(desc, &ctx->cdata, ctx->authsize);
+	cnstr_shdsc_rfc4543_encap(desc, &ctx->cdata, ivsize, ctx->authsize,
+				  false);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_enc_dma,
 				   desc_bytes(desc), ctx->dir);
 
@@ -485,7 +491,8 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	}
 
 	desc = ctx->sh_desc_dec;
-	cnstr_shdsc_rfc4543_decap(desc, &ctx->cdata, ctx->authsize);
+	cnstr_shdsc_rfc4543_decap(desc, &ctx->cdata, ivsize, ctx->authsize,
+				  false);
 	dma_sync_single_for_device(jrdev, ctx->sh_desc_dec_dma,
 				   desc_bytes(desc), ctx->dir);
 
@@ -563,9 +570,11 @@ static int aead_setkey(struct crypto_aead *aead,
 
 skip_split_key:
 	ctx->cdata.keylen = keys.enckeylen;
+	memzero_explicit(&keys, sizeof(keys));
 	return aead_set_sh_desc(aead);
 badkey:
 	crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	memzero_explicit(&keys, sizeof(keys));
 	return -EINVAL;
 }
 
diff --git a/drivers/crypto/caam/caamalg_desc.c b/drivers/crypto/caam/caamalg_desc.c
index ceb93fbb76e6..8ae7a1be7dfd 100644
--- a/drivers/crypto/caam/caamalg_desc.c
+++ b/drivers/crypto/caam/caamalg_desc.c
@@ -625,10 +625,13 @@ EXPORT_SYMBOL(cnstr_shdsc_aead_givencap);
  * @desc: pointer to buffer used for descriptor construction
  * @cdata: pointer to block cipher transform definitions
  *         Valid algorithm values - OP_ALG_ALGSEL_AES ANDed with OP_ALG_AAI_GCM.
+ * @ivsize: initialization vector size
  * @icvsize: integrity check value (ICV) size (truncated or full)
+ * @is_qi: true when called from caam/qi
  */
 void cnstr_shdsc_gcm_encap(u32 * const desc, struct alginfo *cdata,
-			   unsigned int icvsize)
+			   unsigned int ivsize, unsigned int icvsize,
+			   const bool is_qi)
 {
 	u32 *key_jump_cmd, *zero_payload_jump_cmd, *zero_assoc_jump_cmd1,
 	    *zero_assoc_jump_cmd2;
@@ -650,11 +653,35 @@ void cnstr_shdsc_gcm_encap(u32 * const desc, struct alginfo *cdata,
 	append_operation(desc, cdata->algtype | OP_ALG_AS_INITFINAL |
 			 OP_ALG_ENCRYPT);
 
+	if (is_qi) {
+		u32 *wait_load_cmd;
+
+		/* REG3 = assoclen */
+		append_seq_load(desc, 4, LDST_CLASS_DECO |
+				LDST_SRCDST_WORD_DECO_MATH3 |
+				(4 << LDST_OFFSET_SHIFT));
+
+		wait_load_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
+					    JUMP_COND_CALM | JUMP_COND_NCP |
+					    JUMP_COND_NOP | JUMP_COND_NIP |
+					    JUMP_COND_NIFP);
+		set_jump_tgt_here(desc, wait_load_cmd);
+
+		append_math_sub_imm_u32(desc, VARSEQOUTLEN, SEQINLEN, IMM,
+					ivsize);
+	} else {
+		append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG0,
+				CAAM_CMD_SZ);
+	}
+
 	/* if assoclen + cryptlen is ZERO, skip to ICV write */
-	append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 	zero_assoc_jump_cmd2 = append_jump(desc, JUMP_TEST_ALL |
 						 JUMP_COND_MATH_Z);
 
+	if (is_qi)
+		append_seq_fifo_load(desc, ivsize, FIFOLD_CLASS_CLASS1 |
+				     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+
 	/* if assoclen is ZERO, skip reading the assoc data */
 	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
 	zero_assoc_jump_cmd1 = append_jump(desc, JUMP_TEST_ALL |
@@ -686,8 +713,11 @@ void cnstr_shdsc_gcm_encap(u32 * const desc, struct alginfo *cdata,
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_MSG | FIFOLD_TYPE_LAST1);
 
-	/* jump the zero-payload commands */
-	append_jump(desc, JUMP_TEST_ALL | 2);
+	/* jump to ICV writing */
+	if (is_qi)
+		append_jump(desc, JUMP_TEST_ALL | 4);
+	else
+		append_jump(desc, JUMP_TEST_ALL | 2);
 
 	/* zero-payload commands */
 	set_jump_tgt_here(desc, zero_payload_jump_cmd);
@@ -695,10 +725,18 @@ void cnstr_shdsc_gcm_encap(u32 * const desc, struct alginfo *cdata,
 	/* read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_LAST1);
+	if (is_qi)
+		/* jump to ICV writing */
+		append_jump(desc, JUMP_TEST_ALL | 2);
 
 	/* There is no input data */
 	set_jump_tgt_here(desc, zero_assoc_jump_cmd2);
 
+	if (is_qi)
+		append_seq_fifo_load(desc, ivsize, FIFOLD_CLASS_CLASS1 |
+				     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 |
+				     FIFOLD_TYPE_LAST1);
+
 	/* write ICV */
 	append_seq_store(desc, icvsize, LDST_CLASS_1_CCB |
 			 LDST_SRCDST_BYTE_CONTEXT);
@@ -715,10 +753,13 @@ EXPORT_SYMBOL(cnstr_shdsc_gcm_encap);
  * @desc: pointer to buffer used for descriptor construction
  * @cdata: pointer to block cipher transform definitions
  *         Valid algorithm values - OP_ALG_ALGSEL_AES ANDed with OP_ALG_AAI_GCM.
+ * @ivsize: initialization vector size
  * @icvsize: integrity check value (ICV) size (truncated or full)
+ * @is_qi: true when called from caam/qi
  */
 void cnstr_shdsc_gcm_decap(u32 * const desc, struct alginfo *cdata,
-			   unsigned int icvsize)
+			   unsigned int ivsize, unsigned int icvsize,
+			   const bool is_qi)
 {
 	u32 *key_jump_cmd, *zero_payload_jump_cmd, *zero_assoc_jump_cmd1;
 
@@ -739,6 +780,24 @@ void cnstr_shdsc_gcm_decap(u32 * const desc, struct alginfo *cdata,
 	append_operation(desc, cdata->algtype | OP_ALG_AS_INITFINAL |
 			 OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
+	if (is_qi) {
+		u32 *wait_load_cmd;
+
+		/* REG3 = assoclen */
+		append_seq_load(desc, 4, LDST_CLASS_DECO |
+				LDST_SRCDST_WORD_DECO_MATH3 |
+				(4 << LDST_OFFSET_SHIFT));
+
+		wait_load_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
+					    JUMP_COND_CALM | JUMP_COND_NCP |
+					    JUMP_COND_NOP | JUMP_COND_NIP |
+					    JUMP_COND_NIFP);
+		set_jump_tgt_here(desc, wait_load_cmd);
+
+		append_seq_fifo_load(desc, ivsize, FIFOLD_CLASS_CLASS1 |
+				     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	}
+
 	/* if assoclen is ZERO, skip reading the assoc data */
 	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
 	zero_assoc_jump_cmd1 = append_jump(desc, JUMP_TEST_ALL |
@@ -791,10 +850,13 @@ EXPORT_SYMBOL(cnstr_shdsc_gcm_decap);
  * @desc: pointer to buffer used for descriptor construction
  * @cdata: pointer to block cipher transform definitions
  *         Valid algorithm values - OP_ALG_ALGSEL_AES ANDed with OP_ALG_AAI_GCM.
+ * @ivsize: initialization vector size
  * @icvsize: integrity check value (ICV) size (truncated or full)
+ * @is_qi: true when called from caam/qi
  */
 void cnstr_shdsc_rfc4106_encap(u32 * const desc, struct alginfo *cdata,
-			       unsigned int icvsize)
+			       unsigned int ivsize, unsigned int icvsize,
+			       const bool is_qi)
 {
 	u32 *key_jump_cmd;
 
@@ -815,7 +877,29 @@ void cnstr_shdsc_rfc4106_encap(u32 * const desc, struct alginfo *cdata,
 	append_operation(desc, cdata->algtype | OP_ALG_AS_INITFINAL |
 			 OP_ALG_ENCRYPT);
 
-	append_math_sub_imm_u32(desc, VARSEQINLEN, REG3, IMM, 8);
+	if (is_qi) {
+		u32 *wait_load_cmd;
+
+		/* REG3 = assoclen */
+		append_seq_load(desc, 4, LDST_CLASS_DECO |
+				LDST_SRCDST_WORD_DECO_MATH3 |
+				(4 << LDST_OFFSET_SHIFT));
+
+		wait_load_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
+					    JUMP_COND_CALM | JUMP_COND_NCP |
+					    JUMP_COND_NOP | JUMP_COND_NIP |
+					    JUMP_COND_NIFP);
+		set_jump_tgt_here(desc, wait_load_cmd);
+
+		/* Read salt and IV */
+		append_fifo_load_as_imm(desc, (void *)(cdata->key_virt +
+					cdata->keylen), 4, FIFOLD_CLASS_CLASS1 |
+					FIFOLD_TYPE_IV);
+		append_seq_fifo_load(desc, ivsize, FIFOLD_CLASS_CLASS1 |
+				     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	}
+
+	append_math_sub_imm_u32(desc, VARSEQINLEN, REG3, IMM, ivsize);
 	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
 	/* Read assoc data */
@@ -823,7 +907,7 @@ void cnstr_shdsc_rfc4106_encap(u32 * const desc, struct alginfo *cdata,
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
 
 	/* Skip IV */
-	append_seq_fifo_load(desc, 8, FIFOLD_CLASS_SKIP);
+	append_seq_fifo_load(desc, ivsize, FIFOLD_CLASS_SKIP);
 
 	/* Will read cryptlen bytes */
 	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
@@ -862,10 +946,13 @@ EXPORT_SYMBOL(cnstr_shdsc_rfc4106_encap);
  * @desc: pointer to buffer used for descriptor construction
  * @cdata: pointer to block cipher transform definitions
  *         Valid algorithm values - OP_ALG_ALGSEL_AES ANDed with OP_ALG_AAI_GCM.
+ * @ivsize: initialization vector size
  * @icvsize: integrity check value (ICV) size (truncated or full)
+ * @is_qi: true when called from caam/qi
  */
 void cnstr_shdsc_rfc4106_decap(u32 * const desc, struct alginfo *cdata,
-			       unsigned int icvsize)
+			       unsigned int ivsize, unsigned int icvsize,
+			       const bool is_qi)
 {
 	u32 *key_jump_cmd;
 
@@ -887,7 +974,29 @@ void cnstr_shdsc_rfc4106_decap(u32 * const desc, struct alginfo *cdata,
 	append_operation(desc, cdata->algtype | OP_ALG_AS_INITFINAL |
 			 OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
-	append_math_sub_imm_u32(desc, VARSEQINLEN, REG3, IMM, 8);
+	if (is_qi) {
+		u32 *wait_load_cmd;
+
+		/* REG3 = assoclen */
+		append_seq_load(desc, 4, LDST_CLASS_DECO |
+				LDST_SRCDST_WORD_DECO_MATH3 |
+				(4 << LDST_OFFSET_SHIFT));
+
+		wait_load_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
+					    JUMP_COND_CALM | JUMP_COND_NCP |
+					    JUMP_COND_NOP | JUMP_COND_NIP |
+					    JUMP_COND_NIFP);
+		set_jump_tgt_here(desc, wait_load_cmd);
+
+		/* Read salt and IV */
+		append_fifo_load_as_imm(desc, (void *)(cdata->key_virt +
+					cdata->keylen), 4, FIFOLD_CLASS_CLASS1 |
+					FIFOLD_TYPE_IV);
+		append_seq_fifo_load(desc, ivsize, FIFOLD_CLASS_CLASS1 |
+				     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	}
+
+	append_math_sub_imm_u32(desc, VARSEQINLEN, REG3, IMM, ivsize);
 	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
 	/* Read assoc data */
@@ -895,7 +1004,7 @@ void cnstr_shdsc_rfc4106_decap(u32 * const desc, struct alginfo *cdata,
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
 
 	/* Skip IV */
-	append_seq_fifo_load(desc, 8, FIFOLD_CLASS_SKIP);
+	append_seq_fifo_load(desc, ivsize, FIFOLD_CLASS_SKIP);
 
 	/* Will read cryptlen bytes */
 	append_math_sub(desc, VARSEQINLEN, SEQOUTLEN, REG3, CAAM_CMD_SZ);
@@ -934,10 +1043,13 @@ EXPORT_SYMBOL(cnstr_shdsc_rfc4106_decap);
  * @desc: pointer to buffer used for descriptor construction
  * @cdata: pointer to block cipher transform definitions
  *         Valid algorithm values - OP_ALG_ALGSEL_AES ANDed with OP_ALG_AAI_GCM.
+ * @ivsize: initialization vector size
  * @icvsize: integrity check value (ICV) size (truncated or full)
+ * @is_qi: true when called from caam/qi
  */
 void cnstr_shdsc_rfc4543_encap(u32 * const desc, struct alginfo *cdata,
-			       unsigned int icvsize)
+			       unsigned int ivsize, unsigned int icvsize,
+			       const bool is_qi)
 {
 	u32 *key_jump_cmd, *read_move_cmd, *write_move_cmd;
 
@@ -958,6 +1070,18 @@ void cnstr_shdsc_rfc4543_encap(u32 * const desc, struct alginfo *cdata,
 	append_operation(desc, cdata->algtype | OP_ALG_AS_INITFINAL |
 			 OP_ALG_ENCRYPT);
 
+	if (is_qi) {
+		/* assoclen is not needed, skip it */
+		append_seq_fifo_load(desc, 4, FIFOLD_CLASS_SKIP);
+
+		/* Read salt and IV */
+		append_fifo_load_as_imm(desc, (void *)(cdata->key_virt +
+					cdata->keylen), 4, FIFOLD_CLASS_CLASS1 |
+					FIFOLD_TYPE_IV);
+		append_seq_fifo_load(desc, ivsize, FIFOLD_CLASS_CLASS1 |
+				     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	}
+
 	/* assoclen + cryptlen = seqinlen */
 	append_math_sub(desc, REG3, SEQINLEN, REG0, CAAM_CMD_SZ);
 
@@ -1004,10 +1128,13 @@ EXPORT_SYMBOL(cnstr_shdsc_rfc4543_encap);
  * @desc: pointer to buffer used for descriptor construction
  * @cdata: pointer to block cipher transform definitions
  *         Valid algorithm values - OP_ALG_ALGSEL_AES ANDed with OP_ALG_AAI_GCM.
+ * @ivsize: initialization vector size
  * @icvsize: integrity check value (ICV) size (truncated or full)
+ * @is_qi: true when called from caam/qi
  */
 void cnstr_shdsc_rfc4543_decap(u32 * const desc, struct alginfo *cdata,
-			       unsigned int icvsize)
+			       unsigned int ivsize, unsigned int icvsize,
+			       const bool is_qi)
 {
 	u32 *key_jump_cmd, *read_move_cmd, *write_move_cmd;
 
@@ -1028,6 +1155,18 @@ void cnstr_shdsc_rfc4543_decap(u32 * const desc, struct alginfo *cdata,
 	append_operation(desc, cdata->algtype | OP_ALG_AS_INITFINAL |
 			 OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
+	if (is_qi) {
+		/* assoclen is not needed, skip it */
+		append_seq_fifo_load(desc, 4, FIFOLD_CLASS_SKIP);
+
+		/* Read salt and IV */
+		append_fifo_load_as_imm(desc, (void *)(cdata->key_virt +
+					cdata->keylen), 4, FIFOLD_CLASS_CLASS1 |
+					FIFOLD_TYPE_IV);
+		append_seq_fifo_load(desc, ivsize, FIFOLD_CLASS_CLASS1 |
+				     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	}
+
 	/* assoclen + cryptlen = seqoutlen */
 	append_math_sub(desc, REG3, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
diff --git a/drivers/crypto/caam/caamalg_desc.h b/drivers/crypto/caam/caamalg_desc.h
index 5f9445ae2114..a917af5776ce 100644
--- a/drivers/crypto/caam/caamalg_desc.h
+++ b/drivers/crypto/caam/caamalg_desc.h
@@ -27,14 +27,20 @@
 #define DESC_GCM_BASE			(3 * CAAM_CMD_SZ)
 #define DESC_GCM_ENC_LEN		(DESC_GCM_BASE + 16 * CAAM_CMD_SZ)
 #define DESC_GCM_DEC_LEN		(DESC_GCM_BASE + 12 * CAAM_CMD_SZ)
+#define DESC_QI_GCM_ENC_LEN		(DESC_GCM_ENC_LEN + 6 * CAAM_CMD_SZ)
+#define DESC_QI_GCM_DEC_LEN		(DESC_GCM_DEC_LEN + 3 * CAAM_CMD_SZ)
 
 #define DESC_RFC4106_BASE		(3 * CAAM_CMD_SZ)
 #define DESC_RFC4106_ENC_LEN		(DESC_RFC4106_BASE + 13 * CAAM_CMD_SZ)
 #define DESC_RFC4106_DEC_LEN		(DESC_RFC4106_BASE + 13 * CAAM_CMD_SZ)
+#define DESC_QI_RFC4106_ENC_LEN		(DESC_RFC4106_ENC_LEN + 5 * CAAM_CMD_SZ)
+#define DESC_QI_RFC4106_DEC_LEN		(DESC_RFC4106_DEC_LEN + 5 * CAAM_CMD_SZ)
 
 #define DESC_RFC4543_BASE		(3 * CAAM_CMD_SZ)
 #define DESC_RFC4543_ENC_LEN		(DESC_RFC4543_BASE + 11 * CAAM_CMD_SZ)
 #define DESC_RFC4543_DEC_LEN		(DESC_RFC4543_BASE + 12 * CAAM_CMD_SZ)
+#define DESC_QI_RFC4543_ENC_LEN		(DESC_RFC4543_ENC_LEN + 4 * CAAM_CMD_SZ)
+#define DESC_QI_RFC4543_DEC_LEN		(DESC_RFC4543_DEC_LEN + 4 * CAAM_CMD_SZ)
 
 #define DESC_ABLKCIPHER_BASE		(3 * CAAM_CMD_SZ)
 #define DESC_ABLKCIPHER_ENC_LEN		(DESC_ABLKCIPHER_BASE + \
@@ -67,22 +73,28 @@ void cnstr_shdsc_aead_givencap(u32 * const desc, struct alginfo *cdata,
 			       const bool is_qi, int era);
 
 void cnstr_shdsc_gcm_encap(u32 * const desc, struct alginfo *cdata,
-			   unsigned int icvsize);
+			   unsigned int ivsize, unsigned int icvsize,
+			   const bool is_qi);
 
 void cnstr_shdsc_gcm_decap(u32 * const desc, struct alginfo *cdata,
-			   unsigned int icvsize);
+			   unsigned int ivsize, unsigned int icvsize,
+			   const bool is_qi);
 
 void cnstr_shdsc_rfc4106_encap(u32 * const desc, struct alginfo *cdata,
-			       unsigned int icvsize);
+			       unsigned int ivsize, unsigned int icvsize,
+			       const bool is_qi);
 
 void cnstr_shdsc_rfc4106_decap(u32 * const desc, struct alginfo *cdata,
-			       unsigned int icvsize);
+			       unsigned int ivsize, unsigned int icvsize,
+			       const bool is_qi);
 
 void cnstr_shdsc_rfc4543_encap(u32 * const desc, struct alginfo *cdata,
-			       unsigned int icvsize);
+			       unsigned int ivsize, unsigned int icvsize,
+			       const bool is_qi);
 
 void cnstr_shdsc_rfc4543_decap(u32 * const desc, struct alginfo *cdata,
-			       unsigned int icvsize);
+			       unsigned int ivsize, unsigned int icvsize,
+			       const bool is_qi);
 
 void cnstr_shdsc_ablkcipher_encap(u32 * const desc, struct alginfo *cdata,
 				  unsigned int ivsize, const bool is_rfc3686,
diff --git a/drivers/crypto/caam/caamalg_qi.c b/drivers/crypto/caam/caamalg_qi.c
index 4aecc9435f69..cacda0831390 100644
--- a/drivers/crypto/caam/caamalg_qi.c
+++ b/drivers/crypto/caam/caamalg_qi.c
@@ -278,12 +278,317 @@ skip_split_key:
 		}
 	}
 
+	memzero_explicit(&keys, sizeof(keys));
 	return ret;
 badkey:
 	crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	memzero_explicit(&keys, sizeof(keys));
 	return -EINVAL;
 }
 
+static int gcm_set_sh_desc(struct crypto_aead *aead)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int ivsize = crypto_aead_ivsize(aead);
+	int rem_bytes = CAAM_DESC_BYTES_MAX - DESC_JOB_IO_LEN -
+			ctx->cdata.keylen;
+
+	if (!ctx->cdata.keylen || !ctx->authsize)
+		return 0;
+
+	/*
+	 * Job Descriptor and Shared Descriptor
+	 * must fit into the 64-word Descriptor h/w Buffer
+	 */
+	if (rem_bytes >= DESC_QI_GCM_ENC_LEN) {
+		ctx->cdata.key_inline = true;
+		ctx->cdata.key_virt = ctx->key;
+	} else {
+		ctx->cdata.key_inline = false;
+		ctx->cdata.key_dma = ctx->key_dma;
+	}
+
+	cnstr_shdsc_gcm_encap(ctx->sh_desc_enc, &ctx->cdata, ivsize,
+			      ctx->authsize, true);
+
+	/*
+	 * Job Descriptor and Shared Descriptor
+	 * must fit into the 64-word Descriptor h/w Buffer
+	 */
+	if (rem_bytes >= DESC_QI_GCM_DEC_LEN) {
+		ctx->cdata.key_inline = true;
+		ctx->cdata.key_virt = ctx->key;
+	} else {
+		ctx->cdata.key_inline = false;
+		ctx->cdata.key_dma = ctx->key_dma;
+	}
+
+	cnstr_shdsc_gcm_decap(ctx->sh_desc_dec, &ctx->cdata, ivsize,
+			      ctx->authsize, true);
+
+	return 0;
+}
+
+static int gcm_setauthsize(struct crypto_aead *authenc, unsigned int authsize)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(authenc);
+
+	ctx->authsize = authsize;
+	gcm_set_sh_desc(authenc);
+
+	return 0;
+}
+
+static int gcm_setkey(struct crypto_aead *aead,
+		      const u8 *key, unsigned int keylen)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct device *jrdev = ctx->jrdev;
+	int ret;
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "key in @" __stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
+#endif
+
+	memcpy(ctx->key, key, keylen);
+	dma_sync_single_for_device(jrdev, ctx->key_dma, keylen, ctx->dir);
+	ctx->cdata.keylen = keylen;
+
+	ret = gcm_set_sh_desc(aead);
+	if (ret)
+		return ret;
+
+	/* Now update the driver contexts with the new shared descriptor */
+	if (ctx->drv_ctx[ENCRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[ENCRYPT],
+					  ctx->sh_desc_enc);
+		if (ret) {
+			dev_err(jrdev, "driver enc context update failed\n");
+			return ret;
+		}
+	}
+
+	if (ctx->drv_ctx[DECRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[DECRYPT],
+					  ctx->sh_desc_dec);
+		if (ret) {
+			dev_err(jrdev, "driver dec context update failed\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int rfc4106_set_sh_desc(struct crypto_aead *aead)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int ivsize = crypto_aead_ivsize(aead);
+	int rem_bytes = CAAM_DESC_BYTES_MAX - DESC_JOB_IO_LEN -
+			ctx->cdata.keylen;
+
+	if (!ctx->cdata.keylen || !ctx->authsize)
+		return 0;
+
+	ctx->cdata.key_virt = ctx->key;
+
+	/*
+	 * Job Descriptor and Shared Descriptor
+	 * must fit into the 64-word Descriptor h/w Buffer
+	 */
+	if (rem_bytes >= DESC_QI_RFC4106_ENC_LEN) {
+		ctx->cdata.key_inline = true;
+	} else {
+		ctx->cdata.key_inline = false;
+		ctx->cdata.key_dma = ctx->key_dma;
+	}
+
+	cnstr_shdsc_rfc4106_encap(ctx->sh_desc_enc, &ctx->cdata, ivsize,
+				  ctx->authsize, true);
+
+	/*
+	 * Job Descriptor and Shared Descriptor
+	 * must fit into the 64-word Descriptor h/w Buffer
+	 */
+	if (rem_bytes >= DESC_QI_RFC4106_DEC_LEN) {
+		ctx->cdata.key_inline = true;
+	} else {
+		ctx->cdata.key_inline = false;
+		ctx->cdata.key_dma = ctx->key_dma;
+	}
+
+	cnstr_shdsc_rfc4106_decap(ctx->sh_desc_dec, &ctx->cdata, ivsize,
+				  ctx->authsize, true);
+
+	return 0;
+}
+
+static int rfc4106_setauthsize(struct crypto_aead *authenc,
+			       unsigned int authsize)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(authenc);
+
+	ctx->authsize = authsize;
+	rfc4106_set_sh_desc(authenc);
+
+	return 0;
+}
+
+static int rfc4106_setkey(struct crypto_aead *aead,
+			  const u8 *key, unsigned int keylen)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct device *jrdev = ctx->jrdev;
+	int ret;
+
+	if (keylen < 4)
+		return -EINVAL;
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "key in @" __stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
+#endif
+
+	memcpy(ctx->key, key, keylen);
+	/*
+	 * The last four bytes of the key material are used as the salt value
+	 * in the nonce. Update the AES key length.
+	 */
+	ctx->cdata.keylen = keylen - 4;
+	dma_sync_single_for_device(jrdev, ctx->key_dma, ctx->cdata.keylen,
+				   ctx->dir);
+
+	ret = rfc4106_set_sh_desc(aead);
+	if (ret)
+		return ret;
+
+	/* Now update the driver contexts with the new shared descriptor */
+	if (ctx->drv_ctx[ENCRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[ENCRYPT],
+					  ctx->sh_desc_enc);
+		if (ret) {
+			dev_err(jrdev, "driver enc context update failed\n");
+			return ret;
+		}
+	}
+
+	if (ctx->drv_ctx[DECRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[DECRYPT],
+					  ctx->sh_desc_dec);
+		if (ret) {
+			dev_err(jrdev, "driver dec context update failed\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int rfc4543_set_sh_desc(struct crypto_aead *aead)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int ivsize = crypto_aead_ivsize(aead);
+	int rem_bytes = CAAM_DESC_BYTES_MAX - DESC_JOB_IO_LEN -
+			ctx->cdata.keylen;
+
+	if (!ctx->cdata.keylen || !ctx->authsize)
+		return 0;
+
+	ctx->cdata.key_virt = ctx->key;
+
+	/*
+	 * Job Descriptor and Shared Descriptor
+	 * must fit into the 64-word Descriptor h/w Buffer
+	 */
+	if (rem_bytes >= DESC_QI_RFC4543_ENC_LEN) {
+		ctx->cdata.key_inline = true;
+	} else {
+		ctx->cdata.key_inline = false;
+		ctx->cdata.key_dma = ctx->key_dma;
+	}
+
+	cnstr_shdsc_rfc4543_encap(ctx->sh_desc_enc, &ctx->cdata, ivsize,
+				  ctx->authsize, true);
+
+	/*
+	 * Job Descriptor and Shared Descriptor
+	 * must fit into the 64-word Descriptor h/w Buffer
+	 */
+	if (rem_bytes >= DESC_QI_RFC4543_DEC_LEN) {
+		ctx->cdata.key_inline = true;
+	} else {
+		ctx->cdata.key_inline = false;
+		ctx->cdata.key_dma = ctx->key_dma;
+	}
+
+	cnstr_shdsc_rfc4543_decap(ctx->sh_desc_dec, &ctx->cdata, ivsize,
+				  ctx->authsize, true);
+
+	return 0;
+}
+
+static int rfc4543_setauthsize(struct crypto_aead *authenc,
+			       unsigned int authsize)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(authenc);
+
+	ctx->authsize = authsize;
+	rfc4543_set_sh_desc(authenc);
+
+	return 0;
+}
+
+static int rfc4543_setkey(struct crypto_aead *aead,
+			  const u8 *key, unsigned int keylen)
+{
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct device *jrdev = ctx->jrdev;
+	int ret;
+
+	if (keylen < 4)
+		return -EINVAL;
+
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "key in @" __stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
+#endif
+
+	memcpy(ctx->key, key, keylen);
+	/*
+	 * The last four bytes of the key material are used as the salt value
+	 * in the nonce. Update the AES key length.
+	 */
+	ctx->cdata.keylen = keylen - 4;
+	dma_sync_single_for_device(jrdev, ctx->key_dma, ctx->cdata.keylen,
+				   ctx->dir);
+
+	ret = rfc4543_set_sh_desc(aead);
+	if (ret)
+		return ret;
+
+	/* Now update the driver contexts with the new shared descriptor */
+	if (ctx->drv_ctx[ENCRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[ENCRYPT],
+					  ctx->sh_desc_enc);
+		if (ret) {
+			dev_err(jrdev, "driver enc context update failed\n");
+			return ret;
+		}
+	}
+
+	if (ctx->drv_ctx[DECRYPT]) {
+		ret = caam_drv_ctx_update(ctx->drv_ctx[DECRYPT],
+					  ctx->sh_desc_dec);
+		if (ret) {
+			dev_err(jrdev, "driver dec context update failed\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 			     const u8 *key, unsigned int keylen)
 {
@@ -562,8 +867,18 @@ static void aead_done(struct caam_drv_req *drv_req, u32 status)
 	qidev = caam_ctx->qidev;
 
 	if (unlikely(status)) {
+		u32 ssrc = status & JRSTA_SSRC_MASK;
+		u8 err_id = status & JRSTA_CCBERR_ERRID_MASK;
+
 		caam_jr_strstatus(qidev, status);
-		ecode = -EIO;
+		/*
+		 * verify hw auth check passed else return -EBADMSG
+		 */
+		if (ssrc == JRSTA_SSRC_CCB_ERROR &&
+		    err_id == JRSTA_CCBERR_ERRID_ICVCHK)
+			ecode = -EBADMSG;
+		else
+			ecode = -EIO;
 	}
 
 	edesc = container_of(drv_req, typeof(*edesc), drv_req);
@@ -807,6 +1122,22 @@ static int aead_decrypt(struct aead_request *req)
 	return aead_crypt(req, false);
 }
 
+static int ipsec_gcm_encrypt(struct aead_request *req)
+{
+	if (req->assoclen < 8)
+		return -EINVAL;
+
+	return aead_crypt(req, true);
+}
+
+static int ipsec_gcm_decrypt(struct aead_request *req)
+{
+	if (req->assoclen < 8)
+		return -EINVAL;
+
+	return aead_crypt(req, false);
+}
+
 static void ablkcipher_done(struct caam_drv_req *drv_req, u32 status)
 {
 	struct ablkcipher_edesc *edesc;
@@ -1327,6 +1658,61 @@ static struct caam_alg_template driver_algs[] = {
 };
 
 static struct caam_aead_alg driver_aeads[] = {
+	{
+		.aead = {
+			.base = {
+				.cra_name = "rfc4106(gcm(aes))",
+				.cra_driver_name = "rfc4106-gcm-aes-caam-qi",
+				.cra_blocksize = 1,
+			},
+			.setkey = rfc4106_setkey,
+			.setauthsize = rfc4106_setauthsize,
+			.encrypt = ipsec_gcm_encrypt,
+			.decrypt = ipsec_gcm_decrypt,
+			.ivsize = 8,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "rfc4543(gcm(aes))",
+				.cra_driver_name = "rfc4543-gcm-aes-caam-qi",
+				.cra_blocksize = 1,
+			},
+			.setkey = rfc4543_setkey,
+			.setauthsize = rfc4543_setauthsize,
+			.encrypt = ipsec_gcm_encrypt,
+			.decrypt = ipsec_gcm_decrypt,
+			.ivsize = 8,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
+	/* Galois Counter Mode */
+	{
+		.aead = {
+			.base = {
+				.cra_name = "gcm(aes)",
+				.cra_driver_name = "gcm-aes-caam-qi",
+				.cra_blocksize = 1,
+			},
+			.setkey = gcm_setkey,
+			.setauthsize = gcm_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.ivsize = 12,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		}
+	},
 	/* single-pass ipsec_esp descriptor */
 	{
 		.aead = {
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index e843cf410373..e4cc636e1104 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -337,7 +337,8 @@ static int caam_remove(struct platform_device *pdev)
 
 	/* shut clocks off before finalizing shutdown */
 	clk_disable_unprepare(ctrlpriv->caam_ipg);
-	clk_disable_unprepare(ctrlpriv->caam_mem);
+	if (ctrlpriv->caam_mem)
+		clk_disable_unprepare(ctrlpriv->caam_mem);
 	clk_disable_unprepare(ctrlpriv->caam_aclk);
 	if (ctrlpriv->caam_emi_slow)
 		clk_disable_unprepare(ctrlpriv->caam_emi_slow);
@@ -466,14 +467,17 @@ static int caam_probe(struct platform_device *pdev)
 	}
 	ctrlpriv->caam_ipg = clk;
 
-	clk = caam_drv_identify_clk(&pdev->dev, "mem");
-	if (IS_ERR(clk)) {
-		ret = PTR_ERR(clk);
-		dev_err(&pdev->dev,
-			"can't identify CAAM mem clk: %d\n", ret);
-		return ret;
+	if (!of_machine_is_compatible("fsl,imx7d") &&
+	    !of_machine_is_compatible("fsl,imx7s")) {
+		clk = caam_drv_identify_clk(&pdev->dev, "mem");
+		if (IS_ERR(clk)) {
+			ret = PTR_ERR(clk);
+			dev_err(&pdev->dev,
+				"can't identify CAAM mem clk: %d\n", ret);
+			return ret;
+		}
+		ctrlpriv->caam_mem = clk;
 	}
-	ctrlpriv->caam_mem = clk;
 
 	clk = caam_drv_identify_clk(&pdev->dev, "aclk");
 	if (IS_ERR(clk)) {
@@ -484,7 +488,9 @@ static int caam_probe(struct platform_device *pdev)
 	}
 	ctrlpriv->caam_aclk = clk;
 
-	if (!of_machine_is_compatible("fsl,imx6ul")) {
+	if (!of_machine_is_compatible("fsl,imx6ul") &&
+	    !of_machine_is_compatible("fsl,imx7d") &&
+	    !of_machine_is_compatible("fsl,imx7s")) {
 		clk = caam_drv_identify_clk(&pdev->dev, "emi_slow");
 		if (IS_ERR(clk)) {
 			ret = PTR_ERR(clk);
@@ -501,11 +507,13 @@ static int caam_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = clk_prepare_enable(ctrlpriv->caam_mem);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "can't enable CAAM secure mem clock: %d\n",
-			ret);
-		goto disable_caam_ipg;
+	if (ctrlpriv->caam_mem) {
+		ret = clk_prepare_enable(ctrlpriv->caam_mem);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "can't enable CAAM secure mem clock: %d\n",
+				ret);
+			goto disable_caam_ipg;
+		}
 	}
 
 	ret = clk_prepare_enable(ctrlpriv->caam_aclk);
@@ -815,9 +823,6 @@ static int caam_probe(struct platform_device *pdev)
 	return 0;
 
 caam_remove:
-#ifdef CONFIG_DEBUG_FS
-	debugfs_remove_recursive(ctrlpriv->dfs_root);
-#endif
 	caam_remove(pdev);
 	return ret;
 
@@ -829,7 +834,8 @@ disable_caam_emi_slow:
 disable_caam_aclk:
 	clk_disable_unprepare(ctrlpriv->caam_aclk);
 disable_caam_mem:
-	clk_disable_unprepare(ctrlpriv->caam_mem);
+	if (ctrlpriv->caam_mem)
+		clk_disable_unprepare(ctrlpriv->caam_mem);
 disable_caam_ipg:
 	clk_disable_unprepare(ctrlpriv->caam_ipg);
 	return ret;
diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c
index f9a44f485aac..b9480828da38 100644
--- a/drivers/crypto/caam/qi.c
+++ b/drivers/crypto/caam/qi.c
@@ -579,8 +579,15 @@ static enum qman_cb_dqrr_result caam_rsp_fq_dqrr_cb(struct qman_portal *p,
 
 	fd = &dqrr->fd;
 	status = be32_to_cpu(fd->status);
-	if (unlikely(status))
-		dev_err(qidev, "Error: %#x in CAAM response FD\n", status);
+	if (unlikely(status)) {
+		u32 ssrc = status & JRSTA_SSRC_MASK;
+		u8 err_id = status & JRSTA_CCBERR_ERRID_MASK;
+
+		if (ssrc != JRSTA_SSRC_CCB_ERROR ||
+		    err_id != JRSTA_CCBERR_ERRID_ICVCHK)
+			dev_err(qidev, "Error: %#x in CAAM response FD\n",
+				status);
+	}
 
 	if (unlikely(qm_fd_get_format(fd) != qm_fd_compound)) {
 		dev_err(qidev, "Non-compound FD from CAAM\n");
diff --git a/drivers/crypto/cavium/cpt/cptpf_main.c b/drivers/crypto/cavium/cpt/cptpf_main.c
index 34a6d8bf229e..06ad85ab5e86 100644
--- a/drivers/crypto/cavium/cpt/cptpf_main.c
+++ b/drivers/crypto/cavium/cpt/cptpf_main.c
@@ -436,7 +436,7 @@ static int cpt_device_init(struct cpt_device *cpt)
 
 	/* Reset the PF when probed first */
 	cpt_reset(cpt);
-	mdelay(100);
+	msleep(100);
 
 	/*Check BIST status*/
 	bist = (u64)cpt_check_bist_status(cpt);
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
index 60fc0fa26fd3..26687f318de6 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
@@ -46,7 +46,7 @@ static int ccp_aes_cmac_complete(struct crypto_async_request *async_req,
 	}
 
 	/* Update result area if supplied */
-	if (req->result)
+	if (req->result && rctx->final)
 		memcpy(req->result, rctx->iv, digest_size);
 
 e_free:
diff --git a/drivers/crypto/ccp/ccp-crypto-rsa.c b/drivers/crypto/ccp/ccp-crypto-rsa.c
index e6db8672d89c..05850dfd7940 100644
--- a/drivers/crypto/ccp/ccp-crypto-rsa.c
+++ b/drivers/crypto/ccp/ccp-crypto-rsa.c
@@ -60,10 +60,9 @@ static int ccp_rsa_complete(struct crypto_async_request *async_req, int ret)
 
 static unsigned int ccp_rsa_maxsize(struct crypto_akcipher *tfm)
 {
-	if (ccp_version() > CCP_VERSION(3, 0))
-		return CCP5_RSA_MAXMOD;
-	else
-		return CCP_RSA_MAXMOD;
+	struct ccp_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+	return ctx->u.rsa.n_len;
 }
 
 static int ccp_rsa_crypt(struct akcipher_request *req, bool encrypt)
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index 8b9b16d433f7..871c9628a2ee 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -47,7 +47,7 @@ static int ccp_sha_complete(struct crypto_async_request *async_req, int ret)
 	}
 
 	/* Update result area if supplied */
-	if (req->result)
+	if (req->result && rctx->final)
 		memcpy(req->result, rctx->ctx, digest_size);
 
 e_free:
diff --git a/drivers/crypto/ccp/ccp-debugfs.c b/drivers/crypto/ccp/ccp-debugfs.c
index 59d4ca4e72d8..1a734bd2070a 100644
--- a/drivers/crypto/ccp/ccp-debugfs.c
+++ b/drivers/crypto/ccp/ccp-debugfs.c
@@ -278,7 +278,7 @@ static const struct file_operations ccp_debugfs_stats_ops = {
 };
 
 static struct dentry *ccp_debugfs_dir;
-static DEFINE_RWLOCK(ccp_debugfs_lock);
+static DEFINE_MUTEX(ccp_debugfs_lock);
 
 #define	MAX_NAME_LEN	20
 
@@ -290,16 +290,15 @@ void ccp5_debugfs_setup(struct ccp_device *ccp)
 	struct dentry *debugfs_stats;
 	struct dentry *debugfs_q_instance;
 	struct dentry *debugfs_q_stats;
-	unsigned long flags;
 	int i;
 
 	if (!debugfs_initialized())
 		return;
 
-	write_lock_irqsave(&ccp_debugfs_lock, flags);
+	mutex_lock(&ccp_debugfs_lock);
 	if (!ccp_debugfs_dir)
 		ccp_debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
-	write_unlock_irqrestore(&ccp_debugfs_lock, flags);
+	mutex_unlock(&ccp_debugfs_lock);
 	if (!ccp_debugfs_dir)
 		return;
 
diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c
index 8b9da58459df..67155cb21636 100644
--- a/drivers/crypto/ccp/ccp-dmaengine.c
+++ b/drivers/crypto/ccp/ccp-dmaengine.c
@@ -38,7 +38,7 @@ static unsigned int dma_chan_attr = CCP_DMA_DFLT;
 module_param(dma_chan_attr, uint, 0444);
 MODULE_PARM_DESC(dma_chan_attr, "Set DMA channel visibility: 0 (default) = device defaults, 1 = make private, 2 = make public");
 
-unsigned int ccp_get_dma_chan_attr(struct ccp_device *ccp)
+static unsigned int ccp_get_dma_chan_attr(struct ccp_device *ccp)
 {
 	switch (dma_chan_attr) {
 	case CCP_DMA_DFLT:
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index 406b95329b3d..0ea43cdeb05f 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -178,14 +178,18 @@ static int ccp_init_dm_workarea(struct ccp_dm_workarea *wa,
 	return 0;
 }
 
-static void ccp_set_dm_area(struct ccp_dm_workarea *wa, unsigned int wa_offset,
-			    struct scatterlist *sg, unsigned int sg_offset,
-			    unsigned int len)
+static int ccp_set_dm_area(struct ccp_dm_workarea *wa, unsigned int wa_offset,
+			   struct scatterlist *sg, unsigned int sg_offset,
+			   unsigned int len)
 {
 	WARN_ON(!wa->address);
 
+	if (len > (wa->length - wa_offset))
+		return -EINVAL;
+
 	scatterwalk_map_and_copy(wa->address + wa_offset, sg, sg_offset, len,
 				 0);
+	return 0;
 }
 
 static void ccp_get_dm_area(struct ccp_dm_workarea *wa, unsigned int wa_offset,
@@ -205,8 +209,11 @@ static int ccp_reverse_set_dm_area(struct ccp_dm_workarea *wa,
 				   unsigned int len)
 {
 	u8 *p, *q;
+	int	rc;
 
-	ccp_set_dm_area(wa, wa_offset, sg, sg_offset, len);
+	rc = ccp_set_dm_area(wa, wa_offset, sg, sg_offset, len);
+	if (rc)
+		return rc;
 
 	p = wa->address + wa_offset;
 	q = p + len - 1;
@@ -509,7 +516,9 @@ static int ccp_run_aes_cmac_cmd(struct ccp_cmd_queue *cmd_q,
 		return ret;
 
 	dm_offset = CCP_SB_BYTES - aes->key_len;
-	ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	ret = ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	if (ret)
+		goto e_key;
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
 	if (ret) {
@@ -528,7 +537,9 @@ static int ccp_run_aes_cmac_cmd(struct ccp_cmd_queue *cmd_q,
 		goto e_key;
 
 	dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
-	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	ret = ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	if (ret)
+		goto e_ctx;
 	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
 	if (ret) {
@@ -556,8 +567,10 @@ static int ccp_run_aes_cmac_cmd(struct ccp_cmd_queue *cmd_q,
 				goto e_src;
 			}
 
-			ccp_set_dm_area(&ctx, 0, aes->cmac_key, 0,
-					aes->cmac_key_len);
+			ret = ccp_set_dm_area(&ctx, 0, aes->cmac_key, 0,
+					      aes->cmac_key_len);
+			if (ret)
+				goto e_src;
 			ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 					     CCP_PASSTHRU_BYTESWAP_256BIT);
 			if (ret) {
@@ -666,7 +679,9 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 		return ret;
 
 	dm_offset = CCP_SB_BYTES - aes->key_len;
-	ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	ret = ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	if (ret)
+		goto e_key;
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
 	if (ret) {
@@ -685,7 +700,9 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 		goto e_key;
 
 	dm_offset = CCP_AES_CTX_SB_COUNT * CCP_SB_BYTES - aes->iv_len;
-	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	ret = ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	if (ret)
+		goto e_ctx;
 
 	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
@@ -777,7 +794,9 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 		goto e_dst;
 	}
 
-	ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	ret = ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+	if (ret)
+		goto e_dst;
 
 	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
@@ -820,7 +839,9 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q,
 					   DMA_BIDIRECTIONAL);
 		if (ret)
 			goto e_tag;
-		ccp_set_dm_area(&tag, 0, p_tag, 0, AES_BLOCK_SIZE);
+		ret = ccp_set_dm_area(&tag, 0, p_tag, 0, AES_BLOCK_SIZE);
+		if (ret)
+			goto e_tag;
 
 		ret = memcmp(tag.address, final_wa.address, AES_BLOCK_SIZE);
 		ccp_dm_free(&tag);
@@ -914,7 +935,9 @@ static int ccp_run_aes_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		return ret;
 
 	dm_offset = CCP_SB_BYTES - aes->key_len;
-	ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	ret = ccp_set_dm_area(&key, dm_offset, aes->key, 0, aes->key_len);
+	if (ret)
+		goto e_key;
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
 	if (ret) {
@@ -935,7 +958,9 @@ static int ccp_run_aes_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	if (aes->mode != CCP_AES_MODE_ECB) {
 		/* Load the AES context - convert to LE */
 		dm_offset = CCP_SB_BYTES - AES_BLOCK_SIZE;
-		ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+		ret = ccp_set_dm_area(&ctx, dm_offset, aes->iv, 0, aes->iv_len);
+		if (ret)
+			goto e_ctx;
 		ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 				     CCP_PASSTHRU_BYTESWAP_256BIT);
 		if (ret) {
@@ -1113,8 +1138,12 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 		 * big endian to little endian.
 		 */
 		dm_offset = CCP_SB_BYTES - AES_KEYSIZE_128;
-		ccp_set_dm_area(&key, dm_offset, xts->key, 0, xts->key_len);
-		ccp_set_dm_area(&key, 0, xts->key, xts->key_len, xts->key_len);
+		ret = ccp_set_dm_area(&key, dm_offset, xts->key, 0, xts->key_len);
+		if (ret)
+			goto e_key;
+		ret = ccp_set_dm_area(&key, 0, xts->key, xts->key_len, xts->key_len);
+		if (ret)
+			goto e_key;
 	} else {
 		/* Version 5 CCPs use a 512-bit space for the key: each portion
 		 * occupies 256 bits, or one entire slot, and is zero-padded.
@@ -1123,9 +1152,13 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 
 		dm_offset = CCP_SB_BYTES;
 		pad = dm_offset - xts->key_len;
-		ccp_set_dm_area(&key, pad, xts->key, 0, xts->key_len);
-		ccp_set_dm_area(&key, dm_offset + pad, xts->key, xts->key_len,
-				xts->key_len);
+		ret = ccp_set_dm_area(&key, pad, xts->key, 0, xts->key_len);
+		if (ret)
+			goto e_key;
+		ret = ccp_set_dm_area(&key, dm_offset + pad, xts->key,
+				      xts->key_len, xts->key_len);
+		if (ret)
+			goto e_key;
 	}
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
 			     CCP_PASSTHRU_BYTESWAP_256BIT);
@@ -1144,7 +1177,9 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 	if (ret)
 		goto e_key;
 
-	ccp_set_dm_area(&ctx, 0, xts->iv, 0, xts->iv_len);
+	ret = ccp_set_dm_area(&ctx, 0, xts->iv, 0, xts->iv_len);
+	if (ret)
+		goto e_ctx;
 	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
 			     CCP_PASSTHRU_BYTESWAP_NOOP);
 	if (ret) {
@@ -1287,12 +1322,18 @@ static int ccp_run_des3_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	dm_offset = CCP_SB_BYTES - des3->key_len; /* Basic offset */
 
 	len_singlekey = des3->key_len / 3;
-	ccp_set_dm_area(&key, dm_offset + 2 * len_singlekey,
-			des3->key, 0, len_singlekey);
-	ccp_set_dm_area(&key, dm_offset + len_singlekey,
-			des3->key, len_singlekey, len_singlekey);
-	ccp_set_dm_area(&key, dm_offset,
-			des3->key, 2 * len_singlekey, len_singlekey);
+	ret = ccp_set_dm_area(&key, dm_offset + 2 * len_singlekey,
+			      des3->key, 0, len_singlekey);
+	if (ret)
+		goto e_key;
+	ret = ccp_set_dm_area(&key, dm_offset + len_singlekey,
+			      des3->key, len_singlekey, len_singlekey);
+	if (ret)
+		goto e_key;
+	ret = ccp_set_dm_area(&key, dm_offset,
+			      des3->key, 2 * len_singlekey, len_singlekey);
+	if (ret)
+		goto e_key;
 
 	/* Copy the key to the SB */
 	ret = ccp_copy_to_sb(cmd_q, &key, op.jobid, op.sb_key,
@@ -1320,7 +1361,10 @@ static int ccp_run_des3_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 
 		/* Load the context into the LSB */
 		dm_offset = CCP_SB_BYTES - des3->iv_len;
-		ccp_set_dm_area(&ctx, dm_offset, des3->iv, 0, des3->iv_len);
+		ret = ccp_set_dm_area(&ctx, dm_offset, des3->iv, 0,
+				      des3->iv_len);
+		if (ret)
+			goto e_ctx;
 
 		if (cmd_q->ccp->vdata->version == CCP_VERSION(3, 0))
 			load_mode = CCP_PASSTHRU_BYTESWAP_NOOP;
@@ -1604,8 +1648,10 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		}
 	} else {
 		/* Restore the context */
-		ccp_set_dm_area(&ctx, 0, sha->ctx, 0,
-				sb_count * CCP_SB_BYTES);
+		ret = ccp_set_dm_area(&ctx, 0, sha->ctx, 0,
+				      sb_count * CCP_SB_BYTES);
+		if (ret)
+			goto e_ctx;
 	}
 
 	ret = ccp_copy_to_sb(cmd_q, &ctx, op.jobid, op.sb_ctx,
@@ -1927,7 +1973,9 @@ static int ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q,
 		if (ret)
 			return ret;
 
-		ccp_set_dm_area(&mask, 0, pt->mask, 0, pt->mask_len);
+		ret = ccp_set_dm_area(&mask, 0, pt->mask, 0, pt->mask_len);
+		if (ret)
+			goto e_mask;
 		ret = ccp_copy_to_sb(cmd_q, &mask, op.jobid, op.sb_key,
 				     CCP_PASSTHRU_BYTESWAP_NOOP);
 		if (ret) {
diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index b3afb6cc9d72..d95ec526587a 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -367,8 +367,6 @@ e_free:
 
 void *psp_copy_user_blob(u64 __user uaddr, u32 len)
 {
-	void *data;
-
 	if (!uaddr || !len)
 		return ERR_PTR(-EINVAL);
 
@@ -376,18 +374,7 @@ void *psp_copy_user_blob(u64 __user uaddr, u32 len)
 	if (len > SEV_FW_BLOB_MAX_SIZE)
 		return ERR_PTR(-EINVAL);
 
-	data = kmalloc(len, GFP_KERNEL);
-	if (!data)
-		return ERR_PTR(-ENOMEM);
-
-	if (copy_from_user(data, (void __user *)(uintptr_t)uaddr, len))
-		goto e_free;
-
-	return data;
-
-e_free:
-	kfree(data);
-	return ERR_PTR(-EFAULT);
+	return memdup_user((void __user *)(uintptr_t)uaddr, len);
 }
 EXPORT_SYMBOL_GPL(psp_copy_user_blob);
 
diff --git a/drivers/crypto/ccp/sp-dev.c b/drivers/crypto/ccp/sp-dev.c
index eb0da6572720..e0459002eb71 100644
--- a/drivers/crypto/ccp/sp-dev.c
+++ b/drivers/crypto/ccp/sp-dev.c
@@ -252,12 +252,12 @@ struct sp_device *sp_get_psp_master_device(void)
 		goto unlock;
 
 	list_for_each_entry(i, &sp_units, entry) {
-		if (i->psp_data)
+		if (i->psp_data && i->get_psp_master_device) {
+			ret = i->get_psp_master_device();
 			break;
+		}
 	}
 
-	if (i->get_psp_master_device)
-		ret = i->get_psp_master_device();
 unlock:
 	write_unlock_irqrestore(&sp_unit_lock, flags);
 	return ret;
diff --git a/drivers/crypto/ccree/Makefile b/drivers/crypto/ccree/Makefile
new file mode 100644
index 000000000000..bdc27970f95f
--- /dev/null
+++ b/drivers/crypto/ccree/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_CRYPTO_DEV_CCREE) := ccree.o
+ccree-y := cc_driver.o cc_buffer_mgr.o cc_request_mgr.o cc_cipher.o cc_hash.o cc_aead.o cc_ivgen.o cc_sram_mgr.o
+ccree-$(CONFIG_CRYPTO_FIPS) += cc_fips.o
+ccree-$(CONFIG_DEBUG_FS) += cc_debugfs.o
+ccree-$(CONFIG_PM) += cc_pm.o
diff --git a/drivers/crypto/ccree/cc_aead.c b/drivers/crypto/ccree/cc_aead.c
new file mode 100644
index 000000000000..03f4b9fce556
--- /dev/null
+++ b/drivers/crypto/ccree/cc_aead.c
@@ -0,0 +1,2718 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/aead.h>
+#include <crypto/authenc.h>
+#include <crypto/des.h>
+#include <linux/rtnetlink.h>
+#include "cc_driver.h"
+#include "cc_buffer_mgr.h"
+#include "cc_aead.h"
+#include "cc_request_mgr.h"
+#include "cc_hash.h"
+#include "cc_sram_mgr.h"
+
+#define template_aead	template_u.aead
+
+#define MAX_AEAD_SETKEY_SEQ 12
+#define MAX_AEAD_PROCESS_SEQ 23
+
+#define MAX_HMAC_DIGEST_SIZE (SHA256_DIGEST_SIZE)
+#define MAX_HMAC_BLOCK_SIZE (SHA256_BLOCK_SIZE)
+
+#define AES_CCM_RFC4309_NONCE_SIZE 3
+#define MAX_NONCE_SIZE CTR_RFC3686_NONCE_SIZE
+
+/* Value of each ICV_CMP byte (of 8) in case of success */
+#define ICV_VERIF_OK 0x01
+
+struct cc_aead_handle {
+	cc_sram_addr_t sram_workspace_addr;
+	struct list_head aead_list;
+};
+
+struct cc_hmac_s {
+	u8 *padded_authkey;
+	u8 *ipad_opad; /* IPAD, OPAD*/
+	dma_addr_t padded_authkey_dma_addr;
+	dma_addr_t ipad_opad_dma_addr;
+};
+
+struct cc_xcbc_s {
+	u8 *xcbc_keys; /* K1,K2,K3 */
+	dma_addr_t xcbc_keys_dma_addr;
+};
+
+struct cc_aead_ctx {
+	struct cc_drvdata *drvdata;
+	u8 ctr_nonce[MAX_NONCE_SIZE]; /* used for ctr3686 iv and aes ccm */
+	u8 *enckey;
+	dma_addr_t enckey_dma_addr;
+	union {
+		struct cc_hmac_s hmac;
+		struct cc_xcbc_s xcbc;
+	} auth_state;
+	unsigned int enc_keylen;
+	unsigned int auth_keylen;
+	unsigned int authsize; /* Actual (reduced?) size of the MAC/ICv */
+	enum drv_cipher_mode cipher_mode;
+	enum cc_flow_mode flow_mode;
+	enum drv_hash_mode auth_mode;
+};
+
+static inline bool valid_assoclen(struct aead_request *req)
+{
+	return ((req->assoclen == 16) || (req->assoclen == 20));
+}
+
+static void cc_aead_exit(struct crypto_aead *tfm)
+{
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	dev_dbg(dev, "Clearing context @%p for %s\n", crypto_aead_ctx(tfm),
+		crypto_tfm_alg_name(&tfm->base));
+
+	/* Unmap enckey buffer */
+	if (ctx->enckey) {
+		dma_free_coherent(dev, AES_MAX_KEY_SIZE, ctx->enckey,
+				  ctx->enckey_dma_addr);
+		dev_dbg(dev, "Freed enckey DMA buffer enckey_dma_addr=%pad\n",
+			&ctx->enckey_dma_addr);
+		ctx->enckey_dma_addr = 0;
+		ctx->enckey = NULL;
+	}
+
+	if (ctx->auth_mode == DRV_HASH_XCBC_MAC) { /* XCBC authetication */
+		struct cc_xcbc_s *xcbc = &ctx->auth_state.xcbc;
+
+		if (xcbc->xcbc_keys) {
+			dma_free_coherent(dev, CC_AES_128_BIT_KEY_SIZE * 3,
+					  xcbc->xcbc_keys,
+					  xcbc->xcbc_keys_dma_addr);
+		}
+		dev_dbg(dev, "Freed xcbc_keys DMA buffer xcbc_keys_dma_addr=%pad\n",
+			&xcbc->xcbc_keys_dma_addr);
+		xcbc->xcbc_keys_dma_addr = 0;
+		xcbc->xcbc_keys = NULL;
+	} else if (ctx->auth_mode != DRV_HASH_NULL) { /* HMAC auth. */
+		struct cc_hmac_s *hmac = &ctx->auth_state.hmac;
+
+		if (hmac->ipad_opad) {
+			dma_free_coherent(dev, 2 * MAX_HMAC_DIGEST_SIZE,
+					  hmac->ipad_opad,
+					  hmac->ipad_opad_dma_addr);
+			dev_dbg(dev, "Freed ipad_opad DMA buffer ipad_opad_dma_addr=%pad\n",
+				&hmac->ipad_opad_dma_addr);
+			hmac->ipad_opad_dma_addr = 0;
+			hmac->ipad_opad = NULL;
+		}
+		if (hmac->padded_authkey) {
+			dma_free_coherent(dev, MAX_HMAC_BLOCK_SIZE,
+					  hmac->padded_authkey,
+					  hmac->padded_authkey_dma_addr);
+			dev_dbg(dev, "Freed padded_authkey DMA buffer padded_authkey_dma_addr=%pad\n",
+				&hmac->padded_authkey_dma_addr);
+			hmac->padded_authkey_dma_addr = 0;
+			hmac->padded_authkey = NULL;
+		}
+	}
+}
+
+static int cc_aead_init(struct crypto_aead *tfm)
+{
+	struct aead_alg *alg = crypto_aead_alg(tfm);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct cc_crypto_alg *cc_alg =
+			container_of(alg, struct cc_crypto_alg, aead_alg);
+	struct device *dev = drvdata_to_dev(cc_alg->drvdata);
+
+	dev_dbg(dev, "Initializing context @%p for %s\n", ctx,
+		crypto_tfm_alg_name(&tfm->base));
+
+	/* Initialize modes in instance */
+	ctx->cipher_mode = cc_alg->cipher_mode;
+	ctx->flow_mode = cc_alg->flow_mode;
+	ctx->auth_mode = cc_alg->auth_mode;
+	ctx->drvdata = cc_alg->drvdata;
+	crypto_aead_set_reqsize(tfm, sizeof(struct aead_req_ctx));
+
+	/* Allocate key buffer, cache line aligned */
+	ctx->enckey = dma_alloc_coherent(dev, AES_MAX_KEY_SIZE,
+					 &ctx->enckey_dma_addr, GFP_KERNEL);
+	if (!ctx->enckey) {
+		dev_err(dev, "Failed allocating key buffer\n");
+		goto init_failed;
+	}
+	dev_dbg(dev, "Allocated enckey buffer in context ctx->enckey=@%p\n",
+		ctx->enckey);
+
+	/* Set default authlen value */
+
+	if (ctx->auth_mode == DRV_HASH_XCBC_MAC) { /* XCBC authetication */
+		struct cc_xcbc_s *xcbc = &ctx->auth_state.xcbc;
+		const unsigned int key_size = CC_AES_128_BIT_KEY_SIZE * 3;
+
+		/* Allocate dma-coherent buffer for XCBC's K1+K2+K3 */
+		/* (and temporary for user key - up to 256b) */
+		xcbc->xcbc_keys = dma_alloc_coherent(dev, key_size,
+						     &xcbc->xcbc_keys_dma_addr,
+						     GFP_KERNEL);
+		if (!xcbc->xcbc_keys) {
+			dev_err(dev, "Failed allocating buffer for XCBC keys\n");
+			goto init_failed;
+		}
+	} else if (ctx->auth_mode != DRV_HASH_NULL) { /* HMAC authentication */
+		struct cc_hmac_s *hmac = &ctx->auth_state.hmac;
+		const unsigned int digest_size = 2 * MAX_HMAC_DIGEST_SIZE;
+		dma_addr_t *pkey_dma = &hmac->padded_authkey_dma_addr;
+
+		/* Allocate dma-coherent buffer for IPAD + OPAD */
+		hmac->ipad_opad = dma_alloc_coherent(dev, digest_size,
+						     &hmac->ipad_opad_dma_addr,
+						     GFP_KERNEL);
+
+		if (!hmac->ipad_opad) {
+			dev_err(dev, "Failed allocating IPAD/OPAD buffer\n");
+			goto init_failed;
+		}
+
+		dev_dbg(dev, "Allocated authkey buffer in context ctx->authkey=@%p\n",
+			hmac->ipad_opad);
+
+		hmac->padded_authkey = dma_alloc_coherent(dev,
+							  MAX_HMAC_BLOCK_SIZE,
+							  pkey_dma,
+							  GFP_KERNEL);
+
+		if (!hmac->padded_authkey) {
+			dev_err(dev, "failed to allocate padded_authkey\n");
+			goto init_failed;
+		}
+	} else {
+		ctx->auth_state.hmac.ipad_opad = NULL;
+		ctx->auth_state.hmac.padded_authkey = NULL;
+	}
+
+	return 0;
+
+init_failed:
+	cc_aead_exit(tfm);
+	return -ENOMEM;
+}
+
+static void cc_aead_complete(struct device *dev, void *cc_req, int err)
+{
+	struct aead_request *areq = (struct aead_request *)cc_req;
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(areq);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(cc_req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+
+	cc_unmap_aead_request(dev, areq);
+
+	/* Restore ordinary iv pointer */
+	areq->iv = areq_ctx->backup_iv;
+
+	if (err)
+		goto done;
+
+	if (areq_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT) {
+		if (memcmp(areq_ctx->mac_buf, areq_ctx->icv_virt_addr,
+			   ctx->authsize) != 0) {
+			dev_dbg(dev, "Payload authentication failure, (auth-size=%d, cipher=%d)\n",
+				ctx->authsize, ctx->cipher_mode);
+			/* In case of payload authentication failure, MUST NOT
+			 * revealed the decrypted message --> zero its memory.
+			 */
+			cc_zero_sgl(areq->dst, areq_ctx->cryptlen);
+			err = -EBADMSG;
+		}
+	} else { /*ENCRYPT*/
+		if (areq_ctx->is_icv_fragmented) {
+			u32 skip = areq->cryptlen + areq_ctx->dst_offset;
+
+			cc_copy_sg_portion(dev, areq_ctx->mac_buf,
+					   areq_ctx->dst_sgl, skip,
+					   (skip + ctx->authsize),
+					   CC_SG_FROM_BUF);
+		}
+
+		/* If an IV was generated, copy it back to the user provided
+		 * buffer.
+		 */
+		if (areq_ctx->backup_giv) {
+			if (ctx->cipher_mode == DRV_CIPHER_CTR)
+				memcpy(areq_ctx->backup_giv, areq_ctx->ctr_iv +
+				       CTR_RFC3686_NONCE_SIZE,
+				       CTR_RFC3686_IV_SIZE);
+			else if (ctx->cipher_mode == DRV_CIPHER_CCM)
+				memcpy(areq_ctx->backup_giv, areq_ctx->ctr_iv +
+				       CCM_BLOCK_IV_OFFSET, CCM_BLOCK_IV_SIZE);
+		}
+	}
+done:
+	aead_request_complete(areq, err);
+}
+
+static unsigned int xcbc_setkey(struct cc_hw_desc *desc,
+				struct cc_aead_ctx *ctx)
+{
+	/* Load the AES key */
+	hw_desc_init(&desc[0]);
+	/* We are using for the source/user key the same buffer
+	 * as for the output keys, * because after this key loading it
+	 * is not needed anymore
+	 */
+	set_din_type(&desc[0], DMA_DLLI,
+		     ctx->auth_state.xcbc.xcbc_keys_dma_addr, ctx->auth_keylen,
+		     NS_BIT);
+	set_cipher_mode(&desc[0], DRV_CIPHER_ECB);
+	set_cipher_config0(&desc[0], DRV_CRYPTO_DIRECTION_ENCRYPT);
+	set_key_size_aes(&desc[0], ctx->auth_keylen);
+	set_flow_mode(&desc[0], S_DIN_to_AES);
+	set_setup_mode(&desc[0], SETUP_LOAD_KEY0);
+
+	hw_desc_init(&desc[1]);
+	set_din_const(&desc[1], 0x01010101, CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[1], DIN_AES_DOUT);
+	set_dout_dlli(&desc[1], ctx->auth_state.xcbc.xcbc_keys_dma_addr,
+		      AES_KEYSIZE_128, NS_BIT, 0);
+
+	hw_desc_init(&desc[2]);
+	set_din_const(&desc[2], 0x02020202, CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[2], DIN_AES_DOUT);
+	set_dout_dlli(&desc[2], (ctx->auth_state.xcbc.xcbc_keys_dma_addr
+					 + AES_KEYSIZE_128),
+			      AES_KEYSIZE_128, NS_BIT, 0);
+
+	hw_desc_init(&desc[3]);
+	set_din_const(&desc[3], 0x03030303, CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[3], DIN_AES_DOUT);
+	set_dout_dlli(&desc[3], (ctx->auth_state.xcbc.xcbc_keys_dma_addr
+					  + 2 * AES_KEYSIZE_128),
+			      AES_KEYSIZE_128, NS_BIT, 0);
+
+	return 4;
+}
+
+static int hmac_setkey(struct cc_hw_desc *desc, struct cc_aead_ctx *ctx)
+{
+	unsigned int hmac_pad_const[2] = { HMAC_IPAD_CONST, HMAC_OPAD_CONST };
+	unsigned int digest_ofs = 0;
+	unsigned int hash_mode = (ctx->auth_mode == DRV_HASH_SHA1) ?
+			DRV_HASH_HW_SHA1 : DRV_HASH_HW_SHA256;
+	unsigned int digest_size = (ctx->auth_mode == DRV_HASH_SHA1) ?
+			CC_SHA1_DIGEST_SIZE : CC_SHA256_DIGEST_SIZE;
+	struct cc_hmac_s *hmac = &ctx->auth_state.hmac;
+
+	unsigned int idx = 0;
+	int i;
+
+	/* calc derived HMAC key */
+	for (i = 0; i < 2; i++) {
+		/* Load hash initial state */
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], hash_mode);
+		set_din_sram(&desc[idx],
+			     cc_larval_digest_addr(ctx->drvdata,
+						   ctx->auth_mode),
+			     digest_size);
+		set_flow_mode(&desc[idx], S_DIN_to_HASH);
+		set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+		idx++;
+
+		/* Load the hash current length*/
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], hash_mode);
+		set_din_const(&desc[idx], 0, ctx->drvdata->hash_len_sz);
+		set_flow_mode(&desc[idx], S_DIN_to_HASH);
+		set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+		idx++;
+
+		/* Prepare ipad key */
+		hw_desc_init(&desc[idx]);
+		set_xor_val(&desc[idx], hmac_pad_const[i]);
+		set_cipher_mode(&desc[idx], hash_mode);
+		set_flow_mode(&desc[idx], S_DIN_to_HASH);
+		set_setup_mode(&desc[idx], SETUP_LOAD_STATE1);
+		idx++;
+
+		/* Perform HASH update */
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_DLLI,
+			     hmac->padded_authkey_dma_addr,
+			     SHA256_BLOCK_SIZE, NS_BIT);
+		set_cipher_mode(&desc[idx], hash_mode);
+		set_xor_active(&desc[idx]);
+		set_flow_mode(&desc[idx], DIN_HASH);
+		idx++;
+
+		/* Get the digset */
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], hash_mode);
+		set_dout_dlli(&desc[idx],
+			      (hmac->ipad_opad_dma_addr + digest_ofs),
+			      digest_size, NS_BIT, 0);
+		set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+		set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+		set_cipher_config1(&desc[idx], HASH_PADDING_DISABLED);
+		idx++;
+
+		digest_ofs += digest_size;
+	}
+
+	return idx;
+}
+
+static int validate_keys_sizes(struct cc_aead_ctx *ctx)
+{
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	dev_dbg(dev, "enc_keylen=%u  authkeylen=%u\n",
+		ctx->enc_keylen, ctx->auth_keylen);
+
+	switch (ctx->auth_mode) {
+	case DRV_HASH_SHA1:
+	case DRV_HASH_SHA256:
+		break;
+	case DRV_HASH_XCBC_MAC:
+		if (ctx->auth_keylen != AES_KEYSIZE_128 &&
+		    ctx->auth_keylen != AES_KEYSIZE_192 &&
+		    ctx->auth_keylen != AES_KEYSIZE_256)
+			return -ENOTSUPP;
+		break;
+	case DRV_HASH_NULL: /* Not authenc (e.g., CCM) - no auth_key) */
+		if (ctx->auth_keylen > 0)
+			return -EINVAL;
+		break;
+	default:
+		dev_err(dev, "Invalid auth_mode=%d\n", ctx->auth_mode);
+		return -EINVAL;
+	}
+	/* Check cipher key size */
+	if (ctx->flow_mode == S_DIN_to_DES) {
+		if (ctx->enc_keylen != DES3_EDE_KEY_SIZE) {
+			dev_err(dev, "Invalid cipher(3DES) key size: %u\n",
+				ctx->enc_keylen);
+			return -EINVAL;
+		}
+	} else { /* Default assumed to be AES ciphers */
+		if (ctx->enc_keylen != AES_KEYSIZE_128 &&
+		    ctx->enc_keylen != AES_KEYSIZE_192 &&
+		    ctx->enc_keylen != AES_KEYSIZE_256) {
+			dev_err(dev, "Invalid cipher(AES) key size: %u\n",
+				ctx->enc_keylen);
+			return -EINVAL;
+		}
+	}
+
+	return 0; /* All tests of keys sizes passed */
+}
+
+/* This function prepers the user key so it can pass to the hmac processing
+ * (copy to intenral buffer or hash in case of key longer than block
+ */
+static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	dma_addr_t key_dma_addr = 0;
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	u32 larval_addr = cc_larval_digest_addr(ctx->drvdata, ctx->auth_mode);
+	struct cc_crypto_req cc_req = {};
+	unsigned int blocksize;
+	unsigned int digestsize;
+	unsigned int hashmode;
+	unsigned int idx = 0;
+	int rc = 0;
+	struct cc_hw_desc desc[MAX_AEAD_SETKEY_SEQ];
+	dma_addr_t padded_authkey_dma_addr =
+		ctx->auth_state.hmac.padded_authkey_dma_addr;
+
+	switch (ctx->auth_mode) { /* auth_key required and >0 */
+	case DRV_HASH_SHA1:
+		blocksize = SHA1_BLOCK_SIZE;
+		digestsize = SHA1_DIGEST_SIZE;
+		hashmode = DRV_HASH_HW_SHA1;
+		break;
+	case DRV_HASH_SHA256:
+	default:
+		blocksize = SHA256_BLOCK_SIZE;
+		digestsize = SHA256_DIGEST_SIZE;
+		hashmode = DRV_HASH_HW_SHA256;
+	}
+
+	if (keylen != 0) {
+		key_dma_addr = dma_map_single(dev, (void *)key, keylen,
+					      DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, key_dma_addr)) {
+			dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
+				key, keylen);
+			return -ENOMEM;
+		}
+		if (keylen > blocksize) {
+			/* Load hash initial state */
+			hw_desc_init(&desc[idx]);
+			set_cipher_mode(&desc[idx], hashmode);
+			set_din_sram(&desc[idx], larval_addr, digestsize);
+			set_flow_mode(&desc[idx], S_DIN_to_HASH);
+			set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+			idx++;
+
+			/* Load the hash current length*/
+			hw_desc_init(&desc[idx]);
+			set_cipher_mode(&desc[idx], hashmode);
+			set_din_const(&desc[idx], 0, ctx->drvdata->hash_len_sz);
+			set_cipher_config1(&desc[idx], HASH_PADDING_ENABLED);
+			set_flow_mode(&desc[idx], S_DIN_to_HASH);
+			set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+			idx++;
+
+			hw_desc_init(&desc[idx]);
+			set_din_type(&desc[idx], DMA_DLLI,
+				     key_dma_addr, keylen, NS_BIT);
+			set_flow_mode(&desc[idx], DIN_HASH);
+			idx++;
+
+			/* Get hashed key */
+			hw_desc_init(&desc[idx]);
+			set_cipher_mode(&desc[idx], hashmode);
+			set_dout_dlli(&desc[idx], padded_authkey_dma_addr,
+				      digestsize, NS_BIT, 0);
+			set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+			set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+			set_cipher_config1(&desc[idx], HASH_PADDING_DISABLED);
+			set_cipher_config0(&desc[idx],
+					   HASH_DIGEST_RESULT_LITTLE_ENDIAN);
+			idx++;
+
+			hw_desc_init(&desc[idx]);
+			set_din_const(&desc[idx], 0, (blocksize - digestsize));
+			set_flow_mode(&desc[idx], BYPASS);
+			set_dout_dlli(&desc[idx], (padded_authkey_dma_addr +
+				      digestsize), (blocksize - digestsize),
+				      NS_BIT, 0);
+			idx++;
+		} else {
+			hw_desc_init(&desc[idx]);
+			set_din_type(&desc[idx], DMA_DLLI, key_dma_addr,
+				     keylen, NS_BIT);
+			set_flow_mode(&desc[idx], BYPASS);
+			set_dout_dlli(&desc[idx], padded_authkey_dma_addr,
+				      keylen, NS_BIT, 0);
+			idx++;
+
+			if ((blocksize - keylen) != 0) {
+				hw_desc_init(&desc[idx]);
+				set_din_const(&desc[idx], 0,
+					      (blocksize - keylen));
+				set_flow_mode(&desc[idx], BYPASS);
+				set_dout_dlli(&desc[idx],
+					      (padded_authkey_dma_addr +
+					       keylen),
+					      (blocksize - keylen), NS_BIT, 0);
+				idx++;
+			}
+		}
+	} else {
+		hw_desc_init(&desc[idx]);
+		set_din_const(&desc[idx], 0, (blocksize - keylen));
+		set_flow_mode(&desc[idx], BYPASS);
+		set_dout_dlli(&desc[idx], padded_authkey_dma_addr,
+			      blocksize, NS_BIT, 0);
+		idx++;
+	}
+
+	rc = cc_send_sync_request(ctx->drvdata, &cc_req, desc, idx);
+	if (rc)
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+
+	if (key_dma_addr)
+		dma_unmap_single(dev, key_dma_addr, keylen, DMA_TO_DEVICE);
+
+	return rc;
+}
+
+static int cc_aead_setkey(struct crypto_aead *tfm, const u8 *key,
+			  unsigned int keylen)
+{
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct rtattr *rta = (struct rtattr *)key;
+	struct cc_crypto_req cc_req = {};
+	struct crypto_authenc_key_param *param;
+	struct cc_hw_desc desc[MAX_AEAD_SETKEY_SEQ];
+	int rc = -EINVAL;
+	unsigned int seq_len = 0;
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	dev_dbg(dev, "Setting key in context @%p for %s. key=%p keylen=%u\n",
+		ctx, crypto_tfm_alg_name(crypto_aead_tfm(tfm)), key, keylen);
+
+	/* STAT_PHASE_0: Init and sanity checks */
+
+	if (ctx->auth_mode != DRV_HASH_NULL) { /* authenc() alg. */
+		if (!RTA_OK(rta, keylen))
+			goto badkey;
+		if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM)
+			goto badkey;
+		if (RTA_PAYLOAD(rta) < sizeof(*param))
+			goto badkey;
+		param = RTA_DATA(rta);
+		ctx->enc_keylen = be32_to_cpu(param->enckeylen);
+		key += RTA_ALIGN(rta->rta_len);
+		keylen -= RTA_ALIGN(rta->rta_len);
+		if (keylen < ctx->enc_keylen)
+			goto badkey;
+		ctx->auth_keylen = keylen - ctx->enc_keylen;
+
+		if (ctx->cipher_mode == DRV_CIPHER_CTR) {
+			/* the nonce is stored in bytes at end of key */
+			if (ctx->enc_keylen <
+			    (AES_MIN_KEY_SIZE + CTR_RFC3686_NONCE_SIZE))
+				goto badkey;
+			/* Copy nonce from last 4 bytes in CTR key to
+			 *  first 4 bytes in CTR IV
+			 */
+			memcpy(ctx->ctr_nonce, key + ctx->auth_keylen +
+			       ctx->enc_keylen - CTR_RFC3686_NONCE_SIZE,
+			       CTR_RFC3686_NONCE_SIZE);
+			/* Set CTR key size */
+			ctx->enc_keylen -= CTR_RFC3686_NONCE_SIZE;
+		}
+	} else { /* non-authenc - has just one key */
+		ctx->enc_keylen = keylen;
+		ctx->auth_keylen = 0;
+	}
+
+	rc = validate_keys_sizes(ctx);
+	if (rc)
+		goto badkey;
+
+	/* STAT_PHASE_1: Copy key to ctx */
+
+	/* Get key material */
+	memcpy(ctx->enckey, key + ctx->auth_keylen, ctx->enc_keylen);
+	if (ctx->enc_keylen == 24)
+		memset(ctx->enckey + 24, 0, CC_AES_KEY_SIZE_MAX - 24);
+	if (ctx->auth_mode == DRV_HASH_XCBC_MAC) {
+		memcpy(ctx->auth_state.xcbc.xcbc_keys, key, ctx->auth_keylen);
+	} else if (ctx->auth_mode != DRV_HASH_NULL) { /* HMAC */
+		rc = cc_get_plain_hmac_key(tfm, key, ctx->auth_keylen);
+		if (rc)
+			goto badkey;
+	}
+
+	/* STAT_PHASE_2: Create sequence */
+
+	switch (ctx->auth_mode) {
+	case DRV_HASH_SHA1:
+	case DRV_HASH_SHA256:
+		seq_len = hmac_setkey(desc, ctx);
+		break;
+	case DRV_HASH_XCBC_MAC:
+		seq_len = xcbc_setkey(desc, ctx);
+		break;
+	case DRV_HASH_NULL: /* non-authenc modes, e.g., CCM */
+		break; /* No auth. key setup */
+	default:
+		dev_err(dev, "Unsupported authenc (%d)\n", ctx->auth_mode);
+		rc = -ENOTSUPP;
+		goto badkey;
+	}
+
+	/* STAT_PHASE_3: Submit sequence to HW */
+
+	if (seq_len > 0) { /* For CCM there is no sequence to setup the key */
+		rc = cc_send_sync_request(ctx->drvdata, &cc_req, desc, seq_len);
+		if (rc) {
+			dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+			goto setkey_error;
+		}
+	}
+
+	/* Update STAT_PHASE_3 */
+	return rc;
+
+badkey:
+	crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+
+setkey_error:
+	return rc;
+}
+
+static int cc_rfc4309_ccm_setkey(struct crypto_aead *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+
+	if (keylen < 3)
+		return -EINVAL;
+
+	keylen -= 3;
+	memcpy(ctx->ctr_nonce, key + keylen, 3);
+
+	return cc_aead_setkey(tfm, key, keylen);
+}
+
+static int cc_aead_setauthsize(struct crypto_aead *authenc,
+			       unsigned int authsize)
+{
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(authenc);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	/* Unsupported auth. sizes */
+	if (authsize == 0 ||
+	    authsize > crypto_aead_maxauthsize(authenc)) {
+		return -ENOTSUPP;
+	}
+
+	ctx->authsize = authsize;
+	dev_dbg(dev, "authlen=%d\n", ctx->authsize);
+
+	return 0;
+}
+
+static int cc_rfc4309_ccm_setauthsize(struct crypto_aead *authenc,
+				      unsigned int authsize)
+{
+	switch (authsize) {
+	case 8:
+	case 12:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return cc_aead_setauthsize(authenc, authsize);
+}
+
+static int cc_ccm_setauthsize(struct crypto_aead *authenc,
+			      unsigned int authsize)
+{
+	switch (authsize) {
+	case 4:
+	case 6:
+	case 8:
+	case 10:
+	case 12:
+	case 14:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return cc_aead_setauthsize(authenc, authsize);
+}
+
+static void cc_set_assoc_desc(struct aead_request *areq, unsigned int flow_mode,
+			      struct cc_hw_desc desc[], unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(areq);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(areq);
+	enum cc_req_dma_buf_type assoc_dma_type = areq_ctx->assoc_buff_type;
+	unsigned int idx = *seq_size;
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	switch (assoc_dma_type) {
+	case CC_DMA_BUF_DLLI:
+		dev_dbg(dev, "ASSOC buffer type DLLI\n");
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_DLLI, sg_dma_address(areq->src),
+			     areq->assoclen, NS_BIT);
+		set_flow_mode(&desc[idx], flow_mode);
+		if (ctx->auth_mode == DRV_HASH_XCBC_MAC &&
+		    areq_ctx->cryptlen > 0)
+			set_din_not_last_indication(&desc[idx]);
+		break;
+	case CC_DMA_BUF_MLLI:
+		dev_dbg(dev, "ASSOC buffer type MLLI\n");
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_MLLI, areq_ctx->assoc.sram_addr,
+			     areq_ctx->assoc.mlli_nents, NS_BIT);
+		set_flow_mode(&desc[idx], flow_mode);
+		if (ctx->auth_mode == DRV_HASH_XCBC_MAC &&
+		    areq_ctx->cryptlen > 0)
+			set_din_not_last_indication(&desc[idx]);
+		break;
+	case CC_DMA_BUF_NULL:
+	default:
+		dev_err(dev, "Invalid ASSOC buffer type\n");
+	}
+
+	*seq_size = (++idx);
+}
+
+static void cc_proc_authen_desc(struct aead_request *areq,
+				unsigned int flow_mode,
+				struct cc_hw_desc desc[],
+				unsigned int *seq_size, int direct)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(areq);
+	enum cc_req_dma_buf_type data_dma_type = areq_ctx->data_buff_type;
+	unsigned int idx = *seq_size;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(areq);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	switch (data_dma_type) {
+	case CC_DMA_BUF_DLLI:
+	{
+		struct scatterlist *cipher =
+			(direct == DRV_CRYPTO_DIRECTION_ENCRYPT) ?
+			areq_ctx->dst_sgl : areq_ctx->src_sgl;
+
+		unsigned int offset =
+			(direct == DRV_CRYPTO_DIRECTION_ENCRYPT) ?
+			areq_ctx->dst_offset : areq_ctx->src_offset;
+		dev_dbg(dev, "AUTHENC: SRC/DST buffer type DLLI\n");
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_DLLI,
+			     (sg_dma_address(cipher) + offset),
+			     areq_ctx->cryptlen, NS_BIT);
+		set_flow_mode(&desc[idx], flow_mode);
+		break;
+	}
+	case CC_DMA_BUF_MLLI:
+	{
+		/* DOUBLE-PASS flow (as default)
+		 * assoc. + iv + data -compact in one table
+		 * if assoclen is ZERO only IV perform
+		 */
+		cc_sram_addr_t mlli_addr = areq_ctx->assoc.sram_addr;
+		u32 mlli_nents = areq_ctx->assoc.mlli_nents;
+
+		if (areq_ctx->is_single_pass) {
+			if (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) {
+				mlli_addr = areq_ctx->dst.sram_addr;
+				mlli_nents = areq_ctx->dst.mlli_nents;
+			} else {
+				mlli_addr = areq_ctx->src.sram_addr;
+				mlli_nents = areq_ctx->src.mlli_nents;
+			}
+		}
+
+		dev_dbg(dev, "AUTHENC: SRC/DST buffer type MLLI\n");
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_MLLI, mlli_addr, mlli_nents,
+			     NS_BIT);
+		set_flow_mode(&desc[idx], flow_mode);
+		break;
+	}
+	case CC_DMA_BUF_NULL:
+	default:
+		dev_err(dev, "AUTHENC: Invalid SRC/DST buffer type\n");
+	}
+
+	*seq_size = (++idx);
+}
+
+static void cc_proc_cipher_desc(struct aead_request *areq,
+				unsigned int flow_mode,
+				struct cc_hw_desc desc[],
+				unsigned int *seq_size)
+{
+	unsigned int idx = *seq_size;
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(areq);
+	enum cc_req_dma_buf_type data_dma_type = areq_ctx->data_buff_type;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(areq);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	if (areq_ctx->cryptlen == 0)
+		return; /*null processing*/
+
+	switch (data_dma_type) {
+	case CC_DMA_BUF_DLLI:
+		dev_dbg(dev, "CIPHER: SRC/DST buffer type DLLI\n");
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_DLLI,
+			     (sg_dma_address(areq_ctx->src_sgl) +
+			      areq_ctx->src_offset), areq_ctx->cryptlen,
+			      NS_BIT);
+		set_dout_dlli(&desc[idx],
+			      (sg_dma_address(areq_ctx->dst_sgl) +
+			       areq_ctx->dst_offset),
+			      areq_ctx->cryptlen, NS_BIT, 0);
+		set_flow_mode(&desc[idx], flow_mode);
+		break;
+	case CC_DMA_BUF_MLLI:
+		dev_dbg(dev, "CIPHER: SRC/DST buffer type MLLI\n");
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_MLLI, areq_ctx->src.sram_addr,
+			     areq_ctx->src.mlli_nents, NS_BIT);
+		set_dout_mlli(&desc[idx], areq_ctx->dst.sram_addr,
+			      areq_ctx->dst.mlli_nents, NS_BIT, 0);
+		set_flow_mode(&desc[idx], flow_mode);
+		break;
+	case CC_DMA_BUF_NULL:
+	default:
+		dev_err(dev, "CIPHER: Invalid SRC/DST buffer type\n");
+	}
+
+	*seq_size = (++idx);
+}
+
+static void cc_proc_digest_desc(struct aead_request *req,
+				struct cc_hw_desc desc[],
+				unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	unsigned int idx = *seq_size;
+	unsigned int hash_mode = (ctx->auth_mode == DRV_HASH_SHA1) ?
+				DRV_HASH_HW_SHA1 : DRV_HASH_HW_SHA256;
+	int direct = req_ctx->gen_ctx.op_type;
+
+	/* Get final ICV result */
+	if (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) {
+		hw_desc_init(&desc[idx]);
+		set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+		set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+		set_dout_dlli(&desc[idx], req_ctx->icv_dma_addr, ctx->authsize,
+			      NS_BIT, 1);
+		set_queue_last_ind(ctx->drvdata, &desc[idx]);
+		if (ctx->auth_mode == DRV_HASH_XCBC_MAC) {
+			set_aes_not_hash_mode(&desc[idx]);
+			set_cipher_mode(&desc[idx], DRV_CIPHER_XCBC_MAC);
+		} else {
+			set_cipher_config0(&desc[idx],
+					   HASH_DIGEST_RESULT_LITTLE_ENDIAN);
+			set_cipher_mode(&desc[idx], hash_mode);
+		}
+	} else { /*Decrypt*/
+		/* Get ICV out from hardware */
+		hw_desc_init(&desc[idx]);
+		set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+		set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+		set_dout_dlli(&desc[idx], req_ctx->mac_buf_dma_addr,
+			      ctx->authsize, NS_BIT, 1);
+		set_queue_last_ind(ctx->drvdata, &desc[idx]);
+		set_cipher_config0(&desc[idx],
+				   HASH_DIGEST_RESULT_LITTLE_ENDIAN);
+		set_cipher_config1(&desc[idx], HASH_PADDING_DISABLED);
+		if (ctx->auth_mode == DRV_HASH_XCBC_MAC) {
+			set_cipher_mode(&desc[idx], DRV_CIPHER_XCBC_MAC);
+			set_aes_not_hash_mode(&desc[idx]);
+		} else {
+			set_cipher_mode(&desc[idx], hash_mode);
+		}
+	}
+
+	*seq_size = (++idx);
+}
+
+static void cc_set_cipher_desc(struct aead_request *req,
+			       struct cc_hw_desc desc[],
+			       unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	unsigned int hw_iv_size = req_ctx->hw_iv_size;
+	unsigned int idx = *seq_size;
+	int direct = req_ctx->gen_ctx.op_type;
+
+	/* Setup cipher state */
+	hw_desc_init(&desc[idx]);
+	set_cipher_config0(&desc[idx], direct);
+	set_flow_mode(&desc[idx], ctx->flow_mode);
+	set_din_type(&desc[idx], DMA_DLLI, req_ctx->gen_ctx.iv_dma_addr,
+		     hw_iv_size, NS_BIT);
+	if (ctx->cipher_mode == DRV_CIPHER_CTR)
+		set_setup_mode(&desc[idx], SETUP_LOAD_STATE1);
+	else
+		set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	set_cipher_mode(&desc[idx], ctx->cipher_mode);
+	idx++;
+
+	/* Setup enc. key */
+	hw_desc_init(&desc[idx]);
+	set_cipher_config0(&desc[idx], direct);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	set_flow_mode(&desc[idx], ctx->flow_mode);
+	if (ctx->flow_mode == S_DIN_to_AES) {
+		set_din_type(&desc[idx], DMA_DLLI, ctx->enckey_dma_addr,
+			     ((ctx->enc_keylen == 24) ? CC_AES_KEY_SIZE_MAX :
+			      ctx->enc_keylen), NS_BIT);
+		set_key_size_aes(&desc[idx], ctx->enc_keylen);
+	} else {
+		set_din_type(&desc[idx], DMA_DLLI, ctx->enckey_dma_addr,
+			     ctx->enc_keylen, NS_BIT);
+		set_key_size_des(&desc[idx], ctx->enc_keylen);
+	}
+	set_cipher_mode(&desc[idx], ctx->cipher_mode);
+	idx++;
+
+	*seq_size = idx;
+}
+
+static void cc_proc_cipher(struct aead_request *req, struct cc_hw_desc desc[],
+			   unsigned int *seq_size, unsigned int data_flow_mode)
+{
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	int direct = req_ctx->gen_ctx.op_type;
+	unsigned int idx = *seq_size;
+
+	if (req_ctx->cryptlen == 0)
+		return; /*null processing*/
+
+	cc_set_cipher_desc(req, desc, &idx);
+	cc_proc_cipher_desc(req, data_flow_mode, desc, &idx);
+	if (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) {
+		/* We must wait for DMA to write all cipher */
+		hw_desc_init(&desc[idx]);
+		set_din_no_dma(&desc[idx], 0, 0xfffff0);
+		set_dout_no_dma(&desc[idx], 0, 0, 1);
+		idx++;
+	}
+
+	*seq_size = idx;
+}
+
+static void cc_set_hmac_desc(struct aead_request *req, struct cc_hw_desc desc[],
+			     unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	unsigned int hash_mode = (ctx->auth_mode == DRV_HASH_SHA1) ?
+				DRV_HASH_HW_SHA1 : DRV_HASH_HW_SHA256;
+	unsigned int digest_size = (ctx->auth_mode == DRV_HASH_SHA1) ?
+				CC_SHA1_DIGEST_SIZE : CC_SHA256_DIGEST_SIZE;
+	unsigned int idx = *seq_size;
+
+	/* Loading hash ipad xor key state */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], hash_mode);
+	set_din_type(&desc[idx], DMA_DLLI,
+		     ctx->auth_state.hmac.ipad_opad_dma_addr, digest_size,
+		     NS_BIT);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	idx++;
+
+	/* Load init. digest len (64 bytes) */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], hash_mode);
+	set_din_sram(&desc[idx], cc_digest_len_addr(ctx->drvdata, hash_mode),
+		     ctx->drvdata->hash_len_sz);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	idx++;
+
+	*seq_size = idx;
+}
+
+static void cc_set_xcbc_desc(struct aead_request *req, struct cc_hw_desc desc[],
+			     unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	unsigned int idx = *seq_size;
+
+	/* Loading MAC state */
+	hw_desc_init(&desc[idx]);
+	set_din_const(&desc[idx], 0, CC_AES_BLOCK_SIZE);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_XCBC_MAC);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_key_size_aes(&desc[idx], CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_aes_not_hash_mode(&desc[idx]);
+	idx++;
+
+	/* Setup XCBC MAC K1 */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI,
+		     ctx->auth_state.xcbc.xcbc_keys_dma_addr,
+		     AES_KEYSIZE_128, NS_BIT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_XCBC_MAC);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_key_size_aes(&desc[idx], CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_aes_not_hash_mode(&desc[idx]);
+	idx++;
+
+	/* Setup XCBC MAC K2 */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI,
+		     (ctx->auth_state.xcbc.xcbc_keys_dma_addr +
+		      AES_KEYSIZE_128), AES_KEYSIZE_128, NS_BIT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE1);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_XCBC_MAC);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_key_size_aes(&desc[idx], CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_aes_not_hash_mode(&desc[idx]);
+	idx++;
+
+	/* Setup XCBC MAC K3 */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI,
+		     (ctx->auth_state.xcbc.xcbc_keys_dma_addr +
+		      2 * AES_KEYSIZE_128), AES_KEYSIZE_128, NS_BIT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE2);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_XCBC_MAC);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_key_size_aes(&desc[idx], CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_aes_not_hash_mode(&desc[idx]);
+	idx++;
+
+	*seq_size = idx;
+}
+
+static void cc_proc_header_desc(struct aead_request *req,
+				struct cc_hw_desc desc[],
+				unsigned int *seq_size)
+{
+	unsigned int idx = *seq_size;
+	/* Hash associated data */
+	if (req->assoclen > 0)
+		cc_set_assoc_desc(req, DIN_HASH, desc, &idx);
+
+	/* Hash IV */
+	*seq_size = idx;
+}
+
+static void cc_proc_scheme_desc(struct aead_request *req,
+				struct cc_hw_desc desc[],
+				unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct cc_aead_handle *aead_handle = ctx->drvdata->aead_handle;
+	unsigned int hash_mode = (ctx->auth_mode == DRV_HASH_SHA1) ?
+				DRV_HASH_HW_SHA1 : DRV_HASH_HW_SHA256;
+	unsigned int digest_size = (ctx->auth_mode == DRV_HASH_SHA1) ?
+				CC_SHA1_DIGEST_SIZE : CC_SHA256_DIGEST_SIZE;
+	unsigned int idx = *seq_size;
+
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], hash_mode);
+	set_dout_sram(&desc[idx], aead_handle->sram_workspace_addr,
+		      ctx->drvdata->hash_len_sz);
+	set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE1);
+	set_cipher_do(&desc[idx], DO_PAD);
+	idx++;
+
+	/* Get final ICV result */
+	hw_desc_init(&desc[idx]);
+	set_dout_sram(&desc[idx], aead_handle->sram_workspace_addr,
+		      digest_size);
+	set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+	set_cipher_config0(&desc[idx], HASH_DIGEST_RESULT_LITTLE_ENDIAN);
+	set_cipher_mode(&desc[idx], hash_mode);
+	idx++;
+
+	/* Loading hash opad xor key state */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], hash_mode);
+	set_din_type(&desc[idx], DMA_DLLI,
+		     (ctx->auth_state.hmac.ipad_opad_dma_addr + digest_size),
+		     digest_size, NS_BIT);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	idx++;
+
+	/* Load init. digest len (64 bytes) */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], hash_mode);
+	set_din_sram(&desc[idx], cc_digest_len_addr(ctx->drvdata, hash_mode),
+		     ctx->drvdata->hash_len_sz);
+	set_cipher_config1(&desc[idx], HASH_PADDING_ENABLED);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	idx++;
+
+	/* Perform HASH update */
+	hw_desc_init(&desc[idx]);
+	set_din_sram(&desc[idx], aead_handle->sram_workspace_addr,
+		     digest_size);
+	set_flow_mode(&desc[idx], DIN_HASH);
+	idx++;
+
+	*seq_size = idx;
+}
+
+static void cc_mlli_to_sram(struct aead_request *req,
+			    struct cc_hw_desc desc[], unsigned int *seq_size)
+{
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	if (req_ctx->assoc_buff_type == CC_DMA_BUF_MLLI ||
+	    req_ctx->data_buff_type == CC_DMA_BUF_MLLI ||
+	    !req_ctx->is_single_pass) {
+		dev_dbg(dev, "Copy-to-sram: mlli_dma=%08x, mlli_size=%u\n",
+			(unsigned int)ctx->drvdata->mlli_sram_addr,
+			req_ctx->mlli_params.mlli_len);
+		/* Copy MLLI table host-to-sram */
+		hw_desc_init(&desc[*seq_size]);
+		set_din_type(&desc[*seq_size], DMA_DLLI,
+			     req_ctx->mlli_params.mlli_dma_addr,
+			     req_ctx->mlli_params.mlli_len, NS_BIT);
+		set_dout_sram(&desc[*seq_size],
+			      ctx->drvdata->mlli_sram_addr,
+			      req_ctx->mlli_params.mlli_len);
+		set_flow_mode(&desc[*seq_size], BYPASS);
+		(*seq_size)++;
+	}
+}
+
+static enum cc_flow_mode cc_get_data_flow(enum drv_crypto_direction direct,
+					  enum cc_flow_mode setup_flow_mode,
+					  bool is_single_pass)
+{
+	enum cc_flow_mode data_flow_mode;
+
+	if (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) {
+		if (setup_flow_mode == S_DIN_to_AES)
+			data_flow_mode = is_single_pass ?
+				AES_to_HASH_and_DOUT : DIN_AES_DOUT;
+		else
+			data_flow_mode = is_single_pass ?
+				DES_to_HASH_and_DOUT : DIN_DES_DOUT;
+	} else { /* Decrypt */
+		if (setup_flow_mode == S_DIN_to_AES)
+			data_flow_mode = is_single_pass ?
+				AES_and_HASH : DIN_AES_DOUT;
+		else
+			data_flow_mode = is_single_pass ?
+				DES_and_HASH : DIN_DES_DOUT;
+	}
+
+	return data_flow_mode;
+}
+
+static void cc_hmac_authenc(struct aead_request *req, struct cc_hw_desc desc[],
+			    unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	int direct = req_ctx->gen_ctx.op_type;
+	unsigned int data_flow_mode =
+		cc_get_data_flow(direct, ctx->flow_mode,
+				 req_ctx->is_single_pass);
+
+	if (req_ctx->is_single_pass) {
+		/**
+		 * Single-pass flow
+		 */
+		cc_set_hmac_desc(req, desc, seq_size);
+		cc_set_cipher_desc(req, desc, seq_size);
+		cc_proc_header_desc(req, desc, seq_size);
+		cc_proc_cipher_desc(req, data_flow_mode, desc, seq_size);
+		cc_proc_scheme_desc(req, desc, seq_size);
+		cc_proc_digest_desc(req, desc, seq_size);
+		return;
+	}
+
+	/**
+	 * Double-pass flow
+	 * Fallback for unsupported single-pass modes,
+	 * i.e. using assoc. data of non-word-multiple
+	 */
+	if (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) {
+		/* encrypt first.. */
+		cc_proc_cipher(req, desc, seq_size, data_flow_mode);
+		/* authenc after..*/
+		cc_set_hmac_desc(req, desc, seq_size);
+		cc_proc_authen_desc(req, DIN_HASH, desc, seq_size, direct);
+		cc_proc_scheme_desc(req, desc, seq_size);
+		cc_proc_digest_desc(req, desc, seq_size);
+
+	} else { /*DECRYPT*/
+		/* authenc first..*/
+		cc_set_hmac_desc(req, desc, seq_size);
+		cc_proc_authen_desc(req, DIN_HASH, desc, seq_size, direct);
+		cc_proc_scheme_desc(req, desc, seq_size);
+		/* decrypt after.. */
+		cc_proc_cipher(req, desc, seq_size, data_flow_mode);
+		/* read the digest result with setting the completion bit
+		 * must be after the cipher operation
+		 */
+		cc_proc_digest_desc(req, desc, seq_size);
+	}
+}
+
+static void
+cc_xcbc_authenc(struct aead_request *req, struct cc_hw_desc desc[],
+		unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	int direct = req_ctx->gen_ctx.op_type;
+	unsigned int data_flow_mode =
+		cc_get_data_flow(direct, ctx->flow_mode,
+				 req_ctx->is_single_pass);
+
+	if (req_ctx->is_single_pass) {
+		/**
+		 * Single-pass flow
+		 */
+		cc_set_xcbc_desc(req, desc, seq_size);
+		cc_set_cipher_desc(req, desc, seq_size);
+		cc_proc_header_desc(req, desc, seq_size);
+		cc_proc_cipher_desc(req, data_flow_mode, desc, seq_size);
+		cc_proc_digest_desc(req, desc, seq_size);
+		return;
+	}
+
+	/**
+	 * Double-pass flow
+	 * Fallback for unsupported single-pass modes,
+	 * i.e. using assoc. data of non-word-multiple
+	 */
+	if (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) {
+		/* encrypt first.. */
+		cc_proc_cipher(req, desc, seq_size, data_flow_mode);
+		/* authenc after.. */
+		cc_set_xcbc_desc(req, desc, seq_size);
+		cc_proc_authen_desc(req, DIN_HASH, desc, seq_size, direct);
+		cc_proc_digest_desc(req, desc, seq_size);
+	} else { /*DECRYPT*/
+		/* authenc first.. */
+		cc_set_xcbc_desc(req, desc, seq_size);
+		cc_proc_authen_desc(req, DIN_HASH, desc, seq_size, direct);
+		/* decrypt after..*/
+		cc_proc_cipher(req, desc, seq_size, data_flow_mode);
+		/* read the digest result with setting the completion bit
+		 * must be after the cipher operation
+		 */
+		cc_proc_digest_desc(req, desc, seq_size);
+	}
+}
+
+static int validate_data_size(struct cc_aead_ctx *ctx,
+			      enum drv_crypto_direction direct,
+			      struct aead_request *req)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	unsigned int assoclen = req->assoclen;
+	unsigned int cipherlen = (direct == DRV_CRYPTO_DIRECTION_DECRYPT) ?
+			(req->cryptlen - ctx->authsize) : req->cryptlen;
+
+	if (direct == DRV_CRYPTO_DIRECTION_DECRYPT &&
+	    req->cryptlen < ctx->authsize)
+		goto data_size_err;
+
+	areq_ctx->is_single_pass = true; /*defaulted to fast flow*/
+
+	switch (ctx->flow_mode) {
+	case S_DIN_to_AES:
+		if (ctx->cipher_mode == DRV_CIPHER_CBC &&
+		    !IS_ALIGNED(cipherlen, AES_BLOCK_SIZE))
+			goto data_size_err;
+		if (ctx->cipher_mode == DRV_CIPHER_CCM)
+			break;
+		if (ctx->cipher_mode == DRV_CIPHER_GCTR) {
+			if (areq_ctx->plaintext_authenticate_only)
+				areq_ctx->is_single_pass = false;
+			break;
+		}
+
+		if (!IS_ALIGNED(assoclen, sizeof(u32)))
+			areq_ctx->is_single_pass = false;
+
+		if (ctx->cipher_mode == DRV_CIPHER_CTR &&
+		    !IS_ALIGNED(cipherlen, sizeof(u32)))
+			areq_ctx->is_single_pass = false;
+
+		break;
+	case S_DIN_to_DES:
+		if (!IS_ALIGNED(cipherlen, DES_BLOCK_SIZE))
+			goto data_size_err;
+		if (!IS_ALIGNED(assoclen, DES_BLOCK_SIZE))
+			areq_ctx->is_single_pass = false;
+		break;
+	default:
+		dev_err(dev, "Unexpected flow mode (%d)\n", ctx->flow_mode);
+		goto data_size_err;
+	}
+
+	return 0;
+
+data_size_err:
+	return -EINVAL;
+}
+
+static unsigned int format_ccm_a0(u8 *pa0_buff, u32 header_size)
+{
+	unsigned int len = 0;
+
+	if (header_size == 0)
+		return 0;
+
+	if (header_size < ((1UL << 16) - (1UL << 8))) {
+		len = 2;
+
+		pa0_buff[0] = (header_size >> 8) & 0xFF;
+		pa0_buff[1] = header_size & 0xFF;
+	} else {
+		len = 6;
+
+		pa0_buff[0] = 0xFF;
+		pa0_buff[1] = 0xFE;
+		pa0_buff[2] = (header_size >> 24) & 0xFF;
+		pa0_buff[3] = (header_size >> 16) & 0xFF;
+		pa0_buff[4] = (header_size >> 8) & 0xFF;
+		pa0_buff[5] = header_size & 0xFF;
+	}
+
+	return len;
+}
+
+static int set_msg_len(u8 *block, unsigned int msglen, unsigned int csize)
+{
+	__be32 data;
+
+	memset(block, 0, csize);
+	block += csize;
+
+	if (csize >= 4)
+		csize = 4;
+	else if (msglen > (1 << (8 * csize)))
+		return -EOVERFLOW;
+
+	data = cpu_to_be32(msglen);
+	memcpy(block - csize, (u8 *)&data + 4 - csize, csize);
+
+	return 0;
+}
+
+static int cc_ccm(struct aead_request *req, struct cc_hw_desc desc[],
+		  unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	unsigned int idx = *seq_size;
+	unsigned int cipher_flow_mode;
+	dma_addr_t mac_result;
+
+	if (req_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT) {
+		cipher_flow_mode = AES_to_HASH_and_DOUT;
+		mac_result = req_ctx->mac_buf_dma_addr;
+	} else { /* Encrypt */
+		cipher_flow_mode = AES_and_HASH;
+		mac_result = req_ctx->icv_dma_addr;
+	}
+
+	/* load key */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_CTR);
+	set_din_type(&desc[idx], DMA_DLLI, ctx->enckey_dma_addr,
+		     ((ctx->enc_keylen == 24) ?  CC_AES_KEY_SIZE_MAX :
+		      ctx->enc_keylen), NS_BIT);
+	set_key_size_aes(&desc[idx], ctx->enc_keylen);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+
+	/* load ctr state */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_CTR);
+	set_key_size_aes(&desc[idx], ctx->enc_keylen);
+	set_din_type(&desc[idx], DMA_DLLI,
+		     req_ctx->gen_ctx.iv_dma_addr, AES_BLOCK_SIZE, NS_BIT);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE1);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+
+	/* load MAC key */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_CBC_MAC);
+	set_din_type(&desc[idx], DMA_DLLI, ctx->enckey_dma_addr,
+		     ((ctx->enc_keylen == 24) ?  CC_AES_KEY_SIZE_MAX :
+		      ctx->enc_keylen), NS_BIT);
+	set_key_size_aes(&desc[idx], ctx->enc_keylen);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_aes_not_hash_mode(&desc[idx]);
+	idx++;
+
+	/* load MAC state */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_CBC_MAC);
+	set_key_size_aes(&desc[idx], ctx->enc_keylen);
+	set_din_type(&desc[idx], DMA_DLLI, req_ctx->mac_buf_dma_addr,
+		     AES_BLOCK_SIZE, NS_BIT);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_aes_not_hash_mode(&desc[idx]);
+	idx++;
+
+	/* process assoc data */
+	if (req->assoclen > 0) {
+		cc_set_assoc_desc(req, DIN_HASH, desc, &idx);
+	} else {
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_DLLI,
+			     sg_dma_address(&req_ctx->ccm_adata_sg),
+			     AES_BLOCK_SIZE + req_ctx->ccm_hdr_size, NS_BIT);
+		set_flow_mode(&desc[idx], DIN_HASH);
+		idx++;
+	}
+
+	/* process the cipher */
+	if (req_ctx->cryptlen)
+		cc_proc_cipher_desc(req, cipher_flow_mode, desc, &idx);
+
+	/* Read temporal MAC */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_CBC_MAC);
+	set_dout_dlli(&desc[idx], req_ctx->mac_buf_dma_addr, ctx->authsize,
+		      NS_BIT, 0);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+	set_cipher_config0(&desc[idx], HASH_DIGEST_RESULT_LITTLE_ENDIAN);
+	set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+	set_aes_not_hash_mode(&desc[idx]);
+	idx++;
+
+	/* load AES-CTR state (for last MAC calculation)*/
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_CTR);
+	set_cipher_config0(&desc[idx], DRV_CRYPTO_DIRECTION_ENCRYPT);
+	set_din_type(&desc[idx], DMA_DLLI, req_ctx->ccm_iv0_dma_addr,
+		     AES_BLOCK_SIZE, NS_BIT);
+	set_key_size_aes(&desc[idx], ctx->enc_keylen);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE1);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+
+	hw_desc_init(&desc[idx]);
+	set_din_no_dma(&desc[idx], 0, 0xfffff0);
+	set_dout_no_dma(&desc[idx], 0, 0, 1);
+	idx++;
+
+	/* encrypt the "T" value and store MAC in mac_state */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI, req_ctx->mac_buf_dma_addr,
+		     ctx->authsize, NS_BIT);
+	set_dout_dlli(&desc[idx], mac_result, ctx->authsize, NS_BIT, 1);
+	set_queue_last_ind(ctx->drvdata, &desc[idx]);
+	set_flow_mode(&desc[idx], DIN_AES_DOUT);
+	idx++;
+
+	*seq_size = idx;
+	return 0;
+}
+
+static int config_ccm_adata(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	//unsigned int size_of_a = 0, rem_a_size = 0;
+	unsigned int lp = req->iv[0];
+	/* Note: The code assume that req->iv[0] already contains the value
+	 * of L' of RFC3610
+	 */
+	unsigned int l = lp + 1;  /* This is L' of RFC 3610. */
+	unsigned int m = ctx->authsize;  /* This is M' of RFC 3610. */
+	u8 *b0 = req_ctx->ccm_config + CCM_B0_OFFSET;
+	u8 *a0 = req_ctx->ccm_config + CCM_A0_OFFSET;
+	u8 *ctr_count_0 = req_ctx->ccm_config + CCM_CTR_COUNT_0_OFFSET;
+	unsigned int cryptlen = (req_ctx->gen_ctx.op_type ==
+				 DRV_CRYPTO_DIRECTION_ENCRYPT) ?
+				req->cryptlen :
+				(req->cryptlen - ctx->authsize);
+	int rc;
+
+	memset(req_ctx->mac_buf, 0, AES_BLOCK_SIZE);
+	memset(req_ctx->ccm_config, 0, AES_BLOCK_SIZE * 3);
+
+	/* taken from crypto/ccm.c */
+	/* 2 <= L <= 8, so 1 <= L' <= 7. */
+	if (l < 2 || l > 8) {
+		dev_err(dev, "illegal iv value %X\n", req->iv[0]);
+		return -EINVAL;
+	}
+	memcpy(b0, req->iv, AES_BLOCK_SIZE);
+
+	/* format control info per RFC 3610 and
+	 * NIST Special Publication 800-38C
+	 */
+	*b0 |= (8 * ((m - 2) / 2));
+	if (req->assoclen > 0)
+		*b0 |= 64;  /* Enable bit 6 if Adata exists. */
+
+	rc = set_msg_len(b0 + 16 - l, cryptlen, l);  /* Write L'. */
+	if (rc) {
+		dev_err(dev, "message len overflow detected");
+		return rc;
+	}
+	 /* END of "taken from crypto/ccm.c" */
+
+	/* l(a) - size of associated data. */
+	req_ctx->ccm_hdr_size = format_ccm_a0(a0, req->assoclen);
+
+	memset(req->iv + 15 - req->iv[0], 0, req->iv[0] + 1);
+	req->iv[15] = 1;
+
+	memcpy(ctr_count_0, req->iv, AES_BLOCK_SIZE);
+	ctr_count_0[15] = 0;
+
+	return 0;
+}
+
+static void cc_proc_rfc4309_ccm(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+
+	/* L' */
+	memset(areq_ctx->ctr_iv, 0, AES_BLOCK_SIZE);
+	/* For RFC 4309, always use 4 bytes for message length
+	 * (at most 2^32-1 bytes).
+	 */
+	areq_ctx->ctr_iv[0] = 3;
+
+	/* In RFC 4309 there is an 11-bytes nonce+IV part,
+	 * that we build here.
+	 */
+	memcpy(areq_ctx->ctr_iv + CCM_BLOCK_NONCE_OFFSET, ctx->ctr_nonce,
+	       CCM_BLOCK_NONCE_SIZE);
+	memcpy(areq_ctx->ctr_iv + CCM_BLOCK_IV_OFFSET, req->iv,
+	       CCM_BLOCK_IV_SIZE);
+	req->iv = areq_ctx->ctr_iv;
+	req->assoclen -= CCM_BLOCK_IV_SIZE;
+}
+
+static void cc_set_ghash_desc(struct aead_request *req,
+			      struct cc_hw_desc desc[], unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	unsigned int idx = *seq_size;
+
+	/* load key to AES*/
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_ECB);
+	set_cipher_config0(&desc[idx], DRV_CRYPTO_DIRECTION_ENCRYPT);
+	set_din_type(&desc[idx], DMA_DLLI, ctx->enckey_dma_addr,
+		     ctx->enc_keylen, NS_BIT);
+	set_key_size_aes(&desc[idx], ctx->enc_keylen);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+
+	/* process one zero block to generate hkey */
+	hw_desc_init(&desc[idx]);
+	set_din_const(&desc[idx], 0x0, AES_BLOCK_SIZE);
+	set_dout_dlli(&desc[idx], req_ctx->hkey_dma_addr, AES_BLOCK_SIZE,
+		      NS_BIT, 0);
+	set_flow_mode(&desc[idx], DIN_AES_DOUT);
+	idx++;
+
+	/* Memory Barrier */
+	hw_desc_init(&desc[idx]);
+	set_din_no_dma(&desc[idx], 0, 0xfffff0);
+	set_dout_no_dma(&desc[idx], 0, 0, 1);
+	idx++;
+
+	/* Load GHASH subkey */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI, req_ctx->hkey_dma_addr,
+		     AES_BLOCK_SIZE, NS_BIT);
+	set_dout_no_dma(&desc[idx], 0, 0, 1);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_aes_not_hash_mode(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_HASH_HW_GHASH);
+	set_cipher_config1(&desc[idx], HASH_PADDING_ENABLED);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	idx++;
+
+	/* Configure Hash Engine to work with GHASH.
+	 * Since it was not possible to extend HASH submodes to add GHASH,
+	 * The following command is necessary in order to
+	 * select GHASH (according to HW designers)
+	 */
+	hw_desc_init(&desc[idx]);
+	set_din_no_dma(&desc[idx], 0, 0xfffff0);
+	set_dout_no_dma(&desc[idx], 0, 0, 1);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_aes_not_hash_mode(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_HASH_HW_GHASH);
+	set_cipher_do(&desc[idx], 1); //1=AES_SK RKEK
+	set_cipher_config0(&desc[idx], DRV_CRYPTO_DIRECTION_ENCRYPT);
+	set_cipher_config1(&desc[idx], HASH_PADDING_ENABLED);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	idx++;
+
+	/* Load GHASH initial STATE (which is 0). (for any hash there is an
+	 * initial state)
+	 */
+	hw_desc_init(&desc[idx]);
+	set_din_const(&desc[idx], 0x0, AES_BLOCK_SIZE);
+	set_dout_no_dma(&desc[idx], 0, 0, 1);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_aes_not_hash_mode(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_HASH_HW_GHASH);
+	set_cipher_config1(&desc[idx], HASH_PADDING_ENABLED);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	idx++;
+
+	*seq_size = idx;
+}
+
+static void cc_set_gctr_desc(struct aead_request *req, struct cc_hw_desc desc[],
+			     unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	unsigned int idx = *seq_size;
+
+	/* load key to AES*/
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_GCTR);
+	set_cipher_config0(&desc[idx], DRV_CRYPTO_DIRECTION_ENCRYPT);
+	set_din_type(&desc[idx], DMA_DLLI, ctx->enckey_dma_addr,
+		     ctx->enc_keylen, NS_BIT);
+	set_key_size_aes(&desc[idx], ctx->enc_keylen);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+
+	if (req_ctx->cryptlen && !req_ctx->plaintext_authenticate_only) {
+		/* load AES/CTR initial CTR value inc by 2*/
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], DRV_CIPHER_GCTR);
+		set_key_size_aes(&desc[idx], ctx->enc_keylen);
+		set_din_type(&desc[idx], DMA_DLLI,
+			     req_ctx->gcm_iv_inc2_dma_addr, AES_BLOCK_SIZE,
+			     NS_BIT);
+		set_cipher_config0(&desc[idx], DRV_CRYPTO_DIRECTION_ENCRYPT);
+		set_setup_mode(&desc[idx], SETUP_LOAD_STATE1);
+		set_flow_mode(&desc[idx], S_DIN_to_AES);
+		idx++;
+	}
+
+	*seq_size = idx;
+}
+
+static void cc_proc_gcm_result(struct aead_request *req,
+			       struct cc_hw_desc desc[],
+			       unsigned int *seq_size)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	dma_addr_t mac_result;
+	unsigned int idx = *seq_size;
+
+	if (req_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT) {
+		mac_result = req_ctx->mac_buf_dma_addr;
+	} else { /* Encrypt */
+		mac_result = req_ctx->icv_dma_addr;
+	}
+
+	/* process(ghash) gcm_block_len */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI, req_ctx->gcm_block_len_dma_addr,
+		     AES_BLOCK_SIZE, NS_BIT);
+	set_flow_mode(&desc[idx], DIN_HASH);
+	idx++;
+
+	/* Store GHASH state after GHASH(Associated Data + Cipher +LenBlock) */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_HASH_HW_GHASH);
+	set_din_no_dma(&desc[idx], 0, 0xfffff0);
+	set_dout_dlli(&desc[idx], req_ctx->mac_buf_dma_addr, AES_BLOCK_SIZE,
+		      NS_BIT, 0);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+	set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+	set_aes_not_hash_mode(&desc[idx]);
+
+	idx++;
+
+	/* load AES/CTR initial CTR value inc by 1*/
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_GCTR);
+	set_key_size_aes(&desc[idx], ctx->enc_keylen);
+	set_din_type(&desc[idx], DMA_DLLI, req_ctx->gcm_iv_inc1_dma_addr,
+		     AES_BLOCK_SIZE, NS_BIT);
+	set_cipher_config0(&desc[idx], DRV_CRYPTO_DIRECTION_ENCRYPT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE1);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+
+	/* Memory Barrier */
+	hw_desc_init(&desc[idx]);
+	set_din_no_dma(&desc[idx], 0, 0xfffff0);
+	set_dout_no_dma(&desc[idx], 0, 0, 1);
+	idx++;
+
+	/* process GCTR on stored GHASH and store MAC in mac_state*/
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_GCTR);
+	set_din_type(&desc[idx], DMA_DLLI, req_ctx->mac_buf_dma_addr,
+		     AES_BLOCK_SIZE, NS_BIT);
+	set_dout_dlli(&desc[idx], mac_result, ctx->authsize, NS_BIT, 1);
+	set_queue_last_ind(ctx->drvdata, &desc[idx]);
+	set_flow_mode(&desc[idx], DIN_AES_DOUT);
+	idx++;
+
+	*seq_size = idx;
+}
+
+static int cc_gcm(struct aead_request *req, struct cc_hw_desc desc[],
+		  unsigned int *seq_size)
+{
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	unsigned int cipher_flow_mode;
+
+	if (req_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT) {
+		cipher_flow_mode = AES_and_HASH;
+	} else { /* Encrypt */
+		cipher_flow_mode = AES_to_HASH_and_DOUT;
+	}
+
+	//in RFC4543 no data to encrypt. just copy data from src to dest.
+	if (req_ctx->plaintext_authenticate_only) {
+		cc_proc_cipher_desc(req, BYPASS, desc, seq_size);
+		cc_set_ghash_desc(req, desc, seq_size);
+		/* process(ghash) assoc data */
+		cc_set_assoc_desc(req, DIN_HASH, desc, seq_size);
+		cc_set_gctr_desc(req, desc, seq_size);
+		cc_proc_gcm_result(req, desc, seq_size);
+		return 0;
+	}
+
+	// for gcm and rfc4106.
+	cc_set_ghash_desc(req, desc, seq_size);
+	/* process(ghash) assoc data */
+	if (req->assoclen > 0)
+		cc_set_assoc_desc(req, DIN_HASH, desc, seq_size);
+	cc_set_gctr_desc(req, desc, seq_size);
+	/* process(gctr+ghash) */
+	if (req_ctx->cryptlen)
+		cc_proc_cipher_desc(req, cipher_flow_mode, desc, seq_size);
+	cc_proc_gcm_result(req, desc, seq_size);
+
+	return 0;
+}
+
+static int config_gcm_context(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *req_ctx = aead_request_ctx(req);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	unsigned int cryptlen = (req_ctx->gen_ctx.op_type ==
+				 DRV_CRYPTO_DIRECTION_ENCRYPT) ?
+				req->cryptlen :
+				(req->cryptlen - ctx->authsize);
+	__be32 counter = cpu_to_be32(2);
+
+	dev_dbg(dev, "%s() cryptlen = %d, req->assoclen = %d ctx->authsize = %d\n",
+		__func__, cryptlen, req->assoclen, ctx->authsize);
+
+	memset(req_ctx->hkey, 0, AES_BLOCK_SIZE);
+
+	memset(req_ctx->mac_buf, 0, AES_BLOCK_SIZE);
+
+	memcpy(req->iv + 12, &counter, 4);
+	memcpy(req_ctx->gcm_iv_inc2, req->iv, 16);
+
+	counter = cpu_to_be32(1);
+	memcpy(req->iv + 12, &counter, 4);
+	memcpy(req_ctx->gcm_iv_inc1, req->iv, 16);
+
+	if (!req_ctx->plaintext_authenticate_only) {
+		__be64 temp64;
+
+		temp64 = cpu_to_be64(req->assoclen * 8);
+		memcpy(&req_ctx->gcm_len_block.len_a, &temp64, sizeof(temp64));
+		temp64 = cpu_to_be64(cryptlen * 8);
+		memcpy(&req_ctx->gcm_len_block.len_c, &temp64, 8);
+	} else {
+		/* rfc4543=>  all data(AAD,IV,Plain) are considered additional
+		 * data that is nothing is encrypted.
+		 */
+		__be64 temp64;
+
+		temp64 = cpu_to_be64((req->assoclen + GCM_BLOCK_RFC4_IV_SIZE +
+				      cryptlen) * 8);
+		memcpy(&req_ctx->gcm_len_block.len_a, &temp64, sizeof(temp64));
+		temp64 = 0;
+		memcpy(&req_ctx->gcm_len_block.len_c, &temp64, 8);
+	}
+
+	return 0;
+}
+
+static void cc_proc_rfc4_gcm(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+
+	memcpy(areq_ctx->ctr_iv + GCM_BLOCK_RFC4_NONCE_OFFSET,
+	       ctx->ctr_nonce, GCM_BLOCK_RFC4_NONCE_SIZE);
+	memcpy(areq_ctx->ctr_iv + GCM_BLOCK_RFC4_IV_OFFSET, req->iv,
+	       GCM_BLOCK_RFC4_IV_SIZE);
+	req->iv = areq_ctx->ctr_iv;
+	req->assoclen -= GCM_BLOCK_RFC4_IV_SIZE;
+}
+
+static int cc_proc_aead(struct aead_request *req,
+			enum drv_crypto_direction direct)
+{
+	int rc = 0;
+	int seq_len = 0;
+	struct cc_hw_desc desc[MAX_AEAD_PROCESS_SEQ];
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	struct cc_crypto_req cc_req = {};
+
+	dev_dbg(dev, "%s context=%p req=%p iv=%p src=%p src_ofs=%d dst=%p dst_ofs=%d cryptolen=%d\n",
+		((direct == DRV_CRYPTO_DIRECTION_ENCRYPT) ? "Enc" : "Dec"),
+		ctx, req, req->iv, sg_virt(req->src), req->src->offset,
+		sg_virt(req->dst), req->dst->offset, req->cryptlen);
+
+	/* STAT_PHASE_0: Init and sanity checks */
+
+	/* Check data length according to mode */
+	if (validate_data_size(ctx, direct, req)) {
+		dev_err(dev, "Unsupported crypt/assoc len %d/%d.\n",
+			req->cryptlen, req->assoclen);
+		crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_BLOCK_LEN);
+		return -EINVAL;
+	}
+
+	/* Setup request structure */
+	cc_req.user_cb = (void *)cc_aead_complete;
+	cc_req.user_arg = (void *)req;
+
+	/* Setup request context */
+	areq_ctx->gen_ctx.op_type = direct;
+	areq_ctx->req_authsize = ctx->authsize;
+	areq_ctx->cipher_mode = ctx->cipher_mode;
+
+	/* STAT_PHASE_1: Map buffers */
+
+	if (ctx->cipher_mode == DRV_CIPHER_CTR) {
+		/* Build CTR IV - Copy nonce from last 4 bytes in
+		 * CTR key to first 4 bytes in CTR IV
+		 */
+		memcpy(areq_ctx->ctr_iv, ctx->ctr_nonce,
+		       CTR_RFC3686_NONCE_SIZE);
+		if (!areq_ctx->backup_giv) /*User none-generated IV*/
+			memcpy(areq_ctx->ctr_iv + CTR_RFC3686_NONCE_SIZE,
+			       req->iv, CTR_RFC3686_IV_SIZE);
+		/* Initialize counter portion of counter block */
+		*(__be32 *)(areq_ctx->ctr_iv + CTR_RFC3686_NONCE_SIZE +
+			    CTR_RFC3686_IV_SIZE) = cpu_to_be32(1);
+
+		/* Replace with counter iv */
+		req->iv = areq_ctx->ctr_iv;
+		areq_ctx->hw_iv_size = CTR_RFC3686_BLOCK_SIZE;
+	} else if ((ctx->cipher_mode == DRV_CIPHER_CCM) ||
+		   (ctx->cipher_mode == DRV_CIPHER_GCTR)) {
+		areq_ctx->hw_iv_size = AES_BLOCK_SIZE;
+		if (areq_ctx->ctr_iv != req->iv) {
+			memcpy(areq_ctx->ctr_iv, req->iv,
+			       crypto_aead_ivsize(tfm));
+			req->iv = areq_ctx->ctr_iv;
+		}
+	}  else {
+		areq_ctx->hw_iv_size = crypto_aead_ivsize(tfm);
+	}
+
+	if (ctx->cipher_mode == DRV_CIPHER_CCM) {
+		rc = config_ccm_adata(req);
+		if (rc) {
+			dev_dbg(dev, "config_ccm_adata() returned with a failure %d!",
+				rc);
+			goto exit;
+		}
+	} else {
+		areq_ctx->ccm_hdr_size = ccm_header_size_null;
+	}
+
+	if (ctx->cipher_mode == DRV_CIPHER_GCTR) {
+		rc = config_gcm_context(req);
+		if (rc) {
+			dev_dbg(dev, "config_gcm_context() returned with a failure %d!",
+				rc);
+			goto exit;
+		}
+	}
+
+	rc = cc_map_aead_request(ctx->drvdata, req);
+	if (rc) {
+		dev_err(dev, "map_request() failed\n");
+		goto exit;
+	}
+
+	/* do we need to generate IV? */
+	if (areq_ctx->backup_giv) {
+		/* set the DMA mapped IV address*/
+		if (ctx->cipher_mode == DRV_CIPHER_CTR) {
+			cc_req.ivgen_dma_addr[0] =
+				areq_ctx->gen_ctx.iv_dma_addr +
+				CTR_RFC3686_NONCE_SIZE;
+			cc_req.ivgen_dma_addr_len = 1;
+		} else if (ctx->cipher_mode == DRV_CIPHER_CCM) {
+			/* In ccm, the IV needs to exist both inside B0 and
+			 * inside the counter.It is also copied to iv_dma_addr
+			 * for other reasons (like returning it to the user).
+			 * So, using 3 (identical) IV outputs.
+			 */
+			cc_req.ivgen_dma_addr[0] =
+				areq_ctx->gen_ctx.iv_dma_addr +
+				CCM_BLOCK_IV_OFFSET;
+			cc_req.ivgen_dma_addr[1] =
+				sg_dma_address(&areq_ctx->ccm_adata_sg) +
+				CCM_B0_OFFSET + CCM_BLOCK_IV_OFFSET;
+			cc_req.ivgen_dma_addr[2] =
+				sg_dma_address(&areq_ctx->ccm_adata_sg) +
+				CCM_CTR_COUNT_0_OFFSET + CCM_BLOCK_IV_OFFSET;
+			cc_req.ivgen_dma_addr_len = 3;
+		} else {
+			cc_req.ivgen_dma_addr[0] =
+				areq_ctx->gen_ctx.iv_dma_addr;
+			cc_req.ivgen_dma_addr_len = 1;
+		}
+
+		/* set the IV size (8/16 B long)*/
+		cc_req.ivgen_size = crypto_aead_ivsize(tfm);
+	}
+
+	/* STAT_PHASE_2: Create sequence */
+
+	/* Load MLLI tables to SRAM if necessary */
+	cc_mlli_to_sram(req, desc, &seq_len);
+
+	/*TODO: move seq len by reference */
+	switch (ctx->auth_mode) {
+	case DRV_HASH_SHA1:
+	case DRV_HASH_SHA256:
+		cc_hmac_authenc(req, desc, &seq_len);
+		break;
+	case DRV_HASH_XCBC_MAC:
+		cc_xcbc_authenc(req, desc, &seq_len);
+		break;
+	case DRV_HASH_NULL:
+		if (ctx->cipher_mode == DRV_CIPHER_CCM)
+			cc_ccm(req, desc, &seq_len);
+		if (ctx->cipher_mode == DRV_CIPHER_GCTR)
+			cc_gcm(req, desc, &seq_len);
+		break;
+	default:
+		dev_err(dev, "Unsupported authenc (%d)\n", ctx->auth_mode);
+		cc_unmap_aead_request(dev, req);
+		rc = -ENOTSUPP;
+		goto exit;
+	}
+
+	/* STAT_PHASE_3: Lock HW and push sequence */
+
+	rc = cc_send_request(ctx->drvdata, &cc_req, desc, seq_len, &req->base);
+
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+		cc_unmap_aead_request(dev, req);
+	}
+
+exit:
+	return rc;
+}
+
+static int cc_aead_encrypt(struct aead_request *req)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	int rc;
+
+	/* No generated IV required */
+	areq_ctx->backup_iv = req->iv;
+	areq_ctx->backup_giv = NULL;
+	areq_ctx->is_gcm4543 = false;
+
+	areq_ctx->plaintext_authenticate_only = false;
+
+	rc = cc_proc_aead(req, DRV_CRYPTO_DIRECTION_ENCRYPT);
+	if (rc != -EINPROGRESS && rc != -EBUSY)
+		req->iv = areq_ctx->backup_iv;
+
+	return rc;
+}
+
+static int cc_rfc4309_ccm_encrypt(struct aead_request *req)
+{
+	/* Very similar to cc_aead_encrypt() above. */
+
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	int rc = -EINVAL;
+
+	if (!valid_assoclen(req)) {
+		dev_err(dev, "invalid Assoclen:%u\n", req->assoclen);
+		goto out;
+	}
+
+	/* No generated IV required */
+	areq_ctx->backup_iv = req->iv;
+	areq_ctx->backup_giv = NULL;
+	areq_ctx->is_gcm4543 = true;
+
+	cc_proc_rfc4309_ccm(req);
+
+	rc = cc_proc_aead(req, DRV_CRYPTO_DIRECTION_ENCRYPT);
+	if (rc != -EINPROGRESS && rc != -EBUSY)
+		req->iv = areq_ctx->backup_iv;
+out:
+	return rc;
+}
+
+static int cc_aead_decrypt(struct aead_request *req)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	int rc;
+
+	/* No generated IV required */
+	areq_ctx->backup_iv = req->iv;
+	areq_ctx->backup_giv = NULL;
+	areq_ctx->is_gcm4543 = false;
+
+	areq_ctx->plaintext_authenticate_only = false;
+
+	rc = cc_proc_aead(req, DRV_CRYPTO_DIRECTION_DECRYPT);
+	if (rc != -EINPROGRESS && rc != -EBUSY)
+		req->iv = areq_ctx->backup_iv;
+
+	return rc;
+}
+
+static int cc_rfc4309_ccm_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	int rc = -EINVAL;
+
+	if (!valid_assoclen(req)) {
+		dev_err(dev, "invalid Assoclen:%u\n", req->assoclen);
+		goto out;
+	}
+
+	/* No generated IV required */
+	areq_ctx->backup_iv = req->iv;
+	areq_ctx->backup_giv = NULL;
+
+	areq_ctx->is_gcm4543 = true;
+	cc_proc_rfc4309_ccm(req);
+
+	rc = cc_proc_aead(req, DRV_CRYPTO_DIRECTION_DECRYPT);
+	if (rc != -EINPROGRESS && rc != -EBUSY)
+		req->iv = areq_ctx->backup_iv;
+
+out:
+	return rc;
+}
+
+static int cc_rfc4106_gcm_setkey(struct crypto_aead *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	dev_dbg(dev, "%s()  keylen %d, key %p\n", __func__, keylen, key);
+
+	if (keylen < 4)
+		return -EINVAL;
+
+	keylen -= 4;
+	memcpy(ctx->ctr_nonce, key + keylen, 4);
+
+	return cc_aead_setkey(tfm, key, keylen);
+}
+
+static int cc_rfc4543_gcm_setkey(struct crypto_aead *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	dev_dbg(dev, "%s()  keylen %d, key %p\n", __func__, keylen, key);
+
+	if (keylen < 4)
+		return -EINVAL;
+
+	keylen -= 4;
+	memcpy(ctx->ctr_nonce, key + keylen, 4);
+
+	return cc_aead_setkey(tfm, key, keylen);
+}
+
+static int cc_gcm_setauthsize(struct crypto_aead *authenc,
+			      unsigned int authsize)
+{
+	switch (authsize) {
+	case 4:
+	case 8:
+	case 12:
+	case 13:
+	case 14:
+	case 15:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return cc_aead_setauthsize(authenc, authsize);
+}
+
+static int cc_rfc4106_gcm_setauthsize(struct crypto_aead *authenc,
+				      unsigned int authsize)
+{
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(authenc);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	dev_dbg(dev, "authsize %d\n", authsize);
+
+	switch (authsize) {
+	case 8:
+	case 12:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return cc_aead_setauthsize(authenc, authsize);
+}
+
+static int cc_rfc4543_gcm_setauthsize(struct crypto_aead *authenc,
+				      unsigned int authsize)
+{
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(authenc);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	dev_dbg(dev, "authsize %d\n", authsize);
+
+	if (authsize != 16)
+		return -EINVAL;
+
+	return cc_aead_setauthsize(authenc, authsize);
+}
+
+static int cc_rfc4106_gcm_encrypt(struct aead_request *req)
+{
+	/* Very similar to cc_aead_encrypt() above. */
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	int rc = -EINVAL;
+
+	if (!valid_assoclen(req)) {
+		dev_err(dev, "invalid Assoclen:%u\n", req->assoclen);
+		goto out;
+	}
+
+	/* No generated IV required */
+	areq_ctx->backup_iv = req->iv;
+	areq_ctx->backup_giv = NULL;
+
+	areq_ctx->plaintext_authenticate_only = false;
+
+	cc_proc_rfc4_gcm(req);
+	areq_ctx->is_gcm4543 = true;
+
+	rc = cc_proc_aead(req, DRV_CRYPTO_DIRECTION_ENCRYPT);
+	if (rc != -EINPROGRESS && rc != -EBUSY)
+		req->iv = areq_ctx->backup_iv;
+out:
+	return rc;
+}
+
+static int cc_rfc4543_gcm_encrypt(struct aead_request *req)
+{
+	/* Very similar to cc_aead_encrypt() above. */
+
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	int rc;
+
+	//plaintext is not encryped with rfc4543
+	areq_ctx->plaintext_authenticate_only = true;
+
+	/* No generated IV required */
+	areq_ctx->backup_iv = req->iv;
+	areq_ctx->backup_giv = NULL;
+
+	cc_proc_rfc4_gcm(req);
+	areq_ctx->is_gcm4543 = true;
+
+	rc = cc_proc_aead(req, DRV_CRYPTO_DIRECTION_ENCRYPT);
+	if (rc != -EINPROGRESS && rc != -EBUSY)
+		req->iv = areq_ctx->backup_iv;
+
+	return rc;
+}
+
+static int cc_rfc4106_gcm_decrypt(struct aead_request *req)
+{
+	/* Very similar to cc_aead_decrypt() above. */
+
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	int rc = -EINVAL;
+
+	if (!valid_assoclen(req)) {
+		dev_err(dev, "invalid Assoclen:%u\n", req->assoclen);
+		goto out;
+	}
+
+	/* No generated IV required */
+	areq_ctx->backup_iv = req->iv;
+	areq_ctx->backup_giv = NULL;
+
+	areq_ctx->plaintext_authenticate_only = false;
+
+	cc_proc_rfc4_gcm(req);
+	areq_ctx->is_gcm4543 = true;
+
+	rc = cc_proc_aead(req, DRV_CRYPTO_DIRECTION_DECRYPT);
+	if (rc != -EINPROGRESS && rc != -EBUSY)
+		req->iv = areq_ctx->backup_iv;
+out:
+	return rc;
+}
+
+static int cc_rfc4543_gcm_decrypt(struct aead_request *req)
+{
+	/* Very similar to cc_aead_decrypt() above. */
+
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	int rc;
+
+	//plaintext is not decryped with rfc4543
+	areq_ctx->plaintext_authenticate_only = true;
+
+	/* No generated IV required */
+	areq_ctx->backup_iv = req->iv;
+	areq_ctx->backup_giv = NULL;
+
+	cc_proc_rfc4_gcm(req);
+	areq_ctx->is_gcm4543 = true;
+
+	rc = cc_proc_aead(req, DRV_CRYPTO_DIRECTION_DECRYPT);
+	if (rc != -EINPROGRESS && rc != -EBUSY)
+		req->iv = areq_ctx->backup_iv;
+
+	return rc;
+}
+
+/* aead alg */
+static struct cc_alg_template aead_algs[] = {
+	{
+		.name = "authenc(hmac(sha1),cbc(aes))",
+		.driver_name = "authenc-hmac-sha1-cbc-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_aead_setkey,
+			.setauthsize = cc_aead_setauthsize,
+			.encrypt = cc_aead_encrypt,
+			.decrypt = cc_aead_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CBC,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_SHA1,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "authenc(hmac(sha1),cbc(des3_ede))",
+		.driver_name = "authenc-hmac-sha1-cbc-des3-ccree",
+		.blocksize = DES3_EDE_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_aead_setkey,
+			.setauthsize = cc_aead_setauthsize,
+			.encrypt = cc_aead_encrypt,
+			.decrypt = cc_aead_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CBC,
+		.flow_mode = S_DIN_to_DES,
+		.auth_mode = DRV_HASH_SHA1,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "authenc(hmac(sha256),cbc(aes))",
+		.driver_name = "authenc-hmac-sha256-cbc-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_aead_setkey,
+			.setauthsize = cc_aead_setauthsize,
+			.encrypt = cc_aead_encrypt,
+			.decrypt = cc_aead_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CBC,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_SHA256,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "authenc(hmac(sha256),cbc(des3_ede))",
+		.driver_name = "authenc-hmac-sha256-cbc-des3-ccree",
+		.blocksize = DES3_EDE_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_aead_setkey,
+			.setauthsize = cc_aead_setauthsize,
+			.encrypt = cc_aead_encrypt,
+			.decrypt = cc_aead_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CBC,
+		.flow_mode = S_DIN_to_DES,
+		.auth_mode = DRV_HASH_SHA256,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "authenc(xcbc(aes),cbc(aes))",
+		.driver_name = "authenc-xcbc-aes-cbc-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_aead_setkey,
+			.setauthsize = cc_aead_setauthsize,
+			.encrypt = cc_aead_encrypt,
+			.decrypt = cc_aead_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CBC,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_XCBC_MAC,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "authenc(hmac(sha1),rfc3686(ctr(aes)))",
+		.driver_name = "authenc-hmac-sha1-rfc3686-ctr-aes-ccree",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_aead_setkey,
+			.setauthsize = cc_aead_setauthsize,
+			.encrypt = cc_aead_encrypt,
+			.decrypt = cc_aead_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CTR,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_SHA1,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "authenc(hmac(sha256),rfc3686(ctr(aes)))",
+		.driver_name = "authenc-hmac-sha256-rfc3686-ctr-aes-ccree",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_aead_setkey,
+			.setauthsize = cc_aead_setauthsize,
+			.encrypt = cc_aead_encrypt,
+			.decrypt = cc_aead_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CTR,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_SHA256,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "authenc(xcbc(aes),rfc3686(ctr(aes)))",
+		.driver_name = "authenc-xcbc-aes-rfc3686-ctr-aes-ccree",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_aead_setkey,
+			.setauthsize = cc_aead_setauthsize,
+			.encrypt = cc_aead_encrypt,
+			.decrypt = cc_aead_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = CTR_RFC3686_IV_SIZE,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CTR,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_XCBC_MAC,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "ccm(aes)",
+		.driver_name = "ccm-aes-ccree",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_aead_setkey,
+			.setauthsize = cc_ccm_setauthsize,
+			.encrypt = cc_aead_encrypt,
+			.decrypt = cc_aead_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CCM,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_NULL,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "rfc4309(ccm(aes))",
+		.driver_name = "rfc4309-ccm-aes-ccree",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_rfc4309_ccm_setkey,
+			.setauthsize = cc_rfc4309_ccm_setauthsize,
+			.encrypt = cc_rfc4309_ccm_encrypt,
+			.decrypt = cc_rfc4309_ccm_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = CCM_BLOCK_IV_SIZE,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CCM,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_NULL,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "gcm(aes)",
+		.driver_name = "gcm-aes-ccree",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_aead_setkey,
+			.setauthsize = cc_gcm_setauthsize,
+			.encrypt = cc_aead_encrypt,
+			.decrypt = cc_aead_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = 12,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_GCTR,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_NULL,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "rfc4106(gcm(aes))",
+		.driver_name = "rfc4106-gcm-aes-ccree",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_rfc4106_gcm_setkey,
+			.setauthsize = cc_rfc4106_gcm_setauthsize,
+			.encrypt = cc_rfc4106_gcm_encrypt,
+			.decrypt = cc_rfc4106_gcm_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = GCM_BLOCK_RFC4_IV_SIZE,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_GCTR,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_NULL,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "rfc4543(gcm(aes))",
+		.driver_name = "rfc4543-gcm-aes-ccree",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = cc_rfc4543_gcm_setkey,
+			.setauthsize = cc_rfc4543_gcm_setauthsize,
+			.encrypt = cc_rfc4543_gcm_encrypt,
+			.decrypt = cc_rfc4543_gcm_decrypt,
+			.init = cc_aead_init,
+			.exit = cc_aead_exit,
+			.ivsize = GCM_BLOCK_RFC4_IV_SIZE,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_GCTR,
+		.flow_mode = S_DIN_to_AES,
+		.auth_mode = DRV_HASH_NULL,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+};
+
+static struct cc_crypto_alg *cc_create_aead_alg(struct cc_alg_template *tmpl,
+						struct device *dev)
+{
+	struct cc_crypto_alg *t_alg;
+	struct aead_alg *alg;
+
+	t_alg = kzalloc(sizeof(*t_alg), GFP_KERNEL);
+	if (!t_alg)
+		return ERR_PTR(-ENOMEM);
+
+	alg = &tmpl->template_aead;
+
+	snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name);
+	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+		 tmpl->driver_name);
+	alg->base.cra_module = THIS_MODULE;
+	alg->base.cra_priority = CC_CRA_PRIO;
+
+	alg->base.cra_ctxsize = sizeof(struct cc_aead_ctx);
+	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY |
+			 tmpl->type;
+	alg->init = cc_aead_init;
+	alg->exit = cc_aead_exit;
+
+	t_alg->aead_alg = *alg;
+
+	t_alg->cipher_mode = tmpl->cipher_mode;
+	t_alg->flow_mode = tmpl->flow_mode;
+	t_alg->auth_mode = tmpl->auth_mode;
+
+	return t_alg;
+}
+
+int cc_aead_free(struct cc_drvdata *drvdata)
+{
+	struct cc_crypto_alg *t_alg, *n;
+	struct cc_aead_handle *aead_handle =
+		(struct cc_aead_handle *)drvdata->aead_handle;
+
+	if (aead_handle) {
+		/* Remove registered algs */
+		list_for_each_entry_safe(t_alg, n, &aead_handle->aead_list,
+					 entry) {
+			crypto_unregister_aead(&t_alg->aead_alg);
+			list_del(&t_alg->entry);
+			kfree(t_alg);
+		}
+		kfree(aead_handle);
+		drvdata->aead_handle = NULL;
+	}
+
+	return 0;
+}
+
+int cc_aead_alloc(struct cc_drvdata *drvdata)
+{
+	struct cc_aead_handle *aead_handle;
+	struct cc_crypto_alg *t_alg;
+	int rc = -ENOMEM;
+	int alg;
+	struct device *dev = drvdata_to_dev(drvdata);
+
+	aead_handle = kmalloc(sizeof(*aead_handle), GFP_KERNEL);
+	if (!aead_handle) {
+		rc = -ENOMEM;
+		goto fail0;
+	}
+
+	INIT_LIST_HEAD(&aead_handle->aead_list);
+	drvdata->aead_handle = aead_handle;
+
+	aead_handle->sram_workspace_addr = cc_sram_alloc(drvdata,
+							 MAX_HMAC_DIGEST_SIZE);
+
+	if (aead_handle->sram_workspace_addr == NULL_SRAM_ADDR) {
+		dev_err(dev, "SRAM pool exhausted\n");
+		rc = -ENOMEM;
+		goto fail1;
+	}
+
+	/* Linux crypto */
+	for (alg = 0; alg < ARRAY_SIZE(aead_algs); alg++) {
+		if (aead_algs[alg].min_hw_rev > drvdata->hw_rev)
+			continue;
+
+		t_alg = cc_create_aead_alg(&aead_algs[alg], dev);
+		if (IS_ERR(t_alg)) {
+			rc = PTR_ERR(t_alg);
+			dev_err(dev, "%s alg allocation failed\n",
+				aead_algs[alg].driver_name);
+			goto fail1;
+		}
+		t_alg->drvdata = drvdata;
+		rc = crypto_register_aead(&t_alg->aead_alg);
+		if (rc) {
+			dev_err(dev, "%s alg registration failed\n",
+				t_alg->aead_alg.base.cra_driver_name);
+			goto fail2;
+		} else {
+			list_add_tail(&t_alg->entry, &aead_handle->aead_list);
+			dev_dbg(dev, "Registered %s\n",
+				t_alg->aead_alg.base.cra_driver_name);
+		}
+	}
+
+	return 0;
+
+fail2:
+	kfree(t_alg);
+fail1:
+	cc_aead_free(drvdata);
+fail0:
+	return rc;
+}
diff --git a/drivers/crypto/ccree/cc_aead.h b/drivers/crypto/ccree/cc_aead.h
new file mode 100644
index 000000000000..5edf3b351fa4
--- /dev/null
+++ b/drivers/crypto/ccree/cc_aead.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+/* \file cc_aead.h
+ * ARM CryptoCell AEAD Crypto API
+ */
+
+#ifndef __CC_AEAD_H__
+#define __CC_AEAD_H__
+
+#include <linux/kernel.h>
+#include <crypto/algapi.h>
+#include <crypto/ctr.h>
+
+/* mac_cmp - HW writes 8 B but all bytes hold the same value */
+#define ICV_CMP_SIZE 8
+#define CCM_CONFIG_BUF_SIZE (AES_BLOCK_SIZE * 3)
+#define MAX_MAC_SIZE SHA256_DIGEST_SIZE
+
+/* defines for AES GCM configuration buffer */
+#define GCM_BLOCK_LEN_SIZE 8
+
+#define GCM_BLOCK_RFC4_IV_OFFSET	4
+#define GCM_BLOCK_RFC4_IV_SIZE		8  /* IV size for rfc's */
+#define GCM_BLOCK_RFC4_NONCE_OFFSET	0
+#define GCM_BLOCK_RFC4_NONCE_SIZE	4
+
+/* Offsets into AES CCM configuration buffer */
+#define CCM_B0_OFFSET 0
+#define CCM_A0_OFFSET 16
+#define CCM_CTR_COUNT_0_OFFSET 32
+/* CCM B0 and CTR_COUNT constants. */
+#define CCM_BLOCK_NONCE_OFFSET 1  /* Nonce offset inside B0 and CTR_COUNT */
+#define CCM_BLOCK_NONCE_SIZE   3  /* Nonce size inside B0 and CTR_COUNT */
+#define CCM_BLOCK_IV_OFFSET    4  /* IV offset inside B0 and CTR_COUNT */
+#define CCM_BLOCK_IV_SIZE      8  /* IV size inside B0 and CTR_COUNT */
+
+enum aead_ccm_header_size {
+	ccm_header_size_null = -1,
+	ccm_header_size_zero = 0,
+	ccm_header_size_2 = 2,
+	ccm_header_size_6 = 6,
+	ccm_header_size_max = S32_MAX
+};
+
+struct aead_req_ctx {
+	/* Allocate cache line although only 4 bytes are needed to
+	 *  assure next field falls @ cache line
+	 *  Used for both: digest HW compare and CCM/GCM MAC value
+	 */
+	u8 mac_buf[MAX_MAC_SIZE] ____cacheline_aligned;
+	u8 ctr_iv[AES_BLOCK_SIZE] ____cacheline_aligned;
+
+	//used in gcm
+	u8 gcm_iv_inc1[AES_BLOCK_SIZE] ____cacheline_aligned;
+	u8 gcm_iv_inc2[AES_BLOCK_SIZE] ____cacheline_aligned;
+	u8 hkey[AES_BLOCK_SIZE] ____cacheline_aligned;
+	struct {
+		u8 len_a[GCM_BLOCK_LEN_SIZE] ____cacheline_aligned;
+		u8 len_c[GCM_BLOCK_LEN_SIZE];
+	} gcm_len_block;
+
+	u8 ccm_config[CCM_CONFIG_BUF_SIZE] ____cacheline_aligned;
+	/* HW actual size input */
+	unsigned int hw_iv_size ____cacheline_aligned;
+	/* used to prevent cache coherence problem */
+	u8 backup_mac[MAX_MAC_SIZE];
+	u8 *backup_iv; /*store iv for generated IV flow*/
+	u8 *backup_giv; /*store iv for rfc3686(ctr) flow*/
+	dma_addr_t mac_buf_dma_addr; /* internal ICV DMA buffer */
+	/* buffer for internal ccm configurations */
+	dma_addr_t ccm_iv0_dma_addr;
+	dma_addr_t icv_dma_addr; /* Phys. address of ICV */
+
+	//used in gcm
+	/* buffer for internal gcm configurations */
+	dma_addr_t gcm_iv_inc1_dma_addr;
+	/* buffer for internal gcm configurations */
+	dma_addr_t gcm_iv_inc2_dma_addr;
+	dma_addr_t hkey_dma_addr; /* Phys. address of hkey */
+	dma_addr_t gcm_block_len_dma_addr; /* Phys. address of gcm block len */
+	bool is_gcm4543;
+
+	u8 *icv_virt_addr; /* Virt. address of ICV */
+	struct async_gen_req_ctx gen_ctx;
+	struct cc_mlli assoc;
+	struct cc_mlli src;
+	struct cc_mlli dst;
+	struct scatterlist *src_sgl;
+	struct scatterlist *dst_sgl;
+	unsigned int src_offset;
+	unsigned int dst_offset;
+	enum cc_req_dma_buf_type assoc_buff_type;
+	enum cc_req_dma_buf_type data_buff_type;
+	struct mlli_params mlli_params;
+	unsigned int cryptlen;
+	struct scatterlist ccm_adata_sg;
+	enum aead_ccm_header_size ccm_hdr_size;
+	unsigned int req_authsize;
+	enum drv_cipher_mode cipher_mode;
+	bool is_icv_fragmented;
+	bool is_single_pass;
+	bool plaintext_authenticate_only; //for gcm_rfc4543
+};
+
+int cc_aead_alloc(struct cc_drvdata *drvdata);
+int cc_aead_free(struct cc_drvdata *drvdata);
+
+#endif /*__CC_AEAD_H__*/
diff --git a/drivers/crypto/ccree/cc_buffer_mgr.c b/drivers/crypto/ccree/cc_buffer_mgr.c
new file mode 100644
index 000000000000..b32577477b4c
--- /dev/null
+++ b/drivers/crypto/ccree/cc_buffer_mgr.c
@@ -0,0 +1,1651 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include <crypto/internal/aead.h>
+#include <crypto/authenc.h>
+#include <crypto/scatterwalk.h>
+#include <linux/dmapool.h>
+#include <linux/dma-mapping.h>
+
+#include "cc_buffer_mgr.h"
+#include "cc_lli_defs.h"
+#include "cc_cipher.h"
+#include "cc_hash.h"
+#include "cc_aead.h"
+
+enum dma_buffer_type {
+	DMA_NULL_TYPE = -1,
+	DMA_SGL_TYPE = 1,
+	DMA_BUFF_TYPE = 2,
+};
+
+struct buff_mgr_handle {
+	struct dma_pool *mlli_buffs_pool;
+};
+
+union buffer_array_entry {
+	struct scatterlist *sgl;
+	dma_addr_t buffer_dma;
+};
+
+struct buffer_array {
+	unsigned int num_of_buffers;
+	union buffer_array_entry entry[MAX_NUM_OF_BUFFERS_IN_MLLI];
+	unsigned int offset[MAX_NUM_OF_BUFFERS_IN_MLLI];
+	int nents[MAX_NUM_OF_BUFFERS_IN_MLLI];
+	int total_data_len[MAX_NUM_OF_BUFFERS_IN_MLLI];
+	enum dma_buffer_type type[MAX_NUM_OF_BUFFERS_IN_MLLI];
+	bool is_last[MAX_NUM_OF_BUFFERS_IN_MLLI];
+	u32 *mlli_nents[MAX_NUM_OF_BUFFERS_IN_MLLI];
+};
+
+static inline char *cc_dma_buf_type(enum cc_req_dma_buf_type type)
+{
+	switch (type) {
+	case CC_DMA_BUF_NULL:
+		return "BUF_NULL";
+	case CC_DMA_BUF_DLLI:
+		return "BUF_DLLI";
+	case CC_DMA_BUF_MLLI:
+		return "BUF_MLLI";
+	default:
+		return "BUF_INVALID";
+	}
+}
+
+/**
+ * cc_copy_mac() - Copy MAC to temporary location
+ *
+ * @dev: device object
+ * @req: aead request object
+ * @dir: [IN] copy from/to sgl
+ */
+static void cc_copy_mac(struct device *dev, struct aead_request *req,
+			enum cc_sg_cpy_direct dir)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	u32 skip = req->assoclen + req->cryptlen;
+
+	if (areq_ctx->is_gcm4543)
+		skip += crypto_aead_ivsize(tfm);
+
+	cc_copy_sg_portion(dev, areq_ctx->backup_mac, req->src,
+			   (skip - areq_ctx->req_authsize), skip, dir);
+}
+
+/**
+ * cc_get_sgl_nents() - Get scatterlist number of entries.
+ *
+ * @sg_list: SG list
+ * @nbytes: [IN] Total SGL data bytes.
+ * @lbytes: [OUT] Returns the amount of bytes at the last entry
+ */
+static unsigned int cc_get_sgl_nents(struct device *dev,
+				     struct scatterlist *sg_list,
+				     unsigned int nbytes, u32 *lbytes,
+				     bool *is_chained)
+{
+	unsigned int nents = 0;
+
+	while (nbytes && sg_list) {
+		if (sg_list->length) {
+			nents++;
+			/* get the number of bytes in the last entry */
+			*lbytes = nbytes;
+			nbytes -= (sg_list->length > nbytes) ?
+					nbytes : sg_list->length;
+			sg_list = sg_next(sg_list);
+		} else {
+			sg_list = (struct scatterlist *)sg_page(sg_list);
+			if (is_chained)
+				*is_chained = true;
+		}
+	}
+	dev_dbg(dev, "nents %d last bytes %d\n", nents, *lbytes);
+	return nents;
+}
+
+/**
+ * cc_zero_sgl() - Zero scatter scatter list data.
+ *
+ * @sgl:
+ */
+void cc_zero_sgl(struct scatterlist *sgl, u32 data_len)
+{
+	struct scatterlist *current_sg = sgl;
+	int sg_index = 0;
+
+	while (sg_index <= data_len) {
+		if (!current_sg) {
+			/* reached the end of the sgl --> just return back */
+			return;
+		}
+		memset(sg_virt(current_sg), 0, current_sg->length);
+		sg_index += current_sg->length;
+		current_sg = sg_next(current_sg);
+	}
+}
+
+/**
+ * cc_copy_sg_portion() - Copy scatter list data,
+ * from to_skip to end, to dest and vice versa
+ *
+ * @dest:
+ * @sg:
+ * @to_skip:
+ * @end:
+ * @direct:
+ */
+void cc_copy_sg_portion(struct device *dev, u8 *dest, struct scatterlist *sg,
+			u32 to_skip, u32 end, enum cc_sg_cpy_direct direct)
+{
+	u32 nents, lbytes;
+
+	nents = cc_get_sgl_nents(dev, sg, end, &lbytes, NULL);
+	sg_copy_buffer(sg, nents, (void *)dest, (end - to_skip + 1), to_skip,
+		       (direct == CC_SG_TO_BUF));
+}
+
+static int cc_render_buff_to_mlli(struct device *dev, dma_addr_t buff_dma,
+				  u32 buff_size, u32 *curr_nents,
+				  u32 **mlli_entry_pp)
+{
+	u32 *mlli_entry_p = *mlli_entry_pp;
+	u32 new_nents;
+
+	/* Verify there is no memory overflow*/
+	new_nents = (*curr_nents + buff_size / CC_MAX_MLLI_ENTRY_SIZE + 1);
+	if (new_nents > MAX_NUM_OF_TOTAL_MLLI_ENTRIES)
+		return -ENOMEM;
+
+	/*handle buffer longer than 64 kbytes */
+	while (buff_size > CC_MAX_MLLI_ENTRY_SIZE) {
+		cc_lli_set_addr(mlli_entry_p, buff_dma);
+		cc_lli_set_size(mlli_entry_p, CC_MAX_MLLI_ENTRY_SIZE);
+		dev_dbg(dev, "entry[%d]: single_buff=0x%08X size=%08X\n",
+			*curr_nents, mlli_entry_p[LLI_WORD0_OFFSET],
+			mlli_entry_p[LLI_WORD1_OFFSET]);
+		buff_dma += CC_MAX_MLLI_ENTRY_SIZE;
+		buff_size -= CC_MAX_MLLI_ENTRY_SIZE;
+		mlli_entry_p = mlli_entry_p + 2;
+		(*curr_nents)++;
+	}
+	/*Last entry */
+	cc_lli_set_addr(mlli_entry_p, buff_dma);
+	cc_lli_set_size(mlli_entry_p, buff_size);
+	dev_dbg(dev, "entry[%d]: single_buff=0x%08X size=%08X\n",
+		*curr_nents, mlli_entry_p[LLI_WORD0_OFFSET],
+		mlli_entry_p[LLI_WORD1_OFFSET]);
+	mlli_entry_p = mlli_entry_p + 2;
+	*mlli_entry_pp = mlli_entry_p;
+	(*curr_nents)++;
+	return 0;
+}
+
+static int cc_render_sg_to_mlli(struct device *dev, struct scatterlist *sgl,
+				u32 sgl_data_len, u32 sgl_offset,
+				u32 *curr_nents, u32 **mlli_entry_pp)
+{
+	struct scatterlist *curr_sgl = sgl;
+	u32 *mlli_entry_p = *mlli_entry_pp;
+	s32 rc = 0;
+
+	for ( ; (curr_sgl && sgl_data_len);
+	      curr_sgl = sg_next(curr_sgl)) {
+		u32 entry_data_len =
+			(sgl_data_len > sg_dma_len(curr_sgl) - sgl_offset) ?
+				sg_dma_len(curr_sgl) - sgl_offset :
+				sgl_data_len;
+		sgl_data_len -= entry_data_len;
+		rc = cc_render_buff_to_mlli(dev, sg_dma_address(curr_sgl) +
+					    sgl_offset, entry_data_len,
+					    curr_nents, &mlli_entry_p);
+		if (rc)
+			return rc;
+
+		sgl_offset = 0;
+	}
+	*mlli_entry_pp = mlli_entry_p;
+	return 0;
+}
+
+static int cc_generate_mlli(struct device *dev, struct buffer_array *sg_data,
+			    struct mlli_params *mlli_params, gfp_t flags)
+{
+	u32 *mlli_p;
+	u32 total_nents = 0, prev_total_nents = 0;
+	int rc = 0, i;
+
+	dev_dbg(dev, "NUM of SG's = %d\n", sg_data->num_of_buffers);
+
+	/* Allocate memory from the pointed pool */
+	mlli_params->mlli_virt_addr =
+		dma_pool_alloc(mlli_params->curr_pool, flags,
+			       &mlli_params->mlli_dma_addr);
+	if (!mlli_params->mlli_virt_addr) {
+		dev_err(dev, "dma_pool_alloc() failed\n");
+		rc = -ENOMEM;
+		goto build_mlli_exit;
+	}
+	/* Point to start of MLLI */
+	mlli_p = (u32 *)mlli_params->mlli_virt_addr;
+	/* go over all SG's and link it to one MLLI table */
+	for (i = 0; i < sg_data->num_of_buffers; i++) {
+		union buffer_array_entry *entry = &sg_data->entry[i];
+		u32 tot_len = sg_data->total_data_len[i];
+		u32 offset = sg_data->offset[i];
+
+		if (sg_data->type[i] == DMA_SGL_TYPE)
+			rc = cc_render_sg_to_mlli(dev, entry->sgl, tot_len,
+						  offset, &total_nents,
+						  &mlli_p);
+		else /*DMA_BUFF_TYPE*/
+			rc = cc_render_buff_to_mlli(dev, entry->buffer_dma,
+						    tot_len, &total_nents,
+						    &mlli_p);
+		if (rc)
+			return rc;
+
+		/* set last bit in the current table */
+		if (sg_data->mlli_nents[i]) {
+			/*Calculate the current MLLI table length for the
+			 *length field in the descriptor
+			 */
+			*sg_data->mlli_nents[i] +=
+				(total_nents - prev_total_nents);
+			prev_total_nents = total_nents;
+		}
+	}
+
+	/* Set MLLI size for the bypass operation */
+	mlli_params->mlli_len = (total_nents * LLI_ENTRY_BYTE_SIZE);
+
+	dev_dbg(dev, "MLLI params: virt_addr=%pK dma_addr=%pad mlli_len=0x%X\n",
+		mlli_params->mlli_virt_addr, &mlli_params->mlli_dma_addr,
+		mlli_params->mlli_len);
+
+build_mlli_exit:
+	return rc;
+}
+
+static void cc_add_buffer_entry(struct device *dev,
+				struct buffer_array *sgl_data,
+				dma_addr_t buffer_dma, unsigned int buffer_len,
+				bool is_last_entry, u32 *mlli_nents)
+{
+	unsigned int index = sgl_data->num_of_buffers;
+
+	dev_dbg(dev, "index=%u single_buff=%pad buffer_len=0x%08X is_last=%d\n",
+		index, &buffer_dma, buffer_len, is_last_entry);
+	sgl_data->nents[index] = 1;
+	sgl_data->entry[index].buffer_dma = buffer_dma;
+	sgl_data->offset[index] = 0;
+	sgl_data->total_data_len[index] = buffer_len;
+	sgl_data->type[index] = DMA_BUFF_TYPE;
+	sgl_data->is_last[index] = is_last_entry;
+	sgl_data->mlli_nents[index] = mlli_nents;
+	if (sgl_data->mlli_nents[index])
+		*sgl_data->mlli_nents[index] = 0;
+	sgl_data->num_of_buffers++;
+}
+
+static void cc_add_sg_entry(struct device *dev, struct buffer_array *sgl_data,
+			    unsigned int nents, struct scatterlist *sgl,
+			    unsigned int data_len, unsigned int data_offset,
+			    bool is_last_table, u32 *mlli_nents)
+{
+	unsigned int index = sgl_data->num_of_buffers;
+
+	dev_dbg(dev, "index=%u nents=%u sgl=%pK data_len=0x%08X is_last=%d\n",
+		index, nents, sgl, data_len, is_last_table);
+	sgl_data->nents[index] = nents;
+	sgl_data->entry[index].sgl = sgl;
+	sgl_data->offset[index] = data_offset;
+	sgl_data->total_data_len[index] = data_len;
+	sgl_data->type[index] = DMA_SGL_TYPE;
+	sgl_data->is_last[index] = is_last_table;
+	sgl_data->mlli_nents[index] = mlli_nents;
+	if (sgl_data->mlli_nents[index])
+		*sgl_data->mlli_nents[index] = 0;
+	sgl_data->num_of_buffers++;
+}
+
+static int cc_dma_map_sg(struct device *dev, struct scatterlist *sg, u32 nents,
+			 enum dma_data_direction direction)
+{
+	u32 i, j;
+	struct scatterlist *l_sg = sg;
+
+	for (i = 0; i < nents; i++) {
+		if (!l_sg)
+			break;
+		if (dma_map_sg(dev, l_sg, 1, direction) != 1) {
+			dev_err(dev, "dma_map_page() sg buffer failed\n");
+			goto err;
+		}
+		l_sg = sg_next(l_sg);
+	}
+	return nents;
+
+err:
+	/* Restore mapped parts */
+	for (j = 0; j < i; j++) {
+		if (!sg)
+			break;
+		dma_unmap_sg(dev, sg, 1, direction);
+		sg = sg_next(sg);
+	}
+	return 0;
+}
+
+static int cc_map_sg(struct device *dev, struct scatterlist *sg,
+		     unsigned int nbytes, int direction, u32 *nents,
+		     u32 max_sg_nents, u32 *lbytes, u32 *mapped_nents)
+{
+	bool is_chained = false;
+
+	if (sg_is_last(sg)) {
+		/* One entry only case -set to DLLI */
+		if (dma_map_sg(dev, sg, 1, direction) != 1) {
+			dev_err(dev, "dma_map_sg() single buffer failed\n");
+			return -ENOMEM;
+		}
+		dev_dbg(dev, "Mapped sg: dma_address=%pad page=%p addr=%pK offset=%u length=%u\n",
+			&sg_dma_address(sg), sg_page(sg), sg_virt(sg),
+			sg->offset, sg->length);
+		*lbytes = nbytes;
+		*nents = 1;
+		*mapped_nents = 1;
+	} else {  /*sg_is_last*/
+		*nents = cc_get_sgl_nents(dev, sg, nbytes, lbytes,
+					  &is_chained);
+		if (*nents > max_sg_nents) {
+			*nents = 0;
+			dev_err(dev, "Too many fragments. current %d max %d\n",
+				*nents, max_sg_nents);
+			return -ENOMEM;
+		}
+		if (!is_chained) {
+			/* In case of mmu the number of mapped nents might
+			 * be changed from the original sgl nents
+			 */
+			*mapped_nents = dma_map_sg(dev, sg, *nents, direction);
+			if (*mapped_nents == 0) {
+				*nents = 0;
+				dev_err(dev, "dma_map_sg() sg buffer failed\n");
+				return -ENOMEM;
+			}
+		} else {
+			/*In this case the driver maps entry by entry so it
+			 * must have the same nents before and after map
+			 */
+			*mapped_nents = cc_dma_map_sg(dev, sg, *nents,
+						      direction);
+			if (*mapped_nents != *nents) {
+				*nents = *mapped_nents;
+				dev_err(dev, "dma_map_sg() sg buffer failed\n");
+				return -ENOMEM;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int
+cc_set_aead_conf_buf(struct device *dev, struct aead_req_ctx *areq_ctx,
+		     u8 *config_data, struct buffer_array *sg_data,
+		     unsigned int assoclen)
+{
+	dev_dbg(dev, " handle additional data config set to DLLI\n");
+	/* create sg for the current buffer */
+	sg_init_one(&areq_ctx->ccm_adata_sg, config_data,
+		    AES_BLOCK_SIZE + areq_ctx->ccm_hdr_size);
+	if (dma_map_sg(dev, &areq_ctx->ccm_adata_sg, 1, DMA_TO_DEVICE) != 1) {
+		dev_err(dev, "dma_map_sg() config buffer failed\n");
+		return -ENOMEM;
+	}
+	dev_dbg(dev, "Mapped curr_buff: dma_address=%pad page=%p addr=%pK offset=%u length=%u\n",
+		&sg_dma_address(&areq_ctx->ccm_adata_sg),
+		sg_page(&areq_ctx->ccm_adata_sg),
+		sg_virt(&areq_ctx->ccm_adata_sg),
+		areq_ctx->ccm_adata_sg.offset, areq_ctx->ccm_adata_sg.length);
+	/* prepare for case of MLLI */
+	if (assoclen > 0) {
+		cc_add_sg_entry(dev, sg_data, 1, &areq_ctx->ccm_adata_sg,
+				(AES_BLOCK_SIZE + areq_ctx->ccm_hdr_size),
+				0, false, NULL);
+	}
+	return 0;
+}
+
+static int cc_set_hash_buf(struct device *dev, struct ahash_req_ctx *areq_ctx,
+			   u8 *curr_buff, u32 curr_buff_cnt,
+			   struct buffer_array *sg_data)
+{
+	dev_dbg(dev, " handle curr buff %x set to   DLLI\n", curr_buff_cnt);
+	/* create sg for the current buffer */
+	sg_init_one(areq_ctx->buff_sg, curr_buff, curr_buff_cnt);
+	if (dma_map_sg(dev, areq_ctx->buff_sg, 1, DMA_TO_DEVICE) != 1) {
+		dev_err(dev, "dma_map_sg() src buffer failed\n");
+		return -ENOMEM;
+	}
+	dev_dbg(dev, "Mapped curr_buff: dma_address=%pad page=%p addr=%pK offset=%u length=%u\n",
+		&sg_dma_address(areq_ctx->buff_sg), sg_page(areq_ctx->buff_sg),
+		sg_virt(areq_ctx->buff_sg), areq_ctx->buff_sg->offset,
+		areq_ctx->buff_sg->length);
+	areq_ctx->data_dma_buf_type = CC_DMA_BUF_DLLI;
+	areq_ctx->curr_sg = areq_ctx->buff_sg;
+	areq_ctx->in_nents = 0;
+	/* prepare for case of MLLI */
+	cc_add_sg_entry(dev, sg_data, 1, areq_ctx->buff_sg, curr_buff_cnt, 0,
+			false, NULL);
+	return 0;
+}
+
+void cc_unmap_cipher_request(struct device *dev, void *ctx,
+				unsigned int ivsize, struct scatterlist *src,
+				struct scatterlist *dst)
+{
+	struct cipher_req_ctx *req_ctx = (struct cipher_req_ctx *)ctx;
+
+	if (req_ctx->gen_ctx.iv_dma_addr) {
+		dev_dbg(dev, "Unmapped iv: iv_dma_addr=%pad iv_size=%u\n",
+			&req_ctx->gen_ctx.iv_dma_addr, ivsize);
+		dma_unmap_single(dev, req_ctx->gen_ctx.iv_dma_addr,
+				 ivsize,
+				 req_ctx->is_giv ? DMA_BIDIRECTIONAL :
+				 DMA_TO_DEVICE);
+	}
+	/* Release pool */
+	if (req_ctx->dma_buf_type == CC_DMA_BUF_MLLI &&
+	    req_ctx->mlli_params.mlli_virt_addr) {
+		dma_pool_free(req_ctx->mlli_params.curr_pool,
+			      req_ctx->mlli_params.mlli_virt_addr,
+			      req_ctx->mlli_params.mlli_dma_addr);
+	}
+
+	dma_unmap_sg(dev, src, req_ctx->in_nents, DMA_BIDIRECTIONAL);
+	dev_dbg(dev, "Unmapped req->src=%pK\n", sg_virt(src));
+
+	if (src != dst) {
+		dma_unmap_sg(dev, dst, req_ctx->out_nents, DMA_BIDIRECTIONAL);
+		dev_dbg(dev, "Unmapped req->dst=%pK\n", sg_virt(dst));
+	}
+}
+
+int cc_map_cipher_request(struct cc_drvdata *drvdata, void *ctx,
+			  unsigned int ivsize, unsigned int nbytes,
+			  void *info, struct scatterlist *src,
+			  struct scatterlist *dst, gfp_t flags)
+{
+	struct cipher_req_ctx *req_ctx = (struct cipher_req_ctx *)ctx;
+	struct mlli_params *mlli_params = &req_ctx->mlli_params;
+	struct buff_mgr_handle *buff_mgr = drvdata->buff_mgr_handle;
+	struct device *dev = drvdata_to_dev(drvdata);
+	struct buffer_array sg_data;
+	u32 dummy = 0;
+	int rc = 0;
+	u32 mapped_nents = 0;
+
+	req_ctx->dma_buf_type = CC_DMA_BUF_DLLI;
+	mlli_params->curr_pool = NULL;
+	sg_data.num_of_buffers = 0;
+
+	/* Map IV buffer */
+	if (ivsize) {
+		dump_byte_array("iv", (u8 *)info, ivsize);
+		req_ctx->gen_ctx.iv_dma_addr =
+			dma_map_single(dev, (void *)info,
+				       ivsize,
+				       req_ctx->is_giv ? DMA_BIDIRECTIONAL :
+				       DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, req_ctx->gen_ctx.iv_dma_addr)) {
+			dev_err(dev, "Mapping iv %u B at va=%pK for DMA failed\n",
+				ivsize, info);
+			return -ENOMEM;
+		}
+		dev_dbg(dev, "Mapped iv %u B at va=%pK to dma=%pad\n",
+			ivsize, info, &req_ctx->gen_ctx.iv_dma_addr);
+	} else {
+		req_ctx->gen_ctx.iv_dma_addr = 0;
+	}
+
+	/* Map the src SGL */
+	rc = cc_map_sg(dev, src, nbytes, DMA_BIDIRECTIONAL, &req_ctx->in_nents,
+		       LLI_MAX_NUM_OF_DATA_ENTRIES, &dummy, &mapped_nents);
+	if (rc) {
+		rc = -ENOMEM;
+		goto cipher_exit;
+	}
+	if (mapped_nents > 1)
+		req_ctx->dma_buf_type = CC_DMA_BUF_MLLI;
+
+	if (src == dst) {
+		/* Handle inplace operation */
+		if (req_ctx->dma_buf_type == CC_DMA_BUF_MLLI) {
+			req_ctx->out_nents = 0;
+			cc_add_sg_entry(dev, &sg_data, req_ctx->in_nents, src,
+					nbytes, 0, true,
+					&req_ctx->in_mlli_nents);
+		}
+	} else {
+		/* Map the dst sg */
+		if (cc_map_sg(dev, dst, nbytes, DMA_BIDIRECTIONAL,
+			      &req_ctx->out_nents, LLI_MAX_NUM_OF_DATA_ENTRIES,
+			      &dummy, &mapped_nents)) {
+			rc = -ENOMEM;
+			goto cipher_exit;
+		}
+		if (mapped_nents > 1)
+			req_ctx->dma_buf_type = CC_DMA_BUF_MLLI;
+
+		if (req_ctx->dma_buf_type == CC_DMA_BUF_MLLI) {
+			cc_add_sg_entry(dev, &sg_data, req_ctx->in_nents, src,
+					nbytes, 0, true,
+					&req_ctx->in_mlli_nents);
+			cc_add_sg_entry(dev, &sg_data, req_ctx->out_nents, dst,
+					nbytes, 0, true,
+					&req_ctx->out_mlli_nents);
+		}
+	}
+
+	if (req_ctx->dma_buf_type == CC_DMA_BUF_MLLI) {
+		mlli_params->curr_pool = buff_mgr->mlli_buffs_pool;
+		rc = cc_generate_mlli(dev, &sg_data, mlli_params, flags);
+		if (rc)
+			goto cipher_exit;
+	}
+
+	dev_dbg(dev, "areq_ctx->dma_buf_type = %s\n",
+		cc_dma_buf_type(req_ctx->dma_buf_type));
+
+	return 0;
+
+cipher_exit:
+	cc_unmap_cipher_request(dev, req_ctx, ivsize, src, dst);
+	return rc;
+}
+
+void cc_unmap_aead_request(struct device *dev, struct aead_request *req)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	unsigned int hw_iv_size = areq_ctx->hw_iv_size;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
+	u32 dummy;
+	bool chained;
+	u32 size_to_unmap = 0;
+
+	if (areq_ctx->mac_buf_dma_addr) {
+		dma_unmap_single(dev, areq_ctx->mac_buf_dma_addr,
+				 MAX_MAC_SIZE, DMA_BIDIRECTIONAL);
+	}
+
+	if (areq_ctx->cipher_mode == DRV_CIPHER_GCTR) {
+		if (areq_ctx->hkey_dma_addr) {
+			dma_unmap_single(dev, areq_ctx->hkey_dma_addr,
+					 AES_BLOCK_SIZE, DMA_BIDIRECTIONAL);
+		}
+
+		if (areq_ctx->gcm_block_len_dma_addr) {
+			dma_unmap_single(dev, areq_ctx->gcm_block_len_dma_addr,
+					 AES_BLOCK_SIZE, DMA_TO_DEVICE);
+		}
+
+		if (areq_ctx->gcm_iv_inc1_dma_addr) {
+			dma_unmap_single(dev, areq_ctx->gcm_iv_inc1_dma_addr,
+					 AES_BLOCK_SIZE, DMA_TO_DEVICE);
+		}
+
+		if (areq_ctx->gcm_iv_inc2_dma_addr) {
+			dma_unmap_single(dev, areq_ctx->gcm_iv_inc2_dma_addr,
+					 AES_BLOCK_SIZE, DMA_TO_DEVICE);
+		}
+	}
+
+	if (areq_ctx->ccm_hdr_size != ccm_header_size_null) {
+		if (areq_ctx->ccm_iv0_dma_addr) {
+			dma_unmap_single(dev, areq_ctx->ccm_iv0_dma_addr,
+					 AES_BLOCK_SIZE, DMA_TO_DEVICE);
+		}
+
+		dma_unmap_sg(dev, &areq_ctx->ccm_adata_sg, 1, DMA_TO_DEVICE);
+	}
+	if (areq_ctx->gen_ctx.iv_dma_addr) {
+		dma_unmap_single(dev, areq_ctx->gen_ctx.iv_dma_addr,
+				 hw_iv_size, DMA_BIDIRECTIONAL);
+	}
+
+	/*In case a pool was set, a table was
+	 *allocated and should be released
+	 */
+	if (areq_ctx->mlli_params.curr_pool) {
+		dev_dbg(dev, "free MLLI buffer: dma=%pad virt=%pK\n",
+			&areq_ctx->mlli_params.mlli_dma_addr,
+			areq_ctx->mlli_params.mlli_virt_addr);
+		dma_pool_free(areq_ctx->mlli_params.curr_pool,
+			      areq_ctx->mlli_params.mlli_virt_addr,
+			      areq_ctx->mlli_params.mlli_dma_addr);
+	}
+
+	dev_dbg(dev, "Unmapping src sgl: req->src=%pK areq_ctx->src.nents=%u areq_ctx->assoc.nents=%u assoclen:%u cryptlen=%u\n",
+		sg_virt(req->src), areq_ctx->src.nents, areq_ctx->assoc.nents,
+		req->assoclen, req->cryptlen);
+	size_to_unmap = req->assoclen + req->cryptlen;
+	if (areq_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_ENCRYPT)
+		size_to_unmap += areq_ctx->req_authsize;
+	if (areq_ctx->is_gcm4543)
+		size_to_unmap += crypto_aead_ivsize(tfm);
+
+	dma_unmap_sg(dev, req->src,
+		     cc_get_sgl_nents(dev, req->src, size_to_unmap,
+				      &dummy, &chained),
+		     DMA_BIDIRECTIONAL);
+	if (req->src != req->dst) {
+		dev_dbg(dev, "Unmapping dst sgl: req->dst=%pK\n",
+			sg_virt(req->dst));
+		dma_unmap_sg(dev, req->dst,
+			     cc_get_sgl_nents(dev, req->dst, size_to_unmap,
+					      &dummy, &chained),
+			     DMA_BIDIRECTIONAL);
+	}
+	if (drvdata->coherent &&
+	    areq_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT &&
+	    req->src == req->dst) {
+		/* copy back mac from temporary location to deal with possible
+		 * data memory overriding that caused by cache coherence
+		 * problem.
+		 */
+		cc_copy_mac(dev, req, CC_SG_FROM_BUF);
+	}
+}
+
+static int cc_get_aead_icv_nents(struct device *dev, struct scatterlist *sgl,
+				 unsigned int sgl_nents, unsigned int authsize,
+				 u32 last_entry_data_size,
+				 bool *is_icv_fragmented)
+{
+	unsigned int icv_max_size = 0;
+	unsigned int icv_required_size = authsize > last_entry_data_size ?
+					(authsize - last_entry_data_size) :
+					authsize;
+	unsigned int nents;
+	unsigned int i;
+
+	if (sgl_nents < MAX_ICV_NENTS_SUPPORTED) {
+		*is_icv_fragmented = false;
+		return 0;
+	}
+
+	for (i = 0 ; i < (sgl_nents - MAX_ICV_NENTS_SUPPORTED) ; i++) {
+		if (!sgl)
+			break;
+		sgl = sg_next(sgl);
+	}
+
+	if (sgl)
+		icv_max_size = sgl->length;
+
+	if (last_entry_data_size > authsize) {
+		/* ICV attached to data in last entry (not fragmented!) */
+		nents = 0;
+		*is_icv_fragmented = false;
+	} else if (last_entry_data_size == authsize) {
+		/* ICV placed in whole last entry (not fragmented!) */
+		nents = 1;
+		*is_icv_fragmented = false;
+	} else if (icv_max_size > icv_required_size) {
+		nents = 1;
+		*is_icv_fragmented = true;
+	} else if (icv_max_size == icv_required_size) {
+		nents = 2;
+		*is_icv_fragmented = true;
+	} else {
+		dev_err(dev, "Unsupported num. of ICV fragments (> %d)\n",
+			MAX_ICV_NENTS_SUPPORTED);
+		nents = -1; /*unsupported*/
+	}
+	dev_dbg(dev, "is_frag=%s icv_nents=%u\n",
+		(*is_icv_fragmented ? "true" : "false"), nents);
+
+	return nents;
+}
+
+static int cc_aead_chain_iv(struct cc_drvdata *drvdata,
+			    struct aead_request *req,
+			    struct buffer_array *sg_data,
+			    bool is_last, bool do_chain)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	unsigned int hw_iv_size = areq_ctx->hw_iv_size;
+	struct device *dev = drvdata_to_dev(drvdata);
+	int rc = 0;
+
+	if (!req->iv) {
+		areq_ctx->gen_ctx.iv_dma_addr = 0;
+		goto chain_iv_exit;
+	}
+
+	areq_ctx->gen_ctx.iv_dma_addr = dma_map_single(dev, req->iv,
+						       hw_iv_size,
+						       DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dev, areq_ctx->gen_ctx.iv_dma_addr)) {
+		dev_err(dev, "Mapping iv %u B at va=%pK for DMA failed\n",
+			hw_iv_size, req->iv);
+		rc = -ENOMEM;
+		goto chain_iv_exit;
+	}
+
+	dev_dbg(dev, "Mapped iv %u B at va=%pK to dma=%pad\n",
+		hw_iv_size, req->iv, &areq_ctx->gen_ctx.iv_dma_addr);
+	// TODO: what about CTR?? ask Ron
+	if (do_chain && areq_ctx->plaintext_authenticate_only) {
+		struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+		unsigned int iv_size_to_authenc = crypto_aead_ivsize(tfm);
+		unsigned int iv_ofs = GCM_BLOCK_RFC4_IV_OFFSET;
+		/* Chain to given list */
+		cc_add_buffer_entry(dev, sg_data,
+				    (areq_ctx->gen_ctx.iv_dma_addr + iv_ofs),
+				    iv_size_to_authenc, is_last,
+				    &areq_ctx->assoc.mlli_nents);
+		areq_ctx->assoc_buff_type = CC_DMA_BUF_MLLI;
+	}
+
+chain_iv_exit:
+	return rc;
+}
+
+static int cc_aead_chain_assoc(struct cc_drvdata *drvdata,
+			       struct aead_request *req,
+			       struct buffer_array *sg_data,
+			       bool is_last, bool do_chain)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	int rc = 0;
+	u32 mapped_nents = 0;
+	struct scatterlist *current_sg = req->src;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	unsigned int sg_index = 0;
+	u32 size_of_assoc = req->assoclen;
+	struct device *dev = drvdata_to_dev(drvdata);
+
+	if (areq_ctx->is_gcm4543)
+		size_of_assoc += crypto_aead_ivsize(tfm);
+
+	if (!sg_data) {
+		rc = -EINVAL;
+		goto chain_assoc_exit;
+	}
+
+	if (req->assoclen == 0) {
+		areq_ctx->assoc_buff_type = CC_DMA_BUF_NULL;
+		areq_ctx->assoc.nents = 0;
+		areq_ctx->assoc.mlli_nents = 0;
+		dev_dbg(dev, "Chain assoc of length 0: buff_type=%s nents=%u\n",
+			cc_dma_buf_type(areq_ctx->assoc_buff_type),
+			areq_ctx->assoc.nents);
+		goto chain_assoc_exit;
+	}
+
+	//iterate over the sgl to see how many entries are for associated data
+	//it is assumed that if we reach here , the sgl is already mapped
+	sg_index = current_sg->length;
+	//the first entry in the scatter list contains all the associated data
+	if (sg_index > size_of_assoc) {
+		mapped_nents++;
+	} else {
+		while (sg_index <= size_of_assoc) {
+			current_sg = sg_next(current_sg);
+			/* if have reached the end of the sgl, then this is
+			 * unexpected
+			 */
+			if (!current_sg) {
+				dev_err(dev, "reached end of sg list. unexpected\n");
+				return -EINVAL;
+			}
+			sg_index += current_sg->length;
+			mapped_nents++;
+		}
+	}
+	if (mapped_nents > LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES) {
+		dev_err(dev, "Too many fragments. current %d max %d\n",
+			mapped_nents, LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES);
+		return -ENOMEM;
+	}
+	areq_ctx->assoc.nents = mapped_nents;
+
+	/* in CCM case we have additional entry for
+	 * ccm header configurations
+	 */
+	if (areq_ctx->ccm_hdr_size != ccm_header_size_null) {
+		if ((mapped_nents + 1) > LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES) {
+			dev_err(dev, "CCM case.Too many fragments. Current %d max %d\n",
+				(areq_ctx->assoc.nents + 1),
+				LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES);
+			rc = -ENOMEM;
+			goto chain_assoc_exit;
+		}
+	}
+
+	if (mapped_nents == 1 && areq_ctx->ccm_hdr_size == ccm_header_size_null)
+		areq_ctx->assoc_buff_type = CC_DMA_BUF_DLLI;
+	else
+		areq_ctx->assoc_buff_type = CC_DMA_BUF_MLLI;
+
+	if (do_chain || areq_ctx->assoc_buff_type == CC_DMA_BUF_MLLI) {
+		dev_dbg(dev, "Chain assoc: buff_type=%s nents=%u\n",
+			cc_dma_buf_type(areq_ctx->assoc_buff_type),
+			areq_ctx->assoc.nents);
+		cc_add_sg_entry(dev, sg_data, areq_ctx->assoc.nents, req->src,
+				req->assoclen, 0, is_last,
+				&areq_ctx->assoc.mlli_nents);
+		areq_ctx->assoc_buff_type = CC_DMA_BUF_MLLI;
+	}
+
+chain_assoc_exit:
+	return rc;
+}
+
+static void cc_prepare_aead_data_dlli(struct aead_request *req,
+				      u32 *src_last_bytes, u32 *dst_last_bytes)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	enum drv_crypto_direction direct = areq_ctx->gen_ctx.op_type;
+	unsigned int authsize = areq_ctx->req_authsize;
+
+	areq_ctx->is_icv_fragmented = false;
+	if (req->src == req->dst) {
+		/*INPLACE*/
+		areq_ctx->icv_dma_addr = sg_dma_address(areq_ctx->src_sgl) +
+			(*src_last_bytes - authsize);
+		areq_ctx->icv_virt_addr = sg_virt(areq_ctx->src_sgl) +
+			(*src_last_bytes - authsize);
+	} else if (direct == DRV_CRYPTO_DIRECTION_DECRYPT) {
+		/*NON-INPLACE and DECRYPT*/
+		areq_ctx->icv_dma_addr = sg_dma_address(areq_ctx->src_sgl) +
+			(*src_last_bytes - authsize);
+		areq_ctx->icv_virt_addr = sg_virt(areq_ctx->src_sgl) +
+			(*src_last_bytes - authsize);
+	} else {
+		/*NON-INPLACE and ENCRYPT*/
+		areq_ctx->icv_dma_addr = sg_dma_address(areq_ctx->dst_sgl) +
+			(*dst_last_bytes - authsize);
+		areq_ctx->icv_virt_addr = sg_virt(areq_ctx->dst_sgl) +
+			(*dst_last_bytes - authsize);
+	}
+}
+
+static int cc_prepare_aead_data_mlli(struct cc_drvdata *drvdata,
+				     struct aead_request *req,
+				     struct buffer_array *sg_data,
+				     u32 *src_last_bytes, u32 *dst_last_bytes,
+				     bool is_last_table)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	enum drv_crypto_direction direct = areq_ctx->gen_ctx.op_type;
+	unsigned int authsize = areq_ctx->req_authsize;
+	int rc = 0, icv_nents;
+	struct device *dev = drvdata_to_dev(drvdata);
+	struct scatterlist *sg;
+
+	if (req->src == req->dst) {
+		/*INPLACE*/
+		cc_add_sg_entry(dev, sg_data, areq_ctx->src.nents,
+				areq_ctx->src_sgl, areq_ctx->cryptlen,
+				areq_ctx->src_offset, is_last_table,
+				&areq_ctx->src.mlli_nents);
+
+		icv_nents = cc_get_aead_icv_nents(dev, areq_ctx->src_sgl,
+						  areq_ctx->src.nents,
+						  authsize, *src_last_bytes,
+						  &areq_ctx->is_icv_fragmented);
+		if (icv_nents < 0) {
+			rc = -ENOTSUPP;
+			goto prepare_data_mlli_exit;
+		}
+
+		if (areq_ctx->is_icv_fragmented) {
+			/* Backup happens only when ICV is fragmented, ICV
+			 * verification is made by CPU compare in order to
+			 * simplify MAC verification upon request completion
+			 */
+			if (direct == DRV_CRYPTO_DIRECTION_DECRYPT) {
+				/* In coherent platforms (e.g. ACP)
+				 * already copying ICV for any
+				 * INPLACE-DECRYPT operation, hence
+				 * we must neglect this code.
+				 */
+				if (!drvdata->coherent)
+					cc_copy_mac(dev, req, CC_SG_TO_BUF);
+
+				areq_ctx->icv_virt_addr = areq_ctx->backup_mac;
+			} else {
+				areq_ctx->icv_virt_addr = areq_ctx->mac_buf;
+				areq_ctx->icv_dma_addr =
+					areq_ctx->mac_buf_dma_addr;
+			}
+		} else { /* Contig. ICV */
+			sg = &areq_ctx->src_sgl[areq_ctx->src.nents - 1];
+			/*Should hanlde if the sg is not contig.*/
+			areq_ctx->icv_dma_addr = sg_dma_address(sg) +
+				(*src_last_bytes - authsize);
+			areq_ctx->icv_virt_addr = sg_virt(sg) +
+				(*src_last_bytes - authsize);
+		}
+
+	} else if (direct == DRV_CRYPTO_DIRECTION_DECRYPT) {
+		/*NON-INPLACE and DECRYPT*/
+		cc_add_sg_entry(dev, sg_data, areq_ctx->src.nents,
+				areq_ctx->src_sgl, areq_ctx->cryptlen,
+				areq_ctx->src_offset, is_last_table,
+				&areq_ctx->src.mlli_nents);
+		cc_add_sg_entry(dev, sg_data, areq_ctx->dst.nents,
+				areq_ctx->dst_sgl, areq_ctx->cryptlen,
+				areq_ctx->dst_offset, is_last_table,
+				&areq_ctx->dst.mlli_nents);
+
+		icv_nents = cc_get_aead_icv_nents(dev, areq_ctx->src_sgl,
+						  areq_ctx->src.nents,
+						  authsize, *src_last_bytes,
+						  &areq_ctx->is_icv_fragmented);
+		if (icv_nents < 0) {
+			rc = -ENOTSUPP;
+			goto prepare_data_mlli_exit;
+		}
+
+		/* Backup happens only when ICV is fragmented, ICV
+		 * verification is made by CPU compare in order to simplify
+		 * MAC verification upon request completion
+		 */
+		if (areq_ctx->is_icv_fragmented) {
+			cc_copy_mac(dev, req, CC_SG_TO_BUF);
+			areq_ctx->icv_virt_addr = areq_ctx->backup_mac;
+
+		} else { /* Contig. ICV */
+			sg = &areq_ctx->src_sgl[areq_ctx->src.nents - 1];
+			/*Should hanlde if the sg is not contig.*/
+			areq_ctx->icv_dma_addr = sg_dma_address(sg) +
+				(*src_last_bytes - authsize);
+			areq_ctx->icv_virt_addr = sg_virt(sg) +
+				(*src_last_bytes - authsize);
+		}
+
+	} else {
+		/*NON-INPLACE and ENCRYPT*/
+		cc_add_sg_entry(dev, sg_data, areq_ctx->dst.nents,
+				areq_ctx->dst_sgl, areq_ctx->cryptlen,
+				areq_ctx->dst_offset, is_last_table,
+				&areq_ctx->dst.mlli_nents);
+		cc_add_sg_entry(dev, sg_data, areq_ctx->src.nents,
+				areq_ctx->src_sgl, areq_ctx->cryptlen,
+				areq_ctx->src_offset, is_last_table,
+				&areq_ctx->src.mlli_nents);
+
+		icv_nents = cc_get_aead_icv_nents(dev, areq_ctx->dst_sgl,
+						  areq_ctx->dst.nents,
+						  authsize, *dst_last_bytes,
+						  &areq_ctx->is_icv_fragmented);
+		if (icv_nents < 0) {
+			rc = -ENOTSUPP;
+			goto prepare_data_mlli_exit;
+		}
+
+		if (!areq_ctx->is_icv_fragmented) {
+			sg = &areq_ctx->dst_sgl[areq_ctx->dst.nents - 1];
+			/* Contig. ICV */
+			areq_ctx->icv_dma_addr = sg_dma_address(sg) +
+				(*dst_last_bytes - authsize);
+			areq_ctx->icv_virt_addr = sg_virt(sg) +
+				(*dst_last_bytes - authsize);
+		} else {
+			areq_ctx->icv_dma_addr = areq_ctx->mac_buf_dma_addr;
+			areq_ctx->icv_virt_addr = areq_ctx->mac_buf;
+		}
+	}
+
+prepare_data_mlli_exit:
+	return rc;
+}
+
+static int cc_aead_chain_data(struct cc_drvdata *drvdata,
+			      struct aead_request *req,
+			      struct buffer_array *sg_data,
+			      bool is_last_table, bool do_chain)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	struct device *dev = drvdata_to_dev(drvdata);
+	enum drv_crypto_direction direct = areq_ctx->gen_ctx.op_type;
+	unsigned int authsize = areq_ctx->req_authsize;
+	unsigned int src_last_bytes = 0, dst_last_bytes = 0;
+	int rc = 0;
+	u32 src_mapped_nents = 0, dst_mapped_nents = 0;
+	u32 offset = 0;
+	/* non-inplace mode */
+	unsigned int size_for_map = req->assoclen + req->cryptlen;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	u32 sg_index = 0;
+	bool chained = false;
+	bool is_gcm4543 = areq_ctx->is_gcm4543;
+	u32 size_to_skip = req->assoclen;
+
+	if (is_gcm4543)
+		size_to_skip += crypto_aead_ivsize(tfm);
+
+	offset = size_to_skip;
+
+	if (!sg_data)
+		return -EINVAL;
+
+	areq_ctx->src_sgl = req->src;
+	areq_ctx->dst_sgl = req->dst;
+
+	if (is_gcm4543)
+		size_for_map += crypto_aead_ivsize(tfm);
+
+	size_for_map += (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) ?
+			authsize : 0;
+	src_mapped_nents = cc_get_sgl_nents(dev, req->src, size_for_map,
+					    &src_last_bytes, &chained);
+	sg_index = areq_ctx->src_sgl->length;
+	//check where the data starts
+	while (sg_index <= size_to_skip) {
+		offset -= areq_ctx->src_sgl->length;
+		areq_ctx->src_sgl = sg_next(areq_ctx->src_sgl);
+		//if have reached the end of the sgl, then this is unexpected
+		if (!areq_ctx->src_sgl) {
+			dev_err(dev, "reached end of sg list. unexpected\n");
+			return -EINVAL;
+		}
+		sg_index += areq_ctx->src_sgl->length;
+		src_mapped_nents--;
+	}
+	if (src_mapped_nents > LLI_MAX_NUM_OF_DATA_ENTRIES) {
+		dev_err(dev, "Too many fragments. current %d max %d\n",
+			src_mapped_nents, LLI_MAX_NUM_OF_DATA_ENTRIES);
+		return -ENOMEM;
+	}
+
+	areq_ctx->src.nents = src_mapped_nents;
+
+	areq_ctx->src_offset = offset;
+
+	if (req->src != req->dst) {
+		size_for_map = req->assoclen + req->cryptlen;
+		size_for_map += (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) ?
+				authsize : 0;
+		if (is_gcm4543)
+			size_for_map += crypto_aead_ivsize(tfm);
+
+		rc = cc_map_sg(dev, req->dst, size_for_map, DMA_BIDIRECTIONAL,
+			       &areq_ctx->dst.nents,
+			       LLI_MAX_NUM_OF_DATA_ENTRIES, &dst_last_bytes,
+			       &dst_mapped_nents);
+		if (rc) {
+			rc = -ENOMEM;
+			goto chain_data_exit;
+		}
+	}
+
+	dst_mapped_nents = cc_get_sgl_nents(dev, req->dst, size_for_map,
+					    &dst_last_bytes, &chained);
+	sg_index = areq_ctx->dst_sgl->length;
+	offset = size_to_skip;
+
+	//check where the data starts
+	while (sg_index <= size_to_skip) {
+		offset -= areq_ctx->dst_sgl->length;
+		areq_ctx->dst_sgl = sg_next(areq_ctx->dst_sgl);
+		//if have reached the end of the sgl, then this is unexpected
+		if (!areq_ctx->dst_sgl) {
+			dev_err(dev, "reached end of sg list. unexpected\n");
+			return -EINVAL;
+		}
+		sg_index += areq_ctx->dst_sgl->length;
+		dst_mapped_nents--;
+	}
+	if (dst_mapped_nents > LLI_MAX_NUM_OF_DATA_ENTRIES) {
+		dev_err(dev, "Too many fragments. current %d max %d\n",
+			dst_mapped_nents, LLI_MAX_NUM_OF_DATA_ENTRIES);
+		return -ENOMEM;
+	}
+	areq_ctx->dst.nents = dst_mapped_nents;
+	areq_ctx->dst_offset = offset;
+	if (src_mapped_nents > 1 ||
+	    dst_mapped_nents  > 1 ||
+	    do_chain) {
+		areq_ctx->data_buff_type = CC_DMA_BUF_MLLI;
+		rc = cc_prepare_aead_data_mlli(drvdata, req, sg_data,
+					       &src_last_bytes,
+					       &dst_last_bytes, is_last_table);
+	} else {
+		areq_ctx->data_buff_type = CC_DMA_BUF_DLLI;
+		cc_prepare_aead_data_dlli(req, &src_last_bytes,
+					  &dst_last_bytes);
+	}
+
+chain_data_exit:
+	return rc;
+}
+
+static void cc_update_aead_mlli_nents(struct cc_drvdata *drvdata,
+				      struct aead_request *req)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	u32 curr_mlli_size = 0;
+
+	if (areq_ctx->assoc_buff_type == CC_DMA_BUF_MLLI) {
+		areq_ctx->assoc.sram_addr = drvdata->mlli_sram_addr;
+		curr_mlli_size = areq_ctx->assoc.mlli_nents *
+						LLI_ENTRY_BYTE_SIZE;
+	}
+
+	if (areq_ctx->data_buff_type == CC_DMA_BUF_MLLI) {
+		/*Inplace case dst nents equal to src nents*/
+		if (req->src == req->dst) {
+			areq_ctx->dst.mlli_nents = areq_ctx->src.mlli_nents;
+			areq_ctx->src.sram_addr = drvdata->mlli_sram_addr +
+								curr_mlli_size;
+			areq_ctx->dst.sram_addr = areq_ctx->src.sram_addr;
+			if (!areq_ctx->is_single_pass)
+				areq_ctx->assoc.mlli_nents +=
+					areq_ctx->src.mlli_nents;
+		} else {
+			if (areq_ctx->gen_ctx.op_type ==
+					DRV_CRYPTO_DIRECTION_DECRYPT) {
+				areq_ctx->src.sram_addr =
+						drvdata->mlli_sram_addr +
+								curr_mlli_size;
+				areq_ctx->dst.sram_addr =
+						areq_ctx->src.sram_addr +
+						areq_ctx->src.mlli_nents *
+						LLI_ENTRY_BYTE_SIZE;
+				if (!areq_ctx->is_single_pass)
+					areq_ctx->assoc.mlli_nents +=
+						areq_ctx->src.mlli_nents;
+			} else {
+				areq_ctx->dst.sram_addr =
+						drvdata->mlli_sram_addr +
+								curr_mlli_size;
+				areq_ctx->src.sram_addr =
+						areq_ctx->dst.sram_addr +
+						areq_ctx->dst.mlli_nents *
+						LLI_ENTRY_BYTE_SIZE;
+				if (!areq_ctx->is_single_pass)
+					areq_ctx->assoc.mlli_nents +=
+						areq_ctx->dst.mlli_nents;
+			}
+		}
+	}
+}
+
+int cc_map_aead_request(struct cc_drvdata *drvdata, struct aead_request *req)
+{
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
+	struct mlli_params *mlli_params = &areq_ctx->mlli_params;
+	struct device *dev = drvdata_to_dev(drvdata);
+	struct buffer_array sg_data;
+	unsigned int authsize = areq_ctx->req_authsize;
+	struct buff_mgr_handle *buff_mgr = drvdata->buff_mgr_handle;
+	int rc = 0;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	bool is_gcm4543 = areq_ctx->is_gcm4543;
+	dma_addr_t dma_addr;
+	u32 mapped_nents = 0;
+	u32 dummy = 0; /*used for the assoc data fragments */
+	u32 size_to_map = 0;
+	gfp_t flags = cc_gfp_flags(&req->base);
+
+	mlli_params->curr_pool = NULL;
+	sg_data.num_of_buffers = 0;
+
+	/* copy mac to a temporary location to deal with possible
+	 * data memory overriding that caused by cache coherence problem.
+	 */
+	if (drvdata->coherent &&
+	    areq_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT &&
+	    req->src == req->dst)
+		cc_copy_mac(dev, req, CC_SG_TO_BUF);
+
+	/* cacluate the size for cipher remove ICV in decrypt*/
+	areq_ctx->cryptlen = (areq_ctx->gen_ctx.op_type ==
+				 DRV_CRYPTO_DIRECTION_ENCRYPT) ?
+				req->cryptlen :
+				(req->cryptlen - authsize);
+
+	dma_addr = dma_map_single(dev, areq_ctx->mac_buf, MAX_MAC_SIZE,
+				  DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dev, dma_addr)) {
+		dev_err(dev, "Mapping mac_buf %u B at va=%pK for DMA failed\n",
+			MAX_MAC_SIZE, areq_ctx->mac_buf);
+		rc = -ENOMEM;
+		goto aead_map_failure;
+	}
+	areq_ctx->mac_buf_dma_addr = dma_addr;
+
+	if (areq_ctx->ccm_hdr_size != ccm_header_size_null) {
+		void *addr = areq_ctx->ccm_config + CCM_CTR_COUNT_0_OFFSET;
+
+		dma_addr = dma_map_single(dev, addr, AES_BLOCK_SIZE,
+					  DMA_TO_DEVICE);
+
+		if (dma_mapping_error(dev, dma_addr)) {
+			dev_err(dev, "Mapping mac_buf %u B at va=%pK for DMA failed\n",
+				AES_BLOCK_SIZE, addr);
+			areq_ctx->ccm_iv0_dma_addr = 0;
+			rc = -ENOMEM;
+			goto aead_map_failure;
+		}
+		areq_ctx->ccm_iv0_dma_addr = dma_addr;
+
+		if (cc_set_aead_conf_buf(dev, areq_ctx, areq_ctx->ccm_config,
+					 &sg_data, req->assoclen)) {
+			rc = -ENOMEM;
+			goto aead_map_failure;
+		}
+	}
+
+	if (areq_ctx->cipher_mode == DRV_CIPHER_GCTR) {
+		dma_addr = dma_map_single(dev, areq_ctx->hkey, AES_BLOCK_SIZE,
+					  DMA_BIDIRECTIONAL);
+		if (dma_mapping_error(dev, dma_addr)) {
+			dev_err(dev, "Mapping hkey %u B at va=%pK for DMA failed\n",
+				AES_BLOCK_SIZE, areq_ctx->hkey);
+			rc = -ENOMEM;
+			goto aead_map_failure;
+		}
+		areq_ctx->hkey_dma_addr = dma_addr;
+
+		dma_addr = dma_map_single(dev, &areq_ctx->gcm_len_block,
+					  AES_BLOCK_SIZE, DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, dma_addr)) {
+			dev_err(dev, "Mapping gcm_len_block %u B at va=%pK for DMA failed\n",
+				AES_BLOCK_SIZE, &areq_ctx->gcm_len_block);
+			rc = -ENOMEM;
+			goto aead_map_failure;
+		}
+		areq_ctx->gcm_block_len_dma_addr = dma_addr;
+
+		dma_addr = dma_map_single(dev, areq_ctx->gcm_iv_inc1,
+					  AES_BLOCK_SIZE, DMA_TO_DEVICE);
+
+		if (dma_mapping_error(dev, dma_addr)) {
+			dev_err(dev, "Mapping gcm_iv_inc1 %u B at va=%pK for DMA failed\n",
+				AES_BLOCK_SIZE, (areq_ctx->gcm_iv_inc1));
+			areq_ctx->gcm_iv_inc1_dma_addr = 0;
+			rc = -ENOMEM;
+			goto aead_map_failure;
+		}
+		areq_ctx->gcm_iv_inc1_dma_addr = dma_addr;
+
+		dma_addr = dma_map_single(dev, areq_ctx->gcm_iv_inc2,
+					  AES_BLOCK_SIZE, DMA_TO_DEVICE);
+
+		if (dma_mapping_error(dev, dma_addr)) {
+			dev_err(dev, "Mapping gcm_iv_inc2 %u B at va=%pK for DMA failed\n",
+				AES_BLOCK_SIZE, (areq_ctx->gcm_iv_inc2));
+			areq_ctx->gcm_iv_inc2_dma_addr = 0;
+			rc = -ENOMEM;
+			goto aead_map_failure;
+		}
+		areq_ctx->gcm_iv_inc2_dma_addr = dma_addr;
+	}
+
+	size_to_map = req->cryptlen + req->assoclen;
+	if (areq_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_ENCRYPT)
+		size_to_map += authsize;
+
+	if (is_gcm4543)
+		size_to_map += crypto_aead_ivsize(tfm);
+	rc = cc_map_sg(dev, req->src, size_to_map, DMA_BIDIRECTIONAL,
+		       &areq_ctx->src.nents,
+		       (LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES +
+			LLI_MAX_NUM_OF_DATA_ENTRIES),
+		       &dummy, &mapped_nents);
+	if (rc) {
+		rc = -ENOMEM;
+		goto aead_map_failure;
+	}
+
+	if (areq_ctx->is_single_pass) {
+		/*
+		 * Create MLLI table for:
+		 *   (1) Assoc. data
+		 *   (2) Src/Dst SGLs
+		 *   Note: IV is contg. buffer (not an SGL)
+		 */
+		rc = cc_aead_chain_assoc(drvdata, req, &sg_data, true, false);
+		if (rc)
+			goto aead_map_failure;
+		rc = cc_aead_chain_iv(drvdata, req, &sg_data, true, false);
+		if (rc)
+			goto aead_map_failure;
+		rc = cc_aead_chain_data(drvdata, req, &sg_data, true, false);
+		if (rc)
+			goto aead_map_failure;
+	} else { /* DOUBLE-PASS flow */
+		/*
+		 * Prepare MLLI table(s) in this order:
+		 *
+		 * If ENCRYPT/DECRYPT (inplace):
+		 *   (1) MLLI table for assoc
+		 *   (2) IV entry (chained right after end of assoc)
+		 *   (3) MLLI for src/dst (inplace operation)
+		 *
+		 * If ENCRYPT (non-inplace)
+		 *   (1) MLLI table for assoc
+		 *   (2) IV entry (chained right after end of assoc)
+		 *   (3) MLLI for dst
+		 *   (4) MLLI for src
+		 *
+		 * If DECRYPT (non-inplace)
+		 *   (1) MLLI table for assoc
+		 *   (2) IV entry (chained right after end of assoc)
+		 *   (3) MLLI for src
+		 *   (4) MLLI for dst
+		 */
+		rc = cc_aead_chain_assoc(drvdata, req, &sg_data, false, true);
+		if (rc)
+			goto aead_map_failure;
+		rc = cc_aead_chain_iv(drvdata, req, &sg_data, false, true);
+		if (rc)
+			goto aead_map_failure;
+		rc = cc_aead_chain_data(drvdata, req, &sg_data, true, true);
+		if (rc)
+			goto aead_map_failure;
+	}
+
+	/* Mlli support -start building the MLLI according to the above
+	 * results
+	 */
+	if (areq_ctx->assoc_buff_type == CC_DMA_BUF_MLLI ||
+	    areq_ctx->data_buff_type == CC_DMA_BUF_MLLI) {
+		mlli_params->curr_pool = buff_mgr->mlli_buffs_pool;
+		rc = cc_generate_mlli(dev, &sg_data, mlli_params, flags);
+		if (rc)
+			goto aead_map_failure;
+
+		cc_update_aead_mlli_nents(drvdata, req);
+		dev_dbg(dev, "assoc params mn %d\n",
+			areq_ctx->assoc.mlli_nents);
+		dev_dbg(dev, "src params mn %d\n", areq_ctx->src.mlli_nents);
+		dev_dbg(dev, "dst params mn %d\n", areq_ctx->dst.mlli_nents);
+	}
+	return 0;
+
+aead_map_failure:
+	cc_unmap_aead_request(dev, req);
+	return rc;
+}
+
+int cc_map_hash_request_final(struct cc_drvdata *drvdata, void *ctx,
+			      struct scatterlist *src, unsigned int nbytes,
+			      bool do_update, gfp_t flags)
+{
+	struct ahash_req_ctx *areq_ctx = (struct ahash_req_ctx *)ctx;
+	struct device *dev = drvdata_to_dev(drvdata);
+	u8 *curr_buff = cc_hash_buf(areq_ctx);
+	u32 *curr_buff_cnt = cc_hash_buf_cnt(areq_ctx);
+	struct mlli_params *mlli_params = &areq_ctx->mlli_params;
+	struct buffer_array sg_data;
+	struct buff_mgr_handle *buff_mgr = drvdata->buff_mgr_handle;
+	u32 dummy = 0;
+	u32 mapped_nents = 0;
+
+	dev_dbg(dev, "final params : curr_buff=%pK curr_buff_cnt=0x%X nbytes = 0x%X src=%pK curr_index=%u\n",
+		curr_buff, *curr_buff_cnt, nbytes, src, areq_ctx->buff_index);
+	/* Init the type of the dma buffer */
+	areq_ctx->data_dma_buf_type = CC_DMA_BUF_NULL;
+	mlli_params->curr_pool = NULL;
+	sg_data.num_of_buffers = 0;
+	areq_ctx->in_nents = 0;
+
+	if (nbytes == 0 && *curr_buff_cnt == 0) {
+		/* nothing to do */
+		return 0;
+	}
+
+	/*TODO: copy data in case that buffer is enough for operation */
+	/* map the previous buffer */
+	if (*curr_buff_cnt) {
+		if (cc_set_hash_buf(dev, areq_ctx, curr_buff, *curr_buff_cnt,
+				    &sg_data)) {
+			return -ENOMEM;
+		}
+	}
+
+	if (src && nbytes > 0 && do_update) {
+		if (cc_map_sg(dev, src, nbytes, DMA_TO_DEVICE,
+			      &areq_ctx->in_nents, LLI_MAX_NUM_OF_DATA_ENTRIES,
+			      &dummy, &mapped_nents)) {
+			goto unmap_curr_buff;
+		}
+		if (src && mapped_nents == 1 &&
+		    areq_ctx->data_dma_buf_type == CC_DMA_BUF_NULL) {
+			memcpy(areq_ctx->buff_sg, src,
+			       sizeof(struct scatterlist));
+			areq_ctx->buff_sg->length = nbytes;
+			areq_ctx->curr_sg = areq_ctx->buff_sg;
+			areq_ctx->data_dma_buf_type = CC_DMA_BUF_DLLI;
+		} else {
+			areq_ctx->data_dma_buf_type = CC_DMA_BUF_MLLI;
+		}
+	}
+
+	/*build mlli */
+	if (areq_ctx->data_dma_buf_type == CC_DMA_BUF_MLLI) {
+		mlli_params->curr_pool = buff_mgr->mlli_buffs_pool;
+		/* add the src data to the sg_data */
+		cc_add_sg_entry(dev, &sg_data, areq_ctx->in_nents, src, nbytes,
+				0, true, &areq_ctx->mlli_nents);
+		if (cc_generate_mlli(dev, &sg_data, mlli_params, flags))
+			goto fail_unmap_din;
+	}
+	/* change the buffer index for the unmap function */
+	areq_ctx->buff_index = (areq_ctx->buff_index ^ 1);
+	dev_dbg(dev, "areq_ctx->data_dma_buf_type = %s\n",
+		cc_dma_buf_type(areq_ctx->data_dma_buf_type));
+	return 0;
+
+fail_unmap_din:
+	dma_unmap_sg(dev, src, areq_ctx->in_nents, DMA_TO_DEVICE);
+
+unmap_curr_buff:
+	if (*curr_buff_cnt)
+		dma_unmap_sg(dev, areq_ctx->buff_sg, 1, DMA_TO_DEVICE);
+
+	return -ENOMEM;
+}
+
+int cc_map_hash_request_update(struct cc_drvdata *drvdata, void *ctx,
+			       struct scatterlist *src, unsigned int nbytes,
+			       unsigned int block_size, gfp_t flags)
+{
+	struct ahash_req_ctx *areq_ctx = (struct ahash_req_ctx *)ctx;
+	struct device *dev = drvdata_to_dev(drvdata);
+	u8 *curr_buff = cc_hash_buf(areq_ctx);
+	u32 *curr_buff_cnt = cc_hash_buf_cnt(areq_ctx);
+	u8 *next_buff = cc_next_buf(areq_ctx);
+	u32 *next_buff_cnt = cc_next_buf_cnt(areq_ctx);
+	struct mlli_params *mlli_params = &areq_ctx->mlli_params;
+	unsigned int update_data_len;
+	u32 total_in_len = nbytes + *curr_buff_cnt;
+	struct buffer_array sg_data;
+	struct buff_mgr_handle *buff_mgr = drvdata->buff_mgr_handle;
+	unsigned int swap_index = 0;
+	u32 dummy = 0;
+	u32 mapped_nents = 0;
+
+	dev_dbg(dev, " update params : curr_buff=%pK curr_buff_cnt=0x%X nbytes=0x%X src=%pK curr_index=%u\n",
+		curr_buff, *curr_buff_cnt, nbytes, src, areq_ctx->buff_index);
+	/* Init the type of the dma buffer */
+	areq_ctx->data_dma_buf_type = CC_DMA_BUF_NULL;
+	mlli_params->curr_pool = NULL;
+	areq_ctx->curr_sg = NULL;
+	sg_data.num_of_buffers = 0;
+	areq_ctx->in_nents = 0;
+
+	if (total_in_len < block_size) {
+		dev_dbg(dev, " less than one block: curr_buff=%pK *curr_buff_cnt=0x%X copy_to=%pK\n",
+			curr_buff, *curr_buff_cnt, &curr_buff[*curr_buff_cnt]);
+		areq_ctx->in_nents =
+			cc_get_sgl_nents(dev, src, nbytes, &dummy, NULL);
+		sg_copy_to_buffer(src, areq_ctx->in_nents,
+				  &curr_buff[*curr_buff_cnt], nbytes);
+		*curr_buff_cnt += nbytes;
+		return 1;
+	}
+
+	/* Calculate the residue size*/
+	*next_buff_cnt = total_in_len & (block_size - 1);
+	/* update data len */
+	update_data_len = total_in_len - *next_buff_cnt;
+
+	dev_dbg(dev, " temp length : *next_buff_cnt=0x%X update_data_len=0x%X\n",
+		*next_buff_cnt, update_data_len);
+
+	/* Copy the new residue to next buffer */
+	if (*next_buff_cnt) {
+		dev_dbg(dev, " handle residue: next buff %pK skip data %u residue %u\n",
+			next_buff, (update_data_len - *curr_buff_cnt),
+			*next_buff_cnt);
+		cc_copy_sg_portion(dev, next_buff, src,
+				   (update_data_len - *curr_buff_cnt),
+				   nbytes, CC_SG_TO_BUF);
+		/* change the buffer index for next operation */
+		swap_index = 1;
+	}
+
+	if (*curr_buff_cnt) {
+		if (cc_set_hash_buf(dev, areq_ctx, curr_buff, *curr_buff_cnt,
+				    &sg_data)) {
+			return -ENOMEM;
+		}
+		/* change the buffer index for next operation */
+		swap_index = 1;
+	}
+
+	if (update_data_len > *curr_buff_cnt) {
+		if (cc_map_sg(dev, src, (update_data_len - *curr_buff_cnt),
+			      DMA_TO_DEVICE, &areq_ctx->in_nents,
+			      LLI_MAX_NUM_OF_DATA_ENTRIES, &dummy,
+			      &mapped_nents)) {
+			goto unmap_curr_buff;
+		}
+		if (mapped_nents == 1 &&
+		    areq_ctx->data_dma_buf_type == CC_DMA_BUF_NULL) {
+			/* only one entry in the SG and no previous data */
+			memcpy(areq_ctx->buff_sg, src,
+			       sizeof(struct scatterlist));
+			areq_ctx->buff_sg->length = update_data_len;
+			areq_ctx->data_dma_buf_type = CC_DMA_BUF_DLLI;
+			areq_ctx->curr_sg = areq_ctx->buff_sg;
+		} else {
+			areq_ctx->data_dma_buf_type = CC_DMA_BUF_MLLI;
+		}
+	}
+
+	if (areq_ctx->data_dma_buf_type == CC_DMA_BUF_MLLI) {
+		mlli_params->curr_pool = buff_mgr->mlli_buffs_pool;
+		/* add the src data to the sg_data */
+		cc_add_sg_entry(dev, &sg_data, areq_ctx->in_nents, src,
+				(update_data_len - *curr_buff_cnt), 0, true,
+				&areq_ctx->mlli_nents);
+		if (cc_generate_mlli(dev, &sg_data, mlli_params, flags))
+			goto fail_unmap_din;
+	}
+	areq_ctx->buff_index = (areq_ctx->buff_index ^ swap_index);
+
+	return 0;
+
+fail_unmap_din:
+	dma_unmap_sg(dev, src, areq_ctx->in_nents, DMA_TO_DEVICE);
+
+unmap_curr_buff:
+	if (*curr_buff_cnt)
+		dma_unmap_sg(dev, areq_ctx->buff_sg, 1, DMA_TO_DEVICE);
+
+	return -ENOMEM;
+}
+
+void cc_unmap_hash_request(struct device *dev, void *ctx,
+			   struct scatterlist *src, bool do_revert)
+{
+	struct ahash_req_ctx *areq_ctx = (struct ahash_req_ctx *)ctx;
+	u32 *prev_len = cc_next_buf_cnt(areq_ctx);
+
+	/*In case a pool was set, a table was
+	 *allocated and should be released
+	 */
+	if (areq_ctx->mlli_params.curr_pool) {
+		dev_dbg(dev, "free MLLI buffer: dma=%pad virt=%pK\n",
+			&areq_ctx->mlli_params.mlli_dma_addr,
+			areq_ctx->mlli_params.mlli_virt_addr);
+		dma_pool_free(areq_ctx->mlli_params.curr_pool,
+			      areq_ctx->mlli_params.mlli_virt_addr,
+			      areq_ctx->mlli_params.mlli_dma_addr);
+	}
+
+	if (src && areq_ctx->in_nents) {
+		dev_dbg(dev, "Unmapped sg src: virt=%pK dma=%pad len=0x%X\n",
+			sg_virt(src), &sg_dma_address(src), sg_dma_len(src));
+		dma_unmap_sg(dev, src,
+			     areq_ctx->in_nents, DMA_TO_DEVICE);
+	}
+
+	if (*prev_len) {
+		dev_dbg(dev, "Unmapped buffer: areq_ctx->buff_sg=%pK dma=%pad len 0x%X\n",
+			sg_virt(areq_ctx->buff_sg),
+			&sg_dma_address(areq_ctx->buff_sg),
+			sg_dma_len(areq_ctx->buff_sg));
+		dma_unmap_sg(dev, areq_ctx->buff_sg, 1, DMA_TO_DEVICE);
+		if (!do_revert) {
+			/* clean the previous data length for update
+			 * operation
+			 */
+			*prev_len = 0;
+		} else {
+			areq_ctx->buff_index ^= 1;
+		}
+	}
+}
+
+int cc_buffer_mgr_init(struct cc_drvdata *drvdata)
+{
+	struct buff_mgr_handle *buff_mgr_handle;
+	struct device *dev = drvdata_to_dev(drvdata);
+
+	buff_mgr_handle = kmalloc(sizeof(*buff_mgr_handle), GFP_KERNEL);
+	if (!buff_mgr_handle)
+		return -ENOMEM;
+
+	drvdata->buff_mgr_handle = buff_mgr_handle;
+
+	buff_mgr_handle->mlli_buffs_pool =
+		dma_pool_create("dx_single_mlli_tables", dev,
+				MAX_NUM_OF_TOTAL_MLLI_ENTRIES *
+				LLI_ENTRY_BYTE_SIZE,
+				MLLI_TABLE_MIN_ALIGNMENT, 0);
+
+	if (!buff_mgr_handle->mlli_buffs_pool)
+		goto error;
+
+	return 0;
+
+error:
+	cc_buffer_mgr_fini(drvdata);
+	return -ENOMEM;
+}
+
+int cc_buffer_mgr_fini(struct cc_drvdata *drvdata)
+{
+	struct buff_mgr_handle *buff_mgr_handle = drvdata->buff_mgr_handle;
+
+	if (buff_mgr_handle) {
+		dma_pool_destroy(buff_mgr_handle->mlli_buffs_pool);
+		kfree(drvdata->buff_mgr_handle);
+		drvdata->buff_mgr_handle = NULL;
+	}
+	return 0;
+}
diff --git a/drivers/crypto/ccree/cc_buffer_mgr.h b/drivers/crypto/ccree/cc_buffer_mgr.h
new file mode 100644
index 000000000000..3ec4b4db5247
--- /dev/null
+++ b/drivers/crypto/ccree/cc_buffer_mgr.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+/* \file cc_buffer_mgr.h
+ * Buffer Manager
+ */
+
+#ifndef __CC_BUFFER_MGR_H__
+#define __CC_BUFFER_MGR_H__
+
+#include <crypto/algapi.h>
+
+#include "cc_driver.h"
+
+enum cc_req_dma_buf_type {
+	CC_DMA_BUF_NULL = 0,
+	CC_DMA_BUF_DLLI,
+	CC_DMA_BUF_MLLI
+};
+
+enum cc_sg_cpy_direct {
+	CC_SG_TO_BUF = 0,
+	CC_SG_FROM_BUF = 1
+};
+
+struct cc_mlli {
+	cc_sram_addr_t sram_addr;
+	unsigned int nents; //sg nents
+	unsigned int mlli_nents; //mlli nents might be different than the above
+};
+
+struct mlli_params {
+	struct dma_pool *curr_pool;
+	u8 *mlli_virt_addr;
+	dma_addr_t mlli_dma_addr;
+	u32 mlli_len;
+};
+
+int cc_buffer_mgr_init(struct cc_drvdata *drvdata);
+
+int cc_buffer_mgr_fini(struct cc_drvdata *drvdata);
+
+int cc_map_cipher_request(struct cc_drvdata *drvdata, void *ctx,
+			  unsigned int ivsize, unsigned int nbytes,
+			  void *info, struct scatterlist *src,
+			  struct scatterlist *dst, gfp_t flags);
+
+void cc_unmap_cipher_request(struct device *dev, void *ctx, unsigned int ivsize,
+			     struct scatterlist *src, struct scatterlist *dst);
+
+int cc_map_aead_request(struct cc_drvdata *drvdata, struct aead_request *req);
+
+void cc_unmap_aead_request(struct device *dev, struct aead_request *req);
+
+int cc_map_hash_request_final(struct cc_drvdata *drvdata, void *ctx,
+			      struct scatterlist *src, unsigned int nbytes,
+			      bool do_update, gfp_t flags);
+
+int cc_map_hash_request_update(struct cc_drvdata *drvdata, void *ctx,
+			       struct scatterlist *src, unsigned int nbytes,
+			       unsigned int block_size, gfp_t flags);
+
+void cc_unmap_hash_request(struct device *dev, void *ctx,
+			   struct scatterlist *src, bool do_revert);
+
+void cc_copy_sg_portion(struct device *dev, u8 *dest, struct scatterlist *sg,
+			u32 to_skip, u32 end, enum cc_sg_cpy_direct direct);
+
+void cc_zero_sgl(struct scatterlist *sgl, u32 data_len);
+
+#endif /*__BUFFER_MGR_H__*/
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
new file mode 100644
index 000000000000..df98f7afe645
--- /dev/null
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -0,0 +1,1150 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/des.h>
+#include <crypto/xts.h>
+#include <crypto/scatterwalk.h>
+
+#include "cc_driver.h"
+#include "cc_lli_defs.h"
+#include "cc_buffer_mgr.h"
+#include "cc_cipher.h"
+#include "cc_request_mgr.h"
+
+#define MAX_ABLKCIPHER_SEQ_LEN 6
+
+#define template_skcipher	template_u.skcipher
+
+#define CC_MIN_AES_XTS_SIZE 0x10
+#define CC_MAX_AES_XTS_SIZE 0x2000
+struct cc_cipher_handle {
+	struct list_head alg_list;
+};
+
+struct cc_user_key_info {
+	u8 *key;
+	dma_addr_t key_dma_addr;
+};
+
+struct cc_hw_key_info {
+	enum cc_hw_crypto_key key1_slot;
+	enum cc_hw_crypto_key key2_slot;
+};
+
+struct cc_cipher_ctx {
+	struct cc_drvdata *drvdata;
+	int keylen;
+	int key_round_number;
+	int cipher_mode;
+	int flow_mode;
+	unsigned int flags;
+	struct cc_user_key_info user;
+	struct cc_hw_key_info hw;
+	struct crypto_shash *shash_tfm;
+};
+
+static void cc_cipher_complete(struct device *dev, void *cc_req, int err);
+
+static int validate_keys_sizes(struct cc_cipher_ctx *ctx_p, u32 size)
+{
+	switch (ctx_p->flow_mode) {
+	case S_DIN_to_AES:
+		switch (size) {
+		case CC_AES_128_BIT_KEY_SIZE:
+		case CC_AES_192_BIT_KEY_SIZE:
+			if (ctx_p->cipher_mode != DRV_CIPHER_XTS &&
+			    ctx_p->cipher_mode != DRV_CIPHER_ESSIV &&
+			    ctx_p->cipher_mode != DRV_CIPHER_BITLOCKER)
+				return 0;
+			break;
+		case CC_AES_256_BIT_KEY_SIZE:
+			return 0;
+		case (CC_AES_192_BIT_KEY_SIZE * 2):
+		case (CC_AES_256_BIT_KEY_SIZE * 2):
+			if (ctx_p->cipher_mode == DRV_CIPHER_XTS ||
+			    ctx_p->cipher_mode == DRV_CIPHER_ESSIV ||
+			    ctx_p->cipher_mode == DRV_CIPHER_BITLOCKER)
+				return 0;
+			break;
+		default:
+			break;
+		}
+	case S_DIN_to_DES:
+		if (size == DES3_EDE_KEY_SIZE || size == DES_KEY_SIZE)
+			return 0;
+		break;
+	default:
+		break;
+	}
+	return -EINVAL;
+}
+
+static int validate_data_size(struct cc_cipher_ctx *ctx_p,
+			      unsigned int size)
+{
+	switch (ctx_p->flow_mode) {
+	case S_DIN_to_AES:
+		switch (ctx_p->cipher_mode) {
+		case DRV_CIPHER_XTS:
+			if (size >= CC_MIN_AES_XTS_SIZE &&
+			    size <= CC_MAX_AES_XTS_SIZE &&
+			    IS_ALIGNED(size, AES_BLOCK_SIZE))
+				return 0;
+			break;
+		case DRV_CIPHER_CBC_CTS:
+			if (size >= AES_BLOCK_SIZE)
+				return 0;
+			break;
+		case DRV_CIPHER_OFB:
+		case DRV_CIPHER_CTR:
+				return 0;
+		case DRV_CIPHER_ECB:
+		case DRV_CIPHER_CBC:
+		case DRV_CIPHER_ESSIV:
+		case DRV_CIPHER_BITLOCKER:
+			if (IS_ALIGNED(size, AES_BLOCK_SIZE))
+				return 0;
+			break;
+		default:
+			break;
+		}
+		break;
+	case S_DIN_to_DES:
+		if (IS_ALIGNED(size, DES_BLOCK_SIZE))
+			return 0;
+		break;
+	default:
+		break;
+	}
+	return -EINVAL;
+}
+
+static int cc_cipher_init(struct crypto_tfm *tfm)
+{
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct cc_crypto_alg *cc_alg =
+			container_of(tfm->__crt_alg, struct cc_crypto_alg,
+				     skcipher_alg.base);
+	struct device *dev = drvdata_to_dev(cc_alg->drvdata);
+	unsigned int max_key_buf_size = cc_alg->skcipher_alg.max_keysize;
+	int rc = 0;
+
+	dev_dbg(dev, "Initializing context @%p for %s\n", ctx_p,
+		crypto_tfm_alg_name(tfm));
+
+	crypto_skcipher_set_reqsize(__crypto_skcipher_cast(tfm),
+				    sizeof(struct cipher_req_ctx));
+
+	ctx_p->cipher_mode = cc_alg->cipher_mode;
+	ctx_p->flow_mode = cc_alg->flow_mode;
+	ctx_p->drvdata = cc_alg->drvdata;
+
+	/* Allocate key buffer, cache line aligned */
+	ctx_p->user.key = kmalloc(max_key_buf_size, GFP_KERNEL);
+	if (!ctx_p->user.key)
+		return -ENOMEM;
+
+	dev_dbg(dev, "Allocated key buffer in context. key=@%p\n",
+		ctx_p->user.key);
+
+	/* Map key buffer */
+	ctx_p->user.key_dma_addr = dma_map_single(dev, (void *)ctx_p->user.key,
+						  max_key_buf_size,
+						  DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, ctx_p->user.key_dma_addr)) {
+		dev_err(dev, "Mapping Key %u B at va=%pK for DMA failed\n",
+			max_key_buf_size, ctx_p->user.key);
+		return -ENOMEM;
+	}
+	dev_dbg(dev, "Mapped key %u B at va=%pK to dma=%pad\n",
+		max_key_buf_size, ctx_p->user.key, &ctx_p->user.key_dma_addr);
+
+	if (ctx_p->cipher_mode == DRV_CIPHER_ESSIV) {
+		/* Alloc hash tfm for essiv */
+		ctx_p->shash_tfm = crypto_alloc_shash("sha256-generic", 0, 0);
+		if (IS_ERR(ctx_p->shash_tfm)) {
+			dev_err(dev, "Error allocating hash tfm for ESSIV.\n");
+			return PTR_ERR(ctx_p->shash_tfm);
+		}
+	}
+
+	return rc;
+}
+
+static void cc_cipher_exit(struct crypto_tfm *tfm)
+{
+	struct crypto_alg *alg = tfm->__crt_alg;
+	struct cc_crypto_alg *cc_alg =
+			container_of(alg, struct cc_crypto_alg,
+				     skcipher_alg.base);
+	unsigned int max_key_buf_size = cc_alg->skcipher_alg.max_keysize;
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+
+	dev_dbg(dev, "Clearing context @%p for %s\n",
+		crypto_tfm_ctx(tfm), crypto_tfm_alg_name(tfm));
+
+	if (ctx_p->cipher_mode == DRV_CIPHER_ESSIV) {
+		/* Free hash tfm for essiv */
+		crypto_free_shash(ctx_p->shash_tfm);
+		ctx_p->shash_tfm = NULL;
+	}
+
+	/* Unmap key buffer */
+	dma_unmap_single(dev, ctx_p->user.key_dma_addr, max_key_buf_size,
+			 DMA_TO_DEVICE);
+	dev_dbg(dev, "Unmapped key buffer key_dma_addr=%pad\n",
+		&ctx_p->user.key_dma_addr);
+
+	/* Free key buffer in context */
+	kzfree(ctx_p->user.key);
+	dev_dbg(dev, "Free key buffer in context. key=@%p\n", ctx_p->user.key);
+}
+
+struct tdes_keys {
+	u8	key1[DES_KEY_SIZE];
+	u8	key2[DES_KEY_SIZE];
+	u8	key3[DES_KEY_SIZE];
+};
+
+static enum cc_hw_crypto_key hw_key_to_cc_hw_key(int slot_num)
+{
+	switch (slot_num) {
+	case 0:
+		return KFDE0_KEY;
+	case 1:
+		return KFDE1_KEY;
+	case 2:
+		return KFDE2_KEY;
+	case 3:
+		return KFDE3_KEY;
+	}
+	return END_OF_KEYS;
+}
+
+static int cc_cipher_setkey(struct crypto_skcipher *sktfm, const u8 *key,
+			    unsigned int keylen)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(sktfm);
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+	u32 tmp[DES3_EDE_EXPKEY_WORDS];
+	struct cc_crypto_alg *cc_alg =
+			container_of(tfm->__crt_alg, struct cc_crypto_alg,
+				     skcipher_alg.base);
+	unsigned int max_key_buf_size = cc_alg->skcipher_alg.max_keysize;
+
+	dev_dbg(dev, "Setting key in context @%p for %s. keylen=%u\n",
+		ctx_p, crypto_tfm_alg_name(tfm), keylen);
+	dump_byte_array("key", (u8 *)key, keylen);
+
+	/* STAT_PHASE_0: Init and sanity checks */
+
+	if (validate_keys_sizes(ctx_p, keylen)) {
+		dev_err(dev, "Unsupported key size %d.\n", keylen);
+		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	if (cc_is_hw_key(tfm)) {
+		/* setting HW key slots */
+		struct arm_hw_key_info *hki = (struct arm_hw_key_info *)key;
+
+		if (ctx_p->flow_mode != S_DIN_to_AES) {
+			dev_err(dev, "HW key not supported for non-AES flows\n");
+			return -EINVAL;
+		}
+
+		ctx_p->hw.key1_slot = hw_key_to_cc_hw_key(hki->hw_key1);
+		if (ctx_p->hw.key1_slot == END_OF_KEYS) {
+			dev_err(dev, "Unsupported hw key1 number (%d)\n",
+				hki->hw_key1);
+			return -EINVAL;
+		}
+
+		if (ctx_p->cipher_mode == DRV_CIPHER_XTS ||
+		    ctx_p->cipher_mode == DRV_CIPHER_ESSIV ||
+		    ctx_p->cipher_mode == DRV_CIPHER_BITLOCKER) {
+			if (hki->hw_key1 == hki->hw_key2) {
+				dev_err(dev, "Illegal hw key numbers (%d,%d)\n",
+					hki->hw_key1, hki->hw_key2);
+				return -EINVAL;
+			}
+			ctx_p->hw.key2_slot =
+				hw_key_to_cc_hw_key(hki->hw_key2);
+			if (ctx_p->hw.key2_slot == END_OF_KEYS) {
+				dev_err(dev, "Unsupported hw key2 number (%d)\n",
+					hki->hw_key2);
+				return -EINVAL;
+			}
+		}
+
+		ctx_p->keylen = keylen;
+		dev_dbg(dev, "cc_is_hw_key ret 0");
+
+		return 0;
+	}
+
+	/*
+	 * Verify DES weak keys
+	 * Note that we're dropping the expanded key since the
+	 * HW does the expansion on its own.
+	 */
+	if (ctx_p->flow_mode == S_DIN_to_DES) {
+		if (keylen == DES3_EDE_KEY_SIZE &&
+		    __des3_ede_setkey(tmp, &tfm->crt_flags, key,
+				      DES3_EDE_KEY_SIZE)) {
+			dev_dbg(dev, "weak 3DES key");
+			return -EINVAL;
+		} else if (!des_ekey(tmp, key) &&
+		    (crypto_tfm_get_flags(tfm) & CRYPTO_TFM_REQ_WEAK_KEY)) {
+			tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
+			dev_dbg(dev, "weak DES key");
+			return -EINVAL;
+		}
+	}
+
+	if (ctx_p->cipher_mode == DRV_CIPHER_XTS &&
+	    xts_check_key(tfm, key, keylen)) {
+		dev_dbg(dev, "weak XTS key");
+		return -EINVAL;
+	}
+
+	/* STAT_PHASE_1: Copy key to ctx */
+	dma_sync_single_for_cpu(dev, ctx_p->user.key_dma_addr,
+				max_key_buf_size, DMA_TO_DEVICE);
+
+	memcpy(ctx_p->user.key, key, keylen);
+	if (keylen == 24)
+		memset(ctx_p->user.key + 24, 0, CC_AES_KEY_SIZE_MAX - 24);
+
+	if (ctx_p->cipher_mode == DRV_CIPHER_ESSIV) {
+		/* sha256 for key2 - use sw implementation */
+		int key_len = keylen >> 1;
+		int err;
+
+		SHASH_DESC_ON_STACK(desc, ctx_p->shash_tfm);
+
+		desc->tfm = ctx_p->shash_tfm;
+
+		err = crypto_shash_digest(desc, ctx_p->user.key, key_len,
+					  ctx_p->user.key + key_len);
+		if (err) {
+			dev_err(dev, "Failed to hash ESSIV key.\n");
+			return err;
+		}
+	}
+	dma_sync_single_for_device(dev, ctx_p->user.key_dma_addr,
+				   max_key_buf_size, DMA_TO_DEVICE);
+	ctx_p->keylen = keylen;
+
+	dev_dbg(dev, "return safely");
+	return 0;
+}
+
+static void cc_setup_cipher_desc(struct crypto_tfm *tfm,
+				 struct cipher_req_ctx *req_ctx,
+				 unsigned int ivsize, unsigned int nbytes,
+				 struct cc_hw_desc desc[],
+				 unsigned int *seq_size)
+{
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+	int cipher_mode = ctx_p->cipher_mode;
+	int flow_mode = ctx_p->flow_mode;
+	int direction = req_ctx->gen_ctx.op_type;
+	dma_addr_t key_dma_addr = ctx_p->user.key_dma_addr;
+	unsigned int key_len = ctx_p->keylen;
+	dma_addr_t iv_dma_addr = req_ctx->gen_ctx.iv_dma_addr;
+	unsigned int du_size = nbytes;
+
+	struct cc_crypto_alg *cc_alg =
+		container_of(tfm->__crt_alg, struct cc_crypto_alg,
+			     skcipher_alg.base);
+
+	if (cc_alg->data_unit)
+		du_size = cc_alg->data_unit;
+
+	switch (cipher_mode) {
+	case DRV_CIPHER_CBC:
+	case DRV_CIPHER_CBC_CTS:
+	case DRV_CIPHER_CTR:
+	case DRV_CIPHER_OFB:
+		/* Load cipher state */
+		hw_desc_init(&desc[*seq_size]);
+		set_din_type(&desc[*seq_size], DMA_DLLI, iv_dma_addr, ivsize,
+			     NS_BIT);
+		set_cipher_config0(&desc[*seq_size], direction);
+		set_flow_mode(&desc[*seq_size], flow_mode);
+		set_cipher_mode(&desc[*seq_size], cipher_mode);
+		if (cipher_mode == DRV_CIPHER_CTR ||
+		    cipher_mode == DRV_CIPHER_OFB) {
+			set_setup_mode(&desc[*seq_size], SETUP_LOAD_STATE1);
+		} else {
+			set_setup_mode(&desc[*seq_size], SETUP_LOAD_STATE0);
+		}
+		(*seq_size)++;
+		/*FALLTHROUGH*/
+	case DRV_CIPHER_ECB:
+		/* Load key */
+		hw_desc_init(&desc[*seq_size]);
+		set_cipher_mode(&desc[*seq_size], cipher_mode);
+		set_cipher_config0(&desc[*seq_size], direction);
+		if (flow_mode == S_DIN_to_AES) {
+			if (cc_is_hw_key(tfm)) {
+				set_hw_crypto_key(&desc[*seq_size],
+						  ctx_p->hw.key1_slot);
+			} else {
+				set_din_type(&desc[*seq_size], DMA_DLLI,
+					     key_dma_addr, ((key_len == 24) ?
+							    AES_MAX_KEY_SIZE :
+							    key_len), NS_BIT);
+			}
+			set_key_size_aes(&desc[*seq_size], key_len);
+		} else {
+			/*des*/
+			set_din_type(&desc[*seq_size], DMA_DLLI, key_dma_addr,
+				     key_len, NS_BIT);
+			set_key_size_des(&desc[*seq_size], key_len);
+		}
+		set_flow_mode(&desc[*seq_size], flow_mode);
+		set_setup_mode(&desc[*seq_size], SETUP_LOAD_KEY0);
+		(*seq_size)++;
+		break;
+	case DRV_CIPHER_XTS:
+	case DRV_CIPHER_ESSIV:
+	case DRV_CIPHER_BITLOCKER:
+		/* Load AES key */
+		hw_desc_init(&desc[*seq_size]);
+		set_cipher_mode(&desc[*seq_size], cipher_mode);
+		set_cipher_config0(&desc[*seq_size], direction);
+		if (cc_is_hw_key(tfm)) {
+			set_hw_crypto_key(&desc[*seq_size],
+					  ctx_p->hw.key1_slot);
+		} else {
+			set_din_type(&desc[*seq_size], DMA_DLLI, key_dma_addr,
+				     (key_len / 2), NS_BIT);
+		}
+		set_key_size_aes(&desc[*seq_size], (key_len / 2));
+		set_flow_mode(&desc[*seq_size], flow_mode);
+		set_setup_mode(&desc[*seq_size], SETUP_LOAD_KEY0);
+		(*seq_size)++;
+
+		/* load XEX key */
+		hw_desc_init(&desc[*seq_size]);
+		set_cipher_mode(&desc[*seq_size], cipher_mode);
+		set_cipher_config0(&desc[*seq_size], direction);
+		if (cc_is_hw_key(tfm)) {
+			set_hw_crypto_key(&desc[*seq_size],
+					  ctx_p->hw.key2_slot);
+		} else {
+			set_din_type(&desc[*seq_size], DMA_DLLI,
+				     (key_dma_addr + (key_len / 2)),
+				     (key_len / 2), NS_BIT);
+		}
+		set_xex_data_unit_size(&desc[*seq_size], du_size);
+		set_flow_mode(&desc[*seq_size], S_DIN_to_AES2);
+		set_key_size_aes(&desc[*seq_size], (key_len / 2));
+		set_setup_mode(&desc[*seq_size], SETUP_LOAD_XEX_KEY);
+		(*seq_size)++;
+
+		/* Set state */
+		hw_desc_init(&desc[*seq_size]);
+		set_setup_mode(&desc[*seq_size], SETUP_LOAD_STATE1);
+		set_cipher_mode(&desc[*seq_size], cipher_mode);
+		set_cipher_config0(&desc[*seq_size], direction);
+		set_key_size_aes(&desc[*seq_size], (key_len / 2));
+		set_flow_mode(&desc[*seq_size], flow_mode);
+		set_din_type(&desc[*seq_size], DMA_DLLI, iv_dma_addr,
+			     CC_AES_BLOCK_SIZE, NS_BIT);
+		(*seq_size)++;
+		break;
+	default:
+		dev_err(dev, "Unsupported cipher mode (%d)\n", cipher_mode);
+	}
+}
+
+static void cc_setup_cipher_data(struct crypto_tfm *tfm,
+				 struct cipher_req_ctx *req_ctx,
+				 struct scatterlist *dst,
+				 struct scatterlist *src, unsigned int nbytes,
+				 void *areq, struct cc_hw_desc desc[],
+				 unsigned int *seq_size)
+{
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+	unsigned int flow_mode = ctx_p->flow_mode;
+
+	switch (ctx_p->flow_mode) {
+	case S_DIN_to_AES:
+		flow_mode = DIN_AES_DOUT;
+		break;
+	case S_DIN_to_DES:
+		flow_mode = DIN_DES_DOUT;
+		break;
+	default:
+		dev_err(dev, "invalid flow mode, flow_mode = %d\n", flow_mode);
+		return;
+	}
+	/* Process */
+	if (req_ctx->dma_buf_type == CC_DMA_BUF_DLLI) {
+		dev_dbg(dev, " data params addr %pad length 0x%X\n",
+			&sg_dma_address(src), nbytes);
+		dev_dbg(dev, " data params addr %pad length 0x%X\n",
+			&sg_dma_address(dst), nbytes);
+		hw_desc_init(&desc[*seq_size]);
+		set_din_type(&desc[*seq_size], DMA_DLLI, sg_dma_address(src),
+			     nbytes, NS_BIT);
+		set_dout_dlli(&desc[*seq_size], sg_dma_address(dst),
+			      nbytes, NS_BIT, (!areq ? 0 : 1));
+		if (areq)
+			set_queue_last_ind(ctx_p->drvdata, &desc[*seq_size]);
+
+		set_flow_mode(&desc[*seq_size], flow_mode);
+		(*seq_size)++;
+	} else {
+		/* bypass */
+		dev_dbg(dev, " bypass params addr %pad length 0x%X addr 0x%08X\n",
+			&req_ctx->mlli_params.mlli_dma_addr,
+			req_ctx->mlli_params.mlli_len,
+			(unsigned int)ctx_p->drvdata->mlli_sram_addr);
+		hw_desc_init(&desc[*seq_size]);
+		set_din_type(&desc[*seq_size], DMA_DLLI,
+			     req_ctx->mlli_params.mlli_dma_addr,
+			     req_ctx->mlli_params.mlli_len, NS_BIT);
+		set_dout_sram(&desc[*seq_size],
+			      ctx_p->drvdata->mlli_sram_addr,
+			      req_ctx->mlli_params.mlli_len);
+		set_flow_mode(&desc[*seq_size], BYPASS);
+		(*seq_size)++;
+
+		hw_desc_init(&desc[*seq_size]);
+		set_din_type(&desc[*seq_size], DMA_MLLI,
+			     ctx_p->drvdata->mlli_sram_addr,
+			     req_ctx->in_mlli_nents, NS_BIT);
+		if (req_ctx->out_nents == 0) {
+			dev_dbg(dev, " din/dout params addr 0x%08X addr 0x%08X\n",
+				(unsigned int)ctx_p->drvdata->mlli_sram_addr,
+				(unsigned int)ctx_p->drvdata->mlli_sram_addr);
+			set_dout_mlli(&desc[*seq_size],
+				      ctx_p->drvdata->mlli_sram_addr,
+				      req_ctx->in_mlli_nents, NS_BIT,
+				      (!areq ? 0 : 1));
+		} else {
+			dev_dbg(dev, " din/dout params addr 0x%08X addr 0x%08X\n",
+				(unsigned int)ctx_p->drvdata->mlli_sram_addr,
+				(unsigned int)ctx_p->drvdata->mlli_sram_addr +
+				(u32)LLI_ENTRY_BYTE_SIZE * req_ctx->in_nents);
+			set_dout_mlli(&desc[*seq_size],
+				      (ctx_p->drvdata->mlli_sram_addr +
+				       (LLI_ENTRY_BYTE_SIZE *
+					req_ctx->in_mlli_nents)),
+				      req_ctx->out_mlli_nents, NS_BIT,
+				      (!areq ? 0 : 1));
+		}
+		if (areq)
+			set_queue_last_ind(ctx_p->drvdata, &desc[*seq_size]);
+
+		set_flow_mode(&desc[*seq_size], flow_mode);
+		(*seq_size)++;
+	}
+}
+
+static void cc_cipher_complete(struct device *dev, void *cc_req, int err)
+{
+	struct skcipher_request *req = (struct skcipher_request *)cc_req;
+	struct scatterlist *dst = req->dst;
+	struct scatterlist *src = req->src;
+	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
+
+	cc_unmap_cipher_request(dev, req_ctx, ivsize, src, dst);
+	kzfree(req_ctx->iv);
+
+	/*
+	 * The crypto API expects us to set the req->iv to the last
+	 * ciphertext block. For encrypt, simply copy from the result.
+	 * For decrypt, we must copy from a saved buffer since this
+	 * could be an in-place decryption operation and the src is
+	 * lost by this point.
+	 */
+	if (req_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT)  {
+		memcpy(req->iv, req_ctx->backup_info, ivsize);
+		kzfree(req_ctx->backup_info);
+	} else if (!err) {
+		scatterwalk_map_and_copy(req->iv, req->dst,
+					 (req->cryptlen - ivsize),
+					 ivsize, 0);
+	}
+
+	skcipher_request_complete(req, err);
+}
+
+static int cc_cipher_process(struct skcipher_request *req,
+			     enum drv_crypto_direction direction)
+{
+	struct crypto_skcipher *sk_tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(sk_tfm);
+	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
+	unsigned int ivsize = crypto_skcipher_ivsize(sk_tfm);
+	struct scatterlist *dst = req->dst;
+	struct scatterlist *src = req->src;
+	unsigned int nbytes = req->cryptlen;
+	void *iv = req->iv;
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+	struct cc_hw_desc desc[MAX_ABLKCIPHER_SEQ_LEN];
+	struct cc_crypto_req cc_req = {};
+	int rc, cts_restore_flag = 0;
+	unsigned int seq_len = 0;
+	gfp_t flags = cc_gfp_flags(&req->base);
+
+	dev_dbg(dev, "%s req=%p iv=%p nbytes=%d\n",
+		((direction == DRV_CRYPTO_DIRECTION_ENCRYPT) ?
+		"Encrypt" : "Decrypt"), req, iv, nbytes);
+
+	/* STAT_PHASE_0: Init and sanity checks */
+
+	/* TODO: check data length according to mode */
+	if (validate_data_size(ctx_p, nbytes)) {
+		dev_err(dev, "Unsupported data size %d.\n", nbytes);
+		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_BLOCK_LEN);
+		rc = -EINVAL;
+		goto exit_process;
+	}
+	if (nbytes == 0) {
+		/* No data to process is valid */
+		rc = 0;
+		goto exit_process;
+	}
+
+	/* The IV we are handed may be allocted from the stack so
+	 * we must copy it to a DMAable buffer before use.
+	 */
+	req_ctx->iv = kmemdup(iv, ivsize, flags);
+	if (!req_ctx->iv) {
+		rc = -ENOMEM;
+		goto exit_process;
+	}
+
+	/*For CTS in case of data size aligned to 16 use CBC mode*/
+	if (((nbytes % AES_BLOCK_SIZE) == 0) &&
+	    ctx_p->cipher_mode == DRV_CIPHER_CBC_CTS) {
+		ctx_p->cipher_mode = DRV_CIPHER_CBC;
+		cts_restore_flag = 1;
+	}
+
+	/* Setup request structure */
+	cc_req.user_cb = (void *)cc_cipher_complete;
+	cc_req.user_arg = (void *)req;
+
+#ifdef ENABLE_CYCLE_COUNT
+	cc_req.op_type = (direction == DRV_CRYPTO_DIRECTION_DECRYPT) ?
+		STAT_OP_TYPE_DECODE : STAT_OP_TYPE_ENCODE;
+
+#endif
+
+	/* Setup request context */
+	req_ctx->gen_ctx.op_type = direction;
+
+	/* STAT_PHASE_1: Map buffers */
+
+	rc = cc_map_cipher_request(ctx_p->drvdata, req_ctx, ivsize, nbytes,
+				      req_ctx->iv, src, dst, flags);
+	if (rc) {
+		dev_err(dev, "map_request() failed\n");
+		goto exit_process;
+	}
+
+	/* STAT_PHASE_2: Create sequence */
+
+	/* Setup processing */
+	cc_setup_cipher_desc(tfm, req_ctx, ivsize, nbytes, desc, &seq_len);
+	/* Data processing */
+	cc_setup_cipher_data(tfm, req_ctx, dst, src, nbytes, req, desc,
+			     &seq_len);
+
+	/* do we need to generate IV? */
+	if (req_ctx->is_giv) {
+		cc_req.ivgen_dma_addr[0] = req_ctx->gen_ctx.iv_dma_addr;
+		cc_req.ivgen_dma_addr_len = 1;
+		/* set the IV size (8/16 B long)*/
+		cc_req.ivgen_size = ivsize;
+	}
+
+	/* STAT_PHASE_3: Lock HW and push sequence */
+
+	rc = cc_send_request(ctx_p->drvdata, &cc_req, desc, seq_len,
+			     &req->base);
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		/* Failed to send the request or request completed
+		 * synchronously
+		 */
+		cc_unmap_cipher_request(dev, req_ctx, ivsize, src, dst);
+	}
+
+exit_process:
+	if (cts_restore_flag)
+		ctx_p->cipher_mode = DRV_CIPHER_CBC_CTS;
+
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		kzfree(req_ctx->backup_info);
+		kzfree(req_ctx->iv);
+	}
+
+	return rc;
+}
+
+static int cc_cipher_encrypt(struct skcipher_request *req)
+{
+	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
+
+	req_ctx->is_giv = false;
+	req_ctx->backup_info = NULL;
+
+	return cc_cipher_process(req, DRV_CRYPTO_DIRECTION_ENCRYPT);
+}
+
+static int cc_cipher_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *sk_tfm = crypto_skcipher_reqtfm(req);
+	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
+	unsigned int ivsize = crypto_skcipher_ivsize(sk_tfm);
+	gfp_t flags = cc_gfp_flags(&req->base);
+
+	/*
+	 * Allocate and save the last IV sized bytes of the source, which will
+	 * be lost in case of in-place decryption and might be needed for CTS.
+	 */
+	req_ctx->backup_info = kmalloc(ivsize, flags);
+	if (!req_ctx->backup_info)
+		return -ENOMEM;
+
+	scatterwalk_map_and_copy(req_ctx->backup_info, req->src,
+				 (req->cryptlen - ivsize), ivsize, 0);
+	req_ctx->is_giv = false;
+
+	return cc_cipher_process(req, DRV_CRYPTO_DIRECTION_DECRYPT);
+}
+
+/* Block cipher alg */
+static const struct cc_alg_template skcipher_algs[] = {
+	{
+		.name = "xts(aes)",
+		.driver_name = "xts-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE * 2,
+			.max_keysize = AES_MAX_KEY_SIZE * 2,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_XTS,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "xts512(aes)",
+		.driver_name = "xts-aes-du512-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE * 2,
+			.max_keysize = AES_MAX_KEY_SIZE * 2,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_XTS,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 512,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "xts4096(aes)",
+		.driver_name = "xts-aes-du4096-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE * 2,
+			.max_keysize = AES_MAX_KEY_SIZE * 2,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_XTS,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 4096,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "essiv(aes)",
+		.driver_name = "essiv-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE * 2,
+			.max_keysize = AES_MAX_KEY_SIZE * 2,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_ESSIV,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "essiv512(aes)",
+		.driver_name = "essiv-aes-du512-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE * 2,
+			.max_keysize = AES_MAX_KEY_SIZE * 2,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_ESSIV,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 512,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "essiv4096(aes)",
+		.driver_name = "essiv-aes-du4096-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE * 2,
+			.max_keysize = AES_MAX_KEY_SIZE * 2,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_ESSIV,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 4096,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "bitlocker(aes)",
+		.driver_name = "bitlocker-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE * 2,
+			.max_keysize = AES_MAX_KEY_SIZE * 2,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_BITLOCKER,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "bitlocker512(aes)",
+		.driver_name = "bitlocker-aes-du512-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE * 2,
+			.max_keysize = AES_MAX_KEY_SIZE * 2,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_BITLOCKER,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 512,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "bitlocker4096(aes)",
+		.driver_name = "bitlocker-aes-du4096-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE * 2,
+			.max_keysize = AES_MAX_KEY_SIZE * 2,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_BITLOCKER,
+		.flow_mode = S_DIN_to_AES,
+		.data_unit = 4096,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "ecb(aes)",
+		.driver_name = "ecb-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = 0,
+			},
+		.cipher_mode = DRV_CIPHER_ECB,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "cbc(aes)",
+		.driver_name = "cbc-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+		},
+		.cipher_mode = DRV_CIPHER_CBC,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "ofb(aes)",
+		.driver_name = "ofb-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_OFB,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "cts1(cbc(aes))",
+		.driver_name = "cts1-cbc-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_CBC_CTS,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "ctr(aes)",
+		.driver_name = "ctr-aes-ccree",
+		.blocksize = 1,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_CTR,
+		.flow_mode = S_DIN_to_AES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "cbc(des3_ede)",
+		.driver_name = "cbc-3des-ccree",
+		.blocksize = DES3_EDE_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_CBC,
+		.flow_mode = S_DIN_to_DES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "ecb(des3_ede)",
+		.driver_name = "ecb-3des-ccree",
+		.blocksize = DES3_EDE_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize = 0,
+			},
+		.cipher_mode = DRV_CIPHER_ECB,
+		.flow_mode = S_DIN_to_DES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "cbc(des)",
+		.driver_name = "cbc-des-ccree",
+		.blocksize = DES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.ivsize = DES_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_CBC,
+		.flow_mode = S_DIN_to_DES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "ecb(des)",
+		.driver_name = "ecb-des-ccree",
+		.blocksize = DES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+		.template_skcipher = {
+			.setkey = cc_cipher_setkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.ivsize = 0,
+			},
+		.cipher_mode = DRV_CIPHER_ECB,
+		.flow_mode = S_DIN_to_DES,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+};
+
+static struct cc_crypto_alg *cc_create_alg(const struct cc_alg_template *tmpl,
+					   struct device *dev)
+{
+	struct cc_crypto_alg *t_alg;
+	struct skcipher_alg *alg;
+
+	t_alg = kzalloc(sizeof(*t_alg), GFP_KERNEL);
+	if (!t_alg)
+		return ERR_PTR(-ENOMEM);
+
+	alg = &t_alg->skcipher_alg;
+
+	memcpy(alg, &tmpl->template_skcipher, sizeof(*alg));
+
+	snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name);
+	snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+		 tmpl->driver_name);
+	alg->base.cra_module = THIS_MODULE;
+	alg->base.cra_priority = CC_CRA_PRIO;
+	alg->base.cra_blocksize = tmpl->blocksize;
+	alg->base.cra_alignmask = 0;
+	alg->base.cra_ctxsize = sizeof(struct cc_cipher_ctx);
+
+	alg->base.cra_init = cc_cipher_init;
+	alg->base.cra_exit = cc_cipher_exit;
+	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY |
+				CRYPTO_ALG_TYPE_SKCIPHER;
+
+	t_alg->cipher_mode = tmpl->cipher_mode;
+	t_alg->flow_mode = tmpl->flow_mode;
+	t_alg->data_unit = tmpl->data_unit;
+
+	return t_alg;
+}
+
+int cc_cipher_free(struct cc_drvdata *drvdata)
+{
+	struct cc_crypto_alg *t_alg, *n;
+	struct cc_cipher_handle *cipher_handle = drvdata->cipher_handle;
+
+	if (cipher_handle) {
+		/* Remove registered algs */
+		list_for_each_entry_safe(t_alg, n, &cipher_handle->alg_list,
+					 entry) {
+			crypto_unregister_skcipher(&t_alg->skcipher_alg);
+			list_del(&t_alg->entry);
+			kfree(t_alg);
+		}
+		kfree(cipher_handle);
+		drvdata->cipher_handle = NULL;
+	}
+	return 0;
+}
+
+int cc_cipher_alloc(struct cc_drvdata *drvdata)
+{
+	struct cc_cipher_handle *cipher_handle;
+	struct cc_crypto_alg *t_alg;
+	struct device *dev = drvdata_to_dev(drvdata);
+	int rc = -ENOMEM;
+	int alg;
+
+	cipher_handle = kmalloc(sizeof(*cipher_handle), GFP_KERNEL);
+	if (!cipher_handle)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&cipher_handle->alg_list);
+	drvdata->cipher_handle = cipher_handle;
+
+	/* Linux crypto */
+	dev_dbg(dev, "Number of algorithms = %zu\n",
+		ARRAY_SIZE(skcipher_algs));
+	for (alg = 0; alg < ARRAY_SIZE(skcipher_algs); alg++) {
+		if (skcipher_algs[alg].min_hw_rev > drvdata->hw_rev)
+			continue;
+
+		dev_dbg(dev, "creating %s\n", skcipher_algs[alg].driver_name);
+		t_alg = cc_create_alg(&skcipher_algs[alg], dev);
+		if (IS_ERR(t_alg)) {
+			rc = PTR_ERR(t_alg);
+			dev_err(dev, "%s alg allocation failed\n",
+				skcipher_algs[alg].driver_name);
+			goto fail0;
+		}
+		t_alg->drvdata = drvdata;
+
+		dev_dbg(dev, "registering %s\n",
+			skcipher_algs[alg].driver_name);
+		rc = crypto_register_skcipher(&t_alg->skcipher_alg);
+		dev_dbg(dev, "%s alg registration rc = %x\n",
+			t_alg->skcipher_alg.base.cra_driver_name, rc);
+		if (rc) {
+			dev_err(dev, "%s alg registration failed\n",
+				t_alg->skcipher_alg.base.cra_driver_name);
+			kfree(t_alg);
+			goto fail0;
+		} else {
+			list_add_tail(&t_alg->entry,
+				      &cipher_handle->alg_list);
+			dev_dbg(dev, "Registered %s\n",
+				t_alg->skcipher_alg.base.cra_driver_name);
+		}
+	}
+	return 0;
+
+fail0:
+	cc_cipher_free(drvdata);
+	return rc;
+}
diff --git a/drivers/crypto/ccree/cc_cipher.h b/drivers/crypto/ccree/cc_cipher.h
new file mode 100644
index 000000000000..2a2a6f46c515
--- /dev/null
+++ b/drivers/crypto/ccree/cc_cipher.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+/* \file cc_cipher.h
+ * ARM CryptoCell Cipher Crypto API
+ */
+
+#ifndef __CC_CIPHER_H__
+#define __CC_CIPHER_H__
+
+#include <linux/kernel.h>
+#include <crypto/algapi.h>
+#include "cc_driver.h"
+#include "cc_buffer_mgr.h"
+
+/* Crypto cipher flags */
+#define CC_CRYPTO_CIPHER_KEY_KFDE0	BIT(0)
+#define CC_CRYPTO_CIPHER_KEY_KFDE1	BIT(1)
+#define CC_CRYPTO_CIPHER_KEY_KFDE2	BIT(2)
+#define CC_CRYPTO_CIPHER_KEY_KFDE3	BIT(3)
+#define CC_CRYPTO_CIPHER_DU_SIZE_512B	BIT(4)
+
+#define CC_CRYPTO_CIPHER_KEY_KFDE_MASK (CC_CRYPTO_CIPHER_KEY_KFDE0 | \
+					CC_CRYPTO_CIPHER_KEY_KFDE1 | \
+					CC_CRYPTO_CIPHER_KEY_KFDE2 | \
+					CC_CRYPTO_CIPHER_KEY_KFDE3)
+
+struct cipher_req_ctx {
+	struct async_gen_req_ctx gen_ctx;
+	enum cc_req_dma_buf_type dma_buf_type;
+	u32 in_nents;
+	u32 in_mlli_nents;
+	u32 out_nents;
+	u32 out_mlli_nents;
+	u8 *backup_info; /*store iv for generated IV flow*/
+	u8 *iv;
+	bool is_giv;
+	struct mlli_params mlli_params;
+};
+
+int cc_cipher_alloc(struct cc_drvdata *drvdata);
+
+int cc_cipher_free(struct cc_drvdata *drvdata);
+
+struct arm_hw_key_info {
+	int hw_key1;
+	int hw_key2;
+};
+
+/*
+ * This is a stub function that will replaced when we
+ * implement secure keys
+ */
+static inline bool cc_is_hw_key(struct crypto_tfm *tfm)
+{
+	return false;
+}
+
+#endif /*__CC_CIPHER_H__*/
diff --git a/drivers/crypto/ccree/cc_crypto_ctx.h b/drivers/crypto/ccree/cc_crypto_ctx.h
new file mode 100644
index 000000000000..e032544f4e31
--- /dev/null
+++ b/drivers/crypto/ccree/cc_crypto_ctx.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#ifndef _CC_CRYPTO_CTX_H_
+#define _CC_CRYPTO_CTX_H_
+
+#include <linux/types.h>
+
+#define CC_DRV_DES_IV_SIZE 8
+#define CC_DRV_DES_BLOCK_SIZE 8
+
+#define CC_DRV_DES_ONE_KEY_SIZE 8
+#define CC_DRV_DES_DOUBLE_KEY_SIZE 16
+#define CC_DRV_DES_TRIPLE_KEY_SIZE 24
+#define CC_DRV_DES_KEY_SIZE_MAX CC_DRV_DES_TRIPLE_KEY_SIZE
+
+#define CC_AES_IV_SIZE 16
+#define CC_AES_IV_SIZE_WORDS (CC_AES_IV_SIZE >> 2)
+
+#define CC_AES_BLOCK_SIZE 16
+#define CC_AES_BLOCK_SIZE_WORDS 4
+
+#define CC_AES_128_BIT_KEY_SIZE 16
+#define CC_AES_128_BIT_KEY_SIZE_WORDS	(CC_AES_128_BIT_KEY_SIZE >> 2)
+#define CC_AES_192_BIT_KEY_SIZE 24
+#define CC_AES_192_BIT_KEY_SIZE_WORDS	(CC_AES_192_BIT_KEY_SIZE >> 2)
+#define CC_AES_256_BIT_KEY_SIZE 32
+#define CC_AES_256_BIT_KEY_SIZE_WORDS	(CC_AES_256_BIT_KEY_SIZE >> 2)
+#define CC_AES_KEY_SIZE_MAX			CC_AES_256_BIT_KEY_SIZE
+#define CC_AES_KEY_SIZE_WORDS_MAX		(CC_AES_KEY_SIZE_MAX >> 2)
+
+#define CC_MD5_DIGEST_SIZE	16
+#define CC_SHA1_DIGEST_SIZE	20
+#define CC_SHA224_DIGEST_SIZE	28
+#define CC_SHA256_DIGEST_SIZE	32
+#define CC_SHA256_DIGEST_SIZE_IN_WORDS 8
+#define CC_SHA384_DIGEST_SIZE	48
+#define CC_SHA512_DIGEST_SIZE	64
+
+#define CC_SHA1_BLOCK_SIZE 64
+#define CC_SHA1_BLOCK_SIZE_IN_WORDS 16
+#define CC_MD5_BLOCK_SIZE 64
+#define CC_MD5_BLOCK_SIZE_IN_WORDS 16
+#define CC_SHA224_BLOCK_SIZE 64
+#define CC_SHA256_BLOCK_SIZE 64
+#define CC_SHA256_BLOCK_SIZE_IN_WORDS 16
+#define CC_SHA1_224_256_BLOCK_SIZE 64
+#define CC_SHA384_BLOCK_SIZE 128
+#define CC_SHA512_BLOCK_SIZE 128
+
+#define CC_DIGEST_SIZE_MAX CC_SHA512_DIGEST_SIZE
+#define CC_HASH_BLOCK_SIZE_MAX CC_SHA512_BLOCK_SIZE /*1024b*/
+
+#define CC_HMAC_BLOCK_SIZE_MAX CC_HASH_BLOCK_SIZE_MAX
+
+#define CC_DRV_ALG_MAX_BLOCK_SIZE CC_HASH_BLOCK_SIZE_MAX
+
+enum drv_engine_type {
+	DRV_ENGINE_NULL = 0,
+	DRV_ENGINE_AES = 1,
+	DRV_ENGINE_DES = 2,
+	DRV_ENGINE_HASH = 3,
+	DRV_ENGINE_RC4 = 4,
+	DRV_ENGINE_DOUT = 5,
+	DRV_ENGINE_RESERVE32B = S32_MAX,
+};
+
+enum drv_crypto_alg {
+	DRV_CRYPTO_ALG_NULL = -1,
+	DRV_CRYPTO_ALG_AES  = 0,
+	DRV_CRYPTO_ALG_DES  = 1,
+	DRV_CRYPTO_ALG_HASH = 2,
+	DRV_CRYPTO_ALG_C2   = 3,
+	DRV_CRYPTO_ALG_HMAC = 4,
+	DRV_CRYPTO_ALG_AEAD = 5,
+	DRV_CRYPTO_ALG_BYPASS = 6,
+	DRV_CRYPTO_ALG_NUM = 7,
+	DRV_CRYPTO_ALG_RESERVE32B = S32_MAX
+};
+
+enum drv_crypto_direction {
+	DRV_CRYPTO_DIRECTION_NULL = -1,
+	DRV_CRYPTO_DIRECTION_ENCRYPT = 0,
+	DRV_CRYPTO_DIRECTION_DECRYPT = 1,
+	DRV_CRYPTO_DIRECTION_DECRYPT_ENCRYPT = 3,
+	DRV_CRYPTO_DIRECTION_RESERVE32B = S32_MAX
+};
+
+enum drv_cipher_mode {
+	DRV_CIPHER_NULL_MODE = -1,
+	DRV_CIPHER_ECB = 0,
+	DRV_CIPHER_CBC = 1,
+	DRV_CIPHER_CTR = 2,
+	DRV_CIPHER_CBC_MAC = 3,
+	DRV_CIPHER_XTS = 4,
+	DRV_CIPHER_XCBC_MAC = 5,
+	DRV_CIPHER_OFB = 6,
+	DRV_CIPHER_CMAC = 7,
+	DRV_CIPHER_CCM = 8,
+	DRV_CIPHER_CBC_CTS = 11,
+	DRV_CIPHER_GCTR = 12,
+	DRV_CIPHER_ESSIV = 13,
+	DRV_CIPHER_BITLOCKER = 14,
+	DRV_CIPHER_RESERVE32B = S32_MAX
+};
+
+enum drv_hash_mode {
+	DRV_HASH_NULL = -1,
+	DRV_HASH_SHA1 = 0,
+	DRV_HASH_SHA256 = 1,
+	DRV_HASH_SHA224 = 2,
+	DRV_HASH_SHA512 = 3,
+	DRV_HASH_SHA384 = 4,
+	DRV_HASH_MD5 = 5,
+	DRV_HASH_CBC_MAC = 6,
+	DRV_HASH_XCBC_MAC = 7,
+	DRV_HASH_CMAC = 8,
+	DRV_HASH_MODE_NUM = 9,
+	DRV_HASH_RESERVE32B = S32_MAX
+};
+
+enum drv_hash_hw_mode {
+	DRV_HASH_HW_MD5 = 0,
+	DRV_HASH_HW_SHA1 = 1,
+	DRV_HASH_HW_SHA256 = 2,
+	DRV_HASH_HW_SHA224 = 10,
+	DRV_HASH_HW_SHA512 = 4,
+	DRV_HASH_HW_SHA384 = 12,
+	DRV_HASH_HW_GHASH = 6,
+	DRV_HASH_HW_RESERVE32B = S32_MAX
+};
+
+#endif /* _CC_CRYPTO_CTX_H_ */
diff --git a/drivers/crypto/ccree/cc_debugfs.c b/drivers/crypto/ccree/cc_debugfs.c
new file mode 100644
index 000000000000..08f8db489cf0
--- /dev/null
+++ b/drivers/crypto/ccree/cc_debugfs.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include <linux/kernel.h>
+#include <linux/debugfs.h>
+#include <linux/stringify.h>
+#include "cc_driver.h"
+#include "cc_crypto_ctx.h"
+#include "cc_debugfs.h"
+
+struct cc_debugfs_ctx {
+	struct dentry *dir;
+};
+
+#define CC_DEBUG_REG(_X) {	\
+	.name = __stringify(_X),\
+	.offset = CC_REG(_X)	\
+	}
+
+/*
+ * This is a global var for the dentry of the
+ * debugfs ccree/ dir. It is not tied down to
+ * a specific instance of ccree, hence it is
+ * global.
+ */
+static struct dentry *cc_debugfs_dir;
+
+static struct debugfs_reg32 debug_regs[] = {
+	CC_DEBUG_REG(HOST_SIGNATURE),
+	CC_DEBUG_REG(HOST_IRR),
+	CC_DEBUG_REG(HOST_POWER_DOWN_EN),
+	CC_DEBUG_REG(AXIM_MON_ERR),
+	CC_DEBUG_REG(DSCRPTR_QUEUE_CONTENT),
+	CC_DEBUG_REG(HOST_IMR),
+	CC_DEBUG_REG(AXIM_CFG),
+	CC_DEBUG_REG(AXIM_CACHE_PARAMS),
+	CC_DEBUG_REG(HOST_VERSION),
+	CC_DEBUG_REG(GPR_HOST),
+	CC_DEBUG_REG(AXIM_MON_COMP),
+};
+
+int __init cc_debugfs_global_init(void)
+{
+	cc_debugfs_dir = debugfs_create_dir("ccree", NULL);
+
+	return !cc_debugfs_dir;
+}
+
+void __exit cc_debugfs_global_fini(void)
+{
+	debugfs_remove(cc_debugfs_dir);
+}
+
+int cc_debugfs_init(struct cc_drvdata *drvdata)
+{
+	struct device *dev = drvdata_to_dev(drvdata);
+	struct cc_debugfs_ctx *ctx;
+	struct debugfs_regset32 *regset;
+	struct dentry *file;
+
+	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	regset = devm_kzalloc(dev, sizeof(*regset), GFP_KERNEL);
+	if (!regset)
+		return -ENOMEM;
+
+	regset->regs = debug_regs;
+	regset->nregs = ARRAY_SIZE(debug_regs);
+	regset->base = drvdata->cc_base;
+
+	ctx->dir = debugfs_create_dir(drvdata->plat_dev->name, cc_debugfs_dir);
+	if (!ctx->dir)
+		return -ENFILE;
+
+	file = debugfs_create_regset32("regs", 0400, ctx->dir, regset);
+	if (!file) {
+		debugfs_remove(ctx->dir);
+		return -ENFILE;
+	}
+
+	file = debugfs_create_bool("coherent", 0400, ctx->dir,
+				   &drvdata->coherent);
+
+	if (!file) {
+		debugfs_remove_recursive(ctx->dir);
+		return -ENFILE;
+	}
+
+	drvdata->debugfs = ctx;
+
+	return 0;
+}
+
+void cc_debugfs_fini(struct cc_drvdata *drvdata)
+{
+	struct cc_debugfs_ctx *ctx = (struct cc_debugfs_ctx *)drvdata->debugfs;
+
+	debugfs_remove_recursive(ctx->dir);
+}
diff --git a/drivers/crypto/ccree/cc_debugfs.h b/drivers/crypto/ccree/cc_debugfs.h
new file mode 100644
index 000000000000..5b5320eca7d2
--- /dev/null
+++ b/drivers/crypto/ccree/cc_debugfs.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#ifndef __CC_DEBUGFS_H__
+#define __CC_DEBUGFS_H__
+
+#ifdef CONFIG_DEBUG_FS
+int cc_debugfs_global_init(void);
+void cc_debugfs_global_fini(void);
+
+int cc_debugfs_init(struct cc_drvdata *drvdata);
+void cc_debugfs_fini(struct cc_drvdata *drvdata);
+
+#else
+
+static inline int cc_debugfs_global_init(void)
+{
+	return 0;
+}
+
+static inline void cc_debugfs_global_fini(void) {}
+
+static inline int cc_debugfs_init(struct cc_drvdata *drvdata)
+{
+	return 0;
+}
+
+static inline void cc_debugfs_fini(struct cc_drvdata *drvdata) {}
+
+#endif
+
+#endif /*__CC_SYSFS_H__*/
diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c
new file mode 100644
index 000000000000..89ce013ae093
--- /dev/null
+++ b/drivers/crypto/ccree/cc_driver.c
@@ -0,0 +1,518 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <linux/crypto.h>
+#include <linux/moduleparam.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/of.h>
+#include <linux/clk.h>
+#include <linux/of_address.h>
+
+#include "cc_driver.h"
+#include "cc_request_mgr.h"
+#include "cc_buffer_mgr.h"
+#include "cc_debugfs.h"
+#include "cc_cipher.h"
+#include "cc_aead.h"
+#include "cc_hash.h"
+#include "cc_ivgen.h"
+#include "cc_sram_mgr.h"
+#include "cc_pm.h"
+#include "cc_fips.h"
+
+bool cc_dump_desc;
+module_param_named(dump_desc, cc_dump_desc, bool, 0600);
+MODULE_PARM_DESC(cc_dump_desc, "Dump descriptors to kernel log as debugging aid");
+
+bool cc_dump_bytes;
+module_param_named(dump_bytes, cc_dump_bytes, bool, 0600);
+MODULE_PARM_DESC(cc_dump_bytes, "Dump buffers to kernel log as debugging aid");
+
+struct cc_hw_data {
+	char *name;
+	enum cc_hw_rev rev;
+	u32 sig;
+};
+
+/* Hardware revisions defs. */
+
+static const struct cc_hw_data cc712_hw = {
+	.name = "712", .rev = CC_HW_REV_712, .sig =  0xDCC71200U
+};
+
+static const struct cc_hw_data cc710_hw = {
+	.name = "710", .rev = CC_HW_REV_710, .sig =  0xDCC63200U
+};
+
+static const struct cc_hw_data cc630p_hw = {
+	.name = "630P", .rev = CC_HW_REV_630, .sig = 0xDCC63000U
+};
+
+static const struct of_device_id arm_ccree_dev_of_match[] = {
+	{ .compatible = "arm,cryptocell-712-ree", .data = &cc712_hw },
+	{ .compatible = "arm,cryptocell-710-ree", .data = &cc710_hw },
+	{ .compatible = "arm,cryptocell-630p-ree", .data = &cc630p_hw },
+	{}
+};
+MODULE_DEVICE_TABLE(of, arm_ccree_dev_of_match);
+
+void __dump_byte_array(const char *name, const u8 *buf, size_t len)
+{
+	char prefix[64];
+
+	if (!buf)
+		return;
+
+	snprintf(prefix, sizeof(prefix), "%s[%zu]: ", name, len);
+
+	print_hex_dump(KERN_DEBUG, prefix, DUMP_PREFIX_ADDRESS, 16, 1, buf,
+		       len, false);
+}
+
+static irqreturn_t cc_isr(int irq, void *dev_id)
+{
+	struct cc_drvdata *drvdata = (struct cc_drvdata *)dev_id;
+	struct device *dev = drvdata_to_dev(drvdata);
+	u32 irr;
+	u32 imr;
+
+	/* STAT_OP_TYPE_GENERIC STAT_PHASE_0: Interrupt */
+
+	/* read the interrupt status */
+	irr = cc_ioread(drvdata, CC_REG(HOST_IRR));
+	dev_dbg(dev, "Got IRR=0x%08X\n", irr);
+	if (irr == 0) { /* Probably shared interrupt line */
+		dev_err(dev, "Got interrupt with empty IRR\n");
+		return IRQ_NONE;
+	}
+	imr = cc_ioread(drvdata, CC_REG(HOST_IMR));
+
+	/* clear interrupt - must be before processing events */
+	cc_iowrite(drvdata, CC_REG(HOST_ICR), irr);
+
+	drvdata->irq = irr;
+	/* Completion interrupt - most probable */
+	if (irr & CC_COMP_IRQ_MASK) {
+		/* Mask AXI completion interrupt - will be unmasked in
+		 * Deferred service handler
+		 */
+		cc_iowrite(drvdata, CC_REG(HOST_IMR), imr | CC_COMP_IRQ_MASK);
+		irr &= ~CC_COMP_IRQ_MASK;
+		complete_request(drvdata);
+	}
+#ifdef CONFIG_CRYPTO_FIPS
+	/* TEE FIPS interrupt */
+	if (irr & CC_GPR0_IRQ_MASK) {
+		/* Mask interrupt - will be unmasked in Deferred service
+		 * handler
+		 */
+		cc_iowrite(drvdata, CC_REG(HOST_IMR), imr | CC_GPR0_IRQ_MASK);
+		irr &= ~CC_GPR0_IRQ_MASK;
+		fips_handler(drvdata);
+	}
+#endif
+	/* AXI error interrupt */
+	if (irr & CC_AXI_ERR_IRQ_MASK) {
+		u32 axi_err;
+
+		/* Read the AXI error ID */
+		axi_err = cc_ioread(drvdata, CC_REG(AXIM_MON_ERR));
+		dev_dbg(dev, "AXI completion error: axim_mon_err=0x%08X\n",
+			axi_err);
+
+		irr &= ~CC_AXI_ERR_IRQ_MASK;
+	}
+
+	if (irr) {
+		dev_dbg(dev, "IRR includes unknown cause bits (0x%08X)\n",
+			irr);
+		/* Just warning */
+	}
+
+	return IRQ_HANDLED;
+}
+
+int init_cc_regs(struct cc_drvdata *drvdata, bool is_probe)
+{
+	unsigned int val, cache_params;
+	struct device *dev = drvdata_to_dev(drvdata);
+
+	/* Unmask all AXI interrupt sources AXI_CFG1 register */
+	val = cc_ioread(drvdata, CC_REG(AXIM_CFG));
+	cc_iowrite(drvdata, CC_REG(AXIM_CFG), val & ~CC_AXI_IRQ_MASK);
+	dev_dbg(dev, "AXIM_CFG=0x%08X\n",
+		cc_ioread(drvdata, CC_REG(AXIM_CFG)));
+
+	/* Clear all pending interrupts */
+	val = cc_ioread(drvdata, CC_REG(HOST_IRR));
+	dev_dbg(dev, "IRR=0x%08X\n", val);
+	cc_iowrite(drvdata, CC_REG(HOST_ICR), val);
+
+	/* Unmask relevant interrupt cause */
+	val = CC_COMP_IRQ_MASK | CC_AXI_ERR_IRQ_MASK;
+
+	if (drvdata->hw_rev >= CC_HW_REV_712)
+		val |= CC_GPR0_IRQ_MASK;
+
+	cc_iowrite(drvdata, CC_REG(HOST_IMR), ~val);
+
+	cache_params = (drvdata->coherent ? CC_COHERENT_CACHE_PARAMS : 0x0);
+
+	val = cc_ioread(drvdata, CC_REG(AXIM_CACHE_PARAMS));
+
+	if (is_probe)
+		dev_info(dev, "Cache params previous: 0x%08X\n", val);
+
+	cc_iowrite(drvdata, CC_REG(AXIM_CACHE_PARAMS), cache_params);
+	val = cc_ioread(drvdata, CC_REG(AXIM_CACHE_PARAMS));
+
+	if (is_probe)
+		dev_info(dev, "Cache params current: 0x%08X (expect: 0x%08X)\n",
+			 val, cache_params);
+
+	return 0;
+}
+
+static int init_cc_resources(struct platform_device *plat_dev)
+{
+	struct resource *req_mem_cc_regs = NULL;
+	struct cc_drvdata *new_drvdata;
+	struct device *dev = &plat_dev->dev;
+	struct device_node *np = dev->of_node;
+	u32 signature_val;
+	u64 dma_mask;
+	const struct cc_hw_data *hw_rev;
+	const struct of_device_id *dev_id;
+	int rc = 0;
+
+	new_drvdata = devm_kzalloc(dev, sizeof(*new_drvdata), GFP_KERNEL);
+	if (!new_drvdata)
+		return -ENOMEM;
+
+	dev_id = of_match_node(arm_ccree_dev_of_match, np);
+	if (!dev_id)
+		return -ENODEV;
+
+	hw_rev = (struct cc_hw_data *)dev_id->data;
+	new_drvdata->hw_rev_name = hw_rev->name;
+	new_drvdata->hw_rev = hw_rev->rev;
+
+	if (hw_rev->rev >= CC_HW_REV_712) {
+		new_drvdata->hash_len_sz = HASH_LEN_SIZE_712;
+		new_drvdata->axim_mon_offset = CC_REG(AXIM_MON_COMP);
+	} else {
+		new_drvdata->hash_len_sz = HASH_LEN_SIZE_630;
+		new_drvdata->axim_mon_offset = CC_REG(AXIM_MON_COMP8);
+	}
+
+	platform_set_drvdata(plat_dev, new_drvdata);
+	new_drvdata->plat_dev = plat_dev;
+
+	new_drvdata->clk = of_clk_get(np, 0);
+	new_drvdata->coherent = of_dma_is_coherent(np);
+
+	/* Get device resources */
+	/* First CC registers space */
+	req_mem_cc_regs = platform_get_resource(plat_dev, IORESOURCE_MEM, 0);
+	/* Map registers space */
+	new_drvdata->cc_base = devm_ioremap_resource(dev, req_mem_cc_regs);
+	if (IS_ERR(new_drvdata->cc_base)) {
+		dev_err(dev, "Failed to ioremap registers");
+		return PTR_ERR(new_drvdata->cc_base);
+	}
+
+	dev_dbg(dev, "Got MEM resource (%s): %pR\n", req_mem_cc_regs->name,
+		req_mem_cc_regs);
+	dev_dbg(dev, "CC registers mapped from %pa to 0x%p\n",
+		&req_mem_cc_regs->start, new_drvdata->cc_base);
+
+	/* Then IRQ */
+	new_drvdata->irq = platform_get_irq(plat_dev, 0);
+	if (new_drvdata->irq < 0) {
+		dev_err(dev, "Failed getting IRQ resource\n");
+		return new_drvdata->irq;
+	}
+
+	rc = devm_request_irq(dev, new_drvdata->irq, cc_isr,
+			      IRQF_SHARED, "ccree", new_drvdata);
+	if (rc) {
+		dev_err(dev, "Could not register to interrupt %d\n",
+			new_drvdata->irq);
+		return rc;
+	}
+	dev_dbg(dev, "Registered to IRQ: %d\n", new_drvdata->irq);
+
+	init_completion(&new_drvdata->hw_queue_avail);
+
+	if (!plat_dev->dev.dma_mask)
+		plat_dev->dev.dma_mask = &plat_dev->dev.coherent_dma_mask;
+
+	dma_mask = DMA_BIT_MASK(DMA_BIT_MASK_LEN);
+	while (dma_mask > 0x7fffffffUL) {
+		if (dma_supported(&plat_dev->dev, dma_mask)) {
+			rc = dma_set_coherent_mask(&plat_dev->dev, dma_mask);
+			if (!rc)
+				break;
+		}
+		dma_mask >>= 1;
+	}
+
+	if (rc) {
+		dev_err(dev, "Failed in dma_set_mask, mask=%pad\n", &dma_mask);
+		return rc;
+	}
+
+	rc = cc_clk_on(new_drvdata);
+	if (rc) {
+		dev_err(dev, "Failed to enable clock");
+		return rc;
+	}
+
+	/* Verify correct mapping */
+	signature_val = cc_ioread(new_drvdata, CC_REG(HOST_SIGNATURE));
+	if (signature_val != hw_rev->sig) {
+		dev_err(dev, "Invalid CC signature: SIGNATURE=0x%08X != expected=0x%08X\n",
+			signature_val, hw_rev->sig);
+		rc = -EINVAL;
+		goto post_clk_err;
+	}
+	dev_dbg(dev, "CC SIGNATURE=0x%08X\n", signature_val);
+
+	/* Display HW versions */
+	dev_info(dev, "ARM CryptoCell %s Driver: HW version 0x%08X, Driver version %s\n",
+		 hw_rev->name, cc_ioread(new_drvdata, CC_REG(HOST_VERSION)),
+		 DRV_MODULE_VERSION);
+
+	rc = init_cc_regs(new_drvdata, true);
+	if (rc) {
+		dev_err(dev, "init_cc_regs failed\n");
+		goto post_clk_err;
+	}
+
+	rc = cc_debugfs_init(new_drvdata);
+	if (rc) {
+		dev_err(dev, "Failed registering debugfs interface\n");
+		goto post_regs_err;
+	}
+
+	rc = cc_fips_init(new_drvdata);
+	if (rc) {
+		dev_err(dev, "CC_FIPS_INIT failed 0x%x\n", rc);
+		goto post_debugfs_err;
+	}
+	rc = cc_sram_mgr_init(new_drvdata);
+	if (rc) {
+		dev_err(dev, "cc_sram_mgr_init failed\n");
+		goto post_fips_init_err;
+	}
+
+	new_drvdata->mlli_sram_addr =
+		cc_sram_alloc(new_drvdata, MAX_MLLI_BUFF_SIZE);
+	if (new_drvdata->mlli_sram_addr == NULL_SRAM_ADDR) {
+		dev_err(dev, "Failed to alloc MLLI Sram buffer\n");
+		rc = -ENOMEM;
+		goto post_sram_mgr_err;
+	}
+
+	rc = cc_req_mgr_init(new_drvdata);
+	if (rc) {
+		dev_err(dev, "cc_req_mgr_init failed\n");
+		goto post_sram_mgr_err;
+	}
+
+	rc = cc_buffer_mgr_init(new_drvdata);
+	if (rc) {
+		dev_err(dev, "buffer_mgr_init failed\n");
+		goto post_req_mgr_err;
+	}
+
+	rc = cc_pm_init(new_drvdata);
+	if (rc) {
+		dev_err(dev, "ssi_power_mgr_init failed\n");
+		goto post_buf_mgr_err;
+	}
+
+	rc = cc_ivgen_init(new_drvdata);
+	if (rc) {
+		dev_err(dev, "cc_ivgen_init failed\n");
+		goto post_power_mgr_err;
+	}
+
+	/* Allocate crypto algs */
+	rc = cc_cipher_alloc(new_drvdata);
+	if (rc) {
+		dev_err(dev, "cc_cipher_alloc failed\n");
+		goto post_ivgen_err;
+	}
+
+	/* hash must be allocated before aead since hash exports APIs */
+	rc = cc_hash_alloc(new_drvdata);
+	if (rc) {
+		dev_err(dev, "cc_hash_alloc failed\n");
+		goto post_cipher_err;
+	}
+
+	rc = cc_aead_alloc(new_drvdata);
+	if (rc) {
+		dev_err(dev, "cc_aead_alloc failed\n");
+		goto post_hash_err;
+	}
+
+	/* If we got here and FIPS mode is enabled
+	 * it means all FIPS test passed, so let TEE
+	 * know we're good.
+	 */
+	cc_set_ree_fips_status(new_drvdata, true);
+
+	return 0;
+
+post_hash_err:
+	cc_hash_free(new_drvdata);
+post_cipher_err:
+	cc_cipher_free(new_drvdata);
+post_ivgen_err:
+	cc_ivgen_fini(new_drvdata);
+post_power_mgr_err:
+	cc_pm_fini(new_drvdata);
+post_buf_mgr_err:
+	 cc_buffer_mgr_fini(new_drvdata);
+post_req_mgr_err:
+	cc_req_mgr_fini(new_drvdata);
+post_sram_mgr_err:
+	cc_sram_mgr_fini(new_drvdata);
+post_fips_init_err:
+	cc_fips_fini(new_drvdata);
+post_debugfs_err:
+	cc_debugfs_fini(new_drvdata);
+post_regs_err:
+	fini_cc_regs(new_drvdata);
+post_clk_err:
+	cc_clk_off(new_drvdata);
+	return rc;
+}
+
+void fini_cc_regs(struct cc_drvdata *drvdata)
+{
+	/* Mask all interrupts */
+	cc_iowrite(drvdata, CC_REG(HOST_IMR), 0xFFFFFFFF);
+}
+
+static void cleanup_cc_resources(struct platform_device *plat_dev)
+{
+	struct cc_drvdata *drvdata =
+		(struct cc_drvdata *)platform_get_drvdata(plat_dev);
+
+	cc_aead_free(drvdata);
+	cc_hash_free(drvdata);
+	cc_cipher_free(drvdata);
+	cc_ivgen_fini(drvdata);
+	cc_pm_fini(drvdata);
+	cc_buffer_mgr_fini(drvdata);
+	cc_req_mgr_fini(drvdata);
+	cc_sram_mgr_fini(drvdata);
+	cc_fips_fini(drvdata);
+	cc_debugfs_fini(drvdata);
+	fini_cc_regs(drvdata);
+	cc_clk_off(drvdata);
+}
+
+int cc_clk_on(struct cc_drvdata *drvdata)
+{
+	struct clk *clk = drvdata->clk;
+	int rc;
+
+	if (IS_ERR(clk))
+		/* Not all devices have a clock associated with CCREE  */
+		return 0;
+
+	rc = clk_prepare_enable(clk);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+void cc_clk_off(struct cc_drvdata *drvdata)
+{
+	struct clk *clk = drvdata->clk;
+
+	if (IS_ERR(clk))
+		/* Not all devices have a clock associated with CCREE */
+		return;
+
+	clk_disable_unprepare(clk);
+}
+
+static int ccree_probe(struct platform_device *plat_dev)
+{
+	int rc;
+	struct device *dev = &plat_dev->dev;
+
+	/* Map registers space */
+	rc = init_cc_resources(plat_dev);
+	if (rc)
+		return rc;
+
+	dev_info(dev, "ARM ccree device initialized\n");
+
+	return 0;
+}
+
+static int ccree_remove(struct platform_device *plat_dev)
+{
+	struct device *dev = &plat_dev->dev;
+
+	dev_dbg(dev, "Releasing ccree resources...\n");
+
+	cleanup_cc_resources(plat_dev);
+
+	dev_info(dev, "ARM ccree device terminated\n");
+
+	return 0;
+}
+
+static struct platform_driver ccree_driver = {
+	.driver = {
+		   .name = "ccree",
+		   .of_match_table = arm_ccree_dev_of_match,
+#ifdef CONFIG_PM
+		   .pm = &ccree_pm,
+#endif
+	},
+	.probe = ccree_probe,
+	.remove = ccree_remove,
+};
+
+static int __init ccree_init(void)
+{
+	int ret;
+
+	cc_hash_global_init();
+
+	ret = cc_debugfs_global_init();
+	if (ret)
+		return ret;
+
+	return platform_driver_register(&ccree_driver);
+}
+module_init(ccree_init);
+
+static void __exit ccree_exit(void)
+{
+	platform_driver_unregister(&ccree_driver);
+	cc_debugfs_global_fini();
+}
+module_exit(ccree_exit);
+
+/* Module description */
+MODULE_DESCRIPTION("ARM TrustZone CryptoCell REE Driver");
+MODULE_VERSION(DRV_MODULE_VERSION);
+MODULE_AUTHOR("ARM");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/crypto/ccree/cc_driver.h b/drivers/crypto/ccree/cc_driver.h
new file mode 100644
index 000000000000..2048fdeb9579
--- /dev/null
+++ b/drivers/crypto/ccree/cc_driver.h
@@ -0,0 +1,208 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+/* \file cc_driver.h
+ * ARM CryptoCell Linux Crypto Driver
+ */
+
+#ifndef __CC_DRIVER_H__
+#define __CC_DRIVER_H__
+
+#ifdef COMP_IN_WQ
+#include <linux/workqueue.h>
+#else
+#include <linux/interrupt.h>
+#endif
+#include <linux/dma-mapping.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/aes.h>
+#include <crypto/sha.h>
+#include <crypto/aead.h>
+#include <crypto/authenc.h>
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
+#include <linux/version.h>
+#include <linux/clk.h>
+#include <linux/platform_device.h>
+
+/* Registers definitions from shared/hw/ree_include */
+#include "cc_host_regs.h"
+#define CC_DEV_SHA_MAX 512
+#include "cc_crypto_ctx.h"
+#include "cc_hw_queue_defs.h"
+#include "cc_sram_mgr.h"
+
+extern bool cc_dump_desc;
+extern bool cc_dump_bytes;
+
+#define DRV_MODULE_VERSION "4.0"
+
+enum cc_hw_rev {
+	CC_HW_REV_630 = 630,
+	CC_HW_REV_710 = 710,
+	CC_HW_REV_712 = 712
+};
+
+#define CC_COHERENT_CACHE_PARAMS 0xEEE
+
+/* Maximum DMA mask supported by IP */
+#define DMA_BIT_MASK_LEN 48
+
+#define CC_AXI_IRQ_MASK ((1 << CC_AXIM_CFG_BRESPMASK_BIT_SHIFT) | \
+			  (1 << CC_AXIM_CFG_RRESPMASK_BIT_SHIFT) | \
+			  (1 << CC_AXIM_CFG_INFLTMASK_BIT_SHIFT) | \
+			  (1 << CC_AXIM_CFG_COMPMASK_BIT_SHIFT))
+
+#define CC_AXI_ERR_IRQ_MASK BIT(CC_HOST_IRR_AXI_ERR_INT_BIT_SHIFT)
+
+#define CC_COMP_IRQ_MASK BIT(CC_HOST_IRR_AXIM_COMP_INT_BIT_SHIFT)
+
+#define AXIM_MON_COMP_VALUE GENMASK(CC_AXIM_MON_COMP_VALUE_BIT_SIZE + \
+				    CC_AXIM_MON_COMP_VALUE_BIT_SHIFT, \
+				    CC_AXIM_MON_COMP_VALUE_BIT_SHIFT)
+
+/* Register name mangling macro */
+#define CC_REG(reg_name) CC_ ## reg_name ## _REG_OFFSET
+
+/* TEE FIPS status interrupt */
+#define CC_GPR0_IRQ_MASK BIT(CC_HOST_IRR_GPR0_BIT_SHIFT)
+
+#define CC_CRA_PRIO 400
+
+#define MIN_HW_QUEUE_SIZE 50 /* Minimum size required for proper function */
+
+#define MAX_REQUEST_QUEUE_SIZE 4096
+#define MAX_MLLI_BUFF_SIZE 2080
+#define MAX_ICV_NENTS_SUPPORTED 2
+
+/* Definitions for HW descriptors DIN/DOUT fields */
+#define NS_BIT 1
+#define AXI_ID 0
+/* AXI_ID is not actually the AXI ID of the transaction but the value of AXI_ID
+ * field in the HW descriptor. The DMA engine +8 that value.
+ */
+
+#define CC_MAX_IVGEN_DMA_ADDRESSES	3
+struct cc_crypto_req {
+	void (*user_cb)(struct device *dev, void *req, int err);
+	void *user_arg;
+	dma_addr_t ivgen_dma_addr[CC_MAX_IVGEN_DMA_ADDRESSES];
+	/* For the first 'ivgen_dma_addr_len' addresses of this array,
+	 * generated IV would be placed in it by send_request().
+	 * Same generated IV for all addresses!
+	 */
+	/* Amount of 'ivgen_dma_addr' elements to be filled. */
+	unsigned int ivgen_dma_addr_len;
+	/* The generated IV size required, 8/16 B allowed. */
+	unsigned int ivgen_size;
+	struct completion seq_compl; /* request completion */
+};
+
+/**
+ * struct cc_drvdata - driver private data context
+ * @cc_base:	virt address of the CC registers
+ * @irq:	device IRQ number
+ * @irq_mask:	Interrupt mask shadow (1 for masked interrupts)
+ * @fw_ver:	SeP loaded firmware version
+ */
+struct cc_drvdata {
+	void __iomem *cc_base;
+	int irq;
+	u32 irq_mask;
+	u32 fw_ver;
+	struct completion hw_queue_avail; /* wait for HW queue availability */
+	struct platform_device *plat_dev;
+	cc_sram_addr_t mlli_sram_addr;
+	void *buff_mgr_handle;
+	void *cipher_handle;
+	void *hash_handle;
+	void *aead_handle;
+	void *request_mgr_handle;
+	void *fips_handle;
+	void *ivgen_handle;
+	void *sram_mgr_handle;
+	void *debugfs;
+	struct clk *clk;
+	bool coherent;
+	char *hw_rev_name;
+	enum cc_hw_rev hw_rev;
+	u32 hash_len_sz;
+	u32 axim_mon_offset;
+};
+
+struct cc_crypto_alg {
+	struct list_head entry;
+	int cipher_mode;
+	int flow_mode; /* Note: currently, refers to the cipher mode only. */
+	int auth_mode;
+	unsigned int data_unit;
+	struct cc_drvdata *drvdata;
+	struct skcipher_alg skcipher_alg;
+	struct aead_alg aead_alg;
+};
+
+struct cc_alg_template {
+	char name[CRYPTO_MAX_ALG_NAME];
+	char driver_name[CRYPTO_MAX_ALG_NAME];
+	unsigned int blocksize;
+	u32 type;
+	union {
+		struct skcipher_alg skcipher;
+		struct aead_alg aead;
+	} template_u;
+	int cipher_mode;
+	int flow_mode; /* Note: currently, refers to the cipher mode only. */
+	int auth_mode;
+	u32 min_hw_rev;
+	unsigned int data_unit;
+	struct cc_drvdata *drvdata;
+};
+
+struct async_gen_req_ctx {
+	dma_addr_t iv_dma_addr;
+	enum drv_crypto_direction op_type;
+};
+
+static inline struct device *drvdata_to_dev(struct cc_drvdata *drvdata)
+{
+	return &drvdata->plat_dev->dev;
+}
+
+void __dump_byte_array(const char *name, const u8 *buf, size_t len);
+static inline void dump_byte_array(const char *name, const u8 *the_array,
+				   size_t size)
+{
+	if (cc_dump_bytes)
+		__dump_byte_array(name, the_array, size);
+}
+
+int init_cc_regs(struct cc_drvdata *drvdata, bool is_probe);
+void fini_cc_regs(struct cc_drvdata *drvdata);
+int cc_clk_on(struct cc_drvdata *drvdata);
+void cc_clk_off(struct cc_drvdata *drvdata);
+
+static inline void cc_iowrite(struct cc_drvdata *drvdata, u32 reg, u32 val)
+{
+	iowrite32(val, (drvdata->cc_base + reg));
+}
+
+static inline u32 cc_ioread(struct cc_drvdata *drvdata, u32 reg)
+{
+	return ioread32(drvdata->cc_base + reg);
+}
+
+static inline gfp_t cc_gfp_flags(struct crypto_async_request *req)
+{
+	return (req->flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			GFP_KERNEL : GFP_ATOMIC;
+}
+
+static inline void set_queue_last_ind(struct cc_drvdata *drvdata,
+				      struct cc_hw_desc *pdesc)
+{
+	if (drvdata->hw_rev >= CC_HW_REV_712)
+		set_queue_last_ind_bit(pdesc);
+}
+
+#endif /*__CC_DRIVER_H__*/
diff --git a/drivers/crypto/ccree/cc_fips.c b/drivers/crypto/ccree/cc_fips.c
new file mode 100644
index 000000000000..b4d0a6d983e0
--- /dev/null
+++ b/drivers/crypto/ccree/cc_fips.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include <linux/kernel.h>
+#include <linux/fips.h>
+
+#include "cc_driver.h"
+#include "cc_fips.h"
+
+static void fips_dsr(unsigned long devarg);
+
+struct cc_fips_handle {
+	struct tasklet_struct tasklet;
+};
+
+/* The function called once at driver entry point to check
+ * whether TEE FIPS error occurred.
+ */
+static bool cc_get_tee_fips_status(struct cc_drvdata *drvdata)
+{
+	u32 reg;
+
+	reg = cc_ioread(drvdata, CC_REG(GPR_HOST));
+	return (reg == (CC_FIPS_SYNC_TEE_STATUS | CC_FIPS_SYNC_MODULE_OK));
+}
+
+/*
+ * This function should push the FIPS REE library status towards the TEE library
+ * by writing the error state to HOST_GPR0 register.
+ */
+void cc_set_ree_fips_status(struct cc_drvdata *drvdata, bool status)
+{
+	int val = CC_FIPS_SYNC_REE_STATUS;
+
+	if (drvdata->hw_rev < CC_HW_REV_712)
+		return;
+
+	val |= (status ? CC_FIPS_SYNC_MODULE_OK : CC_FIPS_SYNC_MODULE_ERROR);
+
+	cc_iowrite(drvdata, CC_REG(HOST_GPR0), val);
+}
+
+void cc_fips_fini(struct cc_drvdata *drvdata)
+{
+	struct cc_fips_handle *fips_h = drvdata->fips_handle;
+
+	if (drvdata->hw_rev < CC_HW_REV_712 || !fips_h)
+		return;
+
+	/* Kill tasklet */
+	tasklet_kill(&fips_h->tasklet);
+
+	kfree(fips_h);
+	drvdata->fips_handle = NULL;
+}
+
+void fips_handler(struct cc_drvdata *drvdata)
+{
+	struct cc_fips_handle *fips_handle_ptr = drvdata->fips_handle;
+
+	if (drvdata->hw_rev < CC_HW_REV_712)
+		return;
+
+	tasklet_schedule(&fips_handle_ptr->tasklet);
+}
+
+static inline void tee_fips_error(struct device *dev)
+{
+	if (fips_enabled)
+		panic("ccree: TEE reported cryptographic error in fips mode!\n");
+	else
+		dev_err(dev, "TEE reported error!\n");
+}
+
+/* Deferred service handler, run as interrupt-fired tasklet */
+static void fips_dsr(unsigned long devarg)
+{
+	struct cc_drvdata *drvdata = (struct cc_drvdata *)devarg;
+	struct device *dev = drvdata_to_dev(drvdata);
+	u32 irq, state, val;
+
+	irq = (drvdata->irq & (CC_GPR0_IRQ_MASK));
+
+	if (irq) {
+		state = cc_ioread(drvdata, CC_REG(GPR_HOST));
+
+		if (state != (CC_FIPS_SYNC_TEE_STATUS | CC_FIPS_SYNC_MODULE_OK))
+			tee_fips_error(dev);
+	}
+
+	/* after verifing that there is nothing to do,
+	 * unmask AXI completion interrupt.
+	 */
+	val = (CC_REG(HOST_IMR) & ~irq);
+	cc_iowrite(drvdata, CC_REG(HOST_IMR), val);
+}
+
+/* The function called once at driver entry point .*/
+int cc_fips_init(struct cc_drvdata *p_drvdata)
+{
+	struct cc_fips_handle *fips_h;
+	struct device *dev = drvdata_to_dev(p_drvdata);
+
+	if (p_drvdata->hw_rev < CC_HW_REV_712)
+		return 0;
+
+	fips_h = kzalloc(sizeof(*fips_h), GFP_KERNEL);
+	if (!fips_h)
+		return -ENOMEM;
+
+	p_drvdata->fips_handle = fips_h;
+
+	dev_dbg(dev, "Initializing fips tasklet\n");
+	tasklet_init(&fips_h->tasklet, fips_dsr, (unsigned long)p_drvdata);
+
+	if (!cc_get_tee_fips_status(p_drvdata))
+		tee_fips_error(dev);
+
+	return 0;
+}
diff --git a/drivers/crypto/ccree/cc_fips.h b/drivers/crypto/ccree/cc_fips.h
new file mode 100644
index 000000000000..645e096a7a82
--- /dev/null
+++ b/drivers/crypto/ccree/cc_fips.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#ifndef __CC_FIPS_H__
+#define __CC_FIPS_H__
+
+#ifdef CONFIG_CRYPTO_FIPS
+
+enum cc_fips_status {
+	CC_FIPS_SYNC_MODULE_OK = 0x0,
+	CC_FIPS_SYNC_MODULE_ERROR = 0x1,
+	CC_FIPS_SYNC_REE_STATUS = 0x4,
+	CC_FIPS_SYNC_TEE_STATUS = 0x8,
+	CC_FIPS_SYNC_STATUS_RESERVE32B = S32_MAX
+};
+
+int cc_fips_init(struct cc_drvdata *p_drvdata);
+void cc_fips_fini(struct cc_drvdata *drvdata);
+void fips_handler(struct cc_drvdata *drvdata);
+void cc_set_ree_fips_status(struct cc_drvdata *drvdata, bool ok);
+
+#else  /* CONFIG_CRYPTO_FIPS */
+
+static inline int cc_fips_init(struct cc_drvdata *p_drvdata)
+{
+	return 0;
+}
+
+static inline void cc_fips_fini(struct cc_drvdata *drvdata) {}
+static inline void cc_set_ree_fips_status(struct cc_drvdata *drvdata,
+					  bool ok) {}
+static inline void fips_handler(struct cc_drvdata *drvdata) {}
+
+#endif /* CONFIG_CRYPTO_FIPS */
+
+#endif  /*__CC_FIPS_H__*/
diff --git a/drivers/crypto/ccree/cc_hash.c b/drivers/crypto/ccree/cc_hash.c
new file mode 100644
index 000000000000..96ff777474d7
--- /dev/null
+++ b/drivers/crypto/ccree/cc_hash.c
@@ -0,0 +1,2296 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <crypto/algapi.h>
+#include <crypto/hash.h>
+#include <crypto/md5.h>
+#include <crypto/internal/hash.h>
+
+#include "cc_driver.h"
+#include "cc_request_mgr.h"
+#include "cc_buffer_mgr.h"
+#include "cc_hash.h"
+#include "cc_sram_mgr.h"
+
+#define CC_MAX_HASH_SEQ_LEN 12
+#define CC_MAX_OPAD_KEYS_SIZE CC_MAX_HASH_BLCK_SIZE
+
+struct cc_hash_handle {
+	cc_sram_addr_t digest_len_sram_addr; /* const value in SRAM*/
+	cc_sram_addr_t larval_digest_sram_addr;   /* const value in SRAM */
+	struct list_head hash_list;
+};
+
+static const u32 digest_len_init[] = {
+	0x00000040, 0x00000000, 0x00000000, 0x00000000 };
+static const u32 md5_init[] = {
+	SHA1_H3, SHA1_H2, SHA1_H1, SHA1_H0 };
+static const u32 sha1_init[] = {
+	SHA1_H4, SHA1_H3, SHA1_H2, SHA1_H1, SHA1_H0 };
+static const u32 sha224_init[] = {
+	SHA224_H7, SHA224_H6, SHA224_H5, SHA224_H4,
+	SHA224_H3, SHA224_H2, SHA224_H1, SHA224_H0 };
+static const u32 sha256_init[] = {
+	SHA256_H7, SHA256_H6, SHA256_H5, SHA256_H4,
+	SHA256_H3, SHA256_H2, SHA256_H1, SHA256_H0 };
+static const u32 digest_len_sha512_init[] = {
+	0x00000080, 0x00000000, 0x00000000, 0x00000000 };
+static u64 sha384_init[] = {
+	SHA384_H7, SHA384_H6, SHA384_H5, SHA384_H4,
+	SHA384_H3, SHA384_H2, SHA384_H1, SHA384_H0 };
+static u64 sha512_init[] = {
+	SHA512_H7, SHA512_H6, SHA512_H5, SHA512_H4,
+	SHA512_H3, SHA512_H2, SHA512_H1, SHA512_H0 };
+
+static void cc_setup_xcbc(struct ahash_request *areq, struct cc_hw_desc desc[],
+			  unsigned int *seq_size);
+
+static void cc_setup_cmac(struct ahash_request *areq, struct cc_hw_desc desc[],
+			  unsigned int *seq_size);
+
+static const void *cc_larval_digest(struct device *dev, u32 mode);
+
+struct cc_hash_alg {
+	struct list_head entry;
+	int hash_mode;
+	int hw_mode;
+	int inter_digestsize;
+	struct cc_drvdata *drvdata;
+	struct ahash_alg ahash_alg;
+};
+
+struct hash_key_req_ctx {
+	u32 keylen;
+	dma_addr_t key_dma_addr;
+};
+
+/* hash per-session context */
+struct cc_hash_ctx {
+	struct cc_drvdata *drvdata;
+	/* holds the origin digest; the digest after "setkey" if HMAC,*
+	 * the initial digest if HASH.
+	 */
+	u8 digest_buff[CC_MAX_HASH_DIGEST_SIZE]  ____cacheline_aligned;
+	u8 opad_tmp_keys_buff[CC_MAX_OPAD_KEYS_SIZE]  ____cacheline_aligned;
+
+	dma_addr_t opad_tmp_keys_dma_addr  ____cacheline_aligned;
+	dma_addr_t digest_buff_dma_addr;
+	/* use for hmac with key large then mode block size */
+	struct hash_key_req_ctx key_params;
+	int hash_mode;
+	int hw_mode;
+	int inter_digestsize;
+	struct completion setkey_comp;
+	bool is_hmac;
+};
+
+static void cc_set_desc(struct ahash_req_ctx *areq_ctx, struct cc_hash_ctx *ctx,
+			unsigned int flow_mode, struct cc_hw_desc desc[],
+			bool is_not_last_data, unsigned int *seq_size);
+
+static void cc_set_endianity(u32 mode, struct cc_hw_desc *desc)
+{
+	if (mode == DRV_HASH_MD5 || mode == DRV_HASH_SHA384 ||
+	    mode == DRV_HASH_SHA512) {
+		set_bytes_swap(desc, 1);
+	} else {
+		set_cipher_config0(desc, HASH_DIGEST_RESULT_LITTLE_ENDIAN);
+	}
+}
+
+static int cc_map_result(struct device *dev, struct ahash_req_ctx *state,
+			 unsigned int digestsize)
+{
+	state->digest_result_dma_addr =
+		dma_map_single(dev, state->digest_result_buff,
+			       digestsize, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dev, state->digest_result_dma_addr)) {
+		dev_err(dev, "Mapping digest result buffer %u B for DMA failed\n",
+			digestsize);
+		return -ENOMEM;
+	}
+	dev_dbg(dev, "Mapped digest result buffer %u B at va=%pK to dma=%pad\n",
+		digestsize, state->digest_result_buff,
+		&state->digest_result_dma_addr);
+
+	return 0;
+}
+
+static void cc_init_req(struct device *dev, struct ahash_req_ctx *state,
+			struct cc_hash_ctx *ctx)
+{
+	bool is_hmac = ctx->is_hmac;
+
+	memset(state, 0, sizeof(*state));
+
+	if (is_hmac) {
+		if (ctx->hw_mode != DRV_CIPHER_XCBC_MAC &&
+		    ctx->hw_mode != DRV_CIPHER_CMAC) {
+			dma_sync_single_for_cpu(dev, ctx->digest_buff_dma_addr,
+						ctx->inter_digestsize,
+						DMA_BIDIRECTIONAL);
+
+			memcpy(state->digest_buff, ctx->digest_buff,
+			       ctx->inter_digestsize);
+			if (ctx->hash_mode == DRV_HASH_SHA512 ||
+			    ctx->hash_mode == DRV_HASH_SHA384)
+				memcpy(state->digest_bytes_len,
+				       digest_len_sha512_init,
+				       ctx->drvdata->hash_len_sz);
+			else
+				memcpy(state->digest_bytes_len, digest_len_init,
+				       ctx->drvdata->hash_len_sz);
+		}
+
+		if (ctx->hash_mode != DRV_HASH_NULL) {
+			dma_sync_single_for_cpu(dev,
+						ctx->opad_tmp_keys_dma_addr,
+						ctx->inter_digestsize,
+						DMA_BIDIRECTIONAL);
+			memcpy(state->opad_digest_buff,
+			       ctx->opad_tmp_keys_buff, ctx->inter_digestsize);
+		}
+	} else { /*hash*/
+		/* Copy the initial digests if hash flow. */
+		const void *larval = cc_larval_digest(dev, ctx->hash_mode);
+
+		memcpy(state->digest_buff, larval, ctx->inter_digestsize);
+	}
+}
+
+static int cc_map_req(struct device *dev, struct ahash_req_ctx *state,
+		      struct cc_hash_ctx *ctx)
+{
+	bool is_hmac = ctx->is_hmac;
+
+	state->digest_buff_dma_addr =
+		dma_map_single(dev, state->digest_buff,
+			       ctx->inter_digestsize, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dev, state->digest_buff_dma_addr)) {
+		dev_err(dev, "Mapping digest len %d B at va=%pK for DMA failed\n",
+			ctx->inter_digestsize, state->digest_buff);
+		return -EINVAL;
+	}
+	dev_dbg(dev, "Mapped digest %d B at va=%pK to dma=%pad\n",
+		ctx->inter_digestsize, state->digest_buff,
+		&state->digest_buff_dma_addr);
+
+	if (ctx->hw_mode != DRV_CIPHER_XCBC_MAC) {
+		state->digest_bytes_len_dma_addr =
+			dma_map_single(dev, state->digest_bytes_len,
+				       HASH_MAX_LEN_SIZE, DMA_BIDIRECTIONAL);
+		if (dma_mapping_error(dev, state->digest_bytes_len_dma_addr)) {
+			dev_err(dev, "Mapping digest len %u B at va=%pK for DMA failed\n",
+				HASH_MAX_LEN_SIZE, state->digest_bytes_len);
+			goto unmap_digest_buf;
+		}
+		dev_dbg(dev, "Mapped digest len %u B at va=%pK to dma=%pad\n",
+			HASH_MAX_LEN_SIZE, state->digest_bytes_len,
+			&state->digest_bytes_len_dma_addr);
+	}
+
+	if (is_hmac && ctx->hash_mode != DRV_HASH_NULL) {
+		state->opad_digest_dma_addr =
+			dma_map_single(dev, state->opad_digest_buff,
+				       ctx->inter_digestsize,
+				       DMA_BIDIRECTIONAL);
+		if (dma_mapping_error(dev, state->opad_digest_dma_addr)) {
+			dev_err(dev, "Mapping opad digest %d B at va=%pK for DMA failed\n",
+				ctx->inter_digestsize,
+				state->opad_digest_buff);
+			goto unmap_digest_len;
+		}
+		dev_dbg(dev, "Mapped opad digest %d B at va=%pK to dma=%pad\n",
+			ctx->inter_digestsize, state->opad_digest_buff,
+			&state->opad_digest_dma_addr);
+	}
+
+	return 0;
+
+unmap_digest_len:
+	if (state->digest_bytes_len_dma_addr) {
+		dma_unmap_single(dev, state->digest_bytes_len_dma_addr,
+				 HASH_MAX_LEN_SIZE, DMA_BIDIRECTIONAL);
+		state->digest_bytes_len_dma_addr = 0;
+	}
+unmap_digest_buf:
+	if (state->digest_buff_dma_addr) {
+		dma_unmap_single(dev, state->digest_buff_dma_addr,
+				 ctx->inter_digestsize, DMA_BIDIRECTIONAL);
+		state->digest_buff_dma_addr = 0;
+	}
+
+	return -EINVAL;
+}
+
+static void cc_unmap_req(struct device *dev, struct ahash_req_ctx *state,
+			 struct cc_hash_ctx *ctx)
+{
+	if (state->digest_buff_dma_addr) {
+		dma_unmap_single(dev, state->digest_buff_dma_addr,
+				 ctx->inter_digestsize, DMA_BIDIRECTIONAL);
+		dev_dbg(dev, "Unmapped digest-buffer: digest_buff_dma_addr=%pad\n",
+			&state->digest_buff_dma_addr);
+		state->digest_buff_dma_addr = 0;
+	}
+	if (state->digest_bytes_len_dma_addr) {
+		dma_unmap_single(dev, state->digest_bytes_len_dma_addr,
+				 HASH_MAX_LEN_SIZE, DMA_BIDIRECTIONAL);
+		dev_dbg(dev, "Unmapped digest-bytes-len buffer: digest_bytes_len_dma_addr=%pad\n",
+			&state->digest_bytes_len_dma_addr);
+		state->digest_bytes_len_dma_addr = 0;
+	}
+	if (state->opad_digest_dma_addr) {
+		dma_unmap_single(dev, state->opad_digest_dma_addr,
+				 ctx->inter_digestsize, DMA_BIDIRECTIONAL);
+		dev_dbg(dev, "Unmapped opad-digest: opad_digest_dma_addr=%pad\n",
+			&state->opad_digest_dma_addr);
+		state->opad_digest_dma_addr = 0;
+	}
+}
+
+static void cc_unmap_result(struct device *dev, struct ahash_req_ctx *state,
+			    unsigned int digestsize, u8 *result)
+{
+	if (state->digest_result_dma_addr) {
+		dma_unmap_single(dev, state->digest_result_dma_addr, digestsize,
+				 DMA_BIDIRECTIONAL);
+		dev_dbg(dev, "unmpa digest result buffer va (%pK) pa (%pad) len %u\n",
+			state->digest_result_buff,
+			&state->digest_result_dma_addr, digestsize);
+		memcpy(result, state->digest_result_buff, digestsize);
+	}
+	state->digest_result_dma_addr = 0;
+}
+
+static void cc_update_complete(struct device *dev, void *cc_req, int err)
+{
+	struct ahash_request *req = (struct ahash_request *)cc_req;
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	dev_dbg(dev, "req=%pK\n", req);
+
+	cc_unmap_hash_request(dev, state, req->src, false);
+	cc_unmap_req(dev, state, ctx);
+	req->base.complete(&req->base, err);
+}
+
+static void cc_digest_complete(struct device *dev, void *cc_req, int err)
+{
+	struct ahash_request *req = (struct ahash_request *)cc_req;
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	u32 digestsize = crypto_ahash_digestsize(tfm);
+
+	dev_dbg(dev, "req=%pK\n", req);
+
+	cc_unmap_hash_request(dev, state, req->src, false);
+	cc_unmap_result(dev, state, digestsize, req->result);
+	cc_unmap_req(dev, state, ctx);
+	req->base.complete(&req->base, err);
+}
+
+static void cc_hash_complete(struct device *dev, void *cc_req, int err)
+{
+	struct ahash_request *req = (struct ahash_request *)cc_req;
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	u32 digestsize = crypto_ahash_digestsize(tfm);
+
+	dev_dbg(dev, "req=%pK\n", req);
+
+	cc_unmap_hash_request(dev, state, req->src, false);
+	cc_unmap_result(dev, state, digestsize, req->result);
+	cc_unmap_req(dev, state, ctx);
+	req->base.complete(&req->base, err);
+}
+
+static int cc_fin_result(struct cc_hw_desc *desc, struct ahash_request *req,
+			 int idx)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	u32 digestsize = crypto_ahash_digestsize(tfm);
+
+	/* Get final MAC result */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	/* TODO */
+	set_dout_dlli(&desc[idx], state->digest_result_dma_addr, digestsize,
+		      NS_BIT, 1);
+	set_queue_last_ind(ctx->drvdata, &desc[idx]);
+	set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+	set_cipher_config1(&desc[idx], HASH_PADDING_DISABLED);
+	cc_set_endianity(ctx->hash_mode, &desc[idx]);
+	idx++;
+
+	return idx;
+}
+
+static int cc_fin_hmac(struct cc_hw_desc *desc, struct ahash_request *req,
+		       int idx)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	u32 digestsize = crypto_ahash_digestsize(tfm);
+
+	/* store the hash digest result in the context */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	set_dout_dlli(&desc[idx], state->digest_buff_dma_addr, digestsize,
+		      NS_BIT, 0);
+	set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+	cc_set_endianity(ctx->hash_mode, &desc[idx]);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+	idx++;
+
+	/* Loading hash opad xor key state */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	set_din_type(&desc[idx], DMA_DLLI, state->opad_digest_dma_addr,
+		     ctx->inter_digestsize, NS_BIT);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	idx++;
+
+	/* Load the hash current length */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	set_din_sram(&desc[idx],
+		     cc_digest_len_addr(ctx->drvdata, ctx->hash_mode),
+		     ctx->drvdata->hash_len_sz);
+	set_cipher_config1(&desc[idx], HASH_PADDING_ENABLED);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	idx++;
+
+	/* Memory Barrier: wait for IPAD/OPAD axi write to complete */
+	hw_desc_init(&desc[idx]);
+	set_din_no_dma(&desc[idx], 0, 0xfffff0);
+	set_dout_no_dma(&desc[idx], 0, 0, 1);
+	idx++;
+
+	/* Perform HASH update */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI, state->digest_buff_dma_addr,
+		     digestsize, NS_BIT);
+	set_flow_mode(&desc[idx], DIN_HASH);
+	idx++;
+
+	return idx;
+}
+
+static int cc_hash_digest(struct ahash_request *req)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	u32 digestsize = crypto_ahash_digestsize(tfm);
+	struct scatterlist *src = req->src;
+	unsigned int nbytes = req->nbytes;
+	u8 *result = req->result;
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	bool is_hmac = ctx->is_hmac;
+	struct cc_crypto_req cc_req = {};
+	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
+	cc_sram_addr_t larval_digest_addr =
+		cc_larval_digest_addr(ctx->drvdata, ctx->hash_mode);
+	int idx = 0;
+	int rc = 0;
+	gfp_t flags = cc_gfp_flags(&req->base);
+
+	dev_dbg(dev, "===== %s-digest (%d) ====\n", is_hmac ? "hmac" : "hash",
+		nbytes);
+
+	cc_init_req(dev, state, ctx);
+
+	if (cc_map_req(dev, state, ctx)) {
+		dev_err(dev, "map_ahash_source() failed\n");
+		return -ENOMEM;
+	}
+
+	if (cc_map_result(dev, state, digestsize)) {
+		dev_err(dev, "map_ahash_digest() failed\n");
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+
+	if (cc_map_hash_request_final(ctx->drvdata, state, src, nbytes, 1,
+				      flags)) {
+		dev_err(dev, "map_ahash_request_final() failed\n");
+		cc_unmap_result(dev, state, digestsize, result);
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+
+	/* Setup request structure */
+	cc_req.user_cb = cc_digest_complete;
+	cc_req.user_arg = req;
+
+	/* If HMAC then load hash IPAD xor key, if HASH then load initial
+	 * digest
+	 */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	if (is_hmac) {
+		set_din_type(&desc[idx], DMA_DLLI, state->digest_buff_dma_addr,
+			     ctx->inter_digestsize, NS_BIT);
+	} else {
+		set_din_sram(&desc[idx], larval_digest_addr,
+			     ctx->inter_digestsize);
+	}
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	idx++;
+
+	/* Load the hash current length */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+
+	if (is_hmac) {
+		set_din_type(&desc[idx], DMA_DLLI,
+			     state->digest_bytes_len_dma_addr,
+			     ctx->drvdata->hash_len_sz, NS_BIT);
+	} else {
+		set_din_const(&desc[idx], 0, ctx->drvdata->hash_len_sz);
+		if (nbytes)
+			set_cipher_config1(&desc[idx], HASH_PADDING_ENABLED);
+		else
+			set_cipher_do(&desc[idx], DO_PAD);
+	}
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	idx++;
+
+	cc_set_desc(state, ctx, DIN_HASH, desc, false, &idx);
+
+	if (is_hmac) {
+		/* HW last hash block padding (aka. "DO_PAD") */
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], ctx->hw_mode);
+		set_dout_dlli(&desc[idx], state->digest_buff_dma_addr,
+			      ctx->drvdata->hash_len_sz, NS_BIT, 0);
+		set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+		set_setup_mode(&desc[idx], SETUP_WRITE_STATE1);
+		set_cipher_do(&desc[idx], DO_PAD);
+		idx++;
+
+		idx = cc_fin_hmac(desc, req, idx);
+	}
+
+	idx = cc_fin_result(desc, req, idx);
+
+	rc = cc_send_request(ctx->drvdata, &cc_req, desc, idx, &req->base);
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+		cc_unmap_hash_request(dev, state, src, true);
+		cc_unmap_result(dev, state, digestsize, result);
+		cc_unmap_req(dev, state, ctx);
+	}
+	return rc;
+}
+
+static int cc_restore_hash(struct cc_hw_desc *desc, struct cc_hash_ctx *ctx,
+			   struct ahash_req_ctx *state, unsigned int idx)
+{
+	/* Restore hash digest */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	set_din_type(&desc[idx], DMA_DLLI, state->digest_buff_dma_addr,
+		     ctx->inter_digestsize, NS_BIT);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	idx++;
+
+	/* Restore hash current length */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	set_cipher_config1(&desc[idx], HASH_PADDING_DISABLED);
+	set_din_type(&desc[idx], DMA_DLLI, state->digest_bytes_len_dma_addr,
+		     ctx->drvdata->hash_len_sz, NS_BIT);
+	set_flow_mode(&desc[idx], S_DIN_to_HASH);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	idx++;
+
+	cc_set_desc(state, ctx, DIN_HASH, desc, false, &idx);
+
+	return idx;
+}
+
+static int cc_hash_update(struct ahash_request *req)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	unsigned int block_size = crypto_tfm_alg_blocksize(&tfm->base);
+	struct scatterlist *src = req->src;
+	unsigned int nbytes = req->nbytes;
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	struct cc_crypto_req cc_req = {};
+	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
+	u32 idx = 0;
+	int rc;
+	gfp_t flags = cc_gfp_flags(&req->base);
+
+	dev_dbg(dev, "===== %s-update (%d) ====\n", ctx->is_hmac ?
+		"hmac" : "hash", nbytes);
+
+	if (nbytes == 0) {
+		/* no real updates required */
+		return 0;
+	}
+
+	rc = cc_map_hash_request_update(ctx->drvdata, state, src, nbytes,
+					block_size, flags);
+	if (rc) {
+		if (rc == 1) {
+			dev_dbg(dev, " data size not require HW update %x\n",
+				nbytes);
+			/* No hardware updates are required */
+			return 0;
+		}
+		dev_err(dev, "map_ahash_request_update() failed\n");
+		return -ENOMEM;
+	}
+
+	if (cc_map_req(dev, state, ctx)) {
+		dev_err(dev, "map_ahash_source() failed\n");
+		cc_unmap_hash_request(dev, state, src, true);
+		return -EINVAL;
+	}
+
+	/* Setup request structure */
+	cc_req.user_cb = cc_update_complete;
+	cc_req.user_arg = req;
+
+	idx = cc_restore_hash(desc, ctx, state, idx);
+
+	/* store the hash digest result in context */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	set_dout_dlli(&desc[idx], state->digest_buff_dma_addr,
+		      ctx->inter_digestsize, NS_BIT, 0);
+	set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+	idx++;
+
+	/* store current hash length in context */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	set_dout_dlli(&desc[idx], state->digest_bytes_len_dma_addr,
+		      ctx->drvdata->hash_len_sz, NS_BIT, 1);
+	set_queue_last_ind(ctx->drvdata, &desc[idx]);
+	set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE1);
+	idx++;
+
+	rc = cc_send_request(ctx->drvdata, &cc_req, desc, idx, &req->base);
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+		cc_unmap_hash_request(dev, state, src, true);
+		cc_unmap_req(dev, state, ctx);
+	}
+	return rc;
+}
+
+static int cc_hash_finup(struct ahash_request *req)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	u32 digestsize = crypto_ahash_digestsize(tfm);
+	struct scatterlist *src = req->src;
+	unsigned int nbytes = req->nbytes;
+	u8 *result = req->result;
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	bool is_hmac = ctx->is_hmac;
+	struct cc_crypto_req cc_req = {};
+	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
+	unsigned int idx = 0;
+	int rc;
+	gfp_t flags = cc_gfp_flags(&req->base);
+
+	dev_dbg(dev, "===== %s-finup (%d) ====\n", is_hmac ? "hmac" : "hash",
+		nbytes);
+
+	if (cc_map_req(dev, state, ctx)) {
+		dev_err(dev, "map_ahash_source() failed\n");
+		return -EINVAL;
+	}
+
+	if (cc_map_hash_request_final(ctx->drvdata, state, src, nbytes, 1,
+				      flags)) {
+		dev_err(dev, "map_ahash_request_final() failed\n");
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+	if (cc_map_result(dev, state, digestsize)) {
+		dev_err(dev, "map_ahash_digest() failed\n");
+		cc_unmap_hash_request(dev, state, src, true);
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+
+	/* Setup request structure */
+	cc_req.user_cb = cc_hash_complete;
+	cc_req.user_arg = req;
+
+	idx = cc_restore_hash(desc, ctx, state, idx);
+
+	if (is_hmac)
+		idx = cc_fin_hmac(desc, req, idx);
+
+	idx = cc_fin_result(desc, req, idx);
+
+	rc = cc_send_request(ctx->drvdata, &cc_req, desc, idx, &req->base);
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+		cc_unmap_hash_request(dev, state, src, true);
+		cc_unmap_result(dev, state, digestsize, result);
+		cc_unmap_req(dev, state, ctx);
+	}
+	return rc;
+}
+
+static int cc_hash_final(struct ahash_request *req)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	u32 digestsize = crypto_ahash_digestsize(tfm);
+	struct scatterlist *src = req->src;
+	unsigned int nbytes = req->nbytes;
+	u8 *result = req->result;
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	bool is_hmac = ctx->is_hmac;
+	struct cc_crypto_req cc_req = {};
+	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
+	unsigned int idx = 0;
+	int rc;
+	gfp_t flags = cc_gfp_flags(&req->base);
+
+	dev_dbg(dev, "===== %s-final (%d) ====\n", is_hmac ? "hmac" : "hash",
+		nbytes);
+
+	if (cc_map_req(dev, state, ctx)) {
+		dev_err(dev, "map_ahash_source() failed\n");
+		return -EINVAL;
+	}
+
+	if (cc_map_hash_request_final(ctx->drvdata, state, src, nbytes, 0,
+				      flags)) {
+		dev_err(dev, "map_ahash_request_final() failed\n");
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+
+	if (cc_map_result(dev, state, digestsize)) {
+		dev_err(dev, "map_ahash_digest() failed\n");
+		cc_unmap_hash_request(dev, state, src, true);
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+
+	/* Setup request structure */
+	cc_req.user_cb = cc_hash_complete;
+	cc_req.user_arg = req;
+
+	idx = cc_restore_hash(desc, ctx, state, idx);
+
+	/* "DO-PAD" must be enabled only when writing current length to HW */
+	hw_desc_init(&desc[idx]);
+	set_cipher_do(&desc[idx], DO_PAD);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	set_dout_dlli(&desc[idx], state->digest_bytes_len_dma_addr,
+		      ctx->drvdata->hash_len_sz, NS_BIT, 0);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE1);
+	set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+	idx++;
+
+	if (is_hmac)
+		idx = cc_fin_hmac(desc, req, idx);
+
+	idx = cc_fin_result(desc, req, idx);
+
+	rc = cc_send_request(ctx->drvdata, &cc_req, desc, idx, &req->base);
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+		cc_unmap_hash_request(dev, state, src, true);
+		cc_unmap_result(dev, state, digestsize, result);
+		cc_unmap_req(dev, state, ctx);
+	}
+	return rc;
+}
+
+static int cc_hash_init(struct ahash_request *req)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	dev_dbg(dev, "===== init (%d) ====\n", req->nbytes);
+
+	cc_init_req(dev, state, ctx);
+
+	return 0;
+}
+
+static int cc_hash_setkey(struct crypto_ahash *ahash, const u8 *key,
+			  unsigned int keylen)
+{
+	unsigned int hmac_pad_const[2] = { HMAC_IPAD_CONST, HMAC_OPAD_CONST };
+	struct cc_crypto_req cc_req = {};
+	struct cc_hash_ctx *ctx = NULL;
+	int blocksize = 0;
+	int digestsize = 0;
+	int i, idx = 0, rc = 0;
+	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
+	cc_sram_addr_t larval_addr;
+	struct device *dev;
+
+	ctx = crypto_ahash_ctx(ahash);
+	dev = drvdata_to_dev(ctx->drvdata);
+	dev_dbg(dev, "start keylen: %d", keylen);
+
+	blocksize = crypto_tfm_alg_blocksize(&ahash->base);
+	digestsize = crypto_ahash_digestsize(ahash);
+
+	larval_addr = cc_larval_digest_addr(ctx->drvdata, ctx->hash_mode);
+
+	/* The keylen value distinguishes HASH in case keylen is ZERO bytes,
+	 * any NON-ZERO value utilizes HMAC flow
+	 */
+	ctx->key_params.keylen = keylen;
+	ctx->key_params.key_dma_addr = 0;
+	ctx->is_hmac = true;
+
+	if (keylen) {
+		ctx->key_params.key_dma_addr =
+			dma_map_single(dev, (void *)key, keylen, DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, ctx->key_params.key_dma_addr)) {
+			dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
+				key, keylen);
+			return -ENOMEM;
+		}
+		dev_dbg(dev, "mapping key-buffer: key_dma_addr=%pad keylen=%u\n",
+			&ctx->key_params.key_dma_addr, ctx->key_params.keylen);
+
+		if (keylen > blocksize) {
+			/* Load hash initial state */
+			hw_desc_init(&desc[idx]);
+			set_cipher_mode(&desc[idx], ctx->hw_mode);
+			set_din_sram(&desc[idx], larval_addr,
+				     ctx->inter_digestsize);
+			set_flow_mode(&desc[idx], S_DIN_to_HASH);
+			set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+			idx++;
+
+			/* Load the hash current length*/
+			hw_desc_init(&desc[idx]);
+			set_cipher_mode(&desc[idx], ctx->hw_mode);
+			set_din_const(&desc[idx], 0, ctx->drvdata->hash_len_sz);
+			set_cipher_config1(&desc[idx], HASH_PADDING_ENABLED);
+			set_flow_mode(&desc[idx], S_DIN_to_HASH);
+			set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+			idx++;
+
+			hw_desc_init(&desc[idx]);
+			set_din_type(&desc[idx], DMA_DLLI,
+				     ctx->key_params.key_dma_addr, keylen,
+				     NS_BIT);
+			set_flow_mode(&desc[idx], DIN_HASH);
+			idx++;
+
+			/* Get hashed key */
+			hw_desc_init(&desc[idx]);
+			set_cipher_mode(&desc[idx], ctx->hw_mode);
+			set_dout_dlli(&desc[idx], ctx->opad_tmp_keys_dma_addr,
+				      digestsize, NS_BIT, 0);
+			set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+			set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+			set_cipher_config1(&desc[idx], HASH_PADDING_DISABLED);
+			cc_set_endianity(ctx->hash_mode, &desc[idx]);
+			idx++;
+
+			hw_desc_init(&desc[idx]);
+			set_din_const(&desc[idx], 0, (blocksize - digestsize));
+			set_flow_mode(&desc[idx], BYPASS);
+			set_dout_dlli(&desc[idx],
+				      (ctx->opad_tmp_keys_dma_addr +
+				       digestsize),
+				      (blocksize - digestsize), NS_BIT, 0);
+			idx++;
+		} else {
+			hw_desc_init(&desc[idx]);
+			set_din_type(&desc[idx], DMA_DLLI,
+				     ctx->key_params.key_dma_addr, keylen,
+				     NS_BIT);
+			set_flow_mode(&desc[idx], BYPASS);
+			set_dout_dlli(&desc[idx], ctx->opad_tmp_keys_dma_addr,
+				      keylen, NS_BIT, 0);
+			idx++;
+
+			if ((blocksize - keylen)) {
+				hw_desc_init(&desc[idx]);
+				set_din_const(&desc[idx], 0,
+					      (blocksize - keylen));
+				set_flow_mode(&desc[idx], BYPASS);
+				set_dout_dlli(&desc[idx],
+					      (ctx->opad_tmp_keys_dma_addr +
+					       keylen), (blocksize - keylen),
+					      NS_BIT, 0);
+				idx++;
+			}
+		}
+	} else {
+		hw_desc_init(&desc[idx]);
+		set_din_const(&desc[idx], 0, blocksize);
+		set_flow_mode(&desc[idx], BYPASS);
+		set_dout_dlli(&desc[idx], (ctx->opad_tmp_keys_dma_addr),
+			      blocksize, NS_BIT, 0);
+		idx++;
+	}
+
+	rc = cc_send_sync_request(ctx->drvdata, &cc_req, desc, idx);
+	if (rc) {
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+		goto out;
+	}
+
+	/* calc derived HMAC key */
+	for (idx = 0, i = 0; i < 2; i++) {
+		/* Load hash initial state */
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], ctx->hw_mode);
+		set_din_sram(&desc[idx], larval_addr, ctx->inter_digestsize);
+		set_flow_mode(&desc[idx], S_DIN_to_HASH);
+		set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+		idx++;
+
+		/* Load the hash current length*/
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], ctx->hw_mode);
+		set_din_const(&desc[idx], 0, ctx->drvdata->hash_len_sz);
+		set_flow_mode(&desc[idx], S_DIN_to_HASH);
+		set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+		idx++;
+
+		/* Prepare ipad key */
+		hw_desc_init(&desc[idx]);
+		set_xor_val(&desc[idx], hmac_pad_const[i]);
+		set_cipher_mode(&desc[idx], ctx->hw_mode);
+		set_flow_mode(&desc[idx], S_DIN_to_HASH);
+		set_setup_mode(&desc[idx], SETUP_LOAD_STATE1);
+		idx++;
+
+		/* Perform HASH update */
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_DLLI, ctx->opad_tmp_keys_dma_addr,
+			     blocksize, NS_BIT);
+		set_cipher_mode(&desc[idx], ctx->hw_mode);
+		set_xor_active(&desc[idx]);
+		set_flow_mode(&desc[idx], DIN_HASH);
+		idx++;
+
+		/* Get the IPAD/OPAD xor key (Note, IPAD is the initial digest
+		 * of the first HASH "update" state)
+		 */
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], ctx->hw_mode);
+		if (i > 0) /* Not first iteration */
+			set_dout_dlli(&desc[idx], ctx->opad_tmp_keys_dma_addr,
+				      ctx->inter_digestsize, NS_BIT, 0);
+		else /* First iteration */
+			set_dout_dlli(&desc[idx], ctx->digest_buff_dma_addr,
+				      ctx->inter_digestsize, NS_BIT, 0);
+		set_flow_mode(&desc[idx], S_HASH_to_DOUT);
+		set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+		idx++;
+	}
+
+	rc = cc_send_sync_request(ctx->drvdata, &cc_req, desc, idx);
+
+out:
+	if (rc)
+		crypto_ahash_set_flags(ahash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+
+	if (ctx->key_params.key_dma_addr) {
+		dma_unmap_single(dev, ctx->key_params.key_dma_addr,
+				 ctx->key_params.keylen, DMA_TO_DEVICE);
+		dev_dbg(dev, "Unmapped key-buffer: key_dma_addr=%pad keylen=%u\n",
+			&ctx->key_params.key_dma_addr, ctx->key_params.keylen);
+	}
+	return rc;
+}
+
+static int cc_xcbc_setkey(struct crypto_ahash *ahash,
+			  const u8 *key, unsigned int keylen)
+{
+	struct cc_crypto_req cc_req = {};
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	int rc = 0;
+	unsigned int idx = 0;
+	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
+
+	dev_dbg(dev, "===== setkey (%d) ====\n", keylen);
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+	case AES_KEYSIZE_192:
+	case AES_KEYSIZE_256:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ctx->key_params.keylen = keylen;
+
+	ctx->key_params.key_dma_addr =
+		dma_map_single(dev, (void *)key, keylen, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, ctx->key_params.key_dma_addr)) {
+		dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
+			key, keylen);
+		return -ENOMEM;
+	}
+	dev_dbg(dev, "mapping key-buffer: key_dma_addr=%pad keylen=%u\n",
+		&ctx->key_params.key_dma_addr, ctx->key_params.keylen);
+
+	ctx->is_hmac = true;
+	/* 1. Load the AES key */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI, ctx->key_params.key_dma_addr,
+		     keylen, NS_BIT);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_ECB);
+	set_cipher_config0(&desc[idx], DRV_CRYPTO_DIRECTION_ENCRYPT);
+	set_key_size_aes(&desc[idx], keylen);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	idx++;
+
+	hw_desc_init(&desc[idx]);
+	set_din_const(&desc[idx], 0x01010101, CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], DIN_AES_DOUT);
+	set_dout_dlli(&desc[idx],
+		      (ctx->opad_tmp_keys_dma_addr + XCBC_MAC_K1_OFFSET),
+		      CC_AES_128_BIT_KEY_SIZE, NS_BIT, 0);
+	idx++;
+
+	hw_desc_init(&desc[idx]);
+	set_din_const(&desc[idx], 0x02020202, CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], DIN_AES_DOUT);
+	set_dout_dlli(&desc[idx],
+		      (ctx->opad_tmp_keys_dma_addr + XCBC_MAC_K2_OFFSET),
+		      CC_AES_128_BIT_KEY_SIZE, NS_BIT, 0);
+	idx++;
+
+	hw_desc_init(&desc[idx]);
+	set_din_const(&desc[idx], 0x03030303, CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], DIN_AES_DOUT);
+	set_dout_dlli(&desc[idx],
+		      (ctx->opad_tmp_keys_dma_addr + XCBC_MAC_K3_OFFSET),
+		      CC_AES_128_BIT_KEY_SIZE, NS_BIT, 0);
+	idx++;
+
+	rc = cc_send_sync_request(ctx->drvdata, &cc_req, desc, idx);
+
+	if (rc)
+		crypto_ahash_set_flags(ahash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+
+	dma_unmap_single(dev, ctx->key_params.key_dma_addr,
+			 ctx->key_params.keylen, DMA_TO_DEVICE);
+	dev_dbg(dev, "Unmapped key-buffer: key_dma_addr=%pad keylen=%u\n",
+		&ctx->key_params.key_dma_addr, ctx->key_params.keylen);
+
+	return rc;
+}
+
+static int cc_cmac_setkey(struct crypto_ahash *ahash,
+			  const u8 *key, unsigned int keylen)
+{
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	dev_dbg(dev, "===== setkey (%d) ====\n", keylen);
+
+	ctx->is_hmac = true;
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+	case AES_KEYSIZE_192:
+	case AES_KEYSIZE_256:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ctx->key_params.keylen = keylen;
+
+	/* STAT_PHASE_1: Copy key to ctx */
+
+	dma_sync_single_for_cpu(dev, ctx->opad_tmp_keys_dma_addr,
+				keylen, DMA_TO_DEVICE);
+
+	memcpy(ctx->opad_tmp_keys_buff, key, keylen);
+	if (keylen == 24) {
+		memset(ctx->opad_tmp_keys_buff + 24, 0,
+		       CC_AES_KEY_SIZE_MAX - 24);
+	}
+
+	dma_sync_single_for_device(dev, ctx->opad_tmp_keys_dma_addr,
+				   keylen, DMA_TO_DEVICE);
+
+	ctx->key_params.keylen = keylen;
+
+	return 0;
+}
+
+static void cc_free_ctx(struct cc_hash_ctx *ctx)
+{
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	if (ctx->digest_buff_dma_addr) {
+		dma_unmap_single(dev, ctx->digest_buff_dma_addr,
+				 sizeof(ctx->digest_buff), DMA_BIDIRECTIONAL);
+		dev_dbg(dev, "Unmapped digest-buffer: digest_buff_dma_addr=%pad\n",
+			&ctx->digest_buff_dma_addr);
+		ctx->digest_buff_dma_addr = 0;
+	}
+	if (ctx->opad_tmp_keys_dma_addr) {
+		dma_unmap_single(dev, ctx->opad_tmp_keys_dma_addr,
+				 sizeof(ctx->opad_tmp_keys_buff),
+				 DMA_BIDIRECTIONAL);
+		dev_dbg(dev, "Unmapped opad-digest: opad_tmp_keys_dma_addr=%pad\n",
+			&ctx->opad_tmp_keys_dma_addr);
+		ctx->opad_tmp_keys_dma_addr = 0;
+	}
+
+	ctx->key_params.keylen = 0;
+}
+
+static int cc_alloc_ctx(struct cc_hash_ctx *ctx)
+{
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	ctx->key_params.keylen = 0;
+
+	ctx->digest_buff_dma_addr =
+		dma_map_single(dev, (void *)ctx->digest_buff,
+			       sizeof(ctx->digest_buff), DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dev, ctx->digest_buff_dma_addr)) {
+		dev_err(dev, "Mapping digest len %zu B at va=%pK for DMA failed\n",
+			sizeof(ctx->digest_buff), ctx->digest_buff);
+		goto fail;
+	}
+	dev_dbg(dev, "Mapped digest %zu B at va=%pK to dma=%pad\n",
+		sizeof(ctx->digest_buff), ctx->digest_buff,
+		&ctx->digest_buff_dma_addr);
+
+	ctx->opad_tmp_keys_dma_addr =
+		dma_map_single(dev, (void *)ctx->opad_tmp_keys_buff,
+			       sizeof(ctx->opad_tmp_keys_buff),
+			       DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dev, ctx->opad_tmp_keys_dma_addr)) {
+		dev_err(dev, "Mapping opad digest %zu B at va=%pK for DMA failed\n",
+			sizeof(ctx->opad_tmp_keys_buff),
+			ctx->opad_tmp_keys_buff);
+		goto fail;
+	}
+	dev_dbg(dev, "Mapped opad_tmp_keys %zu B at va=%pK to dma=%pad\n",
+		sizeof(ctx->opad_tmp_keys_buff), ctx->opad_tmp_keys_buff,
+		&ctx->opad_tmp_keys_dma_addr);
+
+	ctx->is_hmac = false;
+	return 0;
+
+fail:
+	cc_free_ctx(ctx);
+	return -ENOMEM;
+}
+
+static int cc_cra_init(struct crypto_tfm *tfm)
+{
+	struct cc_hash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct hash_alg_common *hash_alg_common =
+		container_of(tfm->__crt_alg, struct hash_alg_common, base);
+	struct ahash_alg *ahash_alg =
+		container_of(hash_alg_common, struct ahash_alg, halg);
+	struct cc_hash_alg *cc_alg =
+			container_of(ahash_alg, struct cc_hash_alg, ahash_alg);
+
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct ahash_req_ctx));
+
+	ctx->hash_mode = cc_alg->hash_mode;
+	ctx->hw_mode = cc_alg->hw_mode;
+	ctx->inter_digestsize = cc_alg->inter_digestsize;
+	ctx->drvdata = cc_alg->drvdata;
+
+	return cc_alloc_ctx(ctx);
+}
+
+static void cc_cra_exit(struct crypto_tfm *tfm)
+{
+	struct cc_hash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	dev_dbg(dev, "cc_cra_exit");
+	cc_free_ctx(ctx);
+}
+
+static int cc_mac_update(struct ahash_request *req)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	unsigned int block_size = crypto_tfm_alg_blocksize(&tfm->base);
+	struct cc_crypto_req cc_req = {};
+	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
+	int rc;
+	u32 idx = 0;
+	gfp_t flags = cc_gfp_flags(&req->base);
+
+	if (req->nbytes == 0) {
+		/* no real updates required */
+		return 0;
+	}
+
+	state->xcbc_count++;
+
+	rc = cc_map_hash_request_update(ctx->drvdata, state, req->src,
+					req->nbytes, block_size, flags);
+	if (rc) {
+		if (rc == 1) {
+			dev_dbg(dev, " data size not require HW update %x\n",
+				req->nbytes);
+			/* No hardware updates are required */
+			return 0;
+		}
+		dev_err(dev, "map_ahash_request_update() failed\n");
+		return -ENOMEM;
+	}
+
+	if (cc_map_req(dev, state, ctx)) {
+		dev_err(dev, "map_ahash_source() failed\n");
+		return -EINVAL;
+	}
+
+	if (ctx->hw_mode == DRV_CIPHER_XCBC_MAC)
+		cc_setup_xcbc(req, desc, &idx);
+	else
+		cc_setup_cmac(req, desc, &idx);
+
+	cc_set_desc(state, ctx, DIN_AES_DOUT, desc, true, &idx);
+
+	/* store the hash digest result in context */
+	hw_desc_init(&desc[idx]);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	set_dout_dlli(&desc[idx], state->digest_buff_dma_addr,
+		      ctx->inter_digestsize, NS_BIT, 1);
+	set_queue_last_ind(ctx->drvdata, &desc[idx]);
+	set_flow_mode(&desc[idx], S_AES_to_DOUT);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+	idx++;
+
+	/* Setup request structure */
+	cc_req.user_cb = (void *)cc_update_complete;
+	cc_req.user_arg = (void *)req;
+
+	rc = cc_send_request(ctx->drvdata, &cc_req, desc, idx, &req->base);
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+		cc_unmap_hash_request(dev, state, req->src, true);
+		cc_unmap_req(dev, state, ctx);
+	}
+	return rc;
+}
+
+static int cc_mac_final(struct ahash_request *req)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	struct cc_crypto_req cc_req = {};
+	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
+	int idx = 0;
+	int rc = 0;
+	u32 key_size, key_len;
+	u32 digestsize = crypto_ahash_digestsize(tfm);
+	gfp_t flags = cc_gfp_flags(&req->base);
+	u32 rem_cnt = *cc_hash_buf_cnt(state);
+
+	if (ctx->hw_mode == DRV_CIPHER_XCBC_MAC) {
+		key_size = CC_AES_128_BIT_KEY_SIZE;
+		key_len  = CC_AES_128_BIT_KEY_SIZE;
+	} else {
+		key_size = (ctx->key_params.keylen == 24) ? AES_MAX_KEY_SIZE :
+			ctx->key_params.keylen;
+		key_len =  ctx->key_params.keylen;
+	}
+
+	dev_dbg(dev, "===== final  xcbc reminder (%d) ====\n", rem_cnt);
+
+	if (cc_map_req(dev, state, ctx)) {
+		dev_err(dev, "map_ahash_source() failed\n");
+		return -EINVAL;
+	}
+
+	if (cc_map_hash_request_final(ctx->drvdata, state, req->src,
+				      req->nbytes, 0, flags)) {
+		dev_err(dev, "map_ahash_request_final() failed\n");
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+
+	if (cc_map_result(dev, state, digestsize)) {
+		dev_err(dev, "map_ahash_digest() failed\n");
+		cc_unmap_hash_request(dev, state, req->src, true);
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+
+	/* Setup request structure */
+	cc_req.user_cb = (void *)cc_hash_complete;
+	cc_req.user_arg = (void *)req;
+
+	if (state->xcbc_count && rem_cnt == 0) {
+		/* Load key for ECB decryption */
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], DRV_CIPHER_ECB);
+		set_cipher_config0(&desc[idx], DRV_CRYPTO_DIRECTION_DECRYPT);
+		set_din_type(&desc[idx], DMA_DLLI,
+			     (ctx->opad_tmp_keys_dma_addr + XCBC_MAC_K1_OFFSET),
+			     key_size, NS_BIT);
+		set_key_size_aes(&desc[idx], key_len);
+		set_flow_mode(&desc[idx], S_DIN_to_AES);
+		set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+		idx++;
+
+		/* Initiate decryption of block state to previous
+		 * block_state-XOR-M[n]
+		 */
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_DLLI, state->digest_buff_dma_addr,
+			     CC_AES_BLOCK_SIZE, NS_BIT);
+		set_dout_dlli(&desc[idx], state->digest_buff_dma_addr,
+			      CC_AES_BLOCK_SIZE, NS_BIT, 0);
+		set_flow_mode(&desc[idx], DIN_AES_DOUT);
+		idx++;
+
+		/* Memory Barrier: wait for axi write to complete */
+		hw_desc_init(&desc[idx]);
+		set_din_no_dma(&desc[idx], 0, 0xfffff0);
+		set_dout_no_dma(&desc[idx], 0, 0, 1);
+		idx++;
+	}
+
+	if (ctx->hw_mode == DRV_CIPHER_XCBC_MAC)
+		cc_setup_xcbc(req, desc, &idx);
+	else
+		cc_setup_cmac(req, desc, &idx);
+
+	if (state->xcbc_count == 0) {
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], ctx->hw_mode);
+		set_key_size_aes(&desc[idx], key_len);
+		set_cmac_size0_mode(&desc[idx]);
+		set_flow_mode(&desc[idx], S_DIN_to_AES);
+		idx++;
+	} else if (rem_cnt > 0) {
+		cc_set_desc(state, ctx, DIN_AES_DOUT, desc, false, &idx);
+	} else {
+		hw_desc_init(&desc[idx]);
+		set_din_const(&desc[idx], 0x00, CC_AES_BLOCK_SIZE);
+		set_flow_mode(&desc[idx], DIN_AES_DOUT);
+		idx++;
+	}
+
+	/* Get final MAC result */
+	hw_desc_init(&desc[idx]);
+	/* TODO */
+	set_dout_dlli(&desc[idx], state->digest_result_dma_addr,
+		      digestsize, NS_BIT, 1);
+	set_queue_last_ind(ctx->drvdata, &desc[idx]);
+	set_flow_mode(&desc[idx], S_AES_to_DOUT);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	idx++;
+
+	rc = cc_send_request(ctx->drvdata, &cc_req, desc, idx, &req->base);
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+		cc_unmap_hash_request(dev, state, req->src, true);
+		cc_unmap_result(dev, state, digestsize, req->result);
+		cc_unmap_req(dev, state, ctx);
+	}
+	return rc;
+}
+
+static int cc_mac_finup(struct ahash_request *req)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	struct cc_crypto_req cc_req = {};
+	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
+	int idx = 0;
+	int rc = 0;
+	u32 key_len = 0;
+	u32 digestsize = crypto_ahash_digestsize(tfm);
+	gfp_t flags = cc_gfp_flags(&req->base);
+
+	dev_dbg(dev, "===== finup xcbc(%d) ====\n", req->nbytes);
+	if (state->xcbc_count > 0 && req->nbytes == 0) {
+		dev_dbg(dev, "No data to update. Call to fdx_mac_final\n");
+		return cc_mac_final(req);
+	}
+
+	if (cc_map_req(dev, state, ctx)) {
+		dev_err(dev, "map_ahash_source() failed\n");
+		return -EINVAL;
+	}
+
+	if (cc_map_hash_request_final(ctx->drvdata, state, req->src,
+				      req->nbytes, 1, flags)) {
+		dev_err(dev, "map_ahash_request_final() failed\n");
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+	if (cc_map_result(dev, state, digestsize)) {
+		dev_err(dev, "map_ahash_digest() failed\n");
+		cc_unmap_hash_request(dev, state, req->src, true);
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+
+	/* Setup request structure */
+	cc_req.user_cb = (void *)cc_hash_complete;
+	cc_req.user_arg = (void *)req;
+
+	if (ctx->hw_mode == DRV_CIPHER_XCBC_MAC) {
+		key_len = CC_AES_128_BIT_KEY_SIZE;
+		cc_setup_xcbc(req, desc, &idx);
+	} else {
+		key_len = ctx->key_params.keylen;
+		cc_setup_cmac(req, desc, &idx);
+	}
+
+	if (req->nbytes == 0) {
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], ctx->hw_mode);
+		set_key_size_aes(&desc[idx], key_len);
+		set_cmac_size0_mode(&desc[idx]);
+		set_flow_mode(&desc[idx], S_DIN_to_AES);
+		idx++;
+	} else {
+		cc_set_desc(state, ctx, DIN_AES_DOUT, desc, false, &idx);
+	}
+
+	/* Get final MAC result */
+	hw_desc_init(&desc[idx]);
+	/* TODO */
+	set_dout_dlli(&desc[idx], state->digest_result_dma_addr,
+		      digestsize, NS_BIT, 1);
+	set_queue_last_ind(ctx->drvdata, &desc[idx]);
+	set_flow_mode(&desc[idx], S_AES_to_DOUT);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	idx++;
+
+	rc = cc_send_request(ctx->drvdata, &cc_req, desc, idx, &req->base);
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+		cc_unmap_hash_request(dev, state, req->src, true);
+		cc_unmap_result(dev, state, digestsize, req->result);
+		cc_unmap_req(dev, state, ctx);
+	}
+	return rc;
+}
+
+static int cc_mac_digest(struct ahash_request *req)
+{
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	u32 digestsize = crypto_ahash_digestsize(tfm);
+	struct cc_crypto_req cc_req = {};
+	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
+	u32 key_len;
+	unsigned int idx = 0;
+	int rc;
+	gfp_t flags = cc_gfp_flags(&req->base);
+
+	dev_dbg(dev, "===== -digest mac (%d) ====\n",  req->nbytes);
+
+	cc_init_req(dev, state, ctx);
+
+	if (cc_map_req(dev, state, ctx)) {
+		dev_err(dev, "map_ahash_source() failed\n");
+		return -ENOMEM;
+	}
+	if (cc_map_result(dev, state, digestsize)) {
+		dev_err(dev, "map_ahash_digest() failed\n");
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+
+	if (cc_map_hash_request_final(ctx->drvdata, state, req->src,
+				      req->nbytes, 1, flags)) {
+		dev_err(dev, "map_ahash_request_final() failed\n");
+		cc_unmap_req(dev, state, ctx);
+		return -ENOMEM;
+	}
+
+	/* Setup request structure */
+	cc_req.user_cb = (void *)cc_digest_complete;
+	cc_req.user_arg = (void *)req;
+
+	if (ctx->hw_mode == DRV_CIPHER_XCBC_MAC) {
+		key_len = CC_AES_128_BIT_KEY_SIZE;
+		cc_setup_xcbc(req, desc, &idx);
+	} else {
+		key_len = ctx->key_params.keylen;
+		cc_setup_cmac(req, desc, &idx);
+	}
+
+	if (req->nbytes == 0) {
+		hw_desc_init(&desc[idx]);
+		set_cipher_mode(&desc[idx], ctx->hw_mode);
+		set_key_size_aes(&desc[idx], key_len);
+		set_cmac_size0_mode(&desc[idx]);
+		set_flow_mode(&desc[idx], S_DIN_to_AES);
+		idx++;
+	} else {
+		cc_set_desc(state, ctx, DIN_AES_DOUT, desc, false, &idx);
+	}
+
+	/* Get final MAC result */
+	hw_desc_init(&desc[idx]);
+	set_dout_dlli(&desc[idx], state->digest_result_dma_addr,
+		      CC_AES_BLOCK_SIZE, NS_BIT, 1);
+	set_queue_last_ind(ctx->drvdata, &desc[idx]);
+	set_flow_mode(&desc[idx], S_AES_to_DOUT);
+	set_setup_mode(&desc[idx], SETUP_WRITE_STATE0);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_cipher_mode(&desc[idx], ctx->hw_mode);
+	idx++;
+
+	rc = cc_send_request(ctx->drvdata, &cc_req, desc, idx, &req->base);
+	if (rc != -EINPROGRESS && rc != -EBUSY) {
+		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
+		cc_unmap_hash_request(dev, state, req->src, true);
+		cc_unmap_result(dev, state, digestsize, req->result);
+		cc_unmap_req(dev, state, ctx);
+	}
+	return rc;
+}
+
+static int cc_hash_export(struct ahash_request *req, void *out)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	u8 *curr_buff = cc_hash_buf(state);
+	u32 curr_buff_cnt = *cc_hash_buf_cnt(state);
+	const u32 tmp = CC_EXPORT_MAGIC;
+
+	memcpy(out, &tmp, sizeof(u32));
+	out += sizeof(u32);
+
+	memcpy(out, state->digest_buff, ctx->inter_digestsize);
+	out += ctx->inter_digestsize;
+
+	memcpy(out, state->digest_bytes_len, ctx->drvdata->hash_len_sz);
+	out += ctx->drvdata->hash_len_sz;
+
+	memcpy(out, &curr_buff_cnt, sizeof(u32));
+	out += sizeof(u32);
+
+	memcpy(out, curr_buff, curr_buff_cnt);
+
+	return 0;
+}
+
+static int cc_hash_import(struct ahash_request *req, const void *in)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	struct ahash_req_ctx *state = ahash_request_ctx(req);
+	u32 tmp;
+
+	memcpy(&tmp, in, sizeof(u32));
+	if (tmp != CC_EXPORT_MAGIC)
+		return -EINVAL;
+	in += sizeof(u32);
+
+	cc_init_req(dev, state, ctx);
+
+	memcpy(state->digest_buff, in, ctx->inter_digestsize);
+	in += ctx->inter_digestsize;
+
+	memcpy(state->digest_bytes_len, in, ctx->drvdata->hash_len_sz);
+	in += ctx->drvdata->hash_len_sz;
+
+	/* Sanity check the data as much as possible */
+	memcpy(&tmp, in, sizeof(u32));
+	if (tmp > CC_MAX_HASH_BLCK_SIZE)
+		return -EINVAL;
+	in += sizeof(u32);
+
+	state->buf_cnt[0] = tmp;
+	memcpy(state->buffers[0], in, tmp);
+
+	return 0;
+}
+
+struct cc_hash_template {
+	char name[CRYPTO_MAX_ALG_NAME];
+	char driver_name[CRYPTO_MAX_ALG_NAME];
+	char mac_name[CRYPTO_MAX_ALG_NAME];
+	char mac_driver_name[CRYPTO_MAX_ALG_NAME];
+	unsigned int blocksize;
+	bool synchronize;
+	struct ahash_alg template_ahash;
+	int hash_mode;
+	int hw_mode;
+	int inter_digestsize;
+	struct cc_drvdata *drvdata;
+	u32 min_hw_rev;
+};
+
+#define CC_STATE_SIZE(_x) \
+	((_x) + HASH_MAX_LEN_SIZE + CC_MAX_HASH_BLCK_SIZE + (2 * sizeof(u32)))
+
+/* hash descriptors */
+static struct cc_hash_template driver_hash[] = {
+	//Asynchronize hash template
+	{
+		.name = "sha1",
+		.driver_name = "sha1-ccree",
+		.mac_name = "hmac(sha1)",
+		.mac_driver_name = "hmac-sha1-ccree",
+		.blocksize = SHA1_BLOCK_SIZE,
+		.synchronize = false,
+		.template_ahash = {
+			.init = cc_hash_init,
+			.update = cc_hash_update,
+			.final = cc_hash_final,
+			.finup = cc_hash_finup,
+			.digest = cc_hash_digest,
+			.export = cc_hash_export,
+			.import = cc_hash_import,
+			.setkey = cc_hash_setkey,
+			.halg = {
+				.digestsize = SHA1_DIGEST_SIZE,
+				.statesize = CC_STATE_SIZE(SHA1_DIGEST_SIZE),
+			},
+		},
+		.hash_mode = DRV_HASH_SHA1,
+		.hw_mode = DRV_HASH_HW_SHA1,
+		.inter_digestsize = SHA1_DIGEST_SIZE,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "sha256",
+		.driver_name = "sha256-ccree",
+		.mac_name = "hmac(sha256)",
+		.mac_driver_name = "hmac-sha256-ccree",
+		.blocksize = SHA256_BLOCK_SIZE,
+		.template_ahash = {
+			.init = cc_hash_init,
+			.update = cc_hash_update,
+			.final = cc_hash_final,
+			.finup = cc_hash_finup,
+			.digest = cc_hash_digest,
+			.export = cc_hash_export,
+			.import = cc_hash_import,
+			.setkey = cc_hash_setkey,
+			.halg = {
+				.digestsize = SHA256_DIGEST_SIZE,
+				.statesize = CC_STATE_SIZE(SHA256_DIGEST_SIZE)
+			},
+		},
+		.hash_mode = DRV_HASH_SHA256,
+		.hw_mode = DRV_HASH_HW_SHA256,
+		.inter_digestsize = SHA256_DIGEST_SIZE,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "sha224",
+		.driver_name = "sha224-ccree",
+		.mac_name = "hmac(sha224)",
+		.mac_driver_name = "hmac-sha224-ccree",
+		.blocksize = SHA224_BLOCK_SIZE,
+		.template_ahash = {
+			.init = cc_hash_init,
+			.update = cc_hash_update,
+			.final = cc_hash_final,
+			.finup = cc_hash_finup,
+			.digest = cc_hash_digest,
+			.export = cc_hash_export,
+			.import = cc_hash_import,
+			.setkey = cc_hash_setkey,
+			.halg = {
+				.digestsize = SHA224_DIGEST_SIZE,
+				.statesize = CC_STATE_SIZE(SHA224_DIGEST_SIZE),
+			},
+		},
+		.hash_mode = DRV_HASH_SHA224,
+		.hw_mode = DRV_HASH_HW_SHA256,
+		.inter_digestsize = SHA256_DIGEST_SIZE,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.name = "sha384",
+		.driver_name = "sha384-ccree",
+		.mac_name = "hmac(sha384)",
+		.mac_driver_name = "hmac-sha384-ccree",
+		.blocksize = SHA384_BLOCK_SIZE,
+		.template_ahash = {
+			.init = cc_hash_init,
+			.update = cc_hash_update,
+			.final = cc_hash_final,
+			.finup = cc_hash_finup,
+			.digest = cc_hash_digest,
+			.export = cc_hash_export,
+			.import = cc_hash_import,
+			.setkey = cc_hash_setkey,
+			.halg = {
+				.digestsize = SHA384_DIGEST_SIZE,
+				.statesize = CC_STATE_SIZE(SHA384_DIGEST_SIZE),
+			},
+		},
+		.hash_mode = DRV_HASH_SHA384,
+		.hw_mode = DRV_HASH_HW_SHA512,
+		.inter_digestsize = SHA512_DIGEST_SIZE,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "sha512",
+		.driver_name = "sha512-ccree",
+		.mac_name = "hmac(sha512)",
+		.mac_driver_name = "hmac-sha512-ccree",
+		.blocksize = SHA512_BLOCK_SIZE,
+		.template_ahash = {
+			.init = cc_hash_init,
+			.update = cc_hash_update,
+			.final = cc_hash_final,
+			.finup = cc_hash_finup,
+			.digest = cc_hash_digest,
+			.export = cc_hash_export,
+			.import = cc_hash_import,
+			.setkey = cc_hash_setkey,
+			.halg = {
+				.digestsize = SHA512_DIGEST_SIZE,
+				.statesize = CC_STATE_SIZE(SHA512_DIGEST_SIZE),
+			},
+		},
+		.hash_mode = DRV_HASH_SHA512,
+		.hw_mode = DRV_HASH_HW_SHA512,
+		.inter_digestsize = SHA512_DIGEST_SIZE,
+		.min_hw_rev = CC_HW_REV_712,
+	},
+	{
+		.name = "md5",
+		.driver_name = "md5-ccree",
+		.mac_name = "hmac(md5)",
+		.mac_driver_name = "hmac-md5-ccree",
+		.blocksize = MD5_HMAC_BLOCK_SIZE,
+		.template_ahash = {
+			.init = cc_hash_init,
+			.update = cc_hash_update,
+			.final = cc_hash_final,
+			.finup = cc_hash_finup,
+			.digest = cc_hash_digest,
+			.export = cc_hash_export,
+			.import = cc_hash_import,
+			.setkey = cc_hash_setkey,
+			.halg = {
+				.digestsize = MD5_DIGEST_SIZE,
+				.statesize = CC_STATE_SIZE(MD5_DIGEST_SIZE),
+			},
+		},
+		.hash_mode = DRV_HASH_MD5,
+		.hw_mode = DRV_HASH_HW_MD5,
+		.inter_digestsize = MD5_DIGEST_SIZE,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.mac_name = "xcbc(aes)",
+		.mac_driver_name = "xcbc-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_ahash = {
+			.init = cc_hash_init,
+			.update = cc_mac_update,
+			.final = cc_mac_final,
+			.finup = cc_mac_finup,
+			.digest = cc_mac_digest,
+			.setkey = cc_xcbc_setkey,
+			.export = cc_hash_export,
+			.import = cc_hash_import,
+			.halg = {
+				.digestsize = AES_BLOCK_SIZE,
+				.statesize = CC_STATE_SIZE(AES_BLOCK_SIZE),
+			},
+		},
+		.hash_mode = DRV_HASH_NULL,
+		.hw_mode = DRV_CIPHER_XCBC_MAC,
+		.inter_digestsize = AES_BLOCK_SIZE,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+	{
+		.mac_name = "cmac(aes)",
+		.mac_driver_name = "cmac-aes-ccree",
+		.blocksize = AES_BLOCK_SIZE,
+		.template_ahash = {
+			.init = cc_hash_init,
+			.update = cc_mac_update,
+			.final = cc_mac_final,
+			.finup = cc_mac_finup,
+			.digest = cc_mac_digest,
+			.setkey = cc_cmac_setkey,
+			.export = cc_hash_export,
+			.import = cc_hash_import,
+			.halg = {
+				.digestsize = AES_BLOCK_SIZE,
+				.statesize = CC_STATE_SIZE(AES_BLOCK_SIZE),
+			},
+		},
+		.hash_mode = DRV_HASH_NULL,
+		.hw_mode = DRV_CIPHER_CMAC,
+		.inter_digestsize = AES_BLOCK_SIZE,
+		.min_hw_rev = CC_HW_REV_630,
+	},
+};
+
+static struct cc_hash_alg *cc_alloc_hash_alg(struct cc_hash_template *template,
+					     struct device *dev, bool keyed)
+{
+	struct cc_hash_alg *t_crypto_alg;
+	struct crypto_alg *alg;
+	struct ahash_alg *halg;
+
+	t_crypto_alg = kzalloc(sizeof(*t_crypto_alg), GFP_KERNEL);
+	if (!t_crypto_alg)
+		return ERR_PTR(-ENOMEM);
+
+	t_crypto_alg->ahash_alg = template->template_ahash;
+	halg = &t_crypto_alg->ahash_alg;
+	alg = &halg->halg.base;
+
+	if (keyed) {
+		snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s",
+			 template->mac_name);
+		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+			 template->mac_driver_name);
+	} else {
+		halg->setkey = NULL;
+		snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s",
+			 template->name);
+		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+			 template->driver_name);
+	}
+	alg->cra_module = THIS_MODULE;
+	alg->cra_ctxsize = sizeof(struct cc_hash_ctx);
+	alg->cra_priority = CC_CRA_PRIO;
+	alg->cra_blocksize = template->blocksize;
+	alg->cra_alignmask = 0;
+	alg->cra_exit = cc_cra_exit;
+
+	alg->cra_init = cc_cra_init;
+	alg->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_TYPE_AHASH |
+			CRYPTO_ALG_KERN_DRIVER_ONLY;
+	alg->cra_type = &crypto_ahash_type;
+
+	t_crypto_alg->hash_mode = template->hash_mode;
+	t_crypto_alg->hw_mode = template->hw_mode;
+	t_crypto_alg->inter_digestsize = template->inter_digestsize;
+
+	return t_crypto_alg;
+}
+
+int cc_init_hash_sram(struct cc_drvdata *drvdata)
+{
+	struct cc_hash_handle *hash_handle = drvdata->hash_handle;
+	cc_sram_addr_t sram_buff_ofs = hash_handle->digest_len_sram_addr;
+	unsigned int larval_seq_len = 0;
+	struct cc_hw_desc larval_seq[CC_DIGEST_SIZE_MAX / sizeof(u32)];
+	bool large_sha_supported = (drvdata->hw_rev >= CC_HW_REV_712);
+	int rc = 0;
+
+	/* Copy-to-sram digest-len */
+	cc_set_sram_desc(digest_len_init, sram_buff_ofs,
+			 ARRAY_SIZE(digest_len_init), larval_seq,
+			 &larval_seq_len);
+	rc = send_request_init(drvdata, larval_seq, larval_seq_len);
+	if (rc)
+		goto init_digest_const_err;
+
+	sram_buff_ofs += sizeof(digest_len_init);
+	larval_seq_len = 0;
+
+	if (large_sha_supported) {
+		/* Copy-to-sram digest-len for sha384/512 */
+		cc_set_sram_desc(digest_len_sha512_init, sram_buff_ofs,
+				 ARRAY_SIZE(digest_len_sha512_init),
+				 larval_seq, &larval_seq_len);
+		rc = send_request_init(drvdata, larval_seq, larval_seq_len);
+		if (rc)
+			goto init_digest_const_err;
+
+		sram_buff_ofs += sizeof(digest_len_sha512_init);
+		larval_seq_len = 0;
+	}
+
+	/* The initial digests offset */
+	hash_handle->larval_digest_sram_addr = sram_buff_ofs;
+
+	/* Copy-to-sram initial SHA* digests */
+	cc_set_sram_desc(md5_init, sram_buff_ofs, ARRAY_SIZE(md5_init),
+			 larval_seq, &larval_seq_len);
+	rc = send_request_init(drvdata, larval_seq, larval_seq_len);
+	if (rc)
+		goto init_digest_const_err;
+	sram_buff_ofs += sizeof(md5_init);
+	larval_seq_len = 0;
+
+	cc_set_sram_desc(sha1_init, sram_buff_ofs,
+			 ARRAY_SIZE(sha1_init), larval_seq,
+			 &larval_seq_len);
+	rc = send_request_init(drvdata, larval_seq, larval_seq_len);
+	if (rc)
+		goto init_digest_const_err;
+	sram_buff_ofs += sizeof(sha1_init);
+	larval_seq_len = 0;
+
+	cc_set_sram_desc(sha224_init, sram_buff_ofs,
+			 ARRAY_SIZE(sha224_init), larval_seq,
+			 &larval_seq_len);
+	rc = send_request_init(drvdata, larval_seq, larval_seq_len);
+	if (rc)
+		goto init_digest_const_err;
+	sram_buff_ofs += sizeof(sha224_init);
+	larval_seq_len = 0;
+
+	cc_set_sram_desc(sha256_init, sram_buff_ofs,
+			 ARRAY_SIZE(sha256_init), larval_seq,
+			 &larval_seq_len);
+	rc = send_request_init(drvdata, larval_seq, larval_seq_len);
+	if (rc)
+		goto init_digest_const_err;
+	sram_buff_ofs += sizeof(sha256_init);
+	larval_seq_len = 0;
+
+	if (large_sha_supported) {
+		cc_set_sram_desc((u32 *)sha384_init, sram_buff_ofs,
+				 (ARRAY_SIZE(sha384_init) * 2), larval_seq,
+				 &larval_seq_len);
+		rc = send_request_init(drvdata, larval_seq, larval_seq_len);
+		if (rc)
+			goto init_digest_const_err;
+		sram_buff_ofs += sizeof(sha384_init);
+		larval_seq_len = 0;
+
+		cc_set_sram_desc((u32 *)sha512_init, sram_buff_ofs,
+				 (ARRAY_SIZE(sha512_init) * 2), larval_seq,
+				 &larval_seq_len);
+		rc = send_request_init(drvdata, larval_seq, larval_seq_len);
+		if (rc)
+			goto init_digest_const_err;
+	}
+
+init_digest_const_err:
+	return rc;
+}
+
+static void __init cc_swap_dwords(u32 *buf, unsigned long size)
+{
+	int i;
+	u32 tmp;
+
+	for (i = 0; i < size; i += 2) {
+		tmp = buf[i];
+		buf[i] = buf[i + 1];
+		buf[i + 1] = tmp;
+	}
+}
+
+/*
+ * Due to the way the HW works we need to swap every
+ * double word in the SHA384 and SHA512 larval hashes
+ */
+void __init cc_hash_global_init(void)
+{
+	cc_swap_dwords((u32 *)&sha384_init, (ARRAY_SIZE(sha384_init) * 2));
+	cc_swap_dwords((u32 *)&sha512_init, (ARRAY_SIZE(sha512_init) * 2));
+}
+
+int cc_hash_alloc(struct cc_drvdata *drvdata)
+{
+	struct cc_hash_handle *hash_handle;
+	cc_sram_addr_t sram_buff;
+	u32 sram_size_to_alloc;
+	struct device *dev = drvdata_to_dev(drvdata);
+	int rc = 0;
+	int alg;
+
+	hash_handle = kzalloc(sizeof(*hash_handle), GFP_KERNEL);
+	if (!hash_handle)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&hash_handle->hash_list);
+	drvdata->hash_handle = hash_handle;
+
+	sram_size_to_alloc = sizeof(digest_len_init) +
+			sizeof(md5_init) +
+			sizeof(sha1_init) +
+			sizeof(sha224_init) +
+			sizeof(sha256_init);
+
+	if (drvdata->hw_rev >= CC_HW_REV_712)
+		sram_size_to_alloc += sizeof(digest_len_sha512_init) +
+			sizeof(sha384_init) + sizeof(sha512_init);
+
+	sram_buff = cc_sram_alloc(drvdata, sram_size_to_alloc);
+	if (sram_buff == NULL_SRAM_ADDR) {
+		dev_err(dev, "SRAM pool exhausted\n");
+		rc = -ENOMEM;
+		goto fail;
+	}
+
+	/* The initial digest-len offset */
+	hash_handle->digest_len_sram_addr = sram_buff;
+
+	/*must be set before the alg registration as it is being used there*/
+	rc = cc_init_hash_sram(drvdata);
+	if (rc) {
+		dev_err(dev, "Init digest CONST failed (rc=%d)\n", rc);
+		goto fail;
+	}
+
+	/* ahash registration */
+	for (alg = 0; alg < ARRAY_SIZE(driver_hash); alg++) {
+		struct cc_hash_alg *t_alg;
+		int hw_mode = driver_hash[alg].hw_mode;
+
+		/* We either support both HASH and MAC or none */
+		if (driver_hash[alg].min_hw_rev > drvdata->hw_rev)
+			continue;
+
+		/* register hmac version */
+		t_alg = cc_alloc_hash_alg(&driver_hash[alg], dev, true);
+		if (IS_ERR(t_alg)) {
+			rc = PTR_ERR(t_alg);
+			dev_err(dev, "%s alg allocation failed\n",
+				driver_hash[alg].driver_name);
+			goto fail;
+		}
+		t_alg->drvdata = drvdata;
+
+		rc = crypto_register_ahash(&t_alg->ahash_alg);
+		if (rc) {
+			dev_err(dev, "%s alg registration failed\n",
+				driver_hash[alg].driver_name);
+			kfree(t_alg);
+			goto fail;
+		} else {
+			list_add_tail(&t_alg->entry, &hash_handle->hash_list);
+		}
+
+		if (hw_mode == DRV_CIPHER_XCBC_MAC ||
+		    hw_mode == DRV_CIPHER_CMAC)
+			continue;
+
+		/* register hash version */
+		t_alg = cc_alloc_hash_alg(&driver_hash[alg], dev, false);
+		if (IS_ERR(t_alg)) {
+			rc = PTR_ERR(t_alg);
+			dev_err(dev, "%s alg allocation failed\n",
+				driver_hash[alg].driver_name);
+			goto fail;
+		}
+		t_alg->drvdata = drvdata;
+
+		rc = crypto_register_ahash(&t_alg->ahash_alg);
+		if (rc) {
+			dev_err(dev, "%s alg registration failed\n",
+				driver_hash[alg].driver_name);
+			kfree(t_alg);
+			goto fail;
+		} else {
+			list_add_tail(&t_alg->entry, &hash_handle->hash_list);
+		}
+	}
+
+	return 0;
+
+fail:
+	kfree(drvdata->hash_handle);
+	drvdata->hash_handle = NULL;
+	return rc;
+}
+
+int cc_hash_free(struct cc_drvdata *drvdata)
+{
+	struct cc_hash_alg *t_hash_alg, *hash_n;
+	struct cc_hash_handle *hash_handle = drvdata->hash_handle;
+
+	if (hash_handle) {
+		list_for_each_entry_safe(t_hash_alg, hash_n,
+					 &hash_handle->hash_list, entry) {
+			crypto_unregister_ahash(&t_hash_alg->ahash_alg);
+			list_del(&t_hash_alg->entry);
+			kfree(t_hash_alg);
+		}
+
+		kfree(hash_handle);
+		drvdata->hash_handle = NULL;
+	}
+	return 0;
+}
+
+static void cc_setup_xcbc(struct ahash_request *areq, struct cc_hw_desc desc[],
+			  unsigned int *seq_size)
+{
+	unsigned int idx = *seq_size;
+	struct ahash_req_ctx *state = ahash_request_ctx(areq);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	/* Setup XCBC MAC K1 */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI, (ctx->opad_tmp_keys_dma_addr +
+					    XCBC_MAC_K1_OFFSET),
+		     CC_AES_128_BIT_KEY_SIZE, NS_BIT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_XCBC_MAC);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_key_size_aes(&desc[idx], CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+
+	/* Setup XCBC MAC K2 */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI,
+		     (ctx->opad_tmp_keys_dma_addr + XCBC_MAC_K2_OFFSET),
+		     CC_AES_128_BIT_KEY_SIZE, NS_BIT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE1);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_XCBC_MAC);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_key_size_aes(&desc[idx], CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+
+	/* Setup XCBC MAC K3 */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI,
+		     (ctx->opad_tmp_keys_dma_addr + XCBC_MAC_K3_OFFSET),
+		     CC_AES_128_BIT_KEY_SIZE, NS_BIT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE2);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_XCBC_MAC);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_key_size_aes(&desc[idx], CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+
+	/* Loading MAC state */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI, state->digest_buff_dma_addr,
+		     CC_AES_BLOCK_SIZE, NS_BIT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_XCBC_MAC);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_key_size_aes(&desc[idx], CC_AES_128_BIT_KEY_SIZE);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+	*seq_size = idx;
+}
+
+static void cc_setup_cmac(struct ahash_request *areq, struct cc_hw_desc desc[],
+			  unsigned int *seq_size)
+{
+	unsigned int idx = *seq_size;
+	struct ahash_req_ctx *state = ahash_request_ctx(areq);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	/* Setup CMAC Key */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI, ctx->opad_tmp_keys_dma_addr,
+		     ((ctx->key_params.keylen == 24) ? AES_MAX_KEY_SIZE :
+		      ctx->key_params.keylen), NS_BIT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_KEY0);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_CMAC);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_key_size_aes(&desc[idx], ctx->key_params.keylen);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+
+	/* Load MAC state */
+	hw_desc_init(&desc[idx]);
+	set_din_type(&desc[idx], DMA_DLLI, state->digest_buff_dma_addr,
+		     CC_AES_BLOCK_SIZE, NS_BIT);
+	set_setup_mode(&desc[idx], SETUP_LOAD_STATE0);
+	set_cipher_mode(&desc[idx], DRV_CIPHER_CMAC);
+	set_cipher_config0(&desc[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_key_size_aes(&desc[idx], ctx->key_params.keylen);
+	set_flow_mode(&desc[idx], S_DIN_to_AES);
+	idx++;
+	*seq_size = idx;
+}
+
+static void cc_set_desc(struct ahash_req_ctx *areq_ctx,
+			struct cc_hash_ctx *ctx, unsigned int flow_mode,
+			struct cc_hw_desc desc[], bool is_not_last_data,
+			unsigned int *seq_size)
+{
+	unsigned int idx = *seq_size;
+	struct device *dev = drvdata_to_dev(ctx->drvdata);
+
+	if (areq_ctx->data_dma_buf_type == CC_DMA_BUF_DLLI) {
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_DLLI,
+			     sg_dma_address(areq_ctx->curr_sg),
+			     areq_ctx->curr_sg->length, NS_BIT);
+		set_flow_mode(&desc[idx], flow_mode);
+		idx++;
+	} else {
+		if (areq_ctx->data_dma_buf_type == CC_DMA_BUF_NULL) {
+			dev_dbg(dev, " NULL mode\n");
+			/* nothing to build */
+			return;
+		}
+		/* bypass */
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_DLLI,
+			     areq_ctx->mlli_params.mlli_dma_addr,
+			     areq_ctx->mlli_params.mlli_len, NS_BIT);
+		set_dout_sram(&desc[idx], ctx->drvdata->mlli_sram_addr,
+			      areq_ctx->mlli_params.mlli_len);
+		set_flow_mode(&desc[idx], BYPASS);
+		idx++;
+		/* process */
+		hw_desc_init(&desc[idx]);
+		set_din_type(&desc[idx], DMA_MLLI,
+			     ctx->drvdata->mlli_sram_addr,
+			     areq_ctx->mlli_nents, NS_BIT);
+		set_flow_mode(&desc[idx], flow_mode);
+		idx++;
+	}
+	if (is_not_last_data)
+		set_din_not_last_indication(&desc[(idx - 1)]);
+	/* return updated desc sequence size */
+	*seq_size = idx;
+}
+
+static const void *cc_larval_digest(struct device *dev, u32 mode)
+{
+	switch (mode) {
+	case DRV_HASH_MD5:
+		return md5_init;
+	case DRV_HASH_SHA1:
+		return sha1_init;
+	case DRV_HASH_SHA224:
+		return sha224_init;
+	case DRV_HASH_SHA256:
+		return sha256_init;
+	case DRV_HASH_SHA384:
+		return sha384_init;
+	case DRV_HASH_SHA512:
+		return sha512_init;
+	default:
+		dev_err(dev, "Invalid hash mode (%d)\n", mode);
+		return md5_init;
+	}
+}
+
+/*!
+ * Gets the address of the initial digest in SRAM
+ * according to the given hash mode
+ *
+ * \param drvdata
+ * \param mode The Hash mode. Supported modes: MD5/SHA1/SHA224/SHA256
+ *
+ * \return u32 The address of the initial digest in SRAM
+ */
+cc_sram_addr_t cc_larval_digest_addr(void *drvdata, u32 mode)
+{
+	struct cc_drvdata *_drvdata = (struct cc_drvdata *)drvdata;
+	struct cc_hash_handle *hash_handle = _drvdata->hash_handle;
+	struct device *dev = drvdata_to_dev(_drvdata);
+
+	switch (mode) {
+	case DRV_HASH_NULL:
+		break; /*Ignore*/
+	case DRV_HASH_MD5:
+		return (hash_handle->larval_digest_sram_addr);
+	case DRV_HASH_SHA1:
+		return (hash_handle->larval_digest_sram_addr +
+			sizeof(md5_init));
+	case DRV_HASH_SHA224:
+		return (hash_handle->larval_digest_sram_addr +
+			sizeof(md5_init) +
+			sizeof(sha1_init));
+	case DRV_HASH_SHA256:
+		return (hash_handle->larval_digest_sram_addr +
+			sizeof(md5_init) +
+			sizeof(sha1_init) +
+			sizeof(sha224_init));
+	case DRV_HASH_SHA384:
+		return (hash_handle->larval_digest_sram_addr +
+			sizeof(md5_init) +
+			sizeof(sha1_init) +
+			sizeof(sha224_init) +
+			sizeof(sha256_init));
+	case DRV_HASH_SHA512:
+		return (hash_handle->larval_digest_sram_addr +
+			sizeof(md5_init) +
+			sizeof(sha1_init) +
+			sizeof(sha224_init) +
+			sizeof(sha256_init) +
+			sizeof(sha384_init));
+	default:
+		dev_err(dev, "Invalid hash mode (%d)\n", mode);
+	}
+
+	/*This is valid wrong value to avoid kernel crash*/
+	return hash_handle->larval_digest_sram_addr;
+}
+
+cc_sram_addr_t
+cc_digest_len_addr(void *drvdata, u32 mode)
+{
+	struct cc_drvdata *_drvdata = (struct cc_drvdata *)drvdata;
+	struct cc_hash_handle *hash_handle = _drvdata->hash_handle;
+	cc_sram_addr_t digest_len_addr = hash_handle->digest_len_sram_addr;
+
+	switch (mode) {
+	case DRV_HASH_SHA1:
+	case DRV_HASH_SHA224:
+	case DRV_HASH_SHA256:
+	case DRV_HASH_MD5:
+		return digest_len_addr;
+#if (CC_DEV_SHA_MAX > 256)
+	case DRV_HASH_SHA384:
+	case DRV_HASH_SHA512:
+		return  digest_len_addr + sizeof(digest_len_init);
+#endif
+	default:
+		return digest_len_addr; /*to avoid kernel crash*/
+	}
+}
diff --git a/drivers/crypto/ccree/cc_hash.h b/drivers/crypto/ccree/cc_hash.h
new file mode 100644
index 000000000000..2e5bf8b0bbb6
--- /dev/null
+++ b/drivers/crypto/ccree/cc_hash.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+/* \file cc_hash.h
+ * ARM CryptoCell Hash Crypto API
+ */
+
+#ifndef __CC_HASH_H__
+#define __CC_HASH_H__
+
+#include "cc_buffer_mgr.h"
+
+#define HMAC_IPAD_CONST	0x36363636
+#define HMAC_OPAD_CONST	0x5C5C5C5C
+#define HASH_LEN_SIZE_712 16
+#define HASH_LEN_SIZE_630 8
+#define HASH_MAX_LEN_SIZE HASH_LEN_SIZE_712
+#define CC_MAX_HASH_DIGEST_SIZE	SHA512_DIGEST_SIZE
+#define CC_MAX_HASH_BLCK_SIZE SHA512_BLOCK_SIZE
+
+#define XCBC_MAC_K1_OFFSET 0
+#define XCBC_MAC_K2_OFFSET 16
+#define XCBC_MAC_K3_OFFSET 32
+
+#define CC_EXPORT_MAGIC 0xC2EE1070U
+
+/* this struct was taken from drivers/crypto/nx/nx-aes-xcbc.c and it is used
+ * for xcbc/cmac statesize
+ */
+struct aeshash_state {
+	u8 state[AES_BLOCK_SIZE];
+	unsigned int count;
+	u8 buffer[AES_BLOCK_SIZE];
+};
+
+/* ahash state */
+struct ahash_req_ctx {
+	u8 buffers[2][CC_MAX_HASH_BLCK_SIZE] ____cacheline_aligned;
+	u8 digest_result_buff[CC_MAX_HASH_DIGEST_SIZE] ____cacheline_aligned;
+	u8 digest_buff[CC_MAX_HASH_DIGEST_SIZE] ____cacheline_aligned;
+	u8 opad_digest_buff[CC_MAX_HASH_DIGEST_SIZE] ____cacheline_aligned;
+	u8 digest_bytes_len[HASH_MAX_LEN_SIZE] ____cacheline_aligned;
+	struct async_gen_req_ctx gen_ctx ____cacheline_aligned;
+	enum cc_req_dma_buf_type data_dma_buf_type;
+	dma_addr_t opad_digest_dma_addr;
+	dma_addr_t digest_buff_dma_addr;
+	dma_addr_t digest_bytes_len_dma_addr;
+	dma_addr_t digest_result_dma_addr;
+	u32 buf_cnt[2];
+	u32 buff_index;
+	u32 xcbc_count; /* count xcbc update operatations */
+	struct scatterlist buff_sg[2];
+	struct scatterlist *curr_sg;
+	u32 in_nents;
+	u32 mlli_nents;
+	struct mlli_params mlli_params;
+};
+
+static inline u32 *cc_hash_buf_cnt(struct ahash_req_ctx *state)
+{
+	return &state->buf_cnt[state->buff_index];
+}
+
+static inline u8 *cc_hash_buf(struct ahash_req_ctx *state)
+{
+	return state->buffers[state->buff_index];
+}
+
+static inline u32 *cc_next_buf_cnt(struct ahash_req_ctx *state)
+{
+	return &state->buf_cnt[state->buff_index ^ 1];
+}
+
+static inline u8 *cc_next_buf(struct ahash_req_ctx *state)
+{
+	return state->buffers[state->buff_index ^ 1];
+}
+
+int cc_hash_alloc(struct cc_drvdata *drvdata);
+int cc_init_hash_sram(struct cc_drvdata *drvdata);
+int cc_hash_free(struct cc_drvdata *drvdata);
+
+/*!
+ * Gets the initial digest length
+ *
+ * \param drvdata
+ * \param mode The Hash mode. Supported modes:
+ *             MD5/SHA1/SHA224/SHA256/SHA384/SHA512
+ *
+ * \return u32 returns the address of the initial digest length in SRAM
+ */
+cc_sram_addr_t
+cc_digest_len_addr(void *drvdata, u32 mode);
+
+/*!
+ * Gets the address of the initial digest in SRAM
+ * according to the given hash mode
+ *
+ * \param drvdata
+ * \param mode The Hash mode. Supported modes:
+ *             MD5/SHA1/SHA224/SHA256/SHA384/SHA512
+ *
+ * \return u32 The address of the initial digest in SRAM
+ */
+cc_sram_addr_t cc_larval_digest_addr(void *drvdata, u32 mode);
+
+void cc_hash_global_init(void);
+
+#endif /*__CC_HASH_H__*/
diff --git a/drivers/crypto/ccree/cc_host_regs.h b/drivers/crypto/ccree/cc_host_regs.h
new file mode 100644
index 000000000000..f51001898ca1
--- /dev/null
+++ b/drivers/crypto/ccree/cc_host_regs.h
@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#ifndef __CC_HOST_H__
+#define __CC_HOST_H__
+
+// --------------------------------------
+// BLOCK: HOST_P
+// --------------------------------------
+#define CC_HOST_IRR_REG_OFFSET	0xA00UL
+#define CC_HOST_IRR_DSCRPTR_COMPLETION_LOW_INT_BIT_SHIFT	0x2UL
+#define CC_HOST_IRR_DSCRPTR_COMPLETION_LOW_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_AXI_ERR_INT_BIT_SHIFT	0x8UL
+#define CC_HOST_IRR_AXI_ERR_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_GPR0_BIT_SHIFT	0xBUL
+#define CC_HOST_IRR_GPR0_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_DSCRPTR_WATERMARK_INT_BIT_SHIFT	0x13UL
+#define CC_HOST_IRR_DSCRPTR_WATERMARK_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_AXIM_COMP_INT_BIT_SHIFT	0x17UL
+#define CC_HOST_IRR_AXIM_COMP_INT_BIT_SIZE	0x1UL
+#define CC_HOST_SEP_SRAM_THRESHOLD_REG_OFFSET	0xA10UL
+#define CC_HOST_SEP_SRAM_THRESHOLD_VALUE_BIT_SHIFT	0x0UL
+#define CC_HOST_SEP_SRAM_THRESHOLD_VALUE_BIT_SIZE	0xCUL
+#define CC_HOST_IMR_REG_OFFSET	0xA04UL
+#define CC_HOST_IMR_NOT_USED_MASK_BIT_SHIFT	0x1UL
+#define CC_HOST_IMR_NOT_USED_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_DSCRPTR_COMPLETION_MASK_BIT_SHIFT	0x2UL
+#define CC_HOST_IMR_DSCRPTR_COMPLETION_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_AXI_ERR_MASK_BIT_SHIFT	0x8UL
+#define CC_HOST_IMR_AXI_ERR_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_GPR0_BIT_SHIFT	0xBUL
+#define CC_HOST_IMR_GPR0_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_DSCRPTR_WATERMARK_MASK0_BIT_SHIFT	0x13UL
+#define CC_HOST_IMR_DSCRPTR_WATERMARK_MASK0_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_AXIM_COMP_INT_MASK_BIT_SHIFT	0x17UL
+#define CC_HOST_IMR_AXIM_COMP_INT_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_ICR_REG_OFFSET	0xA08UL
+#define CC_HOST_ICR_DSCRPTR_COMPLETION_BIT_SHIFT	0x2UL
+#define CC_HOST_ICR_DSCRPTR_COMPLETION_BIT_SIZE	0x1UL
+#define CC_HOST_ICR_AXI_ERR_CLEAR_BIT_SHIFT	0x8UL
+#define CC_HOST_ICR_AXI_ERR_CLEAR_BIT_SIZE	0x1UL
+#define CC_HOST_ICR_GPR_INT_CLEAR_BIT_SHIFT	0xBUL
+#define CC_HOST_ICR_GPR_INT_CLEAR_BIT_SIZE	0x1UL
+#define CC_HOST_ICR_DSCRPTR_WATERMARK_QUEUE0_CLEAR_BIT_SHIFT	0x13UL
+#define CC_HOST_ICR_DSCRPTR_WATERMARK_QUEUE0_CLEAR_BIT_SIZE	0x1UL
+#define CC_HOST_ICR_AXIM_COMP_INT_CLEAR_BIT_SHIFT	0x17UL
+#define CC_HOST_ICR_AXIM_COMP_INT_CLEAR_BIT_SIZE	0x1UL
+#define CC_HOST_SIGNATURE_REG_OFFSET	0xA24UL
+#define CC_HOST_SIGNATURE_VALUE_BIT_SHIFT	0x0UL
+#define CC_HOST_SIGNATURE_VALUE_BIT_SIZE	0x20UL
+#define CC_HOST_BOOT_REG_OFFSET	0xA28UL
+#define CC_HOST_BOOT_SYNTHESIS_CONFIG_BIT_SHIFT	0x0UL
+#define CC_HOST_BOOT_SYNTHESIS_CONFIG_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_LARGE_RKEK_LOCAL_BIT_SHIFT	0x1UL
+#define CC_HOST_BOOT_LARGE_RKEK_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_HASH_IN_FUSES_LOCAL_BIT_SHIFT	0x2UL
+#define CC_HOST_BOOT_HASH_IN_FUSES_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_EXT_MEM_SECURED_LOCAL_BIT_SHIFT	0x3UL
+#define CC_HOST_BOOT_EXT_MEM_SECURED_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_RKEK_ECC_EXISTS_LOCAL_N_BIT_SHIFT	0x5UL
+#define CC_HOST_BOOT_RKEK_ECC_EXISTS_LOCAL_N_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_SRAM_SIZE_LOCAL_BIT_SHIFT	0x6UL
+#define CC_HOST_BOOT_SRAM_SIZE_LOCAL_BIT_SIZE	0x3UL
+#define CC_HOST_BOOT_DSCRPTR_EXISTS_LOCAL_BIT_SHIFT	0x9UL
+#define CC_HOST_BOOT_DSCRPTR_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_PAU_EXISTS_LOCAL_BIT_SHIFT	0xAUL
+#define CC_HOST_BOOT_PAU_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_RNG_EXISTS_LOCAL_BIT_SHIFT	0xBUL
+#define CC_HOST_BOOT_RNG_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_PKA_EXISTS_LOCAL_BIT_SHIFT	0xCUL
+#define CC_HOST_BOOT_PKA_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_RC4_EXISTS_LOCAL_BIT_SHIFT	0xDUL
+#define CC_HOST_BOOT_RC4_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_SHA_512_PRSNT_LOCAL_BIT_SHIFT	0xEUL
+#define CC_HOST_BOOT_SHA_512_PRSNT_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_SHA_256_PRSNT_LOCAL_BIT_SHIFT	0xFUL
+#define CC_HOST_BOOT_SHA_256_PRSNT_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_MD5_PRSNT_LOCAL_BIT_SHIFT	0x10UL
+#define CC_HOST_BOOT_MD5_PRSNT_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_HASH_EXISTS_LOCAL_BIT_SHIFT	0x11UL
+#define CC_HOST_BOOT_HASH_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_C2_EXISTS_LOCAL_BIT_SHIFT	0x12UL
+#define CC_HOST_BOOT_C2_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_DES_EXISTS_LOCAL_BIT_SHIFT	0x13UL
+#define CC_HOST_BOOT_DES_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_AES_XCBC_MAC_EXISTS_LOCAL_BIT_SHIFT	0x14UL
+#define CC_HOST_BOOT_AES_XCBC_MAC_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_AES_CMAC_EXISTS_LOCAL_BIT_SHIFT	0x15UL
+#define CC_HOST_BOOT_AES_CMAC_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_AES_CCM_EXISTS_LOCAL_BIT_SHIFT	0x16UL
+#define CC_HOST_BOOT_AES_CCM_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_AES_XEX_HW_T_CALC_LOCAL_BIT_SHIFT	0x17UL
+#define CC_HOST_BOOT_AES_XEX_HW_T_CALC_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_AES_XEX_EXISTS_LOCAL_BIT_SHIFT	0x18UL
+#define CC_HOST_BOOT_AES_XEX_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_CTR_EXISTS_LOCAL_BIT_SHIFT	0x19UL
+#define CC_HOST_BOOT_CTR_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_AES_DIN_BYTE_RESOLUTION_LOCAL_BIT_SHIFT	0x1AUL
+#define CC_HOST_BOOT_AES_DIN_BYTE_RESOLUTION_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_TUNNELING_ENB_LOCAL_BIT_SHIFT	0x1BUL
+#define CC_HOST_BOOT_TUNNELING_ENB_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_SUPPORT_256_192_KEY_LOCAL_BIT_SHIFT	0x1CUL
+#define CC_HOST_BOOT_SUPPORT_256_192_KEY_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_ONLY_ENCRYPT_LOCAL_BIT_SHIFT	0x1DUL
+#define CC_HOST_BOOT_ONLY_ENCRYPT_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_BOOT_AES_EXISTS_LOCAL_BIT_SHIFT	0x1EUL
+#define CC_HOST_BOOT_AES_EXISTS_LOCAL_BIT_SIZE	0x1UL
+#define CC_HOST_VERSION_REG_OFFSET	0xA40UL
+#define CC_HOST_VERSION_VALUE_BIT_SHIFT	0x0UL
+#define CC_HOST_VERSION_VALUE_BIT_SIZE	0x20UL
+#define CC_HOST_KFDE0_VALID_REG_OFFSET	0xA60UL
+#define CC_HOST_KFDE0_VALID_VALUE_BIT_SHIFT	0x0UL
+#define CC_HOST_KFDE0_VALID_VALUE_BIT_SIZE	0x1UL
+#define CC_HOST_KFDE1_VALID_REG_OFFSET	0xA64UL
+#define CC_HOST_KFDE1_VALID_VALUE_BIT_SHIFT	0x0UL
+#define CC_HOST_KFDE1_VALID_VALUE_BIT_SIZE	0x1UL
+#define CC_HOST_KFDE2_VALID_REG_OFFSET	0xA68UL
+#define CC_HOST_KFDE2_VALID_VALUE_BIT_SHIFT	0x0UL
+#define CC_HOST_KFDE2_VALID_VALUE_BIT_SIZE	0x1UL
+#define CC_HOST_KFDE3_VALID_REG_OFFSET	0xA6CUL
+#define CC_HOST_KFDE3_VALID_VALUE_BIT_SHIFT	0x0UL
+#define CC_HOST_KFDE3_VALID_VALUE_BIT_SIZE	0x1UL
+#define CC_HOST_GPR0_REG_OFFSET	0xA70UL
+#define CC_HOST_GPR0_VALUE_BIT_SHIFT	0x0UL
+#define CC_HOST_GPR0_VALUE_BIT_SIZE	0x20UL
+#define CC_GPR_HOST_REG_OFFSET	0xA74UL
+#define CC_GPR_HOST_VALUE_BIT_SHIFT	0x0UL
+#define CC_GPR_HOST_VALUE_BIT_SIZE	0x20UL
+#define CC_HOST_POWER_DOWN_EN_REG_OFFSET	0xA78UL
+#define CC_HOST_POWER_DOWN_EN_VALUE_BIT_SHIFT	0x0UL
+#define CC_HOST_POWER_DOWN_EN_VALUE_BIT_SIZE	0x1UL
+// --------------------------------------
+// BLOCK: HOST_SRAM
+// --------------------------------------
+#define CC_SRAM_DATA_REG_OFFSET	0xF00UL
+#define CC_SRAM_DATA_VALUE_BIT_SHIFT	0x0UL
+#define CC_SRAM_DATA_VALUE_BIT_SIZE	0x20UL
+#define CC_SRAM_ADDR_REG_OFFSET	0xF04UL
+#define CC_SRAM_ADDR_VALUE_BIT_SHIFT	0x0UL
+#define CC_SRAM_ADDR_VALUE_BIT_SIZE	0xFUL
+#define CC_SRAM_DATA_READY_REG_OFFSET	0xF08UL
+#define CC_SRAM_DATA_READY_VALUE_BIT_SHIFT	0x0UL
+#define CC_SRAM_DATA_READY_VALUE_BIT_SIZE	0x1UL
+
+#endif //__CC_HOST_H__
diff --git a/drivers/crypto/ccree/cc_hw_queue_defs.h b/drivers/crypto/ccree/cc_hw_queue_defs.h
new file mode 100644
index 000000000000..a091ae57f902
--- /dev/null
+++ b/drivers/crypto/ccree/cc_hw_queue_defs.h
@@ -0,0 +1,576 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#ifndef __CC_HW_QUEUE_DEFS_H__
+#define __CC_HW_QUEUE_DEFS_H__
+
+#include <linux/types.h>
+
+#include "cc_kernel_regs.h"
+#include <linux/bitfield.h>
+
+/******************************************************************************
+ *				DEFINITIONS
+ ******************************************************************************/
+
+#define HW_DESC_SIZE_WORDS		6
+/* Define max. available slots in HW queue */
+#define HW_QUEUE_SLOTS_MAX              15
+
+#define CC_REG_LOW(word, name)  \
+	(CC_DSCRPTR_QUEUE_WORD ## word ## _ ## name ## _BIT_SHIFT)
+
+#define CC_REG_HIGH(word, name) \
+	(CC_REG_LOW(word, name) + \
+	 CC_DSCRPTR_QUEUE_WORD ## word ## _ ## name ## _BIT_SIZE - 1)
+
+#define CC_GENMASK(word, name) \
+	GENMASK(CC_REG_HIGH(word, name), CC_REG_LOW(word, name))
+
+#define WORD0_VALUE		CC_GENMASK(0, VALUE)
+#define WORD1_DIN_CONST_VALUE	CC_GENMASK(1, DIN_CONST_VALUE)
+#define WORD1_DIN_DMA_MODE	CC_GENMASK(1, DIN_DMA_MODE)
+#define WORD1_DIN_SIZE		CC_GENMASK(1, DIN_SIZE)
+#define WORD1_NOT_LAST		CC_GENMASK(1, NOT_LAST)
+#define WORD1_NS_BIT		CC_GENMASK(1, NS_BIT)
+#define WORD2_VALUE		CC_GENMASK(2, VALUE)
+#define WORD3_DOUT_DMA_MODE	CC_GENMASK(3, DOUT_DMA_MODE)
+#define WORD3_DOUT_LAST_IND	CC_GENMASK(3, DOUT_LAST_IND)
+#define WORD3_DOUT_SIZE		CC_GENMASK(3, DOUT_SIZE)
+#define WORD3_HASH_XOR_BIT	CC_GENMASK(3, HASH_XOR_BIT)
+#define WORD3_NS_BIT		CC_GENMASK(3, NS_BIT)
+#define WORD3_QUEUE_LAST_IND	CC_GENMASK(3, QUEUE_LAST_IND)
+#define WORD4_ACK_NEEDED	CC_GENMASK(4, ACK_NEEDED)
+#define WORD4_AES_SEL_N_HASH	CC_GENMASK(4, AES_SEL_N_HASH)
+#define WORD4_BYTES_SWAP	CC_GENMASK(4, BYTES_SWAP)
+#define WORD4_CIPHER_CONF0	CC_GENMASK(4, CIPHER_CONF0)
+#define WORD4_CIPHER_CONF1	CC_GENMASK(4, CIPHER_CONF1)
+#define WORD4_CIPHER_CONF2	CC_GENMASK(4, CIPHER_CONF2)
+#define WORD4_CIPHER_DO		CC_GENMASK(4, CIPHER_DO)
+#define WORD4_CIPHER_MODE	CC_GENMASK(4, CIPHER_MODE)
+#define WORD4_CMAC_SIZE0	CC_GENMASK(4, CMAC_SIZE0)
+#define WORD4_DATA_FLOW_MODE	CC_GENMASK(4, DATA_FLOW_MODE)
+#define WORD4_KEY_SIZE		CC_GENMASK(4, KEY_SIZE)
+#define WORD4_SETUP_OPERATION	CC_GENMASK(4, SETUP_OPERATION)
+#define WORD5_DIN_ADDR_HIGH	CC_GENMASK(5, DIN_ADDR_HIGH)
+#define WORD5_DOUT_ADDR_HIGH	CC_GENMASK(5, DOUT_ADDR_HIGH)
+
+/******************************************************************************
+ *				TYPE DEFINITIONS
+ ******************************************************************************/
+
+struct cc_hw_desc {
+	union {
+		u32 word[HW_DESC_SIZE_WORDS];
+		u16 hword[HW_DESC_SIZE_WORDS * 2];
+	};
+};
+
+enum cc_axi_sec {
+	AXI_SECURE = 0,
+	AXI_NOT_SECURE = 1
+};
+
+enum cc_desc_direction {
+	DESC_DIRECTION_ILLEGAL = -1,
+	DESC_DIRECTION_ENCRYPT_ENCRYPT = 0,
+	DESC_DIRECTION_DECRYPT_DECRYPT = 1,
+	DESC_DIRECTION_DECRYPT_ENCRYPT = 3,
+	DESC_DIRECTION_END = S32_MAX,
+};
+
+enum cc_dma_mode {
+	DMA_MODE_NULL		= -1,
+	NO_DMA			= 0,
+	DMA_SRAM		= 1,
+	DMA_DLLI		= 2,
+	DMA_MLLI		= 3,
+	DMA_MODE_END		= S32_MAX,
+};
+
+enum cc_flow_mode {
+	FLOW_MODE_NULL		= -1,
+	/* data flows */
+	BYPASS			= 0,
+	DIN_AES_DOUT		= 1,
+	AES_to_HASH		= 2,
+	AES_and_HASH		= 3,
+	DIN_DES_DOUT		= 4,
+	DES_to_HASH		= 5,
+	DES_and_HASH		= 6,
+	DIN_HASH		= 7,
+	DIN_HASH_and_BYPASS	= 8,
+	AESMAC_and_BYPASS	= 9,
+	AES_to_HASH_and_DOUT	= 10,
+	DIN_RC4_DOUT		= 11,
+	DES_to_HASH_and_DOUT	= 12,
+	AES_to_AES_to_HASH_and_DOUT	= 13,
+	AES_to_AES_to_HASH	= 14,
+	AES_to_HASH_and_AES	= 15,
+	DIN_AES_AESMAC		= 17,
+	HASH_to_DOUT		= 18,
+	/* setup flows */
+	S_DIN_to_AES		= 32,
+	S_DIN_to_AES2		= 33,
+	S_DIN_to_DES		= 34,
+	S_DIN_to_RC4		= 35,
+	S_DIN_to_HASH		= 37,
+	S_AES_to_DOUT		= 38,
+	S_AES2_to_DOUT		= 39,
+	S_RC4_to_DOUT		= 41,
+	S_DES_to_DOUT		= 42,
+	S_HASH_to_DOUT		= 43,
+	SET_FLOW_ID		= 44,
+	FLOW_MODE_END = S32_MAX,
+};
+
+enum cc_setup_op {
+	SETUP_LOAD_NOP		= 0,
+	SETUP_LOAD_STATE0	= 1,
+	SETUP_LOAD_STATE1	= 2,
+	SETUP_LOAD_STATE2	= 3,
+	SETUP_LOAD_KEY0		= 4,
+	SETUP_LOAD_XEX_KEY	= 5,
+	SETUP_WRITE_STATE0	= 8,
+	SETUP_WRITE_STATE1	= 9,
+	SETUP_WRITE_STATE2	= 10,
+	SETUP_WRITE_STATE3	= 11,
+	SETUP_OP_END = S32_MAX,
+};
+
+enum cc_hash_conf_pad {
+	HASH_PADDING_DISABLED = 0,
+	HASH_PADDING_ENABLED = 1,
+	HASH_DIGEST_RESULT_LITTLE_ENDIAN = 2,
+	HASH_CONFIG1_PADDING_RESERVE32 = S32_MAX,
+};
+
+enum cc_aes_mac_selector {
+	AES_SK = 1,
+	AES_CMAC_INIT = 2,
+	AES_CMAC_SIZE0 = 3,
+	AES_MAC_END = S32_MAX,
+};
+
+#define HW_KEY_MASK_CIPHER_DO	  0x3
+#define HW_KEY_SHIFT_CIPHER_CFG2  2
+
+/* HwCryptoKey[1:0] is mapped to cipher_do[1:0] */
+/* HwCryptoKey[2:3] is mapped to cipher_config2[1:0] */
+enum cc_hw_crypto_key {
+	USER_KEY = 0,			/* 0x0000 */
+	ROOT_KEY = 1,			/* 0x0001 */
+	PROVISIONING_KEY = 2,		/* 0x0010 */ /* ==KCP */
+	SESSION_KEY = 3,		/* 0x0011 */
+	RESERVED_KEY = 4,		/* NA */
+	PLATFORM_KEY = 5,		/* 0x0101 */
+	CUSTOMER_KEY = 6,		/* 0x0110 */
+	KFDE0_KEY = 7,			/* 0x0111 */
+	KFDE1_KEY = 9,			/* 0x1001 */
+	KFDE2_KEY = 10,			/* 0x1010 */
+	KFDE3_KEY = 11,			/* 0x1011 */
+	END_OF_KEYS = S32_MAX,
+};
+
+enum cc_hw_aes_key_size {
+	AES_128_KEY = 0,
+	AES_192_KEY = 1,
+	AES_256_KEY = 2,
+	END_OF_AES_KEYS = S32_MAX,
+};
+
+enum cc_hash_cipher_pad {
+	DO_NOT_PAD = 0,
+	DO_PAD = 1,
+	HASH_CIPHER_DO_PADDING_RESERVE32 = S32_MAX,
+};
+
+/*****************************/
+/* Descriptor packing macros */
+/*****************************/
+
+/*
+ * Init a HW descriptor struct
+ * @pdesc: pointer HW descriptor struct
+ */
+static inline void hw_desc_init(struct cc_hw_desc *pdesc)
+{
+	memset(pdesc, 0, sizeof(struct cc_hw_desc));
+}
+
+/*
+ * Indicates the end of current HW descriptors flow and release the HW engines.
+ *
+ * @pdesc: pointer HW descriptor struct
+ */
+static inline void set_queue_last_ind_bit(struct cc_hw_desc *pdesc)
+{
+	pdesc->word[3] |= FIELD_PREP(WORD3_QUEUE_LAST_IND, 1);
+}
+
+/*
+ * Set the DIN field of a HW descriptors
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @dma_mode: dmaMode The DMA mode: NO_DMA, SRAM, DLLI, MLLI, CONSTANT
+ * @addr: dinAdr DIN address
+ * @size: Data size in bytes
+ * @axi_sec: AXI secure bit
+ */
+static inline void set_din_type(struct cc_hw_desc *pdesc,
+				enum cc_dma_mode dma_mode, dma_addr_t addr,
+				u32 size, enum cc_axi_sec axi_sec)
+{
+	pdesc->word[0] = (u32)addr;
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	pdesc->word[5] |= FIELD_PREP(WORD5_DIN_ADDR_HIGH, ((u16)(addr >> 32)));
+#endif
+	pdesc->word[1] |= FIELD_PREP(WORD1_DIN_DMA_MODE, dma_mode) |
+				FIELD_PREP(WORD1_DIN_SIZE, size) |
+				FIELD_PREP(WORD1_NS_BIT, axi_sec);
+}
+
+/*
+ * Set the DIN field of a HW descriptors to NO DMA mode.
+ * Used for NOP descriptor, register patches and other special modes.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @addr: DIN address
+ * @size: Data size in bytes
+ */
+static inline void set_din_no_dma(struct cc_hw_desc *pdesc, u32 addr, u32 size)
+{
+	pdesc->word[0] = addr;
+	pdesc->word[1] |= FIELD_PREP(WORD1_DIN_SIZE, size);
+}
+
+/*
+ * Set the DIN field of a HW descriptors to SRAM mode.
+ * Note: No need to check SRAM alignment since host requests do not use SRAM and
+ * adaptor will enforce alignment check.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @addr: DIN address
+ * @size Data size in bytes
+ */
+static inline void set_din_sram(struct cc_hw_desc *pdesc, dma_addr_t addr,
+				u32 size)
+{
+	pdesc->word[0] = (u32)addr;
+	pdesc->word[1] |= FIELD_PREP(WORD1_DIN_SIZE, size) |
+				FIELD_PREP(WORD1_DIN_DMA_MODE, DMA_SRAM);
+}
+
+/*
+ * Set the DIN field of a HW descriptors to CONST mode
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @val: DIN const value
+ * @size: Data size in bytes
+ */
+static inline void set_din_const(struct cc_hw_desc *pdesc, u32 val, u32 size)
+{
+	pdesc->word[0] = val;
+	pdesc->word[1] |= FIELD_PREP(WORD1_DIN_CONST_VALUE, 1) |
+			FIELD_PREP(WORD1_DIN_DMA_MODE, DMA_SRAM) |
+			FIELD_PREP(WORD1_DIN_SIZE, size);
+}
+
+/*
+ * Set the DIN not last input data indicator
+ *
+ * @pdesc: pointer HW descriptor struct
+ */
+static inline void set_din_not_last_indication(struct cc_hw_desc *pdesc)
+{
+	pdesc->word[1] |= FIELD_PREP(WORD1_NOT_LAST, 1);
+}
+
+/*
+ * Set the DOUT field of a HW descriptors
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @dma_mode: The DMA mode: NO_DMA, SRAM, DLLI, MLLI, CONSTANT
+ * @addr: DOUT address
+ * @size: Data size in bytes
+ * @axi_sec: AXI secure bit
+ */
+static inline void set_dout_type(struct cc_hw_desc *pdesc,
+				 enum cc_dma_mode dma_mode, dma_addr_t addr,
+				 u32 size, enum cc_axi_sec axi_sec)
+{
+	pdesc->word[2] = (u32)addr;
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	pdesc->word[5] |= FIELD_PREP(WORD5_DOUT_ADDR_HIGH, ((u16)(addr >> 32)));
+#endif
+	pdesc->word[3] |= FIELD_PREP(WORD3_DOUT_DMA_MODE, dma_mode) |
+				FIELD_PREP(WORD3_DOUT_SIZE, size) |
+				FIELD_PREP(WORD3_NS_BIT, axi_sec);
+}
+
+/*
+ * Set the DOUT field of a HW descriptors to DLLI type
+ * The LAST INDICATION is provided by the user
+ *
+ * @pdesc pointer HW descriptor struct
+ * @addr: DOUT address
+ * @size: Data size in bytes
+ * @last_ind: The last indication bit
+ * @axi_sec: AXI secure bit
+ */
+static inline void set_dout_dlli(struct cc_hw_desc *pdesc, dma_addr_t addr,
+				 u32 size, enum cc_axi_sec axi_sec,
+				 u32 last_ind)
+{
+	set_dout_type(pdesc, DMA_DLLI, addr, size, axi_sec);
+	pdesc->word[3] |= FIELD_PREP(WORD3_DOUT_LAST_IND, last_ind);
+}
+
+/*
+ * Set the DOUT field of a HW descriptors to DLLI type
+ * The LAST INDICATION is provided by the user
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @addr: DOUT address
+ * @size: Data size in bytes
+ * @last_ind: The last indication bit
+ * @axi_sec: AXI secure bit
+ */
+static inline void set_dout_mlli(struct cc_hw_desc *pdesc, dma_addr_t addr,
+				 u32 size, enum cc_axi_sec axi_sec,
+				 bool last_ind)
+{
+	set_dout_type(pdesc, DMA_MLLI, addr, size, axi_sec);
+	pdesc->word[3] |= FIELD_PREP(WORD3_DOUT_LAST_IND, last_ind);
+}
+
+/*
+ * Set the DOUT field of a HW descriptors to NO DMA mode.
+ * Used for NOP descriptor, register patches and other special modes.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @addr: DOUT address
+ * @size: Data size in bytes
+ * @write_enable: Enables a write operation to a register
+ */
+static inline void set_dout_no_dma(struct cc_hw_desc *pdesc, u32 addr,
+				   u32 size, bool write_enable)
+{
+	pdesc->word[2] = addr;
+	pdesc->word[3] |= FIELD_PREP(WORD3_DOUT_SIZE, size) |
+			FIELD_PREP(WORD3_DOUT_LAST_IND, write_enable);
+}
+
+/*
+ * Set the word for the XOR operation.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @val: xor data value
+ */
+static inline void set_xor_val(struct cc_hw_desc *pdesc, u32 val)
+{
+	pdesc->word[2] = val;
+}
+
+/*
+ * Sets the XOR indicator bit in the descriptor
+ *
+ * @pdesc: pointer HW descriptor struct
+ */
+static inline void set_xor_active(struct cc_hw_desc *pdesc)
+{
+	pdesc->word[3] |= FIELD_PREP(WORD3_HASH_XOR_BIT, 1);
+}
+
+/*
+ * Select the AES engine instead of HASH engine when setting up combined mode
+ * with AES XCBC MAC
+ *
+ * @pdesc: pointer HW descriptor struct
+ */
+static inline void set_aes_not_hash_mode(struct cc_hw_desc *pdesc)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_AES_SEL_N_HASH, 1);
+}
+
+/*
+ * Set the DOUT field of a HW descriptors to SRAM mode
+ * Note: No need to check SRAM alignment since host requests do not use SRAM and
+ * adaptor will enforce alignment check.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @addr: DOUT address
+ * @size: Data size in bytes
+ */
+static inline void set_dout_sram(struct cc_hw_desc *pdesc, u32 addr, u32 size)
+{
+	pdesc->word[2] = addr;
+	pdesc->word[3] |= FIELD_PREP(WORD3_DOUT_DMA_MODE, DMA_SRAM) |
+			FIELD_PREP(WORD3_DOUT_SIZE, size);
+}
+
+/*
+ * Sets the data unit size for XEX mode in data_out_addr[15:0]
+ *
+ * @pdesc: pDesc pointer HW descriptor struct
+ * @size: data unit size for XEX mode
+ */
+static inline void set_xex_data_unit_size(struct cc_hw_desc *pdesc, u32 size)
+{
+	pdesc->word[2] = size;
+}
+
+/*
+ * Set the number of rounds for Multi2 in data_out_addr[15:0]
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @num: number of rounds for Multi2
+ */
+static inline void set_multi2_num_rounds(struct cc_hw_desc *pdesc, u32 num)
+{
+	pdesc->word[2] = num;
+}
+
+/*
+ * Set the flow mode.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @mode: Any one of the modes defined in [CC7x-DESC]
+ */
+static inline void set_flow_mode(struct cc_hw_desc *pdesc,
+				 enum cc_flow_mode mode)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_DATA_FLOW_MODE, mode);
+}
+
+/*
+ * Set the cipher mode.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @mode:  Any one of the modes defined in [CC7x-DESC]
+ */
+static inline void set_cipher_mode(struct cc_hw_desc *pdesc,
+				   enum drv_cipher_mode mode)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_CIPHER_MODE, mode);
+}
+
+/*
+ * Set the cipher configuration fields.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @mode: Any one of the modes defined in [CC7x-DESC]
+ */
+static inline void set_cipher_config0(struct cc_hw_desc *pdesc,
+				      enum drv_crypto_direction mode)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_CIPHER_CONF0, mode);
+}
+
+/*
+ * Set the cipher configuration fields.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @config: Any one of the modes defined in [CC7x-DESC]
+ */
+static inline void set_cipher_config1(struct cc_hw_desc *pdesc,
+				      enum cc_hash_conf_pad config)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_CIPHER_CONF1, config);
+}
+
+/*
+ * Set HW key configuration fields.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @hw_key: The HW key slot asdefined in enum cc_hw_crypto_key
+ */
+static inline void set_hw_crypto_key(struct cc_hw_desc *pdesc,
+				     enum cc_hw_crypto_key hw_key)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_CIPHER_DO,
+				     (hw_key & HW_KEY_MASK_CIPHER_DO)) |
+			FIELD_PREP(WORD4_CIPHER_CONF2,
+				   (hw_key >> HW_KEY_SHIFT_CIPHER_CFG2));
+}
+
+/*
+ * Set byte order of all setup-finalize descriptors.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @config: Any one of the modes defined in [CC7x-DESC]
+ */
+static inline void set_bytes_swap(struct cc_hw_desc *pdesc, bool config)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_BYTES_SWAP, config);
+}
+
+/*
+ * Set CMAC_SIZE0 mode.
+ *
+ * @pdesc: pointer HW descriptor struct
+ */
+static inline void set_cmac_size0_mode(struct cc_hw_desc *pdesc)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_CMAC_SIZE0, 1);
+}
+
+/*
+ * Set key size descriptor field.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @size: key size in bytes (NOT size code)
+ */
+static inline void set_key_size(struct cc_hw_desc *pdesc, u32 size)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_KEY_SIZE, size);
+}
+
+/*
+ * Set AES key size.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @size: key size in bytes (NOT size code)
+ */
+static inline void set_key_size_aes(struct cc_hw_desc *pdesc, u32 size)
+{
+	set_key_size(pdesc, ((size >> 3) - 2));
+}
+
+/*
+ * Set DES key size.
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @size: key size in bytes (NOT size code)
+ */
+static inline void set_key_size_des(struct cc_hw_desc *pdesc, u32 size)
+{
+	set_key_size(pdesc, ((size >> 3) - 1));
+}
+
+/*
+ * Set the descriptor setup mode
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @mode: Any one of the setup modes defined in [CC7x-DESC]
+ */
+static inline void set_setup_mode(struct cc_hw_desc *pdesc,
+				  enum cc_setup_op mode)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_SETUP_OPERATION, mode);
+}
+
+/*
+ * Set the descriptor cipher DO
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @config: Any one of the cipher do defined in [CC7x-DESC]
+ */
+static inline void set_cipher_do(struct cc_hw_desc *pdesc,
+				 enum cc_hash_cipher_pad config)
+{
+	pdesc->word[4] |= FIELD_PREP(WORD4_CIPHER_DO,
+				(config & HW_KEY_MASK_CIPHER_DO));
+}
+
+#endif /*__CC_HW_QUEUE_DEFS_H__*/
diff --git a/drivers/crypto/ccree/cc_ivgen.c b/drivers/crypto/ccree/cc_ivgen.c
new file mode 100644
index 000000000000..769458323394
--- /dev/null
+++ b/drivers/crypto/ccree/cc_ivgen.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include <crypto/ctr.h>
+#include "cc_driver.h"
+#include "cc_ivgen.h"
+#include "cc_request_mgr.h"
+#include "cc_sram_mgr.h"
+#include "cc_buffer_mgr.h"
+
+/* The max. size of pool *MUST* be <= SRAM total size */
+#define CC_IVPOOL_SIZE 1024
+/* The first 32B fraction of pool are dedicated to the
+ * next encryption "key" & "IV" for pool regeneration
+ */
+#define CC_IVPOOL_META_SIZE (CC_AES_IV_SIZE + AES_KEYSIZE_128)
+#define CC_IVPOOL_GEN_SEQ_LEN	4
+
+/**
+ * struct cc_ivgen_ctx -IV pool generation context
+ * @pool:          the start address of the iv-pool resides in internal RAM
+ * @ctr_key_dma:   address of pool's encryption key material in internal RAM
+ * @ctr_iv_dma:    address of pool's counter iv in internal RAM
+ * @next_iv_ofs:   the offset to the next available IV in pool
+ * @pool_meta:     virt. address of the initial enc. key/IV
+ * @pool_meta_dma: phys. address of the initial enc. key/IV
+ */
+struct cc_ivgen_ctx {
+	cc_sram_addr_t pool;
+	cc_sram_addr_t ctr_key;
+	cc_sram_addr_t ctr_iv;
+	u32 next_iv_ofs;
+	u8 *pool_meta;
+	dma_addr_t pool_meta_dma;
+};
+
+/*!
+ * Generates CC_IVPOOL_SIZE of random bytes by
+ * encrypting 0's using AES128-CTR.
+ *
+ * \param ivgen iv-pool context
+ * \param iv_seq IN/OUT array to the descriptors sequence
+ * \param iv_seq_len IN/OUT pointer to the sequence length
+ */
+static int cc_gen_iv_pool(struct cc_ivgen_ctx *ivgen_ctx,
+			  struct cc_hw_desc iv_seq[], unsigned int *iv_seq_len)
+{
+	unsigned int idx = *iv_seq_len;
+
+	if ((*iv_seq_len + CC_IVPOOL_GEN_SEQ_LEN) > CC_IVPOOL_SEQ_LEN) {
+		/* The sequence will be longer than allowed */
+		return -EINVAL;
+	}
+	/* Setup key */
+	hw_desc_init(&iv_seq[idx]);
+	set_din_sram(&iv_seq[idx], ivgen_ctx->ctr_key, AES_KEYSIZE_128);
+	set_setup_mode(&iv_seq[idx], SETUP_LOAD_KEY0);
+	set_cipher_config0(&iv_seq[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_flow_mode(&iv_seq[idx], S_DIN_to_AES);
+	set_key_size_aes(&iv_seq[idx], CC_AES_128_BIT_KEY_SIZE);
+	set_cipher_mode(&iv_seq[idx], DRV_CIPHER_CTR);
+	idx++;
+
+	/* Setup cipher state */
+	hw_desc_init(&iv_seq[idx]);
+	set_din_sram(&iv_seq[idx], ivgen_ctx->ctr_iv, CC_AES_IV_SIZE);
+	set_cipher_config0(&iv_seq[idx], DESC_DIRECTION_ENCRYPT_ENCRYPT);
+	set_flow_mode(&iv_seq[idx], S_DIN_to_AES);
+	set_setup_mode(&iv_seq[idx], SETUP_LOAD_STATE1);
+	set_key_size_aes(&iv_seq[idx], CC_AES_128_BIT_KEY_SIZE);
+	set_cipher_mode(&iv_seq[idx], DRV_CIPHER_CTR);
+	idx++;
+
+	/* Perform dummy encrypt to skip first block */
+	hw_desc_init(&iv_seq[idx]);
+	set_din_const(&iv_seq[idx], 0, CC_AES_IV_SIZE);
+	set_dout_sram(&iv_seq[idx], ivgen_ctx->pool, CC_AES_IV_SIZE);
+	set_flow_mode(&iv_seq[idx], DIN_AES_DOUT);
+	idx++;
+
+	/* Generate IV pool */
+	hw_desc_init(&iv_seq[idx]);
+	set_din_const(&iv_seq[idx], 0, CC_IVPOOL_SIZE);
+	set_dout_sram(&iv_seq[idx], ivgen_ctx->pool, CC_IVPOOL_SIZE);
+	set_flow_mode(&iv_seq[idx], DIN_AES_DOUT);
+	idx++;
+
+	*iv_seq_len = idx; /* Update sequence length */
+
+	/* queue ordering assures pool readiness */
+	ivgen_ctx->next_iv_ofs = CC_IVPOOL_META_SIZE;
+
+	return 0;
+}
+
+/*!
+ * Generates the initial pool in SRAM.
+ * This function should be invoked when resuming driver.
+ *
+ * \param drvdata
+ *
+ * \return int Zero for success, negative value otherwise.
+ */
+int cc_init_iv_sram(struct cc_drvdata *drvdata)
+{
+	struct cc_ivgen_ctx *ivgen_ctx = drvdata->ivgen_handle;
+	struct cc_hw_desc iv_seq[CC_IVPOOL_SEQ_LEN];
+	unsigned int iv_seq_len = 0;
+	int rc;
+
+	/* Generate initial enc. key/iv */
+	get_random_bytes(ivgen_ctx->pool_meta, CC_IVPOOL_META_SIZE);
+
+	/* The first 32B reserved for the enc. Key/IV */
+	ivgen_ctx->ctr_key = ivgen_ctx->pool;
+	ivgen_ctx->ctr_iv = ivgen_ctx->pool + AES_KEYSIZE_128;
+
+	/* Copy initial enc. key and IV to SRAM at a single descriptor */
+	hw_desc_init(&iv_seq[iv_seq_len]);
+	set_din_type(&iv_seq[iv_seq_len], DMA_DLLI, ivgen_ctx->pool_meta_dma,
+		     CC_IVPOOL_META_SIZE, NS_BIT);
+	set_dout_sram(&iv_seq[iv_seq_len], ivgen_ctx->pool,
+		      CC_IVPOOL_META_SIZE);
+	set_flow_mode(&iv_seq[iv_seq_len], BYPASS);
+	iv_seq_len++;
+
+	/* Generate initial pool */
+	rc = cc_gen_iv_pool(ivgen_ctx, iv_seq, &iv_seq_len);
+	if (rc)
+		return rc;
+
+	/* Fire-and-forget */
+	return send_request_init(drvdata, iv_seq, iv_seq_len);
+}
+
+/*!
+ * Free iv-pool and ivgen context.
+ *
+ * \param drvdata
+ */
+void cc_ivgen_fini(struct cc_drvdata *drvdata)
+{
+	struct cc_ivgen_ctx *ivgen_ctx = drvdata->ivgen_handle;
+	struct device *device = &drvdata->plat_dev->dev;
+
+	if (!ivgen_ctx)
+		return;
+
+	if (ivgen_ctx->pool_meta) {
+		memset(ivgen_ctx->pool_meta, 0, CC_IVPOOL_META_SIZE);
+		dma_free_coherent(device, CC_IVPOOL_META_SIZE,
+				  ivgen_ctx->pool_meta,
+				  ivgen_ctx->pool_meta_dma);
+	}
+
+	ivgen_ctx->pool = NULL_SRAM_ADDR;
+
+	/* release "this" context */
+	kfree(ivgen_ctx);
+}
+
+/*!
+ * Allocates iv-pool and maps resources.
+ * This function generates the first IV pool.
+ *
+ * \param drvdata Driver's private context
+ *
+ * \return int Zero for success, negative value otherwise.
+ */
+int cc_ivgen_init(struct cc_drvdata *drvdata)
+{
+	struct cc_ivgen_ctx *ivgen_ctx;
+	struct device *device = &drvdata->plat_dev->dev;
+	int rc;
+
+	/* Allocate "this" context */
+	ivgen_ctx = kzalloc(sizeof(*ivgen_ctx), GFP_KERNEL);
+	if (!ivgen_ctx)
+		return -ENOMEM;
+
+	/* Allocate pool's header for initial enc. key/IV */
+	ivgen_ctx->pool_meta = dma_alloc_coherent(device, CC_IVPOOL_META_SIZE,
+						  &ivgen_ctx->pool_meta_dma,
+						  GFP_KERNEL);
+	if (!ivgen_ctx->pool_meta) {
+		dev_err(device, "Not enough memory to allocate DMA of pool_meta (%u B)\n",
+			CC_IVPOOL_META_SIZE);
+		rc = -ENOMEM;
+		goto out;
+	}
+	/* Allocate IV pool in SRAM */
+	ivgen_ctx->pool = cc_sram_alloc(drvdata, CC_IVPOOL_SIZE);
+	if (ivgen_ctx->pool == NULL_SRAM_ADDR) {
+		dev_err(device, "SRAM pool exhausted\n");
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	drvdata->ivgen_handle = ivgen_ctx;
+
+	return cc_init_iv_sram(drvdata);
+
+out:
+	cc_ivgen_fini(drvdata);
+	return rc;
+}
+
+/*!
+ * Acquires 16 Bytes IV from the iv-pool
+ *
+ * \param drvdata Driver private context
+ * \param iv_out_dma Array of physical IV out addresses
+ * \param iv_out_dma_len Length of iv_out_dma array (additional elements
+ *                       of iv_out_dma array are ignore)
+ * \param iv_out_size May be 8 or 16 bytes long
+ * \param iv_seq IN/OUT array to the descriptors sequence
+ * \param iv_seq_len IN/OUT pointer to the sequence length
+ *
+ * \return int Zero for success, negative value otherwise.
+ */
+int cc_get_iv(struct cc_drvdata *drvdata, dma_addr_t iv_out_dma[],
+	      unsigned int iv_out_dma_len, unsigned int iv_out_size,
+	      struct cc_hw_desc iv_seq[], unsigned int *iv_seq_len)
+{
+	struct cc_ivgen_ctx *ivgen_ctx = drvdata->ivgen_handle;
+	unsigned int idx = *iv_seq_len;
+	struct device *dev = drvdata_to_dev(drvdata);
+	unsigned int t;
+
+	if (iv_out_size != CC_AES_IV_SIZE &&
+	    iv_out_size != CTR_RFC3686_IV_SIZE) {
+		return -EINVAL;
+	}
+	if ((iv_out_dma_len + 1) > CC_IVPOOL_SEQ_LEN) {
+		/* The sequence will be longer than allowed */
+		return -EINVAL;
+	}
+
+	/* check that number of generated IV is limited to max dma address
+	 * iv buffer size
+	 */
+	if (iv_out_dma_len > CC_MAX_IVGEN_DMA_ADDRESSES) {
+		/* The sequence will be longer than allowed */
+		return -EINVAL;
+	}
+
+	for (t = 0; t < iv_out_dma_len; t++) {
+		/* Acquire IV from pool */
+		hw_desc_init(&iv_seq[idx]);
+		set_din_sram(&iv_seq[idx], (ivgen_ctx->pool +
+					    ivgen_ctx->next_iv_ofs),
+			     iv_out_size);
+		set_dout_dlli(&iv_seq[idx], iv_out_dma[t], iv_out_size,
+			      NS_BIT, 0);
+		set_flow_mode(&iv_seq[idx], BYPASS);
+		idx++;
+	}
+
+	/* Bypass operation is proceeded by crypto sequence, hence must
+	 *  assure bypass-write-transaction by a memory barrier
+	 */
+	hw_desc_init(&iv_seq[idx]);
+	set_din_no_dma(&iv_seq[idx], 0, 0xfffff0);
+	set_dout_no_dma(&iv_seq[idx], 0, 0, 1);
+	idx++;
+
+	*iv_seq_len = idx; /* update seq length */
+
+	/* Update iv index */
+	ivgen_ctx->next_iv_ofs += iv_out_size;
+
+	if ((CC_IVPOOL_SIZE - ivgen_ctx->next_iv_ofs) < CC_AES_IV_SIZE) {
+		dev_dbg(dev, "Pool exhausted, regenerating iv-pool\n");
+		/* pool is drained -regenerate it! */
+		return cc_gen_iv_pool(ivgen_ctx, iv_seq, iv_seq_len);
+	}
+
+	return 0;
+}
diff --git a/drivers/crypto/ccree/cc_ivgen.h b/drivers/crypto/ccree/cc_ivgen.h
new file mode 100644
index 000000000000..b6ac16903dda
--- /dev/null
+++ b/drivers/crypto/ccree/cc_ivgen.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#ifndef __CC_IVGEN_H__
+#define __CC_IVGEN_H__
+
+#include "cc_hw_queue_defs.h"
+
+#define CC_IVPOOL_SEQ_LEN 8
+
+/*!
+ * Allocates iv-pool and maps resources.
+ * This function generates the first IV pool.
+ *
+ * \param drvdata Driver's private context
+ *
+ * \return int Zero for success, negative value otherwise.
+ */
+int cc_ivgen_init(struct cc_drvdata *drvdata);
+
+/*!
+ * Free iv-pool and ivgen context.
+ *
+ * \param drvdata
+ */
+void cc_ivgen_fini(struct cc_drvdata *drvdata);
+
+/*!
+ * Generates the initial pool in SRAM.
+ * This function should be invoked when resuming DX driver.
+ *
+ * \param drvdata
+ *
+ * \return int Zero for success, negative value otherwise.
+ */
+int cc_init_iv_sram(struct cc_drvdata *drvdata);
+
+/*!
+ * Acquires 16 Bytes IV from the iv-pool
+ *
+ * \param drvdata Driver private context
+ * \param iv_out_dma Array of physical IV out addresses
+ * \param iv_out_dma_len Length of iv_out_dma array (additional elements of
+ *                       iv_out_dma array are ignore)
+ * \param iv_out_size May be 8 or 16 bytes long
+ * \param iv_seq IN/OUT array to the descriptors sequence
+ * \param iv_seq_len IN/OUT pointer to the sequence length
+ *
+ * \return int Zero for success, negative value otherwise.
+ */
+int cc_get_iv(struct cc_drvdata *drvdata, dma_addr_t iv_out_dma[],
+	      unsigned int iv_out_dma_len, unsigned int iv_out_size,
+	      struct cc_hw_desc iv_seq[], unsigned int *iv_seq_len);
+
+#endif /*__CC_IVGEN_H__*/
diff --git a/drivers/crypto/ccree/cc_kernel_regs.h b/drivers/crypto/ccree/cc_kernel_regs.h
new file mode 100644
index 000000000000..8d7262a35156
--- /dev/null
+++ b/drivers/crypto/ccree/cc_kernel_regs.h
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#ifndef __CC_CRYS_KERNEL_H__
+#define __CC_CRYS_KERNEL_H__
+
+// --------------------------------------
+// BLOCK: DSCRPTR
+// --------------------------------------
+#define CC_DSCRPTR_COMPLETION_COUNTER_REG_OFFSET	0xE00UL
+#define CC_DSCRPTR_COMPLETION_COUNTER_COMPLETION_COUNTER_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_COMPLETION_COUNTER_COMPLETION_COUNTER_BIT_SIZE	0x6UL
+#define CC_DSCRPTR_COMPLETION_COUNTER_OVERFLOW_COUNTER_BIT_SHIFT	0x6UL
+#define CC_DSCRPTR_COMPLETION_COUNTER_OVERFLOW_COUNTER_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_SW_RESET_REG_OFFSET	0xE40UL
+#define CC_DSCRPTR_SW_RESET_VALUE_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_SW_RESET_VALUE_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_SRAM_SIZE_REG_OFFSET	0xE60UL
+#define CC_DSCRPTR_QUEUE_SRAM_SIZE_NUM_OF_DSCRPTR_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_QUEUE_SRAM_SIZE_NUM_OF_DSCRPTR_BIT_SIZE	0xAUL
+#define CC_DSCRPTR_QUEUE_SRAM_SIZE_DSCRPTR_SRAM_SIZE_BIT_SHIFT	0xAUL
+#define CC_DSCRPTR_QUEUE_SRAM_SIZE_DSCRPTR_SRAM_SIZE_BIT_SIZE	0xCUL
+#define CC_DSCRPTR_QUEUE_SRAM_SIZE_SRAM_SIZE_BIT_SHIFT	0x16UL
+#define CC_DSCRPTR_QUEUE_SRAM_SIZE_SRAM_SIZE_BIT_SIZE	0x3UL
+#define CC_DSCRPTR_SINGLE_ADDR_EN_REG_OFFSET	0xE64UL
+#define CC_DSCRPTR_SINGLE_ADDR_EN_VALUE_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_SINGLE_ADDR_EN_VALUE_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_MEASURE_CNTR_REG_OFFSET	0xE68UL
+#define CC_DSCRPTR_MEASURE_CNTR_VALUE_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_MEASURE_CNTR_VALUE_BIT_SIZE	0x20UL
+#define CC_DSCRPTR_QUEUE_WORD0_REG_OFFSET	0xE80UL
+#define CC_DSCRPTR_QUEUE_WORD0_VALUE_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_QUEUE_WORD0_VALUE_BIT_SIZE	0x20UL
+#define CC_DSCRPTR_QUEUE_WORD1_REG_OFFSET	0xE84UL
+#define CC_DSCRPTR_QUEUE_WORD1_DIN_DMA_MODE_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_QUEUE_WORD1_DIN_DMA_MODE_BIT_SIZE	0x2UL
+#define CC_DSCRPTR_QUEUE_WORD1_DIN_SIZE_BIT_SHIFT	0x2UL
+#define CC_DSCRPTR_QUEUE_WORD1_DIN_SIZE_BIT_SIZE	0x18UL
+#define CC_DSCRPTR_QUEUE_WORD1_NS_BIT_BIT_SHIFT	0x1AUL
+#define CC_DSCRPTR_QUEUE_WORD1_NS_BIT_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD1_DIN_CONST_VALUE_BIT_SHIFT	0x1BUL
+#define CC_DSCRPTR_QUEUE_WORD1_DIN_CONST_VALUE_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD1_NOT_LAST_BIT_SHIFT	0x1CUL
+#define CC_DSCRPTR_QUEUE_WORD1_NOT_LAST_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD1_LOCK_QUEUE_BIT_SHIFT	0x1DUL
+#define CC_DSCRPTR_QUEUE_WORD1_LOCK_QUEUE_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD1_NOT_USED_BIT_SHIFT	0x1EUL
+#define CC_DSCRPTR_QUEUE_WORD1_NOT_USED_BIT_SIZE	0x2UL
+#define CC_DSCRPTR_QUEUE_WORD2_REG_OFFSET	0xE88UL
+#define CC_DSCRPTR_QUEUE_WORD2_VALUE_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_QUEUE_WORD2_VALUE_BIT_SIZE	0x20UL
+#define CC_DSCRPTR_QUEUE_WORD3_REG_OFFSET	0xE8CUL
+#define CC_DSCRPTR_QUEUE_WORD3_DOUT_DMA_MODE_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_QUEUE_WORD3_DOUT_DMA_MODE_BIT_SIZE	0x2UL
+#define CC_DSCRPTR_QUEUE_WORD3_DOUT_SIZE_BIT_SHIFT	0x2UL
+#define CC_DSCRPTR_QUEUE_WORD3_DOUT_SIZE_BIT_SIZE	0x18UL
+#define CC_DSCRPTR_QUEUE_WORD3_NS_BIT_BIT_SHIFT	0x1AUL
+#define CC_DSCRPTR_QUEUE_WORD3_NS_BIT_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD3_DOUT_LAST_IND_BIT_SHIFT	0x1BUL
+#define CC_DSCRPTR_QUEUE_WORD3_DOUT_LAST_IND_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD3_HASH_XOR_BIT_BIT_SHIFT	0x1DUL
+#define CC_DSCRPTR_QUEUE_WORD3_HASH_XOR_BIT_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD3_NOT_USED_BIT_SHIFT	0x1EUL
+#define CC_DSCRPTR_QUEUE_WORD3_NOT_USED_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD3_QUEUE_LAST_IND_BIT_SHIFT	0x1FUL
+#define CC_DSCRPTR_QUEUE_WORD3_QUEUE_LAST_IND_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD4_REG_OFFSET	0xE90UL
+#define CC_DSCRPTR_QUEUE_WORD4_DATA_FLOW_MODE_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_QUEUE_WORD4_DATA_FLOW_MODE_BIT_SIZE	0x6UL
+#define CC_DSCRPTR_QUEUE_WORD4_AES_SEL_N_HASH_BIT_SHIFT	0x6UL
+#define CC_DSCRPTR_QUEUE_WORD4_AES_SEL_N_HASH_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD4_AES_XOR_CRYPTO_KEY_BIT_SHIFT	0x7UL
+#define CC_DSCRPTR_QUEUE_WORD4_AES_XOR_CRYPTO_KEY_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD4_ACK_NEEDED_BIT_SHIFT	0x8UL
+#define CC_DSCRPTR_QUEUE_WORD4_ACK_NEEDED_BIT_SIZE	0x2UL
+#define CC_DSCRPTR_QUEUE_WORD4_CIPHER_MODE_BIT_SHIFT	0xAUL
+#define CC_DSCRPTR_QUEUE_WORD4_CIPHER_MODE_BIT_SIZE	0x4UL
+#define CC_DSCRPTR_QUEUE_WORD4_CMAC_SIZE0_BIT_SHIFT	0xEUL
+#define CC_DSCRPTR_QUEUE_WORD4_CMAC_SIZE0_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD4_CIPHER_DO_BIT_SHIFT	0xFUL
+#define CC_DSCRPTR_QUEUE_WORD4_CIPHER_DO_BIT_SIZE	0x2UL
+#define CC_DSCRPTR_QUEUE_WORD4_CIPHER_CONF0_BIT_SHIFT	0x11UL
+#define CC_DSCRPTR_QUEUE_WORD4_CIPHER_CONF0_BIT_SIZE	0x2UL
+#define CC_DSCRPTR_QUEUE_WORD4_CIPHER_CONF1_BIT_SHIFT	0x13UL
+#define CC_DSCRPTR_QUEUE_WORD4_CIPHER_CONF1_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD4_CIPHER_CONF2_BIT_SHIFT	0x14UL
+#define CC_DSCRPTR_QUEUE_WORD4_CIPHER_CONF2_BIT_SIZE	0x2UL
+#define CC_DSCRPTR_QUEUE_WORD4_KEY_SIZE_BIT_SHIFT	0x16UL
+#define CC_DSCRPTR_QUEUE_WORD4_KEY_SIZE_BIT_SIZE	0x2UL
+#define CC_DSCRPTR_QUEUE_WORD4_SETUP_OPERATION_BIT_SHIFT	0x18UL
+#define CC_DSCRPTR_QUEUE_WORD4_SETUP_OPERATION_BIT_SIZE	0x4UL
+#define CC_DSCRPTR_QUEUE_WORD4_DIN_SRAM_ENDIANNESS_BIT_SHIFT	0x1CUL
+#define CC_DSCRPTR_QUEUE_WORD4_DIN_SRAM_ENDIANNESS_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD4_DOUT_SRAM_ENDIANNESS_BIT_SHIFT	0x1DUL
+#define CC_DSCRPTR_QUEUE_WORD4_DOUT_SRAM_ENDIANNESS_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD4_WORD_SWAP_BIT_SHIFT	0x1EUL
+#define CC_DSCRPTR_QUEUE_WORD4_WORD_SWAP_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD4_BYTES_SWAP_BIT_SHIFT	0x1FUL
+#define CC_DSCRPTR_QUEUE_WORD4_BYTES_SWAP_BIT_SIZE	0x1UL
+#define CC_DSCRPTR_QUEUE_WORD5_REG_OFFSET	0xE94UL
+#define CC_DSCRPTR_QUEUE_WORD5_DIN_ADDR_HIGH_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_QUEUE_WORD5_DIN_ADDR_HIGH_BIT_SIZE	0x10UL
+#define CC_DSCRPTR_QUEUE_WORD5_DOUT_ADDR_HIGH_BIT_SHIFT	0x10UL
+#define CC_DSCRPTR_QUEUE_WORD5_DOUT_ADDR_HIGH_BIT_SIZE	0x10UL
+#define CC_DSCRPTR_QUEUE_WATERMARK_REG_OFFSET	0xE98UL
+#define CC_DSCRPTR_QUEUE_WATERMARK_VALUE_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_QUEUE_WATERMARK_VALUE_BIT_SIZE	0xAUL
+#define CC_DSCRPTR_QUEUE_CONTENT_REG_OFFSET	0xE9CUL
+#define CC_DSCRPTR_QUEUE_CONTENT_VALUE_BIT_SHIFT	0x0UL
+#define CC_DSCRPTR_QUEUE_CONTENT_VALUE_BIT_SIZE	0xAUL
+// --------------------------------------
+// BLOCK: AXI_P
+// --------------------------------------
+#define CC_AXIM_MON_INFLIGHT_REG_OFFSET	0xB00UL
+#define CC_AXIM_MON_INFLIGHT_VALUE_BIT_SHIFT	0x0UL
+#define CC_AXIM_MON_INFLIGHT_VALUE_BIT_SIZE	0x8UL
+#define CC_AXIM_MON_INFLIGHTLAST_REG_OFFSET	0xB40UL
+#define CC_AXIM_MON_INFLIGHTLAST_VALUE_BIT_SHIFT	0x0UL
+#define CC_AXIM_MON_INFLIGHTLAST_VALUE_BIT_SIZE	0x8UL
+#define CC_AXIM_MON_COMP_REG_OFFSET	0xB80UL
+#define CC_AXIM_MON_COMP8_REG_OFFSET	0xBA0UL
+#define CC_AXIM_MON_COMP_VALUE_BIT_SHIFT	0x0UL
+#define CC_AXIM_MON_COMP_VALUE_BIT_SIZE	0x10UL
+#define CC_AXIM_MON_ERR_REG_OFFSET	0xBC4UL
+#define CC_AXIM_MON_ERR_BRESP_BIT_SHIFT	0x0UL
+#define CC_AXIM_MON_ERR_BRESP_BIT_SIZE	0x2UL
+#define CC_AXIM_MON_ERR_BID_BIT_SHIFT	0x2UL
+#define CC_AXIM_MON_ERR_BID_BIT_SIZE	0x4UL
+#define CC_AXIM_MON_ERR_RRESP_BIT_SHIFT	0x10UL
+#define CC_AXIM_MON_ERR_RRESP_BIT_SIZE	0x2UL
+#define CC_AXIM_MON_ERR_RID_BIT_SHIFT	0x12UL
+#define CC_AXIM_MON_ERR_RID_BIT_SIZE	0x4UL
+#define CC_AXIM_CFG_REG_OFFSET	0xBE8UL
+#define CC_AXIM_CFG_BRESPMASK_BIT_SHIFT	0x4UL
+#define CC_AXIM_CFG_BRESPMASK_BIT_SIZE	0x1UL
+#define CC_AXIM_CFG_RRESPMASK_BIT_SHIFT	0x5UL
+#define CC_AXIM_CFG_RRESPMASK_BIT_SIZE	0x1UL
+#define CC_AXIM_CFG_INFLTMASK_BIT_SHIFT	0x6UL
+#define CC_AXIM_CFG_INFLTMASK_BIT_SIZE	0x1UL
+#define CC_AXIM_CFG_COMPMASK_BIT_SHIFT	0x7UL
+#define CC_AXIM_CFG_COMPMASK_BIT_SIZE	0x1UL
+#define CC_AXIM_ACE_CONST_REG_OFFSET	0xBECUL
+#define CC_AXIM_ACE_CONST_ARDOMAIN_BIT_SHIFT	0x0UL
+#define CC_AXIM_ACE_CONST_ARDOMAIN_BIT_SIZE	0x2UL
+#define CC_AXIM_ACE_CONST_AWDOMAIN_BIT_SHIFT	0x2UL
+#define CC_AXIM_ACE_CONST_AWDOMAIN_BIT_SIZE	0x2UL
+#define CC_AXIM_ACE_CONST_ARBAR_BIT_SHIFT	0x4UL
+#define CC_AXIM_ACE_CONST_ARBAR_BIT_SIZE	0x2UL
+#define CC_AXIM_ACE_CONST_AWBAR_BIT_SHIFT	0x6UL
+#define CC_AXIM_ACE_CONST_AWBAR_BIT_SIZE	0x2UL
+#define CC_AXIM_ACE_CONST_ARSNOOP_BIT_SHIFT	0x8UL
+#define CC_AXIM_ACE_CONST_ARSNOOP_BIT_SIZE	0x4UL
+#define CC_AXIM_ACE_CONST_AWSNOOP_NOT_ALIGNED_BIT_SHIFT	0xCUL
+#define CC_AXIM_ACE_CONST_AWSNOOP_NOT_ALIGNED_BIT_SIZE	0x3UL
+#define CC_AXIM_ACE_CONST_AWSNOOP_ALIGNED_BIT_SHIFT	0xFUL
+#define CC_AXIM_ACE_CONST_AWSNOOP_ALIGNED_BIT_SIZE	0x3UL
+#define CC_AXIM_ACE_CONST_AWADDR_NOT_MASKED_BIT_SHIFT	0x12UL
+#define CC_AXIM_ACE_CONST_AWADDR_NOT_MASKED_BIT_SIZE	0x7UL
+#define CC_AXIM_ACE_CONST_AWLEN_VAL_BIT_SHIFT	0x19UL
+#define CC_AXIM_ACE_CONST_AWLEN_VAL_BIT_SIZE	0x4UL
+#define CC_AXIM_CACHE_PARAMS_REG_OFFSET	0xBF0UL
+#define CC_AXIM_CACHE_PARAMS_AWCACHE_LAST_BIT_SHIFT	0x0UL
+#define CC_AXIM_CACHE_PARAMS_AWCACHE_LAST_BIT_SIZE	0x4UL
+#define CC_AXIM_CACHE_PARAMS_AWCACHE_BIT_SHIFT	0x4UL
+#define CC_AXIM_CACHE_PARAMS_AWCACHE_BIT_SIZE	0x4UL
+#define CC_AXIM_CACHE_PARAMS_ARCACHE_BIT_SHIFT	0x8UL
+#define CC_AXIM_CACHE_PARAMS_ARCACHE_BIT_SIZE	0x4UL
+#endif	// __CC_CRYS_KERNEL_H__
diff --git a/drivers/crypto/ccree/cc_lli_defs.h b/drivers/crypto/ccree/cc_lli_defs.h
new file mode 100644
index 000000000000..64b15ac9f1d3
--- /dev/null
+++ b/drivers/crypto/ccree/cc_lli_defs.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#ifndef _CC_LLI_DEFS_H_
+#define _CC_LLI_DEFS_H_
+
+#include <linux/types.h>
+
+/* Max DLLI size
+ *  AKA CC_DSCRPTR_QUEUE_WORD1_DIN_SIZE_BIT_SIZE
+ */
+#define DLLI_SIZE_BIT_SIZE	0x18
+
+#define CC_MAX_MLLI_ENTRY_SIZE 0xFFFF
+
+#define LLI_MAX_NUM_OF_DATA_ENTRIES 128
+#define LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES 4
+#define MLLI_TABLE_MIN_ALIGNMENT 4 /* 32 bit alignment */
+#define MAX_NUM_OF_BUFFERS_IN_MLLI 4
+#define MAX_NUM_OF_TOTAL_MLLI_ENTRIES \
+		(2 * LLI_MAX_NUM_OF_DATA_ENTRIES + \
+		 LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES)
+
+/* Size of entry */
+#define LLI_ENTRY_WORD_SIZE 2
+#define LLI_ENTRY_BYTE_SIZE (LLI_ENTRY_WORD_SIZE * sizeof(u32))
+
+/* Word0[31:0] = ADDR[31:0] */
+#define LLI_WORD0_OFFSET 0
+#define LLI_LADDR_BIT_OFFSET 0
+#define LLI_LADDR_BIT_SIZE 32
+/* Word1[31:16] = ADDR[47:32]; Word1[15:0] = SIZE */
+#define LLI_WORD1_OFFSET 1
+#define LLI_SIZE_BIT_OFFSET 0
+#define LLI_SIZE_BIT_SIZE 16
+#define LLI_HADDR_BIT_OFFSET 16
+#define LLI_HADDR_BIT_SIZE 16
+
+#define LLI_SIZE_MASK GENMASK((LLI_SIZE_BIT_SIZE - 1), LLI_SIZE_BIT_OFFSET)
+#define LLI_HADDR_MASK GENMASK( \
+			       (LLI_HADDR_BIT_OFFSET + LLI_HADDR_BIT_SIZE - 1),\
+				LLI_HADDR_BIT_OFFSET)
+
+static inline void cc_lli_set_addr(u32 *lli_p, dma_addr_t addr)
+{
+	lli_p[LLI_WORD0_OFFSET] = (addr & U32_MAX);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	lli_p[LLI_WORD1_OFFSET] &= ~LLI_HADDR_MASK;
+	lli_p[LLI_WORD1_OFFSET] |= FIELD_PREP(LLI_HADDR_MASK, (addr >> 32));
+#endif /* CONFIG_ARCH_DMA_ADDR_T_64BIT */
+}
+
+static inline void cc_lli_set_size(u32 *lli_p, u16 size)
+{
+	lli_p[LLI_WORD1_OFFSET] &= ~LLI_SIZE_MASK;
+	lli_p[LLI_WORD1_OFFSET] |= FIELD_PREP(LLI_SIZE_MASK, size);
+}
+
+#endif /*_CC_LLI_DEFS_H_*/
diff --git a/drivers/crypto/ccree/cc_pm.c b/drivers/crypto/ccree/cc_pm.c
new file mode 100644
index 000000000000..d990f472e89f
--- /dev/null
+++ b/drivers/crypto/ccree/cc_pm.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/pm_runtime.h>
+#include "cc_driver.h"
+#include "cc_buffer_mgr.h"
+#include "cc_request_mgr.h"
+#include "cc_sram_mgr.h"
+#include "cc_ivgen.h"
+#include "cc_hash.h"
+#include "cc_pm.h"
+
+#define POWER_DOWN_ENABLE 0x01
+#define POWER_DOWN_DISABLE 0x00
+
+const struct dev_pm_ops ccree_pm = {
+	SET_RUNTIME_PM_OPS(cc_pm_suspend, cc_pm_resume, NULL)
+};
+
+int cc_pm_suspend(struct device *dev)
+{
+	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
+	int rc;
+
+	dev_dbg(dev, "set HOST_POWER_DOWN_EN\n");
+	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_ENABLE);
+	rc = cc_suspend_req_queue(drvdata);
+	if (rc) {
+		dev_err(dev, "cc_suspend_req_queue (%x)\n", rc);
+		return rc;
+	}
+	fini_cc_regs(drvdata);
+	cc_clk_off(drvdata);
+	return 0;
+}
+
+int cc_pm_resume(struct device *dev)
+{
+	int rc;
+	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "unset HOST_POWER_DOWN_EN\n");
+	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_DISABLE);
+
+	rc = cc_clk_on(drvdata);
+	if (rc) {
+		dev_err(dev, "failed getting clock back on. We're toast.\n");
+		return rc;
+	}
+
+	rc = init_cc_regs(drvdata, false);
+	if (rc) {
+		dev_err(dev, "init_cc_regs (%x)\n", rc);
+		return rc;
+	}
+
+	rc = cc_resume_req_queue(drvdata);
+	if (rc) {
+		dev_err(dev, "cc_resume_req_queue (%x)\n", rc);
+		return rc;
+	}
+
+	/* must be after the queue resuming as it uses the HW queue*/
+	cc_init_hash_sram(drvdata);
+
+	cc_init_iv_sram(drvdata);
+	return 0;
+}
+
+int cc_pm_get(struct device *dev)
+{
+	int rc = 0;
+	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
+
+	if (cc_req_queue_suspended(drvdata))
+		rc = pm_runtime_get_sync(dev);
+	else
+		pm_runtime_get_noresume(dev);
+
+	return rc;
+}
+
+int cc_pm_put_suspend(struct device *dev)
+{
+	int rc = 0;
+	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
+
+	if (!cc_req_queue_suspended(drvdata)) {
+		pm_runtime_mark_last_busy(dev);
+		rc = pm_runtime_put_autosuspend(dev);
+	} else {
+		/* Something wrong happens*/
+		dev_err(dev, "request to suspend already suspended queue");
+		rc = -EBUSY;
+	}
+	return rc;
+}
+
+int cc_pm_init(struct cc_drvdata *drvdata)
+{
+	int rc = 0;
+	struct device *dev = drvdata_to_dev(drvdata);
+
+	/* must be before the enabling to avoid resdundent suspending */
+	pm_runtime_set_autosuspend_delay(dev, CC_SUSPEND_TIMEOUT);
+	pm_runtime_use_autosuspend(dev);
+	/* activate the PM module */
+	rc = pm_runtime_set_active(dev);
+	if (rc)
+		return rc;
+	/* enable the PM module*/
+	pm_runtime_enable(dev);
+
+	return rc;
+}
+
+void cc_pm_fini(struct cc_drvdata *drvdata)
+{
+	pm_runtime_disable(drvdata_to_dev(drvdata));
+}
diff --git a/drivers/crypto/ccree/cc_pm.h b/drivers/crypto/ccree/cc_pm.h
new file mode 100644
index 000000000000..020a5403c58b
--- /dev/null
+++ b/drivers/crypto/ccree/cc_pm.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+/* \file cc_pm.h
+ */
+
+#ifndef __CC_POWER_MGR_H__
+#define __CC_POWER_MGR_H__
+
+#include "cc_driver.h"
+
+#define CC_SUSPEND_TIMEOUT 3000
+
+#if defined(CONFIG_PM)
+
+extern const struct dev_pm_ops ccree_pm;
+
+int cc_pm_init(struct cc_drvdata *drvdata);
+void cc_pm_fini(struct cc_drvdata *drvdata);
+int cc_pm_suspend(struct device *dev);
+int cc_pm_resume(struct device *dev);
+int cc_pm_get(struct device *dev);
+int cc_pm_put_suspend(struct device *dev);
+
+#else
+
+static inline int cc_pm_init(struct cc_drvdata *drvdata)
+{
+	return 0;
+}
+
+static inline void cc_pm_fini(struct cc_drvdata *drvdata) {}
+
+static inline int cc_pm_suspend(struct device *dev)
+{
+	return 0;
+}
+
+static inline int cc_pm_resume(struct device *dev)
+{
+	return 0;
+}
+
+static inline int cc_pm_get(struct device *dev)
+{
+	return 0;
+}
+
+static inline int cc_pm_put_suspend(struct device *dev)
+{
+	return 0;
+}
+
+#endif
+
+#endif /*__POWER_MGR_H__*/
diff --git a/drivers/crypto/ccree/cc_request_mgr.c b/drivers/crypto/ccree/cc_request_mgr.c
new file mode 100644
index 000000000000..83a8aaae61c7
--- /dev/null
+++ b/drivers/crypto/ccree/cc_request_mgr.c
@@ -0,0 +1,711 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include <linux/kernel.h>
+#include "cc_driver.h"
+#include "cc_buffer_mgr.h"
+#include "cc_request_mgr.h"
+#include "cc_ivgen.h"
+#include "cc_pm.h"
+
+#define CC_MAX_POLL_ITER	10
+/* The highest descriptor count in used */
+#define CC_MAX_DESC_SEQ_LEN	23
+
+struct cc_req_mgr_handle {
+	/* Request manager resources */
+	unsigned int hw_queue_size; /* HW capability */
+	unsigned int min_free_hw_slots;
+	unsigned int max_used_sw_slots;
+	struct cc_crypto_req req_queue[MAX_REQUEST_QUEUE_SIZE];
+	u32 req_queue_head;
+	u32 req_queue_tail;
+	u32 axi_completed;
+	u32 q_free_slots;
+	/* This lock protects access to HW register
+	 * that must be single request at a time
+	 */
+	spinlock_t hw_lock;
+	struct cc_hw_desc compl_desc;
+	u8 *dummy_comp_buff;
+	dma_addr_t dummy_comp_buff_dma;
+
+	/* backlog queue */
+	struct list_head backlog;
+	unsigned int bl_len;
+	spinlock_t bl_lock; /* protect backlog queue */
+
+#ifdef COMP_IN_WQ
+	struct workqueue_struct *workq;
+	struct delayed_work compwork;
+#else
+	struct tasklet_struct comptask;
+#endif
+	bool is_runtime_suspended;
+};
+
+struct cc_bl_item {
+	struct cc_crypto_req creq;
+	struct cc_hw_desc desc[CC_MAX_DESC_SEQ_LEN];
+	unsigned int len;
+	struct list_head list;
+	bool notif;
+};
+
+static void comp_handler(unsigned long devarg);
+#ifdef COMP_IN_WQ
+static void comp_work_handler(struct work_struct *work);
+#endif
+
+void cc_req_mgr_fini(struct cc_drvdata *drvdata)
+{
+	struct cc_req_mgr_handle *req_mgr_h = drvdata->request_mgr_handle;
+	struct device *dev = drvdata_to_dev(drvdata);
+
+	if (!req_mgr_h)
+		return; /* Not allocated */
+
+	if (req_mgr_h->dummy_comp_buff_dma) {
+		dma_free_coherent(dev, sizeof(u32), req_mgr_h->dummy_comp_buff,
+				  req_mgr_h->dummy_comp_buff_dma);
+	}
+
+	dev_dbg(dev, "max_used_hw_slots=%d\n", (req_mgr_h->hw_queue_size -
+						req_mgr_h->min_free_hw_slots));
+	dev_dbg(dev, "max_used_sw_slots=%d\n", req_mgr_h->max_used_sw_slots);
+
+#ifdef COMP_IN_WQ
+	flush_workqueue(req_mgr_h->workq);
+	destroy_workqueue(req_mgr_h->workq);
+#else
+	/* Kill tasklet */
+	tasklet_kill(&req_mgr_h->comptask);
+#endif
+	kzfree(req_mgr_h);
+	drvdata->request_mgr_handle = NULL;
+}
+
+int cc_req_mgr_init(struct cc_drvdata *drvdata)
+{
+	struct cc_req_mgr_handle *req_mgr_h;
+	struct device *dev = drvdata_to_dev(drvdata);
+	int rc = 0;
+
+	req_mgr_h = kzalloc(sizeof(*req_mgr_h), GFP_KERNEL);
+	if (!req_mgr_h) {
+		rc = -ENOMEM;
+		goto req_mgr_init_err;
+	}
+
+	drvdata->request_mgr_handle = req_mgr_h;
+
+	spin_lock_init(&req_mgr_h->hw_lock);
+	spin_lock_init(&req_mgr_h->bl_lock);
+	INIT_LIST_HEAD(&req_mgr_h->backlog);
+
+#ifdef COMP_IN_WQ
+	dev_dbg(dev, "Initializing completion workqueue\n");
+	req_mgr_h->workq = create_singlethread_workqueue("ccree");
+	if (!req_mgr_h->workq) {
+		dev_err(dev, "Failed creating work queue\n");
+		rc = -ENOMEM;
+		goto req_mgr_init_err;
+	}
+	INIT_DELAYED_WORK(&req_mgr_h->compwork, comp_work_handler);
+#else
+	dev_dbg(dev, "Initializing completion tasklet\n");
+	tasklet_init(&req_mgr_h->comptask, comp_handler,
+		     (unsigned long)drvdata);
+#endif
+	req_mgr_h->hw_queue_size = cc_ioread(drvdata,
+					     CC_REG(DSCRPTR_QUEUE_SRAM_SIZE));
+	dev_dbg(dev, "hw_queue_size=0x%08X\n", req_mgr_h->hw_queue_size);
+	if (req_mgr_h->hw_queue_size < MIN_HW_QUEUE_SIZE) {
+		dev_err(dev, "Invalid HW queue size = %u (Min. required is %u)\n",
+			req_mgr_h->hw_queue_size, MIN_HW_QUEUE_SIZE);
+		rc = -ENOMEM;
+		goto req_mgr_init_err;
+	}
+	req_mgr_h->min_free_hw_slots = req_mgr_h->hw_queue_size;
+	req_mgr_h->max_used_sw_slots = 0;
+
+	/* Allocate DMA word for "dummy" completion descriptor use */
+	req_mgr_h->dummy_comp_buff =
+		dma_alloc_coherent(dev, sizeof(u32),
+				   &req_mgr_h->dummy_comp_buff_dma,
+				   GFP_KERNEL);
+	if (!req_mgr_h->dummy_comp_buff) {
+		dev_err(dev, "Not enough memory to allocate DMA (%zu) dropped buffer\n",
+			sizeof(u32));
+		rc = -ENOMEM;
+		goto req_mgr_init_err;
+	}
+
+	/* Init. "dummy" completion descriptor */
+	hw_desc_init(&req_mgr_h->compl_desc);
+	set_din_const(&req_mgr_h->compl_desc, 0, sizeof(u32));
+	set_dout_dlli(&req_mgr_h->compl_desc, req_mgr_h->dummy_comp_buff_dma,
+		      sizeof(u32), NS_BIT, 1);
+	set_flow_mode(&req_mgr_h->compl_desc, BYPASS);
+	set_queue_last_ind(drvdata, &req_mgr_h->compl_desc);
+
+	return 0;
+
+req_mgr_init_err:
+	cc_req_mgr_fini(drvdata);
+	return rc;
+}
+
+static void enqueue_seq(struct cc_drvdata *drvdata, struct cc_hw_desc seq[],
+			unsigned int seq_len)
+{
+	int i, w;
+	void __iomem *reg = drvdata->cc_base + CC_REG(DSCRPTR_QUEUE_WORD0);
+	struct device *dev = drvdata_to_dev(drvdata);
+
+	/*
+	 * We do indeed write all 6 command words to the same
+	 * register. The HW supports this.
+	 */
+
+	for (i = 0; i < seq_len; i++) {
+		for (w = 0; w <= 5; w++)
+			writel_relaxed(seq[i].word[w], reg);
+
+		if (cc_dump_desc)
+			dev_dbg(dev, "desc[%02d]: 0x%08X 0x%08X 0x%08X 0x%08X 0x%08X 0x%08X\n",
+				i, seq[i].word[0], seq[i].word[1],
+				seq[i].word[2], seq[i].word[3],
+				seq[i].word[4], seq[i].word[5]);
+	}
+}
+
+/*!
+ * Completion will take place if and only if user requested completion
+ * by cc_send_sync_request().
+ *
+ * \param dev
+ * \param dx_compl_h The completion event to signal
+ */
+static void request_mgr_complete(struct device *dev, void *dx_compl_h,
+				 int dummy)
+{
+	struct completion *this_compl = dx_compl_h;
+
+	complete(this_compl);
+}
+
+static int cc_queues_status(struct cc_drvdata *drvdata,
+			    struct cc_req_mgr_handle *req_mgr_h,
+			    unsigned int total_seq_len)
+{
+	unsigned long poll_queue;
+	struct device *dev = drvdata_to_dev(drvdata);
+
+	/* SW queue is checked only once as it will not
+	 * be chaned during the poll because the spinlock_bh
+	 * is held by the thread
+	 */
+	if (((req_mgr_h->req_queue_head + 1) & (MAX_REQUEST_QUEUE_SIZE - 1)) ==
+	    req_mgr_h->req_queue_tail) {
+		dev_err(dev, "SW FIFO is full. req_queue_head=%d sw_fifo_len=%d\n",
+			req_mgr_h->req_queue_head, MAX_REQUEST_QUEUE_SIZE);
+		return -ENOSPC;
+	}
+
+	if (req_mgr_h->q_free_slots >= total_seq_len)
+		return 0;
+
+	/* Wait for space in HW queue. Poll constant num of iterations. */
+	for (poll_queue = 0; poll_queue < CC_MAX_POLL_ITER ; poll_queue++) {
+		req_mgr_h->q_free_slots =
+			cc_ioread(drvdata, CC_REG(DSCRPTR_QUEUE_CONTENT));
+		if (req_mgr_h->q_free_slots < req_mgr_h->min_free_hw_slots)
+			req_mgr_h->min_free_hw_slots = req_mgr_h->q_free_slots;
+
+		if (req_mgr_h->q_free_slots >= total_seq_len) {
+			/* If there is enough place return */
+			return 0;
+		}
+
+		dev_dbg(dev, "HW FIFO is full. q_free_slots=%d total_seq_len=%d\n",
+			req_mgr_h->q_free_slots, total_seq_len);
+	}
+	/* No room in the HW queue try again later */
+	dev_dbg(dev, "HW FIFO full, timeout. req_queue_head=%d sw_fifo_len=%d q_free_slots=%d total_seq_len=%d\n",
+		req_mgr_h->req_queue_head, MAX_REQUEST_QUEUE_SIZE,
+		req_mgr_h->q_free_slots, total_seq_len);
+	return -ENOSPC;
+}
+
+/*!
+ * Enqueue caller request to crypto hardware.
+ * Need to be called with HW lock held and PM running
+ *
+ * \param drvdata
+ * \param cc_req The request to enqueue
+ * \param desc The crypto sequence
+ * \param len The crypto sequence length
+ * \param add_comp If "true": add an artificial dout DMA to mark completion
+ *
+ * \return int Returns -EINPROGRESS or error code
+ */
+static int cc_do_send_request(struct cc_drvdata *drvdata,
+			      struct cc_crypto_req *cc_req,
+			      struct cc_hw_desc *desc, unsigned int len,
+				bool add_comp, bool ivgen)
+{
+	struct cc_req_mgr_handle *req_mgr_h = drvdata->request_mgr_handle;
+	unsigned int used_sw_slots;
+	unsigned int iv_seq_len = 0;
+	unsigned int total_seq_len = len; /*initial sequence length*/
+	struct cc_hw_desc iv_seq[CC_IVPOOL_SEQ_LEN];
+	struct device *dev = drvdata_to_dev(drvdata);
+	int rc;
+
+	if (ivgen) {
+		dev_dbg(dev, "Acquire IV from pool into %d DMA addresses %pad, %pad, %pad, IV-size=%u\n",
+			cc_req->ivgen_dma_addr_len,
+			&cc_req->ivgen_dma_addr[0],
+			&cc_req->ivgen_dma_addr[1],
+			&cc_req->ivgen_dma_addr[2],
+			cc_req->ivgen_size);
+
+		/* Acquire IV from pool */
+		rc = cc_get_iv(drvdata, cc_req->ivgen_dma_addr,
+			       cc_req->ivgen_dma_addr_len,
+			       cc_req->ivgen_size, iv_seq, &iv_seq_len);
+
+		if (rc) {
+			dev_err(dev, "Failed to generate IV (rc=%d)\n", rc);
+			return rc;
+		}
+
+		total_seq_len += iv_seq_len;
+	}
+
+	used_sw_slots = ((req_mgr_h->req_queue_head -
+			  req_mgr_h->req_queue_tail) &
+			 (MAX_REQUEST_QUEUE_SIZE - 1));
+	if (used_sw_slots > req_mgr_h->max_used_sw_slots)
+		req_mgr_h->max_used_sw_slots = used_sw_slots;
+
+	/* Enqueue request - must be locked with HW lock*/
+	req_mgr_h->req_queue[req_mgr_h->req_queue_head] = *cc_req;
+	req_mgr_h->req_queue_head = (req_mgr_h->req_queue_head + 1) &
+				    (MAX_REQUEST_QUEUE_SIZE - 1);
+	/* TODO: Use circ_buf.h ? */
+
+	dev_dbg(dev, "Enqueue request head=%u\n", req_mgr_h->req_queue_head);
+
+	/*
+	 * We are about to push command to the HW via the command registers
+	 * that may refernece hsot memory. We need to issue a memory barrier
+	 * to make sure there are no outstnading memory writes
+	 */
+	wmb();
+
+	/* STAT_PHASE_4: Push sequence */
+	if (ivgen)
+		enqueue_seq(drvdata, iv_seq, iv_seq_len);
+
+	enqueue_seq(drvdata, desc, len);
+
+	if (add_comp) {
+		enqueue_seq(drvdata, &req_mgr_h->compl_desc, 1);
+		total_seq_len++;
+	}
+
+	if (req_mgr_h->q_free_slots < total_seq_len) {
+		/* This situation should never occur. Maybe indicating problem
+		 * with resuming power. Set the free slot count to 0 and hope
+		 * for the best.
+		 */
+		dev_err(dev, "HW free slot count mismatch.");
+		req_mgr_h->q_free_slots = 0;
+	} else {
+		/* Update the free slots in HW queue */
+		req_mgr_h->q_free_slots -= total_seq_len;
+	}
+
+	/* Operation still in process */
+	return -EINPROGRESS;
+}
+
+static void cc_enqueue_backlog(struct cc_drvdata *drvdata,
+			       struct cc_bl_item *bli)
+{
+	struct cc_req_mgr_handle *mgr = drvdata->request_mgr_handle;
+
+	spin_lock_bh(&mgr->bl_lock);
+	list_add_tail(&bli->list, &mgr->backlog);
+	++mgr->bl_len;
+	spin_unlock_bh(&mgr->bl_lock);
+	tasklet_schedule(&mgr->comptask);
+}
+
+static void cc_proc_backlog(struct cc_drvdata *drvdata)
+{
+	struct cc_req_mgr_handle *mgr = drvdata->request_mgr_handle;
+	struct cc_bl_item *bli;
+	struct cc_crypto_req *creq;
+	struct crypto_async_request *req;
+	bool ivgen;
+	unsigned int total_len;
+	struct device *dev = drvdata_to_dev(drvdata);
+	int rc;
+
+	spin_lock(&mgr->bl_lock);
+
+	while (mgr->bl_len) {
+		bli = list_first_entry(&mgr->backlog, struct cc_bl_item, list);
+		spin_unlock(&mgr->bl_lock);
+
+		creq = &bli->creq;
+		req = (struct crypto_async_request *)creq->user_arg;
+
+		/*
+		 * Notify the request we're moving out of the backlog
+		 * but only if we haven't done so already.
+		 */
+		if (!bli->notif) {
+			req->complete(req, -EINPROGRESS);
+			bli->notif = true;
+		}
+
+		ivgen = !!creq->ivgen_dma_addr_len;
+		total_len = bli->len + (ivgen ? CC_IVPOOL_SEQ_LEN : 0);
+
+		spin_lock(&mgr->hw_lock);
+
+		rc = cc_queues_status(drvdata, mgr, total_len);
+		if (rc) {
+			/*
+			 * There is still not room in the FIFO for
+			 * this request. Bail out. We'll return here
+			 * on the next completion irq.
+			 */
+			spin_unlock(&mgr->hw_lock);
+			return;
+		}
+
+		rc = cc_do_send_request(drvdata, &bli->creq, bli->desc,
+					bli->len, false, ivgen);
+
+		spin_unlock(&mgr->hw_lock);
+
+		if (rc != -EINPROGRESS) {
+			cc_pm_put_suspend(dev);
+			creq->user_cb(dev, req, rc);
+		}
+
+		/* Remove ourselves from the backlog list */
+		spin_lock(&mgr->bl_lock);
+		list_del(&bli->list);
+		--mgr->bl_len;
+	}
+
+	spin_unlock(&mgr->bl_lock);
+}
+
+int cc_send_request(struct cc_drvdata *drvdata, struct cc_crypto_req *cc_req,
+		    struct cc_hw_desc *desc, unsigned int len,
+		    struct crypto_async_request *req)
+{
+	int rc;
+	struct cc_req_mgr_handle *mgr = drvdata->request_mgr_handle;
+	bool ivgen = !!cc_req->ivgen_dma_addr_len;
+	unsigned int total_len = len + (ivgen ? CC_IVPOOL_SEQ_LEN : 0);
+	struct device *dev = drvdata_to_dev(drvdata);
+	bool backlog_ok = req->flags & CRYPTO_TFM_REQ_MAY_BACKLOG;
+	gfp_t flags = cc_gfp_flags(req);
+	struct cc_bl_item *bli;
+
+	rc = cc_pm_get(dev);
+	if (rc) {
+		dev_err(dev, "ssi_power_mgr_runtime_get returned %x\n", rc);
+		return rc;
+	}
+
+	spin_lock_bh(&mgr->hw_lock);
+	rc = cc_queues_status(drvdata, mgr, total_len);
+
+#ifdef CC_DEBUG_FORCE_BACKLOG
+	if (backlog_ok)
+		rc = -ENOSPC;
+#endif /* CC_DEBUG_FORCE_BACKLOG */
+
+	if (rc == -ENOSPC && backlog_ok) {
+		spin_unlock_bh(&mgr->hw_lock);
+
+		bli = kmalloc(sizeof(*bli), flags);
+		if (!bli) {
+			cc_pm_put_suspend(dev);
+			return -ENOMEM;
+		}
+
+		memcpy(&bli->creq, cc_req, sizeof(*cc_req));
+		memcpy(&bli->desc, desc, len * sizeof(*desc));
+		bli->len = len;
+		bli->notif = false;
+		cc_enqueue_backlog(drvdata, bli);
+		return -EBUSY;
+	}
+
+	if (!rc)
+		rc = cc_do_send_request(drvdata, cc_req, desc, len, false,
+					ivgen);
+
+	spin_unlock_bh(&mgr->hw_lock);
+	return rc;
+}
+
+int cc_send_sync_request(struct cc_drvdata *drvdata,
+			 struct cc_crypto_req *cc_req, struct cc_hw_desc *desc,
+			 unsigned int len)
+{
+	int rc;
+	struct device *dev = drvdata_to_dev(drvdata);
+	struct cc_req_mgr_handle *mgr = drvdata->request_mgr_handle;
+
+	init_completion(&cc_req->seq_compl);
+	cc_req->user_cb = request_mgr_complete;
+	cc_req->user_arg = &cc_req->seq_compl;
+
+	rc = cc_pm_get(dev);
+	if (rc) {
+		dev_err(dev, "ssi_power_mgr_runtime_get returned %x\n", rc);
+		return rc;
+	}
+
+	while (true) {
+		spin_lock_bh(&mgr->hw_lock);
+		rc = cc_queues_status(drvdata, mgr, len + 1);
+
+		if (!rc)
+			break;
+
+		spin_unlock_bh(&mgr->hw_lock);
+		if (rc != -EAGAIN) {
+			cc_pm_put_suspend(dev);
+			return rc;
+		}
+		wait_for_completion_interruptible(&drvdata->hw_queue_avail);
+		reinit_completion(&drvdata->hw_queue_avail);
+	}
+
+	rc = cc_do_send_request(drvdata, cc_req, desc, len, true, false);
+	spin_unlock_bh(&mgr->hw_lock);
+
+	if (rc != -EINPROGRESS) {
+		cc_pm_put_suspend(dev);
+		return rc;
+	}
+
+	wait_for_completion(&cc_req->seq_compl);
+	return 0;
+}
+
+/*!
+ * Enqueue caller request to crypto hardware during init process.
+ * assume this function is not called in middle of a flow,
+ * since we set QUEUE_LAST_IND flag in the last descriptor.
+ *
+ * \param drvdata
+ * \param desc The crypto sequence
+ * \param len The crypto sequence length
+ *
+ * \return int Returns "0" upon success
+ */
+int send_request_init(struct cc_drvdata *drvdata, struct cc_hw_desc *desc,
+		      unsigned int len)
+{
+	struct cc_req_mgr_handle *req_mgr_h = drvdata->request_mgr_handle;
+	unsigned int total_seq_len = len; /*initial sequence length*/
+	int rc = 0;
+
+	/* Wait for space in HW and SW FIFO. Poll for as much as FIFO_TIMEOUT.
+	 */
+	rc = cc_queues_status(drvdata, req_mgr_h, total_seq_len);
+	if (rc)
+		return rc;
+
+	set_queue_last_ind(drvdata, &desc[(len - 1)]);
+
+	/*
+	 * We are about to push command to the HW via the command registers
+	 * that may refernece hsot memory. We need to issue a memory barrier
+	 * to make sure there are no outstnading memory writes
+	 */
+	wmb();
+	enqueue_seq(drvdata, desc, len);
+
+	/* Update the free slots in HW queue */
+	req_mgr_h->q_free_slots =
+		cc_ioread(drvdata, CC_REG(DSCRPTR_QUEUE_CONTENT));
+
+	return 0;
+}
+
+void complete_request(struct cc_drvdata *drvdata)
+{
+	struct cc_req_mgr_handle *request_mgr_handle =
+						drvdata->request_mgr_handle;
+
+	complete(&drvdata->hw_queue_avail);
+#ifdef COMP_IN_WQ
+	queue_delayed_work(request_mgr_handle->workq,
+			   &request_mgr_handle->compwork, 0);
+#else
+	tasklet_schedule(&request_mgr_handle->comptask);
+#endif
+}
+
+#ifdef COMP_IN_WQ
+static void comp_work_handler(struct work_struct *work)
+{
+	struct cc_drvdata *drvdata =
+		container_of(work, struct cc_drvdata, compwork.work);
+
+	comp_handler((unsigned long)drvdata);
+}
+#endif
+
+static void proc_completions(struct cc_drvdata *drvdata)
+{
+	struct cc_crypto_req *cc_req;
+	struct device *dev = drvdata_to_dev(drvdata);
+	struct cc_req_mgr_handle *request_mgr_handle =
+						drvdata->request_mgr_handle;
+	unsigned int *tail = &request_mgr_handle->req_queue_tail;
+	unsigned int *head = &request_mgr_handle->req_queue_head;
+
+	while (request_mgr_handle->axi_completed) {
+		request_mgr_handle->axi_completed--;
+
+		/* Dequeue request */
+		if (*head == *tail) {
+			/* We are supposed to handle a completion but our
+			 * queue is empty. This is not normal. Return and
+			 * hope for the best.
+			 */
+			dev_err(dev, "Request queue is empty head == tail %u\n",
+				*head);
+			break;
+		}
+
+		cc_req = &request_mgr_handle->req_queue[*tail];
+
+		if (cc_req->user_cb)
+			cc_req->user_cb(dev, cc_req->user_arg, 0);
+		*tail = (*tail + 1) & (MAX_REQUEST_QUEUE_SIZE - 1);
+		dev_dbg(dev, "Dequeue request tail=%u\n", *tail);
+		dev_dbg(dev, "Request completed. axi_completed=%d\n",
+			request_mgr_handle->axi_completed);
+		cc_pm_put_suspend(dev);
+	}
+}
+
+static inline u32 cc_axi_comp_count(struct cc_drvdata *drvdata)
+{
+	return FIELD_GET(AXIM_MON_COMP_VALUE,
+			 cc_ioread(drvdata, drvdata->axim_mon_offset));
+}
+
+/* Deferred service handler, run as interrupt-fired tasklet */
+static void comp_handler(unsigned long devarg)
+{
+	struct cc_drvdata *drvdata = (struct cc_drvdata *)devarg;
+	struct cc_req_mgr_handle *request_mgr_handle =
+						drvdata->request_mgr_handle;
+
+	u32 irq;
+
+	irq = (drvdata->irq & CC_COMP_IRQ_MASK);
+
+	if (irq & CC_COMP_IRQ_MASK) {
+		/* To avoid the interrupt from firing as we unmask it,
+		 * we clear it now
+		 */
+		cc_iowrite(drvdata, CC_REG(HOST_ICR), CC_COMP_IRQ_MASK);
+
+		/* Avoid race with above clear: Test completion counter
+		 * once more
+		 */
+		request_mgr_handle->axi_completed +=
+				cc_axi_comp_count(drvdata);
+
+		while (request_mgr_handle->axi_completed) {
+			do {
+				proc_completions(drvdata);
+				/* At this point (after proc_completions()),
+				 * request_mgr_handle->axi_completed is 0.
+				 */
+				request_mgr_handle->axi_completed =
+						cc_axi_comp_count(drvdata);
+			} while (request_mgr_handle->axi_completed > 0);
+
+			cc_iowrite(drvdata, CC_REG(HOST_ICR),
+				   CC_COMP_IRQ_MASK);
+
+			request_mgr_handle->axi_completed +=
+					cc_axi_comp_count(drvdata);
+		}
+	}
+	/* after verifing that there is nothing to do,
+	 * unmask AXI completion interrupt
+	 */
+	cc_iowrite(drvdata, CC_REG(HOST_IMR),
+		   cc_ioread(drvdata, CC_REG(HOST_IMR)) & ~irq);
+
+	cc_proc_backlog(drvdata);
+}
+
+/*
+ * resume the queue configuration - no need to take the lock as this happens
+ * inside the spin lock protection
+ */
+#if defined(CONFIG_PM)
+int cc_resume_req_queue(struct cc_drvdata *drvdata)
+{
+	struct cc_req_mgr_handle *request_mgr_handle =
+		drvdata->request_mgr_handle;
+
+	spin_lock_bh(&request_mgr_handle->hw_lock);
+	request_mgr_handle->is_runtime_suspended = false;
+	spin_unlock_bh(&request_mgr_handle->hw_lock);
+
+	return 0;
+}
+
+/*
+ * suspend the queue configuration. Since it is used for the runtime suspend
+ * only verify that the queue can be suspended.
+ */
+int cc_suspend_req_queue(struct cc_drvdata *drvdata)
+{
+	struct cc_req_mgr_handle *request_mgr_handle =
+						drvdata->request_mgr_handle;
+
+	/* lock the send_request */
+	spin_lock_bh(&request_mgr_handle->hw_lock);
+	if (request_mgr_handle->req_queue_head !=
+	    request_mgr_handle->req_queue_tail) {
+		spin_unlock_bh(&request_mgr_handle->hw_lock);
+		return -EBUSY;
+	}
+	request_mgr_handle->is_runtime_suspended = true;
+	spin_unlock_bh(&request_mgr_handle->hw_lock);
+
+	return 0;
+}
+
+bool cc_req_queue_suspended(struct cc_drvdata *drvdata)
+{
+	struct cc_req_mgr_handle *request_mgr_handle =
+						drvdata->request_mgr_handle;
+
+	return	request_mgr_handle->is_runtime_suspended;
+}
+
+#endif
diff --git a/drivers/crypto/ccree/cc_request_mgr.h b/drivers/crypto/ccree/cc_request_mgr.h
new file mode 100644
index 000000000000..573cb97af085
--- /dev/null
+++ b/drivers/crypto/ccree/cc_request_mgr.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+/* \file cc_request_mgr.h
+ * Request Manager
+ */
+
+#ifndef __REQUEST_MGR_H__
+#define __REQUEST_MGR_H__
+
+#include "cc_hw_queue_defs.h"
+
+int cc_req_mgr_init(struct cc_drvdata *drvdata);
+
+/*!
+ * Enqueue caller request to crypto hardware.
+ *
+ * \param drvdata
+ * \param cc_req The request to enqueue
+ * \param desc The crypto sequence
+ * \param len The crypto sequence length
+ * \param is_dout If "true": completion is handled by the caller
+ *	  If "false": this function adds a dummy descriptor completion
+ *	  and waits upon completion signal.
+ *
+ * \return int Returns -EINPROGRESS or error
+ */
+int cc_send_request(struct cc_drvdata *drvdata, struct cc_crypto_req *cc_req,
+		    struct cc_hw_desc *desc, unsigned int len,
+		    struct crypto_async_request *req);
+
+int cc_send_sync_request(struct cc_drvdata *drvdata,
+			 struct cc_crypto_req *cc_req, struct cc_hw_desc *desc,
+			 unsigned int len);
+
+int send_request_init(struct cc_drvdata *drvdata, struct cc_hw_desc *desc,
+		      unsigned int len);
+
+void complete_request(struct cc_drvdata *drvdata);
+
+void cc_req_mgr_fini(struct cc_drvdata *drvdata);
+
+#if defined(CONFIG_PM)
+int cc_resume_req_queue(struct cc_drvdata *drvdata);
+
+int cc_suspend_req_queue(struct cc_drvdata *drvdata);
+
+bool cc_req_queue_suspended(struct cc_drvdata *drvdata);
+#endif
+
+#endif /*__REQUEST_MGR_H__*/
diff --git a/drivers/crypto/ccree/cc_sram_mgr.c b/drivers/crypto/ccree/cc_sram_mgr.c
new file mode 100644
index 000000000000..c8c276f6dee9
--- /dev/null
+++ b/drivers/crypto/ccree/cc_sram_mgr.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#include "cc_driver.h"
+#include "cc_sram_mgr.h"
+
+/**
+ * struct cc_sram_ctx -Internal RAM context manager
+ * @sram_free_offset:   the offset to the non-allocated area
+ */
+struct cc_sram_ctx {
+	cc_sram_addr_t sram_free_offset;
+};
+
+/**
+ * cc_sram_mgr_fini() - Cleanup SRAM pool.
+ *
+ * @drvdata: Associated device driver context
+ */
+void cc_sram_mgr_fini(struct cc_drvdata *drvdata)
+{
+	/* Free "this" context */
+	kfree(drvdata->sram_mgr_handle);
+}
+
+/**
+ * cc_sram_mgr_init() - Initializes SRAM pool.
+ *      The pool starts right at the beginning of SRAM.
+ *      Returns zero for success, negative value otherwise.
+ *
+ * @drvdata: Associated device driver context
+ */
+int cc_sram_mgr_init(struct cc_drvdata *drvdata)
+{
+	struct cc_sram_ctx *ctx;
+	dma_addr_t start = 0;
+	struct device *dev = drvdata_to_dev(drvdata);
+
+	if (drvdata->hw_rev < CC_HW_REV_712) {
+		/* Pool starts after ROM bytes */
+		start = (dma_addr_t)cc_ioread(drvdata,
+					      CC_REG(HOST_SEP_SRAM_THRESHOLD));
+
+		if ((start & 0x3) != 0) {
+			dev_err(dev, "Invalid SRAM offset %pad\n", &start);
+			return -EINVAL;
+		}
+	}
+
+	/* Allocate "this" context */
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->sram_free_offset = start;
+	drvdata->sram_mgr_handle = ctx;
+
+	return 0;
+}
+
+/*!
+ * Allocated buffer from SRAM pool.
+ * Note: Caller is responsible to free the LAST allocated buffer.
+ * This function does not taking care of any fragmentation may occur
+ * by the order of calls to alloc/free.
+ *
+ * \param drvdata
+ * \param size The requested bytes to allocate
+ */
+cc_sram_addr_t cc_sram_alloc(struct cc_drvdata *drvdata, u32 size)
+{
+	struct cc_sram_ctx *smgr_ctx = drvdata->sram_mgr_handle;
+	struct device *dev = drvdata_to_dev(drvdata);
+	cc_sram_addr_t p;
+
+	if ((size & 0x3)) {
+		dev_err(dev, "Requested buffer size (%u) is not multiple of 4",
+			size);
+		return NULL_SRAM_ADDR;
+	}
+	if (size > (CC_CC_SRAM_SIZE - smgr_ctx->sram_free_offset)) {
+		dev_err(dev, "Not enough space to allocate %u B (at offset %llu)\n",
+			size, smgr_ctx->sram_free_offset);
+		return NULL_SRAM_ADDR;
+	}
+
+	p = smgr_ctx->sram_free_offset;
+	smgr_ctx->sram_free_offset += size;
+	dev_dbg(dev, "Allocated %u B @ %u\n", size, (unsigned int)p);
+	return p;
+}
+
+/**
+ * cc_set_sram_desc() - Create const descriptors sequence to
+ *	set values in given array into SRAM.
+ * Note: each const value can't exceed word size.
+ *
+ * @src:	  A pointer to array of words to set as consts.
+ * @dst:	  The target SRAM buffer to set into
+ * @nelements:	  The number of words in "src" array
+ * @seq:	  A pointer to the given IN/OUT descriptor sequence
+ * @seq_len:	  A pointer to the given IN/OUT sequence length
+ */
+void cc_set_sram_desc(const u32 *src, cc_sram_addr_t dst,
+		      unsigned int nelement, struct cc_hw_desc *seq,
+		      unsigned int *seq_len)
+{
+	u32 i;
+	unsigned int idx = *seq_len;
+
+	for (i = 0; i < nelement; i++, idx++) {
+		hw_desc_init(&seq[idx]);
+		set_din_const(&seq[idx], src[i], sizeof(u32));
+		set_dout_sram(&seq[idx], dst + (i * sizeof(u32)), sizeof(u32));
+		set_flow_mode(&seq[idx], BYPASS);
+	}
+
+	*seq_len = idx;
+}
diff --git a/drivers/crypto/ccree/cc_sram_mgr.h b/drivers/crypto/ccree/cc_sram_mgr.h
new file mode 100644
index 000000000000..d48649fb3323
--- /dev/null
+++ b/drivers/crypto/ccree/cc_sram_mgr.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+
+#ifndef __CC_SRAM_MGR_H__
+#define __CC_SRAM_MGR_H__
+
+#ifndef CC_CC_SRAM_SIZE
+#define CC_CC_SRAM_SIZE 4096
+#endif
+
+struct cc_drvdata;
+
+/**
+ * Address (offset) within CC internal SRAM
+ */
+
+typedef u64 cc_sram_addr_t;
+
+#define NULL_SRAM_ADDR ((cc_sram_addr_t)-1)
+
+/*!
+ * Initializes SRAM pool.
+ * The first X bytes of SRAM are reserved for ROM usage, hence, pool
+ * starts right after X bytes.
+ *
+ * \param drvdata
+ *
+ * \return int Zero for success, negative value otherwise.
+ */
+int cc_sram_mgr_init(struct cc_drvdata *drvdata);
+
+/*!
+ * Uninits SRAM pool.
+ *
+ * \param drvdata
+ */
+void cc_sram_mgr_fini(struct cc_drvdata *drvdata);
+
+/*!
+ * Allocated buffer from SRAM pool.
+ * Note: Caller is responsible to free the LAST allocated buffer.
+ * This function does not taking care of any fragmentation may occur
+ * by the order of calls to alloc/free.
+ *
+ * \param drvdata
+ * \param size The requested bytes to allocate
+ */
+cc_sram_addr_t cc_sram_alloc(struct cc_drvdata *drvdata, u32 size);
+
+/**
+ * cc_set_sram_desc() - Create const descriptors sequence to
+ *	set values in given array into SRAM.
+ * Note: each const value can't exceed word size.
+ *
+ * @src:	  A pointer to array of words to set as consts.
+ * @dst:	  The target SRAM buffer to set into
+ * @nelements:	  The number of words in "src" array
+ * @seq:	  A pointer to the given IN/OUT descriptor sequence
+ * @seq_len:	  A pointer to the given IN/OUT sequence length
+ */
+void cc_set_sram_desc(const u32 *src, cc_sram_addr_t dst,
+		      unsigned int nelement, struct cc_hw_desc *seq,
+		      unsigned int *seq_len);
+
+#endif /*__CC_SRAM_MGR_H__*/
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 34a02d690548..59fe6631e73e 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -131,6 +131,11 @@ static inline int is_ofld_imm(const struct sk_buff *skb)
 	return (skb->len <= SGE_MAX_WR_LEN);
 }
 
+static inline void chcr_init_hctx_per_wr(struct chcr_ahash_req_ctx *reqctx)
+{
+	memset(&reqctx->hctx_wr, 0, sizeof(struct chcr_hctx_per_wr));
+}
+
 static int sg_nents_xlen(struct scatterlist *sg, unsigned int reqlen,
 			 unsigned int entlen,
 			 unsigned int skip)
@@ -160,41 +165,6 @@ static int sg_nents_xlen(struct scatterlist *sg, unsigned int reqlen,
 	return nents;
 }
 
-static inline void chcr_handle_ahash_resp(struct ahash_request *req,
-					  unsigned char *input,
-					  int err)
-{
-	struct chcr_ahash_req_ctx *reqctx = ahash_request_ctx(req);
-	int digestsize, updated_digestsize;
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct uld_ctx *u_ctx = ULD_CTX(h_ctx(tfm));
-
-	if (input == NULL)
-		goto out;
-	digestsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req));
-	if (reqctx->is_sg_map)
-		chcr_hash_dma_unmap(&u_ctx->lldi.pdev->dev, req);
-	if (reqctx->dma_addr)
-		dma_unmap_single(&u_ctx->lldi.pdev->dev, reqctx->dma_addr,
-				 reqctx->dma_len, DMA_TO_DEVICE);
-	reqctx->dma_addr = 0;
-	updated_digestsize = digestsize;
-	if (digestsize == SHA224_DIGEST_SIZE)
-		updated_digestsize = SHA256_DIGEST_SIZE;
-	else if (digestsize == SHA384_DIGEST_SIZE)
-		updated_digestsize = SHA512_DIGEST_SIZE;
-	if (reqctx->result == 1) {
-		reqctx->result = 0;
-		memcpy(req->result, input + sizeof(struct cpl_fw6_pld),
-		       digestsize);
-	} else {
-		memcpy(reqctx->partial_hash, input + sizeof(struct cpl_fw6_pld),
-		       updated_digestsize);
-	}
-out:
-	req->base.complete(&req->base, err);
-}
-
 static inline int get_aead_subtype(struct crypto_aead *aead)
 {
 	struct aead_alg *alg = crypto_aead_alg(aead);
@@ -247,34 +217,6 @@ static inline void chcr_handle_aead_resp(struct aead_request *req,
 	req->base.complete(&req->base, err);
 }
 
-/*
- *	chcr_handle_resp - Unmap the DMA buffers associated with the request
- *	@req: crypto request
- */
-int chcr_handle_resp(struct crypto_async_request *req, unsigned char *input,
-			 int err)
-{
-	struct crypto_tfm *tfm = req->tfm;
-	struct chcr_context *ctx = crypto_tfm_ctx(tfm);
-	struct adapter *adap = padap(ctx->dev);
-
-	switch (tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK) {
-	case CRYPTO_ALG_TYPE_AEAD:
-		chcr_handle_aead_resp(aead_request_cast(req), input, err);
-		break;
-
-	case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		 err = chcr_handle_cipher_resp(ablkcipher_request_cast(req),
-					       input, err);
-		break;
-
-	case CRYPTO_ALG_TYPE_AHASH:
-		chcr_handle_ahash_resp(ahash_request_cast(req), input, err);
-		}
-	atomic_inc(&adap->chcr_stats.complete);
-	return err;
-}
-
 static void get_aes_decrypt_key(unsigned char *dec_key,
 				       const unsigned char *key,
 				       unsigned int keylength)
@@ -563,7 +505,6 @@ static void  ulptx_walk_add_sg(struct ulptx_walk *walk,
 
 	if (!len)
 		return;
-
 	while (sg && skip) {
 		if (sg_dma_len(sg) <= skip) {
 			skip -= sg_dma_len(sg);
@@ -653,6 +594,35 @@ static int generate_copy_rrkey(struct ablk_ctx *ablkctx,
 	}
 	return 0;
 }
+
+static int chcr_hash_ent_in_wr(struct scatterlist *src,
+			     unsigned int minsg,
+			     unsigned int space,
+			     unsigned int srcskip)
+{
+	int srclen = 0;
+	int srcsg = minsg;
+	int soffset = 0, sless;
+
+	if (sg_dma_len(src) == srcskip) {
+		src = sg_next(src);
+		srcskip = 0;
+	}
+	while (src && space > (sgl_ent_len[srcsg + 1])) {
+		sless = min_t(unsigned int, sg_dma_len(src) - soffset -	srcskip,
+							CHCR_SRC_SG_SIZE);
+		srclen += sless;
+		soffset += sless;
+		srcsg++;
+		if (sg_dma_len(src) == (soffset + srcskip)) {
+			src = sg_next(src);
+			soffset = 0;
+			srcskip = 0;
+		}
+	}
+	return srclen;
+}
+
 static int chcr_sg_ent_in_wr(struct scatterlist *src,
 			     struct scatterlist *dst,
 			     unsigned int minsg,
@@ -662,7 +632,7 @@ static int chcr_sg_ent_in_wr(struct scatterlist *src,
 {
 	int srclen = 0, dstlen = 0;
 	int srcsg = minsg, dstsg = minsg;
-	int offset = 0, less;
+	int offset = 0, soffset = 0, less, sless = 0;
 
 	if (sg_dma_len(src) == srcskip) {
 		src = sg_next(src);
@@ -676,7 +646,9 @@ static int chcr_sg_ent_in_wr(struct scatterlist *src,
 
 	while (src && dst &&
 	       space > (sgl_ent_len[srcsg + 1] + dsgl_ent_len[dstsg])) {
-		srclen += (sg_dma_len(src) - srcskip);
+		sless = min_t(unsigned int, sg_dma_len(src) - srcskip - soffset,
+				CHCR_SRC_SG_SIZE);
+		srclen += sless;
 		srcsg++;
 		offset = 0;
 		while (dst && ((dstsg + 1) <= MAX_DSGL_ENT) &&
@@ -687,15 +659,20 @@ static int chcr_sg_ent_in_wr(struct scatterlist *src,
 				     dstskip, CHCR_DST_SG_SIZE);
 			dstlen += less;
 			offset += less;
-			if (offset == sg_dma_len(dst)) {
+			if ((offset + dstskip) == sg_dma_len(dst)) {
 				dst = sg_next(dst);
 				offset = 0;
 			}
 			dstsg++;
 			dstskip = 0;
 		}
-		src = sg_next(src);
-		srcskip = 0;
+		soffset += sless;
+		if ((soffset + srcskip) == sg_dma_len(src)) {
+			src = sg_next(src);
+			srcskip = 0;
+			soffset = 0;
+		}
+
 	}
 	return min(srclen, dstlen);
 }
@@ -784,14 +761,14 @@ static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam)
 	nents = sg_nents_xlen(reqctx->dstsg,  wrparam->bytes, CHCR_DST_SG_SIZE,
 			      reqctx->dst_ofst);
 	dst_size = get_space_for_phys_dsgl(nents + 1);
-	kctx_len = (DIV_ROUND_UP(ablkctx->enckey_len, 16) * 16);
+	kctx_len = roundup(ablkctx->enckey_len, 16);
 	transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size);
 	nents = sg_nents_xlen(reqctx->srcsg, wrparam->bytes,
 				  CHCR_SRC_SG_SIZE, reqctx->src_ofst);
-	temp = reqctx->imm ? (DIV_ROUND_UP((IV + wrparam->req->nbytes), 16)
-			      * 16) : (sgl_len(nents + MIN_CIPHER_SG) * 8);
+	temp = reqctx->imm ? roundup(IV + wrparam->req->nbytes, 16) :
+				     (sgl_len(nents + MIN_CIPHER_SG) * 8);
 	transhdr_len += temp;
-	transhdr_len = DIV_ROUND_UP(transhdr_len, 16) * 16;
+	transhdr_len = roundup(transhdr_len, 16);
 	skb = alloc_skb(SGE_MAX_WR_LEN, flags);
 	if (!skb) {
 		error = -ENOMEM;
@@ -847,6 +824,13 @@ static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam)
 		    transhdr_len, temp,
 			ablkctx->ciph_mode == CHCR_SCMD_CIPHER_MODE_AES_CBC);
 	reqctx->skb = skb;
+
+	if (reqctx->op && (ablkctx->ciph_mode ==
+			   CHCR_SCMD_CIPHER_MODE_AES_CBC))
+		sg_pcopy_to_buffer(wrparam->req->src,
+			sg_nents(wrparam->req->src), wrparam->req->info, 16,
+			reqctx->processed + wrparam->bytes - AES_BLOCK_SIZE);
+
 	return skb;
 err:
 	return ERR_PTR(error);
@@ -1070,9 +1054,8 @@ static int chcr_update_cipher_iv(struct ablkcipher_request *req,
 		ret = chcr_update_tweak(req, iv, 0);
 	else if (subtype == CRYPTO_ALG_SUB_TYPE_CBC) {
 		if (reqctx->op)
-			sg_pcopy_to_buffer(req->src, sg_nents(req->src), iv,
-					   16,
-					   reqctx->processed - AES_BLOCK_SIZE);
+			/*Updated before sending last WR*/
+			memcpy(iv, req->info, AES_BLOCK_SIZE);
 		else
 			memcpy(iv, &fw6_pld->data[2], AES_BLOCK_SIZE);
 	}
@@ -1100,11 +1083,8 @@ static int chcr_final_cipher_iv(struct ablkcipher_request *req,
 	else if (subtype == CRYPTO_ALG_SUB_TYPE_XTS)
 		ret = chcr_update_tweak(req, iv, 1);
 	else if (subtype == CRYPTO_ALG_SUB_TYPE_CBC) {
-		if (reqctx->op)
-			sg_pcopy_to_buffer(req->src, sg_nents(req->src), iv,
-					   16,
-					   reqctx->processed - AES_BLOCK_SIZE);
-		else
+		/*Already updated for Decrypt*/
+		if (!reqctx->op)
 			memcpy(iv, &fw6_pld->data[2], AES_BLOCK_SIZE);
 
 	}
@@ -1143,12 +1123,12 @@ static int chcr_handle_cipher_resp(struct ablkcipher_request *req,
 	}
 	if (!reqctx->imm) {
 		bytes = chcr_sg_ent_in_wr(reqctx->srcsg, reqctx->dstsg, 1,
-					  SPACE_LEFT(ablkctx->enckey_len),
+					  CIP_SPACE_LEFT(ablkctx->enckey_len),
 					  reqctx->src_ofst, reqctx->dst_ofst);
 		if ((bytes + reqctx->processed) >= req->nbytes)
 			bytes  = req->nbytes - reqctx->processed;
 		else
-			bytes = ROUND_16(bytes);
+			bytes = rounddown(bytes, 16);
 	} else {
 		/*CTR mode counter overfloa*/
 		bytes  = req->nbytes - reqctx->processed;
@@ -1234,7 +1214,7 @@ static int process_cipher(struct ablkcipher_request *req,
 				       CHCR_DST_SG_SIZE, 0);
 		dnents += 1; // IV
 		phys_dsgl = get_space_for_phys_dsgl(dnents);
-		kctx_len = (DIV_ROUND_UP(ablkctx->enckey_len, 16) * 16);
+		kctx_len = roundup(ablkctx->enckey_len, 16);
 		transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, phys_dsgl);
 		reqctx->imm = (transhdr_len + IV + req->nbytes) <=
 			SGE_MAX_WR_LEN;
@@ -1247,12 +1227,12 @@ static int process_cipher(struct ablkcipher_request *req,
 	if (!reqctx->imm) {
 		bytes = chcr_sg_ent_in_wr(req->src, req->dst,
 					  MIN_CIPHER_SG,
-					  SPACE_LEFT(ablkctx->enckey_len),
+					  CIP_SPACE_LEFT(ablkctx->enckey_len),
 					  0, 0);
 		if ((bytes + reqctx->processed) >= req->nbytes)
 			bytes  = req->nbytes - reqctx->processed;
 		else
-			bytes = ROUND_16(bytes);
+			bytes = rounddown(bytes, 16);
 	} else {
 		bytes = req->nbytes;
 	}
@@ -1282,7 +1262,7 @@ static int process_cipher(struct ablkcipher_request *req,
 					   req->src,
 					   req->dst,
 					   req->nbytes,
-					   req->info,
+					   reqctx->iv,
 					   op_type);
 		goto error;
 	}
@@ -1503,35 +1483,24 @@ static struct sk_buff *create_hash_wr(struct ahash_request *req,
 	struct uld_ctx *u_ctx = ULD_CTX(h_ctx(tfm));
 	struct chcr_wr *chcr_req;
 	struct ulptx_sgl *ulptx;
-	unsigned int nents = 0, transhdr_len, iopad_alignment = 0;
-	unsigned int digestsize = crypto_ahash_digestsize(tfm);
-	unsigned int kctx_len = 0, temp = 0;
-	u8 hash_size_in_response = 0;
+	unsigned int nents = 0, transhdr_len;
+	unsigned int temp = 0;
 	gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL :
 		GFP_ATOMIC;
 	struct adapter *adap = padap(h_ctx(tfm)->dev);
 	int error = 0;
 
-	iopad_alignment = KEYCTX_ALIGN_PAD(digestsize);
-	kctx_len = param->alg_prm.result_size + iopad_alignment;
-	if (param->opad_needed)
-		kctx_len += param->alg_prm.result_size + iopad_alignment;
-
-	if (req_ctx->result)
-		hash_size_in_response = digestsize;
-	else
-		hash_size_in_response = param->alg_prm.result_size;
-	transhdr_len = HASH_TRANSHDR_SIZE(kctx_len);
-	req_ctx->imm = (transhdr_len + param->bfr_len + param->sg_len) <=
-		SGE_MAX_WR_LEN;
-	nents = sg_nents_xlen(req->src, param->sg_len, CHCR_SRC_SG_SIZE, 0);
+	transhdr_len = HASH_TRANSHDR_SIZE(param->kctx_len);
+	req_ctx->hctx_wr.imm = (transhdr_len + param->bfr_len +
+				param->sg_len) <= SGE_MAX_WR_LEN;
+	nents = sg_nents_xlen(req_ctx->hctx_wr.srcsg, param->sg_len,
+		      CHCR_SRC_SG_SIZE, req_ctx->hctx_wr.src_ofst);
 	nents += param->bfr_len ? 1 : 0;
-	transhdr_len += req_ctx->imm ? (DIV_ROUND_UP((param->bfr_len +
-			param->sg_len), 16) * 16) :
-			(sgl_len(nents) * 8);
-	transhdr_len = DIV_ROUND_UP(transhdr_len, 16) * 16;
+	transhdr_len += req_ctx->hctx_wr.imm ? roundup(param->bfr_len +
+				param->sg_len, 16) : (sgl_len(nents) * 8);
+	transhdr_len = roundup(transhdr_len, 16);
 
-	skb = alloc_skb(SGE_MAX_WR_LEN, flags);
+	skb = alloc_skb(transhdr_len, flags);
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 	chcr_req = __skb_put_zero(skb, transhdr_len);
@@ -1563,33 +1532,33 @@ static struct sk_buff *create_hash_wr(struct ahash_request *req,
 	chcr_req->key_ctx.ctx_hdr = FILL_KEY_CTX_HDR(CHCR_KEYCTX_NO_KEY,
 					    param->alg_prm.mk_size, 0,
 					    param->opad_needed,
-					    ((kctx_len +
+					    ((param->kctx_len +
 					     sizeof(chcr_req->key_ctx)) >> 4));
 	chcr_req->sec_cpl.scmd1 = cpu_to_be64((u64)param->scmd1);
-	ulptx = (struct ulptx_sgl *)((u8 *)(chcr_req + 1) + kctx_len +
+	ulptx = (struct ulptx_sgl *)((u8 *)(chcr_req + 1) + param->kctx_len +
 				     DUMMY_BYTES);
 	if (param->bfr_len != 0) {
-		req_ctx->dma_addr = dma_map_single(&u_ctx->lldi.pdev->dev,
-					  req_ctx->reqbfr, param->bfr_len,
-					  DMA_TO_DEVICE);
+		req_ctx->hctx_wr.dma_addr =
+			dma_map_single(&u_ctx->lldi.pdev->dev, req_ctx->reqbfr,
+				       param->bfr_len, DMA_TO_DEVICE);
 		if (dma_mapping_error(&u_ctx->lldi.pdev->dev,
-				       req_ctx->dma_addr)) {
+				       req_ctx->hctx_wr. dma_addr)) {
 			error = -ENOMEM;
 			goto err;
 		}
-		req_ctx->dma_len = param->bfr_len;
+		req_ctx->hctx_wr.dma_len = param->bfr_len;
 	} else {
-		req_ctx->dma_addr = 0;
+		req_ctx->hctx_wr.dma_addr = 0;
 	}
 	chcr_add_hash_src_ent(req, ulptx, param);
 	/* Request upto max wr size */
-	temp = kctx_len + DUMMY_BYTES + (req_ctx->imm ? (param->sg_len
-					+ param->bfr_len) : 0);
+	temp = param->kctx_len + DUMMY_BYTES + (req_ctx->hctx_wr.imm ?
+				(param->sg_len + param->bfr_len) : 0);
 	atomic_inc(&adap->chcr_stats.digest_rqst);
-	create_wreq(h_ctx(tfm), chcr_req, &req->base, req_ctx->imm,
-		    hash_size_in_response, transhdr_len,
+	create_wreq(h_ctx(tfm), chcr_req, &req->base, req_ctx->hctx_wr.imm,
+		    param->hash_size, transhdr_len,
 		    temp,  0);
-	req_ctx->skb = skb;
+	req_ctx->hctx_wr.skb = skb;
 	return skb;
 err:
 	kfree_skb(skb);
@@ -1608,7 +1577,6 @@ static int chcr_ahash_update(struct ahash_request *req)
 	int error;
 
 	bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm));
-
 	u_ctx = ULD_CTX(h_ctx(rtfm));
 	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
 					    h_ctx(rtfm)->tx_qidx))) {
@@ -1625,17 +1593,26 @@ static int chcr_ahash_update(struct ahash_request *req)
 		req_ctx->reqlen += nbytes;
 		return 0;
 	}
+	chcr_init_hctx_per_wr(req_ctx);
 	error = chcr_hash_dma_map(&u_ctx->lldi.pdev->dev, req);
 	if (error)
 		return -ENOMEM;
+	get_alg_config(&params.alg_prm, crypto_ahash_digestsize(rtfm));
+	params.kctx_len = roundup(params.alg_prm.result_size, 16);
+	params.sg_len = chcr_hash_ent_in_wr(req->src, !!req_ctx->reqlen,
+				     HASH_SPACE_LEFT(params.kctx_len), 0);
+	if (params.sg_len > req->nbytes)
+		params.sg_len = req->nbytes;
+	params.sg_len = rounddown(params.sg_len + req_ctx->reqlen, bs) -
+			req_ctx->reqlen;
 	params.opad_needed = 0;
 	params.more = 1;
 	params.last = 0;
-	params.sg_len = nbytes - req_ctx->reqlen;
 	params.bfr_len = req_ctx->reqlen;
 	params.scmd1 = 0;
-	get_alg_config(&params.alg_prm, crypto_ahash_digestsize(rtfm));
-	req_ctx->result = 0;
+	req_ctx->hctx_wr.srcsg = req->src;
+
+	params.hash_size = params.alg_prm.result_size;
 	req_ctx->data_len += params.sg_len + params.bfr_len;
 	skb = create_hash_wr(req, &params);
 	if (IS_ERR(skb)) {
@@ -1643,6 +1620,7 @@ static int chcr_ahash_update(struct ahash_request *req)
 		goto unmap;
 	}
 
+	req_ctx->hctx_wr.processed += params.sg_len;
 	if (remainder) {
 		/* Swap buffers */
 		swap(req_ctx->reqbfr, req_ctx->skbfr);
@@ -1680,16 +1658,27 @@ static int chcr_ahash_final(struct ahash_request *req)
 	struct uld_ctx *u_ctx = NULL;
 	u8 bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm));
 
+	chcr_init_hctx_per_wr(req_ctx);
 	u_ctx = ULD_CTX(h_ctx(rtfm));
 	if (is_hmac(crypto_ahash_tfm(rtfm)))
 		params.opad_needed = 1;
 	else
 		params.opad_needed = 0;
 	params.sg_len = 0;
+	req_ctx->hctx_wr.isfinal = 1;
 	get_alg_config(&params.alg_prm, crypto_ahash_digestsize(rtfm));
-	req_ctx->result = 1;
+	params.kctx_len = roundup(params.alg_prm.result_size, 16);
+	if (is_hmac(crypto_ahash_tfm(rtfm))) {
+		params.opad_needed = 1;
+		params.kctx_len *= 2;
+	} else {
+		params.opad_needed = 0;
+	}
+
+	req_ctx->hctx_wr.result = 1;
 	params.bfr_len = req_ctx->reqlen;
 	req_ctx->data_len += params.bfr_len + params.sg_len;
+	req_ctx->hctx_wr.srcsg = req->src;
 	if (req_ctx->reqlen == 0) {
 		create_last_hash_block(req_ctx->reqbfr, bs, req_ctx->data_len);
 		params.last = 0;
@@ -1702,10 +1691,11 @@ static int chcr_ahash_final(struct ahash_request *req)
 		params.last = 1;
 		params.more = 0;
 	}
+	params.hash_size = crypto_ahash_digestsize(rtfm);
 	skb = create_hash_wr(req, &params);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
-
+	req_ctx->reqlen = 0;
 	skb->dev = u_ctx->lldi.ports[0];
 	set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx);
 	chcr_send_wr(skb);
@@ -1730,37 +1720,59 @@ static int chcr_ahash_finup(struct ahash_request *req)
 		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
 			return -EBUSY;
 	}
+	chcr_init_hctx_per_wr(req_ctx);
+	error = chcr_hash_dma_map(&u_ctx->lldi.pdev->dev, req);
+	if (error)
+		return -ENOMEM;
 
-	if (is_hmac(crypto_ahash_tfm(rtfm)))
+	get_alg_config(&params.alg_prm, crypto_ahash_digestsize(rtfm));
+	params.kctx_len = roundup(params.alg_prm.result_size, 16);
+	if (is_hmac(crypto_ahash_tfm(rtfm))) {
+		params.kctx_len *= 2;
 		params.opad_needed = 1;
-	else
+	} else {
 		params.opad_needed = 0;
+	}
 
-	params.sg_len = req->nbytes;
+	params.sg_len = chcr_hash_ent_in_wr(req->src, !!req_ctx->reqlen,
+				    HASH_SPACE_LEFT(params.kctx_len), 0);
+	if (params.sg_len < req->nbytes) {
+		if (is_hmac(crypto_ahash_tfm(rtfm))) {
+			params.kctx_len /= 2;
+			params.opad_needed = 0;
+		}
+		params.last = 0;
+		params.more = 1;
+		params.sg_len = rounddown(params.sg_len + req_ctx->reqlen, bs)
+					- req_ctx->reqlen;
+		params.hash_size = params.alg_prm.result_size;
+		params.scmd1 = 0;
+	} else {
+		params.last = 1;
+		params.more = 0;
+		params.sg_len = req->nbytes;
+		params.hash_size = crypto_ahash_digestsize(rtfm);
+		params.scmd1 = req_ctx->data_len + req_ctx->reqlen +
+				params.sg_len;
+	}
 	params.bfr_len = req_ctx->reqlen;
-	get_alg_config(&params.alg_prm, crypto_ahash_digestsize(rtfm));
 	req_ctx->data_len += params.bfr_len + params.sg_len;
-	req_ctx->result = 1;
+	req_ctx->hctx_wr.result = 1;
+	req_ctx->hctx_wr.srcsg = req->src;
 	if ((req_ctx->reqlen + req->nbytes) == 0) {
 		create_last_hash_block(req_ctx->reqbfr, bs, req_ctx->data_len);
 		params.last = 0;
 		params.more = 1;
 		params.scmd1 = 0;
 		params.bfr_len = bs;
-	} else {
-		params.scmd1 = req_ctx->data_len;
-		params.last = 1;
-		params.more = 0;
 	}
-	error = chcr_hash_dma_map(&u_ctx->lldi.pdev->dev, req);
-	if (error)
-		return -ENOMEM;
-
 	skb = create_hash_wr(req, &params);
 	if (IS_ERR(skb)) {
 		error = PTR_ERR(skb);
 		goto unmap;
 	}
+	req_ctx->reqlen = 0;
+	req_ctx->hctx_wr.processed += params.sg_len;
 	skb->dev = u_ctx->lldi.ports[0];
 	set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx);
 	chcr_send_wr(skb);
@@ -1791,21 +1803,42 @@ static int chcr_ahash_digest(struct ahash_request *req)
 			return -EBUSY;
 	}
 
-	if (is_hmac(crypto_ahash_tfm(rtfm)))
-		params.opad_needed = 1;
-	else
-		params.opad_needed = 0;
+	chcr_init_hctx_per_wr(req_ctx);
 	error = chcr_hash_dma_map(&u_ctx->lldi.pdev->dev, req);
 	if (error)
 		return -ENOMEM;
 
-	params.last = 0;
-	params.more = 0;
-	params.sg_len = req->nbytes;
-	params.bfr_len = 0;
-	params.scmd1 = 0;
 	get_alg_config(&params.alg_prm, crypto_ahash_digestsize(rtfm));
-	req_ctx->result = 1;
+	params.kctx_len = roundup(params.alg_prm.result_size, 16);
+	if (is_hmac(crypto_ahash_tfm(rtfm))) {
+		params.kctx_len *= 2;
+		params.opad_needed = 1;
+	} else {
+		params.opad_needed = 0;
+	}
+	params.sg_len = chcr_hash_ent_in_wr(req->src, !!req_ctx->reqlen,
+				HASH_SPACE_LEFT(params.kctx_len), 0);
+	if (params.sg_len < req->nbytes) {
+		if (is_hmac(crypto_ahash_tfm(rtfm))) {
+			params.kctx_len /= 2;
+			params.opad_needed = 0;
+		}
+		params.last = 0;
+		params.more = 1;
+		params.scmd1 = 0;
+		params.sg_len = rounddown(params.sg_len, bs);
+		params.hash_size = params.alg_prm.result_size;
+	} else {
+		params.sg_len = req->nbytes;
+		params.hash_size = crypto_ahash_digestsize(rtfm);
+		params.last = 1;
+		params.more = 0;
+		params.scmd1 = req->nbytes + req_ctx->data_len;
+
+	}
+	params.bfr_len = 0;
+	req_ctx->hctx_wr.result = 1;
+	req_ctx->hctx_wr.srcsg = req->src;
 	req_ctx->data_len += params.bfr_len + params.sg_len;
 
 	if (req->nbytes == 0) {
@@ -1819,6 +1852,7 @@ static int chcr_ahash_digest(struct ahash_request *req)
 		error = PTR_ERR(skb);
 		goto unmap;
 	}
+	req_ctx->hctx_wr.processed += params.sg_len;
 	skb->dev = u_ctx->lldi.ports[0];
 	set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx);
 	chcr_send_wr(skb);
@@ -1828,6 +1862,151 @@ unmap:
 	return error;
 }
 
+static int chcr_ahash_continue(struct ahash_request *req)
+{
+	struct chcr_ahash_req_ctx *reqctx = ahash_request_ctx(req);
+	struct chcr_hctx_per_wr *hctx_wr = &reqctx->hctx_wr;
+	struct crypto_ahash *rtfm = crypto_ahash_reqtfm(req);
+	struct uld_ctx *u_ctx = NULL;
+	struct sk_buff *skb;
+	struct hash_wr_param params;
+	u8  bs;
+	int error;
+
+	bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm));
+	u_ctx = ULD_CTX(h_ctx(rtfm));
+	if (unlikely(cxgb4_is_crypto_q_full(u_ctx->lldi.ports[0],
+					    h_ctx(rtfm)->tx_qidx))) {
+		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
+			return -EBUSY;
+	}
+	get_alg_config(&params.alg_prm, crypto_ahash_digestsize(rtfm));
+	params.kctx_len = roundup(params.alg_prm.result_size, 16);
+	if (is_hmac(crypto_ahash_tfm(rtfm))) {
+		params.kctx_len *= 2;
+		params.opad_needed = 1;
+	} else {
+		params.opad_needed = 0;
+	}
+	params.sg_len = chcr_hash_ent_in_wr(hctx_wr->srcsg, 0,
+					    HASH_SPACE_LEFT(params.kctx_len),
+					    hctx_wr->src_ofst);
+	if ((params.sg_len + hctx_wr->processed) > req->nbytes)
+		params.sg_len = req->nbytes - hctx_wr->processed;
+	if (!hctx_wr->result ||
+	    ((params.sg_len + hctx_wr->processed) < req->nbytes)) {
+		if (is_hmac(crypto_ahash_tfm(rtfm))) {
+			params.kctx_len /= 2;
+			params.opad_needed = 0;
+		}
+		params.last = 0;
+		params.more = 1;
+		params.sg_len = rounddown(params.sg_len, bs);
+		params.hash_size = params.alg_prm.result_size;
+		params.scmd1 = 0;
+	} else {
+		params.last = 1;
+		params.more = 0;
+		params.hash_size = crypto_ahash_digestsize(rtfm);
+		params.scmd1 = reqctx->data_len + params.sg_len;
+	}
+	params.bfr_len = 0;
+	reqctx->data_len += params.sg_len;
+	skb = create_hash_wr(req, &params);
+	if (IS_ERR(skb)) {
+		error = PTR_ERR(skb);
+		goto err;
+	}
+	hctx_wr->processed += params.sg_len;
+	skb->dev = u_ctx->lldi.ports[0];
+	set_wr_txq(skb, CPL_PRIORITY_DATA, h_ctx(rtfm)->tx_qidx);
+	chcr_send_wr(skb);
+	return 0;
+err:
+	return error;
+}
+
+static inline void chcr_handle_ahash_resp(struct ahash_request *req,
+					  unsigned char *input,
+					  int err)
+{
+	struct chcr_ahash_req_ctx *reqctx = ahash_request_ctx(req);
+	struct chcr_hctx_per_wr *hctx_wr = &reqctx->hctx_wr;
+	int digestsize, updated_digestsize;
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct uld_ctx *u_ctx = ULD_CTX(h_ctx(tfm));
+
+	if (input == NULL)
+		goto out;
+	digestsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req));
+	updated_digestsize = digestsize;
+	if (digestsize == SHA224_DIGEST_SIZE)
+		updated_digestsize = SHA256_DIGEST_SIZE;
+	else if (digestsize == SHA384_DIGEST_SIZE)
+		updated_digestsize = SHA512_DIGEST_SIZE;
+
+	if (hctx_wr->dma_addr) {
+		dma_unmap_single(&u_ctx->lldi.pdev->dev, hctx_wr->dma_addr,
+				 hctx_wr->dma_len, DMA_TO_DEVICE);
+		hctx_wr->dma_addr = 0;
+	}
+	if (hctx_wr->isfinal || ((hctx_wr->processed + reqctx->reqlen) ==
+				 req->nbytes)) {
+		if (hctx_wr->result == 1) {
+			hctx_wr->result = 0;
+			memcpy(req->result, input + sizeof(struct cpl_fw6_pld),
+			       digestsize);
+		} else {
+			memcpy(reqctx->partial_hash,
+			       input + sizeof(struct cpl_fw6_pld),
+			       updated_digestsize);
+
+		}
+		goto unmap;
+	}
+	memcpy(reqctx->partial_hash, input + sizeof(struct cpl_fw6_pld),
+	       updated_digestsize);
+
+	err = chcr_ahash_continue(req);
+	if (err)
+		goto unmap;
+	return;
+unmap:
+	if (hctx_wr->is_sg_map)
+		chcr_hash_dma_unmap(&u_ctx->lldi.pdev->dev, req);
+
+
+out:
+	req->base.complete(&req->base, err);
+}
+
+/*
+ *	chcr_handle_resp - Unmap the DMA buffers associated with the request
+ *	@req: crypto request
+ */
+int chcr_handle_resp(struct crypto_async_request *req, unsigned char *input,
+			 int err)
+{
+	struct crypto_tfm *tfm = req->tfm;
+	struct chcr_context *ctx = crypto_tfm_ctx(tfm);
+	struct adapter *adap = padap(ctx->dev);
+
+	switch (tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK) {
+	case CRYPTO_ALG_TYPE_AEAD:
+		chcr_handle_aead_resp(aead_request_cast(req), input, err);
+		break;
+
+	case CRYPTO_ALG_TYPE_ABLKCIPHER:
+		 err = chcr_handle_cipher_resp(ablkcipher_request_cast(req),
+					       input, err);
+		break;
+
+	case CRYPTO_ALG_TYPE_AHASH:
+		chcr_handle_ahash_resp(ahash_request_cast(req), input, err);
+		}
+	atomic_inc(&adap->chcr_stats.complete);
+	return err;
+}
 static int chcr_ahash_export(struct ahash_request *areq, void *out)
 {
 	struct chcr_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
@@ -1835,11 +2014,10 @@ static int chcr_ahash_export(struct ahash_request *areq, void *out)
 
 	state->reqlen = req_ctx->reqlen;
 	state->data_len = req_ctx->data_len;
-	state->is_sg_map = 0;
-	state->result = 0;
 	memcpy(state->bfr1, req_ctx->reqbfr, req_ctx->reqlen);
 	memcpy(state->partial_hash, req_ctx->partial_hash,
 	       CHCR_HASH_MAX_DIGEST_SIZE);
+	chcr_init_hctx_per_wr(state);
 		return 0;
 }
 
@@ -1852,11 +2030,10 @@ static int chcr_ahash_import(struct ahash_request *areq, const void *in)
 	req_ctx->data_len = state->data_len;
 	req_ctx->reqbfr = req_ctx->bfr1;
 	req_ctx->skbfr = req_ctx->bfr2;
-	req_ctx->is_sg_map = 0;
-	req_ctx->result = 0;
 	memcpy(req_ctx->bfr1, state->bfr1, CHCR_HASH_MAX_BLOCK_SIZE_128);
 	memcpy(req_ctx->partial_hash, state->partial_hash,
 	       CHCR_HASH_MAX_DIGEST_SIZE);
+	chcr_init_hctx_per_wr(req_ctx);
 	return 0;
 }
 
@@ -1953,10 +2130,8 @@ static int chcr_sha_init(struct ahash_request *areq)
 	req_ctx->reqlen = 0;
 	req_ctx->reqbfr = req_ctx->bfr1;
 	req_ctx->skbfr = req_ctx->bfr2;
-	req_ctx->skb = NULL;
-	req_ctx->result = 0;
-	req_ctx->is_sg_map = 0;
 	copy_hash_init_values(req_ctx->partial_hash, digestsize);
+
 	return 0;
 }
 
@@ -2124,11 +2299,11 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size);
 	reqctx->imm = (transhdr_len + assoclen + IV + req->cryptlen) <
 			SGE_MAX_WR_LEN;
-	temp = reqctx->imm ? (DIV_ROUND_UP((assoclen + IV + req->cryptlen), 16)
-			* 16) : (sgl_len(reqctx->src_nents + reqctx->aad_nents
+	temp = reqctx->imm ? roundup(assoclen + IV + req->cryptlen, 16)
+			: (sgl_len(reqctx->src_nents + reqctx->aad_nents
 			+ MIN_GCM_SG) * 8);
 	transhdr_len += temp;
-	transhdr_len = DIV_ROUND_UP(transhdr_len, 16) * 16;
+	transhdr_len = roundup(transhdr_len, 16);
 
 	if (chcr_aead_need_fallback(req, dnents, T6_MAX_AAD_SIZE,
 				    transhdr_len, op_type)) {
@@ -2187,9 +2362,8 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 		memcpy(chcr_req->key_ctx.key, actx->dec_rrkey,
 		       aeadctx->enckey_len);
 
-	memcpy(chcr_req->key_ctx.key + (DIV_ROUND_UP(aeadctx->enckey_len, 16) <<
-					4), actx->h_iopad, kctx_len -
-				(DIV_ROUND_UP(aeadctx->enckey_len, 16) << 4));
+	memcpy(chcr_req->key_ctx.key + roundup(aeadctx->enckey_len, 16),
+	       actx->h_iopad, kctx_len - roundup(aeadctx->enckey_len, 16));
 	if (subtype == CRYPTO_ALG_SUB_TYPE_CTR_SHA ||
 	    subtype == CRYPTO_ALG_SUB_TYPE_CTR_NULL) {
 		memcpy(reqctx->iv, aeadctx->nonce, CTR_RFC3686_NONCE_SIZE);
@@ -2398,22 +2572,26 @@ void chcr_add_hash_src_ent(struct ahash_request *req,
 	struct ulptx_walk ulp_walk;
 	struct chcr_ahash_req_ctx *reqctx = ahash_request_ctx(req);
 
-	if (reqctx->imm) {
+	if (reqctx->hctx_wr.imm) {
 		u8 *buf = (u8 *)ulptx;
 
 		if (param->bfr_len) {
 			memcpy(buf, reqctx->reqbfr, param->bfr_len);
 			buf += param->bfr_len;
 		}
-		sg_pcopy_to_buffer(req->src, sg_nents(req->src),
-				   buf, param->sg_len, 0);
+
+		sg_pcopy_to_buffer(reqctx->hctx_wr.srcsg,
+				   sg_nents(reqctx->hctx_wr.srcsg), buf,
+				   param->sg_len, 0);
 	} else {
 		ulptx_walk_init(&ulp_walk, ulptx);
 		if (param->bfr_len)
 			ulptx_walk_add_page(&ulp_walk, param->bfr_len,
-					    &reqctx->dma_addr);
-		ulptx_walk_add_sg(&ulp_walk, req->src, param->sg_len,
-				  0);
+					    &reqctx->hctx_wr.dma_addr);
+		ulptx_walk_add_sg(&ulp_walk, reqctx->hctx_wr.srcsg,
+				  param->sg_len, reqctx->hctx_wr.src_ofst);
+		reqctx->hctx_wr.srcsg = ulp_walk.last_sg;
+		reqctx->hctx_wr.src_ofst = ulp_walk.last_sg_len;
 		ulptx_walk_end(&ulp_walk);
 	}
 }
@@ -2430,7 +2608,7 @@ int chcr_hash_dma_map(struct device *dev,
 			   DMA_TO_DEVICE);
 	if (!error)
 		return -ENOMEM;
-	req_ctx->is_sg_map = 1;
+	req_ctx->hctx_wr.is_sg_map = 1;
 	return 0;
 }
 
@@ -2444,7 +2622,7 @@ void chcr_hash_dma_unmap(struct device *dev,
 
 	dma_unmap_sg(dev, req->src, sg_nents(req->src),
 			   DMA_TO_DEVICE);
-	req_ctx->is_sg_map = 0;
+	req_ctx->hctx_wr.is_sg_map = 0;
 
 }
 
@@ -2636,10 +2814,10 @@ static void fill_sec_cpl_for_aead(struct cpl_tx_sec_pdu *sec_cpl,
 					0, dst_size);
 }
 
-int aead_ccm_validate_input(unsigned short op_type,
-			    struct aead_request *req,
-			    struct chcr_aead_ctx *aeadctx,
-			    unsigned int sub_type)
+static int aead_ccm_validate_input(unsigned short op_type,
+				   struct aead_request *req,
+				   struct chcr_aead_ctx *aeadctx,
+				   unsigned int sub_type)
 {
 	if (sub_type != CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309) {
 		if (crypto_ccm_check_iv(req->iv)) {
@@ -2696,16 +2874,16 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 			CHCR_DST_SG_SIZE, req->assoclen);
 	dnents += MIN_CCM_SG; // For IV and B0
 	dst_size = get_space_for_phys_dsgl(dnents);
-	kctx_len = ((DIV_ROUND_UP(aeadctx->enckey_len, 16)) << 4) * 2;
+	kctx_len = roundup(aeadctx->enckey_len, 16) * 2;
 	transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size);
 	reqctx->imm = (transhdr_len + assoclen + IV + req->cryptlen +
 		       reqctx->b0_len) <= SGE_MAX_WR_LEN;
-	temp = reqctx->imm ? (DIV_ROUND_UP((assoclen + IV + req->cryptlen +
-				reqctx->b0_len), 16) * 16) :
+	temp = reqctx->imm ? roundup(assoclen + IV + req->cryptlen +
+				     reqctx->b0_len, 16) :
 		(sgl_len(reqctx->src_nents + reqctx->aad_nents +
 				    MIN_CCM_SG) *  8);
 	transhdr_len += temp;
-	transhdr_len = DIV_ROUND_UP(transhdr_len, 16) * 16;
+	transhdr_len = roundup(transhdr_len, 16);
 
 	if (chcr_aead_need_fallback(req, dnents, T6_MAX_AAD_SIZE -
 				    reqctx->b0_len, transhdr_len, op_type)) {
@@ -2727,8 +2905,8 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 
 	chcr_req->key_ctx.ctx_hdr = aeadctx->key_ctx_hdr;
 	memcpy(chcr_req->key_ctx.key, aeadctx->key, aeadctx->enckey_len);
-	memcpy(chcr_req->key_ctx.key + (DIV_ROUND_UP(aeadctx->enckey_len, 16) *
-					16), aeadctx->key, aeadctx->enckey_len);
+	memcpy(chcr_req->key_ctx.key + roundup(aeadctx->enckey_len, 16),
+			aeadctx->key, aeadctx->enckey_len);
 
 	phys_cpl = (struct cpl_rx_phys_dsgl *)((u8 *)(chcr_req + 1) + kctx_len);
 	ulptx = (struct ulptx_sgl *)((u8 *)(phys_cpl + 1) + dst_size);
@@ -2798,16 +2976,15 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 				CHCR_DST_SG_SIZE, req->assoclen);
 	dnents += MIN_GCM_SG; // For IV
 	dst_size = get_space_for_phys_dsgl(dnents);
-	kctx_len = ((DIV_ROUND_UP(aeadctx->enckey_len, 16)) << 4) +
-		AEAD_H_SIZE;
+	kctx_len = roundup(aeadctx->enckey_len, 16) + AEAD_H_SIZE;
 	transhdr_len = CIPHER_TRANSHDR_SIZE(kctx_len, dst_size);
 	reqctx->imm = (transhdr_len + assoclen + IV + req->cryptlen) <=
 			SGE_MAX_WR_LEN;
-	temp = reqctx->imm ? (DIV_ROUND_UP((assoclen + IV +
-	req->cryptlen), 16) * 16) : (sgl_len(reqctx->src_nents +
-				reqctx->aad_nents + MIN_GCM_SG) * 8);
+	temp = reqctx->imm ? roundup(assoclen + IV + req->cryptlen, 16) :
+		(sgl_len(reqctx->src_nents +
+		reqctx->aad_nents + MIN_GCM_SG) * 8);
 	transhdr_len += temp;
-	transhdr_len = DIV_ROUND_UP(transhdr_len, 16) * 16;
+	transhdr_len = roundup(transhdr_len, 16);
 	if (chcr_aead_need_fallback(req, dnents, T6_MAX_AAD_SIZE,
 			    transhdr_len, op_type)) {
 		atomic_inc(&adap->chcr_stats.fallback);
@@ -2846,8 +3023,8 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 					0, 0, dst_size);
 	chcr_req->key_ctx.ctx_hdr = aeadctx->key_ctx_hdr;
 	memcpy(chcr_req->key_ctx.key, aeadctx->key, aeadctx->enckey_len);
-	memcpy(chcr_req->key_ctx.key + (DIV_ROUND_UP(aeadctx->enckey_len, 16) *
-				16), GCM_CTX(aeadctx)->ghash_h, AEAD_H_SIZE);
+	memcpy(chcr_req->key_ctx.key + roundup(aeadctx->enckey_len, 16),
+	       GCM_CTX(aeadctx)->ghash_h, AEAD_H_SIZE);
 
 	/* prepare a 16 byte iv */
 	/* S   A   L  T |  IV | 0x00000001 */
@@ -3067,11 +3244,10 @@ static int chcr_ccm_common_setkey(struct crypto_aead *aead,
 	unsigned char ck_size, mk_size;
 	int key_ctx_size = 0;
 
-	key_ctx_size = sizeof(struct _key_ctx) +
-		((DIV_ROUND_UP(keylen, 16)) << 4)  * 2;
+	key_ctx_size = sizeof(struct _key_ctx) + roundup(keylen, 16) * 2;
 	if (keylen == AES_KEYSIZE_128) {
-		mk_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128;
 		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128;
+		mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_128;
 	} else if (keylen == AES_KEYSIZE_192) {
 		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192;
 		mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_192;
@@ -3178,10 +3354,9 @@ static int chcr_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 
 	memcpy(aeadctx->key, key, keylen);
 	aeadctx->enckey_len = keylen;
-	key_ctx_size = sizeof(struct _key_ctx) +
-		((DIV_ROUND_UP(keylen, 16)) << 4) +
+	key_ctx_size = sizeof(struct _key_ctx) + roundup(keylen, 16) +
 		AEAD_H_SIZE;
-		aeadctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size,
+	aeadctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size,
 						CHCR_KEYCTX_MAC_KEY_SIZE_128,
 						0, 0,
 						key_ctx_size >> 4);
@@ -3281,6 +3456,7 @@ static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 	if (IS_ERR(base_hash)) {
 		pr_err("chcr : Base driver cannot be loaded\n");
 		aeadctx->enckey_len = 0;
+		memzero_explicit(&keys, sizeof(keys));
 		return -EINVAL;
 	}
 	{
@@ -3325,17 +3501,19 @@ static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 		chcr_change_order(actx->h_iopad, param.result_size);
 		chcr_change_order(o_ptr, param.result_size);
 		key_ctx_len = sizeof(struct _key_ctx) +
-			((DIV_ROUND_UP(keys.enckeylen, 16)) << 4) +
+			roundup(keys.enckeylen, 16) +
 			(param.result_size + align) * 2;
 		aeadctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, param.mk_size,
 						0, 1, key_ctx_len >> 4);
 		actx->auth_mode = param.auth_mode;
 		chcr_free_shash(base_hash);
 
+		memzero_explicit(&keys, sizeof(keys));
 		return 0;
 	}
 out:
 	aeadctx->enckey_len = 0;
+	memzero_explicit(&keys, sizeof(keys));
 	if (!IS_ERR(base_hash))
 		chcr_free_shash(base_hash);
 	return -EINVAL;
@@ -3393,15 +3571,16 @@ static int chcr_aead_digest_null_setkey(struct crypto_aead *authenc,
 		get_aes_decrypt_key(actx->dec_rrkey, aeadctx->key,
 				aeadctx->enckey_len << 3);
 	}
-	key_ctx_len =  sizeof(struct _key_ctx)
-		+ ((DIV_ROUND_UP(keys.enckeylen, 16)) << 4);
+	key_ctx_len =  sizeof(struct _key_ctx) + roundup(keys.enckeylen, 16);
 
 	aeadctx->key_ctx_hdr = FILL_KEY_CTX_HDR(ck_size, CHCR_KEYCTX_NO_KEY, 0,
 						0, key_ctx_len >> 4);
 	actx->auth_mode = CHCR_SCMD_AUTH_MODE_NOP;
+	memzero_explicit(&keys, sizeof(keys));
 	return 0;
 out:
 	aeadctx->enckey_len = 0;
+	memzero_explicit(&keys, sizeof(keys));
 	return -EINVAL;
 }
 
diff --git a/drivers/crypto/chelsio/chcr_algo.h b/drivers/crypto/chelsio/chcr_algo.h
index f263cd42a84f..dba3dff1e209 100644
--- a/drivers/crypto/chelsio/chcr_algo.h
+++ b/drivers/crypto/chelsio/chcr_algo.h
@@ -258,15 +258,16 @@
 #define FILL_CMD_MORE(immdatalen) htonl(ULPTX_CMD_V(ULP_TX_SC_IMM) |\
 					ULP_TX_SC_MORE_V((immdatalen)))
 #define MAX_NK 8
-#define ROUND_16(bytes)		((bytes) & 0xFFFFFFF0)
 #define MAX_DSGL_ENT			32
 #define MIN_CIPHER_SG			1 /* IV */
 #define MIN_AUTH_SG			1 /* IV */
 #define MIN_GCM_SG			1 /* IV */
 #define MIN_DIGEST_SG			1 /*Partial Buffer*/
 #define MIN_CCM_SG			2 /*IV+B0*/
-#define SPACE_LEFT(len) \
-	((SGE_MAX_WR_LEN - WR_MIN_LEN - (len)))
+#define CIP_SPACE_LEFT(len) \
+	((SGE_MAX_WR_LEN - CIP_WR_MIN_LEN - (len)))
+#define HASH_SPACE_LEFT(len) \
+	((SGE_MAX_WR_LEN - HASH_WR_MIN_LEN - (len)))
 
 struct algo_param {
 	unsigned int auth_mode;
@@ -275,12 +276,14 @@ struct algo_param {
 };
 
 struct hash_wr_param {
+	struct algo_param alg_prm;
 	unsigned int opad_needed;
 	unsigned int more;
 	unsigned int last;
-	struct algo_param alg_prm;
+	unsigned int kctx_len;
 	unsigned int sg_len;
 	unsigned int bfr_len;
+	unsigned int hash_size;
 	u64 scmd1;
 };
 
diff --git a/drivers/crypto/chelsio/chcr_core.h b/drivers/crypto/chelsio/chcr_core.h
index 77056a90c8e1..1a20424e18c6 100644
--- a/drivers/crypto/chelsio/chcr_core.h
+++ b/drivers/crypto/chelsio/chcr_core.h
@@ -54,10 +54,14 @@
 #define MAC_ERROR_BIT		0
 #define CHK_MAC_ERR_BIT(x)	(((x) >> MAC_ERROR_BIT) & 1)
 #define MAX_SALT                4
-#define WR_MIN_LEN (sizeof(struct chcr_wr) + \
+#define CIP_WR_MIN_LEN (sizeof(struct chcr_wr) + \
 		    sizeof(struct cpl_rx_phys_dsgl) + \
 		    sizeof(struct ulptx_sgl))
 
+#define HASH_WR_MIN_LEN (sizeof(struct chcr_wr) + \
+			DUMMY_BYTES + \
+		    sizeof(struct ulptx_sgl))
+
 #define padap(dev) pci_get_drvdata(dev->u_ctx->lldi.pdev)
 
 struct uld_ctx;
diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h
index 7daf0a17a7d2..c8e8972af283 100644
--- a/drivers/crypto/chelsio/chcr_crypto.h
+++ b/drivers/crypto/chelsio/chcr_crypto.h
@@ -258,21 +258,32 @@ struct chcr_context {
 	struct __crypto_ctx crypto_ctx[0];
 };
 
-struct chcr_ahash_req_ctx {
+struct chcr_hctx_per_wr {
+	struct scatterlist *srcsg;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	u32 dma_len;
+	unsigned int src_ofst;
+	unsigned int processed;
 	u32 result;
-	u8 bfr1[CHCR_HASH_MAX_BLOCK_SIZE_128];
-	u8 bfr2[CHCR_HASH_MAX_BLOCK_SIZE_128];
+	u8 is_sg_map;
+	u8 imm;
+	/*Final callback called. Driver cannot rely on nbytes to decide
+	 * final call
+	 */
+	u8 isfinal;
+};
+
+struct chcr_ahash_req_ctx {
+	struct chcr_hctx_per_wr hctx_wr;
 	u8 *reqbfr;
 	u8 *skbfr;
-	dma_addr_t dma_addr;
-	u32 dma_len;
+	/* SKB which is being sent to the hardware for processing */
+	u64 data_len;  /* Data len till time */
 	u8 reqlen;
-	u8 imm;
-	u8 is_sg_map;
 	u8 partial_hash[CHCR_HASH_MAX_DIGEST_SIZE];
-	u64 data_len;  /* Data len till time */
-	/* SKB which is being sent to the hardware for processing */
-	struct sk_buff *skb;
+	u8 bfr1[CHCR_HASH_MAX_BLOCK_SIZE_128];
+	u8 bfr2[CHCR_HASH_MAX_BLOCK_SIZE_128];
 };
 
 struct chcr_blkcipher_req_ctx {
diff --git a/drivers/crypto/chelsio/chcr_ipsec.c b/drivers/crypto/chelsio/chcr_ipsec.c
index db1e241104ed..8e0aa3f175c9 100644
--- a/drivers/crypto/chelsio/chcr_ipsec.c
+++ b/drivers/crypto/chelsio/chcr_ipsec.c
@@ -360,8 +360,7 @@ inline void *copy_cpltx_pktxt(struct sk_buff *skb,
 
 	cpl = (struct cpl_tx_pkt_core *)pos;
 
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
+	cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
 	ctrl0 = TXPKT_OPCODE_V(CPL_TX_PKT_XT) | TXPKT_INTF_V(pi->tx_chan) |
 			       TXPKT_PF_V(adap->pf);
 	if (skb_vlan_tag_present(skb)) {
@@ -475,7 +474,7 @@ inline void *chcr_crypto_wreq(struct sk_buff *skb,
 	wr->req.ulptx.len = htonl(DIV_ROUND_UP(flits, 2)  - 1);
 
 	/* Sub-command */
-	wr->req.sc_imm.cmd_more = FILL_CMD_MORE(immdatalen);
+	wr->req.sc_imm.cmd_more = FILL_CMD_MORE(!immdatalen);
 	wr->req.sc_imm.len = cpu_to_be32(sizeof(struct cpl_tx_sec_pdu) +
 					 sizeof(wr->req.key_ctx) +
 					 kctx_len +
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 225e74a7f724..d4a81be0d7d2 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -235,7 +235,7 @@ static int safexcel_hw_setup_rdesc_rings(struct safexcel_crypto_priv *priv)
 		/* Configure DMA tx control */
 		val = EIP197_HIA_xDR_CFG_WR_CACHE(WR_CACHE_3BITS);
 		val |= EIP197_HIA_xDR_CFG_RD_CACHE(RD_CACHE_3BITS);
-		val |= EIP197_HIA_xDR_WR_RES_BUF | EIP197_HIA_xDR_WR_CTRL_BUG;
+		val |= EIP197_HIA_xDR_WR_RES_BUF | EIP197_HIA_xDR_WR_CTRL_BUF;
 		writel(val,
 		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_DMA_CFG);
 
@@ -332,7 +332,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	val = EIP197_HIA_DSE_CFG_DIS_DEBUG;
 	val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(7) | EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(8);
 	val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(WR_CACHE_3BITS);
-	val |= EIP197_HIA_DSE_CFG_ALLWAYS_BUFFERABLE;
+	val |= EIP197_HIA_DSE_CFG_ALWAYS_BUFFERABLE;
 	/* FIXME: instability issues can occur for EIP97 but disabling it impact
 	 * performances.
 	 */
@@ -354,7 +354,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
 	val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
 	val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
-	val |= EIP197_ALG_SHA2;
+	val |= EIP197_ALG_SHA2 | EIP197_ALG_HMAC_SHA2;
 	writel(val, EIP197_PE(priv) + EIP197_PE_EIP96_FUNCTION_EN);
 
 	/* Command Descriptor Rings prepare */
@@ -432,20 +432,18 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 }
 
 /* Called with ring's lock taken */
-static int safexcel_try_push_requests(struct safexcel_crypto_priv *priv,
-				      int ring, int reqs)
+static void safexcel_try_push_requests(struct safexcel_crypto_priv *priv,
+				       int ring)
 {
-	int coal = min_t(int, reqs, EIP197_MAX_BATCH_SZ);
+	int coal = min_t(int, priv->ring[ring].requests, EIP197_MAX_BATCH_SZ);
 
 	if (!coal)
-		return 0;
+		return;
 
 	/* Configure when we want an interrupt */
 	writel(EIP197_HIA_RDR_THRESH_PKT_MODE |
 	       EIP197_HIA_RDR_THRESH_PROC_PKT(coal),
 	       EIP197_HIA_RDR(priv, ring) + EIP197_HIA_xDR_THRESH);
-
-	return coal;
 }
 
 void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring)
@@ -490,6 +488,15 @@ handle_req:
 		if (backlog)
 			backlog->complete(backlog, -EINPROGRESS);
 
+		/* In case the send() helper did not issue any command to push
+		 * to the engine because the input data was cached, continue to
+		 * dequeue other requests as this is valid and not an error.
+		 */
+		if (!commands && !results) {
+			kfree(request);
+			continue;
+		}
+
 		spin_lock_bh(&priv->ring[ring].egress_lock);
 		list_add_tail(&request->list, &priv->ring[ring].list);
 		spin_unlock_bh(&priv->ring[ring].egress_lock);
@@ -512,14 +519,13 @@ finalize:
 
 	spin_lock_bh(&priv->ring[ring].egress_lock);
 
+	priv->ring[ring].requests += nreq;
+
 	if (!priv->ring[ring].busy) {
-		nreq -= safexcel_try_push_requests(priv, ring, nreq);
-		if (nreq)
-			priv->ring[ring].busy = true;
+		safexcel_try_push_requests(priv, ring);
+		priv->ring[ring].busy = true;
 	}
 
-	priv->ring[ring].requests_left += nreq;
-
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	/* let the RDR know we have pending descriptors */
@@ -531,25 +537,6 @@ finalize:
 	       EIP197_HIA_CDR(priv, ring) + EIP197_HIA_xDR_PREP_COUNT);
 }
 
-void safexcel_free_context(struct safexcel_crypto_priv *priv,
-			   struct crypto_async_request *req,
-			   int result_sz)
-{
-	struct safexcel_context *ctx = crypto_tfm_ctx(req->tfm);
-
-	if (ctx->result_dma)
-		dma_unmap_single(priv->dev, ctx->result_dma, result_sz,
-				 DMA_FROM_DEVICE);
-
-	if (ctx->cache) {
-		dma_unmap_single(priv->dev, ctx->cache_dma, ctx->cache_sz,
-				 DMA_TO_DEVICE);
-		kfree(ctx->cache);
-		ctx->cache = NULL;
-		ctx->cache_sz = 0;
-	}
-}
-
 void safexcel_complete(struct safexcel_crypto_priv *priv, int ring)
 {
 	struct safexcel_command_desc *cdesc;
@@ -623,7 +610,7 @@ static inline void safexcel_handle_result_descriptor(struct safexcel_crypto_priv
 {
 	struct safexcel_request *sreq;
 	struct safexcel_context *ctx;
-	int ret, i, nreq, ndesc, tot_descs, done;
+	int ret, i, nreq, ndesc, tot_descs, handled = 0;
 	bool should_complete;
 
 handle_results:
@@ -659,6 +646,7 @@ handle_results:
 
 		kfree(sreq);
 		tot_descs += ndesc;
+		handled++;
 	}
 
 acknowledge:
@@ -677,11 +665,10 @@ acknowledge:
 requests_left:
 	spin_lock_bh(&priv->ring[ring].egress_lock);
 
-	done = safexcel_try_push_requests(priv, ring,
-					  priv->ring[ring].requests_left);
+	priv->ring[ring].requests -= handled;
+	safexcel_try_push_requests(priv, ring);
 
-	priv->ring[ring].requests_left -= done;
-	if (!done && !priv->ring[ring].requests_left)
+	if (!priv->ring[ring].requests)
 		priv->ring[ring].busy = false;
 
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
@@ -781,6 +768,8 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_sha224,
 	&safexcel_alg_sha256,
 	&safexcel_alg_hmac_sha1,
+	&safexcel_alg_hmac_sha224,
+	&safexcel_alg_hmac_sha256,
 };
 
 static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
@@ -894,29 +883,44 @@ static int safexcel_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->base);
 	}
 
-	priv->clk = of_clk_get(dev->of_node, 0);
-	if (!IS_ERR(priv->clk)) {
+	priv->clk = devm_clk_get(&pdev->dev, NULL);
+	ret = PTR_ERR_OR_ZERO(priv->clk);
+	/* The clock isn't mandatory */
+	if  (ret != -ENOENT) {
+		if (ret)
+			return ret;
+
 		ret = clk_prepare_enable(priv->clk);
 		if (ret) {
 			dev_err(dev, "unable to enable clk (%d)\n", ret);
 			return ret;
 		}
-	} else {
-		/* The clock isn't mandatory */
-		if (PTR_ERR(priv->clk) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
+	}
+
+	priv->reg_clk = devm_clk_get(&pdev->dev, "reg");
+	ret = PTR_ERR_OR_ZERO(priv->reg_clk);
+	/* The clock isn't mandatory */
+	if  (ret != -ENOENT) {
+		if (ret)
+			goto err_core_clk;
+
+		ret = clk_prepare_enable(priv->reg_clk);
+		if (ret) {
+			dev_err(dev, "unable to enable reg clk (%d)\n", ret);
+			goto err_core_clk;
+		}
 	}
 
 	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (ret)
-		goto err_clk;
+		goto err_reg_clk;
 
 	priv->context_pool = dmam_pool_create("safexcel-context", dev,
 					      sizeof(struct safexcel_context_record),
 					      1, 0);
 	if (!priv->context_pool) {
 		ret = -ENOMEM;
-		goto err_clk;
+		goto err_reg_clk;
 	}
 
 	safexcel_configure(priv);
@@ -931,12 +935,12 @@ static int safexcel_probe(struct platform_device *pdev)
 						     &priv->ring[i].cdr,
 						     &priv->ring[i].rdr);
 		if (ret)
-			goto err_clk;
+			goto err_reg_clk;
 
 		ring_irq = devm_kzalloc(dev, sizeof(*ring_irq), GFP_KERNEL);
 		if (!ring_irq) {
 			ret = -ENOMEM;
-			goto err_clk;
+			goto err_reg_clk;
 		}
 
 		ring_irq->priv = priv;
@@ -948,7 +952,7 @@ static int safexcel_probe(struct platform_device *pdev)
 						ring_irq);
 		if (irq < 0) {
 			ret = irq;
-			goto err_clk;
+			goto err_reg_clk;
 		}
 
 		priv->ring[i].work_data.priv = priv;
@@ -959,10 +963,10 @@ static int safexcel_probe(struct platform_device *pdev)
 		priv->ring[i].workqueue = create_singlethread_workqueue(wq_name);
 		if (!priv->ring[i].workqueue) {
 			ret = -ENOMEM;
-			goto err_clk;
+			goto err_reg_clk;
 		}
 
-		priv->ring[i].requests_left = 0;
+		priv->ring[i].requests = 0;
 		priv->ring[i].busy = false;
 
 		crypto_init_queue(&priv->ring[i].queue,
@@ -980,18 +984,20 @@ static int safexcel_probe(struct platform_device *pdev)
 	ret = safexcel_hw_init(priv);
 	if (ret) {
 		dev_err(dev, "EIP h/w init failed (%d)\n", ret);
-		goto err_clk;
+		goto err_reg_clk;
 	}
 
 	ret = safexcel_register_algorithms(priv);
 	if (ret) {
 		dev_err(dev, "Failed to register algorithms (%d)\n", ret);
-		goto err_clk;
+		goto err_reg_clk;
 	}
 
 	return 0;
 
-err_clk:
+err_reg_clk:
+	clk_disable_unprepare(priv->reg_clk);
+err_core_clk:
 	clk_disable_unprepare(priv->clk);
 	return ret;
 }
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 4e219c21608b..b470a849721f 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -135,7 +135,7 @@
 
 /* EIP197_HIA_xDR_DMA_CFG */
 #define EIP197_HIA_xDR_WR_RES_BUF		BIT(22)
-#define EIP197_HIA_xDR_WR_CTRL_BUG		BIT(23)
+#define EIP197_HIA_xDR_WR_CTRL_BUF		BIT(23)
 #define EIP197_HIA_xDR_WR_OWN_BUF		BIT(24)
 #define EIP197_HIA_xDR_CFG_WR_CACHE(n)		(((n) & 0x7) << 25)
 #define EIP197_HIA_xDR_CFG_RD_CACHE(n)		(((n) & 0x7) << 29)
@@ -179,7 +179,7 @@
 #define EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(n)	((n) << 0)
 #define EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(n)	(((n) & 0x7) << 4)
 #define EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(n)	((n) << 8)
-#define EIP197_HIA_DSE_CFG_ALLWAYS_BUFFERABLE	GENMASK(15, 14)
+#define EIP197_HIA_DSE_CFG_ALWAYS_BUFFERABLE	GENMASK(15, 14)
 #define EIP197_HIA_DxE_CFG_MIN_CTRL_SIZE(n)	((n) << 16)
 #define EIP197_HIA_DxE_CFG_CTRL_CACHE_CTRL(n)	(((n) & 0x7) << 20)
 #define EIP197_HIA_DxE_CFG_MAX_CTRL_SIZE(n)	((n) << 24)
@@ -525,6 +525,7 @@ struct safexcel_crypto_priv {
 	void __iomem *base;
 	struct device *dev;
 	struct clk *clk;
+	struct clk *reg_clk;
 	struct safexcel_config config;
 
 	enum safexcel_eip_version version;
@@ -551,10 +552,8 @@ struct safexcel_crypto_priv {
 		struct crypto_queue queue;
 		spinlock_t queue_lock;
 
-		/* Number of requests in the engine that needs the threshold
-		 * interrupt to be set up.
-		 */
-		int requests_left;
+		/* Number of requests in the engine. */
+		int requests;
 
 		/* The ring is currently handling at least one request */
 		bool busy;
@@ -580,12 +579,6 @@ struct safexcel_context {
 	int ring;
 	bool needs_inv;
 	bool exit_inv;
-
-	/* Used for ahash requests */
-	dma_addr_t result_dma;
-	void *cache;
-	dma_addr_t cache_dma;
-	unsigned int cache_sz;
 };
 
 /*
@@ -609,9 +602,6 @@ struct safexcel_inv_result {
 
 void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring);
 void safexcel_complete(struct safexcel_crypto_priv *priv, int ring);
-void safexcel_free_context(struct safexcel_crypto_priv *priv,
-				  struct crypto_async_request *req,
-				  int result_sz);
 int safexcel_invalidate_cache(struct crypto_async_request *async,
 			      struct safexcel_crypto_priv *priv,
 			      dma_addr_t ctxr_dma, int ring,
@@ -643,5 +633,7 @@ extern struct safexcel_alg_template safexcel_alg_sha1;
 extern struct safexcel_alg_template safexcel_alg_sha224;
 extern struct safexcel_alg_template safexcel_alg_sha256;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha1;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha224;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha256;
 
 #endif
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 63a8768ed2ae..bafb60505fab 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -58,7 +58,8 @@ static void safexcel_cipher_token(struct safexcel_cipher_ctx *ctx,
 
 	token[0].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
 	token[0].packet_length = length;
-	token[0].stat = EIP197_TOKEN_STAT_LAST_PACKET;
+	token[0].stat = EIP197_TOKEN_STAT_LAST_PACKET |
+			EIP197_TOKEN_STAT_LAST_HASH;
 	token[0].instructions = EIP197_TOKEN_INS_LAST |
 				EIP197_TOKEN_INS_TYPE_CRYTO |
 				EIP197_TOKEN_INS_TYPE_OUTPUT;
@@ -456,7 +457,7 @@ static int safexcel_cipher_exit_inv(struct crypto_tfm *tfm)
 	queue_work(priv->ring[ring].workqueue,
 		   &priv->ring[ring].work_data.work);
 
-	wait_for_completion_interruptible(&result.completion);
+	wait_for_completion(&result.completion);
 
 	if (result.error) {
 		dev_warn(priv->dev,
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 122a2a58e98f..317b9e480312 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -21,10 +21,9 @@ struct safexcel_ahash_ctx {
 	struct safexcel_crypto_priv *priv;
 
 	u32 alg;
-	u32 digest;
 
-	u32 ipad[SHA1_DIGEST_SIZE / sizeof(u32)];
-	u32 opad[SHA1_DIGEST_SIZE / sizeof(u32)];
+	u32 ipad[SHA256_DIGEST_SIZE / sizeof(u32)];
+	u32 opad[SHA256_DIGEST_SIZE / sizeof(u32)];
 };
 
 struct safexcel_ahash_req {
@@ -34,6 +33,9 @@ struct safexcel_ahash_req {
 	bool needs_inv;
 
 	int nents;
+	dma_addr_t result_dma;
+
+	u32 digest;
 
 	u8 state_sz;    /* expected sate size, only set once */
 	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)] __aligned(sizeof(u32));
@@ -42,6 +44,9 @@ struct safexcel_ahash_req {
 	u64 processed;
 
 	u8 cache[SHA256_BLOCK_SIZE] __aligned(sizeof(u32));
+	dma_addr_t cache_dma;
+	unsigned int cache_sz;
+
 	u8 cache_next[SHA256_BLOCK_SIZE] __aligned(sizeof(u32));
 };
 
@@ -49,6 +54,8 @@ struct safexcel_ahash_export_state {
 	u64 len;
 	u64 processed;
 
+	u32 digest;
+
 	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)];
 	u8 cache[SHA256_BLOCK_SIZE];
 };
@@ -82,9 +89,9 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 
 	cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_HASH_OUT;
 	cdesc->control_data.control0 |= ctx->alg;
-	cdesc->control_data.control0 |= ctx->digest;
+	cdesc->control_data.control0 |= req->digest;
 
-	if (ctx->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED) {
+	if (req->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED) {
 		if (req->processed) {
 			if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
 				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(6);
@@ -112,12 +119,12 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 			if (req->finish)
 				ctx->base.ctxr->data[i] = cpu_to_le32(req->processed / blocksize);
 		}
-	} else if (ctx->digest == CONTEXT_CONTROL_DIGEST_HMAC) {
-		cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(10);
+	} else if (req->digest == CONTEXT_CONTROL_DIGEST_HMAC) {
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(2 * req->state_sz / sizeof(u32));
 
-		memcpy(ctx->base.ctxr->data, ctx->ipad, digestsize);
-		memcpy(ctx->base.ctxr->data + digestsize / sizeof(u32),
-		       ctx->opad, digestsize);
+		memcpy(ctx->base.ctxr->data, ctx->ipad, req->state_sz);
+		memcpy(ctx->base.ctxr->data + req->state_sz / sizeof(u32),
+		       ctx->opad, req->state_sz);
 	}
 }
 
@@ -149,16 +156,26 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	safexcel_complete(priv, ring);
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
-	if (sreq->finish)
-		memcpy(areq->result, sreq->state,
-		       crypto_ahash_digestsize(ahash));
-
 	if (sreq->nents) {
 		dma_unmap_sg(priv->dev, areq->src, sreq->nents, DMA_TO_DEVICE);
 		sreq->nents = 0;
 	}
 
-	safexcel_free_context(priv, async, sreq->state_sz);
+	if (sreq->result_dma) {
+		dma_unmap_single(priv->dev, sreq->result_dma, sreq->state_sz,
+				 DMA_FROM_DEVICE);
+		sreq->result_dma = 0;
+	}
+
+	if (sreq->cache_dma) {
+		dma_unmap_single(priv->dev, sreq->cache_dma, sreq->cache_sz,
+				 DMA_TO_DEVICE);
+		sreq->cache_dma = 0;
+	}
+
+	if (sreq->finish)
+		memcpy(areq->result, sreq->state,
+		       crypto_ahash_digestsize(ahash));
 
 	cache_len = sreq->len - sreq->processed;
 	if (cache_len)
@@ -184,7 +201,7 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 	int i, queued, len, cache_len, extra, n_cdesc = 0, ret = 0;
 
 	queued = len = req->len - req->processed;
-	if (queued < crypto_ahash_blocksize(ahash))
+	if (queued <= crypto_ahash_blocksize(ahash))
 		cache_len = queued;
 	else
 		cache_len = queued - areq->nbytes;
@@ -198,7 +215,7 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 			/* If this is not the last request and the queued data
 			 * is a multiple of a block, cache the last one for now.
 			 */
-			extra = queued - crypto_ahash_blocksize(ahash);
+			extra = crypto_ahash_blocksize(ahash);
 
 		if (extra) {
 			sg_pcopy_to_buffer(areq->src, sg_nents(areq->src),
@@ -220,24 +237,17 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 
 	/* Add a command descriptor for the cached data, if any */
 	if (cache_len) {
-		ctx->base.cache = kzalloc(cache_len, EIP197_GFP_FLAGS(*async));
-		if (!ctx->base.cache) {
-			ret = -ENOMEM;
-			goto unlock;
-		}
-		memcpy(ctx->base.cache, req->cache, cache_len);
-		ctx->base.cache_dma = dma_map_single(priv->dev, ctx->base.cache,
-						     cache_len, DMA_TO_DEVICE);
-		if (dma_mapping_error(priv->dev, ctx->base.cache_dma)) {
-			ret = -EINVAL;
-			goto free_cache;
+		req->cache_dma = dma_map_single(priv->dev, req->cache,
+						cache_len, DMA_TO_DEVICE);
+		if (dma_mapping_error(priv->dev, req->cache_dma)) {
+			spin_unlock_bh(&priv->ring[ring].egress_lock);
+			return -EINVAL;
 		}
 
-		ctx->base.cache_sz = cache_len;
+		req->cache_sz = cache_len;
 		first_cdesc = safexcel_add_cdesc(priv, ring, 1,
 						 (cache_len == len),
-						 ctx->base.cache_dma,
-						 cache_len, len,
+						 req->cache_dma, cache_len, len,
 						 ctx->base.ctxr_dma);
 		if (IS_ERR(first_cdesc)) {
 			ret = PTR_ERR(first_cdesc);
@@ -271,7 +281,7 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 					   sglen, len, ctx->base.ctxr_dma);
 		if (IS_ERR(cdesc)) {
 			ret = PTR_ERR(cdesc);
-			goto cdesc_rollback;
+			goto unmap_sg;
 		}
 		n_cdesc++;
 
@@ -291,19 +301,19 @@ send_command:
 	/* Add the token */
 	safexcel_hash_token(first_cdesc, len, req->state_sz);
 
-	ctx->base.result_dma = dma_map_single(priv->dev, req->state,
-					      req->state_sz, DMA_FROM_DEVICE);
-	if (dma_mapping_error(priv->dev, ctx->base.result_dma)) {
+	req->result_dma = dma_map_single(priv->dev, req->state, req->state_sz,
+					 DMA_FROM_DEVICE);
+	if (dma_mapping_error(priv->dev, req->result_dma)) {
 		ret = -EINVAL;
-		goto cdesc_rollback;
+		goto unmap_sg;
 	}
 
 	/* Add a result descriptor */
-	rdesc = safexcel_add_rdesc(priv, ring, 1, 1, ctx->base.result_dma,
+	rdesc = safexcel_add_rdesc(priv, ring, 1, 1, req->result_dma,
 				   req->state_sz);
 	if (IS_ERR(rdesc)) {
 		ret = PTR_ERR(rdesc);
-		goto cdesc_rollback;
+		goto unmap_result;
 	}
 
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
@@ -315,20 +325,21 @@ send_command:
 	*results = 1;
 	return 0;
 
+unmap_result:
+	dma_unmap_single(priv->dev, req->result_dma, req->state_sz,
+			 DMA_FROM_DEVICE);
+unmap_sg:
+	dma_unmap_sg(priv->dev, areq->src, req->nents, DMA_TO_DEVICE);
 cdesc_rollback:
 	for (i = 0; i < n_cdesc; i++)
 		safexcel_ring_rollback_wptr(priv, &priv->ring[ring].cdr);
 unmap_cache:
-	if (ctx->base.cache_dma) {
-		dma_unmap_single(priv->dev, ctx->base.cache_dma,
-				 ctx->base.cache_sz, DMA_TO_DEVICE);
-		ctx->base.cache_sz = 0;
+	if (req->cache_dma) {
+		dma_unmap_single(priv->dev, req->cache_dma, req->cache_sz,
+				 DMA_TO_DEVICE);
+		req->cache_sz = 0;
 	}
-free_cache:
-	kfree(ctx->base.cache);
-	ctx->base.cache = NULL;
 
-unlock:
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
 	return ret;
 }
@@ -493,7 +504,7 @@ static int safexcel_ahash_exit_inv(struct crypto_tfm *tfm)
 	queue_work(priv->ring[ring].workqueue,
 		   &priv->ring[ring].work_data.work);
 
-	wait_for_completion_interruptible(&result.completion);
+	wait_for_completion(&result.completion);
 
 	if (result.error) {
 		dev_warn(priv->dev, "hash: completion error (%d)\n",
@@ -550,7 +561,7 @@ static int safexcel_ahash_enqueue(struct ahash_request *areq)
 	if (ctx->base.ctxr) {
 		if (priv->version == EIP197 &&
 		    !ctx->base.needs_inv && req->processed &&
-		    ctx->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED)
+		    req->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED)
 			/* We're still setting needs_inv here, even though it is
 			 * cleared right away, because the needs_inv flag can be
 			 * set in other functions and we want to keep the same
@@ -585,7 +596,6 @@ static int safexcel_ahash_enqueue(struct ahash_request *areq)
 
 static int safexcel_ahash_update(struct ahash_request *areq)
 {
-	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
 
@@ -601,7 +611,7 @@ static int safexcel_ahash_update(struct ahash_request *areq)
 	 * We're not doing partial updates when performing an hmac request.
 	 * Everything will be handled by the final() call.
 	 */
-	if (ctx->digest == CONTEXT_CONTROL_DIGEST_HMAC)
+	if (req->digest == CONTEXT_CONTROL_DIGEST_HMAC)
 		return 0;
 
 	if (req->hmac)
@@ -660,6 +670,8 @@ static int safexcel_ahash_export(struct ahash_request *areq, void *out)
 	export->len = req->len;
 	export->processed = req->processed;
 
+	export->digest = req->digest;
+
 	memcpy(export->state, req->state, req->state_sz);
 	memcpy(export->cache, req->cache, crypto_ahash_blocksize(ahash));
 
@@ -680,6 +692,8 @@ static int safexcel_ahash_import(struct ahash_request *areq, const void *in)
 	req->len = export->len;
 	req->processed = export->processed;
 
+	req->digest = export->digest;
+
 	memcpy(req->cache, export->cache, crypto_ahash_blocksize(ahash));
 	memcpy(req->state, export->state, req->state_sz);
 
@@ -716,7 +730,7 @@ static int safexcel_sha1_init(struct ahash_request *areq)
 	req->state[4] = SHA1_H4;
 
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA1;
-	ctx->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA1_DIGEST_SIZE;
 
 	return 0;
@@ -783,10 +797,10 @@ struct safexcel_alg_template safexcel_alg_sha1 = {
 
 static int safexcel_hmac_sha1_init(struct ahash_request *areq)
 {
-	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 
 	safexcel_sha1_init(areq);
-	ctx->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
 	return 0;
 }
 
@@ -839,7 +853,7 @@ static int safexcel_hmac_init_pad(struct ahash_request *areq,
 		init_completion(&result.completion);
 
 		ret = crypto_ahash_digest(areq);
-		if (ret == -EINPROGRESS) {
+		if (ret == -EINPROGRESS || ret == -EBUSY) {
 			wait_for_completion_interruptible(&result.completion);
 			ret = result.error;
 		}
@@ -949,20 +963,21 @@ free_ahash:
 	return ret;
 }
 
-static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
-				     unsigned int keylen)
+static int safexcel_hmac_alg_setkey(struct crypto_ahash *tfm, const u8 *key,
+				    unsigned int keylen, const char *alg,
+				    unsigned int state_sz)
 {
 	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	struct safexcel_ahash_export_state istate, ostate;
 	int ret, i;
 
-	ret = safexcel_hmac_setkey("safexcel-sha1", key, keylen, &istate, &ostate);
+	ret = safexcel_hmac_setkey(alg, key, keylen, &istate, &ostate);
 	if (ret)
 		return ret;
 
 	if (priv->version == EIP197 && ctx->base.ctxr) {
-		for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(u32); i++) {
+		for (i = 0; i < state_sz / sizeof(u32); i++) {
 			if (ctx->ipad[i] != le32_to_cpu(istate.state[i]) ||
 			    ctx->opad[i] != le32_to_cpu(ostate.state[i])) {
 				ctx->base.needs_inv = true;
@@ -971,12 +986,19 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
 		}
 	}
 
-	memcpy(ctx->ipad, &istate.state, SHA1_DIGEST_SIZE);
-	memcpy(ctx->opad, &ostate.state, SHA1_DIGEST_SIZE);
+	memcpy(ctx->ipad, &istate.state, state_sz);
+	memcpy(ctx->opad, &ostate.state, state_sz);
 
 	return 0;
 }
 
+static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
+				     unsigned int keylen)
+{
+	return safexcel_hmac_alg_setkey(tfm, key, keylen, "safexcel-sha1",
+					SHA1_DIGEST_SIZE);
+}
+
 struct safexcel_alg_template safexcel_alg_hmac_sha1 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
 	.alg.ahash = {
@@ -1024,7 +1046,7 @@ static int safexcel_sha256_init(struct ahash_request *areq)
 	req->state[7] = SHA256_H7;
 
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA256;
-	ctx->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA256_DIGEST_SIZE;
 
 	return 0;
@@ -1086,7 +1108,7 @@ static int safexcel_sha224_init(struct ahash_request *areq)
 	req->state[7] = SHA224_H7;
 
 	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA224;
-	ctx->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
 	req->state_sz = SHA256_DIGEST_SIZE;
 
 	return 0;
@@ -1130,3 +1152,115 @@ struct safexcel_alg_template safexcel_alg_sha224 = {
 		},
 	},
 };
+
+static int safexcel_hmac_sha224_setkey(struct crypto_ahash *tfm, const u8 *key,
+				       unsigned int keylen)
+{
+	return safexcel_hmac_alg_setkey(tfm, key, keylen, "safexcel-sha224",
+					SHA256_DIGEST_SIZE);
+}
+
+static int safexcel_hmac_sha224_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	safexcel_sha224_init(areq);
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	return 0;
+}
+
+static int safexcel_hmac_sha224_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_hmac_sha224_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sha224 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha224_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_hmac_sha224_digest,
+		.setkey = safexcel_hmac_sha224_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA224_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha224)",
+				.cra_driver_name = "safexcel-hmac-sha224",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA224_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_hmac_sha256_setkey(struct crypto_ahash *tfm, const u8 *key,
+				     unsigned int keylen)
+{
+	return safexcel_hmac_alg_setkey(tfm, key, keylen, "safexcel-sha256",
+					SHA256_DIGEST_SIZE);
+}
+
+static int safexcel_hmac_sha256_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	safexcel_sha256_init(areq);
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	return 0;
+}
+
+static int safexcel_hmac_sha256_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_hmac_sha256_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sha256 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha256_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_hmac_sha256_digest,
+		.setkey = safexcel_hmac_sha256_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA256_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha256)",
+				.cra_driver_name = "safexcel-hmac-sha256",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA256_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 717a26607bdb..27f7dad2d45d 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -1167,9 +1167,11 @@ static int aead_setkey(struct crypto_aead *tfm, const u8 *key,
 	ctx->authkey_len = keys.authkeylen;
 	ctx->enckey_len = keys.enckeylen;
 
+	memzero_explicit(&keys, sizeof(keys));
 	return aead_setup(tfm, crypto_aead_authsize(tfm));
 badkey:
 	crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	memzero_explicit(&keys, sizeof(keys));
 	return -EINVAL;
 }
 
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index aca2373fa1de..f81fa4a3e66b 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -25,7 +25,6 @@
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <linux/dma-direct.h> /* XXX: drivers shall never use this directly! */
 #include <linux/clk.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
index 764be3e6933c..a10c418d4e5c 100644
--- a/drivers/crypto/mxs-dcp.c
+++ b/drivers/crypto/mxs-dcp.c
@@ -759,6 +759,16 @@ static int dcp_sha_digest(struct ahash_request *req)
 	return dcp_sha_finup(req);
 }
 
+static int dcp_sha_noimport(struct ahash_request *req, const void *in)
+{
+	return -ENOSYS;
+}
+
+static int dcp_sha_noexport(struct ahash_request *req, void *out)
+{
+	return -ENOSYS;
+}
+
 static int dcp_sha_cra_init(struct crypto_tfm *tfm)
 {
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
@@ -829,6 +839,8 @@ static struct ahash_alg dcp_sha1_alg = {
 	.final	= dcp_sha_final,
 	.finup	= dcp_sha_finup,
 	.digest	= dcp_sha_digest,
+	.import = dcp_sha_noimport,
+	.export = dcp_sha_noexport,
 	.halg	= {
 		.digestsize	= SHA1_DIGEST_SIZE,
 		.base		= {
@@ -853,6 +865,8 @@ static struct ahash_alg dcp_sha256_alg = {
 	.final	= dcp_sha_final,
 	.finup	= dcp_sha_finup,
 	.digest	= dcp_sha_digest,
+	.import = dcp_sha_noimport,
+	.export = dcp_sha_noexport,
 	.halg	= {
 		.digestsize	= SHA256_DIGEST_SIZE,
 		.base		= {
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index 662e709812cc..80e9c842aad4 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -359,6 +359,16 @@ static int n2_hash_async_finup(struct ahash_request *req)
 	return crypto_ahash_finup(&rctx->fallback_req);
 }
 
+static int n2_hash_async_noimport(struct ahash_request *req, const void *in)
+{
+	return -ENOSYS;
+}
+
+static int n2_hash_async_noexport(struct ahash_request *req, void *out)
+{
+	return -ENOSYS;
+}
+
 static int n2_hash_cra_init(struct crypto_tfm *tfm)
 {
 	const char *fallback_driver_name = crypto_tfm_alg_name(tfm);
@@ -1467,6 +1477,8 @@ static int __n2_register_one_ahash(const struct n2_hash_tmpl *tmpl)
 	ahash->final = n2_hash_async_final;
 	ahash->finup = n2_hash_async_finup;
 	ahash->digest = n2_hash_async_digest;
+	ahash->export = n2_hash_async_noexport;
+	ahash->import = n2_hash_async_noimport;
 
 	halg = &ahash->halg;
 	halg->digestsize = tmpl->digest_size;
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index bf52cd1d7fca..66869976cfa2 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -1105,10 +1105,9 @@ static int __init nx842_pseries_init(void)
 
 	RCU_INIT_POINTER(devdata, NULL);
 	new_devdata = kzalloc(sizeof(*new_devdata), GFP_KERNEL);
-	if (!new_devdata) {
-		pr_err("Could not allocate memory for device data\n");
+	if (!new_devdata)
 		return -ENOMEM;
-	}
+
 	RCU_INIT_POINTER(devdata, new_devdata);
 
 	ret = vio_register_driver(&nx842_vio_driver);
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index fbec0a2e76dd..9019f6b67986 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -47,6 +47,8 @@
 static LIST_HEAD(dev_list);
 static DEFINE_SPINLOCK(list_lock);
 
+static int aes_fallback_sz = 200;
+
 #ifdef DEBUG
 #define omap_aes_read(dd, offset)				\
 ({								\
@@ -388,7 +390,7 @@ static void omap_aes_finish_req(struct omap_aes_dev *dd, int err)
 
 	pr_debug("err: %d\n", err);
 
-	crypto_finalize_cipher_request(dd->engine, req, err);
+	crypto_finalize_ablkcipher_request(dd->engine, req, err);
 
 	pm_runtime_mark_last_busy(dd->dev);
 	pm_runtime_put_autosuspend(dd->dev);
@@ -408,14 +410,15 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd,
 				 struct ablkcipher_request *req)
 {
 	if (req)
-		return crypto_transfer_cipher_request_to_engine(dd->engine, req);
+		return crypto_transfer_ablkcipher_request_to_engine(dd->engine, req);
 
 	return 0;
 }
 
 static int omap_aes_prepare_req(struct crypto_engine *engine,
-				struct ablkcipher_request *req)
+				void *areq)
 {
+	struct ablkcipher_request *req = container_of(areq, struct ablkcipher_request, base);
 	struct omap_aes_ctx *ctx = crypto_ablkcipher_ctx(
 			crypto_ablkcipher_reqtfm(req));
 	struct omap_aes_reqctx *rctx = ablkcipher_request_ctx(req);
@@ -468,8 +471,9 @@ static int omap_aes_prepare_req(struct crypto_engine *engine,
 }
 
 static int omap_aes_crypt_req(struct crypto_engine *engine,
-			      struct ablkcipher_request *req)
+			      void *areq)
 {
+	struct ablkcipher_request *req = container_of(areq, struct ablkcipher_request, base);
 	struct omap_aes_reqctx *rctx = ablkcipher_request_ctx(req);
 	struct omap_aes_dev *dd = rctx->dd;
 
@@ -517,7 +521,7 @@ static int omap_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 		  !!(mode & FLAGS_ENCRYPT),
 		  !!(mode & FLAGS_CBC));
 
-	if (req->nbytes < 200) {
+	if (req->nbytes < aes_fallback_sz) {
 		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
 
 		skcipher_request_set_tfm(subreq, ctx->fallback);
@@ -601,6 +605,11 @@ static int omap_aes_ctr_decrypt(struct ablkcipher_request *req)
 	return omap_aes_crypt(req, FLAGS_CTR);
 }
 
+static int omap_aes_prepare_req(struct crypto_engine *engine,
+				void *req);
+static int omap_aes_crypt_req(struct crypto_engine *engine,
+			      void *req);
+
 static int omap_aes_cra_init(struct crypto_tfm *tfm)
 {
 	const char *name = crypto_tfm_alg_name(tfm);
@@ -616,6 +625,10 @@ static int omap_aes_cra_init(struct crypto_tfm *tfm)
 
 	tfm->crt_ablkcipher.reqsize = sizeof(struct omap_aes_reqctx);
 
+	ctx->enginectx.op.prepare_request = omap_aes_prepare_req;
+	ctx->enginectx.op.unprepare_request = NULL;
+	ctx->enginectx.op.do_one_request = omap_aes_crypt_req;
+
 	return 0;
 }
 
@@ -1029,6 +1042,87 @@ err:
 	return err;
 }
 
+static ssize_t fallback_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	return sprintf(buf, "%d\n", aes_fallback_sz);
+}
+
+static ssize_t fallback_store(struct device *dev, struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	ssize_t status;
+	long value;
+
+	status = kstrtol(buf, 0, &value);
+	if (status)
+		return status;
+
+	/* HW accelerator only works with buffers > 9 */
+	if (value < 9) {
+		dev_err(dev, "minimum fallback size 9\n");
+		return -EINVAL;
+	}
+
+	aes_fallback_sz = value;
+
+	return size;
+}
+
+static ssize_t queue_len_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	struct omap_aes_dev *dd = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", dd->engine->queue.max_qlen);
+}
+
+static ssize_t queue_len_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t size)
+{
+	struct omap_aes_dev *dd;
+	ssize_t status;
+	long value;
+	unsigned long flags;
+
+	status = kstrtol(buf, 0, &value);
+	if (status)
+		return status;
+
+	if (value < 1)
+		return -EINVAL;
+
+	/*
+	 * Changing the queue size in fly is safe, if size becomes smaller
+	 * than current size, it will just not accept new entries until
+	 * it has shrank enough.
+	 */
+	spin_lock_bh(&list_lock);
+	list_for_each_entry(dd, &dev_list, list) {
+		spin_lock_irqsave(&dd->lock, flags);
+		dd->engine->queue.max_qlen = value;
+		dd->aead_queue.base.max_qlen = value;
+		spin_unlock_irqrestore(&dd->lock, flags);
+	}
+	spin_unlock_bh(&list_lock);
+
+	return size;
+}
+
+static DEVICE_ATTR_RW(queue_len);
+static DEVICE_ATTR_RW(fallback);
+
+static struct attribute *omap_aes_attrs[] = {
+	&dev_attr_queue_len.attr,
+	&dev_attr_fallback.attr,
+	NULL,
+};
+
+static struct attribute_group omap_aes_attr_group = {
+	.attrs = omap_aes_attrs,
+};
+
 static int omap_aes_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1119,8 +1213,6 @@ static int omap_aes_probe(struct platform_device *pdev)
 		goto err_engine;
 	}
 
-	dd->engine->prepare_cipher_request = omap_aes_prepare_req;
-	dd->engine->cipher_one_request = omap_aes_crypt_req;
 	err = crypto_engine_start(dd->engine);
 	if (err)
 		goto err_engine;
@@ -1159,6 +1251,12 @@ static int omap_aes_probe(struct platform_device *pdev)
 		}
 	}
 
+	err = sysfs_create_group(&dev->kobj, &omap_aes_attr_group);
+	if (err) {
+		dev_err(dev, "could not create sysfs device attrs\n");
+		goto err_aead_algs;
+	}
+
 	return 0;
 err_aead_algs:
 	for (i = dd->pdata->aead_algs_info->registered - 1; i >= 0; i--) {
diff --git a/drivers/crypto/omap-aes.h b/drivers/crypto/omap-aes.h
index 8906342e2b9a..fc3b46a85809 100644
--- a/drivers/crypto/omap-aes.h
+++ b/drivers/crypto/omap-aes.h
@@ -13,6 +13,8 @@
 #ifndef __OMAP_AES_H__
 #define __OMAP_AES_H__
 
+#include <crypto/engine.h>
+
 #define DST_MAXBURST			4
 #define DMA_MIN				(DST_MAXBURST * sizeof(u32))
 
@@ -95,6 +97,7 @@ struct omap_aes_gcm_result {
 };
 
 struct omap_aes_ctx {
+	struct crypto_engine_ctx enginectx;
 	int		keylen;
 	u32		key[AES_KEYSIZE_256 / sizeof(u32)];
 	u8		nonce[4];
diff --git a/drivers/crypto/omap-crypto.c b/drivers/crypto/omap-crypto.c
index 23e37779317e..2c42e4b4a6e9 100644
--- a/drivers/crypto/omap-crypto.c
+++ b/drivers/crypto/omap-crypto.c
@@ -104,6 +104,10 @@ static int omap_crypto_check_sg(struct scatterlist *sg, int total, int bs,
 			return OMAP_CRYPTO_NOT_ALIGNED;
 		if (!IS_ALIGNED(sg->length, bs))
 			return OMAP_CRYPTO_NOT_ALIGNED;
+#ifdef CONFIG_ZONE_DMA
+		if (page_zonenum(sg_page(sg)) != ZONE_DMA)
+			return OMAP_CRYPTO_NOT_ALIGNED;
+#endif
 
 		len += sg->length;
 		sg = sg_next(sg);
diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c
index ebc5c0f11f03..eb95b0d7f184 100644
--- a/drivers/crypto/omap-des.c
+++ b/drivers/crypto/omap-des.c
@@ -86,6 +86,7 @@
 #define FLAGS_OUT_DATA_ST_SHIFT	10
 
 struct omap_des_ctx {
+	struct crypto_engine_ctx enginectx;
 	struct omap_des_dev *dd;
 
 	int		keylen;
@@ -498,7 +499,7 @@ static void omap_des_finish_req(struct omap_des_dev *dd, int err)
 
 	pr_debug("err: %d\n", err);
 
-	crypto_finalize_cipher_request(dd->engine, req, err);
+	crypto_finalize_ablkcipher_request(dd->engine, req, err);
 
 	pm_runtime_mark_last_busy(dd->dev);
 	pm_runtime_put_autosuspend(dd->dev);
@@ -520,14 +521,15 @@ static int omap_des_handle_queue(struct omap_des_dev *dd,
 				 struct ablkcipher_request *req)
 {
 	if (req)
-		return crypto_transfer_cipher_request_to_engine(dd->engine, req);
+		return crypto_transfer_ablkcipher_request_to_engine(dd->engine, req);
 
 	return 0;
 }
 
 static int omap_des_prepare_req(struct crypto_engine *engine,
-				struct ablkcipher_request *req)
+				void *areq)
 {
+	struct ablkcipher_request *req = container_of(areq, struct ablkcipher_request, base);
 	struct omap_des_ctx *ctx = crypto_ablkcipher_ctx(
 			crypto_ablkcipher_reqtfm(req));
 	struct omap_des_dev *dd = omap_des_find_dev(ctx);
@@ -582,8 +584,9 @@ static int omap_des_prepare_req(struct crypto_engine *engine,
 }
 
 static int omap_des_crypt_req(struct crypto_engine *engine,
-			      struct ablkcipher_request *req)
+			      void *areq)
 {
+	struct ablkcipher_request *req = container_of(areq, struct ablkcipher_request, base);
 	struct omap_des_ctx *ctx = crypto_ablkcipher_ctx(
 			crypto_ablkcipher_reqtfm(req));
 	struct omap_des_dev *dd = omap_des_find_dev(ctx);
@@ -695,12 +698,23 @@ static int omap_des_cbc_decrypt(struct ablkcipher_request *req)
 	return omap_des_crypt(req, FLAGS_CBC);
 }
 
+static int omap_des_prepare_req(struct crypto_engine *engine,
+				void *areq);
+static int omap_des_crypt_req(struct crypto_engine *engine,
+			      void *areq);
+
 static int omap_des_cra_init(struct crypto_tfm *tfm)
 {
+	struct omap_des_ctx *ctx = crypto_tfm_ctx(tfm);
+
 	pr_debug("enter\n");
 
 	tfm->crt_ablkcipher.reqsize = sizeof(struct omap_des_reqctx);
 
+	ctx->enginectx.op.prepare_request = omap_des_prepare_req;
+	ctx->enginectx.op.unprepare_request = NULL;
+	ctx->enginectx.op.do_one_request = omap_des_crypt_req;
+
 	return 0;
 }
 
@@ -1046,8 +1060,6 @@ static int omap_des_probe(struct platform_device *pdev)
 		goto err_engine;
 	}
 
-	dd->engine->prepare_cipher_request = omap_des_prepare_req;
-	dd->engine->cipher_one_request = omap_des_crypt_req;
 	err = crypto_engine_start(dd->engine);
 	if (err)
 		goto err_engine;
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index 86b89ace836f..ad02aa63b519 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -229,6 +229,7 @@ struct omap_sham_dev {
 	u8			xmit_buf[BUFLEN] OMAP_ALIGNED;
 
 	unsigned long		flags;
+	int			fallback_sz;
 	struct crypto_queue	queue;
 	struct ahash_request	*req;
 
@@ -759,6 +760,13 @@ static int omap_sham_align_sgs(struct scatterlist *sg,
 	while (nbytes > 0 && sg_tmp) {
 		n++;
 
+#ifdef CONFIG_ZONE_DMA
+		if (page_zonenum(sg_page(sg_tmp)) != ZONE_DMA) {
+			aligned = false;
+			break;
+		}
+#endif
+
 		if (offset < sg_tmp->length) {
 			if (!IS_ALIGNED(offset + sg_tmp->offset, 4)) {
 				aligned = false;
@@ -809,9 +817,6 @@ static int omap_sham_prepare_request(struct ahash_request *req, bool update)
 	bool final = rctx->flags & BIT(FLAGS_FINUP);
 	int xmit_len, hash_later;
 
-	if (!req)
-		return 0;
-
 	bs = get_block_size(rctx);
 
 	if (update)
@@ -1002,7 +1007,7 @@ static int omap_sham_update_req(struct omap_sham_dev *dd)
 		 ctx->total, ctx->digcnt, (ctx->flags & BIT(FLAGS_FINUP)) != 0);
 
 	if (ctx->total < get_block_size(ctx) ||
-	    ctx->total < OMAP_SHA_DMA_THRESHOLD)
+	    ctx->total < dd->fallback_sz)
 		ctx->flags |= BIT(FLAGS_CPU);
 
 	if (ctx->flags & BIT(FLAGS_CPU))
@@ -1258,11 +1263,11 @@ static int omap_sham_final(struct ahash_request *req)
 	/*
 	 * OMAP HW accel works only with buffers >= 9.
 	 * HMAC is always >= 9 because ipad == block size.
-	 * If buffersize is less than DMA_THRESHOLD, we use fallback
+	 * If buffersize is less than fallback_sz, we use fallback
 	 * SW encoding, as using DMA + HW in this case doesn't provide
 	 * any benefit.
 	 */
-	if (!ctx->digcnt && ctx->bufcnt < OMAP_SHA_DMA_THRESHOLD)
+	if (!ctx->digcnt && ctx->bufcnt < ctx->dd->fallback_sz)
 		return omap_sham_final_shash(req);
 	else if (ctx->bufcnt)
 		return omap_sham_enqueue(req, OP_FINAL);
@@ -1761,7 +1766,7 @@ static void omap_sham_done_task(unsigned long data)
 		if (test_and_clear_bit(FLAGS_OUTPUT_READY, &dd->flags)) {
 			/* hash or semi-hash ready */
 			clear_bit(FLAGS_DMA_READY, &dd->flags);
-				goto finish;
+			goto finish;
 		}
 	}
 
@@ -2013,6 +2018,85 @@ err:
 	return err;
 }
 
+static ssize_t fallback_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct omap_sham_dev *dd = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", dd->fallback_sz);
+}
+
+static ssize_t fallback_store(struct device *dev, struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	struct omap_sham_dev *dd = dev_get_drvdata(dev);
+	ssize_t status;
+	long value;
+
+	status = kstrtol(buf, 0, &value);
+	if (status)
+		return status;
+
+	/* HW accelerator only works with buffers > 9 */
+	if (value < 9) {
+		dev_err(dev, "minimum fallback size 9\n");
+		return -EINVAL;
+	}
+
+	dd->fallback_sz = value;
+
+	return size;
+}
+
+static ssize_t queue_len_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	struct omap_sham_dev *dd = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", dd->queue.max_qlen);
+}
+
+static ssize_t queue_len_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t size)
+{
+	struct omap_sham_dev *dd = dev_get_drvdata(dev);
+	ssize_t status;
+	long value;
+	unsigned long flags;
+
+	status = kstrtol(buf, 0, &value);
+	if (status)
+		return status;
+
+	if (value < 1)
+		return -EINVAL;
+
+	/*
+	 * Changing the queue size in fly is safe, if size becomes smaller
+	 * than current size, it will just not accept new entries until
+	 * it has shrank enough.
+	 */
+	spin_lock_irqsave(&dd->lock, flags);
+	dd->queue.max_qlen = value;
+	spin_unlock_irqrestore(&dd->lock, flags);
+
+	return size;
+}
+
+static DEVICE_ATTR_RW(queue_len);
+static DEVICE_ATTR_RW(fallback);
+
+static struct attribute *omap_sham_attrs[] = {
+	&dev_attr_queue_len.attr,
+	&dev_attr_fallback.attr,
+	NULL,
+};
+
+static struct attribute_group omap_sham_attr_group = {
+	.attrs = omap_sham_attrs,
+};
+
 static int omap_sham_probe(struct platform_device *pdev)
 {
 	struct omap_sham_dev *dd;
@@ -2074,6 +2158,8 @@ static int omap_sham_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_set_autosuspend_delay(dev, DEFAULT_AUTOSUSPEND_DELAY);
 
+	dd->fallback_sz = OMAP_SHA_DMA_THRESHOLD;
+
 	pm_runtime_enable(dev);
 	pm_runtime_irq_safe(dev);
 
@@ -2111,6 +2197,12 @@ static int omap_sham_probe(struct platform_device *pdev)
 		}
 	}
 
+	err = sysfs_create_group(&dev->kobj, &omap_sham_attr_group);
+	if (err) {
+		dev_err(dev, "could not create sysfs device attrs\n");
+		goto err_algs;
+	}
+
 	return 0;
 
 err_algs:
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index 4ef52c9d72fc..a4df966adbf6 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -499,10 +499,12 @@ static int spacc_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 	memcpy(ctx->hash_ctx, keys.authkey, keys.authkeylen);
 	ctx->hash_key_len = keys.authkeylen;
 
+	memzero_explicit(&keys, sizeof(keys));
 	return 0;
 
 badkey:
 	crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	memzero_explicit(&keys, sizeof(keys));
 	return -EINVAL;
 }
 
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index baffae817259..1138e41d6805 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -546,11 +546,14 @@ static int qat_alg_aead_init_sessions(struct crypto_aead *tfm, const u8 *key,
 	if (qat_alg_aead_init_dec_session(tfm, alg, &keys, mode))
 		goto error;
 
+	memzero_explicit(&keys, sizeof(keys));
 	return 0;
 bad_key:
 	crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	memzero_explicit(&keys, sizeof(keys));
 	return -EINVAL;
 error:
+	memzero_explicit(&keys, sizeof(keys));
 	return -EFAULT;
 }
 
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c
index 13c52d6bf630..320e7854b4ee 100644
--- a/drivers/crypto/qat/qat_common/qat_asym_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c
@@ -969,7 +969,8 @@ unmap_src:
 	return ret;
 }
 
-int qat_rsa_set_n(struct qat_rsa_ctx *ctx, const char *value, size_t vlen)
+static int qat_rsa_set_n(struct qat_rsa_ctx *ctx, const char *value,
+			 size_t vlen)
 {
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
@@ -1000,7 +1001,8 @@ err:
 	return ret;
 }
 
-int qat_rsa_set_e(struct qat_rsa_ctx *ctx, const char *value, size_t vlen)
+static int qat_rsa_set_e(struct qat_rsa_ctx *ctx, const char *value,
+			 size_t vlen)
 {
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
@@ -1024,7 +1026,8 @@ int qat_rsa_set_e(struct qat_rsa_ctx *ctx, const char *value, size_t vlen)
 	return 0;
 }
 
-int qat_rsa_set_d(struct qat_rsa_ctx *ctx, const char *value, size_t vlen)
+static int qat_rsa_set_d(struct qat_rsa_ctx *ctx, const char *value,
+			 size_t vlen)
 {
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index 5d64c08b7f47..bf7163042569 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -404,29 +404,31 @@ static const struct of_device_id s5p_sss_dt_match[] = {
 };
 MODULE_DEVICE_TABLE(of, s5p_sss_dt_match);
 
-static inline struct samsung_aes_variant *find_s5p_sss_version
-				   (struct platform_device *pdev)
+static inline const struct samsung_aes_variant *find_s5p_sss_version
+				   (const struct platform_device *pdev)
 {
 	if (IS_ENABLED(CONFIG_OF) && (pdev->dev.of_node)) {
 		const struct of_device_id *match;
 
 		match = of_match_node(s5p_sss_dt_match,
 					pdev->dev.of_node);
-		return (struct samsung_aes_variant *)match->data;
+		return (const struct samsung_aes_variant *)match->data;
 	}
-	return (struct samsung_aes_variant *)
+	return (const struct samsung_aes_variant *)
 			platform_get_device_id(pdev)->driver_data;
 }
 
 static struct s5p_aes_dev *s5p_dev;
 
-static void s5p_set_dma_indata(struct s5p_aes_dev *dev, struct scatterlist *sg)
+static void s5p_set_dma_indata(struct s5p_aes_dev *dev,
+			       const struct scatterlist *sg)
 {
 	SSS_WRITE(dev, FCBRDMAS, sg_dma_address(sg));
 	SSS_WRITE(dev, FCBRDMAL, sg_dma_len(sg));
 }
 
-static void s5p_set_dma_outdata(struct s5p_aes_dev *dev, struct scatterlist *sg)
+static void s5p_set_dma_outdata(struct s5p_aes_dev *dev,
+				const struct scatterlist *sg)
 {
 	SSS_WRITE(dev, FCBTDMAS, sg_dma_address(sg));
 	SSS_WRITE(dev, FCBTDMAL, sg_dma_len(sg));
@@ -619,7 +621,7 @@ static inline void s5p_hash_write(struct s5p_aes_dev *dd,
  * @sg:		scatterlist ready to DMA transmit
  */
 static void s5p_set_dma_hashdata(struct s5p_aes_dev *dev,
-				 struct scatterlist *sg)
+				 const struct scatterlist *sg)
 {
 	dev->hash_sg_cnt--;
 	SSS_WRITE(dev, FCHRDMAS, sg_dma_address(sg));
@@ -792,9 +794,9 @@ static void s5p_hash_read_msg(struct ahash_request *req)
  * @ctx:	request context
  */
 static void s5p_hash_write_ctx_iv(struct s5p_aes_dev *dd,
-				  struct s5p_hash_reqctx *ctx)
+				  const struct s5p_hash_reqctx *ctx)
 {
-	u32 *hash = (u32 *)ctx->digest;
+	const u32 *hash = (const u32 *)ctx->digest;
 	unsigned int i;
 
 	for (i = 0; i < ctx->nregs; i++)
@@ -818,7 +820,7 @@ static void s5p_hash_write_iv(struct ahash_request *req)
  */
 static void s5p_hash_copy_result(struct ahash_request *req)
 {
-	struct s5p_hash_reqctx *ctx = ahash_request_ctx(req);
+	const struct s5p_hash_reqctx *ctx = ahash_request_ctx(req);
 
 	if (!req->result)
 		return;
@@ -1210,9 +1212,6 @@ static int s5p_hash_prepare_request(struct ahash_request *req, bool update)
 	int xmit_len, hash_later, nbytes;
 	int ret;
 
-	if (!req)
-		return 0;
-
 	if (update)
 		nbytes = req->nbytes;
 	else
@@ -1293,7 +1292,7 @@ static int s5p_hash_prepare_request(struct ahash_request *req, bool update)
  */
 static void s5p_hash_update_dma_stop(struct s5p_aes_dev *dd)
 {
-	struct s5p_hash_reqctx *ctx = ahash_request_ctx(dd->hash_req);
+	const struct s5p_hash_reqctx *ctx = ahash_request_ctx(dd->hash_req);
 
 	dma_unmap_sg(dd->dev, ctx->sg, ctx->sg_len, DMA_TO_DEVICE);
 	clear_bit(HASH_FLAGS_DMA_ACTIVE, &dd->hash_flags);
@@ -1720,7 +1719,7 @@ static void s5p_hash_cra_exit(struct crypto_tfm *tfm)
  */
 static int s5p_hash_export(struct ahash_request *req, void *out)
 {
-	struct s5p_hash_reqctx *ctx = ahash_request_ctx(req);
+	const struct s5p_hash_reqctx *ctx = ahash_request_ctx(req);
 
 	memcpy(out, ctx, sizeof(*ctx) + ctx->bufcnt);
 
@@ -1834,7 +1833,8 @@ static struct ahash_alg algs_sha1_md5_sha256[] = {
 };
 
 static void s5p_set_aes(struct s5p_aes_dev *dev,
-			uint8_t *key, uint8_t *iv, unsigned int keylen)
+			const uint8_t *key, const uint8_t *iv,
+			unsigned int keylen)
 {
 	void __iomem *keystart;
 
@@ -2153,7 +2153,7 @@ static int s5p_aes_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	int i, j, err = -ENODEV;
-	struct samsung_aes_variant *variant;
+	const struct samsung_aes_variant *variant;
 	struct s5p_aes_dev *pdata;
 	struct resource *res;
 	unsigned int hash_i;
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 08e7bdcaa6e3..0f2245e1af2b 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -1397,11 +1397,9 @@ static int sahara_probe(struct platform_device *pdev)
 	int err;
 	int i;
 
-	dev = devm_kzalloc(&pdev->dev, sizeof(struct sahara_dev), GFP_KERNEL);
-	if (dev == NULL) {
-		dev_err(&pdev->dev, "unable to alloc data struct.\n");
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
 		return -ENOMEM;
-	}
 
 	dev->device = &pdev->dev;
 	platform_set_drvdata(pdev, dev);
diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c
index 4a06a7a665ee..c5d3efc54a4f 100644
--- a/drivers/crypto/stm32/stm32-cryp.c
+++ b/drivers/crypto/stm32/stm32-cryp.c
@@ -17,6 +17,7 @@
 #include <crypto/des.h>
 #include <crypto/engine.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/internal/aead.h>
 
 #define DRIVER_NAME             "stm32-cryp"
 
@@ -29,8 +30,12 @@
 #define FLG_ECB                 BIT(4)
 #define FLG_CBC                 BIT(5)
 #define FLG_CTR                 BIT(6)
+#define FLG_GCM                 BIT(7)
+#define FLG_CCM                 BIT(8)
 /* Mode mask = bits [15..0] */
 #define FLG_MODE_MASK           GENMASK(15, 0)
+/* Bit [31..16] status  */
+#define FLG_CCM_PADDED_WA       BIT(16)
 
 /* Registers */
 #define CRYP_CR                 0x00000000
@@ -53,6 +58,8 @@
 #define CRYP_IV0RR              0x00000044
 #define CRYP_IV1LR              0x00000048
 #define CRYP_IV1RR              0x0000004C
+#define CRYP_CSGCMCCM0R         0x00000050
+#define CRYP_CSGCM0R            0x00000070
 
 /* Registers values */
 #define CR_DEC_NOT_ENC          0x00000004
@@ -64,6 +71,8 @@
 #define CR_AES_CBC              0x00000028
 #define CR_AES_CTR              0x00000030
 #define CR_AES_KP               0x00000038
+#define CR_AES_GCM              0x00080000
+#define CR_AES_CCM              0x00080008
 #define CR_AES_UNKNOWN          0xFFFFFFFF
 #define CR_ALGO_MASK            0x00080038
 #define CR_DATA32               0x00000000
@@ -75,6 +84,12 @@
 #define CR_KEY256               0x00000200
 #define CR_FFLUSH               0x00004000
 #define CR_CRYPEN               0x00008000
+#define CR_PH_INIT              0x00000000
+#define CR_PH_HEADER            0x00010000
+#define CR_PH_PAYLOAD           0x00020000
+#define CR_PH_FINAL             0x00030000
+#define CR_PH_MASK              0x00030000
+#define CR_NBPBL_SHIFT          20
 
 #define SR_BUSY                 0x00000010
 #define SR_OFNE                 0x00000004
@@ -87,10 +102,17 @@
 
 /* Misc */
 #define AES_BLOCK_32            (AES_BLOCK_SIZE / sizeof(u32))
+#define GCM_CTR_INIT            2
 #define _walked_in              (cryp->in_walk.offset - cryp->in_sg->offset)
 #define _walked_out             (cryp->out_walk.offset - cryp->out_sg->offset)
 
+struct stm32_cryp_caps {
+	bool                    swap_final;
+	bool                    padding_wa;
+};
+
 struct stm32_cryp_ctx {
+	struct crypto_engine_ctx enginectx;
 	struct stm32_cryp       *cryp;
 	int                     keylen;
 	u32                     key[AES_KEYSIZE_256 / sizeof(u32)];
@@ -108,13 +130,16 @@ struct stm32_cryp {
 	struct clk              *clk;
 	unsigned long           flags;
 	u32                     irq_status;
+	const struct stm32_cryp_caps *caps;
 	struct stm32_cryp_ctx   *ctx;
 
 	struct crypto_engine    *engine;
 
-	struct mutex            lock; /* protects req */
+	struct mutex            lock; /* protects req / areq */
 	struct ablkcipher_request *req;
+	struct aead_request     *areq;
 
+	size_t                  authsize;
 	size_t                  hw_blocksize;
 
 	size_t                  total_in;
@@ -137,6 +162,7 @@ struct stm32_cryp {
 	struct scatter_walk     out_walk;
 
 	u32                     last_ctr[4];
+	u32                     gcm_ctr;
 };
 
 struct stm32_cryp_list {
@@ -179,6 +205,16 @@ static inline bool is_ctr(struct stm32_cryp *cryp)
 	return cryp->flags & FLG_CTR;
 }
 
+static inline bool is_gcm(struct stm32_cryp *cryp)
+{
+	return cryp->flags & FLG_GCM;
+}
+
+static inline bool is_ccm(struct stm32_cryp *cryp)
+{
+	return cryp->flags & FLG_CCM;
+}
+
 static inline bool is_encrypt(struct stm32_cryp *cryp)
 {
 	return cryp->flags & FLG_ENCRYPT;
@@ -207,6 +243,24 @@ static inline int stm32_cryp_wait_busy(struct stm32_cryp *cryp)
 			!(status & SR_BUSY), 10, 100000);
 }
 
+static inline int stm32_cryp_wait_enable(struct stm32_cryp *cryp)
+{
+	u32 status;
+
+	return readl_relaxed_poll_timeout(cryp->regs + CRYP_CR, status,
+			!(status & CR_CRYPEN), 10, 100000);
+}
+
+static inline int stm32_cryp_wait_output(struct stm32_cryp *cryp)
+{
+	u32 status;
+
+	return readl_relaxed_poll_timeout(cryp->regs + CRYP_SR, status,
+			status & SR_OFNE, 10, 100000);
+}
+
+static int stm32_cryp_read_auth_tag(struct stm32_cryp *cryp);
+
 static struct stm32_cryp *stm32_cryp_find_dev(struct stm32_cryp_ctx *ctx)
 {
 	struct stm32_cryp *tmp, *cryp = NULL;
@@ -365,6 +419,12 @@ static u32 stm32_cryp_get_hw_mode(struct stm32_cryp *cryp)
 	if (is_aes(cryp) && is_ctr(cryp))
 		return CR_AES_CTR;
 
+	if (is_aes(cryp) && is_gcm(cryp))
+		return CR_AES_GCM;
+
+	if (is_aes(cryp) && is_ccm(cryp))
+		return CR_AES_CCM;
+
 	if (is_des(cryp) && is_ecb(cryp))
 		return CR_DES_ECB;
 
@@ -381,6 +441,79 @@ static u32 stm32_cryp_get_hw_mode(struct stm32_cryp *cryp)
 	return CR_AES_UNKNOWN;
 }
 
+static unsigned int stm32_cryp_get_input_text_len(struct stm32_cryp *cryp)
+{
+	return is_encrypt(cryp) ? cryp->areq->cryptlen :
+				  cryp->areq->cryptlen - cryp->authsize;
+}
+
+static int stm32_cryp_gcm_init(struct stm32_cryp *cryp, u32 cfg)
+{
+	int ret;
+	u32 iv[4];
+
+	/* Phase 1 : init */
+	memcpy(iv, cryp->areq->iv, 12);
+	iv[3] = cpu_to_be32(GCM_CTR_INIT);
+	cryp->gcm_ctr = GCM_CTR_INIT;
+	stm32_cryp_hw_write_iv(cryp, iv);
+
+	stm32_cryp_write(cryp, CRYP_CR, cfg | CR_PH_INIT | CR_CRYPEN);
+
+	/* Wait for end of processing */
+	ret = stm32_cryp_wait_enable(cryp);
+	if (ret)
+		dev_err(cryp->dev, "Timeout (gcm init)\n");
+
+	return ret;
+}
+
+static int stm32_cryp_ccm_init(struct stm32_cryp *cryp, u32 cfg)
+{
+	int ret;
+	u8 iv[AES_BLOCK_SIZE], b0[AES_BLOCK_SIZE];
+	u32 *d;
+	unsigned int i, textlen;
+
+	/* Phase 1 : init. Firstly set the CTR value to 1 (not 0) */
+	memcpy(iv, cryp->areq->iv, AES_BLOCK_SIZE);
+	memset(iv + AES_BLOCK_SIZE - 1 - iv[0], 0, iv[0] + 1);
+	iv[AES_BLOCK_SIZE - 1] = 1;
+	stm32_cryp_hw_write_iv(cryp, (u32 *)iv);
+
+	/* Build B0 */
+	memcpy(b0, iv, AES_BLOCK_SIZE);
+
+	b0[0] |= (8 * ((cryp->authsize - 2) / 2));
+
+	if (cryp->areq->assoclen)
+		b0[0] |= 0x40;
+
+	textlen = stm32_cryp_get_input_text_len(cryp);
+
+	b0[AES_BLOCK_SIZE - 2] = textlen >> 8;
+	b0[AES_BLOCK_SIZE - 1] = textlen & 0xFF;
+
+	/* Enable HW */
+	stm32_cryp_write(cryp, CRYP_CR, cfg | CR_PH_INIT | CR_CRYPEN);
+
+	/* Write B0 */
+	d = (u32 *)b0;
+
+	for (i = 0; i < AES_BLOCK_32; i++) {
+		if (!cryp->caps->padding_wa)
+			*d = cpu_to_be32(*d);
+		stm32_cryp_write(cryp, CRYP_DIN, *d++);
+	}
+
+	/* Wait for end of processing */
+	ret = stm32_cryp_wait_enable(cryp);
+	if (ret)
+		dev_err(cryp->dev, "Timeout (ccm init)\n");
+
+	return ret;
+}
+
 static int stm32_cryp_hw_init(struct stm32_cryp *cryp)
 {
 	int ret;
@@ -436,6 +569,29 @@ static int stm32_cryp_hw_init(struct stm32_cryp *cryp)
 	stm32_cryp_write(cryp, CRYP_CR, cfg);
 
 	switch (hw_mode) {
+	case CR_AES_GCM:
+	case CR_AES_CCM:
+		/* Phase 1 : init */
+		if (hw_mode == CR_AES_CCM)
+			ret = stm32_cryp_ccm_init(cryp, cfg);
+		else
+			ret = stm32_cryp_gcm_init(cryp, cfg);
+
+		if (ret)
+			return ret;
+
+		/* Phase 2 : header (authenticated data) */
+		if (cryp->areq->assoclen) {
+			cfg |= CR_PH_HEADER;
+		} else if (stm32_cryp_get_input_text_len(cryp)) {
+			cfg |= CR_PH_PAYLOAD;
+			stm32_cryp_write(cryp, CRYP_CR, cfg);
+		} else {
+			cfg |= CR_PH_INIT;
+		}
+
+		break;
+
 	case CR_DES_CBC:
 	case CR_TDES_CBC:
 	case CR_AES_CBC:
@@ -452,12 +608,16 @@ static int stm32_cryp_hw_init(struct stm32_cryp *cryp)
 
 	stm32_cryp_write(cryp, CRYP_CR, cfg);
 
+	cryp->flags &= ~FLG_CCM_PADDED_WA;
+
 	return 0;
 }
 
-static void stm32_cryp_finish_req(struct stm32_cryp *cryp)
+static void stm32_cryp_finish_req(struct stm32_cryp *cryp, int err)
 {
-	int err = 0;
+	if (!err && (is_gcm(cryp) || is_ccm(cryp)))
+		/* Phase 4 : output tag */
+		err = stm32_cryp_read_auth_tag(cryp);
 
 	if (cryp->sgs_copied) {
 		void *buf_in, *buf_out;
@@ -478,8 +638,14 @@ static void stm32_cryp_finish_req(struct stm32_cryp *cryp)
 		free_pages((unsigned long)buf_out, pages);
 	}
 
-	crypto_finalize_cipher_request(cryp->engine, cryp->req, err);
-	cryp->req = NULL;
+	if (is_gcm(cryp) || is_ccm(cryp)) {
+		crypto_finalize_aead_request(cryp->engine, cryp->areq, err);
+		cryp->areq = NULL;
+	} else {
+		crypto_finalize_ablkcipher_request(cryp->engine, cryp->req,
+						   err);
+		cryp->req = NULL;
+	}
 
 	memset(cryp->ctx->key, 0, cryp->ctx->keylen);
 
@@ -494,10 +660,36 @@ static int stm32_cryp_cpu_start(struct stm32_cryp *cryp)
 	return 0;
 }
 
+static int stm32_cryp_cipher_one_req(struct crypto_engine *engine, void *areq);
+static int stm32_cryp_prepare_cipher_req(struct crypto_engine *engine,
+					 void *areq);
+
 static int stm32_cryp_cra_init(struct crypto_tfm *tfm)
 {
+	struct stm32_cryp_ctx *ctx = crypto_tfm_ctx(tfm);
+
 	tfm->crt_ablkcipher.reqsize = sizeof(struct stm32_cryp_reqctx);
 
+	ctx->enginectx.op.do_one_request = stm32_cryp_cipher_one_req;
+	ctx->enginectx.op.prepare_request = stm32_cryp_prepare_cipher_req;
+	ctx->enginectx.op.unprepare_request = NULL;
+	return 0;
+}
+
+static int stm32_cryp_aead_one_req(struct crypto_engine *engine, void *areq);
+static int stm32_cryp_prepare_aead_req(struct crypto_engine *engine,
+				       void *areq);
+
+static int stm32_cryp_aes_aead_init(struct crypto_aead *tfm)
+{
+	struct stm32_cryp_ctx *ctx = crypto_aead_ctx(tfm);
+
+	tfm->reqsize = sizeof(struct stm32_cryp_reqctx);
+
+	ctx->enginectx.op.do_one_request = stm32_cryp_aead_one_req;
+	ctx->enginectx.op.prepare_request = stm32_cryp_prepare_aead_req;
+	ctx->enginectx.op.unprepare_request = NULL;
+
 	return 0;
 }
 
@@ -513,7 +705,21 @@ static int stm32_cryp_crypt(struct ablkcipher_request *req, unsigned long mode)
 
 	rctx->mode = mode;
 
-	return crypto_transfer_cipher_request_to_engine(cryp->engine, req);
+	return crypto_transfer_ablkcipher_request_to_engine(cryp->engine, req);
+}
+
+static int stm32_cryp_aead_crypt(struct aead_request *req, unsigned long mode)
+{
+	struct stm32_cryp_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct stm32_cryp_reqctx *rctx = aead_request_ctx(req);
+	struct stm32_cryp *cryp = stm32_cryp_find_dev(ctx);
+
+	if (!cryp)
+		return -ENODEV;
+
+	rctx->mode = mode;
+
+	return crypto_transfer_aead_request_to_engine(cryp->engine, req);
 }
 
 static int stm32_cryp_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
@@ -555,6 +761,46 @@ static int stm32_cryp_tdes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 		return stm32_cryp_setkey(tfm, key, keylen);
 }
 
+static int stm32_cryp_aes_aead_setkey(struct crypto_aead *tfm, const u8 *key,
+				      unsigned int keylen)
+{
+	struct stm32_cryp_ctx *ctx = crypto_aead_ctx(tfm);
+
+	if (keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_192 &&
+	    keylen != AES_KEYSIZE_256)
+		return -EINVAL;
+
+	memcpy(ctx->key, key, keylen);
+	ctx->keylen = keylen;
+
+	return 0;
+}
+
+static int stm32_cryp_aes_gcm_setauthsize(struct crypto_aead *tfm,
+					  unsigned int authsize)
+{
+	return authsize == AES_BLOCK_SIZE ? 0 : -EINVAL;
+}
+
+static int stm32_cryp_aes_ccm_setauthsize(struct crypto_aead *tfm,
+					  unsigned int authsize)
+{
+	switch (authsize) {
+	case 4:
+	case 6:
+	case 8:
+	case 10:
+	case 12:
+	case 14:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int stm32_cryp_aes_ecb_encrypt(struct ablkcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_AES | FLG_ECB | FLG_ENCRYPT);
@@ -585,6 +831,26 @@ static int stm32_cryp_aes_ctr_decrypt(struct ablkcipher_request *req)
 	return stm32_cryp_crypt(req, FLG_AES | FLG_CTR);
 }
 
+static int stm32_cryp_aes_gcm_encrypt(struct aead_request *req)
+{
+	return stm32_cryp_aead_crypt(req, FLG_AES | FLG_GCM | FLG_ENCRYPT);
+}
+
+static int stm32_cryp_aes_gcm_decrypt(struct aead_request *req)
+{
+	return stm32_cryp_aead_crypt(req, FLG_AES | FLG_GCM);
+}
+
+static int stm32_cryp_aes_ccm_encrypt(struct aead_request *req)
+{
+	return stm32_cryp_aead_crypt(req, FLG_AES | FLG_CCM | FLG_ENCRYPT);
+}
+
+static int stm32_cryp_aes_ccm_decrypt(struct aead_request *req)
+{
+	return stm32_cryp_aead_crypt(req, FLG_AES | FLG_CCM);
+}
+
 static int stm32_cryp_des_ecb_encrypt(struct ablkcipher_request *req)
 {
 	return stm32_cryp_crypt(req, FLG_DES | FLG_ECB | FLG_ENCRYPT);
@@ -625,18 +891,19 @@ static int stm32_cryp_tdes_cbc_decrypt(struct ablkcipher_request *req)
 	return stm32_cryp_crypt(req, FLG_TDES | FLG_CBC);
 }
 
-static int stm32_cryp_prepare_req(struct crypto_engine *engine,
-				  struct ablkcipher_request *req)
+static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
+				  struct aead_request *areq)
 {
 	struct stm32_cryp_ctx *ctx;
 	struct stm32_cryp *cryp;
 	struct stm32_cryp_reqctx *rctx;
 	int ret;
 
-	if (!req)
+	if (!req && !areq)
 		return -EINVAL;
 
-	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
+	ctx = req ? crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req)) :
+		    crypto_aead_ctx(crypto_aead_reqtfm(areq));
 
 	cryp = ctx->cryp;
 
@@ -645,7 +912,7 @@ static int stm32_cryp_prepare_req(struct crypto_engine *engine,
 
 	mutex_lock(&cryp->lock);
 
-	rctx = ablkcipher_request_ctx(req);
+	rctx = req ? ablkcipher_request_ctx(req) : aead_request_ctx(areq);
 	rctx->mode &= FLG_MODE_MASK;
 
 	ctx->cryp = cryp;
@@ -654,15 +921,48 @@ static int stm32_cryp_prepare_req(struct crypto_engine *engine,
 	cryp->hw_blocksize = is_aes(cryp) ? AES_BLOCK_SIZE : DES_BLOCK_SIZE;
 	cryp->ctx = ctx;
 
-	cryp->req = req;
-	cryp->total_in = req->nbytes;
-	cryp->total_out = cryp->total_in;
+	if (req) {
+		cryp->req = req;
+		cryp->total_in = req->nbytes;
+		cryp->total_out = cryp->total_in;
+	} else {
+		/*
+		 * Length of input and output data:
+		 * Encryption case:
+		 *  INPUT  =   AssocData  ||   PlainText
+		 *          <- assoclen ->  <- cryptlen ->
+		 *          <------- total_in ----------->
+		 *
+		 *  OUTPUT =   AssocData  ||  CipherText  ||   AuthTag
+		 *          <- assoclen ->  <- cryptlen ->  <- authsize ->
+		 *          <---------------- total_out ----------------->
+		 *
+		 * Decryption case:
+		 *  INPUT  =   AssocData  ||  CipherText  ||  AuthTag
+		 *          <- assoclen ->  <--------- cryptlen --------->
+		 *                                          <- authsize ->
+		 *          <---------------- total_in ------------------>
+		 *
+		 *  OUTPUT =   AssocData  ||   PlainText
+		 *          <- assoclen ->  <- crypten - authsize ->
+		 *          <---------- total_out ----------------->
+		 */
+		cryp->areq = areq;
+		cryp->authsize = crypto_aead_authsize(crypto_aead_reqtfm(areq));
+		cryp->total_in = areq->assoclen + areq->cryptlen;
+		if (is_encrypt(cryp))
+			/* Append auth tag to output */
+			cryp->total_out = cryp->total_in + cryp->authsize;
+		else
+			/* No auth tag in output */
+			cryp->total_out = cryp->total_in - cryp->authsize;
+	}
 
 	cryp->total_in_save = cryp->total_in;
 	cryp->total_out_save = cryp->total_out;
 
-	cryp->in_sg = req->src;
-	cryp->out_sg = req->dst;
+	cryp->in_sg = req ? req->src : areq->src;
+	cryp->out_sg = req ? req->dst : areq->dst;
 	cryp->out_sg_save = cryp->out_sg;
 
 	cryp->in_sg_len = sg_nents_for_len(cryp->in_sg, cryp->total_in);
@@ -686,6 +986,12 @@ static int stm32_cryp_prepare_req(struct crypto_engine *engine,
 	scatterwalk_start(&cryp->in_walk, cryp->in_sg);
 	scatterwalk_start(&cryp->out_walk, cryp->out_sg);
 
+	if (is_gcm(cryp) || is_ccm(cryp)) {
+		/* In output, jump after assoc data */
+		scatterwalk_advance(&cryp->out_walk, cryp->areq->assoclen);
+		cryp->total_out -= cryp->areq->assoclen;
+	}
+
 	ret = stm32_cryp_hw_init(cryp);
 out:
 	if (ret)
@@ -695,14 +1001,20 @@ out:
 }
 
 static int stm32_cryp_prepare_cipher_req(struct crypto_engine *engine,
-					 struct ablkcipher_request *req)
+					 void *areq)
 {
-	return stm32_cryp_prepare_req(engine, req);
+	struct ablkcipher_request *req = container_of(areq,
+						      struct ablkcipher_request,
+						      base);
+
+	return stm32_cryp_prepare_req(req, NULL);
 }
 
-static int stm32_cryp_cipher_one_req(struct crypto_engine *engine,
-				     struct ablkcipher_request *req)
+static int stm32_cryp_cipher_one_req(struct crypto_engine *engine, void *areq)
 {
+	struct ablkcipher_request *req = container_of(areq,
+						      struct ablkcipher_request,
+						      base);
 	struct stm32_cryp_ctx *ctx = crypto_ablkcipher_ctx(
 			crypto_ablkcipher_reqtfm(req));
 	struct stm32_cryp *cryp = ctx->cryp;
@@ -713,6 +1025,34 @@ static int stm32_cryp_cipher_one_req(struct crypto_engine *engine,
 	return stm32_cryp_cpu_start(cryp);
 }
 
+static int stm32_cryp_prepare_aead_req(struct crypto_engine *engine, void *areq)
+{
+	struct aead_request *req = container_of(areq, struct aead_request,
+						base);
+
+	return stm32_cryp_prepare_req(NULL, req);
+}
+
+static int stm32_cryp_aead_one_req(struct crypto_engine *engine, void *areq)
+{
+	struct aead_request *req = container_of(areq, struct aead_request,
+						base);
+	struct stm32_cryp_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct stm32_cryp *cryp = ctx->cryp;
+
+	if (!cryp)
+		return -ENODEV;
+
+	if (unlikely(!cryp->areq->assoclen &&
+		     !stm32_cryp_get_input_text_len(cryp))) {
+		/* No input data to process: get tag and finish */
+		stm32_cryp_finish_req(cryp, 0);
+		return 0;
+	}
+
+	return stm32_cryp_cpu_start(cryp);
+}
+
 static u32 *stm32_cryp_next_out(struct stm32_cryp *cryp, u32 *dst,
 				unsigned int n)
 {
@@ -745,6 +1085,111 @@ static u32 *stm32_cryp_next_in(struct stm32_cryp *cryp, u32 *src,
 	return (u32 *)((u8 *)src + n);
 }
 
+static int stm32_cryp_read_auth_tag(struct stm32_cryp *cryp)
+{
+	u32 cfg, size_bit, *dst, d32;
+	u8 *d8;
+	unsigned int i, j;
+	int ret = 0;
+
+	/* Update Config */
+	cfg = stm32_cryp_read(cryp, CRYP_CR);
+
+	cfg &= ~CR_PH_MASK;
+	cfg |= CR_PH_FINAL;
+	cfg &= ~CR_DEC_NOT_ENC;
+	cfg |= CR_CRYPEN;
+
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	if (is_gcm(cryp)) {
+		/* GCM: write aad and payload size (in bits) */
+		size_bit = cryp->areq->assoclen * 8;
+		if (cryp->caps->swap_final)
+			size_bit = cpu_to_be32(size_bit);
+
+		stm32_cryp_write(cryp, CRYP_DIN, 0);
+		stm32_cryp_write(cryp, CRYP_DIN, size_bit);
+
+		size_bit = is_encrypt(cryp) ? cryp->areq->cryptlen :
+				cryp->areq->cryptlen - AES_BLOCK_SIZE;
+		size_bit *= 8;
+		if (cryp->caps->swap_final)
+			size_bit = cpu_to_be32(size_bit);
+
+		stm32_cryp_write(cryp, CRYP_DIN, 0);
+		stm32_cryp_write(cryp, CRYP_DIN, size_bit);
+	} else {
+		/* CCM: write CTR0 */
+		u8 iv[AES_BLOCK_SIZE];
+		u32 *iv32 = (u32 *)iv;
+
+		memcpy(iv, cryp->areq->iv, AES_BLOCK_SIZE);
+		memset(iv + AES_BLOCK_SIZE - 1 - iv[0], 0, iv[0] + 1);
+
+		for (i = 0; i < AES_BLOCK_32; i++) {
+			if (!cryp->caps->padding_wa)
+				*iv32 = cpu_to_be32(*iv32);
+			stm32_cryp_write(cryp, CRYP_DIN, *iv32++);
+		}
+	}
+
+	/* Wait for output data */
+	ret = stm32_cryp_wait_output(cryp);
+	if (ret) {
+		dev_err(cryp->dev, "Timeout (read tag)\n");
+		return ret;
+	}
+
+	if (is_encrypt(cryp)) {
+		/* Get and write tag */
+		dst = sg_virt(cryp->out_sg) + _walked_out;
+
+		for (i = 0; i < AES_BLOCK_32; i++) {
+			if (cryp->total_out >= sizeof(u32)) {
+				/* Read a full u32 */
+				*dst = stm32_cryp_read(cryp, CRYP_DOUT);
+
+				dst = stm32_cryp_next_out(cryp, dst,
+							  sizeof(u32));
+				cryp->total_out -= sizeof(u32);
+			} else if (!cryp->total_out) {
+				/* Empty fifo out (data from input padding) */
+				stm32_cryp_read(cryp, CRYP_DOUT);
+			} else {
+				/* Read less than an u32 */
+				d32 = stm32_cryp_read(cryp, CRYP_DOUT);
+				d8 = (u8 *)&d32;
+
+				for (j = 0; j < cryp->total_out; j++) {
+					*((u8 *)dst) = *(d8++);
+					dst = stm32_cryp_next_out(cryp, dst, 1);
+				}
+				cryp->total_out = 0;
+			}
+		}
+	} else {
+		/* Get and check tag */
+		u32 in_tag[AES_BLOCK_32], out_tag[AES_BLOCK_32];
+
+		scatterwalk_map_and_copy(in_tag, cryp->in_sg,
+					 cryp->total_in_save - cryp->authsize,
+					 cryp->authsize, 0);
+
+		for (i = 0; i < AES_BLOCK_32; i++)
+			out_tag[i] = stm32_cryp_read(cryp, CRYP_DOUT);
+
+		if (crypto_memneq(in_tag, out_tag, cryp->authsize))
+			ret = -EBADMSG;
+	}
+
+	/* Disable cryp */
+	cfg &= ~CR_CRYPEN;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	return ret;
+}
+
 static void stm32_cryp_check_ctr_counter(struct stm32_cryp *cryp)
 {
 	u32 cr;
@@ -777,17 +1222,24 @@ static bool stm32_cryp_irq_read_data(struct stm32_cryp *cryp)
 	unsigned int i, j;
 	u32 d32, *dst;
 	u8 *d8;
+	size_t tag_size;
+
+	/* Do no read tag now (if any) */
+	if (is_encrypt(cryp) && (is_gcm(cryp) || is_ccm(cryp)))
+		tag_size = cryp->authsize;
+	else
+		tag_size = 0;
 
 	dst = sg_virt(cryp->out_sg) + _walked_out;
 
 	for (i = 0; i < cryp->hw_blocksize / sizeof(u32); i++) {
-		if (likely(cryp->total_out >= sizeof(u32))) {
+		if (likely(cryp->total_out - tag_size >= sizeof(u32))) {
 			/* Read a full u32 */
 			*dst = stm32_cryp_read(cryp, CRYP_DOUT);
 
 			dst = stm32_cryp_next_out(cryp, dst, sizeof(u32));
 			cryp->total_out -= sizeof(u32);
-		} else if (!cryp->total_out) {
+		} else if (cryp->total_out == tag_size) {
 			/* Empty fifo out (data from input padding) */
 			d32 = stm32_cryp_read(cryp, CRYP_DOUT);
 		} else {
@@ -795,15 +1247,15 @@ static bool stm32_cryp_irq_read_data(struct stm32_cryp *cryp)
 			d32 = stm32_cryp_read(cryp, CRYP_DOUT);
 			d8 = (u8 *)&d32;
 
-			for (j = 0; j < cryp->total_out; j++) {
+			for (j = 0; j < cryp->total_out - tag_size; j++) {
 				*((u8 *)dst) = *(d8++);
 				dst = stm32_cryp_next_out(cryp, dst, 1);
 			}
-			cryp->total_out = 0;
+			cryp->total_out = tag_size;
 		}
 	}
 
-	return !cryp->total_out || !cryp->total_in;
+	return !(cryp->total_out - tag_size) || !cryp->total_in;
 }
 
 static void stm32_cryp_irq_write_block(struct stm32_cryp *cryp)
@@ -811,33 +1263,219 @@ static void stm32_cryp_irq_write_block(struct stm32_cryp *cryp)
 	unsigned int i, j;
 	u32 *src;
 	u8 d8[4];
+	size_t tag_size;
+
+	/* Do no write tag (if any) */
+	if (is_decrypt(cryp) && (is_gcm(cryp) || is_ccm(cryp)))
+		tag_size = cryp->authsize;
+	else
+		tag_size = 0;
 
 	src = sg_virt(cryp->in_sg) + _walked_in;
 
 	for (i = 0; i < cryp->hw_blocksize / sizeof(u32); i++) {
-		if (likely(cryp->total_in >= sizeof(u32))) {
+		if (likely(cryp->total_in - tag_size >= sizeof(u32))) {
 			/* Write a full u32 */
 			stm32_cryp_write(cryp, CRYP_DIN, *src);
 
 			src = stm32_cryp_next_in(cryp, src, sizeof(u32));
 			cryp->total_in -= sizeof(u32);
-		} else if (!cryp->total_in) {
+		} else if (cryp->total_in == tag_size) {
 			/* Write padding data */
 			stm32_cryp_write(cryp, CRYP_DIN, 0);
 		} else {
 			/* Write less than an u32 */
 			memset(d8, 0, sizeof(u32));
-			for (j = 0; j < cryp->total_in; j++) {
+			for (j = 0; j < cryp->total_in - tag_size; j++) {
 				d8[j] = *((u8 *)src);
 				src = stm32_cryp_next_in(cryp, src, 1);
 			}
 
 			stm32_cryp_write(cryp, CRYP_DIN, *(u32 *)d8);
-			cryp->total_in = 0;
+			cryp->total_in = tag_size;
 		}
 	}
 }
 
+static void stm32_cryp_irq_write_gcm_padded_data(struct stm32_cryp *cryp)
+{
+	int err;
+	u32 cfg, tmp[AES_BLOCK_32];
+	size_t total_in_ori = cryp->total_in;
+	struct scatterlist *out_sg_ori = cryp->out_sg;
+	unsigned int i;
+
+	/* 'Special workaround' procedure described in the datasheet */
+
+	/* a) disable ip */
+	stm32_cryp_write(cryp, CRYP_IMSCR, 0);
+	cfg = stm32_cryp_read(cryp, CRYP_CR);
+	cfg &= ~CR_CRYPEN;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	/* b) Update IV1R */
+	stm32_cryp_write(cryp, CRYP_IV1RR, cryp->gcm_ctr - 2);
+
+	/* c) change mode to CTR */
+	cfg &= ~CR_ALGO_MASK;
+	cfg |= CR_AES_CTR;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	/* a) enable IP */
+	cfg |= CR_CRYPEN;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	/* b) pad and write the last block */
+	stm32_cryp_irq_write_block(cryp);
+	cryp->total_in = total_in_ori;
+	err = stm32_cryp_wait_output(cryp);
+	if (err) {
+		dev_err(cryp->dev, "Timeout (write gcm header)\n");
+		return stm32_cryp_finish_req(cryp, err);
+	}
+
+	/* c) get and store encrypted data */
+	stm32_cryp_irq_read_data(cryp);
+	scatterwalk_map_and_copy(tmp, out_sg_ori,
+				 cryp->total_in_save - total_in_ori,
+				 total_in_ori, 0);
+
+	/* d) change mode back to AES GCM */
+	cfg &= ~CR_ALGO_MASK;
+	cfg |= CR_AES_GCM;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	/* e) change phase to Final */
+	cfg &= ~CR_PH_MASK;
+	cfg |= CR_PH_FINAL;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	/* f) write padded data */
+	for (i = 0; i < AES_BLOCK_32; i++) {
+		if (cryp->total_in)
+			stm32_cryp_write(cryp, CRYP_DIN, tmp[i]);
+		else
+			stm32_cryp_write(cryp, CRYP_DIN, 0);
+
+		cryp->total_in -= min_t(size_t, sizeof(u32), cryp->total_in);
+	}
+
+	/* g) Empty fifo out */
+	err = stm32_cryp_wait_output(cryp);
+	if (err) {
+		dev_err(cryp->dev, "Timeout (write gcm header)\n");
+		return stm32_cryp_finish_req(cryp, err);
+	}
+
+	for (i = 0; i < AES_BLOCK_32; i++)
+		stm32_cryp_read(cryp, CRYP_DOUT);
+
+	/* h) run the he normal Final phase */
+	stm32_cryp_finish_req(cryp, 0);
+}
+
+static void stm32_cryp_irq_set_npblb(struct stm32_cryp *cryp)
+{
+	u32 cfg, payload_bytes;
+
+	/* disable ip, set NPBLB and reneable ip */
+	cfg = stm32_cryp_read(cryp, CRYP_CR);
+	cfg &= ~CR_CRYPEN;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	payload_bytes = is_decrypt(cryp) ? cryp->total_in - cryp->authsize :
+					   cryp->total_in;
+	cfg |= (cryp->hw_blocksize - payload_bytes) << CR_NBPBL_SHIFT;
+	cfg |= CR_CRYPEN;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+}
+
+static void stm32_cryp_irq_write_ccm_padded_data(struct stm32_cryp *cryp)
+{
+	int err = 0;
+	u32 cfg, iv1tmp;
+	u32 cstmp1[AES_BLOCK_32], cstmp2[AES_BLOCK_32], tmp[AES_BLOCK_32];
+	size_t last_total_out, total_in_ori = cryp->total_in;
+	struct scatterlist *out_sg_ori = cryp->out_sg;
+	unsigned int i;
+
+	/* 'Special workaround' procedure described in the datasheet */
+	cryp->flags |= FLG_CCM_PADDED_WA;
+
+	/* a) disable ip */
+	stm32_cryp_write(cryp, CRYP_IMSCR, 0);
+
+	cfg = stm32_cryp_read(cryp, CRYP_CR);
+	cfg &= ~CR_CRYPEN;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	/* b) get IV1 from CRYP_CSGCMCCM7 */
+	iv1tmp = stm32_cryp_read(cryp, CRYP_CSGCMCCM0R + 7 * 4);
+
+	/* c) Load CRYP_CSGCMCCMxR */
+	for (i = 0; i < ARRAY_SIZE(cstmp1); i++)
+		cstmp1[i] = stm32_cryp_read(cryp, CRYP_CSGCMCCM0R + i * 4);
+
+	/* d) Write IV1R */
+	stm32_cryp_write(cryp, CRYP_IV1RR, iv1tmp);
+
+	/* e) change mode to CTR */
+	cfg &= ~CR_ALGO_MASK;
+	cfg |= CR_AES_CTR;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	/* a) enable IP */
+	cfg |= CR_CRYPEN;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	/* b) pad and write the last block */
+	stm32_cryp_irq_write_block(cryp);
+	cryp->total_in = total_in_ori;
+	err = stm32_cryp_wait_output(cryp);
+	if (err) {
+		dev_err(cryp->dev, "Timeout (wite ccm padded data)\n");
+		return stm32_cryp_finish_req(cryp, err);
+	}
+
+	/* c) get and store decrypted data */
+	last_total_out = cryp->total_out;
+	stm32_cryp_irq_read_data(cryp);
+
+	memset(tmp, 0, sizeof(tmp));
+	scatterwalk_map_and_copy(tmp, out_sg_ori,
+				 cryp->total_out_save - last_total_out,
+				 last_total_out, 0);
+
+	/* d) Load again CRYP_CSGCMCCMxR */
+	for (i = 0; i < ARRAY_SIZE(cstmp2); i++)
+		cstmp2[i] = stm32_cryp_read(cryp, CRYP_CSGCMCCM0R + i * 4);
+
+	/* e) change mode back to AES CCM */
+	cfg &= ~CR_ALGO_MASK;
+	cfg |= CR_AES_CCM;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	/* f) change phase to header */
+	cfg &= ~CR_PH_MASK;
+	cfg |= CR_PH_HEADER;
+	stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+	/* g) XOR and write padded data */
+	for (i = 0; i < ARRAY_SIZE(tmp); i++) {
+		tmp[i] ^= cstmp1[i];
+		tmp[i] ^= cstmp2[i];
+		stm32_cryp_write(cryp, CRYP_DIN, tmp[i]);
+	}
+
+	/* h) wait for completion */
+	err = stm32_cryp_wait_busy(cryp);
+	if (err)
+		dev_err(cryp->dev, "Timeout (wite ccm padded data)\n");
+
+	/* i) run the he normal Final phase */
+	stm32_cryp_finish_req(cryp, err);
+}
+
 static void stm32_cryp_irq_write_data(struct stm32_cryp *cryp)
 {
 	if (unlikely(!cryp->total_in)) {
@@ -845,28 +1483,220 @@ static void stm32_cryp_irq_write_data(struct stm32_cryp *cryp)
 		return;
 	}
 
+	if (unlikely(cryp->total_in < AES_BLOCK_SIZE &&
+		     (stm32_cryp_get_hw_mode(cryp) == CR_AES_GCM) &&
+		     is_encrypt(cryp))) {
+		/* Padding for AES GCM encryption */
+		if (cryp->caps->padding_wa)
+			/* Special case 1 */
+			return stm32_cryp_irq_write_gcm_padded_data(cryp);
+
+		/* Setting padding bytes (NBBLB) */
+		stm32_cryp_irq_set_npblb(cryp);
+	}
+
+	if (unlikely((cryp->total_in - cryp->authsize < AES_BLOCK_SIZE) &&
+		     (stm32_cryp_get_hw_mode(cryp) == CR_AES_CCM) &&
+		     is_decrypt(cryp))) {
+		/* Padding for AES CCM decryption */
+		if (cryp->caps->padding_wa)
+			/* Special case 2 */
+			return stm32_cryp_irq_write_ccm_padded_data(cryp);
+
+		/* Setting padding bytes (NBBLB) */
+		stm32_cryp_irq_set_npblb(cryp);
+	}
+
 	if (is_aes(cryp) && is_ctr(cryp))
 		stm32_cryp_check_ctr_counter(cryp);
 
 	stm32_cryp_irq_write_block(cryp);
 }
 
+static void stm32_cryp_irq_write_gcm_header(struct stm32_cryp *cryp)
+{
+	int err;
+	unsigned int i, j;
+	u32 cfg, *src;
+
+	src = sg_virt(cryp->in_sg) + _walked_in;
+
+	for (i = 0; i < AES_BLOCK_32; i++) {
+		stm32_cryp_write(cryp, CRYP_DIN, *src);
+
+		src = stm32_cryp_next_in(cryp, src, sizeof(u32));
+		cryp->total_in -= min_t(size_t, sizeof(u32), cryp->total_in);
+
+		/* Check if whole header written */
+		if ((cryp->total_in_save - cryp->total_in) ==
+				cryp->areq->assoclen) {
+			/* Write padding if needed */
+			for (j = i + 1; j < AES_BLOCK_32; j++)
+				stm32_cryp_write(cryp, CRYP_DIN, 0);
+
+			/* Wait for completion */
+			err = stm32_cryp_wait_busy(cryp);
+			if (err) {
+				dev_err(cryp->dev, "Timeout (gcm header)\n");
+				return stm32_cryp_finish_req(cryp, err);
+			}
+
+			if (stm32_cryp_get_input_text_len(cryp)) {
+				/* Phase 3 : payload */
+				cfg = stm32_cryp_read(cryp, CRYP_CR);
+				cfg &= ~CR_CRYPEN;
+				stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+				cfg &= ~CR_PH_MASK;
+				cfg |= CR_PH_PAYLOAD;
+				cfg |= CR_CRYPEN;
+				stm32_cryp_write(cryp, CRYP_CR, cfg);
+			} else {
+				/* Phase 4 : tag */
+				stm32_cryp_write(cryp, CRYP_IMSCR, 0);
+				stm32_cryp_finish_req(cryp, 0);
+			}
+
+			break;
+		}
+
+		if (!cryp->total_in)
+			break;
+	}
+}
+
+static void stm32_cryp_irq_write_ccm_header(struct stm32_cryp *cryp)
+{
+	int err;
+	unsigned int i = 0, j, k;
+	u32 alen, cfg, *src;
+	u8 d8[4];
+
+	src = sg_virt(cryp->in_sg) + _walked_in;
+	alen = cryp->areq->assoclen;
+
+	if (!_walked_in) {
+		if (cryp->areq->assoclen <= 65280) {
+			/* Write first u32 of B1 */
+			d8[0] = (alen >> 8) & 0xFF;
+			d8[1] = alen & 0xFF;
+			d8[2] = *((u8 *)src);
+			src = stm32_cryp_next_in(cryp, src, 1);
+			d8[3] = *((u8 *)src);
+			src = stm32_cryp_next_in(cryp, src, 1);
+
+			stm32_cryp_write(cryp, CRYP_DIN, *(u32 *)d8);
+			i++;
+
+			cryp->total_in -= min_t(size_t, 2, cryp->total_in);
+		} else {
+			/* Build the two first u32 of B1 */
+			d8[0] = 0xFF;
+			d8[1] = 0xFE;
+			d8[2] = alen & 0xFF000000;
+			d8[3] = alen & 0x00FF0000;
+
+			stm32_cryp_write(cryp, CRYP_DIN, *(u32 *)d8);
+			i++;
+
+			d8[0] = alen & 0x0000FF00;
+			d8[1] = alen & 0x000000FF;
+			d8[2] = *((u8 *)src);
+			src = stm32_cryp_next_in(cryp, src, 1);
+			d8[3] = *((u8 *)src);
+			src = stm32_cryp_next_in(cryp, src, 1);
+
+			stm32_cryp_write(cryp, CRYP_DIN, *(u32 *)d8);
+			i++;
+
+			cryp->total_in -= min_t(size_t, 2, cryp->total_in);
+		}
+	}
+
+	/* Write next u32 */
+	for (; i < AES_BLOCK_32; i++) {
+		/* Build an u32 */
+		memset(d8, 0, sizeof(u32));
+		for (k = 0; k < sizeof(u32); k++) {
+			d8[k] = *((u8 *)src);
+			src = stm32_cryp_next_in(cryp, src, 1);
+
+			cryp->total_in -= min_t(size_t, 1, cryp->total_in);
+			if ((cryp->total_in_save - cryp->total_in) == alen)
+				break;
+		}
+
+		stm32_cryp_write(cryp, CRYP_DIN, *(u32 *)d8);
+
+		if ((cryp->total_in_save - cryp->total_in) == alen) {
+			/* Write padding if needed */
+			for (j = i + 1; j < AES_BLOCK_32; j++)
+				stm32_cryp_write(cryp, CRYP_DIN, 0);
+
+			/* Wait for completion */
+			err = stm32_cryp_wait_busy(cryp);
+			if (err) {
+				dev_err(cryp->dev, "Timeout (ccm header)\n");
+				return stm32_cryp_finish_req(cryp, err);
+			}
+
+			if (stm32_cryp_get_input_text_len(cryp)) {
+				/* Phase 3 : payload */
+				cfg = stm32_cryp_read(cryp, CRYP_CR);
+				cfg &= ~CR_CRYPEN;
+				stm32_cryp_write(cryp, CRYP_CR, cfg);
+
+				cfg &= ~CR_PH_MASK;
+				cfg |= CR_PH_PAYLOAD;
+				cfg |= CR_CRYPEN;
+				stm32_cryp_write(cryp, CRYP_CR, cfg);
+			} else {
+				/* Phase 4 : tag */
+				stm32_cryp_write(cryp, CRYP_IMSCR, 0);
+				stm32_cryp_finish_req(cryp, 0);
+			}
+
+			break;
+		}
+	}
+}
+
 static irqreturn_t stm32_cryp_irq_thread(int irq, void *arg)
 {
 	struct stm32_cryp *cryp = arg;
+	u32 ph;
 
 	if (cryp->irq_status & MISR_OUT)
 		/* Output FIFO IRQ: read data */
 		if (unlikely(stm32_cryp_irq_read_data(cryp))) {
 			/* All bytes processed, finish */
 			stm32_cryp_write(cryp, CRYP_IMSCR, 0);
-			stm32_cryp_finish_req(cryp);
+			stm32_cryp_finish_req(cryp, 0);
 			return IRQ_HANDLED;
 		}
 
 	if (cryp->irq_status & MISR_IN) {
-		/* Input FIFO IRQ: write data */
-		stm32_cryp_irq_write_data(cryp);
+		if (is_gcm(cryp)) {
+			ph = stm32_cryp_read(cryp, CRYP_CR) & CR_PH_MASK;
+			if (unlikely(ph == CR_PH_HEADER))
+				/* Write Header */
+				stm32_cryp_irq_write_gcm_header(cryp);
+			else
+				/* Input FIFO IRQ: write data */
+				stm32_cryp_irq_write_data(cryp);
+			cryp->gcm_ctr++;
+		} else if (is_ccm(cryp)) {
+			ph = stm32_cryp_read(cryp, CRYP_CR) & CR_PH_MASK;
+			if (unlikely(ph == CR_PH_HEADER))
+				/* Write Header */
+				stm32_cryp_irq_write_ccm_header(cryp);
+			else
+				/* Input FIFO IRQ: write data */
+				stm32_cryp_irq_write_data(cryp);
+		} else {
+			/* Input FIFO IRQ: write data */
+			stm32_cryp_irq_write_data(cryp);
+		}
 	}
 
 	return IRQ_HANDLED;
@@ -1028,8 +1858,62 @@ static struct crypto_alg crypto_algs[] = {
 },
 };
 
+static struct aead_alg aead_algs[] = {
+{
+	.setkey		= stm32_cryp_aes_aead_setkey,
+	.setauthsize	= stm32_cryp_aes_gcm_setauthsize,
+	.encrypt	= stm32_cryp_aes_gcm_encrypt,
+	.decrypt	= stm32_cryp_aes_gcm_decrypt,
+	.init		= stm32_cryp_aes_aead_init,
+	.ivsize		= 12,
+	.maxauthsize	= AES_BLOCK_SIZE,
+
+	.base = {
+		.cra_name		= "gcm(aes)",
+		.cra_driver_name	= "stm32-gcm-aes",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
+		.cra_alignmask		= 0xf,
+		.cra_module		= THIS_MODULE,
+	},
+},
+{
+	.setkey		= stm32_cryp_aes_aead_setkey,
+	.setauthsize	= stm32_cryp_aes_ccm_setauthsize,
+	.encrypt	= stm32_cryp_aes_ccm_encrypt,
+	.decrypt	= stm32_cryp_aes_ccm_decrypt,
+	.init		= stm32_cryp_aes_aead_init,
+	.ivsize		= AES_BLOCK_SIZE,
+	.maxauthsize	= AES_BLOCK_SIZE,
+
+	.base = {
+		.cra_name		= "ccm(aes)",
+		.cra_driver_name	= "stm32-ccm-aes",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct stm32_cryp_ctx),
+		.cra_alignmask		= 0xf,
+		.cra_module		= THIS_MODULE,
+	},
+},
+};
+
+static const struct stm32_cryp_caps f7_data = {
+	.swap_final = true,
+	.padding_wa = true,
+};
+
+static const struct stm32_cryp_caps mp1_data = {
+	.swap_final = false,
+	.padding_wa = false,
+};
+
 static const struct of_device_id stm32_dt_ids[] = {
-	{ .compatible = "st,stm32f756-cryp", },
+	{ .compatible = "st,stm32f756-cryp", .data = &f7_data},
+	{ .compatible = "st,stm32mp1-cryp", .data = &mp1_data},
 	{},
 };
 MODULE_DEVICE_TABLE(of, stm32_dt_ids);
@@ -1046,6 +1930,10 @@ static int stm32_cryp_probe(struct platform_device *pdev)
 	if (!cryp)
 		return -ENOMEM;
 
+	cryp->caps = of_device_get_match_data(dev);
+	if (!cryp->caps)
+		return -ENODEV;
+
 	cryp->dev = dev;
 
 	mutex_init(&cryp->lock);
@@ -1102,9 +1990,6 @@ static int stm32_cryp_probe(struct platform_device *pdev)
 		goto err_engine1;
 	}
 
-	cryp->engine->prepare_cipher_request = stm32_cryp_prepare_cipher_req;
-	cryp->engine->cipher_one_request = stm32_cryp_cipher_one_req;
-
 	ret = crypto_engine_start(cryp->engine);
 	if (ret) {
 		dev_err(dev, "Could not start crypto engine\n");
@@ -1117,10 +2002,16 @@ static int stm32_cryp_probe(struct platform_device *pdev)
 		goto err_algs;
 	}
 
+	ret = crypto_register_aeads(aead_algs, ARRAY_SIZE(aead_algs));
+	if (ret)
+		goto err_aead_algs;
+
 	dev_info(dev, "Initialized\n");
 
 	return 0;
 
+err_aead_algs:
+	crypto_unregister_algs(crypto_algs, ARRAY_SIZE(crypto_algs));
 err_algs:
 err_engine2:
 	crypto_engine_exit(cryp->engine);
@@ -1141,6 +2032,7 @@ static int stm32_cryp_remove(struct platform_device *pdev)
 	if (!cryp)
 		return -ENODEV;
 
+	crypto_unregister_aeads(aead_algs, ARRAY_SIZE(aead_algs));
 	crypto_unregister_algs(crypto_algs, ARRAY_SIZE(crypto_algs));
 
 	crypto_engine_exit(cryp->engine);
diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c
index 4ca4a264a833..981e45692695 100644
--- a/drivers/crypto/stm32/stm32-hash.c
+++ b/drivers/crypto/stm32/stm32-hash.c
@@ -122,6 +122,7 @@ enum stm32_hash_data_format {
 #define HASH_DMA_THRESHOLD		50
 
 struct stm32_hash_ctx {
+	struct crypto_engine_ctx enginectx;
 	struct stm32_hash_dev	*hdev;
 	unsigned long		flags;
 
@@ -626,7 +627,7 @@ static int stm32_hash_dma_send(struct stm32_hash_dev *hdev)
 			writesl(hdev->io_base + HASH_DIN, buffer,
 				DIV_ROUND_UP(ncp, sizeof(u32)));
 		}
-		stm32_hash_set_nblw(hdev, DIV_ROUND_UP(ncp, sizeof(u32)));
+		stm32_hash_set_nblw(hdev, ncp);
 		reg = stm32_hash_read(hdev, HASH_STR);
 		reg |= HASH_STR_DCAL;
 		stm32_hash_write(hdev, HASH_STR, reg);
@@ -743,13 +744,15 @@ static int stm32_hash_final_req(struct stm32_hash_dev *hdev)
 	struct ahash_request *req = hdev->req;
 	struct stm32_hash_request_ctx *rctx = ahash_request_ctx(req);
 	int err;
+	int buflen = rctx->bufcnt;
+
+	rctx->bufcnt = 0;
 
 	if (!(rctx->flags & HASH_FLAGS_CPU))
 		err = stm32_hash_dma_send(hdev);
 	else
-		err = stm32_hash_xmit_cpu(hdev, rctx->buffer, rctx->bufcnt, 1);
+		err = stm32_hash_xmit_cpu(hdev, rctx->buffer, buflen, 1);
 
-	rctx->bufcnt = 0;
 
 	return err;
 }
@@ -828,15 +831,19 @@ static int stm32_hash_hw_init(struct stm32_hash_dev *hdev,
 	return 0;
 }
 
+static int stm32_hash_one_request(struct crypto_engine *engine, void *areq);
+static int stm32_hash_prepare_req(struct crypto_engine *engine, void *areq);
+
 static int stm32_hash_handle_queue(struct stm32_hash_dev *hdev,
 				   struct ahash_request *req)
 {
 	return crypto_transfer_hash_request_to_engine(hdev->engine, req);
 }
 
-static int stm32_hash_prepare_req(struct crypto_engine *engine,
-				  struct ahash_request *req)
+static int stm32_hash_prepare_req(struct crypto_engine *engine, void *areq)
 {
+	struct ahash_request *req = container_of(areq, struct ahash_request,
+						 base);
 	struct stm32_hash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(req));
 	struct stm32_hash_dev *hdev = stm32_hash_find_dev(ctx);
 	struct stm32_hash_request_ctx *rctx;
@@ -854,9 +861,10 @@ static int stm32_hash_prepare_req(struct crypto_engine *engine,
 	return stm32_hash_hw_init(hdev, rctx);
 }
 
-static int stm32_hash_one_request(struct crypto_engine *engine,
-				  struct ahash_request *req)
+static int stm32_hash_one_request(struct crypto_engine *engine, void *areq)
 {
+	struct ahash_request *req = container_of(areq, struct ahash_request,
+						 base);
 	struct stm32_hash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(req));
 	struct stm32_hash_dev *hdev = stm32_hash_find_dev(ctx);
 	struct stm32_hash_request_ctx *rctx;
@@ -1033,6 +1041,9 @@ static int stm32_hash_cra_init_algs(struct crypto_tfm *tfm,
 	if (algs_hmac_name)
 		ctx->flags |= HASH_FLAGS_HMAC;
 
+	ctx->enginectx.op.do_one_request = stm32_hash_one_request;
+	ctx->enginectx.op.prepare_request = stm32_hash_prepare_req;
+	ctx->enginectx.op.unprepare_request = NULL;
 	return 0;
 }
 
@@ -1096,6 +1107,8 @@ static irqreturn_t stm32_hash_irq_handler(int irq, void *dev_id)
 		reg &= ~HASH_SR_OUTPUT_READY;
 		stm32_hash_write(hdev, HASH_SR, reg);
 		hdev->flags |= HASH_FLAGS_OUTPUT_READY;
+		/* Disable IT*/
+		stm32_hash_write(hdev, HASH_IMR, 0);
 		return IRQ_WAKE_THREAD;
 	}
 
@@ -1404,18 +1417,19 @@ MODULE_DEVICE_TABLE(of, stm32_hash_of_match);
 static int stm32_hash_get_of_match(struct stm32_hash_dev *hdev,
 				   struct device *dev)
 {
-	int err;
-
 	hdev->pdata = of_device_get_match_data(dev);
 	if (!hdev->pdata) {
 		dev_err(dev, "no compatible OF match\n");
 		return -EINVAL;
 	}
 
-	err = of_property_read_u32(dev->of_node, "dma-maxburst",
-				   &hdev->dma_maxburst);
+	if (of_property_read_u32(dev->of_node, "dma-maxburst",
+				 &hdev->dma_maxburst)) {
+		dev_info(dev, "dma-maxburst not specified, using 0\n");
+		hdev->dma_maxburst = 0;
+	}
 
-	return err;
+	return 0;
 }
 
 static int stm32_hash_probe(struct platform_device *pdev)
@@ -1493,9 +1507,6 @@ static int stm32_hash_probe(struct platform_device *pdev)
 		goto err_engine;
 	}
 
-	hdev->engine->prepare_hash_request = stm32_hash_prepare_req;
-	hdev->engine->hash_one_request = stm32_hash_one_request;
-
 	ret = crypto_engine_start(hdev->engine);
 	if (ret)
 		goto err_engine_start;
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
index 1547cbe13dc2..a81d89b3b7d8 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
@@ -451,6 +451,7 @@ static struct platform_driver sun4i_ss_driver = {
 
 module_platform_driver(sun4i_ss_driver);
 
+MODULE_ALIAS("platform:sun4i-ss");
 MODULE_DESCRIPTION("Allwinner Security System cryptographic accelerator");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Corentin LABBE <clabbe.montjoie@gmail.com>");
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 6882fa2f8bad..7cebf0a6ffbc 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -104,16 +104,34 @@ static void to_talitos_ptr_ext_or(struct talitos_ptr *ptr, u8 val, bool is_sec1)
 /*
  * map virtual single (contiguous) pointer to h/w descriptor pointer
  */
+static void __map_single_talitos_ptr(struct device *dev,
+				     struct talitos_ptr *ptr,
+				     unsigned int len, void *data,
+				     enum dma_data_direction dir,
+				     unsigned long attrs)
+{
+	dma_addr_t dma_addr = dma_map_single_attrs(dev, data, len, dir, attrs);
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	to_talitos_ptr(ptr, dma_addr, len, is_sec1);
+}
+
 static void map_single_talitos_ptr(struct device *dev,
 				   struct talitos_ptr *ptr,
 				   unsigned int len, void *data,
 				   enum dma_data_direction dir)
 {
-	dma_addr_t dma_addr = dma_map_single(dev, data, len, dir);
-	struct talitos_private *priv = dev_get_drvdata(dev);
-	bool is_sec1 = has_ftr_sec1(priv);
+	__map_single_talitos_ptr(dev, ptr, len, data, dir, 0);
+}
 
-	to_talitos_ptr(ptr, dma_addr, len, is_sec1);
+static void map_single_talitos_ptr_nosync(struct device *dev,
+					  struct talitos_ptr *ptr,
+					  unsigned int len, void *data,
+					  enum dma_data_direction dir)
+{
+	__map_single_talitos_ptr(dev, ptr, len, data, dir,
+				 DMA_ATTR_SKIP_CPU_SYNC);
 }
 
 /*
@@ -832,8 +850,6 @@ struct talitos_ctx {
 	unsigned int keylen;
 	unsigned int enckeylen;
 	unsigned int authkeylen;
-	dma_addr_t dma_buf;
-	dma_addr_t dma_hw_context;
 };
 
 #define HASH_MAX_BLOCK_SIZE		SHA512_BLOCK_SIZE
@@ -888,10 +904,12 @@ static int aead_setkey(struct crypto_aead *authenc,
 	ctx->dma_key = dma_map_single(dev, ctx->key, ctx->keylen,
 				      DMA_TO_DEVICE);
 
+	memzero_explicit(&keys, sizeof(keys));
 	return 0;
 
 badkey:
 	crypto_aead_set_flags(authenc, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	memzero_explicit(&keys, sizeof(keys));
 	return -EINVAL;
 }
 
@@ -1130,10 +1148,10 @@ next:
 	return count;
 }
 
-static int talitos_sg_map(struct device *dev, struct scatterlist *src,
-		   unsigned int len, struct talitos_edesc *edesc,
-		   struct talitos_ptr *ptr,
-		   int sg_count, unsigned int offset, int tbl_off)
+static int talitos_sg_map_ext(struct device *dev, struct scatterlist *src,
+			      unsigned int len, struct talitos_edesc *edesc,
+			      struct talitos_ptr *ptr, int sg_count,
+			      unsigned int offset, int tbl_off, int elen)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
@@ -1142,6 +1160,7 @@ static int talitos_sg_map(struct device *dev, struct scatterlist *src,
 		to_talitos_ptr(ptr, 0, 0, is_sec1);
 		return 1;
 	}
+	to_talitos_ptr_ext_set(ptr, elen, is_sec1);
 	if (sg_count == 1) {
 		to_talitos_ptr(ptr, sg_dma_address(src) + offset, len, is_sec1);
 		return sg_count;
@@ -1150,7 +1169,7 @@ static int talitos_sg_map(struct device *dev, struct scatterlist *src,
 		to_talitos_ptr(ptr, edesc->dma_link_tbl + offset, len, is_sec1);
 		return sg_count;
 	}
-	sg_count = sg_to_link_tbl_offset(src, sg_count, offset, len,
+	sg_count = sg_to_link_tbl_offset(src, sg_count, offset, len + elen,
 					 &edesc->link_tbl[tbl_off]);
 	if (sg_count == 1) {
 		/* Only one segment now, so no link tbl needed*/
@@ -1164,6 +1183,15 @@ static int talitos_sg_map(struct device *dev, struct scatterlist *src,
 	return sg_count;
 }
 
+static int talitos_sg_map(struct device *dev, struct scatterlist *src,
+			  unsigned int len, struct talitos_edesc *edesc,
+			  struct talitos_ptr *ptr, int sg_count,
+			  unsigned int offset, int tbl_off)
+{
+	return talitos_sg_map_ext(dev, src, len, edesc, ptr, sg_count, offset,
+				  tbl_off, 0);
+}
+
 /*
  * fill in and submit ipsec_esp descriptor
  */
@@ -1181,7 +1209,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	unsigned int ivsize = crypto_aead_ivsize(aead);
 	int tbl_off = 0;
 	int sg_count, ret;
-	int sg_link_tbl_len;
+	int elen = 0;
 	bool sync_needed = false;
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
@@ -1223,17 +1251,11 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	 * extent is bytes of HMAC postpended to ciphertext,
 	 * typically 12 for ipsec
 	 */
-	sg_link_tbl_len = cryptlen;
-
-	if (is_ipsec_esp) {
-		to_talitos_ptr_ext_set(&desc->ptr[4], authsize, is_sec1);
+	if (is_ipsec_esp && (desc->hdr & DESC_HDR_MODE1_MDEU_CICV))
+		elen = authsize;
 
-		if (desc->hdr & DESC_HDR_MODE1_MDEU_CICV)
-			sg_link_tbl_len += authsize;
-	}
-
-	ret = talitos_sg_map(dev, areq->src, sg_link_tbl_len, edesc,
-			     &desc->ptr[4], sg_count, areq->assoclen, tbl_off);
+	ret = talitos_sg_map_ext(dev, areq->src, cryptlen, edesc, &desc->ptr[4],
+				 sg_count, areq->assoclen, tbl_off, elen);
 
 	if (ret > 1) {
 		tbl_off += ret;
@@ -1404,7 +1426,6 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 
 	edesc = kmalloc(alloc_len, GFP_DMA | flags);
 	if (!edesc) {
-		dev_err(dev, "could not allocate edescriptor\n");
 		err = ERR_PTR(-ENOMEM);
 		goto error_sg;
 	}
@@ -1690,9 +1711,30 @@ static void common_nonsnoop_hash_unmap(struct device *dev,
 				       struct ahash_request *areq)
 {
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+	struct talitos_desc *desc = &edesc->desc;
+	struct talitos_desc *desc2 = desc + 1;
+
+	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE);
+	if (desc->next_desc &&
+	    desc->ptr[5].ptr != desc2->ptr[5].ptr)
+		unmap_single_talitos_ptr(dev, &desc2->ptr[5], DMA_FROM_DEVICE);
 
 	talitos_sg_unmap(dev, edesc, req_ctx->psrc, NULL, 0, 0);
 
+	/* When using hashctx-in, must unmap it. */
+	if (from_talitos_ptr_len(&edesc->desc.ptr[1], is_sec1))
+		unmap_single_talitos_ptr(dev, &edesc->desc.ptr[1],
+					 DMA_TO_DEVICE);
+	else if (desc->next_desc)
+		unmap_single_talitos_ptr(dev, &desc2->ptr[1],
+					 DMA_TO_DEVICE);
+
+	if (is_sec1 && req_ctx->nbuf)
+		unmap_single_talitos_ptr(dev, &desc->ptr[3],
+					 DMA_TO_DEVICE);
+
 	if (edesc->dma_len)
 		dma_unmap_single(dev, edesc->dma_link_tbl, edesc->dma_len,
 				 DMA_BIDIRECTIONAL);
@@ -1766,8 +1808,10 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 
 	/* hash context in */
 	if (!req_ctx->first || req_ctx->swinit) {
-		to_talitos_ptr(&desc->ptr[1], ctx->dma_hw_context,
-			       req_ctx->hw_context_size, is_sec1);
+		map_single_talitos_ptr_nosync(dev, &desc->ptr[1],
+					      req_ctx->hw_context_size,
+					      req_ctx->hw_context,
+					      DMA_TO_DEVICE);
 		req_ctx->swinit = 0;
 	}
 	/* Indicate next op is not the first. */
@@ -1793,10 +1837,9 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	 * data in
 	 */
 	if (is_sec1 && req_ctx->nbuf) {
-		dma_addr_t dma_buf = ctx->dma_buf + req_ctx->buf_idx *
-						    HASH_MAX_BLOCK_SIZE;
-
-		to_talitos_ptr(&desc->ptr[3], dma_buf, req_ctx->nbuf, is_sec1);
+		map_single_talitos_ptr(dev, &desc->ptr[3], req_ctx->nbuf,
+				       req_ctx->buf[req_ctx->buf_idx],
+				       DMA_TO_DEVICE);
 	} else {
 		sg_count = talitos_sg_map(dev, req_ctx->psrc, length, edesc,
 					  &desc->ptr[3], sg_count, offset, 0);
@@ -1812,8 +1855,10 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 				       crypto_ahash_digestsize(tfm),
 				       areq->result, DMA_FROM_DEVICE);
 	else
-		to_talitos_ptr(&desc->ptr[5], ctx->dma_hw_context,
-			       req_ctx->hw_context_size, is_sec1);
+		map_single_talitos_ptr_nosync(dev, &desc->ptr[5],
+					      req_ctx->hw_context_size,
+					      req_ctx->hw_context,
+					      DMA_FROM_DEVICE);
 
 	/* last DWORD empty */
 
@@ -1832,9 +1877,14 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 		desc->hdr |= DESC_HDR_MODE0_MDEU_CONT;
 		desc->hdr &= ~DESC_HDR_DONE_NOTIFY;
 
-		to_talitos_ptr(&desc2->ptr[1], ctx->dma_hw_context,
-			       req_ctx->hw_context_size, is_sec1);
-
+		if (desc->ptr[1].ptr)
+			copy_talitos_ptr(&desc2->ptr[1], &desc->ptr[1],
+					 is_sec1);
+		else
+			map_single_talitos_ptr_nosync(dev, &desc2->ptr[1],
+						      req_ctx->hw_context_size,
+						      req_ctx->hw_context,
+						      DMA_TO_DEVICE);
 		copy_talitos_ptr(&desc2->ptr[2], &desc->ptr[2], is_sec1);
 		sg_count = talitos_sg_map(dev, req_ctx->psrc, length, edesc,
 					  &desc2->ptr[3], sg_count, offset, 0);
@@ -1842,8 +1892,10 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 			sync_needed = true;
 		copy_talitos_ptr(&desc2->ptr[5], &desc->ptr[5], is_sec1);
 		if (req_ctx->last)
-			to_talitos_ptr(&desc->ptr[5], ctx->dma_hw_context,
-				       req_ctx->hw_context_size, is_sec1);
+			map_single_talitos_ptr_nosync(dev, &desc->ptr[5],
+						      req_ctx->hw_context_size,
+						      req_ctx->hw_context,
+						      DMA_FROM_DEVICE);
 
 		next_desc = dma_map_single(dev, &desc2->hdr1, TALITOS_DESC_SIZE,
 					   DMA_BIDIRECTIONAL);
@@ -1885,8 +1937,7 @@ static int ahash_init(struct ahash_request *areq)
 	struct device *dev = ctx->dev;
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
 	unsigned int size;
-	struct talitos_private *priv = dev_get_drvdata(dev);
-	bool is_sec1 = has_ftr_sec1(priv);
+	dma_addr_t dma;
 
 	/* Initialize the context */
 	req_ctx->buf_idx = 0;
@@ -1898,18 +1949,10 @@ static int ahash_init(struct ahash_request *areq)
 			: TALITOS_MDEU_CONTEXT_SIZE_SHA384_SHA512;
 	req_ctx->hw_context_size = size;
 
-	if (ctx->dma_hw_context)
-		dma_unmap_single(dev, ctx->dma_hw_context, size,
-				 DMA_BIDIRECTIONAL);
-	ctx->dma_hw_context = dma_map_single(dev, req_ctx->hw_context, size,
-					     DMA_BIDIRECTIONAL);
-	if (ctx->dma_buf)
-		dma_unmap_single(dev, ctx->dma_buf, sizeof(req_ctx->buf),
-				 DMA_TO_DEVICE);
-	if (is_sec1)
-		ctx->dma_buf = dma_map_single(dev, req_ctx->buf,
-					      sizeof(req_ctx->buf),
-					      DMA_TO_DEVICE);
+	dma = dma_map_single(dev, req_ctx->hw_context, req_ctx->hw_context_size,
+			     DMA_TO_DEVICE);
+	dma_unmap_single(dev, dma, req_ctx->hw_context_size, DMA_TO_DEVICE);
+
 	return 0;
 }
 
@@ -1920,12 +1963,6 @@ static int ahash_init(struct ahash_request *areq)
 static int ahash_init_sha224_swinit(struct ahash_request *areq)
 {
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
-	struct talitos_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct device *dev = ctx->dev;
-
-	ahash_init(areq);
-	req_ctx->swinit = 1;/* prevent h/w initting context with sha256 values*/
 
 	req_ctx->hw_context[0] = SHA224_H0;
 	req_ctx->hw_context[1] = SHA224_H1;
@@ -1940,8 +1977,8 @@ static int ahash_init_sha224_swinit(struct ahash_request *areq)
 	req_ctx->hw_context[8] = 0;
 	req_ctx->hw_context[9] = 0;
 
-	dma_sync_single_for_device(dev, ctx->dma_hw_context,
-				   req_ctx->hw_context_size, DMA_TO_DEVICE);
+	ahash_init(areq);
+	req_ctx->swinit = 1;/* prevent h/w initting context with sha256 values*/
 
 	return 0;
 }
@@ -2046,13 +2083,6 @@ static int ahash_process_req(struct ahash_request *areq, unsigned int nbytes)
 	/* request SEC to INIT hash. */
 	if (req_ctx->first && !req_ctx->swinit)
 		edesc->desc.hdr |= DESC_HDR_MODE0_MDEU_INIT;
-	if (is_sec1) {
-		dma_addr_t dma_buf = ctx->dma_buf + req_ctx->buf_idx *
-						    HASH_MAX_BLOCK_SIZE;
-
-		dma_sync_single_for_device(dev, dma_buf,
-					   req_ctx->nbuf, DMA_TO_DEVICE);
-	}
 
 	/* When the tfm context has a keylen, it's an HMAC.
 	 * A first or last (ie. not middle) descriptor must request HMAC.
@@ -2106,12 +2136,15 @@ static int ahash_export(struct ahash_request *areq, void *out)
 {
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
 	struct talitos_export_state *export = out;
-	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
-	struct talitos_ctx *ctx = crypto_ahash_ctx(ahash);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct talitos_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct device *dev = ctx->dev;
+	dma_addr_t dma;
+
+	dma = dma_map_single(dev, req_ctx->hw_context, req_ctx->hw_context_size,
+			     DMA_FROM_DEVICE);
+	dma_unmap_single(dev, dma, req_ctx->hw_context_size, DMA_FROM_DEVICE);
 
-	dma_sync_single_for_cpu(dev, ctx->dma_hw_context,
-				req_ctx->hw_context_size, DMA_FROM_DEVICE);
 	memcpy(export->hw_context, req_ctx->hw_context,
 	       req_ctx->hw_context_size);
 	memcpy(export->buf, req_ctx->buf[req_ctx->buf_idx], req_ctx->nbuf);
@@ -2128,39 +2161,29 @@ static int ahash_import(struct ahash_request *areq, const void *in)
 {
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
-	const struct talitos_export_state *export = in;
-	unsigned int size;
 	struct talitos_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct device *dev = ctx->dev;
-	struct talitos_private *priv = dev_get_drvdata(dev);
-	bool is_sec1 = has_ftr_sec1(priv);
+	const struct talitos_export_state *export = in;
+	unsigned int size;
+	dma_addr_t dma;
 
 	memset(req_ctx, 0, sizeof(*req_ctx));
 	size = (crypto_ahash_digestsize(tfm) <= SHA256_DIGEST_SIZE)
 			? TALITOS_MDEU_CONTEXT_SIZE_MD5_SHA1_SHA256
 			: TALITOS_MDEU_CONTEXT_SIZE_SHA384_SHA512;
 	req_ctx->hw_context_size = size;
-	if (ctx->dma_hw_context)
-		dma_unmap_single(dev, ctx->dma_hw_context, size,
-				 DMA_BIDIRECTIONAL);
-
 	memcpy(req_ctx->hw_context, export->hw_context, size);
-	ctx->dma_hw_context = dma_map_single(dev, req_ctx->hw_context, size,
-					     DMA_BIDIRECTIONAL);
-	if (ctx->dma_buf)
-		dma_unmap_single(dev, ctx->dma_buf, sizeof(req_ctx->buf),
-				 DMA_TO_DEVICE);
 	memcpy(req_ctx->buf[0], export->buf, export->nbuf);
-	if (is_sec1)
-		ctx->dma_buf = dma_map_single(dev, req_ctx->buf,
-					      sizeof(req_ctx->buf),
-					      DMA_TO_DEVICE);
 	req_ctx->swinit = export->swinit;
 	req_ctx->first = export->first;
 	req_ctx->last = export->last;
 	req_ctx->to_hash_later = export->to_hash_later;
 	req_ctx->nbuf = export->nbuf;
 
+	dma = dma_map_single(dev, req_ctx->hw_context, req_ctx->hw_context_size,
+			     DMA_TO_DEVICE);
+	dma_unmap_single(dev, dma, req_ctx->hw_context_size, DMA_TO_DEVICE);
+
 	return 0;
 }
 
@@ -3064,27 +3087,6 @@ static void talitos_cra_exit(struct crypto_tfm *tfm)
 		dma_unmap_single(dev, ctx->dma_key, ctx->keylen, DMA_TO_DEVICE);
 }
 
-static void talitos_cra_exit_ahash(struct crypto_tfm *tfm)
-{
-	struct talitos_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct device *dev = ctx->dev;
-	unsigned int size;
-
-	talitos_cra_exit(tfm);
-
-	size = (crypto_ahash_digestsize(__crypto_ahash_cast(tfm)) <=
-		SHA256_DIGEST_SIZE)
-	       ? TALITOS_MDEU_CONTEXT_SIZE_MD5_SHA1_SHA256
-	       : TALITOS_MDEU_CONTEXT_SIZE_SHA384_SHA512;
-
-	if (ctx->dma_hw_context)
-		dma_unmap_single(dev, ctx->dma_hw_context, size,
-				 DMA_BIDIRECTIONAL);
-	if (ctx->dma_buf)
-		dma_unmap_single(dev, ctx->dma_buf, HASH_MAX_BLOCK_SIZE * 2,
-				 DMA_TO_DEVICE);
-}
-
 /*
  * given the alg's descriptor header template, determine whether descriptor
  * type and primary/secondary execution units required match the hw
@@ -3183,7 +3185,7 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 	case CRYPTO_ALG_TYPE_AHASH:
 		alg = &t_alg->algt.alg.hash.halg.base;
 		alg->cra_init = talitos_cra_init_ahash;
-		alg->cra_exit = talitos_cra_exit_ahash;
+		alg->cra_exit = talitos_cra_exit;
 		alg->cra_type = &crypto_ahash_type;
 		t_alg->algt.alg.hash.init = ahash_init;
 		t_alg->algt.alg.hash.update = ahash_update;
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index 765f53e548ab..cb31b59c9d53 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -1404,9 +1404,8 @@ static void cryp_algs_unregister_all(void)
 static int ux500_cryp_probe(struct platform_device *pdev)
 {
 	int ret;
-	int cryp_error = 0;
-	struct resource *res = NULL;
-	struct resource *res_irq = NULL;
+	struct resource *res;
+	struct resource *res_irq;
 	struct cryp_device_data *device_data;
 	struct cryp_protection_config prot = {
 		.privilege_access = CRYP_STATE_ENABLE
@@ -1416,7 +1415,6 @@ static int ux500_cryp_probe(struct platform_device *pdev)
 	dev_dbg(dev, "[%s]", __func__);
 	device_data = devm_kzalloc(dev, sizeof(*device_data), GFP_ATOMIC);
 	if (!device_data) {
-		dev_err(dev, "[%s]: kzalloc() failed!", __func__);
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1479,15 +1477,13 @@ static int ux500_cryp_probe(struct platform_device *pdev)
 		goto out_clk_unprepare;
 	}
 
-	cryp_error = cryp_check(device_data);
-	if (cryp_error != 0) {
-		dev_err(dev, "[%s]: cryp_init() failed!", __func__);
+	if (cryp_check(device_data)) {
+		dev_err(dev, "[%s]: cryp_check() failed!", __func__);
 		ret = -EINVAL;
 		goto out_power;
 	}
 
-	cryp_error = cryp_configure_protection(device_data, &prot);
-	if (cryp_error != 0) {
+	if (cryp_configure_protection(device_data, &prot)) {
 		dev_err(dev, "[%s]: cryp_configure_protection() failed!",
 			__func__);
 		ret = -EINVAL;
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 9acccad26928..2d0a677bcc76 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -1403,6 +1403,16 @@ out:
 	return ret1 ? ret1 : ret2;
 }
 
+static int ahash_noimport(struct ahash_request *req, const void *in)
+{
+	return -ENOSYS;
+}
+
+static int ahash_noexport(struct ahash_request *req, void *out)
+{
+	return -ENOSYS;
+}
+
 static int hmac_sha1_init(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
@@ -1507,6 +1517,8 @@ static struct hash_algo_template hash_algs[] = {
 			.update = ahash_update,
 			.final = ahash_final,
 			.digest = ahash_sha1_digest,
+			.export = ahash_noexport,
+			.import = ahash_noimport,
 			.halg.digestsize = SHA1_DIGEST_SIZE,
 			.halg.statesize = sizeof(struct hash_ctx),
 			.halg.base = {
@@ -1529,6 +1541,8 @@ static struct hash_algo_template hash_algs[] = {
 			.update	= ahash_update,
 			.final = ahash_final,
 			.digest = ahash_sha256_digest,
+			.export = ahash_noexport,
+			.import = ahash_noimport,
 			.halg.digestsize = SHA256_DIGEST_SIZE,
 			.halg.statesize = sizeof(struct hash_ctx),
 			.halg.base = {
@@ -1553,6 +1567,8 @@ static struct hash_algo_template hash_algs[] = {
 			.final = ahash_final,
 			.digest = hmac_sha1_digest,
 			.setkey = hmac_sha1_setkey,
+			.export = ahash_noexport,
+			.import = ahash_noimport,
 			.halg.digestsize = SHA1_DIGEST_SIZE,
 			.halg.statesize = sizeof(struct hash_ctx),
 			.halg.base = {
@@ -1577,6 +1593,8 @@ static struct hash_algo_template hash_algs[] = {
 			.final = ahash_final,
 			.digest = hmac_sha256_digest,
 			.setkey = hmac_sha256_setkey,
+			.export = ahash_noexport,
+			.import = ahash_noimport,
 			.halg.digestsize = SHA256_DIGEST_SIZE,
 			.halg.statesize = sizeof(struct hash_ctx),
 			.halg.base = {
diff --git a/drivers/crypto/virtio/Kconfig b/drivers/crypto/virtio/Kconfig
index 5db07495ddc5..a4324b1383a4 100644
--- a/drivers/crypto/virtio/Kconfig
+++ b/drivers/crypto/virtio/Kconfig
@@ -2,7 +2,6 @@ config CRYPTO_DEV_VIRTIO
 	tristate "VirtIO crypto driver"
 	depends on VIRTIO
 	select CRYPTO_AEAD
-	select CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_ENGINE
 	default m
diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c
index abe8c15450df..ba190cfa7aa1 100644
--- a/drivers/crypto/virtio/virtio_crypto_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_algs.c
@@ -29,6 +29,7 @@
 
 
 struct virtio_crypto_ablkcipher_ctx {
+	struct crypto_engine_ctx enginectx;
 	struct virtio_crypto *vcrypto;
 	struct crypto_tfm *tfm;
 
@@ -491,7 +492,7 @@ static int virtio_crypto_ablkcipher_encrypt(struct ablkcipher_request *req)
 	vc_sym_req->ablkcipher_req = req;
 	vc_sym_req->encrypt = true;
 
-	return crypto_transfer_cipher_request_to_engine(data_vq->engine, req);
+	return crypto_transfer_ablkcipher_request_to_engine(data_vq->engine, req);
 }
 
 static int virtio_crypto_ablkcipher_decrypt(struct ablkcipher_request *req)
@@ -511,7 +512,7 @@ static int virtio_crypto_ablkcipher_decrypt(struct ablkcipher_request *req)
 	vc_sym_req->ablkcipher_req = req;
 	vc_sym_req->encrypt = false;
 
-	return crypto_transfer_cipher_request_to_engine(data_vq->engine, req);
+	return crypto_transfer_ablkcipher_request_to_engine(data_vq->engine, req);
 }
 
 static int virtio_crypto_ablkcipher_init(struct crypto_tfm *tfm)
@@ -521,6 +522,9 @@ static int virtio_crypto_ablkcipher_init(struct crypto_tfm *tfm)
 	tfm->crt_ablkcipher.reqsize = sizeof(struct virtio_crypto_sym_request);
 	ctx->tfm = tfm;
 
+	ctx->enginectx.op.do_one_request = virtio_crypto_ablkcipher_crypt_req;
+	ctx->enginectx.op.prepare_request = NULL;
+	ctx->enginectx.op.unprepare_request = NULL;
 	return 0;
 }
 
@@ -538,9 +542,9 @@ static void virtio_crypto_ablkcipher_exit(struct crypto_tfm *tfm)
 }
 
 int virtio_crypto_ablkcipher_crypt_req(
-	struct crypto_engine *engine,
-	struct ablkcipher_request *req)
+	struct crypto_engine *engine, void *vreq)
 {
+	struct ablkcipher_request *req = container_of(vreq, struct ablkcipher_request, base);
 	struct virtio_crypto_sym_request *vc_sym_req =
 				ablkcipher_request_ctx(req);
 	struct virtio_crypto_request *vc_req = &vc_sym_req->base;
@@ -561,8 +565,8 @@ static void virtio_crypto_ablkcipher_finalize_req(
 	struct ablkcipher_request *req,
 	int err)
 {
-	crypto_finalize_cipher_request(vc_sym_req->base.dataq->engine,
-					req, err);
+	crypto_finalize_ablkcipher_request(vc_sym_req->base.dataq->engine,
+					   req, err);
 	kzfree(vc_sym_req->iv);
 	virtcrypto_clear_request(&vc_sym_req->base);
 }
diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h
index e976539a05d9..66501a5a2b7b 100644
--- a/drivers/crypto/virtio/virtio_crypto_common.h
+++ b/drivers/crypto/virtio/virtio_crypto_common.h
@@ -24,7 +24,6 @@
 #include <linux/spinlock.h>
 #include <crypto/aead.h>
 #include <crypto/aes.h>
-#include <crypto/authenc.h>
 #include <crypto/engine.h>
 
 
@@ -107,8 +106,7 @@ struct virtio_crypto *virtcrypto_get_dev_node(int node);
 int virtcrypto_dev_start(struct virtio_crypto *vcrypto);
 void virtcrypto_dev_stop(struct virtio_crypto *vcrypto);
 int virtio_crypto_ablkcipher_crypt_req(
-	struct crypto_engine *engine,
-	struct ablkcipher_request *req);
+	struct crypto_engine *engine, void *vreq);
 
 void
 virtcrypto_clear_request(struct virtio_crypto_request *vc_req);
diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c
index ff1410a32c2b..83326986c113 100644
--- a/drivers/crypto/virtio/virtio_crypto_core.c
+++ b/drivers/crypto/virtio/virtio_crypto_core.c
@@ -111,9 +111,6 @@ static int virtcrypto_find_vqs(struct virtio_crypto *vi)
 			ret = -ENOMEM;
 			goto err_engine;
 		}
-
-		vi->data_vq[i].engine->cipher_one_request =
-			virtio_crypto_ablkcipher_crypt_req;
 	}
 
 	kfree(names);
diff --git a/drivers/staging/ccree/Kconfig b/drivers/staging/ccree/Kconfig
index c94dfe8adb63..168191fa0357 100644
--- a/drivers/staging/ccree/Kconfig
+++ b/drivers/staging/ccree/Kconfig
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 
-config CRYPTO_DEV_CCREE
+config CRYPTO_DEV_CCREE_OLD
 	tristate "Support for ARM TrustZone CryptoCell C7XX family of Crypto accelerators"
-	depends on CRYPTO && CRYPTO_HW && OF && HAS_DMA
+	depends on CRYPTO && CRYPTO_HW && OF && HAS_DMA && BROKEN
 	default n
 	select CRYPTO_HASH
 	select CRYPTO_BLKCIPHER
diff --git a/drivers/staging/ccree/Makefile b/drivers/staging/ccree/Makefile
index bdc27970f95f..553db5c45354 100644
--- a/drivers/staging/ccree/Makefile
+++ b/drivers/staging/ccree/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-$(CONFIG_CRYPTO_DEV_CCREE) := ccree.o
+obj-$(CONFIG_CRYPTO_DEV_CCREE_OLD) := ccree.o
 ccree-y := cc_driver.o cc_buffer_mgr.o cc_request_mgr.o cc_cipher.o cc_hash.o cc_aead.o cc_ivgen.o cc_sram_mgr.o
 ccree-$(CONFIG_CRYPTO_FIPS) += cc_fips.o
 ccree-$(CONFIG_DEBUG_FS) += cc_debugfs.o
diff --git a/include/crypto/ablk_helper.h b/include/crypto/ablk_helper.h
deleted file mode 100644
index 4e655c2a4e15..000000000000
--- a/include/crypto/ablk_helper.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Shared async block cipher helpers
- */
-
-#ifndef _CRYPTO_ABLK_HELPER_H
-#define _CRYPTO_ABLK_HELPER_H
-
-#include <linux/crypto.h>
-#include <linux/kernel.h>
-#include <crypto/cryptd.h>
-
-struct async_helper_ctx {
-	struct cryptd_ablkcipher *cryptd_tfm;
-};
-
-extern int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
-			unsigned int key_len);
-
-extern int __ablk_encrypt(struct ablkcipher_request *req);
-
-extern int ablk_encrypt(struct ablkcipher_request *req);
-
-extern int ablk_decrypt(struct ablkcipher_request *req);
-
-extern void ablk_exit(struct crypto_tfm *tfm);
-
-extern int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name);
-
-extern int ablk_init(struct crypto_tfm *tfm);
-
-#endif /* _CRYPTO_ABLK_HELPER_H */
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index e3cebf640c00..1aba888241dd 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -30,7 +30,6 @@ struct crypto_type {
 	int (*init_tfm)(struct crypto_tfm *tfm);
 	void (*show)(struct seq_file *m, struct crypto_alg *alg);
 	int (*report)(struct sk_buff *skb, struct crypto_alg *alg);
-	struct crypto_alg *(*lookup)(const char *name, u32 type, u32 mask);
 	void (*free)(struct crypto_instance *inst);
 
 	unsigned int type;
diff --git a/include/crypto/engine.h b/include/crypto/engine.h
index dd04c1699b51..1cbec29af3d6 100644
--- a/include/crypto/engine.h
+++ b/include/crypto/engine.h
@@ -17,7 +17,10 @@
 #include <linux/kernel.h>
 #include <linux/kthread.h>
 #include <crypto/algapi.h>
+#include <crypto/aead.h>
+#include <crypto/akcipher.h>
 #include <crypto/hash.h>
+#include <crypto/skcipher.h>
 
 #define ENGINE_NAME_LEN	30
 /*
@@ -37,12 +40,6 @@
  * @unprepare_crypt_hardware: there are currently no more requests on the
  * queue so the subsystem notifies the driver that it may relax the
  * hardware by issuing this call
- * @prepare_cipher_request: do some prepare if need before handle the current request
- * @unprepare_cipher_request: undo any work done by prepare_cipher_request()
- * @cipher_one_request: do encryption for current request
- * @prepare_hash_request: do some prepare if need before handle the current request
- * @unprepare_hash_request: undo any work done by prepare_hash_request()
- * @hash_one_request: do hash for current request
  * @kworker: kthread worker struct for request pump
  * @pump_requests: work struct for scheduling work to the request pump
  * @priv_data: the engine private data
@@ -65,19 +62,6 @@ struct crypto_engine {
 	int (*prepare_crypt_hardware)(struct crypto_engine *engine);
 	int (*unprepare_crypt_hardware)(struct crypto_engine *engine);
 
-	int (*prepare_cipher_request)(struct crypto_engine *engine,
-				      struct ablkcipher_request *req);
-	int (*unprepare_cipher_request)(struct crypto_engine *engine,
-					struct ablkcipher_request *req);
-	int (*prepare_hash_request)(struct crypto_engine *engine,
-				    struct ahash_request *req);
-	int (*unprepare_hash_request)(struct crypto_engine *engine,
-				      struct ahash_request *req);
-	int (*cipher_one_request)(struct crypto_engine *engine,
-				  struct ablkcipher_request *req);
-	int (*hash_one_request)(struct crypto_engine *engine,
-				struct ahash_request *req);
-
 	struct kthread_worker           *kworker;
 	struct kthread_work             pump_requests;
 
@@ -85,19 +69,45 @@ struct crypto_engine {
 	struct crypto_async_request	*cur_req;
 };
 
-int crypto_transfer_cipher_request(struct crypto_engine *engine,
-				   struct ablkcipher_request *req,
-				   bool need_pump);
-int crypto_transfer_cipher_request_to_engine(struct crypto_engine *engine,
-					     struct ablkcipher_request *req);
-int crypto_transfer_hash_request(struct crypto_engine *engine,
-				 struct ahash_request *req, bool need_pump);
+/*
+ * struct crypto_engine_op - crypto hardware engine operations
+ * @prepare__request: do some prepare if need before handle the current request
+ * @unprepare_request: undo any work done by prepare_request()
+ * @do_one_request: do encryption for current request
+ */
+struct crypto_engine_op {
+	int (*prepare_request)(struct crypto_engine *engine,
+			       void *areq);
+	int (*unprepare_request)(struct crypto_engine *engine,
+				 void *areq);
+	int (*do_one_request)(struct crypto_engine *engine,
+			      void *areq);
+};
+
+struct crypto_engine_ctx {
+	struct crypto_engine_op op;
+};
+
+int crypto_transfer_ablkcipher_request_to_engine(struct crypto_engine *engine,
+						 struct ablkcipher_request *req);
+int crypto_transfer_aead_request_to_engine(struct crypto_engine *engine,
+					   struct aead_request *req);
+int crypto_transfer_akcipher_request_to_engine(struct crypto_engine *engine,
+					       struct akcipher_request *req);
 int crypto_transfer_hash_request_to_engine(struct crypto_engine *engine,
-					   struct ahash_request *req);
-void crypto_finalize_cipher_request(struct crypto_engine *engine,
-				    struct ablkcipher_request *req, int err);
+					       struct ahash_request *req);
+int crypto_transfer_skcipher_request_to_engine(struct crypto_engine *engine,
+					       struct skcipher_request *req);
+void crypto_finalize_ablkcipher_request(struct crypto_engine *engine,
+					struct ablkcipher_request *req, int err);
+void crypto_finalize_aead_request(struct crypto_engine *engine,
+				  struct aead_request *req, int err);
+void crypto_finalize_akcipher_request(struct crypto_engine *engine,
+				      struct akcipher_request *req, int err);
 void crypto_finalize_hash_request(struct crypto_engine *engine,
 				  struct ahash_request *req, int err);
+void crypto_finalize_skcipher_request(struct crypto_engine *engine,
+				      struct skcipher_request *req, int err);
 int crypto_engine_start(struct crypto_engine *engine);
 int crypto_engine_stop(struct crypto_engine *engine);
 struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt);
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 2d1849dffb80..76e432cab75d 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -74,7 +74,8 @@ struct ahash_request {
  * @init: **[mandatory]** Initialize the transformation context. Intended only to initialize the
  *	  state of the HASH transformation at the beginning. This shall fill in
  *	  the internal structures used during the entire duration of the whole
- *	  transformation. No data processing happens at this point.
+ *	  transformation. No data processing happens at this point. Driver code
+ *	  implementation must not use req->result.
  * @update: **[mandatory]** Push a chunk of data into the driver for transformation. This
  *	   function actually pushes blocks of data from upper layers into the
  *	   driver, which then passes those to the hardware as seen fit. This
@@ -83,7 +84,8 @@ struct ahash_request {
  *	   transformation. This function shall not modify the transformation
  *	   context, as this function may be called in parallel with the same
  *	   transformation object. Data processing can happen synchronously
- *	   [SHASH] or asynchronously [AHASH] at this point.
+ *	   [SHASH] or asynchronously [AHASH] at this point. Driver must not use
+ *	   req->result.
  * @final: **[mandatory]** Retrieve result from the driver. This function finalizes the
  *	   transformation and retrieves the resulting hash from the driver and
  *	   pushes it back to upper layers. No data processing happens at this
@@ -120,11 +122,12 @@ struct ahash_request {
  *	    you want to save partial result of the transformation after
  *	    processing certain amount of data and reload this partial result
  *	    multiple times later on for multiple re-use. No data processing
- *	    happens at this point.
+ *	    happens at this point. Driver must not use req->result.
  * @import: Import partial state of the transformation. This function loads the
  *	    entire state of the ongoing transformation from a provided block of
  *	    data so the transformation can continue from this point onward. No
- *	    data processing happens at this point.
+ *	    data processing happens at this point. Driver must not use
+ *	    req->result.
  * @halg: see struct hash_alg_common
  */
 struct ahash_alg {
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 27040a46d50a..a0b0ad9d585e 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -126,11 +126,6 @@ int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc);
 int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc);
 int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc);
 
-int ahash_mcryptd_update(struct ahash_request *desc);
-int ahash_mcryptd_final(struct ahash_request *desc);
-int ahash_mcryptd_finup(struct ahash_request *desc);
-int ahash_mcryptd_digest(struct ahash_request *desc);
-
 int crypto_init_shash_ops_async(struct crypto_tfm *tfm);
 
 static inline void *crypto_ahash_ctx(struct crypto_ahash *tfm)
diff --git a/include/crypto/internal/simd.h b/include/crypto/internal/simd.h
index 32ceb6929885..f18344518e32 100644
--- a/include/crypto/internal/simd.h
+++ b/include/crypto/internal/simd.h
@@ -7,6 +7,7 @@
 #define _CRYPTO_INTERNAL_SIMD_H
 
 struct simd_skcipher_alg;
+struct skcipher_alg;
 
 struct simd_skcipher_alg *simd_skcipher_create_compat(const char *algname,
 						      const char *drvname,
@@ -15,4 +16,10 @@ struct simd_skcipher_alg *simd_skcipher_create(const char *algname,
 					       const char *basename);
 void simd_skcipher_free(struct simd_skcipher_alg *alg);
 
+int simd_register_skciphers_compat(struct skcipher_alg *algs, int count,
+				   struct simd_skcipher_alg **simd_algs);
+
+void simd_unregister_skciphers(struct skcipher_alg *algs, int count,
+			       struct simd_skcipher_alg **simd_algs);
+
 #endif /* _CRYPTO_INTERNAL_SIMD_H */
diff --git a/include/crypto/lrw.h b/include/crypto/lrw.h
deleted file mode 100644
index a9d44c06d081..000000000000
--- a/include/crypto/lrw.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _CRYPTO_LRW_H
-#define _CRYPTO_LRW_H
-
-#include <crypto/b128ops.h>
-
-struct scatterlist;
-struct gf128mul_64k;
-struct blkcipher_desc;
-
-#define LRW_BLOCK_SIZE 16
-
-struct lrw_table_ctx {
-	/* optimizes multiplying a random (non incrementing, as at the
-	 * start of a new sector) value with key2, we could also have
-	 * used 4k optimization tables or no optimization at all. In the
-	 * latter case we would have to store key2 here */
-	struct gf128mul_64k *table;
-	/* stores:
-	 *  key2*{ 0,0,...0,0,0,0,1 }, key2*{ 0,0,...0,0,0,1,1 },
-	 *  key2*{ 0,0,...0,0,1,1,1 }, key2*{ 0,0,...0,1,1,1,1 }
-	 *  key2*{ 0,0,...1,1,1,1,1 }, etc
-	 * needed for optimized multiplication of incrementing values
-	 * with key2 */
-	be128 mulinc[128];
-};
-
-int lrw_init_table(struct lrw_table_ctx *ctx, const u8 *tweak);
-void lrw_free_table(struct lrw_table_ctx *ctx);
-
-struct lrw_crypt_req {
-	be128 *tbuf;
-	unsigned int tbuflen;
-
-	struct lrw_table_ctx *table_ctx;
-	void *crypt_ctx;
-	void (*crypt_fn)(void *ctx, u8 *blks, unsigned int nbytes);
-};
-
-int lrw_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-	      struct scatterlist *src, unsigned int nbytes,
-	      struct lrw_crypt_req *req);
-
-#endif  /* _CRYPTO_LRW_H */
diff --git a/include/crypto/sm4.h b/include/crypto/sm4.h
new file mode 100644
index 000000000000..b64e64d20b28
--- /dev/null
+++ b/include/crypto/sm4.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Common values for the SM4 algorithm
+ * Copyright (C) 2018 ARM Limited or its affiliates.
+ */
+
+#ifndef _CRYPTO_SM4_H
+#define _CRYPTO_SM4_H
+
+#include <linux/types.h>
+#include <linux/crypto.h>
+
+#define SM4_KEY_SIZE	16
+#define SM4_BLOCK_SIZE	16
+#define SM4_RKEY_WORDS	32
+
+struct crypto_sm4_ctx {
+	u32 rkey_enc[SM4_RKEY_WORDS];
+	u32 rkey_dec[SM4_RKEY_WORDS];
+};
+
+int crypto_sm4_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+		       unsigned int key_len);
+int crypto_sm4_expand_key(struct crypto_sm4_ctx *ctx, const u8 *in_key,
+			  unsigned int key_len);
+
+#endif
diff --git a/include/crypto/speck.h b/include/crypto/speck.h
new file mode 100644
index 000000000000..73cfc952d405
--- /dev/null
+++ b/include/crypto/speck.h
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common values for the Speck algorithm
+ */
+
+#ifndef _CRYPTO_SPECK_H
+#define _CRYPTO_SPECK_H
+
+#include <linux/types.h>
+
+/* Speck128 */
+
+#define SPECK128_BLOCK_SIZE	16
+
+#define SPECK128_128_KEY_SIZE	16
+#define SPECK128_128_NROUNDS	32
+
+#define SPECK128_192_KEY_SIZE	24
+#define SPECK128_192_NROUNDS	33
+
+#define SPECK128_256_KEY_SIZE	32
+#define SPECK128_256_NROUNDS	34
+
+struct speck128_tfm_ctx {
+	u64 round_keys[SPECK128_256_NROUNDS];
+	int nrounds;
+};
+
+void crypto_speck128_encrypt(const struct speck128_tfm_ctx *ctx,
+			     u8 *out, const u8 *in);
+
+void crypto_speck128_decrypt(const struct speck128_tfm_ctx *ctx,
+			     u8 *out, const u8 *in);
+
+int crypto_speck128_setkey(struct speck128_tfm_ctx *ctx, const u8 *key,
+			   unsigned int keysize);
+
+/* Speck64 */
+
+#define SPECK64_BLOCK_SIZE	8
+
+#define SPECK64_96_KEY_SIZE	12
+#define SPECK64_96_NROUNDS	26
+
+#define SPECK64_128_KEY_SIZE	16
+#define SPECK64_128_NROUNDS	27
+
+struct speck64_tfm_ctx {
+	u32 round_keys[SPECK64_128_NROUNDS];
+	int nrounds;
+};
+
+void crypto_speck64_encrypt(const struct speck64_tfm_ctx *ctx,
+			    u8 *out, const u8 *in);
+
+void crypto_speck64_decrypt(const struct speck64_tfm_ctx *ctx,
+			    u8 *out, const u8 *in);
+
+int crypto_speck64_setkey(struct speck64_tfm_ctx *ctx, const u8 *key,
+			  unsigned int keysize);
+
+#endif /* _CRYPTO_SPECK_H */
diff --git a/include/crypto/xts.h b/include/crypto/xts.h
index 322aab6e78a7..34d94c95445a 100644
--- a/include/crypto/xts.h
+++ b/include/crypto/xts.h
@@ -6,27 +6,10 @@
 #include <crypto/internal/skcipher.h>
 #include <linux/fips.h>
 
-struct scatterlist;
-struct blkcipher_desc;
-
 #define XTS_BLOCK_SIZE 16
 
-struct xts_crypt_req {
-	le128 *tbuf;
-	unsigned int tbuflen;
-
-	void *tweak_ctx;
-	void (*tweak_fn)(void *ctx, u8* dst, const u8* src);
-	void *crypt_ctx;
-	void (*crypt_fn)(void *ctx, u8 *blks, unsigned int nbytes);
-};
-
 #define XTS_TWEAK_CAST(x) ((void (*)(void *, u8*, const u8*))(x))
 
-int xts_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-	      struct scatterlist *src, unsigned int nbytes,
-	      struct xts_crypt_req *req);
-
 static inline int xts_check_key(struct crypto_tfm *tfm,
 				const u8 *key, unsigned int keylen)
 {
diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h
index 451aaa0786ae..4b13e0a3e15b 100644
--- a/include/linux/byteorder/generic.h
+++ b/include/linux/byteorder/generic.h
@@ -156,6 +156,23 @@ static inline void le64_add_cpu(__le64 *var, u64 val)
 	*var = cpu_to_le64(le64_to_cpu(*var) + val);
 }
 
+/* XXX: this stuff can be optimized */
+static inline void le32_to_cpu_array(u32 *buf, unsigned int words)
+{
+	while (words--) {
+		__le32_to_cpus(buf);
+		buf++;
+	}
+}
+
+static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
+{
+	while (words--) {
+		__cpu_to_le32s(buf);
+		buf++;
+	}
+}
+
 static inline void be16_add_cpu(__be16 *var, u16 val)
 {
 	*var = cpu_to_be16(be16_to_cpu(*var) + val);
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 7e6e84cf6383..6eb06101089f 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -435,6 +435,14 @@ struct compress_alg {
  * @cra_exit: Deinitialize the cryptographic transformation object. This is a
  *	      counterpart to @cra_init, used to remove various changes set in
  *	      @cra_init.
+ * @cra_u.ablkcipher: Union member which contains an asynchronous block cipher
+ *		      definition. See @struct @ablkcipher_alg.
+ * @cra_u.blkcipher: Union member which contains a synchronous block cipher
+ * 		     definition See @struct @blkcipher_alg.
+ * @cra_u.cipher: Union member which contains a single-block symmetric cipher
+ *		  definition. See @struct @cipher_alg.
+ * @cra_u.compress: Union member which contains a (de)compression algorithm.
+ *		    See @struct @compress_alg.
  * @cra_module: Owner of this transformation implementation. Set to THIS_MODULE
  * @cra_list: internally used
  * @cra_users: internally used
author	Linus Torvalds <torvalds@linux-foundation.org>	2018-04-04 17:11:08 -0700
committer	Linus Torvalds <torvalds@linux-foundation.org>	2018-04-04 17:11:08 -0700
commit	9eb31227cbccd3a37da0f42604f1ab5fc556bc53 (patch)
tree	9aa467e620e002bf01cecdd98e3908e0cc3e7221
parent	527cd20771888443b5d8707debe98f62c7a1f596 (diff)
parent	f444ec106407d600f17fa1a4bd14f84577401dec (diff)
download	linux-9eb31227cbccd3a37da0f42604f1ab5fc556bc53.tar.bz2