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

Pull crypto update from Herbert Xu: "API: - Restrict crypto_cipher to internal API users only. Algorithms: - Add x86 aesni acceleration for cts. - Improve x86 aesni acceleration for xts. - Remove x86 acceleration of some uncommon algorithms. - Remove RIPE-MD, Tiger and Salsa20. - Remove tnepres. - Add ARM acceleration for BLAKE2s and BLAKE2b. Drivers: - Add Keem Bay OCS HCU driver. - Add Marvell OcteonTX2 CPT PF driver. - Remove PicoXcell driver. - Remove mediatek driver" * 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (154 commits) hwrng: timeriomem - Use device-managed registration API crypto: hisilicon/qm - fix printing format issue crypto: hisilicon/qm - do not reset hardware when CE happens crypto: hisilicon/qm - update irqflag crypto: hisilicon/qm - fix the value of 'QM_SQC_VFT_BASE_MASK_V2' crypto: hisilicon/qm - fix request missing error crypto: hisilicon/qm - removing driver after reset crypto: octeontx2 - fix -Wpointer-bool-conversion warning crypto: hisilicon/hpre - enable Elliptic curve cryptography crypto: hisilicon - PASID fixed on Kunpeng 930 crypto: hisilicon/qm - fix use of 'dma_map_single' crypto: hisilicon/hpre - tiny fix crypto: hisilicon/hpre - adapt the number of clusters crypto: cpt - remove casting dma_alloc_coherent crypto: keembay-ocs-aes - Fix 'q' assignment during CCM B0 generation crypto: xor - Fix typo of optimization hwrng: optee - Use device-managed registration API crypto: arm64/crc-t10dif - move NEON yield to C code crypto: arm64/aes-ce-mac - simplify NEON yield crypto: arm64/aes-neonbs - remove NEON yield calls ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2021-02-22 04:23:56 +0300
committer: Linus Torvalds <torvalds@linux-foundation.org> 2021-02-22 04:23:56 +0300
commit: 31caf8b2a847214be856f843e251fc2ed2cd1075 (patch)
tree: 245257387cfcae352fae27b1ca824daab55472ba
parent: a2b095e0efa7229a1a88602283ba1a8a32004851 (diff)
parent: 0de9dc80625b0ca1cb9730c5ed1c5a8cab538369 (diff)
download: linux-31caf8b2a847214be856f843e251fc2ed2cd1075.tar.xz
207 files changed, 13961 insertions, 15312 deletions
diff --git a/.mailmap b/.mailmap
index ade90fc9140a..87a8bbdbf749 100644
--- a/.mailmap
+++ b/.mailmap
@@ -174,7 +174,6 @@ Juha Yrjola <at solidboot.com>
 Juha Yrjola <juha.yrjola@nokia.com>
 Juha Yrjola <juha.yrjola@solidboot.com>
 Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com>
-Kamil Konieczny <k.konieczny@samsung.com> <k.konieczny@partner.samsung.com>
 Kay Sievers <kay.sievers@vrfy.org>
 Kees Cook <keescook@chromium.org> <kees.cook@canonical.com>
 Kees Cook <keescook@chromium.org> <keescook@google.com>
diff --git a/Documentation/admin-guide/device-mapper/dm-integrity.rst b/Documentation/admin-guide/device-mapper/dm-integrity.rst
index 2cc5488acbd9..cd198ccf4292 100644
--- a/Documentation/admin-guide/device-mapper/dm-integrity.rst
+++ b/Documentation/admin-guide/device-mapper/dm-integrity.rst
@@ -143,8 +143,8 @@ recalculate
 journal_crypt:algorithm(:key)	(the key is optional)
 	Encrypt the journal using given algorithm to make sure that the
 	attacker can't read the journal. You can use a block cipher here
-	(such as "cbc(aes)") or a stream cipher (for example "chacha20",
-	"salsa20" or "ctr(aes)").
+	(such as "cbc(aes)") or a stream cipher (for example "chacha20"
+	or "ctr(aes)").
 
 	The journal contains history of last writes to the block device,
 	an attacker reading the journal could see the last sector numbers
diff --git a/Documentation/crypto/api-skcipher.rst b/Documentation/crypto/api-skcipher.rst
index 1aaf8985894b..04d6cc5357c8 100644
--- a/Documentation/crypto/api-skcipher.rst
+++ b/Documentation/crypto/api-skcipher.rst
@@ -28,8 +28,8 @@ Symmetric Key Cipher Request Handle
 Single Block Cipher API
 -----------------------
 
-.. kernel-doc:: include/linux/crypto.h
+.. kernel-doc:: include/crypto/internal/cipher.h
    :doc: Single Block Cipher API
 
-.. kernel-doc:: include/linux/crypto.h
+.. kernel-doc:: include/crypto/internal/cipher.h
    :functions: crypto_alloc_cipher crypto_free_cipher crypto_has_cipher crypto_cipher_blocksize crypto_cipher_setkey crypto_cipher_encrypt_one crypto_cipher_decrypt_one
diff --git a/Documentation/devicetree/bindings/crypto/intel,keembay-ocs-hcu.yaml b/Documentation/devicetree/bindings/crypto/intel,keembay-ocs-hcu.yaml
new file mode 100644
index 000000000000..acb92706d280
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/intel,keembay-ocs-hcu.yaml
@@ -0,0 +1,46 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/crypto/intel,keembay-ocs-hcu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Intel Keem Bay OCS HCU Device Tree Bindings
+
+maintainers:
+  - Declan Murphy <declan.murphy@intel.com>
+  - Daniele Alessandrelli <daniele.alessandrelli@intel.com>
+
+description:
+  The Intel Keem Bay Offload and Crypto Subsystem (OCS) Hash Control Unit (HCU)
+  provides hardware-accelerated hashing and HMAC.
+
+properties:
+  compatible:
+    const: intel,keembay-ocs-hcu
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    crypto@3000b000 {
+      compatible = "intel,keembay-ocs-hcu";
+      reg = <0x3000b000 0x1000>;
+      interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
+      clocks = <&scmi_clk 94>;
+    };
diff --git a/Documentation/devicetree/bindings/crypto/samsung-slimsss.yaml b/Documentation/devicetree/bindings/crypto/samsung-slimsss.yaml
index 7743eae049ab..676950bb7b37 100644
--- a/Documentation/devicetree/bindings/crypto/samsung-slimsss.yaml
+++ b/Documentation/devicetree/bindings/crypto/samsung-slimsss.yaml
@@ -8,7 +8,6 @@ title: Samsung Exynos SoC SlimSSS (Slim Security SubSystem) module
 
 maintainers:
   - Krzysztof Kozlowski <krzk@kernel.org>
-  - Kamil Konieczny <k.konieczny@partner.samsung.com>
 
 description: |+
   The SlimSSS module in Exynos5433 SoC supports the following:
diff --git a/Documentation/devicetree/bindings/crypto/samsung-sss.yaml b/Documentation/devicetree/bindings/crypto/samsung-sss.yaml
index cf1c47a81d7f..6d62b0e42fc9 100644
--- a/Documentation/devicetree/bindings/crypto/samsung-sss.yaml
+++ b/Documentation/devicetree/bindings/crypto/samsung-sss.yaml
@@ -8,7 +8,6 @@ title: Samsung Exynos SoC SSS (Security SubSystem) module
 
 maintainers:
   - Krzysztof Kozlowski <krzk@kernel.org>
-  - Kamil Konieczny <k.konieczny@partner.samsung.com>
 
 description: |+
   The SSS module in S5PV210 SoC supports the following:
diff --git a/MAINTAINERS b/MAINTAINERS
index fffcb42ed4d7..3666f3746989 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9032,6 +9032,17 @@ F:	drivers/crypto/keembay/keembay-ocs-aes-core.c
 F:	drivers/crypto/keembay/ocs-aes.c
 F:	drivers/crypto/keembay/ocs-aes.h
 
+INTEL KEEM BAY OCS HCU CRYPTO DRIVER
+M:	Daniele Alessandrelli <daniele.alessandrelli@intel.com>
+M:	Declan Murphy <declan.murphy@intel.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/crypto/intel,keembay-ocs-hcu.yaml
+F:	drivers/crypto/keembay/Kconfig
+F:	drivers/crypto/keembay/Makefile
+F:	drivers/crypto/keembay/keembay-ocs-hcu-core.c
+F:	drivers/crypto/keembay/ocs-hcu.c
+F:	drivers/crypto/keembay/ocs-hcu.h
+
 INTEL MANAGEMENT ENGINE (mei)
 M:	Tomas Winkler <tomas.winkler@intel.com>
 L:	linux-kernel@vger.kernel.org
@@ -15683,7 +15694,6 @@ F:	drivers/media/i2c/s5k5baf.c
 SAMSUNG S5P Security SubSystem (SSS) DRIVER
 M:	Krzysztof Kozlowski <krzk@kernel.org>
 M:	Vladimir Zapolskiy <vz@mleia.com>
-M:	Kamil Konieczny <k.konieczny@samsung.com>
 L:	linux-crypto@vger.kernel.org
 L:	linux-samsung-soc@vger.kernel.org
 S:	Maintained
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index c9bf2df85cb9..2b575792363e 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -62,6 +62,25 @@ config CRYPTO_SHA512_ARM
 	  SHA-512 secure hash standard (DFIPS 180-2) implemented
 	  using optimized ARM assembler and NEON, when available.
 
+config CRYPTO_BLAKE2S_ARM
+	tristate "BLAKE2s digest algorithm (ARM)"
+	select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
+	help
+	  BLAKE2s digest algorithm optimized with ARM scalar instructions.  This
+	  is faster than the generic implementations of BLAKE2s and BLAKE2b, but
+	  slower than the NEON implementation of BLAKE2b.  (There is no NEON
+	  implementation of BLAKE2s, since NEON doesn't really help with it.)
+
+config CRYPTO_BLAKE2B_NEON
+	tristate "BLAKE2b digest algorithm (ARM NEON)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_BLAKE2B
+	help
+	  BLAKE2b digest algorithm optimized with ARM NEON instructions.
+	  On ARM processors that have NEON support but not the ARMv8
+	  Crypto Extensions, typically this BLAKE2b implementation is
+	  much faster than SHA-2 and slightly faster than SHA-1.
+
 config CRYPTO_AES_ARM
 	tristate "Scalar AES cipher for ARM"
 	select CRYPTO_ALGAPI
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index b745c17d356f..8f26c454ea12 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -9,6 +9,8 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
 obj-$(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-$(CONFIG_CRYPTO_BLAKE2S_ARM) += blake2s-arm.o
+obj-$(CONFIG_CRYPTO_BLAKE2B_NEON) += blake2b-neon.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
 obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.o
 obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
@@ -29,6 +31,8 @@ sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
 sha256-arm-y	:= sha256-core.o sha256_glue.o $(sha256-arm-neon-y)
 sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o
 sha512-arm-y	:= sha512-core.o sha512-glue.o $(sha512-arm-neon-y)
+blake2s-arm-y   := blake2s-core.o blake2s-glue.o
+blake2b-neon-y  := blake2b-neon-core.o blake2b-neon-glue.o
 sha1-arm-ce-y	:= sha1-ce-core.o sha1-ce-glue.o
 sha2-arm-ce-y	:= sha2-ce-core.o sha2-ce-glue.o
 aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index f70af1d0514b..5c6cd3c63cbc 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -9,6 +9,7 @@
 #include <asm/simd.h>
 #include <crypto/aes.h>
 #include <crypto/ctr.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
@@ -23,6 +24,8 @@ MODULE_ALIAS_CRYPTO("cbc(aes)-all");
 MODULE_ALIAS_CRYPTO("ctr(aes)");
 MODULE_ALIAS_CRYPTO("xts(aes)");
 
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
+
 asmlinkage void aesbs_convert_key(u8 out[], u32 const rk[], int rounds);
 
 asmlinkage void aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
diff --git a/arch/arm/crypto/blake2b-neon-core.S b/arch/arm/crypto/blake2b-neon-core.S
new file mode 100644
index 000000000000..0406a186377f
--- /dev/null
+++ b/arch/arm/crypto/blake2b-neon-core.S
@@ -0,0 +1,347 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * BLAKE2b digest algorithm, NEON accelerated
+ *
+ * Copyright 2020 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+	.text
+	.fpu		neon
+
+	// The arguments to blake2b_compress_neon()
+	STATE		.req	r0
+	BLOCK		.req	r1
+	NBLOCKS		.req	r2
+	INC		.req	r3
+
+	// Pointers to the rotation tables
+	ROR24_TABLE	.req	r4
+	ROR16_TABLE	.req	r5
+
+	// The original stack pointer
+	ORIG_SP		.req	r6
+
+	// NEON registers which contain the message words of the current block.
+	// M_0-M_3 are occasionally used for other purposes too.
+	M_0		.req	d16
+	M_1		.req	d17
+	M_2		.req	d18
+	M_3		.req	d19
+	M_4		.req	d20
+	M_5		.req	d21
+	M_6		.req	d22
+	M_7		.req	d23
+	M_8		.req	d24
+	M_9		.req	d25
+	M_10		.req	d26
+	M_11		.req	d27
+	M_12		.req	d28
+	M_13		.req	d29
+	M_14		.req	d30
+	M_15		.req	d31
+
+	.align		4
+	// Tables for computing ror64(x, 24) and ror64(x, 16) using the vtbl.8
+	// instruction.  This is the most efficient way to implement these
+	// rotation amounts with NEON.  (On Cortex-A53 it's the same speed as
+	// vshr.u64 + vsli.u64, while on Cortex-A7 it's faster.)
+.Lror24_table:
+	.byte		3, 4, 5, 6, 7, 0, 1, 2
+.Lror16_table:
+	.byte		2, 3, 4, 5, 6, 7, 0, 1
+	// The BLAKE2b initialization vector
+.Lblake2b_IV:
+	.quad		0x6a09e667f3bcc908, 0xbb67ae8584caa73b
+	.quad		0x3c6ef372fe94f82b, 0xa54ff53a5f1d36f1
+	.quad		0x510e527fade682d1, 0x9b05688c2b3e6c1f
+	.quad		0x1f83d9abfb41bd6b, 0x5be0cd19137e2179
+
+// Execute one round of BLAKE2b by updating the state matrix v[0..15] in the
+// NEON registers q0-q7.  The message block is in q8..q15 (M_0-M_15).  The stack
+// pointer points to a 32-byte aligned buffer containing a copy of q8 and q9
+// (M_0-M_3), so that they can be reloaded if they are used as temporary
+// registers.  The macro arguments s0-s15 give the order in which the message
+// words are used in this round.  'final' is 1 if this is the final round.
+.macro	_blake2b_round	s0, s1, s2, s3, s4, s5, s6, s7, \
+			s8, s9, s10, s11, s12, s13, s14, s15, final=0
+
+	// Mix the columns:
+	// (v[0], v[4], v[8], v[12]), (v[1], v[5], v[9], v[13]),
+	// (v[2], v[6], v[10], v[14]), and (v[3], v[7], v[11], v[15]).
+
+	// a += b + m[blake2b_sigma[r][2*i + 0]];
+	vadd.u64	q0, q0, q2
+	vadd.u64	q1, q1, q3
+	vadd.u64	d0, d0, M_\s0
+	vadd.u64	d1, d1, M_\s2
+	vadd.u64	d2, d2, M_\s4
+	vadd.u64	d3, d3, M_\s6
+
+	// d = ror64(d ^ a, 32);
+	veor		q6, q6, q0
+	veor		q7, q7, q1
+	vrev64.32	q6, q6
+	vrev64.32	q7, q7
+
+	// c += d;
+	vadd.u64	q4, q4, q6
+	vadd.u64	q5, q5, q7
+
+	// b = ror64(b ^ c, 24);
+	vld1.8		{M_0}, [ROR24_TABLE, :64]
+	veor		q2, q2, q4
+	veor		q3, q3, q5
+	vtbl.8		d4, {d4}, M_0
+	vtbl.8		d5, {d5}, M_0
+	vtbl.8		d6, {d6}, M_0
+	vtbl.8		d7, {d7}, M_0
+
+	// a += b + m[blake2b_sigma[r][2*i + 1]];
+	//
+	// M_0 got clobbered above, so we have to reload it if any of the four
+	// message words this step needs happens to be M_0.  Otherwise we don't
+	// need to reload it here, as it will just get clobbered again below.
+.if \s1 == 0 || \s3 == 0 || \s5 == 0 || \s7 == 0
+	vld1.8		{M_0}, [sp, :64]
+.endif
+	vadd.u64	q0, q0, q2
+	vadd.u64	q1, q1, q3
+	vadd.u64	d0, d0, M_\s1
+	vadd.u64	d1, d1, M_\s3
+	vadd.u64	d2, d2, M_\s5
+	vadd.u64	d3, d3, M_\s7
+
+	// d = ror64(d ^ a, 16);
+	vld1.8		{M_0}, [ROR16_TABLE, :64]
+	veor		q6, q6, q0
+	veor		q7, q7, q1
+	vtbl.8		d12, {d12}, M_0
+	vtbl.8		d13, {d13}, M_0
+	vtbl.8		d14, {d14}, M_0
+	vtbl.8		d15, {d15}, M_0
+
+	// c += d;
+	vadd.u64	q4, q4, q6
+	vadd.u64	q5, q5, q7
+
+	// b = ror64(b ^ c, 63);
+	//
+	// This rotation amount isn't a multiple of 8, so it has to be
+	// implemented using a pair of shifts, which requires temporary
+	// registers.  Use q8-q9 (M_0-M_3) for this, and reload them afterwards.
+	veor		q8, q2, q4
+	veor		q9, q3, q5
+	vshr.u64	q2, q8, #63
+	vshr.u64	q3, q9, #63
+	vsli.u64	q2, q8, #1
+	vsli.u64	q3, q9, #1
+	vld1.8		{q8-q9}, [sp, :256]
+
+	// Mix the diagonals:
+	// (v[0], v[5], v[10], v[15]), (v[1], v[6], v[11], v[12]),
+	// (v[2], v[7], v[8], v[13]), and (v[3], v[4], v[9], v[14]).
+	//
+	// There are two possible ways to do this: use 'vext' instructions to
+	// shift the rows of the matrix so that the diagonals become columns,
+	// and undo it afterwards; or just use 64-bit operations on 'd'
+	// registers instead of 128-bit operations on 'q' registers.  We use the
+	// latter approach, as it performs much better on Cortex-A7.
+
+	// a += b + m[blake2b_sigma[r][2*i + 0]];
+	vadd.u64	d0, d0, d5
+	vadd.u64	d1, d1, d6
+	vadd.u64	d2, d2, d7
+	vadd.u64	d3, d3, d4
+	vadd.u64	d0, d0, M_\s8
+	vadd.u64	d1, d1, M_\s10
+	vadd.u64	d2, d2, M_\s12
+	vadd.u64	d3, d3, M_\s14
+
+	// d = ror64(d ^ a, 32);
+	veor		d15, d15, d0
+	veor		d12, d12, d1
+	veor		d13, d13, d2
+	veor		d14, d14, d3
+	vrev64.32	d15, d15
+	vrev64.32	d12, d12
+	vrev64.32	d13, d13
+	vrev64.32	d14, d14
+
+	// c += d;
+	vadd.u64	d10, d10, d15
+	vadd.u64	d11, d11, d12
+	vadd.u64	d8, d8, d13
+	vadd.u64	d9, d9, d14
+
+	// b = ror64(b ^ c, 24);
+	vld1.8		{M_0}, [ROR24_TABLE, :64]
+	veor		d5, d5, d10
+	veor		d6, d6, d11
+	veor		d7, d7, d8
+	veor		d4, d4, d9
+	vtbl.8		d5, {d5}, M_0
+	vtbl.8		d6, {d6}, M_0
+	vtbl.8		d7, {d7}, M_0
+	vtbl.8		d4, {d4}, M_0
+
+	// a += b + m[blake2b_sigma[r][2*i + 1]];
+.if \s9 == 0 || \s11 == 0 || \s13 == 0 || \s15 == 0
+	vld1.8		{M_0}, [sp, :64]
+.endif
+	vadd.u64	d0, d0, d5
+	vadd.u64	d1, d1, d6
+	vadd.u64	d2, d2, d7
+	vadd.u64	d3, d3, d4
+	vadd.u64	d0, d0, M_\s9
+	vadd.u64	d1, d1, M_\s11
+	vadd.u64	d2, d2, M_\s13
+	vadd.u64	d3, d3, M_\s15
+
+	// d = ror64(d ^ a, 16);
+	vld1.8		{M_0}, [ROR16_TABLE, :64]
+	veor		d15, d15, d0
+	veor		d12, d12, d1
+	veor		d13, d13, d2
+	veor		d14, d14, d3
+	vtbl.8		d12, {d12}, M_0
+	vtbl.8		d13, {d13}, M_0
+	vtbl.8		d14, {d14}, M_0
+	vtbl.8		d15, {d15}, M_0
+
+	// c += d;
+	vadd.u64	d10, d10, d15
+	vadd.u64	d11, d11, d12
+	vadd.u64	d8, d8, d13
+	vadd.u64	d9, d9, d14
+
+	// b = ror64(b ^ c, 63);
+	veor		d16, d4, d9
+	veor		d17, d5, d10
+	veor		d18, d6, d11
+	veor		d19, d7, d8
+	vshr.u64	q2, q8, #63
+	vshr.u64	q3, q9, #63
+	vsli.u64	q2, q8, #1
+	vsli.u64	q3, q9, #1
+	// Reloading q8-q9 can be skipped on the final round.
+.if ! \final
+	vld1.8		{q8-q9}, [sp, :256]
+.endif
+.endm
+
+//
+// void blake2b_compress_neon(struct blake2b_state *state,
+//			      const u8 *block, size_t nblocks, u32 inc);
+//
+// Only the first three fields of struct blake2b_state are used:
+//	u64 h[8];	(inout)
+//	u64 t[2];	(inout)
+//	u64 f[2];	(in)
+//
+	.align		5
+ENTRY(blake2b_compress_neon)
+	push		{r4-r10}
+
+	// Allocate a 32-byte stack buffer that is 32-byte aligned.
+	mov		ORIG_SP, sp
+	sub		ip, sp, #32
+	bic		ip, ip, #31
+	mov		sp, ip
+
+	adr		ROR24_TABLE, .Lror24_table
+	adr		ROR16_TABLE, .Lror16_table
+
+	mov		ip, STATE
+	vld1.64		{q0-q1}, [ip]!		// Load h[0..3]
+	vld1.64		{q2-q3}, [ip]!		// Load h[4..7]
+.Lnext_block:
+	  adr		r10, .Lblake2b_IV
+	vld1.64		{q14-q15}, [ip]		// Load t[0..1] and f[0..1]
+	vld1.64		{q4-q5}, [r10]!		// Load IV[0..3]
+	  vmov		r7, r8, d28		// Copy t[0] to (r7, r8)
+	vld1.64		{q6-q7}, [r10]		// Load IV[4..7]
+	  adds		r7, r7, INC		// Increment counter
+	bcs		.Lslow_inc_ctr
+	vmov.i32	d28[0], r7
+	vst1.64		{d28}, [ip]		// Update t[0]
+.Linc_ctr_done:
+
+	// Load the next message block and finish initializing the state matrix
+	// 'v'.  Fortunately, there are exactly enough NEON registers to fit the
+	// entire state matrix in q0-q7 and the entire message block in q8-15.
+	//
+	// However, _blake2b_round also needs some extra registers for rotates,
+	// so we have to spill some registers.  It's better to spill the message
+	// registers than the state registers, as the message doesn't change.
+	// Therefore we store a copy of the first 32 bytes of the message block
+	// (q8-q9) in an aligned buffer on the stack so that they can be
+	// reloaded when needed.  (We could just reload directly from the
+	// message buffer, but it's faster to use aligned loads.)
+	vld1.8		{q8-q9}, [BLOCK]!
+	  veor		q6, q6, q14	// v[12..13] = IV[4..5] ^ t[0..1]
+	vld1.8		{q10-q11}, [BLOCK]!
+	  veor		q7, q7, q15	// v[14..15] = IV[6..7] ^ f[0..1]
+	vld1.8		{q12-q13}, [BLOCK]!
+	vst1.8		{q8-q9}, [sp, :256]
+	  mov		ip, STATE
+	vld1.8		{q14-q15}, [BLOCK]!
+
+	// Execute the rounds.  Each round is provided the order in which it
+	// needs to use the message words.
+	_blake2b_round	0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
+	_blake2b_round	14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3
+	_blake2b_round	11, 8, 12, 0, 5, 2, 15, 13, 10, 14, 3, 6, 7, 1, 9, 4
+	_blake2b_round	7, 9, 3, 1, 13, 12, 11, 14, 2, 6, 5, 10, 4, 0, 15, 8
+	_blake2b_round	9, 0, 5, 7, 2, 4, 10, 15, 14, 1, 11, 12, 6, 8, 3, 13
+	_blake2b_round	2, 12, 6, 10, 0, 11, 8, 3, 4, 13, 7, 5, 15, 14, 1, 9
+	_blake2b_round	12, 5, 1, 15, 14, 13, 4, 10, 0, 7, 6, 3, 9, 2, 8, 11
+	_blake2b_round	13, 11, 7, 14, 12, 1, 3, 9, 5, 0, 15, 4, 8, 6, 2, 10
+	_blake2b_round	6, 15, 14, 9, 11, 3, 0, 8, 12, 2, 13, 7, 1, 4, 10, 5
+	_blake2b_round	10, 2, 8, 4, 7, 6, 1, 5, 15, 11, 9, 14, 3, 12, 13, 0
+	_blake2b_round	0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
+	_blake2b_round	14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3 \
+			final=1
+
+	// Fold the final state matrix into the hash chaining value:
+	//
+	//	for (i = 0; i < 8; i++)
+	//		h[i] ^= v[i] ^ v[i + 8];
+	//
+	  vld1.64	{q8-q9}, [ip]!		// Load old h[0..3]
+	veor		q0, q0, q4		// v[0..1] ^= v[8..9]
+	veor		q1, q1, q5		// v[2..3] ^= v[10..11]
+	  vld1.64	{q10-q11}, [ip]		// Load old h[4..7]
+	veor		q2, q2, q6		// v[4..5] ^= v[12..13]
+	veor		q3, q3, q7		// v[6..7] ^= v[14..15]
+	veor		q0, q0, q8		// v[0..1] ^= h[0..1]
+	veor		q1, q1, q9		// v[2..3] ^= h[2..3]
+	  mov		ip, STATE
+	  subs		NBLOCKS, NBLOCKS, #1	// nblocks--
+	  vst1.64	{q0-q1}, [ip]!		// Store new h[0..3]
+	veor		q2, q2, q10		// v[4..5] ^= h[4..5]
+	veor		q3, q3, q11		// v[6..7] ^= h[6..7]
+	  vst1.64	{q2-q3}, [ip]!		// Store new h[4..7]
+
+	// Advance to the next block, if there is one.
+	bne		.Lnext_block		// nblocks != 0?
+
+	mov		sp, ORIG_SP
+	pop		{r4-r10}
+	mov		pc, lr
+
+.Lslow_inc_ctr:
+	// Handle the case where the counter overflowed its low 32 bits, by
+	// carrying the overflow bit into the full 128-bit counter.
+	vmov		r9, r10, d29
+	adcs		r8, r8, #0
+	adcs		r9, r9, #0
+	adc		r10, r10, #0
+	vmov		d28, r7, r8
+	vmov		d29, r9, r10
+	vst1.64		{q14}, [ip]		// Update t[0] and t[1]
+	b		.Linc_ctr_done
+ENDPROC(blake2b_compress_neon)
diff --git a/arch/arm/crypto/blake2b-neon-glue.c b/arch/arm/crypto/blake2b-neon-glue.c
new file mode 100644
index 000000000000..34d73200e7fa
--- /dev/null
+++ b/arch/arm/crypto/blake2b-neon-glue.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * BLAKE2b digest algorithm, NEON accelerated
+ *
+ * Copyright 2020 Google LLC
+ */
+
+#include <crypto/internal/blake2b.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+
+#include <linux/module.h>
+#include <linux/sizes.h>
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void blake2b_compress_neon(struct blake2b_state *state,
+				      const u8 *block, size_t nblocks, u32 inc);
+
+static void blake2b_compress_arch(struct blake2b_state *state,
+				  const u8 *block, size_t nblocks, u32 inc)
+{
+	if (!crypto_simd_usable()) {
+		blake2b_compress_generic(state, block, nblocks, inc);
+		return;
+	}
+
+	do {
+		const size_t blocks = min_t(size_t, nblocks,
+					    SZ_4K / BLAKE2B_BLOCK_SIZE);
+
+		kernel_neon_begin();
+		blake2b_compress_neon(state, block, blocks, inc);
+		kernel_neon_end();
+
+		nblocks -= blocks;
+		block += blocks * BLAKE2B_BLOCK_SIZE;
+	} while (nblocks);
+}
+
+static int crypto_blake2b_update_neon(struct shash_desc *desc,
+				      const u8 *in, unsigned int inlen)
+{
+	return crypto_blake2b_update(desc, in, inlen, blake2b_compress_arch);
+}
+
+static int crypto_blake2b_final_neon(struct shash_desc *desc, u8 *out)
+{
+	return crypto_blake2b_final(desc, out, blake2b_compress_arch);
+}
+
+#define BLAKE2B_ALG(name, driver_name, digest_size)			\
+	{								\
+		.base.cra_name		= name,				\
+		.base.cra_driver_name	= driver_name,			\
+		.base.cra_priority	= 200,				\
+		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,	\
+		.base.cra_blocksize	= BLAKE2B_BLOCK_SIZE,		\
+		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx), \
+		.base.cra_module	= THIS_MODULE,			\
+		.digestsize		= digest_size,			\
+		.setkey			= crypto_blake2b_setkey,	\
+		.init			= crypto_blake2b_init,		\
+		.update			= crypto_blake2b_update_neon,	\
+		.final			= crypto_blake2b_final_neon,	\
+		.descsize		= sizeof(struct blake2b_state),	\
+	}
+
+static struct shash_alg blake2b_neon_algs[] = {
+	BLAKE2B_ALG("blake2b-160", "blake2b-160-neon", BLAKE2B_160_HASH_SIZE),
+	BLAKE2B_ALG("blake2b-256", "blake2b-256-neon", BLAKE2B_256_HASH_SIZE),
+	BLAKE2B_ALG("blake2b-384", "blake2b-384-neon", BLAKE2B_384_HASH_SIZE),
+	BLAKE2B_ALG("blake2b-512", "blake2b-512-neon", BLAKE2B_512_HASH_SIZE),
+};
+
+static int __init blake2b_neon_mod_init(void)
+{
+	if (!(elf_hwcap & HWCAP_NEON))
+		return -ENODEV;
+
+	return crypto_register_shashes(blake2b_neon_algs,
+				       ARRAY_SIZE(blake2b_neon_algs));
+}
+
+static void __exit blake2b_neon_mod_exit(void)
+{
+	return crypto_unregister_shashes(blake2b_neon_algs,
+					 ARRAY_SIZE(blake2b_neon_algs));
+}
+
+module_init(blake2b_neon_mod_init);
+module_exit(blake2b_neon_mod_exit);
+
+MODULE_DESCRIPTION("BLAKE2b digest algorithm, NEON accelerated");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("blake2b-160");
+MODULE_ALIAS_CRYPTO("blake2b-160-neon");
+MODULE_ALIAS_CRYPTO("blake2b-256");
+MODULE_ALIAS_CRYPTO("blake2b-256-neon");
+MODULE_ALIAS_CRYPTO("blake2b-384");
+MODULE_ALIAS_CRYPTO("blake2b-384-neon");
+MODULE_ALIAS_CRYPTO("blake2b-512");
+MODULE_ALIAS_CRYPTO("blake2b-512-neon");
diff --git a/arch/arm/crypto/blake2s-core.S b/arch/arm/crypto/blake2s-core.S
new file mode 100644
index 000000000000..bed897e9a181
--- /dev/null
+++ b/arch/arm/crypto/blake2s-core.S
@@ -0,0 +1,285 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * BLAKE2s digest algorithm, ARM scalar implementation
+ *
+ * Copyright 2020 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+	// Registers used to hold message words temporarily.  There aren't
+	// enough ARM registers to hold the whole message block, so we have to
+	// load the words on-demand.
+	M_0		.req	r12
+	M_1		.req	r14
+
+// The BLAKE2s initialization vector
+.Lblake2s_IV:
+	.word	0x6A09E667, 0xBB67AE85, 0x3C6EF372, 0xA54FF53A
+	.word	0x510E527F, 0x9B05688C, 0x1F83D9AB, 0x5BE0CD19
+
+.macro __ldrd		a, b, src, offset
+#if __LINUX_ARM_ARCH__ >= 6
+	ldrd		\a, \b, [\src, #\offset]
+#else
+	ldr		\a, [\src, #\offset]
+	ldr		\b, [\src, #\offset + 4]
+#endif
+.endm
+
+.macro __strd		a, b, dst, offset
+#if __LINUX_ARM_ARCH__ >= 6
+	strd		\a, \b, [\dst, #\offset]
+#else
+	str		\a, [\dst, #\offset]
+	str		\b, [\dst, #\offset + 4]
+#endif
+.endm
+
+// Execute a quarter-round of BLAKE2s by mixing two columns or two diagonals.
+// (a0, b0, c0, d0) and (a1, b1, c1, d1) give the registers containing the two
+// columns/diagonals.  s0-s1 are the word offsets to the message words the first
+// column/diagonal needs, and likewise s2-s3 for the second column/diagonal.
+// M_0 and M_1 are free to use, and the message block can be found at sp + 32.
+//
+// Note that to save instructions, the rotations don't happen when the
+// pseudocode says they should, but rather they are delayed until the values are
+// used.  See the comment above _blake2s_round().
+.macro _blake2s_quarterround  a0, b0, c0, d0,  a1, b1, c1, d1,  s0, s1, s2, s3
+
+	ldr		M_0, [sp, #32 + 4 * \s0]
+	ldr		M_1, [sp, #32 + 4 * \s2]
+
+	// a += b + m[blake2s_sigma[r][2*i + 0]];
+	add		\a0, \a0, \b0, ror #brot
+	add		\a1, \a1, \b1, ror #brot
+	add		\a0, \a0, M_0
+	add		\a1, \a1, M_1
+
+	// d = ror32(d ^ a, 16);
+	eor		\d0, \a0, \d0, ror #drot
+	eor		\d1, \a1, \d1, ror #drot
+
+	// c += d;
+	add		\c0, \c0, \d0, ror #16
+	add		\c1, \c1, \d1, ror #16
+
+	// b = ror32(b ^ c, 12);
+	eor		\b0, \c0, \b0, ror #brot
+	eor		\b1, \c1, \b1, ror #brot
+
+	ldr		M_0, [sp, #32 + 4 * \s1]
+	ldr		M_1, [sp, #32 + 4 * \s3]
+
+	// a += b + m[blake2s_sigma[r][2*i + 1]];
+	add		\a0, \a0, \b0, ror #12
+	add		\a1, \a1, \b1, ror #12
+	add		\a0, \a0, M_0
+	add		\a1, \a1, M_1
+
+	// d = ror32(d ^ a, 8);
+	eor		\d0, \a0, \d0, ror#16
+	eor		\d1, \a1, \d1, ror#16
+
+	// c += d;
+	add		\c0, \c0, \d0, ror#8
+	add		\c1, \c1, \d1, ror#8
+
+	// b = ror32(b ^ c, 7);
+	eor		\b0, \c0, \b0, ror#12
+	eor		\b1, \c1, \b1, ror#12
+.endm
+
+// Execute one round of BLAKE2s by updating the state matrix v[0..15].  v[0..9]
+// are in r0..r9.  The stack pointer points to 8 bytes of scratch space for
+// spilling v[8..9], then to v[9..15], then to the message block.  r10-r12 and
+// r14 are free to use.  The macro arguments s0-s15 give the order in which the
+// message words are used in this round.
+//
+// All rotates are performed using the implicit rotate operand accepted by the
+// 'add' and 'eor' instructions.  This is faster than using explicit rotate
+// instructions.  To make this work, we allow the values in the second and last
+// rows of the BLAKE2s state matrix (rows 'b' and 'd') to temporarily have the
+// wrong rotation amount.  The rotation amount is then fixed up just in time
+// when the values are used.  'brot' is the number of bits the values in row 'b'
+// need to be rotated right to arrive at the correct values, and 'drot'
+// similarly for row 'd'.  (brot, drot) start out as (0, 0) but we make it such
+// that they end up as (7, 8) after every round.
+.macro	_blake2s_round	s0, s1, s2, s3, s4, s5, s6, s7, \
+			s8, s9, s10, s11, s12, s13, s14, s15
+
+	// Mix first two columns:
+	// (v[0], v[4], v[8], v[12]) and (v[1], v[5], v[9], v[13]).
+	__ldrd		r10, r11, sp, 16	// load v[12] and v[13]
+	_blake2s_quarterround	r0, r4, r8, r10,  r1, r5, r9, r11, \
+				\s0, \s1, \s2, \s3
+	__strd		r8, r9, sp, 0
+	__strd		r10, r11, sp, 16
+
+	// Mix second two columns:
+	// (v[2], v[6], v[10], v[14]) and (v[3], v[7], v[11], v[15]).
+	__ldrd		r8, r9, sp, 8		// load v[10] and v[11]
+	__ldrd		r10, r11, sp, 24	// load v[14] and v[15]
+	_blake2s_quarterround	r2, r6, r8, r10,  r3, r7, r9, r11, \
+				\s4, \s5, \s6, \s7
+	str		r10, [sp, #24]		// store v[14]
+	// v[10], v[11], and v[15] are used below, so no need to store them yet.
+
+	.set brot, 7
+	.set drot, 8
+
+	// Mix first two diagonals:
+	// (v[0], v[5], v[10], v[15]) and (v[1], v[6], v[11], v[12]).
+	ldr		r10, [sp, #16]		// load v[12]
+	_blake2s_quarterround	r0, r5, r8, r11,  r1, r6, r9, r10, \
+				\s8, \s9, \s10, \s11
+	__strd		r8, r9, sp, 8
+	str		r11, [sp, #28]
+	str		r10, [sp, #16]
+
+	// Mix second two diagonals:
+	// (v[2], v[7], v[8], v[13]) and (v[3], v[4], v[9], v[14]).
+	__ldrd		r8, r9, sp, 0		// load v[8] and v[9]
+	__ldrd		r10, r11, sp, 20	// load v[13] and v[14]
+	_blake2s_quarterround	r2, r7, r8, r10,  r3, r4, r9, r11, \
+				\s12, \s13, \s14, \s15
+	__strd		r10, r11, sp, 20
+.endm
+
+//
+// void blake2s_compress_arch(struct blake2s_state *state,
+//			      const u8 *block, size_t nblocks, u32 inc);
+//
+// Only the first three fields of struct blake2s_state are used:
+//	u32 h[8];	(inout)
+//	u32 t[2];	(inout)
+//	u32 f[2];	(in)
+//
+	.align		5
+ENTRY(blake2s_compress_arch)
+	push		{r0-r2,r4-r11,lr}	// keep this an even number
+
+.Lnext_block:
+	// r0 is 'state'
+	// r1 is 'block'
+	// r3 is 'inc'
+
+	// Load and increment the counter t[0..1].
+	__ldrd		r10, r11, r0, 32
+	adds		r10, r10, r3
+	adc		r11, r11, #0
+	__strd		r10, r11, r0, 32
+
+	// _blake2s_round is very short on registers, so copy the message block
+	// to the stack to save a register during the rounds.  This also has the
+	// advantage that misalignment only needs to be dealt with in one place.
+	sub		sp, sp, #64
+	mov		r12, sp
+	tst		r1, #3
+	bne		.Lcopy_block_misaligned
+	ldmia		r1!, {r2-r9}
+	stmia		r12!, {r2-r9}
+	ldmia		r1!, {r2-r9}
+	stmia		r12, {r2-r9}
+.Lcopy_block_done:
+	str		r1, [sp, #68]		// Update message pointer
+
+	// Calculate v[8..15].  Push v[9..15] onto the stack, and leave space
+	// for spilling v[8..9].  Leave v[8..9] in r8-r9.
+	mov		r14, r0			// r14 = state
+	adr		r12, .Lblake2s_IV
+	ldmia		r12!, {r8-r9}		// load IV[0..1]
+	__ldrd		r0, r1, r14, 40		// load f[0..1]
+	ldm		r12, {r2-r7}		// load IV[3..7]
+	eor		r4, r4, r10		// v[12] = IV[4] ^ t[0]
+	eor		r5, r5, r11		// v[13] = IV[5] ^ t[1]
+	eor		r6, r6, r0		// v[14] = IV[6] ^ f[0]
+	eor		r7, r7, r1		// v[15] = IV[7] ^ f[1]
+	push		{r2-r7}			// push v[9..15]
+	sub		sp, sp, #8		// leave space for v[8..9]
+
+	// Load h[0..7] == v[0..7].
+	ldm		r14, {r0-r7}
+
+	// Execute the rounds.  Each round is provided the order in which it
+	// needs to use the message words.
+	.set brot, 0
+	.set drot, 0
+	_blake2s_round	0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
+	_blake2s_round	14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3
+	_blake2s_round	11, 8, 12, 0, 5, 2, 15, 13, 10, 14, 3, 6, 7, 1, 9, 4
+	_blake2s_round	7, 9, 3, 1, 13, 12, 11, 14, 2, 6, 5, 10, 4, 0, 15, 8
+	_blake2s_round	9, 0, 5, 7, 2, 4, 10, 15, 14, 1, 11, 12, 6, 8, 3, 13
+	_blake2s_round	2, 12, 6, 10, 0, 11, 8, 3, 4, 13, 7, 5, 15, 14, 1, 9
+	_blake2s_round	12, 5, 1, 15, 14, 13, 4, 10, 0, 7, 6, 3, 9, 2, 8, 11
+	_blake2s_round	13, 11, 7, 14, 12, 1, 3, 9, 5, 0, 15, 4, 8, 6, 2, 10
+	_blake2s_round	6, 15, 14, 9, 11, 3, 0, 8, 12, 2, 13, 7, 1, 4, 10, 5
+	_blake2s_round	10, 2, 8, 4, 7, 6, 1, 5, 15, 11, 9, 14, 3, 12, 13, 0
+
+	// Fold the final state matrix into the hash chaining value:
+	//
+	//	for (i = 0; i < 8; i++)
+	//		h[i] ^= v[i] ^ v[i + 8];
+	//
+	ldr		r14, [sp, #96]		// r14 = &h[0]
+	add		sp, sp, #8		// v[8..9] are already loaded.
+	pop		{r10-r11}		// load v[10..11]
+	eor		r0, r0, r8
+	eor		r1, r1, r9
+	eor		r2, r2, r10
+	eor		r3, r3, r11
+	ldm		r14, {r8-r11}		// load h[0..3]
+	eor		r0, r0, r8
+	eor		r1, r1, r9
+	eor		r2, r2, r10
+	eor		r3, r3, r11
+	stmia		r14!, {r0-r3}		// store new h[0..3]
+	ldm		r14, {r0-r3}		// load old h[4..7]
+	pop		{r8-r11}		// load v[12..15]
+	eor		r0, r0, r4, ror #brot
+	eor		r1, r1, r5, ror #brot
+	eor		r2, r2, r6, ror #brot
+	eor		r3, r3, r7, ror #brot
+	eor		r0, r0, r8, ror #drot
+	eor		r1, r1, r9, ror #drot
+	eor		r2, r2, r10, ror #drot
+	eor		r3, r3, r11, ror #drot
+	  add		sp, sp, #64		// skip copy of message block
+	stm		r14, {r0-r3}		// store new h[4..7]
+
+	// Advance to the next block, if there is one.  Note that if there are
+	// multiple blocks, then 'inc' (the counter increment amount) must be
+	// 64.  So we can simply set it to 64 without re-loading it.
+	ldm		sp, {r0, r1, r2}	// load (state, block, nblocks)
+	mov		r3, #64			// set 'inc'
+	subs		r2, r2, #1		// nblocks--
+	str		r2, [sp, #8]
+	bne		.Lnext_block		// nblocks != 0?
+
+	pop		{r0-r2,r4-r11,pc}
+
+	// The next message block (pointed to by r1) isn't 4-byte aligned, so it
+	// can't be loaded using ldmia.  Copy it to the stack buffer (pointed to
+	// by r12) using an alternative method.  r2-r9 are free to use.
+.Lcopy_block_misaligned:
+	mov		r2, #64
+1:
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	ldr		r3, [r1], #4
+#else
+	ldrb		r3, [r1, #0]
+	ldrb		r4, [r1, #1]
+	ldrb		r5, [r1, #2]
+	ldrb		r6, [r1, #3]
+	add		r1, r1, #4
+	orr		r3, r3, r4, lsl #8
+	orr		r3, r3, r5, lsl #16
+	orr		r3, r3, r6, lsl #24
+#endif
+	subs		r2, r2, #4
+	str		r3, [r12], #4
+	bne		1b
+	b		.Lcopy_block_done
+ENDPROC(blake2s_compress_arch)
diff --git a/arch/arm/crypto/blake2s-glue.c b/arch/arm/crypto/blake2s-glue.c
new file mode 100644
index 000000000000..f2cc1e5fc9ec
--- /dev/null
+++ b/arch/arm/crypto/blake2s-glue.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * BLAKE2s digest algorithm, ARM scalar implementation
+ *
+ * Copyright 2020 Google LLC
+ */
+
+#include <crypto/internal/blake2s.h>
+#include <crypto/internal/hash.h>
+
+#include <linux/module.h>
+
+/* defined in blake2s-core.S */
+EXPORT_SYMBOL(blake2s_compress_arch);
+
+static int crypto_blake2s_update_arm(struct shash_desc *desc,
+				     const u8 *in, unsigned int inlen)
+{
+	return crypto_blake2s_update(desc, in, inlen, blake2s_compress_arch);
+}
+
+static int crypto_blake2s_final_arm(struct shash_desc *desc, u8 *out)
+{
+	return crypto_blake2s_final(desc, out, blake2s_compress_arch);
+}
+
+#define BLAKE2S_ALG(name, driver_name, digest_size)			\
+	{								\
+		.base.cra_name		= name,				\
+		.base.cra_driver_name	= driver_name,			\
+		.base.cra_priority	= 200,				\
+		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,	\
+		.base.cra_blocksize	= BLAKE2S_BLOCK_SIZE,		\
+		.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx), \
+		.base.cra_module	= THIS_MODULE,			\
+		.digestsize		= digest_size,			\
+		.setkey			= crypto_blake2s_setkey,	\
+		.init			= crypto_blake2s_init,		\
+		.update			= crypto_blake2s_update_arm,	\
+		.final			= crypto_blake2s_final_arm,	\
+		.descsize		= sizeof(struct blake2s_state),	\
+	}
+
+static struct shash_alg blake2s_arm_algs[] = {
+	BLAKE2S_ALG("blake2s-128", "blake2s-128-arm", BLAKE2S_128_HASH_SIZE),
+	BLAKE2S_ALG("blake2s-160", "blake2s-160-arm", BLAKE2S_160_HASH_SIZE),
+	BLAKE2S_ALG("blake2s-224", "blake2s-224-arm", BLAKE2S_224_HASH_SIZE),
+	BLAKE2S_ALG("blake2s-256", "blake2s-256-arm", BLAKE2S_256_HASH_SIZE),
+};
+
+static int __init blake2s_arm_mod_init(void)
+{
+	return IS_REACHABLE(CONFIG_CRYPTO_HASH) ?
+		crypto_register_shashes(blake2s_arm_algs,
+					ARRAY_SIZE(blake2s_arm_algs)) : 0;
+}
+
+static void __exit blake2s_arm_mod_exit(void)
+{
+	if (IS_REACHABLE(CONFIG_CRYPTO_HASH))
+		crypto_unregister_shashes(blake2s_arm_algs,
+					  ARRAY_SIZE(blake2s_arm_algs));
+}
+
+module_init(blake2s_arm_mod_init);
+module_exit(blake2s_arm_mod_exit);
+
+MODULE_DESCRIPTION("BLAKE2s digest algorithm, ARM scalar implementation");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("blake2s-128");
+MODULE_ALIAS_CRYPTO("blake2s-128-arm");
+MODULE_ALIAS_CRYPTO("blake2s-160");
+MODULE_ALIAS_CRYPTO("blake2s-160-arm");
+MODULE_ALIAS_CRYPTO("blake2s-224");
+MODULE_ALIAS_CRYPTO("blake2s-224-arm");
+MODULE_ALIAS_CRYPTO("blake2s-256");
+MODULE_ALIAS_CRYPTO("blake2s-256-arm");
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 34b8a89197be..17e735931a0c 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -24,6 +24,7 @@
 #ifdef USE_V8_CRYPTO_EXTENSIONS
 #define MODE			"ce"
 #define PRIO			300
+#define STRIDE			5
 #define aes_expandkey		ce_aes_expandkey
 #define aes_ecb_encrypt		ce_aes_ecb_encrypt
 #define aes_ecb_decrypt		ce_aes_ecb_decrypt
@@ -41,6 +42,7 @@ MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
 #else
 #define MODE			"neon"
 #define PRIO			200
+#define STRIDE			4
 #define aes_ecb_encrypt		neon_aes_ecb_encrypt
 #define aes_ecb_decrypt		neon_aes_ecb_decrypt
 #define aes_cbc_encrypt		neon_aes_cbc_encrypt
@@ -55,7 +57,7 @@ MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
 #define aes_mac_update		neon_aes_mac_update
 MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON");
 #endif
-#if defined(USE_V8_CRYPTO_EXTENSIONS) || !defined(CONFIG_CRYPTO_AES_ARM64_BS)
+#if defined(USE_V8_CRYPTO_EXTENSIONS) || !IS_ENABLED(CONFIG_CRYPTO_AES_ARM64_BS)
 MODULE_ALIAS_CRYPTO("ecb(aes)");
 MODULE_ALIAS_CRYPTO("cbc(aes)");
 MODULE_ALIAS_CRYPTO("ctr(aes)");
@@ -87,7 +89,7 @@ asmlinkage void aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
 				int rounds, int bytes, u8 const iv[]);
 
 asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[],
-				int rounds, int blocks, u8 ctr[]);
+				int rounds, int bytes, u8 ctr[], u8 finalbuf[]);
 
 asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u32 const rk1[],
 				int rounds, int bytes, u32 const rk2[], u8 iv[],
@@ -103,9 +105,9 @@ asmlinkage void aes_essiv_cbc_decrypt(u8 out[], u8 const in[], u32 const rk1[],
 				      int rounds, int blocks, u8 iv[],
 				      u32 const rk2[]);
 
-asmlinkage void aes_mac_update(u8 const in[], u32 const rk[], int rounds,
-			       int blocks, u8 dg[], int enc_before,
-			       int enc_after);
+asmlinkage int aes_mac_update(u8 const in[], u32 const rk[], int rounds,
+			      int blocks, u8 dg[], int enc_before,
+			      int enc_after);
 
 struct crypto_aes_xts_ctx {
 	struct crypto_aes_ctx key1;
@@ -448,34 +450,36 @@ static int ctr_encrypt(struct skcipher_request *req)
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
-	int blocks;
 
 	err = skcipher_walk_virt(&walk, req, false);
 
-	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
-		kernel_neon_begin();
-		aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				ctx->key_enc, rounds, blocks, walk.iv);
-		kernel_neon_end();
-		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
-	}
-	if (walk.nbytes) {
-		u8 __aligned(8) tail[AES_BLOCK_SIZE];
+	while (walk.nbytes > 0) {
+		const u8 *src = walk.src.virt.addr;
 		unsigned int nbytes = walk.nbytes;
-		u8 *tdst = walk.dst.virt.addr;
-		u8 *tsrc = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+		u8 buf[AES_BLOCK_SIZE];
+		unsigned int tail;
 
-		/*
-		 * Tell aes_ctr_encrypt() to process a tail block.
-		 */
-		blocks = -1;
+		if (unlikely(nbytes < AES_BLOCK_SIZE))
+			src = memcpy(buf, src, nbytes);
+		else if (nbytes < walk.total)
+			nbytes &= ~(AES_BLOCK_SIZE - 1);
 
 		kernel_neon_begin();
-		aes_ctr_encrypt(tail, NULL, ctx->key_enc, rounds,
-				blocks, walk.iv);
+		aes_ctr_encrypt(dst, src, ctx->key_enc, rounds, nbytes,
+				walk.iv, buf);
 		kernel_neon_end();
-		crypto_xor_cpy(tdst, tsrc, tail, nbytes);
-		err = skcipher_walk_done(&walk, 0);
+
+		tail = nbytes % (STRIDE * AES_BLOCK_SIZE);
+		if (tail > 0 && tail < AES_BLOCK_SIZE)
+			/*
+			 * The final partial block could not be returned using
+			 * an overlapping store, so it was passed via buf[]
+			 * instead.
+			 */
+			memcpy(dst + nbytes - tail, buf, tail);
+
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
@@ -650,7 +654,7 @@ static int __maybe_unused xts_decrypt(struct skcipher_request *req)
 }
 
 static struct skcipher_alg aes_algs[] = { {
-#if defined(USE_V8_CRYPTO_EXTENSIONS) || !defined(CONFIG_CRYPTO_AES_ARM64_BS)
+#if defined(USE_V8_CRYPTO_EXTENSIONS) || !IS_ENABLED(CONFIG_CRYPTO_AES_ARM64_BS)
 	.base = {
 		.cra_name		= "__ecb(aes)",
 		.cra_driver_name	= "__ecb-aes-" MODE,
@@ -852,10 +856,17 @@ static void mac_do_update(struct crypto_aes_ctx *ctx, u8 const in[], int blocks,
 	int rounds = 6 + ctx->key_length / 4;
 
 	if (crypto_simd_usable()) {
-		kernel_neon_begin();
-		aes_mac_update(in, ctx->key_enc, rounds, blocks, dg, enc_before,
-			       enc_after);
-		kernel_neon_end();
+		int rem;
+
+		do {
+			kernel_neon_begin();
+			rem = aes_mac_update(in, ctx->key_enc, rounds, blocks,
+					     dg, enc_before, enc_after);
+			kernel_neon_end();
+			in += (blocks - rem) * AES_BLOCK_SIZE;
+			blocks = rem;
+			enc_before = 0;
+		} while (blocks);
 	} else {
 		if (enc_before)
 			aes_encrypt(ctx, dg, dg);
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index cf618d8f6cec..bbdb54702aa7 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -321,42 +321,76 @@ AES_FUNC_END(aes_cbc_cts_decrypt)
 
 	/*
 	 * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
-	 *		   int blocks, u8 ctr[])
+	 *		   int bytes, u8 ctr[], u8 finalbuf[])
 	 */
 
 AES_FUNC_START(aes_ctr_encrypt)
 	stp		x29, x30, [sp, #-16]!
 	mov		x29, sp
 
-	enc_prepare	w3, x2, x6
+	enc_prepare	w3, x2, x12
 	ld1		{vctr.16b}, [x5]
 
-	umov		x6, vctr.d[1]		/* keep swabbed ctr in reg */
-	rev		x6, x6
-	cmn		w6, w4			/* 32 bit overflow? */
-	bcs		.Lctrloop
+	umov		x12, vctr.d[1]		/* keep swabbed ctr in reg */
+	rev		x12, x12
+
 .LctrloopNx:
-	subs		w4, w4, #MAX_STRIDE
-	bmi		.Lctr1x
-	add		w7, w6, #1
+	add		w7, w4, #15
+	sub		w4, w4, #MAX_STRIDE << 4
+	lsr		w7, w7, #4
+	mov		w8, #MAX_STRIDE
+	cmp		w7, w8
+	csel		w7, w7, w8, lt
+	adds		x12, x12, x7
+
 	mov		v0.16b, vctr.16b
-	add		w8, w6, #2
 	mov		v1.16b, vctr.16b
-	add		w9, w6, #3
 	mov		v2.16b, vctr.16b
-	add		w9, w6, #3
-	rev		w7, w7
 	mov		v3.16b, vctr.16b
-	rev		w8, w8
 ST5(	mov		v4.16b, vctr.16b		)
-	mov		v1.s[3], w7
-	rev		w9, w9
-ST5(	add		w10, w6, #4			)
-	mov		v2.s[3], w8
-ST5(	rev		w10, w10			)
-	mov		v3.s[3], w9
-ST5(	mov		v4.s[3], w10			)
-	ld1		{v5.16b-v7.16b}, [x1], #48	/* get 3 input blocks */
+	bcs		0f
+
+	.subsection	1
+	/* apply carry to outgoing counter */
+0:	umov		x8, vctr.d[0]
+	rev		x8, x8
+	add		x8, x8, #1
+	rev		x8, x8
+	ins		vctr.d[0], x8
+
+	/* apply carry to N counter blocks for N := x12 */
+	adr		x16, 1f
+	sub		x16, x16, x12, lsl #3
+	br		x16
+	hint		34			// bti c
+	mov		v0.d[0], vctr.d[0]
+	hint		34			// bti c
+	mov		v1.d[0], vctr.d[0]
+	hint		34			// bti c
+	mov		v2.d[0], vctr.d[0]
+	hint		34			// bti c
+	mov		v3.d[0], vctr.d[0]
+ST5(	hint		34				)
+ST5(	mov		v4.d[0], vctr.d[0]		)
+1:	b		2f
+	.previous
+
+2:	rev		x7, x12
+	ins		vctr.d[1], x7
+	sub		x7, x12, #MAX_STRIDE - 1
+	sub		x8, x12, #MAX_STRIDE - 2
+	sub		x9, x12, #MAX_STRIDE - 3
+	rev		x7, x7
+	rev		x8, x8
+	mov		v1.d[1], x7
+	rev		x9, x9
+ST5(	sub		x10, x12, #MAX_STRIDE - 4	)
+	mov		v2.d[1], x8
+ST5(	rev		x10, x10			)
+	mov		v3.d[1], x9
+ST5(	mov		v4.d[1], x10			)
+	tbnz		w4, #31, .Lctrtail
+	ld1		{v5.16b-v7.16b}, [x1], #48
 ST4(	bl		aes_encrypt_block4x		)
 ST5(	bl		aes_encrypt_block5x		)
 	eor		v0.16b, v5.16b, v0.16b
@@ -368,47 +402,72 @@ ST5(	ld1		{v5.16b-v6.16b}, [x1], #32	)
 ST5(	eor		v4.16b, v6.16b, v4.16b		)
 	st1		{v0.16b-v3.16b}, [x0], #64
 ST5(	st1		{v4.16b}, [x0], #16		)
-	add		x6, x6, #MAX_STRIDE
-	rev		x7, x6
-	ins		vctr.d[1], x7
 	cbz		w4, .Lctrout
 	b		.LctrloopNx
-.Lctr1x:
-	adds		w4, w4, #MAX_STRIDE
-	beq		.Lctrout
-.Lctrloop:
-	mov		v0.16b, vctr.16b
-	encrypt_block	v0, w3, x2, x8, w7
-
-	adds		x6, x6, #1		/* increment BE ctr */
-	rev		x7, x6
-	ins		vctr.d[1], x7
-	bcs		.Lctrcarry		/* overflow? */
-
-.Lctrcarrydone:
-	subs		w4, w4, #1
-	bmi		.Lctrtailblock		/* blocks <0 means tail block */
-	ld1		{v3.16b}, [x1], #16
-	eor		v3.16b, v0.16b, v3.16b
-	st1		{v3.16b}, [x0], #16
-	bne		.Lctrloop
 
 .Lctrout:
 	st1		{vctr.16b}, [x5]	/* return next CTR value */
 	ldp		x29, x30, [sp], #16
 	ret
 
-.Lctrtailblock:
-	st1		{v0.16b}, [x0]
+.Lctrtail:
+	/* XOR up to MAX_STRIDE * 16 - 1 bytes of in/output with v0 ... v3/v4 */
+	mov		x16, #16
+	ands		x13, x4, #0xf
+	csel		x13, x13, x16, ne
+
+ST5(	cmp		w4, #64 - (MAX_STRIDE << 4)	)
+ST5(	csel		x14, x16, xzr, gt		)
+	cmp		w4, #48 - (MAX_STRIDE << 4)
+	csel		x15, x16, xzr, gt
+	cmp		w4, #32 - (MAX_STRIDE << 4)
+	csel		x16, x16, xzr, gt
+	cmp		w4, #16 - (MAX_STRIDE << 4)
+	ble		.Lctrtail1x
+
+	adr_l		x12, .Lcts_permute_table
+	add		x12, x12, x13
+
+ST5(	ld1		{v5.16b}, [x1], x14		)
+	ld1		{v6.16b}, [x1], x15
+	ld1		{v7.16b}, [x1], x16
+
+ST4(	bl		aes_encrypt_block4x		)
+ST5(	bl		aes_encrypt_block5x		)
+
+	ld1		{v8.16b}, [x1], x13
+	ld1		{v9.16b}, [x1]
+	ld1		{v10.16b}, [x12]
+
+ST4(	eor		v6.16b, v6.16b, v0.16b		)
+ST4(	eor		v7.16b, v7.16b, v1.16b		)
+ST4(	tbl		v3.16b, {v3.16b}, v10.16b	)
+ST4(	eor		v8.16b, v8.16b, v2.16b		)
+ST4(	eor		v9.16b, v9.16b, v3.16b		)
+
+ST5(	eor		v5.16b, v5.16b, v0.16b		)
+ST5(	eor		v6.16b, v6.16b, v1.16b		)
+ST5(	tbl		v4.16b, {v4.16b}, v10.16b	)
+ST5(	eor		v7.16b, v7.16b, v2.16b		)
+ST5(	eor		v8.16b, v8.16b, v3.16b		)
+ST5(	eor		v9.16b, v9.16b, v4.16b		)
+
+ST5(	st1		{v5.16b}, [x0], x14		)
+	st1		{v6.16b}, [x0], x15
+	st1		{v7.16b}, [x0], x16
+	add		x13, x13, x0
+	st1		{v9.16b}, [x13]		// overlapping stores
+	st1		{v8.16b}, [x0]
 	b		.Lctrout
 
-.Lctrcarry:
-	umov		x7, vctr.d[0]		/* load upper word of ctr  */
-	rev		x7, x7			/* ... to handle the carry */
-	add		x7, x7, #1
-	rev		x7, x7
-	ins		vctr.d[0], x7
-	b		.Lctrcarrydone
+.Lctrtail1x:
+	csel		x0, x0, x6, eq		// use finalbuf if less than a full block
+	ld1		{v5.16b}, [x1]
+ST5(	mov		v3.16b, v4.16b			)
+	encrypt_block	v3, w3, x2, x8, w7
+	eor		v5.16b, v5.16b, v3.16b
+	st1		{v5.16b}, [x0]
+	b		.Lctrout
 AES_FUNC_END(aes_ctr_encrypt)
 
 
@@ -619,61 +678,47 @@ AES_FUNC_END(aes_xts_decrypt)
 	 *		  int blocks, u8 dg[], int enc_before, int enc_after)
 	 */
 AES_FUNC_START(aes_mac_update)
-	frame_push	6
-
-	mov		x19, x0
-	mov		x20, x1
-	mov		x21, x2
-	mov		x22, x3
-	mov		x23, x4
-	mov		x24, x6
-
-	ld1		{v0.16b}, [x23]			/* get dg */
+	ld1		{v0.16b}, [x4]			/* get dg */
 	enc_prepare	w2, x1, x7
 	cbz		w5, .Lmacloop4x
 
 	encrypt_block	v0, w2, x1, x7, w8
 
 .Lmacloop4x:
-	subs		w22, w22, #4
+	subs		w3, w3, #4
 	bmi		.Lmac1x
-	ld1		{v1.16b-v4.16b}, [x19], #64	/* get next pt block */
+	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, w21, x20, x7, w8
+	encrypt_block	v0, w2, x1, x7, w8
 	eor		v0.16b, v0.16b, v2.16b
-	encrypt_block	v0, w21, x20, x7, w8
+	encrypt_block	v0, w2, x1, x7, w8
 	eor		v0.16b, v0.16b, v3.16b
-	encrypt_block	v0, w21, x20, x7, w8
+	encrypt_block	v0, w2, x1, x7, w8
 	eor		v0.16b, v0.16b, v4.16b
-	cmp		w22, wzr
-	csinv		x5, x24, xzr, eq
+	cmp		w3, wzr
+	csinv		x5, x6, xzr, eq
 	cbz		w5, .Lmacout
-	encrypt_block	v0, w21, x20, x7, w8
-	st1		{v0.16b}, [x23]			/* return dg */
-	cond_yield_neon	.Lmacrestart
+	encrypt_block	v0, w2, x1, x7, w8
+	st1		{v0.16b}, [x4]			/* return dg */
+	cond_yield	.Lmacout, x7
 	b		.Lmacloop4x
 .Lmac1x:
-	add		w22, w22, #4
+	add		w3, w3, #4
 .Lmacloop:
-	cbz		w22, .Lmacout
-	ld1		{v1.16b}, [x19], #16		/* get next pt block */
+	cbz		w3, .Lmacout
+	ld1		{v1.16b}, [x0], #16		/* get next pt block */
 	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with dg */
 
-	subs		w22, w22, #1
-	csinv		x5, x24, xzr, eq
+	subs		w3, w3, #1
+	csinv		x5, x6, xzr, eq
 	cbz		w5, .Lmacout
 
 .Lmacenc:
-	encrypt_block	v0, w21, x20, x7, w8
+	encrypt_block	v0, w2, x1, x7, w8
 	b		.Lmacloop
 
 .Lmacout:
-	st1		{v0.16b}, [x23]			/* return dg */
-	frame_pop
+	st1		{v0.16b}, [x4]			/* return dg */
+	mov		w0, w3
 	ret
-
-.Lmacrestart:
-	ld1		{v0.16b}, [x23]			/* get dg */
-	enc_prepare	w21, x20, x0
-	b		.Lmacloop4x
 AES_FUNC_END(aes_mac_update)
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index 63a52ad9a75c..a3405b8c344b 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -613,7 +613,6 @@ SYM_FUNC_END(aesbs_decrypt8)
 	st1		{\o7\().16b}, [x19], #16
 
 	cbz		x23, 1f
-	cond_yield_neon
 	b		99b
 
 1:	frame_pop
@@ -715,7 +714,6 @@ SYM_FUNC_START(aesbs_cbc_decrypt)
 1:	st1		{v24.16b}, [x24]		// store IV
 
 	cbz		x23, 2f
-	cond_yield_neon
 	b		99b
 
 2:	frame_pop
@@ -801,7 +799,7 @@ SYM_FUNC_END(__xts_crypt8)
 	mov		x23, x4
 	mov		x24, x5
 
-0:	movi		v30.2s, #0x1
+	movi		v30.2s, #0x1
 	movi		v25.2s, #0x87
 	uzp1		v30.4s, v30.4s, v25.4s
 	ld1		{v25.16b}, [x24]
@@ -846,7 +844,6 @@ SYM_FUNC_END(__xts_crypt8)
 	cbz		x23, 1f
 	st1		{v25.16b}, [x24]
 
-	cond_yield_neon	0b
 	b		99b
 
 1:	st1		{v25.16b}, [x24]
@@ -889,7 +886,7 @@ SYM_FUNC_START(aesbs_ctr_encrypt)
 	cset		x26, ne
 	add		x23, x23, x26		// do one extra block if final
 
-98:	ldp		x7, x8, [x24]
+	ldp		x7, x8, [x24]
 	ld1		{v0.16b}, [x24]
 CPU_LE(	rev		x7, x7		)
 CPU_LE(	rev		x8, x8		)
@@ -967,7 +964,6 @@ CPU_LE(	rev		x8, x8		)
 	st1		{v0.16b}, [x24]
 	cbz		x23, .Lctr_done
 
-	cond_yield_neon	98b
 	b		99b
 
 .Lctr_done:
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
index 111d9c9abddd..dce6dcebfca1 100644
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -68,10 +68,10 @@
 	.text
 	.arch		armv8-a+crypto
 
-	init_crc	.req	w19
-	buf		.req	x20
-	len		.req	x21
-	fold_consts_ptr	.req	x22
+	init_crc	.req	w0
+	buf		.req	x1
+	len		.req	x2
+	fold_consts_ptr	.req	x3
 
 	fold_consts	.req	v10
 
@@ -257,12 +257,6 @@ CPU_LE(	ext		v12.16b, v12.16b, v12.16b, #8	)
 	.endm
 
 	.macro		crc_t10dif_pmull, p
-	frame_push	4, 128
-
-	mov		init_crc, w0
-	mov		buf, x1
-	mov		len, x2
-
 	__pmull_init_\p
 
 	// For sizes less than 256 bytes, we can't fold 128 bytes at a time.
@@ -317,26 +311,7 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 	fold_32_bytes	\p, v6, v7
 
 	subs		len, len, #128
-	b.lt		.Lfold_128_bytes_loop_done_\@
-
-	if_will_cond_yield_neon
-	stp		q0, q1, [sp, #.Lframe_local_offset]
-	stp		q2, q3, [sp, #.Lframe_local_offset + 32]
-	stp		q4, q5, [sp, #.Lframe_local_offset + 64]
-	stp		q6, q7, [sp, #.Lframe_local_offset + 96]
-	do_cond_yield_neon
-	ldp		q0, q1, [sp, #.Lframe_local_offset]
-	ldp		q2, q3, [sp, #.Lframe_local_offset + 32]
-	ldp		q4, q5, [sp, #.Lframe_local_offset + 64]
-	ldp		q6, q7, [sp, #.Lframe_local_offset + 96]
-	ld1		{fold_consts.2d}, [fold_consts_ptr]
-	__pmull_init_\p
-	__pmull_pre_\p	fold_consts
-	endif_yield_neon
-
-	b		.Lfold_128_bytes_loop_\@
-
-.Lfold_128_bytes_loop_done_\@:
+	b.ge		.Lfold_128_bytes_loop_\@
 
 	// Now fold the 112 bytes in v0-v6 into the 16 bytes in v7.
 
@@ -453,7 +428,9 @@ CPU_LE(	ext		v0.16b, v0.16b, v0.16b, #8	)
 	// Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of v0.
 
 	umov		w0, v0.h[0]
-	frame_pop
+	.ifc		\p, p8
+	ldp		x29, x30, [sp], #16
+	.endif
 	ret
 
 .Lless_than_256_bytes_\@:
@@ -489,7 +466,9 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 // Assumes len >= 16.
 //
 SYM_FUNC_START(crc_t10dif_pmull_p8)
-	crc_t10dif_pmull	p8
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+	crc_t10dif_pmull p8
 SYM_FUNC_END(crc_t10dif_pmull_p8)
 
 	.align		5
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
index ccc3f6067742..09eb1456aed4 100644
--- a/arch/arm64/crypto/crct10dif-ce-glue.c
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -37,9 +37,18 @@ static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data,
 	u16 *crc = shash_desc_ctx(desc);
 
 	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
-		kernel_neon_begin();
-		*crc = crc_t10dif_pmull_p8(*crc, data, length);
-		kernel_neon_end();
+		do {
+			unsigned int chunk = length;
+
+			if (chunk > SZ_4K + CRC_T10DIF_PMULL_CHUNK_SIZE)
+				chunk = SZ_4K;
+
+			kernel_neon_begin();
+			*crc = crc_t10dif_pmull_p8(*crc, data, chunk);
+			kernel_neon_end();
+			data += chunk;
+			length -= chunk;
+		} while (length);
 	} else {
 		*crc = crc_t10dif_generic(*crc, data, length);
 	}
@@ -53,9 +62,18 @@ static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data,
 	u16 *crc = shash_desc_ctx(desc);
 
 	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
-		kernel_neon_begin();
-		*crc = crc_t10dif_pmull_p64(*crc, data, length);
-		kernel_neon_end();
+		do {
+			unsigned int chunk = length;
+
+			if (chunk > SZ_4K + CRC_T10DIF_PMULL_CHUNK_SIZE)
+				chunk = SZ_4K;
+
+			kernel_neon_begin();
+			*crc = crc_t10dif_pmull_p64(*crc, data, chunk);
+			kernel_neon_end();
+			data += chunk;
+			length -= chunk;
+		} while (length);
 	} else {
 		*crc = crc_t10dif_generic(*crc, data, length);
 	}
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 92d0d2753e81..8c02bbc2684e 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -62,40 +62,34 @@
 	.endm
 
 	/*
-	 * void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
-	 *			  int blocks)
+	 * int sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
+	 *			 int blocks)
 	 */
 SYM_FUNC_START(sha1_ce_transform)
-	frame_push	3
-
-	mov		x19, x0
-	mov		x20, x1
-	mov		x21, x2
-
 	/* load round constants */
-0:	loadrc		k0.4s, 0x5a827999, w6
+	loadrc		k0.4s, 0x5a827999, w6
 	loadrc		k1.4s, 0x6ed9eba1, w6
 	loadrc		k2.4s, 0x8f1bbcdc, w6
 	loadrc		k3.4s, 0xca62c1d6, w6
 
 	/* load state */
-	ld1		{dgav.4s}, [x19]
-	ldr		dgb, [x19, #16]
+	ld1		{dgav.4s}, [x0]
+	ldr		dgb, [x0, #16]
 
 	/* load sha1_ce_state::finalize */
 	ldr_l		w4, sha1_ce_offsetof_finalize, x4
-	ldr		w4, [x19, x4]
+	ldr		w4, [x0, x4]
 
 	/* load input */
-1:	ld1		{v8.4s-v11.4s}, [x20], #64
-	sub		w21, w21, #1
+0:	ld1		{v8.4s-v11.4s}, [x1], #64
+	sub		w2, w2, #1
 
 CPU_LE(	rev32		v8.16b, v8.16b		)
 CPU_LE(	rev32		v9.16b, v9.16b		)
 CPU_LE(	rev32		v10.16b, v10.16b	)
 CPU_LE(	rev32		v11.16b, v11.16b	)
 
-2:	add		t0.4s, v8.4s, k0.4s
+1:	add		t0.4s, v8.4s, k0.4s
 	mov		dg0v.16b, dgav.16b
 
 	add_update	c, ev, k0,  8,  9, 10, 11, dgb
@@ -126,25 +120,18 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	add		dgbv.2s, dgbv.2s, dg1v.2s
 	add		dgav.4s, dgav.4s, dg0v.4s
 
-	cbz		w21, 3f
-
-	if_will_cond_yield_neon
-	st1		{dgav.4s}, [x19]
-	str		dgb, [x19, #16]
-	do_cond_yield_neon
+	cbz		w2, 2f
+	cond_yield	3f, x5
 	b		0b
-	endif_yield_neon
-
-	b		1b
 
 	/*
 	 * Final block: add padding and total bit count.
 	 * Skip if the input size was not a round multiple of the block size,
 	 * the padding is handled by the C code in that case.
 	 */
-3:	cbz		x4, 4f
+2:	cbz		x4, 3f
 	ldr_l		w4, sha1_ce_offsetof_count, x4
-	ldr		x4, [x19, x4]
+	ldr		x4, [x0, x4]
 	movi		v9.2d, #0
 	mov		x8, #0x80000000
 	movi		v10.2d, #0
@@ -153,11 +140,11 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	mov		x4, #0
 	mov		v11.d[0], xzr
 	mov		v11.d[1], x7
-	b		2b
+	b		1b
 
 	/* store new state */
-4:	st1		{dgav.4s}, [x19]
-	str		dgb, [x19, #16]
-	frame_pop
+3:	st1		{dgav.4s}, [x0]
+	str		dgb, [x0, #16]
+	mov		w0, w2
 	ret
 SYM_FUNC_END(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index c93121bcfdeb..71fa4f1122d7 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -19,6 +19,7 @@
 MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sha1");
 
 struct sha1_ce_state {
 	struct sha1_state	sst;
@@ -28,14 +29,22 @@ struct sha1_ce_state {
 extern const u32 sha1_ce_offsetof_count;
 extern const u32 sha1_ce_offsetof_finalize;
 
-asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
-				  int blocks);
+asmlinkage int sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
+				 int blocks);
 
 static void __sha1_ce_transform(struct sha1_state *sst, u8 const *src,
 				int blocks)
 {
-	sha1_ce_transform(container_of(sst, struct sha1_ce_state, sst), src,
-			  blocks);
+	while (blocks) {
+		int rem;
+
+		kernel_neon_begin();
+		rem = sha1_ce_transform(container_of(sst, struct sha1_ce_state,
+						     sst), src, blocks);
+		kernel_neon_end();
+		src += (blocks - rem) * SHA1_BLOCK_SIZE;
+		blocks = rem;
+	}
 }
 
 const u32 sha1_ce_offsetof_count = offsetof(struct sha1_ce_state, sst.count);
@@ -50,9 +59,7 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 		return crypto_sha1_update(desc, data, len);
 
 	sctx->finalize = 0;
-	kernel_neon_begin();
 	sha1_base_do_update(desc, data, len, __sha1_ce_transform);
-	kernel_neon_end();
 
 	return 0;
 }
@@ -72,11 +79,9 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 	 */
 	sctx->finalize = finalize;
 
-	kernel_neon_begin();
 	sha1_base_do_update(desc, data, len, __sha1_ce_transform);
 	if (!finalize)
 		sha1_base_do_finalize(desc, __sha1_ce_transform);
-	kernel_neon_end();
 	return sha1_base_finish(desc, out);
 }
 
@@ -88,9 +93,7 @@ static int sha1_ce_final(struct shash_desc *desc, u8 *out)
 		return crypto_sha1_finup(desc, NULL, 0, out);
 
 	sctx->finalize = 0;
-	kernel_neon_begin();
 	sha1_base_do_finalize(desc, __sha1_ce_transform);
-	kernel_neon_end();
 	return sha1_base_finish(desc, out);
 }
 
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 3f9d0f326987..6cdea7d56059 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -76,36 +76,30 @@
 	 */
 	.text
 SYM_FUNC_START(sha2_ce_transform)
-	frame_push	3
-
-	mov		x19, x0
-	mov		x20, x1
-	mov		x21, x2
-
 	/* load round constants */
-0:	adr_l		x8, .Lsha2_rcon
+	adr_l		x8, .Lsha2_rcon
 	ld1		{ v0.4s- v3.4s}, [x8], #64
 	ld1		{ v4.4s- v7.4s}, [x8], #64
 	ld1		{ v8.4s-v11.4s}, [x8], #64
 	ld1		{v12.4s-v15.4s}, [x8]
 
 	/* load state */
-	ld1		{dgav.4s, dgbv.4s}, [x19]
+	ld1		{dgav.4s, dgbv.4s}, [x0]
 
 	/* load sha256_ce_state::finalize */
 	ldr_l		w4, sha256_ce_offsetof_finalize, x4
-	ldr		w4, [x19, x4]
+	ldr		w4, [x0, x4]
 
 	/* load input */
-1:	ld1		{v16.4s-v19.4s}, [x20], #64
-	sub		w21, w21, #1
+0:	ld1		{v16.4s-v19.4s}, [x1], #64
+	sub		w2, w2, #1
 
 CPU_LE(	rev32		v16.16b, v16.16b	)
 CPU_LE(	rev32		v17.16b, v17.16b	)
 CPU_LE(	rev32		v18.16b, v18.16b	)
 CPU_LE(	rev32		v19.16b, v19.16b	)
 
-2:	add		t0.4s, v16.4s, v0.4s
+1:	add		t0.4s, v16.4s, v0.4s
 	mov		dg0v.16b, dgav.16b
 	mov		dg1v.16b, dgbv.16b
 
@@ -134,24 +128,18 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	add		dgbv.4s, dgbv.4s, dg1v.4s
 
 	/* handled all input blocks? */
-	cbz		w21, 3f
-
-	if_will_cond_yield_neon
-	st1		{dgav.4s, dgbv.4s}, [x19]
-	do_cond_yield_neon
+	cbz		w2, 2f
+	cond_yield	3f, x5
 	b		0b
-	endif_yield_neon
-
-	b		1b
 
 	/*
 	 * Final block: add padding and total bit count.
 	 * Skip if the input size was not a round multiple of the block size,
 	 * the padding is handled by the C code in that case.
 	 */
-3:	cbz		x4, 4f
+2:	cbz		x4, 3f
 	ldr_l		w4, sha256_ce_offsetof_count, x4
-	ldr		x4, [x19, x4]
+	ldr		x4, [x0, x4]
 	movi		v17.2d, #0
 	mov		x8, #0x80000000
 	movi		v18.2d, #0
@@ -160,10 +148,10 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	mov		x4, #0
 	mov		v19.d[0], xzr
 	mov		v19.d[1], x7
-	b		2b
+	b		1b
 
 	/* store new state */
-4:	st1		{dgav.4s, dgbv.4s}, [x19]
-	frame_pop
+3:	st1		{dgav.4s, dgbv.4s}, [x0]
+	mov		w0, w2
 	ret
 SYM_FUNC_END(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 31ba3da5e61b..c57a6119fefc 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -19,6 +19,8 @@
 MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
 
 struct sha256_ce_state {
 	struct sha256_state	sst;
@@ -28,14 +30,22 @@ struct sha256_ce_state {
 extern const u32 sha256_ce_offsetof_count;
 extern const u32 sha256_ce_offsetof_finalize;
 
-asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
-				  int blocks);
+asmlinkage int sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
+				 int blocks);
 
 static void __sha2_ce_transform(struct sha256_state *sst, u8 const *src,
 				int blocks)
 {
-	sha2_ce_transform(container_of(sst, struct sha256_ce_state, sst), src,
-			  blocks);
+	while (blocks) {
+		int rem;
+
+		kernel_neon_begin();
+		rem = sha2_ce_transform(container_of(sst, struct sha256_ce_state,
+						     sst), src, blocks);
+		kernel_neon_end();
+		src += (blocks - rem) * SHA256_BLOCK_SIZE;
+		blocks = rem;
+	}
 }
 
 const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
@@ -61,9 +71,7 @@ static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
 				__sha256_block_data_order);
 
 	sctx->finalize = 0;
-	kernel_neon_begin();
 	sha256_base_do_update(desc, data, len, __sha2_ce_transform);
-	kernel_neon_end();
 
 	return 0;
 }
@@ -88,11 +96,9 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
 	 */
 	sctx->finalize = finalize;
 
-	kernel_neon_begin();
 	sha256_base_do_update(desc, data, len, __sha2_ce_transform);
 	if (!finalize)
 		sha256_base_do_finalize(desc, __sha2_ce_transform);
-	kernel_neon_end();
 	return sha256_base_finish(desc, out);
 }
 
@@ -106,9 +112,7 @@ static int sha256_ce_final(struct shash_desc *desc, u8 *out)
 	}
 
 	sctx->finalize = 0;
-	kernel_neon_begin();
 	sha256_base_do_finalize(desc, __sha2_ce_transform);
-	kernel_neon_end();
 	return sha256_base_finish(desc, out);
 }
 
diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S
index 1cfb768df350..6f5208414fe3 100644
--- a/arch/arm64/crypto/sha3-ce-core.S
+++ b/arch/arm64/crypto/sha3-ce-core.S
@@ -37,20 +37,13 @@
 	.endm
 
 	/*
-	 * sha3_ce_transform(u64 *st, const u8 *data, int blocks, int dg_size)
+	 * int sha3_ce_transform(u64 *st, const u8 *data, int blocks, int dg_size)
 	 */
 	.text
 SYM_FUNC_START(sha3_ce_transform)
-	frame_push	4
-
-	mov	x19, x0
-	mov	x20, x1
-	mov	x21, x2
-	mov	x22, x3
-
-0:	/* load state */
-	add	x8, x19, #32
-	ld1	{ v0.1d- v3.1d}, [x19]
+	/* load state */
+	add	x8, x0, #32
+	ld1	{ v0.1d- v3.1d}, [x0]
 	ld1	{ v4.1d- v7.1d}, [x8], #32
 	ld1	{ v8.1d-v11.1d}, [x8], #32
 	ld1	{v12.1d-v15.1d}, [x8], #32
@@ -58,13 +51,13 @@ SYM_FUNC_START(sha3_ce_transform)
 	ld1	{v20.1d-v23.1d}, [x8], #32
 	ld1	{v24.1d}, [x8]
 
-1:	sub	w21, w21, #1
+0:	sub	w2, w2, #1
 	mov	w8, #24
 	adr_l	x9, .Lsha3_rcon
 
 	/* load input */
-	ld1	{v25.8b-v28.8b}, [x20], #32
-	ld1	{v29.8b-v31.8b}, [x20], #24
+	ld1	{v25.8b-v28.8b}, [x1], #32
+	ld1	{v29.8b-v31.8b}, [x1], #24
 	eor	v0.8b, v0.8b, v25.8b
 	eor	v1.8b, v1.8b, v26.8b
 	eor	v2.8b, v2.8b, v27.8b
@@ -73,10 +66,10 @@ SYM_FUNC_START(sha3_ce_transform)
 	eor	v5.8b, v5.8b, v30.8b
 	eor	v6.8b, v6.8b, v31.8b
 
-	tbnz	x22, #6, 3f		// SHA3-512
+	tbnz	x3, #6, 2f		// SHA3-512
 
-	ld1	{v25.8b-v28.8b}, [x20], #32
-	ld1	{v29.8b-v30.8b}, [x20], #16
+	ld1	{v25.8b-v28.8b}, [x1], #32
+	ld1	{v29.8b-v30.8b}, [x1], #16
 	eor	 v7.8b,  v7.8b, v25.8b
 	eor	 v8.8b,  v8.8b, v26.8b
 	eor	 v9.8b,  v9.8b, v27.8b
@@ -84,34 +77,34 @@ SYM_FUNC_START(sha3_ce_transform)
 	eor	v11.8b, v11.8b, v29.8b
 	eor	v12.8b, v12.8b, v30.8b
 
-	tbnz	x22, #4, 2f		// SHA3-384 or SHA3-224
+	tbnz	x3, #4, 1f		// SHA3-384 or SHA3-224
 
 	// SHA3-256
-	ld1	{v25.8b-v28.8b}, [x20], #32
+	ld1	{v25.8b-v28.8b}, [x1], #32
 	eor	v13.8b, v13.8b, v25.8b
 	eor	v14.8b, v14.8b, v26.8b
 	eor	v15.8b, v15.8b, v27.8b
 	eor	v16.8b, v16.8b, v28.8b
-	b	4f
+	b	3f
 
-2:	tbz	x22, #2, 4f		// bit 2 cleared? SHA-384
+1:	tbz	x3, #2, 3f		// bit 2 cleared? SHA-384
 
 	// SHA3-224
-	ld1	{v25.8b-v28.8b}, [x20], #32
-	ld1	{v29.8b}, [x20], #8
+	ld1	{v25.8b-v28.8b}, [x1], #32
+	ld1	{v29.8b}, [x1], #8
 	eor	v13.8b, v13.8b, v25.8b
 	eor	v14.8b, v14.8b, v26.8b
 	eor	v15.8b, v15.8b, v27.8b
 	eor	v16.8b, v16.8b, v28.8b
 	eor	v17.8b, v17.8b, v29.8b
-	b	4f
+	b	3f
 
 	// SHA3-512
-3:	ld1	{v25.8b-v26.8b}, [x20], #16
+2:	ld1	{v25.8b-v26.8b}, [x1], #16
 	eor	 v7.8b,  v7.8b, v25.8b
 	eor	 v8.8b,  v8.8b, v26.8b
 
-4:	sub	w8, w8, #1
+3:	sub	w8, w8, #1
 
 	eor3	v29.16b,  v4.16b,  v9.16b, v14.16b
 	eor3	v26.16b,  v1.16b,  v6.16b, v11.16b
@@ -190,33 +183,19 @@ SYM_FUNC_START(sha3_ce_transform)
 
 	eor	 v0.16b,  v0.16b, v31.16b
 
-	cbnz	w8, 4b
-	cbz	w21, 5f
-
-	if_will_cond_yield_neon
-	add	x8, x19, #32
-	st1	{ v0.1d- v3.1d}, [x19]
-	st1	{ v4.1d- v7.1d}, [x8], #32
-	st1	{ v8.1d-v11.1d}, [x8], #32
-	st1	{v12.1d-v15.1d}, [x8], #32
-	st1	{v16.1d-v19.1d}, [x8], #32
-	st1	{v20.1d-v23.1d}, [x8], #32
-	st1	{v24.1d}, [x8]
-	do_cond_yield_neon
-	b		0b
-	endif_yield_neon
-
-	b	1b
+	cbnz	w8, 3b
+	cond_yield 3f, x8
+	cbnz	w2, 0b
 
 	/* save state */
-5:	st1	{ v0.1d- v3.1d}, [x19], #32
-	st1	{ v4.1d- v7.1d}, [x19], #32
-	st1	{ v8.1d-v11.1d}, [x19], #32
-	st1	{v12.1d-v15.1d}, [x19], #32
-	st1	{v16.1d-v19.1d}, [x19], #32
-	st1	{v20.1d-v23.1d}, [x19], #32
-	st1	{v24.1d}, [x19]
-	frame_pop
+3:	st1	{ v0.1d- v3.1d}, [x0], #32
+	st1	{ v4.1d- v7.1d}, [x0], #32
+	st1	{ v8.1d-v11.1d}, [x0], #32
+	st1	{v12.1d-v15.1d}, [x0], #32
+	st1	{v16.1d-v19.1d}, [x0], #32
+	st1	{v20.1d-v23.1d}, [x0], #32
+	st1	{v24.1d}, [x0]
+	mov	w0, w2
 	ret
 SYM_FUNC_END(sha3_ce_transform)
 
diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c
index e5a2936f0886..8c65cecf560a 100644
--- a/arch/arm64/crypto/sha3-ce-glue.c
+++ b/arch/arm64/crypto/sha3-ce-glue.c
@@ -23,9 +23,13 @@
 MODULE_DESCRIPTION("SHA3 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sha3-224");
+MODULE_ALIAS_CRYPTO("sha3-256");
+MODULE_ALIAS_CRYPTO("sha3-384");
+MODULE_ALIAS_CRYPTO("sha3-512");
 
-asmlinkage void sha3_ce_transform(u64 *st, const u8 *data, int blocks,
-				  int md_len);
+asmlinkage int sha3_ce_transform(u64 *st, const u8 *data, int blocks,
+				 int md_len);
 
 static int sha3_update(struct shash_desc *desc, const u8 *data,
 		       unsigned int len)
@@ -55,11 +59,15 @@ static int sha3_update(struct shash_desc *desc, const u8 *data,
 		blocks = len / sctx->rsiz;
 		len %= sctx->rsiz;
 
-		if (blocks) {
+		while (blocks) {
+			int rem;
+
 			kernel_neon_begin();
-			sha3_ce_transform(sctx->st, data, blocks, digest_size);
+			rem = sha3_ce_transform(sctx->st, data, blocks,
+						digest_size);
 			kernel_neon_end();
-			data += blocks * sctx->rsiz;
+			data += (blocks - rem) * sctx->rsiz;
+			blocks = rem;
 		}
 	}
 
diff --git a/arch/arm64/crypto/sha512-ce-core.S b/arch/arm64/crypto/sha512-ce-core.S
index cde606c0323e..d6e7f6c95fa6 100644
--- a/arch/arm64/crypto/sha512-ce-core.S
+++ b/arch/arm64/crypto/sha512-ce-core.S
@@ -107,23 +107,17 @@
 	 */
 	.text
 SYM_FUNC_START(sha512_ce_transform)
-	frame_push	3
-
-	mov		x19, x0
-	mov		x20, x1
-	mov		x21, x2
-
 	/* load state */
-0:	ld1		{v8.2d-v11.2d}, [x19]
+	ld1		{v8.2d-v11.2d}, [x0]
 
 	/* load first 4 round constants */
 	adr_l		x3, .Lsha512_rcon
 	ld1		{v20.2d-v23.2d}, [x3], #64
 
 	/* load input */
-1:	ld1		{v12.2d-v15.2d}, [x20], #64
-	ld1		{v16.2d-v19.2d}, [x20], #64
-	sub		w21, w21, #1
+0:	ld1		{v12.2d-v15.2d}, [x1], #64
+	ld1		{v16.2d-v19.2d}, [x1], #64
+	sub		w2, w2, #1
 
 CPU_LE(	rev64		v12.16b, v12.16b	)
 CPU_LE(	rev64		v13.16b, v13.16b	)
@@ -201,19 +195,12 @@ CPU_LE(	rev64		v19.16b, v19.16b	)
 	add		v10.2d, v10.2d, v2.2d
 	add		v11.2d, v11.2d, v3.2d
 
+	cond_yield	3f, x4
 	/* handled all input blocks? */
-	cbz		w21, 3f
-
-	if_will_cond_yield_neon
-	st1		{v8.2d-v11.2d}, [x19]
-	do_cond_yield_neon
-	b		0b
-	endif_yield_neon
-
-	b		1b
+	cbnz		w2, 0b
 
 	/* store new state */
-3:	st1		{v8.2d-v11.2d}, [x19]
-	frame_pop
+3:	st1		{v8.2d-v11.2d}, [x0]
+	mov		w0, w2
 	ret
 SYM_FUNC_END(sha512_ce_transform)
diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c
index faa83f6cf376..e62a094a9d52 100644
--- a/arch/arm64/crypto/sha512-ce-glue.c
+++ b/arch/arm64/crypto/sha512-ce-glue.c
@@ -23,12 +23,28 @@
 MODULE_DESCRIPTION("SHA-384/SHA-512 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
 
-asmlinkage void sha512_ce_transform(struct sha512_state *sst, u8 const *src,
-				    int blocks);
+asmlinkage int sha512_ce_transform(struct sha512_state *sst, u8 const *src,
+				   int blocks);
 
 asmlinkage void sha512_block_data_order(u64 *digest, u8 const *src, int blocks);
 
+static void __sha512_ce_transform(struct sha512_state *sst, u8 const *src,
+				  int blocks)
+{
+	while (blocks) {
+		int rem;
+
+		kernel_neon_begin();
+		rem = sha512_ce_transform(sst, src, blocks);
+		kernel_neon_end();
+		src += (blocks - rem) * SHA512_BLOCK_SIZE;
+		blocks = rem;
+	}
+}
+
 static void __sha512_block_data_order(struct sha512_state *sst, u8 const *src,
 				      int blocks)
 {
@@ -38,45 +54,30 @@ static void __sha512_block_data_order(struct sha512_state *sst, u8 const *src,
 static int sha512_ce_update(struct shash_desc *desc, const u8 *data,
 			    unsigned int len)
 {
-	if (!crypto_simd_usable())
-		return sha512_base_do_update(desc, data, len,
-					     __sha512_block_data_order);
-
-	kernel_neon_begin();
-	sha512_base_do_update(desc, data, len, sha512_ce_transform);
-	kernel_neon_end();
+	sha512_block_fn *fn = crypto_simd_usable() ? __sha512_ce_transform
+						   : __sha512_block_data_order;
 
+	sha512_base_do_update(desc, data, len, fn);
 	return 0;
 }
 
 static int sha512_ce_finup(struct shash_desc *desc, const u8 *data,
 			   unsigned int len, u8 *out)
 {
-	if (!crypto_simd_usable()) {
-		if (len)
-			sha512_base_do_update(desc, data, len,
-					      __sha512_block_data_order);
-		sha512_base_do_finalize(desc, __sha512_block_data_order);
-		return sha512_base_finish(desc, out);
-	}
+	sha512_block_fn *fn = crypto_simd_usable() ? __sha512_ce_transform
+						   : __sha512_block_data_order;
 
-	kernel_neon_begin();
-	sha512_base_do_update(desc, data, len, sha512_ce_transform);
-	sha512_base_do_finalize(desc, sha512_ce_transform);
-	kernel_neon_end();
+	sha512_base_do_update(desc, data, len, fn);
+	sha512_base_do_finalize(desc, fn);
 	return sha512_base_finish(desc, out);
 }
 
 static int sha512_ce_final(struct shash_desc *desc, u8 *out)
 {
-	if (!crypto_simd_usable()) {
-		sha512_base_do_finalize(desc, __sha512_block_data_order);
-		return sha512_base_finish(desc, out);
-	}
+	sha512_block_fn *fn = crypto_simd_usable() ? __sha512_ce_transform
+						   : __sha512_block_data_order;
 
-	kernel_neon_begin();
-	sha512_base_do_finalize(desc, sha512_ce_transform);
-	kernel_neon_end();
+	sha512_base_do_finalize(desc, fn);
 	return sha512_base_finish(desc, out);
 }
 
diff --git a/arch/powerpc/crypto/sha256-spe-glue.c b/arch/powerpc/crypto/sha256-spe-glue.c
index a6e650a97d8f..ffedea7e4bef 100644
--- a/arch/powerpc/crypto/sha256-spe-glue.c
+++ b/arch/powerpc/crypto/sha256-spe-glue.c
@@ -129,7 +129,7 @@ static int ppc_spe_sha256_update(struct shash_desc *desc, const u8 *data,
 
 		src += bytes;
 		len -= bytes;
-	};
+	}
 
 	memcpy((char *)sctx->buf, src, len);
 	return 0;
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 73044634d342..54c7536f2482 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -21,6 +21,7 @@
 #include <crypto/algapi.h>
 #include <crypto/ghash.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/err.h>
@@ -1055,3 +1056,4 @@ MODULE_ALIAS_CRYPTO("aes-all");
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
 MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index a31de0c6ccde..b28e36b7c96b 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -4,8 +4,6 @@
 
 OBJECT_FILES_NON_STANDARD := y
 
-obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
-
 obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
 twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index d1436c37008b..4e3972570916 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -43,10 +43,6 @@
 #ifdef __x86_64__
 
 # constants in mergeable sections, linker can reorder and merge
-.section	.rodata.cst16.gf128mul_x_ble_mask, "aM", @progbits, 16
-.align 16
-.Lgf128mul_x_ble_mask:
-	.octa 0x00000000000000010000000000000087
 .section	.rodata.cst16.POLY, "aM", @progbits, 16
 .align 16
 POLY:   .octa 0xC2000000000000000000000000000001
@@ -146,7 +142,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 #define CTR	%xmm11
 #define INC	%xmm12
 
-#define GF128MUL_MASK %xmm10
+#define GF128MUL_MASK %xmm7
 
 #ifdef __x86_64__
 #define AREG	%rax
@@ -2577,13 +2573,140 @@ SYM_FUNC_START(aesni_cbc_dec)
 	ret
 SYM_FUNC_END(aesni_cbc_dec)
 
-#ifdef __x86_64__
+/*
+ * void aesni_cts_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
+ *			  size_t len, u8 *iv)
+ */
+SYM_FUNC_START(aesni_cts_cbc_enc)
+	FRAME_BEGIN
+#ifndef __x86_64__
+	pushl IVP
+	pushl LEN
+	pushl KEYP
+	pushl KLEN
+	movl (FRAME_OFFSET+20)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+24)(%esp), OUTP	# dst
+	movl (FRAME_OFFSET+28)(%esp), INP	# src
+	movl (FRAME_OFFSET+32)(%esp), LEN	# len
+	movl (FRAME_OFFSET+36)(%esp), IVP	# iv
+	lea .Lcts_permute_table, T1
+#else
+	lea .Lcts_permute_table(%rip), T1
+#endif
+	mov 480(KEYP), KLEN
+	movups (IVP), STATE
+	sub $16, LEN
+	mov T1, IVP
+	add $32, IVP
+	add LEN, T1
+	sub LEN, IVP
+	movups (T1), %xmm4
+	movups (IVP), %xmm5
+
+	movups (INP), IN1
+	add LEN, INP
+	movups (INP), IN2
+
+	pxor IN1, STATE
+	call _aesni_enc1
+
+	pshufb %xmm5, IN2
+	pxor STATE, IN2
+	pshufb %xmm4, STATE
+	add OUTP, LEN
+	movups STATE, (LEN)
+
+	movaps IN2, STATE
+	call _aesni_enc1
+	movups STATE, (OUTP)
+
+#ifndef __x86_64__
+	popl KLEN
+	popl KEYP
+	popl LEN
+	popl IVP
+#endif
+	FRAME_END
+	ret
+SYM_FUNC_END(aesni_cts_cbc_enc)
+
+/*
+ * void aesni_cts_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
+ *			  size_t len, u8 *iv)
+ */
+SYM_FUNC_START(aesni_cts_cbc_dec)
+	FRAME_BEGIN
+#ifndef __x86_64__
+	pushl IVP
+	pushl LEN
+	pushl KEYP
+	pushl KLEN
+	movl (FRAME_OFFSET+20)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+24)(%esp), OUTP	# dst
+	movl (FRAME_OFFSET+28)(%esp), INP	# src
+	movl (FRAME_OFFSET+32)(%esp), LEN	# len
+	movl (FRAME_OFFSET+36)(%esp), IVP	# iv
+	lea .Lcts_permute_table, T1
+#else
+	lea .Lcts_permute_table(%rip), T1
+#endif
+	mov 480(KEYP), KLEN
+	add $240, KEYP
+	movups (IVP), IV
+	sub $16, LEN
+	mov T1, IVP
+	add $32, IVP
+	add LEN, T1
+	sub LEN, IVP
+	movups (T1), %xmm4
+
+	movups (INP), STATE
+	add LEN, INP
+	movups (INP), IN1
+
+	call _aesni_dec1
+	movaps STATE, IN2
+	pshufb %xmm4, STATE
+	pxor IN1, STATE
+
+	add OUTP, LEN
+	movups STATE, (LEN)
+
+	movups (IVP), %xmm0
+	pshufb %xmm0, IN1
+	pblendvb IN2, IN1
+	movaps IN1, STATE
+	call _aesni_dec1
+
+	pxor IV, STATE
+	movups STATE, (OUTP)
+
+#ifndef __x86_64__
+	popl KLEN
+	popl KEYP
+	popl LEN
+	popl IVP
+#endif
+	FRAME_END
+	ret
+SYM_FUNC_END(aesni_cts_cbc_dec)
+
 .pushsection .rodata
 .align 16
+.Lcts_permute_table:
+	.byte		0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+	.byte		0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+	.byte		0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+	.byte		0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+	.byte		0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+	.byte		0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+#ifdef __x86_64__
 .Lbswap_mask:
 	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
+#endif
 .popsection
 
+#ifdef __x86_64__
 /*
  * _aesni_inc_init:	internal ABI
  *	setup registers used by _aesni_inc
@@ -2696,6 +2819,14 @@ SYM_FUNC_START(aesni_ctr_enc)
 	ret
 SYM_FUNC_END(aesni_ctr_enc)
 
+#endif
+
+.section	.rodata.cst16.gf128mul_x_ble_mask, "aM", @progbits, 16
+.align 16
+.Lgf128mul_x_ble_mask:
+	.octa 0x00000000000000010000000000000087
+.previous
+
 /*
  * _aesni_gf128mul_x_ble:		internal ABI
  *	Multiply in GF(2^128) for XTS IVs
@@ -2708,120 +2839,325 @@ SYM_FUNC_END(aesni_ctr_enc)
  *	CTR:	== temporary value
  */
 #define _aesni_gf128mul_x_ble() \
-	pshufd $0x13, IV, CTR; \
+	pshufd $0x13, IV, KEY; \
 	paddq IV, IV; \
-	psrad $31, CTR; \
-	pand GF128MUL_MASK, CTR; \
-	pxor CTR, IV;
+	psrad $31, KEY; \
+	pand GF128MUL_MASK, KEY; \
+	pxor KEY, IV;
 
 /*
- * void aesni_xts_crypt8(const struct crypto_aes_ctx *ctx, u8 *dst,
- *			 const u8 *src, bool enc, le128 *iv)
+ * void aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *dst,
+ *			  const u8 *src, unsigned int len, le128 *iv)
  */
-SYM_FUNC_START(aesni_xts_crypt8)
+SYM_FUNC_START(aesni_xts_encrypt)
 	FRAME_BEGIN
-	testb %cl, %cl
-	movl $0, %ecx
-	movl $240, %r10d
-	leaq _aesni_enc4, %r11
-	leaq _aesni_dec4, %rax
-	cmovel %r10d, %ecx
-	cmoveq %rax, %r11
-
+#ifndef __x86_64__
+	pushl IVP
+	pushl LEN
+	pushl KEYP
+	pushl KLEN
+	movl (FRAME_OFFSET+20)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+24)(%esp), OUTP	# dst
+	movl (FRAME_OFFSET+28)(%esp), INP	# src
+	movl (FRAME_OFFSET+32)(%esp), LEN	# len
+	movl (FRAME_OFFSET+36)(%esp), IVP	# iv
 	movdqa .Lgf128mul_x_ble_mask, GF128MUL_MASK
+#else
+	movdqa .Lgf128mul_x_ble_mask(%rip), GF128MUL_MASK
+#endif
 	movups (IVP), IV
 
 	mov 480(KEYP), KLEN
-	addq %rcx, KEYP
+
+.Lxts_enc_loop4:
+	sub $64, LEN
+	jl .Lxts_enc_1x
 
 	movdqa IV, STATE1
-	movdqu 0x00(INP), INC
-	pxor INC, STATE1
+	movdqu 0x00(INP), IN
+	pxor IN, STATE1
 	movdqu IV, 0x00(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE2
-	movdqu 0x10(INP), INC
-	pxor INC, STATE2
+	movdqu 0x10(INP), IN
+	pxor IN, STATE2
 	movdqu IV, 0x10(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE3
-	movdqu 0x20(INP), INC
-	pxor INC, STATE3
+	movdqu 0x20(INP), IN
+	pxor IN, STATE3
 	movdqu IV, 0x20(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE4
-	movdqu 0x30(INP), INC
-	pxor INC, STATE4
+	movdqu 0x30(INP), IN
+	pxor IN, STATE4
 	movdqu IV, 0x30(OUTP)
 
-	CALL_NOSPEC r11
+	call _aesni_enc4
 
-	movdqu 0x00(OUTP), INC
-	pxor INC, STATE1
+	movdqu 0x00(OUTP), IN
+	pxor IN, STATE1
 	movdqu STATE1, 0x00(OUTP)
 
+	movdqu 0x10(OUTP), IN
+	pxor IN, STATE2
+	movdqu STATE2, 0x10(OUTP)
+
+	movdqu 0x20(OUTP), IN
+	pxor IN, STATE3
+	movdqu STATE3, 0x20(OUTP)
+
+	movdqu 0x30(OUTP), IN
+	pxor IN, STATE4
+	movdqu STATE4, 0x30(OUTP)
+
 	_aesni_gf128mul_x_ble()
-	movdqa IV, STATE1
-	movdqu 0x40(INP), INC
-	pxor INC, STATE1
-	movdqu IV, 0x40(OUTP)
 
-	movdqu 0x10(OUTP), INC
-	pxor INC, STATE2
-	movdqu STATE2, 0x10(OUTP)
+	add $64, INP
+	add $64, OUTP
+	test LEN, LEN
+	jnz .Lxts_enc_loop4
 
+.Lxts_enc_ret_iv:
+	movups IV, (IVP)
+
+.Lxts_enc_ret:
+#ifndef __x86_64__
+	popl KLEN
+	popl KEYP
+	popl LEN
+	popl IVP
+#endif
+	FRAME_END
+	ret
+
+.Lxts_enc_1x:
+	add $64, LEN
+	jz .Lxts_enc_ret_iv
+	sub $16, LEN
+	jl .Lxts_enc_cts4
+
+.Lxts_enc_loop1:
+	movdqu (INP), STATE
+	pxor IV, STATE
+	call _aesni_enc1
+	pxor IV, STATE
 	_aesni_gf128mul_x_ble()
-	movdqa IV, STATE2
-	movdqu 0x50(INP), INC
-	pxor INC, STATE2
-	movdqu IV, 0x50(OUTP)
 
-	movdqu 0x20(OUTP), INC
-	pxor INC, STATE3
-	movdqu STATE3, 0x20(OUTP)
+	test LEN, LEN
+	jz .Lxts_enc_out
+
+	add $16, INP
+	sub $16, LEN
+	jl .Lxts_enc_cts1
+
+	movdqu STATE, (OUTP)
+	add $16, OUTP
+	jmp .Lxts_enc_loop1
+
+.Lxts_enc_out:
+	movdqu STATE, (OUTP)
+	jmp .Lxts_enc_ret_iv
+
+.Lxts_enc_cts4:
+	movdqa STATE4, STATE
+	sub $16, OUTP
+
+.Lxts_enc_cts1:
+#ifndef __x86_64__
+	lea .Lcts_permute_table, T1
+#else
+	lea .Lcts_permute_table(%rip), T1
+#endif
+	add LEN, INP		/* rewind input pointer */
+	add $16, LEN		/* # bytes in final block */
+	movups (INP), IN1
+
+	mov T1, IVP
+	add $32, IVP
+	add LEN, T1
+	sub LEN, IVP
+	add OUTP, LEN
+
+	movups (T1), %xmm4
+	movaps STATE, IN2
+	pshufb %xmm4, STATE
+	movups STATE, (LEN)
+
+	movups (IVP), %xmm0
+	pshufb %xmm0, IN1
+	pblendvb IN2, IN1
+	movaps IN1, STATE
+
+	pxor IV, STATE
+	call _aesni_enc1
+	pxor IV, STATE
+
+	movups STATE, (OUTP)
+	jmp .Lxts_enc_ret
+SYM_FUNC_END(aesni_xts_encrypt)
+
+/*
+ * void aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *dst,
+ *			  const u8 *src, unsigned int len, le128 *iv)
+ */
+SYM_FUNC_START(aesni_xts_decrypt)
+	FRAME_BEGIN
+#ifndef __x86_64__
+	pushl IVP
+	pushl LEN
+	pushl KEYP
+	pushl KLEN
+	movl (FRAME_OFFSET+20)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+24)(%esp), OUTP	# dst
+	movl (FRAME_OFFSET+28)(%esp), INP	# src
+	movl (FRAME_OFFSET+32)(%esp), LEN	# len
+	movl (FRAME_OFFSET+36)(%esp), IVP	# iv
+	movdqa .Lgf128mul_x_ble_mask, GF128MUL_MASK
+#else
+	movdqa .Lgf128mul_x_ble_mask(%rip), GF128MUL_MASK
+#endif
+	movups (IVP), IV
+
+	mov 480(KEYP), KLEN
+	add $240, KEYP
+
+	test $15, LEN
+	jz .Lxts_dec_loop4
+	sub $16, LEN
+
+.Lxts_dec_loop4:
+	sub $64, LEN
+	jl .Lxts_dec_1x
+
+	movdqa IV, STATE1
+	movdqu 0x00(INP), IN
+	pxor IN, STATE1
+	movdqu IV, 0x00(OUTP)
 
 	_aesni_gf128mul_x_ble()
-	movdqa IV, STATE3
-	movdqu 0x60(INP), INC
-	pxor INC, STATE3
-	movdqu IV, 0x60(OUTP)
+	movdqa IV, STATE2
+	movdqu 0x10(INP), IN
+	pxor IN, STATE2
+	movdqu IV, 0x10(OUTP)
 
-	movdqu 0x30(OUTP), INC
-	pxor INC, STATE4
-	movdqu STATE4, 0x30(OUTP)
+	_aesni_gf128mul_x_ble()
+	movdqa IV, STATE3
+	movdqu 0x20(INP), IN
+	pxor IN, STATE3
+	movdqu IV, 0x20(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE4
-	movdqu 0x70(INP), INC
-	pxor INC, STATE4
-	movdqu IV, 0x70(OUTP)
+	movdqu 0x30(INP), IN
+	pxor IN, STATE4
+	movdqu IV, 0x30(OUTP)
 
-	_aesni_gf128mul_x_ble()
-	movups IV, (IVP)
+	call _aesni_dec4
+
+	movdqu 0x00(OUTP), IN
+	pxor IN, STATE1
+	movdqu STATE1, 0x00(OUTP)
+
+	movdqu 0x10(OUTP), IN
+	pxor IN, STATE2
+	movdqu STATE2, 0x10(OUTP)
 
-	CALL_NOSPEC r11
+	movdqu 0x20(OUTP), IN
+	pxor IN, STATE3
+	movdqu STATE3, 0x20(OUTP)
 
-	movdqu 0x40(OUTP), INC
-	pxor INC, STATE1
-	movdqu STATE1, 0x40(OUTP)
+	movdqu 0x30(OUTP), IN
+	pxor IN, STATE4
+	movdqu STATE4, 0x30(OUTP)
 
-	movdqu 0x50(OUTP), INC
-	pxor INC, STATE2
-	movdqu STATE2, 0x50(OUTP)
+	_aesni_gf128mul_x_ble()
 
-	movdqu 0x60(OUTP), INC
-	pxor INC, STATE3
-	movdqu STATE3, 0x60(OUTP)
+	add $64, INP
+	add $64, OUTP
+	test LEN, LEN
+	jnz .Lxts_dec_loop4
 
-	movdqu 0x70(OUTP), INC
-	pxor INC, STATE4
-	movdqu STATE4, 0x70(OUTP)
+.Lxts_dec_ret_iv:
+	movups IV, (IVP)
 
+.Lxts_dec_ret:
+#ifndef __x86_64__
+	popl KLEN
+	popl KEYP
+	popl LEN
+	popl IVP
+#endif
 	FRAME_END
 	ret
-SYM_FUNC_END(aesni_xts_crypt8)
 
+.Lxts_dec_1x:
+	add $64, LEN
+	jz .Lxts_dec_ret_iv
+
+.Lxts_dec_loop1:
+	movdqu (INP), STATE
+
+	add $16, INP
+	sub $16, LEN
+	jl .Lxts_dec_cts1
+
+	pxor IV, STATE
+	call _aesni_dec1
+	pxor IV, STATE
+	_aesni_gf128mul_x_ble()
+
+	test LEN, LEN
+	jz .Lxts_dec_out
+
+	movdqu STATE, (OUTP)
+	add $16, OUTP
+	jmp .Lxts_dec_loop1
+
+.Lxts_dec_out:
+	movdqu STATE, (OUTP)
+	jmp .Lxts_dec_ret_iv
+
+.Lxts_dec_cts1:
+	movdqa IV, STATE4
+	_aesni_gf128mul_x_ble()
+
+	pxor IV, STATE
+	call _aesni_dec1
+	pxor IV, STATE
+
+#ifndef __x86_64__
+	lea .Lcts_permute_table, T1
+#else
+	lea .Lcts_permute_table(%rip), T1
 #endif
+	add LEN, INP		/* rewind input pointer */
+	add $16, LEN		/* # bytes in final block */
+	movups (INP), IN1
+
+	mov T1, IVP
+	add $32, IVP
+	add LEN, T1
+	sub LEN, IVP
+	add OUTP, LEN
+
+	movups (T1), %xmm4
+	movaps STATE, IN2
+	pshufb %xmm4, STATE
+	movups STATE, (LEN)
+
+	movups (IVP), %xmm0
+	pshufb %xmm0, IN1
+	pblendvb IN2, IN1
+	movaps IN1, STATE
+
+	pxor STATE4, STATE
+	call _aesni_dec1
+	pxor STATE4, STATE
+
+	movups STATE, (OUTP)
+	jmp .Lxts_dec_ret
+SYM_FUNC_END(aesni_xts_decrypt)
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index ad8a7188a2bf..2144e54a6c89 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -31,11 +31,10 @@
 #include <crypto/internal/aead.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
+#include <linux/jump_label.h>
 #include <linux/workqueue.h>
 #include <linux/spinlock.h>
-#ifdef CONFIG_X86_64
-#include <asm/crypto/glue_helper.h>
-#endif
+#include <linux/static_call.h>
 
 
 #define AESNI_ALIGN	16
@@ -93,62 +92,25 @@ asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv);
 asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv);
+asmlinkage void aesni_cts_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out,
+				  const u8 *in, unsigned int len, u8 *iv);
+asmlinkage void aesni_cts_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
+				  const u8 *in, unsigned int len, u8 *iv);
 
 #define AVX_GEN2_OPTSIZE 640
 #define AVX_GEN4_OPTSIZE 4096
 
+asmlinkage void aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *out,
+				  const u8 *in, unsigned int len, u8 *iv);
+
+asmlinkage void aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *out,
+				  const u8 *in, unsigned int len, u8 *iv);
+
 #ifdef CONFIG_X86_64
 
-static void (*aesni_ctr_enc_tfm)(struct crypto_aes_ctx *ctx, u8 *out,
-			      const u8 *in, unsigned int len, u8 *iv);
 asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv);
-
-asmlinkage void aesni_xts_crypt8(const struct crypto_aes_ctx *ctx, u8 *out,
-				 const u8 *in, bool enc, le128 *iv);
-
-/* 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.
- * u8 *iv, Pre-counter block j0: 12 byte IV concatenated with 0x00000001.
- *         16-byte aligned pointer.
- * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary.
- * const u8 *aad, Additional Authentication Data (AAD)
- * unsigned long aad_len, Length of AAD in bytes.
- * u8 *auth_tag, Authenticated Tag output.
- * 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,
-			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.
- * u8 *iv, Pre-counter block j0: 12 byte IV concatenated with 0x00000001.
- *         16-byte aligned pointer.
- * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary.
- * const u8 *aad, Additional Authentication Data (AAD)
- * unsigned long aad_len, Length of AAD in bytes. With RFC4106 this is going
- * to be 8 or 12 bytes
- * u8 *auth_tag, Authenticated Tag output.
- * 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,
-			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);
+DEFINE_STATIC_CALL(aesni_ctr_enc_tfm, aesni_ctr_enc);
 
 /* Scatter / Gather routines, with args similar to above */
 asmlinkage void aesni_gcm_init(void *ctx,
@@ -167,24 +129,6 @@ asmlinkage void aesni_gcm_finalize(void *ctx,
 				   struct gcm_context_data *gdata,
 				   u8 *auth_tag, unsigned long auth_tag_len);
 
-static const struct aesni_gcm_tfm_s {
-	void (*init)(void *ctx, struct gcm_context_data *gdata, u8 *iv,
-		     u8 *hash_subkey, const u8 *aad, unsigned long aad_len);
-	void (*enc_update)(void *ctx, struct gcm_context_data *gdata, u8 *out,
-			   const u8 *in, unsigned long plaintext_len);
-	void (*dec_update)(void *ctx, struct gcm_context_data *gdata, u8 *out,
-			   const u8 *in, unsigned long ciphertext_len);
-	void (*finalize)(void *ctx, struct gcm_context_data *gdata,
-			 u8 *auth_tag, unsigned long auth_tag_len);
-} *aesni_gcm_tfm;
-
-static const struct aesni_gcm_tfm_s aesni_gcm_tfm_sse = {
-	.init = &aesni_gcm_init,
-	.enc_update = &aesni_gcm_enc_update,
-	.dec_update = &aesni_gcm_dec_update,
-	.finalize = &aesni_gcm_finalize,
-};
-
 asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv,
 		void *keys, u8 *out, unsigned int num_bytes);
 asmlinkage void aes_ctr_enc_192_avx_by8(const u8 *in, u8 *iv,
@@ -214,25 +158,6 @@ asmlinkage void aesni_gcm_finalize_avx_gen2(void *ctx,
 				   struct gcm_context_data *gdata,
 				   u8 *auth_tag, unsigned long auth_tag_len);
 
-asmlinkage void aesni_gcm_enc_avx_gen2(void *ctx,
-				struct gcm_context_data *gdata, u8 *out,
-			const u8 *in, unsigned long plaintext_len, u8 *iv,
-			const u8 *aad, unsigned long aad_len,
-			u8 *auth_tag, unsigned long auth_tag_len);
-
-asmlinkage void aesni_gcm_dec_avx_gen2(void *ctx,
-				struct gcm_context_data *gdata, u8 *out,
-			const u8 *in, unsigned long ciphertext_len, u8 *iv,
-			const u8 *aad, unsigned long aad_len,
-			u8 *auth_tag, unsigned long auth_tag_len);
-
-static const struct aesni_gcm_tfm_s aesni_gcm_tfm_avx_gen2 = {
-	.init = &aesni_gcm_init_avx_gen2,
-	.enc_update = &aesni_gcm_enc_update_avx_gen2,
-	.dec_update = &aesni_gcm_dec_update_avx_gen2,
-	.finalize = &aesni_gcm_finalize_avx_gen2,
-};
-
 /*
  * asmlinkage void aesni_gcm_init_avx_gen4()
  * gcm_data *my_ctx_data, context data
@@ -256,24 +181,8 @@ asmlinkage void aesni_gcm_finalize_avx_gen4(void *ctx,
 				   struct gcm_context_data *gdata,
 				   u8 *auth_tag, unsigned long auth_tag_len);
 
-asmlinkage void aesni_gcm_enc_avx_gen4(void *ctx,
-				struct gcm_context_data *gdata, u8 *out,
-			const u8 *in, unsigned long plaintext_len, u8 *iv,
-			const u8 *aad, unsigned long aad_len,
-			u8 *auth_tag, unsigned long auth_tag_len);
-
-asmlinkage void aesni_gcm_dec_avx_gen4(void *ctx,
-				struct gcm_context_data *gdata, u8 *out,
-			const u8 *in, unsigned long ciphertext_len, u8 *iv,
-			const u8 *aad, unsigned long aad_len,
-			u8 *auth_tag, unsigned long auth_tag_len);
-
-static const struct aesni_gcm_tfm_s aesni_gcm_tfm_avx_gen4 = {
-	.init = &aesni_gcm_init_avx_gen4,
-	.enc_update = &aesni_gcm_enc_update_avx_gen4,
-	.dec_update = &aesni_gcm_dec_update_avx_gen4,
-	.finalize = &aesni_gcm_finalize_avx_gen4,
-};
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(gcm_use_avx);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(gcm_use_avx2);
 
 static inline struct
 aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm)
@@ -374,16 +283,16 @@ static int ecb_encrypt(struct skcipher_request *req)
 	unsigned int nbytes;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
+		kernel_fpu_begin();
 		aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
 			      nbytes & AES_BLOCK_MASK);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = skcipher_walk_done(&walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -396,16 +305,16 @@ static int ecb_decrypt(struct skcipher_request *req)
 	unsigned int nbytes;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
+		kernel_fpu_begin();
 		aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
 			      nbytes & AES_BLOCK_MASK);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = skcipher_walk_done(&walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -418,16 +327,16 @@ static int cbc_encrypt(struct skcipher_request *req)
 	unsigned int nbytes;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
+		kernel_fpu_begin();
 		aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
 			      nbytes & AES_BLOCK_MASK, walk.iv);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = skcipher_walk_done(&walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -440,36 +349,133 @@ static int cbc_decrypt(struct skcipher_request *req)
 	unsigned int nbytes;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
+		kernel_fpu_begin();
 		aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
 			      nbytes & AES_BLOCK_MASK, walk.iv);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = skcipher_walk_done(&walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
 
-#ifdef CONFIG_X86_64
-static void ctr_crypt_final(struct crypto_aes_ctx *ctx,
-			    struct skcipher_walk *walk)
+static int cts_cbc_encrypt(struct skcipher_request *req)
 {
-	u8 *ctrblk = walk->iv;
-	u8 keystream[AES_BLOCK_SIZE];
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	unsigned int nbytes = walk->nbytes;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
+	int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+	struct scatterlist *src = req->src, *dst = req->dst;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct skcipher_walk walk;
+	int err;
+
+	skcipher_request_set_tfm(&subreq, tfm);
+	skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
+				      NULL, NULL);
+
+	if (req->cryptlen <= AES_BLOCK_SIZE) {
+		if (req->cryptlen < AES_BLOCK_SIZE)
+			return -EINVAL;
+		cbc_blocks = 1;
+	}
+
+	if (cbc_blocks > 0) {
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   cbc_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+
+		err = cbc_encrypt(&subreq);
+		if (err)
+			return err;
+
+		if (req->cryptlen == AES_BLOCK_SIZE)
+			return 0;
+
+		dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
+		if (req->dst != req->src)
+			dst = scatterwalk_ffwd(sg_dst, req->dst,
+					       subreq.cryptlen);
+	}
+
+	/* handle ciphertext stealing */
+	skcipher_request_set_crypt(&subreq, src, dst,
+				   req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+	kernel_fpu_begin();
+	aesni_cts_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+			  walk.nbytes, walk.iv);
+	kernel_fpu_end();
+
+	return skcipher_walk_done(&walk, 0);
+}
+
+static int cts_cbc_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
+	int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+	struct scatterlist *src = req->src, *dst = req->dst;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct skcipher_walk walk;
+	int err;
+
+	skcipher_request_set_tfm(&subreq, tfm);
+	skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
+				      NULL, NULL);
+
+	if (req->cryptlen <= AES_BLOCK_SIZE) {
+		if (req->cryptlen < AES_BLOCK_SIZE)
+			return -EINVAL;
+		cbc_blocks = 1;
+	}
+
+	if (cbc_blocks > 0) {
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   cbc_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+
+		err = cbc_decrypt(&subreq);
+		if (err)
+			return err;
+
+		if (req->cryptlen == AES_BLOCK_SIZE)
+			return 0;
+
+		dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
+		if (req->dst != req->src)
+			dst = scatterwalk_ffwd(sg_dst, req->dst,
+					       subreq.cryptlen);
+	}
+
+	/* handle ciphertext stealing */
+	skcipher_request_set_crypt(&subreq, src, dst,
+				   req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+				   req->iv);
 
-	aesni_enc(ctx, keystream, ctrblk);
-	crypto_xor_cpy(dst, keystream, src, nbytes);
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+	kernel_fpu_begin();
+	aesni_cts_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+			  walk.nbytes, walk.iv);
+	kernel_fpu_end();
 
-	crypto_inc(ctrblk, AES_BLOCK_SIZE);
+	return skcipher_walk_done(&walk, 0);
 }
 
+#ifdef CONFIG_X86_64
 static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv)
 {
@@ -491,120 +497,36 @@ static int ctr_crypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
+	u8 keystream[AES_BLOCK_SIZE];
 	struct skcipher_walk walk;
 	unsigned int nbytes;
 	int err;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_fpu_begin();
-	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
-		aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr,
-			              nbytes & AES_BLOCK_MASK, walk.iv);
-		nbytes &= AES_BLOCK_SIZE - 1;
+	while ((nbytes = walk.nbytes) > 0) {
+		kernel_fpu_begin();
+		if (nbytes & AES_BLOCK_MASK)
+			static_call(aesni_ctr_enc_tfm)(ctx, walk.dst.virt.addr,
+						       walk.src.virt.addr,
+						       nbytes & AES_BLOCK_MASK,
+						       walk.iv);
+		nbytes &= ~AES_BLOCK_MASK;
+
+		if (walk.nbytes == walk.total && nbytes > 0) {
+			aesni_enc(ctx, keystream, walk.iv);
+			crypto_xor_cpy(walk.dst.virt.addr + walk.nbytes - nbytes,
+				       walk.src.virt.addr + walk.nbytes - nbytes,
+				       keystream, nbytes);
+			crypto_inc(walk.iv, AES_BLOCK_SIZE);
+			nbytes = 0;
+		}
+		kernel_fpu_end();
 		err = skcipher_walk_done(&walk, nbytes);
 	}
-	if (walk.nbytes) {
-		ctr_crypt_final(ctx, &walk);
-		err = skcipher_walk_done(&walk, 0);
-	}
-	kernel_fpu_end();
-
 	return err;
 }
 
-static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			    unsigned int keylen)
-{
-	struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err;
-
-	err = xts_verify_key(tfm, key, keylen);
-	if (err)
-		return err;
-
-	keylen /= 2;
-
-	/* first half of xts-key is for crypt */
-	err = aes_set_key_common(crypto_skcipher_tfm(tfm), ctx->raw_crypt_ctx,
-				 key, keylen);
-	if (err)
-		return err;
-
-	/* second half of xts-key is for tweak */
-	return aes_set_key_common(crypto_skcipher_tfm(tfm), ctx->raw_tweak_ctx,
-				  key + keylen, keylen);
-}
-
-
-static void aesni_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	glue_xts_crypt_128bit_one(ctx, dst, src, iv, aesni_enc);
-}
-
-static void aesni_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	glue_xts_crypt_128bit_one(ctx, dst, src, iv, aesni_dec);
-}
-
-static void aesni_xts_enc8(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	aesni_xts_crypt8(ctx, dst, src, true, iv);
-}
-
-static void aesni_xts_dec8(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	aesni_xts_crypt8(ctx, dst, src, false, iv);
-}
-
-static const struct common_glue_ctx aesni_enc_xts = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = 1,
-
-	.funcs = { {
-		.num_blocks = 8,
-		.fn_u = { .xts = aesni_xts_enc8 }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = aesni_xts_enc }
-	} }
-};
-
-static const struct common_glue_ctx aesni_dec_xts = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = 1,
-
-	.funcs = { {
-		.num_blocks = 8,
-		.fn_u = { .xts = aesni_xts_dec8 }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = aesni_xts_dec }
-	} }
-};
-
-static int xts_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&aesni_enc_xts, req, aesni_enc,
-				   aes_ctx(ctx->raw_tweak_ctx),
-				   aes_ctx(ctx->raw_crypt_ctx),
-				   false);
-}
-
-static int xts_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&aesni_dec_xts, req, aesni_enc,
-				   aes_ctx(ctx->raw_tweak_ctx),
-				   aes_ctx(ctx->raw_crypt_ctx),
-				   true);
-}
-
 static int
 rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
 {
@@ -681,42 +603,35 @@ static int generic_gcmaes_set_authsize(struct crypto_aead *tfm,
 
 static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req,
 			      unsigned int assoclen, u8 *hash_subkey,
-			      u8 *iv, void *aes_ctx)
+			      u8 *iv, void *aes_ctx, u8 *auth_tag,
+			      unsigned long auth_tag_len)
 {
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
-	const struct aesni_gcm_tfm_s *gcm_tfm = aesni_gcm_tfm;
-	struct gcm_context_data data AESNI_ALIGN_ATTR;
-	struct scatter_walk dst_sg_walk = {};
+	u8 databuf[sizeof(struct gcm_context_data) + (AESNI_ALIGN - 8)] __aligned(8);
+	struct gcm_context_data *data = PTR_ALIGN((void *)databuf, AESNI_ALIGN);
 	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;
+	struct skcipher_walk walk;
+	bool do_avx, do_avx2;
 	u8 *assocmem = NULL;
-	u8 authTag[16];
+	u8 *assoc;
+	int err;
 
 	if (!enc)
 		left -= auth_tag_len;
 
-	if (left < AVX_GEN4_OPTSIZE && gcm_tfm == &aesni_gcm_tfm_avx_gen4)
-		gcm_tfm = &aesni_gcm_tfm_avx_gen2;
-	if (left < AVX_GEN2_OPTSIZE && gcm_tfm == &aesni_gcm_tfm_avx_gen2)
-		gcm_tfm = &aesni_gcm_tfm_sse;
+	do_avx = (left >= AVX_GEN2_OPTSIZE);
+	do_avx2 = (left >= AVX_GEN4_OPTSIZE);
 
 	/* 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)) {
+	if (req->src->length >= assoclen && req->src->length) {
 		scatterwalk_start(&assoc_sg_walk, req->src);
 		assoc = scatterwalk_map(&assoc_sg_walk);
 	} else {
+		gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			      GFP_KERNEL : GFP_ATOMIC;
+
 		/* assoc can be any length, so must be on heap */
-		assocmem = kmalloc(assoclen, GFP_ATOMIC);
+		assocmem = kmalloc(assoclen, flags);
 		if (unlikely(!assocmem))
 			return -ENOMEM;
 		assoc = assocmem;
@@ -724,62 +639,15 @@ static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req,
 		scatterwalk_map_and_copy(assoc, req->src, 0, assoclen, 0);
 	}
 
-	if (left) {
-		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();
-	gcm_tfm->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)
-					gcm_tfm->enc_update(aes_ctx, &data,
-							     dst, src, len);
-				else
-					gcm_tfm->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)
-					gcm_tfm->enc_update(aes_ctx, &data,
-							     src, src, len);
-				else
-					gcm_tfm->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);
-		}
-	}
-	gcm_tfm->finalize(aes_ctx, &data, authTag, auth_tag_len);
+	if (static_branch_likely(&gcm_use_avx2) && do_avx2)
+		aesni_gcm_init_avx_gen4(aes_ctx, data, iv, hash_subkey, assoc,
+					assoclen);
+	else if (static_branch_likely(&gcm_use_avx) && do_avx)
+		aesni_gcm_init_avx_gen2(aes_ctx, data, iv, hash_subkey, assoc,
+					assoclen);
+	else
+		aesni_gcm_init(aes_ctx, data, iv, hash_subkey, assoc, assoclen);
 	kernel_fpu_end();
 
 	if (!assocmem)
@@ -787,24 +655,58 @@ static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req,
 	else
 		kfree(assocmem);
 
-	if (!enc) {
-		u8 authTagMsg[16];
+	err = enc ? skcipher_walk_aead_encrypt(&walk, req, false)
+		  : skcipher_walk_aead_decrypt(&walk, req, false);
 
-		/* Copy out original authTag */
-		scatterwalk_map_and_copy(authTagMsg, req->src,
-					 req->assoclen + req->cryptlen -
-					 auth_tag_len,
-					 auth_tag_len, 0);
+	while (walk.nbytes > 0) {
+		kernel_fpu_begin();
+		if (static_branch_likely(&gcm_use_avx2) && do_avx2) {
+			if (enc)
+				aesni_gcm_enc_update_avx_gen4(aes_ctx, data,
+							      walk.dst.virt.addr,
+							      walk.src.virt.addr,
+							      walk.nbytes);
+			else
+				aesni_gcm_dec_update_avx_gen4(aes_ctx, data,
+							      walk.dst.virt.addr,
+							      walk.src.virt.addr,
+							      walk.nbytes);
+		} else if (static_branch_likely(&gcm_use_avx) && do_avx) {
+			if (enc)
+				aesni_gcm_enc_update_avx_gen2(aes_ctx, data,
+							      walk.dst.virt.addr,
+							      walk.src.virt.addr,
+							      walk.nbytes);
+			else
+				aesni_gcm_dec_update_avx_gen2(aes_ctx, data,
+							      walk.dst.virt.addr,
+							      walk.src.virt.addr,
+							      walk.nbytes);
+		} else if (enc) {
+			aesni_gcm_enc_update(aes_ctx, data, walk.dst.virt.addr,
+					     walk.src.virt.addr, walk.nbytes);
+		} else {
+			aesni_gcm_dec_update(aes_ctx, data, walk.dst.virt.addr,
+					     walk.src.virt.addr, walk.nbytes);
+		}
+		kernel_fpu_end();
 
-		/* Compare generated tag with passed in tag. */
-		return crypto_memneq(authTagMsg, authTag, auth_tag_len) ?
-			-EBADMSG : 0;
+		err = skcipher_walk_done(&walk, 0);
 	}
 
-	/* Copy in the authTag */
-	scatterwalk_map_and_copy(authTag, req->dst,
-				 req->assoclen + req->cryptlen,
-				 auth_tag_len, 1);
+	if (err)
+		return err;
+
+	kernel_fpu_begin();
+	if (static_branch_likely(&gcm_use_avx2) && do_avx2)
+		aesni_gcm_finalize_avx_gen4(aes_ctx, data, auth_tag,
+					    auth_tag_len);
+	else if (static_branch_likely(&gcm_use_avx) && do_avx)
+		aesni_gcm_finalize_avx_gen2(aes_ctx, data, auth_tag,
+					    auth_tag_len);
+	else
+		aesni_gcm_finalize(aes_ctx, data, auth_tag, auth_tag_len);
+	kernel_fpu_end();
 
 	return 0;
 }
@@ -812,15 +714,47 @@ static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req,
 static int gcmaes_encrypt(struct aead_request *req, unsigned int assoclen,
 			  u8 *hash_subkey, u8 *iv, void *aes_ctx)
 {
-	return gcmaes_crypt_by_sg(true, req, assoclen, hash_subkey, iv,
-				aes_ctx);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
+	u8 auth_tag[16];
+	int err;
+
+	err = gcmaes_crypt_by_sg(true, req, assoclen, hash_subkey, iv, aes_ctx,
+				 auth_tag, auth_tag_len);
+	if (err)
+		return err;
+
+	scatterwalk_map_and_copy(auth_tag, req->dst,
+				 req->assoclen + req->cryptlen,
+				 auth_tag_len, 1);
+	return 0;
 }
 
 static int gcmaes_decrypt(struct aead_request *req, unsigned int assoclen,
 			  u8 *hash_subkey, u8 *iv, void *aes_ctx)
 {
-	return gcmaes_crypt_by_sg(false, req, assoclen, hash_subkey, iv,
-				aes_ctx);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
+	u8 auth_tag_msg[16];
+	u8 auth_tag[16];
+	int err;
+
+	err = gcmaes_crypt_by_sg(false, req, assoclen, hash_subkey, iv, aes_ctx,
+				 auth_tag, auth_tag_len);
+	if (err)
+		return err;
+
+	/* Copy out original auth_tag */
+	scatterwalk_map_and_copy(auth_tag_msg, req->src,
+				 req->assoclen + req->cryptlen - auth_tag_len,
+				 auth_tag_len, 0);
+
+	/* Compare generated tag with passed in tag. */
+	if (crypto_memneq(auth_tag_msg, auth_tag, auth_tag_len)) {
+		memzero_explicit(auth_tag, sizeof(auth_tag));
+		return -EBADMSG;
+	}
+	return 0;
 }
 
 static int helper_rfc4106_encrypt(struct aead_request *req)
@@ -828,7 +762,8 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
 	void *aes_ctx = &(ctx->aes_key_expanded);
-	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8);
+	u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN);
 	unsigned int i;
 	__be32 counter = cpu_to_be32(1);
 
@@ -855,7 +790,8 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
 	void *aes_ctx = &(ctx->aes_key_expanded);
-	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8);
+	u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN);
 	unsigned int i;
 
 	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
@@ -877,6 +813,128 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 }
 #endif
 
+static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			    unsigned int keylen)
+{
+	struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = xts_verify_key(tfm, key, keylen);
+	if (err)
+		return err;
+
+	keylen /= 2;
+
+	/* first half of xts-key is for crypt */
+	err = aes_set_key_common(crypto_skcipher_tfm(tfm), ctx->raw_crypt_ctx,
+				 key, keylen);
+	if (err)
+		return err;
+
+	/* second half of xts-key is for tweak */
+	return aes_set_key_common(crypto_skcipher_tfm(tfm), ctx->raw_tweak_ctx,
+				  key + keylen, keylen);
+}
+
+static int xts_crypt(struct skcipher_request *req, bool encrypt)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	struct skcipher_request subreq;
+	struct skcipher_walk walk;
+	int err;
+
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
+		int blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+
+		skcipher_walk_abort(&walk);
+
+		skcipher_request_set_tfm(&subreq, tfm);
+		skcipher_request_set_callback(&subreq,
+					      skcipher_request_flags(req),
+					      NULL, NULL);
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   blocks * AES_BLOCK_SIZE, req->iv);
+		req = &subreq;
+		err = skcipher_walk_virt(&walk, req, false);
+	} else {
+		tail = 0;
+	}
+
+	kernel_fpu_begin();
+
+	/* calculate first value of T */
+	aesni_enc(aes_ctx(ctx->raw_tweak_ctx), walk.iv, walk.iv);
+
+	while (walk.nbytes > 0) {
+		int nbytes = walk.nbytes;
+
+		if (nbytes < walk.total)
+			nbytes &= ~(AES_BLOCK_SIZE - 1);
+
+		if (encrypt)
+			aesni_xts_encrypt(aes_ctx(ctx->raw_crypt_ctx),
+					  walk.dst.virt.addr, walk.src.virt.addr,
+					  nbytes, walk.iv);
+		else
+			aesni_xts_decrypt(aes_ctx(ctx->raw_crypt_ctx),
+					  walk.dst.virt.addr, walk.src.virt.addr,
+					  nbytes, walk.iv);
+		kernel_fpu_end();
+
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+
+		if (walk.nbytes > 0)
+			kernel_fpu_begin();
+	}
+
+	if (unlikely(tail > 0 && !err)) {
+		struct scatterlist sg_src[2], sg_dst[2];
+		struct scatterlist *src, *dst;
+
+		dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+		if (req->dst != req->src)
+			dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+
+		skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+					   req->iv);
+
+		err = skcipher_walk_virt(&walk, &subreq, false);
+		if (err)
+			return err;
+
+		kernel_fpu_begin();
+		if (encrypt)
+			aesni_xts_encrypt(aes_ctx(ctx->raw_crypt_ctx),
+					  walk.dst.virt.addr, walk.src.virt.addr,
+					  walk.nbytes, walk.iv);
+		else
+			aesni_xts_decrypt(aes_ctx(ctx->raw_crypt_ctx),
+					  walk.dst.virt.addr, walk.src.virt.addr,
+					  walk.nbytes, walk.iv);
+		kernel_fpu_end();
+
+		err = skcipher_walk_done(&walk, 0);
+	}
+	return err;
+}
+
+static int xts_encrypt(struct skcipher_request *req)
+{
+	return xts_crypt(req, true);
+}
+
+static int xts_decrypt(struct skcipher_request *req)
+{
+	return xts_crypt(req, false);
+}
+
 static struct crypto_alg aesni_cipher_alg = {
 	.cra_name		= "aes",
 	.cra_driver_name	= "aes-aesni",
@@ -928,6 +986,23 @@ static struct skcipher_alg aesni_skciphers[] = {
 		.setkey		= aesni_skcipher_setkey,
 		.encrypt	= cbc_encrypt,
 		.decrypt	= cbc_decrypt,
+	}, {
+		.base = {
+			.cra_name		= "__cts(cbc(aes))",
+			.cra_driver_name	= "__cts-cbc-aes-aesni",
+			.cra_priority		= 400,
+			.cra_flags		= CRYPTO_ALG_INTERNAL,
+			.cra_blocksize		= AES_BLOCK_SIZE,
+			.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
+			.cra_module		= THIS_MODULE,
+		},
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.walksize	= 2 * AES_BLOCK_SIZE,
+		.setkey		= aesni_skcipher_setkey,
+		.encrypt	= cts_cbc_encrypt,
+		.decrypt	= cts_cbc_decrypt,
 #ifdef CONFIG_X86_64
 	}, {
 		.base = {
@@ -946,6 +1021,7 @@ static struct skcipher_alg aesni_skciphers[] = {
 		.setkey		= aesni_skcipher_setkey,
 		.encrypt	= ctr_crypt,
 		.decrypt	= ctr_crypt,
+#endif
 	}, {
 		.base = {
 			.cra_name		= "__xts(aes)",
@@ -959,10 +1035,10 @@ static struct skcipher_alg aesni_skciphers[] = {
 		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
 		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
 		.ivsize		= AES_BLOCK_SIZE,
+		.walksize	= 2 * AES_BLOCK_SIZE,
 		.setkey		= xts_aesni_setkey,
 		.encrypt	= xts_encrypt,
 		.decrypt	= xts_decrypt,
-#endif
 	}
 };
 
@@ -985,7 +1061,8 @@ static int generic_gcmaes_encrypt(struct aead_request *req)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm);
 	void *aes_ctx = &(ctx->aes_key_expanded);
-	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8);
+	u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN);
 	__be32 counter = cpu_to_be32(1);
 
 	memcpy(iv, req->iv, 12);
@@ -1001,7 +1078,8 @@ static int generic_gcmaes_decrypt(struct aead_request *req)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm);
 	void *aes_ctx = &(ctx->aes_key_expanded);
-	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8);
+	u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN);
 
 	memcpy(iv, req->iv, 12);
 	*((__be32 *)(iv+12)) = counter;
@@ -1066,19 +1144,18 @@ static int __init aesni_init(void)
 #ifdef CONFIG_X86_64
 	if (boot_cpu_has(X86_FEATURE_AVX2)) {
 		pr_info("AVX2 version of gcm_enc/dec engaged.\n");
-		aesni_gcm_tfm = &aesni_gcm_tfm_avx_gen4;
+		static_branch_enable(&gcm_use_avx);
+		static_branch_enable(&gcm_use_avx2);
 	} else
 	if (boot_cpu_has(X86_FEATURE_AVX)) {
 		pr_info("AVX version of gcm_enc/dec engaged.\n");
-		aesni_gcm_tfm = &aesni_gcm_tfm_avx_gen2;
+		static_branch_enable(&gcm_use_avx);
 	} else {
 		pr_info("SSE version of gcm_enc/dec engaged.\n");
-		aesni_gcm_tfm = &aesni_gcm_tfm_sse;
 	}
-	aesni_ctr_enc_tfm = aesni_ctr_enc;
 	if (boot_cpu_has(X86_FEATURE_AVX)) {
 		/* optimize performance of ctr mode encryption transform */
-		aesni_ctr_enc_tfm = aesni_ctr_enc_avx_tfm;
+		static_call_update(aesni_ctr_enc_tfm, aesni_ctr_enc_avx_tfm);
 		pr_info("AES CTR mode by8 optimization enabled\n");
 	}
 #endif
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
index c025a01cf708..a40365ab301e 100644
--- a/arch/x86/crypto/blake2s-glue.c
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -58,138 +58,40 @@ void blake2s_compress_arch(struct blake2s_state *state,
 }
 EXPORT_SYMBOL(blake2s_compress_arch);
 
-static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key,
-				 unsigned int keylen)
+static int crypto_blake2s_update_x86(struct shash_desc *desc,
+				     const u8 *in, unsigned int inlen)
 {
-	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm);
-
-	if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE)
-		return -EINVAL;
-
-	memcpy(tctx->key, key, keylen);
-	tctx->keylen = keylen;
-
-	return 0;
+	return crypto_blake2s_update(desc, in, inlen, blake2s_compress_arch);
 }
 
-static int crypto_blake2s_init(struct shash_desc *desc)
+static int crypto_blake2s_final_x86(struct shash_desc *desc, u8 *out)
 {
-	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
-	struct blake2s_state *state = shash_desc_ctx(desc);
-	const int outlen = crypto_shash_digestsize(desc->tfm);
-
-	if (tctx->keylen)
-		blake2s_init_key(state, outlen, tctx->key, tctx->keylen);
-	else
-		blake2s_init(state, outlen);
-
-	return 0;
+	return crypto_blake2s_final(desc, out, blake2s_compress_arch);
 }
 
-static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in,
-				 unsigned int inlen)
-{
-	struct blake2s_state *state = shash_desc_ctx(desc);
-	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
-
-	if (unlikely(!inlen))
-		return 0;
-	if (inlen > fill) {
-		memcpy(state->buf + state->buflen, in, fill);
-		blake2s_compress_arch(state, state->buf, 1, BLAKE2S_BLOCK_SIZE);
-		state->buflen = 0;
-		in += fill;
-		inlen -= fill;
+#define BLAKE2S_ALG(name, driver_name, digest_size)			\
+	{								\
+		.base.cra_name		= name,				\
+		.base.cra_driver_name	= driver_name,			\
+		.base.cra_priority	= 200,				\
+		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,	\
+		.base.cra_blocksize	= BLAKE2S_BLOCK_SIZE,		\
+		.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx), \
+		.base.cra_module	= THIS_MODULE,			\
+		.digestsize		= digest_size,			\
+		.setkey			= crypto_blake2s_setkey,	\
+		.init			= crypto_blake2s_init,		\
+		.update			= crypto_blake2s_update_x86,	\
+		.final			= crypto_blake2s_final_x86,	\
+		.descsize		= sizeof(struct blake2s_state),	\
 	}
-	if (inlen > BLAKE2S_BLOCK_SIZE) {
-		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
-		/* Hash one less (full) block than strictly possible */
-		blake2s_compress_arch(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE);
-		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
-		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
-	}
-	memcpy(state->buf + state->buflen, in, inlen);
-	state->buflen += inlen;
-
-	return 0;
-}
-
-static int crypto_blake2s_final(struct shash_desc *desc, u8 *out)
-{
-	struct blake2s_state *state = shash_desc_ctx(desc);
-
-	blake2s_set_lastblock(state);
-	memset(state->buf + state->buflen, 0,
-	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
-	blake2s_compress_arch(state, state->buf, 1, state->buflen);
-	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
-	memcpy(out, state->h, state->outlen);
-	memzero_explicit(state, sizeof(*state));
-
-	return 0;
-}
 
-static struct shash_alg blake2s_algs[] = {{
-	.base.cra_name		= "blake2s-128",
-	.base.cra_driver_name	= "blake2s-128-x86",
-	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
-	.base.cra_priority	= 200,
-	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-
-	.digestsize		= BLAKE2S_128_HASH_SIZE,
-	.setkey			= crypto_blake2s_setkey,
-	.init			= crypto_blake2s_init,
-	.update			= crypto_blake2s_update,
-	.final			= crypto_blake2s_final,
-	.descsize		= sizeof(struct blake2s_state),
-}, {
-	.base.cra_name		= "blake2s-160",
-	.base.cra_driver_name	= "blake2s-160-x86",
-	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
-	.base.cra_priority	= 200,
-	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-
-	.digestsize		= BLAKE2S_160_HASH_SIZE,
-	.setkey			= crypto_blake2s_setkey,
-	.init			= crypto_blake2s_init,
-	.update			= crypto_blake2s_update,
-	.final			= crypto_blake2s_final,
-	.descsize		= sizeof(struct blake2s_state),
-}, {
-	.base.cra_name		= "blake2s-224",
-	.base.cra_driver_name	= "blake2s-224-x86",
-	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
-	.base.cra_priority	= 200,
-	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-
-	.digestsize		= BLAKE2S_224_HASH_SIZE,
-	.setkey			= crypto_blake2s_setkey,
-	.init			= crypto_blake2s_init,
-	.update			= crypto_blake2s_update,
-	.final			= crypto_blake2s_final,
-	.descsize		= sizeof(struct blake2s_state),
-}, {
-	.base.cra_name		= "blake2s-256",
-	.base.cra_driver_name	= "blake2s-256-x86",
-	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
-	.base.cra_priority	= 200,
-	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-
-	.digestsize		= BLAKE2S_256_HASH_SIZE,
-	.setkey			= crypto_blake2s_setkey,
-	.init			= crypto_blake2s_init,
-	.update			= crypto_blake2s_update,
-	.final			= crypto_blake2s_final,
-	.descsize		= sizeof(struct blake2s_state),
-}};
+static struct shash_alg blake2s_algs[] = {
+	BLAKE2S_ALG("blake2s-128", "blake2s-128-x86", BLAKE2S_128_HASH_SIZE),
+	BLAKE2S_ALG("blake2s-160", "blake2s-160-x86", BLAKE2S_160_HASH_SIZE),
+	BLAKE2S_ALG("blake2s-224", "blake2s-224-x86", BLAKE2S_224_HASH_SIZE),
+	BLAKE2S_ALG("blake2s-256", "blake2s-256-x86", BLAKE2S_256_HASH_SIZE),
+};
 
 static int __init blake2s_mod_init(void)
 {
diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c
index cedfdba69ce3..a880e0b1c255 100644
--- a/arch/x86/crypto/blowfish_glue.c
+++ b/arch/x86/crypto/blowfish_glue.c
@@ -6,8 +6,6 @@
  *
  * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
  *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
- * CTR part based on code (crypto/ctr.c) by:
- *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
  */
 
 #include <crypto/algapi.h>
@@ -247,97 +245,6 @@ static int cbc_decrypt(struct skcipher_request *req)
 	return err;
 }
 
-static void ctr_crypt_final(struct bf_ctx *ctx, struct skcipher_walk *walk)
-{
-	u8 *ctrblk = walk->iv;
-	u8 keystream[BF_BLOCK_SIZE];
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	unsigned int nbytes = walk->nbytes;
-
-	blowfish_enc_blk(ctx, keystream, ctrblk);
-	crypto_xor_cpy(dst, keystream, src, nbytes);
-
-	crypto_inc(ctrblk, BF_BLOCK_SIZE);
-}
-
-static unsigned int __ctr_crypt(struct bf_ctx *ctx, struct skcipher_walk *walk)
-{
-	unsigned int bsize = BF_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u64 *src = (u64 *)walk->src.virt.addr;
-	u64 *dst = (u64 *)walk->dst.virt.addr;
-	u64 ctrblk = be64_to_cpu(*(__be64 *)walk->iv);
-	__be64 ctrblocks[4];
-
-	/* Process four block batch */
-	if (nbytes >= bsize * 4) {
-		do {
-			if (dst != src) {
-				dst[0] = src[0];
-				dst[1] = src[1];
-				dst[2] = src[2];
-				dst[3] = src[3];
-			}
-
-			/* create ctrblks for parallel encrypt */
-			ctrblocks[0] = cpu_to_be64(ctrblk++);
-			ctrblocks[1] = cpu_to_be64(ctrblk++);
-			ctrblocks[2] = cpu_to_be64(ctrblk++);
-			ctrblocks[3] = cpu_to_be64(ctrblk++);
-
-			blowfish_enc_blk_xor_4way(ctx, (u8 *)dst,
-						  (u8 *)ctrblocks);
-
-			src += 4;
-			dst += 4;
-		} while ((nbytes -= bsize * 4) >= bsize * 4);
-
-		if (nbytes < bsize)
-			goto done;
-	}
-
-	/* Handle leftovers */
-	do {
-		if (dst != src)
-			*dst = *src;
-
-		ctrblocks[0] = cpu_to_be64(ctrblk++);
-
-		blowfish_enc_blk_xor(ctx, (u8 *)dst, (u8 *)ctrblocks);
-
-		src += 1;
-		dst += 1;
-	} while ((nbytes -= bsize) >= bsize);
-
-done:
-	*(__be64 *)walk->iv = cpu_to_be64(ctrblk);
-	return nbytes;
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	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 = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes) >= BF_BLOCK_SIZE) {
-		nbytes = __ctr_crypt(ctx, &walk);
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	if (nbytes) {
-		ctr_crypt_final(ctx, &walk);
-		err = skcipher_walk_done(&walk, 0);
-	}
-
-	return err;
-}
-
 static struct crypto_alg bf_cipher_alg = {
 	.cra_name		= "blowfish",
 	.cra_driver_name	= "blowfish-asm",
@@ -384,20 +291,6 @@ static struct skcipher_alg bf_skcipher_algs[] = {
 		.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,
 	},
 };
 
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index ecc0a9a905c4..e2a0e0f4bf9d 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -17,7 +17,6 @@
 
 #include <linux/linkage.h>
 #include <asm/frame.h>
-#include <asm/nospec-branch.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -589,14 +588,6 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	.long 0x80808080
 	.long 0x80808080
 
-/* For CTR-mode IV byteswap */
-.Lbswap128_mask:
-	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
-
-/* For XTS mode IV generation */
-.Lxts_gf128mul_and_shl1_mask:
-	.byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0
-
 /*
  * pre-SubByte transform
  *
@@ -998,292 +989,3 @@ SYM_FUNC_START(camellia_cbc_dec_16way)
 	FRAME_END
 	ret;
 SYM_FUNC_END(camellia_cbc_dec_16way)
-
-#define inc_le128(x, minus_one, tmp) \
-	vpcmpeqq minus_one, x, tmp; \
-	vpsubq minus_one, x, x; \
-	vpslldq $8, tmp, tmp; \
-	vpsubq tmp, x, x;
-
-SYM_FUNC_START(camellia_ctr_16way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (16 blocks)
-	 *	%rdx: src (16 blocks)
-	 *	%rcx: iv (little endian, 128bit)
-	 */
-	FRAME_BEGIN
-
-	subq $(16 * 16), %rsp;
-	movq %rsp, %rax;
-
-	vmovdqa .Lbswap128_mask, %xmm14;
-
-	/* load IV and byteswap */
-	vmovdqu (%rcx), %xmm0;
-	vpshufb %xmm14, %xmm0, %xmm15;
-	vmovdqu %xmm15, 15 * 16(%rax);
-
-	vpcmpeqd %xmm15, %xmm15, %xmm15;
-	vpsrldq $8, %xmm15, %xmm15; /* low: -1, high: 0 */
-
-	/* construct IVs */
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm13;
-	vmovdqu %xmm13, 14 * 16(%rax);
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm13;
-	vmovdqu %xmm13, 13 * 16(%rax);
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm12;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm11;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm10;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm9;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm8;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm7;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm6;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm5;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm4;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm3;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm2;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vpshufb %xmm14, %xmm0, %xmm1;
-	inc_le128(%xmm0, %xmm15, %xmm13);
-	vmovdqa %xmm0, %xmm13;
-	vpshufb %xmm14, %xmm0, %xmm0;
-	inc_le128(%xmm13, %xmm15, %xmm14);
-	vmovdqu %xmm13, (%rcx);
-
-	/* inpack16_pre: */
-	vmovq (key_table)(CTX), %xmm15;
-	vpshufb .Lpack_bswap, %xmm15, %xmm15;
-	vpxor %xmm0, %xmm15, %xmm0;
-	vpxor %xmm1, %xmm15, %xmm1;
-	vpxor %xmm2, %xmm15, %xmm2;
-	vpxor %xmm3, %xmm15, %xmm3;
-	vpxor %xmm4, %xmm15, %xmm4;
-	vpxor %xmm5, %xmm15, %xmm5;
-	vpxor %xmm6, %xmm15, %xmm6;
-	vpxor %xmm7, %xmm15, %xmm7;
-	vpxor %xmm8, %xmm15, %xmm8;
-	vpxor %xmm9, %xmm15, %xmm9;
-	vpxor %xmm10, %xmm15, %xmm10;
-	vpxor %xmm11, %xmm15, %xmm11;
-	vpxor %xmm12, %xmm15, %xmm12;
-	vpxor 13 * 16(%rax), %xmm15, %xmm13;
-	vpxor 14 * 16(%rax), %xmm15, %xmm14;
-	vpxor 15 * 16(%rax), %xmm15, %xmm15;
-
-	call __camellia_enc_blk16;
-
-	addq $(16 * 16), %rsp;
-
-	vpxor 0 * 16(%rdx), %xmm7, %xmm7;
-	vpxor 1 * 16(%rdx), %xmm6, %xmm6;
-	vpxor 2 * 16(%rdx), %xmm5, %xmm5;
-	vpxor 3 * 16(%rdx), %xmm4, %xmm4;
-	vpxor 4 * 16(%rdx), %xmm3, %xmm3;
-	vpxor 5 * 16(%rdx), %xmm2, %xmm2;
-	vpxor 6 * 16(%rdx), %xmm1, %xmm1;
-	vpxor 7 * 16(%rdx), %xmm0, %xmm0;
-	vpxor 8 * 16(%rdx), %xmm15, %xmm15;
-	vpxor 9 * 16(%rdx), %xmm14, %xmm14;
-	vpxor 10 * 16(%rdx), %xmm13, %xmm13;
-	vpxor 11 * 16(%rdx), %xmm12, %xmm12;
-	vpxor 12 * 16(%rdx), %xmm11, %xmm11;
-	vpxor 13 * 16(%rdx), %xmm10, %xmm10;
-	vpxor 14 * 16(%rdx), %xmm9, %xmm9;
-	vpxor 15 * 16(%rdx), %xmm8, %xmm8;
-	write_output(%xmm7, %xmm6, %xmm5, %xmm4, %xmm3, %xmm2, %xmm1, %xmm0,
-		     %xmm15, %xmm14, %xmm13, %xmm12, %xmm11, %xmm10, %xmm9,
-		     %xmm8, %rsi);
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(camellia_ctr_16way)
-
-#define gf128mul_x_ble(iv, mask, tmp) \
-	vpsrad $31, iv, tmp; \
-	vpaddq iv, iv, iv; \
-	vpshufd $0x13, tmp, tmp; \
-	vpand mask, tmp, tmp; \
-	vpxor tmp, iv, iv;
-
-.align 8
-SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (16 blocks)
-	 *	%rdx: src (16 blocks)
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 *	%r8: index for input whitening key
-	 *	%r9: pointer to  __camellia_enc_blk16 or __camellia_dec_blk16
-	 */
-	FRAME_BEGIN
-
-	subq $(16 * 16), %rsp;
-	movq %rsp, %rax;
-
-	vmovdqa .Lxts_gf128mul_and_shl1_mask, %xmm14;
-
-	/* load IV */
-	vmovdqu (%rcx), %xmm0;
-	vpxor 0 * 16(%rdx), %xmm0, %xmm15;
-	vmovdqu %xmm15, 15 * 16(%rax);
-	vmovdqu %xmm0, 0 * 16(%rsi);
-
-	/* construct IVs */
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 1 * 16(%rdx), %xmm0, %xmm15;
-	vmovdqu %xmm15, 14 * 16(%rax);
-	vmovdqu %xmm0, 1 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 2 * 16(%rdx), %xmm0, %xmm13;
-	vmovdqu %xmm0, 2 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 3 * 16(%rdx), %xmm0, %xmm12;
-	vmovdqu %xmm0, 3 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 4 * 16(%rdx), %xmm0, %xmm11;
-	vmovdqu %xmm0, 4 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 5 * 16(%rdx), %xmm0, %xmm10;
-	vmovdqu %xmm0, 5 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 6 * 16(%rdx), %xmm0, %xmm9;
-	vmovdqu %xmm0, 6 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 7 * 16(%rdx), %xmm0, %xmm8;
-	vmovdqu %xmm0, 7 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 8 * 16(%rdx), %xmm0, %xmm7;
-	vmovdqu %xmm0, 8 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 9 * 16(%rdx), %xmm0, %xmm6;
-	vmovdqu %xmm0, 9 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 10 * 16(%rdx), %xmm0, %xmm5;
-	vmovdqu %xmm0, 10 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 11 * 16(%rdx), %xmm0, %xmm4;
-	vmovdqu %xmm0, 11 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 12 * 16(%rdx), %xmm0, %xmm3;
-	vmovdqu %xmm0, 12 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 13 * 16(%rdx), %xmm0, %xmm2;
-	vmovdqu %xmm0, 13 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 14 * 16(%rdx), %xmm0, %xmm1;
-	vmovdqu %xmm0, 14 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vpxor 15 * 16(%rdx), %xmm0, %xmm15;
-	vmovdqu %xmm15, 0 * 16(%rax);
-	vmovdqu %xmm0, 15 * 16(%rsi);
-
-	gf128mul_x_ble(%xmm0, %xmm14, %xmm15);
-	vmovdqu %xmm0, (%rcx);
-
-	/* inpack16_pre: */
-	vmovq (key_table)(CTX, %r8, 8), %xmm15;
-	vpshufb .Lpack_bswap, %xmm15, %xmm15;
-	vpxor 0 * 16(%rax), %xmm15, %xmm0;
-	vpxor %xmm1, %xmm15, %xmm1;
-	vpxor %xmm2, %xmm15, %xmm2;
-	vpxor %xmm3, %xmm15, %xmm3;
-	vpxor %xmm4, %xmm15, %xmm4;
-	vpxor %xmm5, %xmm15, %xmm5;
-	vpxor %xmm6, %xmm15, %xmm6;
-	vpxor %xmm7, %xmm15, %xmm7;
-	vpxor %xmm8, %xmm15, %xmm8;
-	vpxor %xmm9, %xmm15, %xmm9;
-	vpxor %xmm10, %xmm15, %xmm10;
-	vpxor %xmm11, %xmm15, %xmm11;
-	vpxor %xmm12, %xmm15, %xmm12;
-	vpxor %xmm13, %xmm15, %xmm13;
-	vpxor 14 * 16(%rax), %xmm15, %xmm14;
-	vpxor 15 * 16(%rax), %xmm15, %xmm15;
-
-	CALL_NOSPEC r9;
-
-	addq $(16 * 16), %rsp;
-
-	vpxor 0 * 16(%rsi), %xmm7, %xmm7;
-	vpxor 1 * 16(%rsi), %xmm6, %xmm6;
-	vpxor 2 * 16(%rsi), %xmm5, %xmm5;
-	vpxor 3 * 16(%rsi), %xmm4, %xmm4;
-	vpxor 4 * 16(%rsi), %xmm3, %xmm3;
-	vpxor 5 * 16(%rsi), %xmm2, %xmm2;
-	vpxor 6 * 16(%rsi), %xmm1, %xmm1;
-	vpxor 7 * 16(%rsi), %xmm0, %xmm0;
-	vpxor 8 * 16(%rsi), %xmm15, %xmm15;
-	vpxor 9 * 16(%rsi), %xmm14, %xmm14;
-	vpxor 10 * 16(%rsi), %xmm13, %xmm13;
-	vpxor 11 * 16(%rsi), %xmm12, %xmm12;
-	vpxor 12 * 16(%rsi), %xmm11, %xmm11;
-	vpxor 13 * 16(%rsi), %xmm10, %xmm10;
-	vpxor 14 * 16(%rsi), %xmm9, %xmm9;
-	vpxor 15 * 16(%rsi), %xmm8, %xmm8;
-	write_output(%xmm7, %xmm6, %xmm5, %xmm4, %xmm3, %xmm2, %xmm1, %xmm0,
-		     %xmm15, %xmm14, %xmm13, %xmm12, %xmm11, %xmm10, %xmm9,
-		     %xmm8, %rsi);
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(camellia_xts_crypt_16way)
-
-SYM_FUNC_START(camellia_xts_enc_16way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (16 blocks)
-	 *	%rdx: src (16 blocks)
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-	xorl %r8d, %r8d; /* input whitening key, 0 for enc */
-
-	leaq __camellia_enc_blk16, %r9;
-
-	jmp camellia_xts_crypt_16way;
-SYM_FUNC_END(camellia_xts_enc_16way)
-
-SYM_FUNC_START(camellia_xts_dec_16way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (16 blocks)
-	 *	%rdx: src (16 blocks)
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-
-	cmpl $16, key_length(CTX);
-	movl $32, %r8d;
-	movl $24, %eax;
-	cmovel %eax, %r8d;  /* input whitening key, last for dec */
-
-	leaq __camellia_dec_blk16, %r9;
-
-	jmp camellia_xts_crypt_16way;
-SYM_FUNC_END(camellia_xts_dec_16way)
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index 0907243c501c..782e9712a1ec 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -7,7 +7,6 @@
 
 #include <linux/linkage.h>
 #include <asm/frame.h>
-#include <asm/nospec-branch.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -625,16 +624,6 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 .section	.rodata.cst16, "aM", @progbits, 16
 .align 16
 
-/* For CTR-mode IV byteswap */
-.Lbswap128_mask:
-	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
-
-/* For XTS mode */
-.Lxts_gf128mul_and_shl1_mask_0:
-	.byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0
-.Lxts_gf128mul_and_shl1_mask_1:
-	.byte 0x0e, 1, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0
-
 /*
  * pre-SubByte transform
  *
@@ -1061,343 +1050,3 @@ SYM_FUNC_START(camellia_cbc_dec_32way)
 	FRAME_END
 	ret;
 SYM_FUNC_END(camellia_cbc_dec_32way)
-
-#define inc_le128(x, minus_one, tmp) \
-	vpcmpeqq minus_one, x, tmp; \
-	vpsubq minus_one, x, x; \
-	vpslldq $8, tmp, tmp; \
-	vpsubq tmp, x, x;
-
-#define add2_le128(x, minus_one, minus_two, tmp1, tmp2) \
-	vpcmpeqq minus_one, x, tmp1; \
-	vpcmpeqq minus_two, x, tmp2; \
-	vpsubq minus_two, x, x; \
-	vpor tmp2, tmp1, tmp1; \
-	vpslldq $8, tmp1, tmp1; \
-	vpsubq tmp1, x, x;
-
-SYM_FUNC_START(camellia_ctr_32way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (32 blocks)
-	 *	%rdx: src (32 blocks)
-	 *	%rcx: iv (little endian, 128bit)
-	 */
-	FRAME_BEGIN
-
-	vzeroupper;
-
-	movq %rsp, %r10;
-	cmpq %rsi, %rdx;
-	je .Lctr_use_stack;
-
-	/* dst can be used as temporary storage, src is not overwritten. */
-	movq %rsi, %rax;
-	jmp .Lctr_continue;
-
-.Lctr_use_stack:
-	subq $(16 * 32), %rsp;
-	movq %rsp, %rax;
-
-.Lctr_continue:
-	vpcmpeqd %ymm15, %ymm15, %ymm15;
-	vpsrldq $8, %ymm15, %ymm15; /* ab: -1:0 ; cd: -1:0 */
-	vpaddq %ymm15, %ymm15, %ymm12; /* ab: -2:0 ; cd: -2:0 */
-
-	/* load IV and byteswap */
-	vmovdqu (%rcx), %xmm0;
-	vmovdqa %xmm0, %xmm1;
-	inc_le128(%xmm0, %xmm15, %xmm14);
-	vbroadcasti128 .Lbswap128_mask, %ymm14;
-	vinserti128 $1, %xmm0, %ymm1, %ymm0;
-	vpshufb %ymm14, %ymm0, %ymm13;
-	vmovdqu %ymm13, 15 * 32(%rax);
-
-	/* construct IVs */
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); /* ab:le2 ; cd:le3 */
-	vpshufb %ymm14, %ymm0, %ymm13;
-	vmovdqu %ymm13, 14 * 32(%rax);
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm13;
-	vmovdqu %ymm13, 13 * 32(%rax);
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm13;
-	vmovdqu %ymm13, 12 * 32(%rax);
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm13;
-	vmovdqu %ymm13, 11 * 32(%rax);
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm10;
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm9;
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm8;
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm7;
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm6;
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm5;
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm4;
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm3;
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm2;
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vpshufb %ymm14, %ymm0, %ymm1;
-	add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13);
-	vextracti128 $1, %ymm0, %xmm13;
-	vpshufb %ymm14, %ymm0, %ymm0;
-	inc_le128(%xmm13, %xmm15, %xmm14);
-	vmovdqu %xmm13, (%rcx);
-
-	/* inpack32_pre: */
-	vpbroadcastq (key_table)(CTX), %ymm15;
-	vpshufb .Lpack_bswap, %ymm15, %ymm15;
-	vpxor %ymm0, %ymm15, %ymm0;
-	vpxor %ymm1, %ymm15, %ymm1;
-	vpxor %ymm2, %ymm15, %ymm2;
-	vpxor %ymm3, %ymm15, %ymm3;
-	vpxor %ymm4, %ymm15, %ymm4;
-	vpxor %ymm5, %ymm15, %ymm5;
-	vpxor %ymm6, %ymm15, %ymm6;
-	vpxor %ymm7, %ymm15, %ymm7;
-	vpxor %ymm8, %ymm15, %ymm8;
-	vpxor %ymm9, %ymm15, %ymm9;
-	vpxor %ymm10, %ymm15, %ymm10;
-	vpxor 11 * 32(%rax), %ymm15, %ymm11;
-	vpxor 12 * 32(%rax), %ymm15, %ymm12;
-	vpxor 13 * 32(%rax), %ymm15, %ymm13;
-	vpxor 14 * 32(%rax), %ymm15, %ymm14;
-	vpxor 15 * 32(%rax), %ymm15, %ymm15;
-
-	call __camellia_enc_blk32;
-
-	movq %r10, %rsp;
-
-	vpxor 0 * 32(%rdx), %ymm7, %ymm7;
-	vpxor 1 * 32(%rdx), %ymm6, %ymm6;
-	vpxor 2 * 32(%rdx), %ymm5, %ymm5;
-	vpxor 3 * 32(%rdx), %ymm4, %ymm4;
-	vpxor 4 * 32(%rdx), %ymm3, %ymm3;
-	vpxor 5 * 32(%rdx), %ymm2, %ymm2;
-	vpxor 6 * 32(%rdx), %ymm1, %ymm1;
-	vpxor 7 * 32(%rdx), %ymm0, %ymm0;
-	vpxor 8 * 32(%rdx), %ymm15, %ymm15;
-	vpxor 9 * 32(%rdx), %ymm14, %ymm14;
-	vpxor 10 * 32(%rdx), %ymm13, %ymm13;
-	vpxor 11 * 32(%rdx), %ymm12, %ymm12;
-	vpxor 12 * 32(%rdx), %ymm11, %ymm11;
-	vpxor 13 * 32(%rdx), %ymm10, %ymm10;
-	vpxor 14 * 32(%rdx), %ymm9, %ymm9;
-	vpxor 15 * 32(%rdx), %ymm8, %ymm8;
-	write_output(%ymm7, %ymm6, %ymm5, %ymm4, %ymm3, %ymm2, %ymm1, %ymm0,
-		     %ymm15, %ymm14, %ymm13, %ymm12, %ymm11, %ymm10, %ymm9,
-		     %ymm8, %rsi);
-
-	vzeroupper;
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(camellia_ctr_32way)
-
-#define gf128mul_x_ble(iv, mask, tmp) \
-	vpsrad $31, iv, tmp; \
-	vpaddq iv, iv, iv; \
-	vpshufd $0x13, tmp, tmp; \
-	vpand mask, tmp, tmp; \
-	vpxor tmp, iv, iv;
-
-#define gf128mul_x2_ble(iv, mask1, mask2, tmp0, tmp1) \
-	vpsrad $31, iv, tmp0; \
-	vpaddq iv, iv, tmp1; \
-	vpsllq $2, iv, iv; \
-	vpshufd $0x13, tmp0, tmp0; \
-	vpsrad $31, tmp1, tmp1; \
-	vpand mask2, tmp0, tmp0; \
-	vpshufd $0x13, tmp1, tmp1; \
-	vpxor tmp0, iv, iv; \
-	vpand mask1, tmp1, tmp1; \
-	vpxor tmp1, iv, iv;
-
-.align 8
-SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (32 blocks)
-	 *	%rdx: src (32 blocks)
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 *	%r8: index for input whitening key
-	 *	%r9: pointer to  __camellia_enc_blk32 or __camellia_dec_blk32
-	 */
-	FRAME_BEGIN
-
-	vzeroupper;
-
-	subq $(16 * 32), %rsp;
-	movq %rsp, %rax;
-
-	vbroadcasti128 .Lxts_gf128mul_and_shl1_mask_0, %ymm12;
-
-	/* load IV and construct second IV */
-	vmovdqu (%rcx), %xmm0;
-	vmovdqa %xmm0, %xmm15;
-	gf128mul_x_ble(%xmm0, %xmm12, %xmm13);
-	vbroadcasti128 .Lxts_gf128mul_and_shl1_mask_1, %ymm13;
-	vinserti128 $1, %xmm0, %ymm15, %ymm0;
-	vpxor 0 * 32(%rdx), %ymm0, %ymm15;
-	vmovdqu %ymm15, 15 * 32(%rax);
-	vmovdqu %ymm0, 0 * 32(%rsi);
-
-	/* construct IVs */
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 1 * 32(%rdx), %ymm0, %ymm15;
-	vmovdqu %ymm15, 14 * 32(%rax);
-	vmovdqu %ymm0, 1 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 2 * 32(%rdx), %ymm0, %ymm15;
-	vmovdqu %ymm15, 13 * 32(%rax);
-	vmovdqu %ymm0, 2 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 3 * 32(%rdx), %ymm0, %ymm15;
-	vmovdqu %ymm15, 12 * 32(%rax);
-	vmovdqu %ymm0, 3 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 4 * 32(%rdx), %ymm0, %ymm11;
-	vmovdqu %ymm0, 4 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 5 * 32(%rdx), %ymm0, %ymm10;
-	vmovdqu %ymm0, 5 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 6 * 32(%rdx), %ymm0, %ymm9;
-	vmovdqu %ymm0, 6 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 7 * 32(%rdx), %ymm0, %ymm8;
-	vmovdqu %ymm0, 7 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 8 * 32(%rdx), %ymm0, %ymm7;
-	vmovdqu %ymm0, 8 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 9 * 32(%rdx), %ymm0, %ymm6;
-	vmovdqu %ymm0, 9 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 10 * 32(%rdx), %ymm0, %ymm5;
-	vmovdqu %ymm0, 10 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 11 * 32(%rdx), %ymm0, %ymm4;
-	vmovdqu %ymm0, 11 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 12 * 32(%rdx), %ymm0, %ymm3;
-	vmovdqu %ymm0, 12 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 13 * 32(%rdx), %ymm0, %ymm2;
-	vmovdqu %ymm0, 13 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 14 * 32(%rdx), %ymm0, %ymm1;
-	vmovdqu %ymm0, 14 * 32(%rsi);
-
-	gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15);
-	vpxor 15 * 32(%rdx), %ymm0, %ymm15;
-	vmovdqu %ymm15, 0 * 32(%rax);
-	vmovdqu %ymm0, 15 * 32(%rsi);
-
-	vextracti128 $1, %ymm0, %xmm0;
-	gf128mul_x_ble(%xmm0, %xmm12, %xmm15);
-	vmovdqu %xmm0, (%rcx);
-
-	/* inpack32_pre: */
-	vpbroadcastq (key_table)(CTX, %r8, 8), %ymm15;
-	vpshufb .Lpack_bswap, %ymm15, %ymm15;
-	vpxor 0 * 32(%rax), %ymm15, %ymm0;
-	vpxor %ymm1, %ymm15, %ymm1;
-	vpxor %ymm2, %ymm15, %ymm2;
-	vpxor %ymm3, %ymm15, %ymm3;
-	vpxor %ymm4, %ymm15, %ymm4;
-	vpxor %ymm5, %ymm15, %ymm5;
-	vpxor %ymm6, %ymm15, %ymm6;
-	vpxor %ymm7, %ymm15, %ymm7;
-	vpxor %ymm8, %ymm15, %ymm8;
-	vpxor %ymm9, %ymm15, %ymm9;
-	vpxor %ymm10, %ymm15, %ymm10;
-	vpxor %ymm11, %ymm15, %ymm11;
-	vpxor 12 * 32(%rax), %ymm15, %ymm12;
-	vpxor 13 * 32(%rax), %ymm15, %ymm13;
-	vpxor 14 * 32(%rax), %ymm15, %ymm14;
-	vpxor 15 * 32(%rax), %ymm15, %ymm15;
-
-	CALL_NOSPEC r9;
-
-	addq $(16 * 32), %rsp;
-
-	vpxor 0 * 32(%rsi), %ymm7, %ymm7;
-	vpxor 1 * 32(%rsi), %ymm6, %ymm6;
-	vpxor 2 * 32(%rsi), %ymm5, %ymm5;
-	vpxor 3 * 32(%rsi), %ymm4, %ymm4;
-	vpxor 4 * 32(%rsi), %ymm3, %ymm3;
-	vpxor 5 * 32(%rsi), %ymm2, %ymm2;
-	vpxor 6 * 32(%rsi), %ymm1, %ymm1;
-	vpxor 7 * 32(%rsi), %ymm0, %ymm0;
-	vpxor 8 * 32(%rsi), %ymm15, %ymm15;
-	vpxor 9 * 32(%rsi), %ymm14, %ymm14;
-	vpxor 10 * 32(%rsi), %ymm13, %ymm13;
-	vpxor 11 * 32(%rsi), %ymm12, %ymm12;
-	vpxor 12 * 32(%rsi), %ymm11, %ymm11;
-	vpxor 13 * 32(%rsi), %ymm10, %ymm10;
-	vpxor 14 * 32(%rsi), %ymm9, %ymm9;
-	vpxor 15 * 32(%rsi), %ymm8, %ymm8;
-	write_output(%ymm7, %ymm6, %ymm5, %ymm4, %ymm3, %ymm2, %ymm1, %ymm0,
-		     %ymm15, %ymm14, %ymm13, %ymm12, %ymm11, %ymm10, %ymm9,
-		     %ymm8, %rsi);
-
-	vzeroupper;
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(camellia_xts_crypt_32way)
-
-SYM_FUNC_START(camellia_xts_enc_32way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (32 blocks)
-	 *	%rdx: src (32 blocks)
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-
-	xorl %r8d, %r8d; /* input whitening key, 0 for enc */
-
-	leaq __camellia_enc_blk32, %r9;
-
-	jmp camellia_xts_crypt_32way;
-SYM_FUNC_END(camellia_xts_enc_32way)
-
-SYM_FUNC_START(camellia_xts_dec_32way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (32 blocks)
-	 *	%rdx: src (32 blocks)
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-
-	cmpl $16, key_length(CTX);
-	movl $32, %r8d;
-	movl $24, %eax;
-	cmovel %eax, %r8d;  /* input whitening key, last for dec */
-
-	leaq __camellia_dec_blk32, %r9;
-
-	jmp camellia_xts_crypt_32way;
-SYM_FUNC_END(camellia_xts_dec_32way)
diff --git a/arch/x86/include/asm/crypto/camellia.h b/arch/x86/crypto/camellia.h
index f6d91861cb14..1dcea79e8f8e 100644
--- a/arch/x86/include/asm/crypto/camellia.h
+++ b/arch/x86/crypto/camellia.h
@@ -19,18 +19,10 @@ struct camellia_ctx {
 	u32 key_length;
 };
 
-struct camellia_xts_ctx {
-	struct camellia_ctx tweak_ctx;
-	struct camellia_ctx crypt_ctx;
-};
-
 extern int __camellia_setkey(struct camellia_ctx *cctx,
 			     const unsigned char *key,
 			     unsigned int key_len);
 
-extern int xts_camellia_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			       unsigned int keylen);
-
 /* regular block cipher functions */
 asmlinkage void __camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src,
 				   bool xor);
@@ -46,13 +38,6 @@ asmlinkage void camellia_ecb_enc_16way(const void *ctx, u8 *dst, const u8 *src);
 asmlinkage void camellia_ecb_dec_16way(const void *ctx, u8 *dst, const u8 *src);
 
 asmlinkage void camellia_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src);
-asmlinkage void camellia_ctr_16way(const void *ctx, u8 *dst, const u8 *src,
-				   le128 *iv);
-
-asmlinkage void camellia_xts_enc_16way(const void *ctx, u8 *dst, const u8 *src,
-				       le128 *iv);
-asmlinkage void camellia_xts_dec_16way(const void *ctx, u8 *dst, const u8 *src,
-				       le128 *iv);
 
 static inline void camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src)
 {
@@ -78,14 +63,5 @@ static inline void camellia_enc_blk_xor_2way(const void *ctx, u8 *dst,
 
 /* glue helpers */
 extern void camellia_decrypt_cbc_2way(const void *ctx, u8 *dst, const u8 *src);
-extern void camellia_crypt_ctr(const void *ctx, u8 *dst, const u8 *src,
-			       le128 *iv);
-extern void camellia_crypt_ctr_2way(const void *ctx, u8 *dst, const u8 *src,
-				    le128 *iv);
-
-extern void camellia_xts_enc(const void *ctx, u8 *dst, const u8 *src,
-			     le128 *iv);
-extern void camellia_xts_dec(const void *ctx, u8 *dst, const u8 *src,
-			     le128 *iv);
 
 #endif /* ASM_X86_CAMELLIA_H */
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index ccda647422d6..e7e4d64e9577 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -5,16 +5,16 @@
  * Copyright © 2013 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
  */
 
-#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>
 
+#include "camellia.h"
+#include "ecb_cbc_helpers.h"
+
 #define CAMELLIA_AESNI_PARALLEL_BLOCKS 16
 #define CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS 32
 
@@ -23,121 +23,6 @@ asmlinkage void camellia_ecb_enc_32way(const void *ctx, u8 *dst, const u8 *src);
 asmlinkage void camellia_ecb_dec_32way(const void *ctx, u8 *dst, const u8 *src);
 
 asmlinkage void camellia_cbc_dec_32way(const void *ctx, u8 *dst, const u8 *src);
-asmlinkage void camellia_ctr_32way(const void *ctx, u8 *dst, const u8 *src,
-				   le128 *iv);
-
-asmlinkage void camellia_xts_enc_32way(const void *ctx, u8 *dst, const u8 *src,
-				       le128 *iv);
-asmlinkage void camellia_xts_dec_32way(const void *ctx, u8 *dst, const u8 *src,
-				       le128 *iv);
-
-static const struct common_glue_ctx camellia_enc = {
-	.num_funcs = 4,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = camellia_ecb_enc_32way }
-	}, {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = camellia_ecb_enc_16way }
-	}, {
-		.num_blocks = 2,
-		.fn_u = { .ecb = camellia_enc_blk_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = camellia_enc_blk }
-	} }
-};
-
-static const struct common_glue_ctx camellia_ctr = {
-	.num_funcs = 4,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
-		.fn_u = { .ctr = camellia_ctr_32way }
-	}, {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .ctr = camellia_ctr_16way }
-	}, {
-		.num_blocks = 2,
-		.fn_u = { .ctr = camellia_crypt_ctr_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ctr = camellia_crypt_ctr }
-	} }
-};
-
-static const struct common_glue_ctx camellia_enc_xts = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
-		.fn_u = { .xts = camellia_xts_enc_32way }
-	}, {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .xts = camellia_xts_enc_16way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = camellia_xts_enc }
-	} }
-};
-
-static const struct common_glue_ctx camellia_dec = {
-	.num_funcs = 4,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = camellia_ecb_dec_32way }
-	}, {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = camellia_ecb_dec_16way }
-	}, {
-		.num_blocks = 2,
-		.fn_u = { .ecb = camellia_dec_blk_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = camellia_dec_blk }
-	} }
-};
-
-static const struct common_glue_ctx camellia_dec_cbc = {
-	.num_funcs = 4,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
-		.fn_u = { .cbc = camellia_cbc_dec_32way }
-	}, {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .cbc = camellia_cbc_dec_16way }
-	}, {
-		.num_blocks = 2,
-		.fn_u = { .cbc = camellia_decrypt_cbc_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .cbc = camellia_dec_blk }
-	} }
-};
-
-static const struct common_glue_ctx camellia_dec_xts = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
-		.fn_u = { .xts = camellia_xts_dec_32way }
-	}, {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .xts = camellia_xts_dec_16way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = camellia_xts_dec }
-	} }
-};
 
 static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			   unsigned int keylen)
@@ -147,45 +32,39 @@ static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key,
 
 static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&camellia_enc, req);
+	ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS);
+	ECB_BLOCK(CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, camellia_ecb_enc_32way);
+	ECB_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_ecb_enc_16way);
+	ECB_BLOCK(2, camellia_enc_blk_2way);
+	ECB_BLOCK(1, camellia_enc_blk);
+	ECB_WALK_END();
 }
 
 static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&camellia_dec, req);
+	ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS);
+	ECB_BLOCK(CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, camellia_ecb_dec_32way);
+	ECB_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_ecb_dec_16way);
+	ECB_BLOCK(2, camellia_dec_blk_2way);
+	ECB_BLOCK(1, camellia_dec_blk);
+	ECB_WALK_END();
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_req_128bit(camellia_enc_blk, req);
+	CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1);
+	CBC_ENC_BLOCK(camellia_enc_blk);
+	CBC_WALK_END();
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_req_128bit(&camellia_dec_cbc, req);
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	return glue_ctr_req_128bit(&camellia_ctr, req);
-}
-
-static int xts_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&camellia_enc_xts, req, camellia_enc_blk,
-				   &ctx->tweak_ctx, &ctx->crypt_ctx, false);
-}
-
-static int xts_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&camellia_dec_xts, req, camellia_enc_blk,
-				   &ctx->tweak_ctx, &ctx->crypt_ctx, true);
+	CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS);
+	CBC_DEC_BLOCK(CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, camellia_cbc_dec_32way);
+	CBC_DEC_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_cbc_dec_16way);
+	CBC_DEC_BLOCK(2, camellia_decrypt_cbc_2way);
+	CBC_DEC_BLOCK(1, camellia_dec_blk);
+	CBC_WALK_END();
 }
 
 static struct skcipher_alg camellia_algs[] = {
@@ -216,35 +95,6 @@ static struct skcipher_alg camellia_algs[] = {
 		.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,
 	},
 };
 
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 4e5de6ef206e..c7ccf63e741e 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -5,16 +5,16 @@
  * Copyright © 2012-2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
  */
 
-#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>
 
+#include "camellia.h"
+#include "ecb_cbc_helpers.h"
+
 #define CAMELLIA_AESNI_PARALLEL_BLOCKS 16
 
 /* 16-way parallel cipher functions (avx/aes-ni) */
@@ -27,120 +27,6 @@ EXPORT_SYMBOL_GPL(camellia_ecb_dec_16way);
 asmlinkage void camellia_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src);
 EXPORT_SYMBOL_GPL(camellia_cbc_dec_16way);
 
-asmlinkage void camellia_ctr_16way(const void *ctx, u8 *dst, const u8 *src,
-				   le128 *iv);
-EXPORT_SYMBOL_GPL(camellia_ctr_16way);
-
-asmlinkage void camellia_xts_enc_16way(const void *ctx, u8 *dst, const u8 *src,
-				       le128 *iv);
-EXPORT_SYMBOL_GPL(camellia_xts_enc_16way);
-
-asmlinkage void camellia_xts_dec_16way(const void *ctx, u8 *dst, const u8 *src,
-				       le128 *iv);
-EXPORT_SYMBOL_GPL(camellia_xts_dec_16way);
-
-void camellia_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	glue_xts_crypt_128bit_one(ctx, dst, src, iv, camellia_enc_blk);
-}
-EXPORT_SYMBOL_GPL(camellia_xts_enc);
-
-void camellia_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	glue_xts_crypt_128bit_one(ctx, dst, src, iv, camellia_dec_blk);
-}
-EXPORT_SYMBOL_GPL(camellia_xts_dec);
-
-static const struct common_glue_ctx camellia_enc = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = camellia_ecb_enc_16way }
-	}, {
-		.num_blocks = 2,
-		.fn_u = { .ecb = camellia_enc_blk_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = camellia_enc_blk }
-	} }
-};
-
-static const struct common_glue_ctx camellia_ctr = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .ctr = camellia_ctr_16way }
-	}, {
-		.num_blocks = 2,
-		.fn_u = { .ctr = camellia_crypt_ctr_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ctr = camellia_crypt_ctr }
-	} }
-};
-
-static const struct common_glue_ctx camellia_enc_xts = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .xts = camellia_xts_enc_16way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = camellia_xts_enc }
-	} }
-};
-
-static const struct common_glue_ctx camellia_dec = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = camellia_ecb_dec_16way }
-	}, {
-		.num_blocks = 2,
-		.fn_u = { .ecb = camellia_dec_blk_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = camellia_dec_blk }
-	} }
-};
-
-static const struct common_glue_ctx camellia_dec_cbc = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .cbc = camellia_cbc_dec_16way }
-	}, {
-		.num_blocks = 2,
-		.fn_u = { .cbc = camellia_decrypt_cbc_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .cbc = camellia_dec_blk }
-	} }
-};
-
-static const struct common_glue_ctx camellia_dec_xts = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
-		.fn_u = { .xts = camellia_xts_dec_16way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = camellia_xts_dec }
-	} }
-};
-
 static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			   unsigned int keylen)
 {
@@ -149,65 +35,36 @@ static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key,
 
 static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&camellia_enc, req);
+	ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS);
+	ECB_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_ecb_enc_16way);
+	ECB_BLOCK(2, camellia_enc_blk_2way);
+	ECB_BLOCK(1, camellia_enc_blk);
+	ECB_WALK_END();
 }
 
 static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&camellia_dec, req);
+	ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS);
+	ECB_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_ecb_dec_16way);
+	ECB_BLOCK(2, camellia_dec_blk_2way);
+	ECB_BLOCK(1, camellia_dec_blk);
+	ECB_WALK_END();
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_req_128bit(camellia_enc_blk, req);
+	CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1);
+	CBC_ENC_BLOCK(camellia_enc_blk);
+	CBC_WALK_END();
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_req_128bit(&camellia_dec_cbc, req);
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	return glue_ctr_req_128bit(&camellia_ctr, req);
-}
-
-int xts_camellia_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			unsigned int keylen)
-{
-	struct camellia_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 = __camellia_setkey(&ctx->crypt_ctx, key, keylen / 2);
-	if (err)
-		return err;
-
-	/* second half of xts-key is for tweak */
-	return __camellia_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2);
-}
-EXPORT_SYMBOL_GPL(xts_camellia_setkey);
-
-static int xts_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&camellia_enc_xts, req, camellia_enc_blk,
-				   &ctx->tweak_ctx, &ctx->crypt_ctx, false);
-}
-
-static int xts_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&camellia_dec_xts, req, camellia_enc_blk,
-				   &ctx->tweak_ctx, &ctx->crypt_ctx, true);
+	CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS);
+	CBC_DEC_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_cbc_dec_16way);
+	CBC_DEC_BLOCK(2, camellia_decrypt_cbc_2way);
+	CBC_DEC_BLOCK(1, camellia_dec_blk);
+	CBC_WALK_END();
 }
 
 static struct skcipher_alg camellia_algs[] = {
@@ -238,36 +95,7 @@ static struct skcipher_alg camellia_algs[] = {
 		.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)];
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index 242c056e5fa8..66c435ba9d3d 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -14,8 +14,9 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <crypto/algapi.h>
-#include <asm/crypto/camellia.h>
-#include <asm/crypto/glue_helper.h>
+
+#include "camellia.h"
+#include "ecb_cbc_helpers.h"
 
 /* regular block cipher functions */
 asmlinkage void __camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src,
@@ -1262,129 +1263,47 @@ static int camellia_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key,
 	return camellia_setkey(&tfm->base, key, key_len);
 }
 
-void camellia_decrypt_cbc_2way(const void *ctx, u8 *d, const u8 *s)
+void camellia_decrypt_cbc_2way(const void *ctx, u8 *dst, const u8 *src)
 {
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-	u128 iv = *src;
-
-	camellia_dec_blk_2way(ctx, (u8 *)dst, (u8 *)src);
+	u8 buf[CAMELLIA_BLOCK_SIZE];
+	const u8 *iv = src;
 
-	u128_xor(&dst[1], &dst[1], &iv);
+	if (dst == src)
+		iv = memcpy(buf, iv, sizeof(buf));
+	camellia_dec_blk_2way(ctx, dst, src);
+	crypto_xor(dst + CAMELLIA_BLOCK_SIZE, iv, CAMELLIA_BLOCK_SIZE);
 }
 EXPORT_SYMBOL_GPL(camellia_decrypt_cbc_2way);
 
-void camellia_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv)
-{
-	be128 ctrblk;
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-
-	if (dst != src)
-		*dst = *src;
-
-	le128_to_be128(&ctrblk, iv);
-	le128_inc(iv);
-
-	camellia_enc_blk_xor(ctx, (u8 *)dst, (u8 *)&ctrblk);
-}
-EXPORT_SYMBOL_GPL(camellia_crypt_ctr);
-
-void camellia_crypt_ctr_2way(const void *ctx, u8 *d, const u8 *s, le128 *iv)
-{
-	be128 ctrblks[2];
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-
-	if (dst != src) {
-		dst[0] = src[0];
-		dst[1] = src[1];
-	}
-
-	le128_to_be128(&ctrblks[0], iv);
-	le128_inc(iv);
-	le128_to_be128(&ctrblks[1], iv);
-	le128_inc(iv);
-
-	camellia_enc_blk_xor_2way(ctx, (u8 *)dst, (u8 *)ctrblks);
-}
-EXPORT_SYMBOL_GPL(camellia_crypt_ctr_2way);
-
-static const struct common_glue_ctx camellia_enc = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = -1,
-
-	.funcs = { {
-		.num_blocks = 2,
-		.fn_u = { .ecb = camellia_enc_blk_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = camellia_enc_blk }
-	} }
-};
-
-static const struct common_glue_ctx camellia_ctr = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = -1,
-
-	.funcs = { {
-		.num_blocks = 2,
-		.fn_u = { .ctr = camellia_crypt_ctr_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ctr = camellia_crypt_ctr }
-	} }
-};
-
-static const struct common_glue_ctx camellia_dec = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = -1,
-
-	.funcs = { {
-		.num_blocks = 2,
-		.fn_u = { .ecb = camellia_dec_blk_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = camellia_dec_blk }
-	} }
-};
-
-static const struct common_glue_ctx camellia_dec_cbc = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = -1,
-
-	.funcs = { {
-		.num_blocks = 2,
-		.fn_u = { .cbc = camellia_decrypt_cbc_2way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .cbc = camellia_dec_blk }
-	} }
-};
-
 static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&camellia_enc, req);
+	ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1);
+	ECB_BLOCK(2, camellia_enc_blk_2way);
+	ECB_BLOCK(1, camellia_enc_blk);
+	ECB_WALK_END();
 }
 
 static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&camellia_dec, req);
+	ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1);
+	ECB_BLOCK(2, camellia_dec_blk_2way);
+	ECB_BLOCK(1, camellia_dec_blk);
+	ECB_WALK_END();
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_req_128bit(camellia_enc_blk, req);
+	CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1);
+	CBC_ENC_BLOCK(camellia_enc_blk);
+	CBC_WALK_END();
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_req_128bit(&camellia_dec_cbc, req);
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	return glue_ctr_req_128bit(&camellia_ctr, req);
+	CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1);
+	CBC_DEC_BLOCK(2, camellia_decrypt_cbc_2way);
+	CBC_DEC_BLOCK(1, camellia_dec_blk);
+	CBC_WALK_END();
 }
 
 static struct crypto_alg camellia_cipher_alg = {
@@ -1433,20 +1352,6 @@ static struct skcipher_alg camellia_skcipher_algs[] = {
 		.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,
 	}
 };
 
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 384ccb00f9e1..3976a87f92ad 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -6,7 +6,6 @@
  *     <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
  */
 
-#include <asm/crypto/glue_helper.h>
 #include <crypto/algapi.h>
 #include <crypto/cast5.h>
 #include <crypto/internal/simd.h>
@@ -15,6 +14,8 @@
 #include <linux/module.h>
 #include <linux/types.h>
 
+#include "ecb_cbc_helpers.h"
+
 #define CAST5_PARALLEL_BLOCKS 16
 
 asmlinkage void cast5_ecb_enc_16way(struct cast5_ctx *ctx, u8 *dst,
@@ -23,8 +24,6 @@ asmlinkage void cast5_ecb_dec_16way(struct cast5_ctx *ctx, u8 *dst,
 				    const u8 *src);
 asmlinkage void cast5_cbc_dec_16way(struct cast5_ctx *ctx, u8 *dst,
 				    const u8 *src);
-asmlinkage void cast5_ctr_16way(struct cast5_ctx *ctx, u8 *dst, const u8 *src,
-				__be64 *iv);
 
 static int cast5_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key,
 				 unsigned int keylen)
@@ -32,272 +31,35 @@ static int cast5_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key,
 	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,
-			      walk, fpu_enabled, nbytes);
-}
-
-static inline void cast5_fpu_end(bool fpu_enabled)
-{
-	return glue_fpu_end(fpu_enabled);
-}
-
-static int ecb_crypt(struct skcipher_request *req, bool enc)
-{
-	bool fpu_enabled = false;
-	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;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes)) {
-		u8 *wsrc = walk.src.virt.addr;
-		u8 *wdst = walk.dst.virt.addr;
-
-		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);
-
-				wsrc += bsize * CAST5_PARALLEL_BLOCKS;
-				wdst += bsize * CAST5_PARALLEL_BLOCKS;
-				nbytes -= bsize * CAST5_PARALLEL_BLOCKS;
-			} while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS);
-
-			if (nbytes < bsize)
-				goto done;
-		}
-
-		fn = (enc) ? __cast5_encrypt : __cast5_decrypt;
-
-		/* Handle leftovers */
-		do {
-			fn(ctx, wdst, wsrc);
-
-			wsrc += bsize;
-			wdst += bsize;
-			nbytes -= bsize;
-		} while (nbytes >= bsize);
-
-done:
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	cast5_fpu_end(fpu_enabled);
-	return err;
-}
-
 static int ecb_encrypt(struct skcipher_request *req)
 {
-	return ecb_crypt(req, true);
+	ECB_WALK_START(req, CAST5_BLOCK_SIZE, CAST5_PARALLEL_BLOCKS);
+	ECB_BLOCK(CAST5_PARALLEL_BLOCKS, cast5_ecb_enc_16way);
+	ECB_BLOCK(1, __cast5_encrypt);
+	ECB_WALK_END();
 }
 
 static int ecb_decrypt(struct skcipher_request *req)
 {
-	return ecb_crypt(req, false);
+	ECB_WALK_START(req, CAST5_BLOCK_SIZE, CAST5_PARALLEL_BLOCKS);
+	ECB_BLOCK(CAST5_PARALLEL_BLOCKS, cast5_ecb_dec_16way);
+	ECB_BLOCK(1, __cast5_decrypt);
+	ECB_WALK_END();
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	const unsigned int bsize = CAST5_BLOCK_SIZE;
-	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;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((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++;
-			dst++;
-			nbytes -= bsize;
-		} while (nbytes >= bsize);
-
-		*(u64 *)walk.iv = *iv;
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	return err;
-}
-
-static unsigned int __cbc_decrypt(struct cast5_ctx *ctx,
-				  struct skcipher_walk *walk)
-{
-	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 last_iv;
-
-	/* Start of the last block. */
-	src += nbytes / bsize - 1;
-	dst += nbytes / bsize - 1;
-
-	last_iv = *src;
-
-	/* Process multi-block batch */
-	if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
-		do {
-			nbytes -= bsize * (CAST5_PARALLEL_BLOCKS - 1);
-			src -= CAST5_PARALLEL_BLOCKS - 1;
-			dst -= CAST5_PARALLEL_BLOCKS - 1;
-
-			cast5_cbc_dec_16way(ctx, (u8 *)dst, (u8 *)src);
-
-			nbytes -= bsize;
-			if (nbytes < bsize)
-				goto done;
-
-			*dst ^= *(src - 1);
-			src -= 1;
-			dst -= 1;
-		} while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS);
-	}
-
-	/* Handle leftovers */
-	for (;;) {
-		__cast5_decrypt(ctx, (u8 *)dst, (u8 *)src);
-
-		nbytes -= bsize;
-		if (nbytes < bsize)
-			break;
-
-		*dst ^= *(src - 1);
-		src -= 1;
-		dst -= 1;
-	}
-
-done:
-	*dst ^= *(u64 *)walk->iv;
-	*(u64 *)walk->iv = last_iv;
-
-	return nbytes;
+	CBC_WALK_START(req, CAST5_BLOCK_SIZE, -1);
+	CBC_ENC_BLOCK(__cast5_encrypt);
+	CBC_WALK_END();
 }
 
 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 skcipher_walk walk;
-	unsigned int nbytes;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = 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 skcipher_walk *walk, struct cast5_ctx *ctx)
-{
-	u8 *ctrblk = walk->iv;
-	u8 keystream[CAST5_BLOCK_SIZE];
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	unsigned int nbytes = walk->nbytes;
-
-	__cast5_encrypt(ctx, keystream, ctrblk);
-	crypto_xor_cpy(dst, keystream, src, nbytes);
-
-	crypto_inc(ctrblk, CAST5_BLOCK_SIZE);
-}
-
-static unsigned int __ctr_crypt(struct skcipher_walk *walk,
-				struct cast5_ctx *ctx)
-{
-	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;
-
-	/* Process multi-block batch */
-	if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
-		do {
-			cast5_ctr_16way(ctx, (u8 *)dst, (u8 *)src,
-					(__be64 *)walk->iv);
-
-			src += CAST5_PARALLEL_BLOCKS;
-			dst += CAST5_PARALLEL_BLOCKS;
-			nbytes -= bsize * CAST5_PARALLEL_BLOCKS;
-		} while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS);
-
-		if (nbytes < bsize)
-			goto done;
-	}
-
-	/* Handle leftovers */
-	do {
-		u64 ctrblk;
-
-		if (dst != src)
-			*dst = *src;
-
-		ctrblk = *(u64 *)walk->iv;
-		be64_add_cpu((__be64 *)walk->iv, 1);
-
-		__cast5_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
-		*dst ^= ctrblk;
-
-		src += 1;
-		dst += 1;
-		nbytes -= bsize;
-	} while (nbytes >= bsize);
-
-done:
-	return 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 skcipher_walk walk;
-	unsigned int nbytes;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) {
-		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(&walk, ctx);
-		err = skcipher_walk_done(&walk, 0);
-	}
-
-	return err;
+	CBC_WALK_START(req, CAST5_BLOCK_SIZE, CAST5_PARALLEL_BLOCKS);
+	CBC_DEC_BLOCK(CAST5_PARALLEL_BLOCKS, cast5_cbc_dec_16way);
+	CBC_DEC_BLOCK(1, __cast5_decrypt);
+	CBC_WALK_END();
 }
 
 static struct skcipher_alg cast5_algs[] = {
@@ -328,21 +90,6 @@ static struct skcipher_alg cast5_algs[] = {
 		.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,
 	}
 };
 
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index 932a3ce32a88..fbddcecc3e3f 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -212,8 +212,6 @@
 
 .section	.rodata.cst16, "aM", @progbits, 16
 .align 16
-.Lxts_gf128mul_and_shl1_mask:
-	.byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0
 .Lbswap_mask:
 	.byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
 .Lbswap128_mask:
@@ -412,85 +410,3 @@ SYM_FUNC_START(cast6_cbc_dec_8way)
 	FRAME_END
 	ret;
 SYM_FUNC_END(cast6_cbc_dec_8way)
-
-SYM_FUNC_START(cast6_ctr_8way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst
-	 *	%rdx: src
-	 *	%rcx: iv (little endian, 128bit)
-	 */
-	FRAME_BEGIN
-	pushq %r12;
-	pushq %r15
-
-	movq %rdi, CTX;
-	movq %rsi, %r11;
-	movq %rdx, %r12;
-
-	load_ctr_8way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2,
-		      RD2, RX, RKR, RKM);
-
-	call __cast6_enc_blk8;
-
-	store_ctr_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
-
-	popq %r15;
-	popq %r12;
-	FRAME_END
-	ret;
-SYM_FUNC_END(cast6_ctr_8way)
-
-SYM_FUNC_START(cast6_xts_enc_8way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst
-	 *	%rdx: src
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-	FRAME_BEGIN
-	pushq %r15;
-
-	movq %rdi, CTX
-	movq %rsi, %r11;
-
-	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
-	load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
-		      RX, RKR, RKM, .Lxts_gf128mul_and_shl1_mask);
-
-	call __cast6_enc_blk8;
-
-	/* dst <= regs xor IVs(in dst) */
-	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
-
-	popq %r15;
-	FRAME_END
-	ret;
-SYM_FUNC_END(cast6_xts_enc_8way)
-
-SYM_FUNC_START(cast6_xts_dec_8way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst
-	 *	%rdx: src
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-	FRAME_BEGIN
-	pushq %r15;
-
-	movq %rdi, CTX
-	movq %rsi, %r11;
-
-	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
-	load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
-		      RX, RKR, RKM, .Lxts_gf128mul_and_shl1_mask);
-
-	call __cast6_dec_blk8;
-
-	/* dst <= regs xor IVs(in dst) */
-	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
-
-	popq %r15;
-	FRAME_END
-	ret;
-SYM_FUNC_END(cast6_xts_dec_8way)
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 48e0f37796fa..7e2aea372349 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -15,8 +15,8 @@
 #include <crypto/algapi.h>
 #include <crypto/cast6.h>
 #include <crypto/internal/simd.h>
-#include <crypto/xts.h>
-#include <asm/crypto/glue_helper.h>
+
+#include "ecb_cbc_helpers.h"
 
 #define CAST6_PARALLEL_BLOCKS 8
 
@@ -24,13 +24,6 @@ asmlinkage void cast6_ecb_enc_8way(const void *ctx, u8 *dst, const u8 *src);
 asmlinkage void cast6_ecb_dec_8way(const void *ctx, u8 *dst, const u8 *src);
 
 asmlinkage void cast6_cbc_dec_8way(const void *ctx, u8 *dst, const u8 *src);
-asmlinkage void cast6_ctr_8way(const void *ctx, u8 *dst, const u8 *src,
-			       le128 *iv);
-
-asmlinkage void cast6_xts_enc_8way(const void *ctx, u8 *dst, const u8 *src,
-				   le128 *iv);
-asmlinkage void cast6_xts_dec_8way(const void *ctx, u8 *dst, const u8 *src,
-				   le128 *iv);
 
 static int cast6_setkey_skcipher(struct crypto_skcipher *tfm,
 				 const u8 *key, unsigned int keylen)
@@ -38,172 +31,35 @@ static int cast6_setkey_skcipher(struct crypto_skcipher *tfm,
 	return cast6_setkey(&tfm->base, key, keylen);
 }
 
-static void cast6_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	glue_xts_crypt_128bit_one(ctx, dst, src, iv, __cast6_encrypt);
-}
-
-static void cast6_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	glue_xts_crypt_128bit_one(ctx, dst, src, iv, __cast6_decrypt);
-}
-
-static void cast6_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv)
-{
-	be128 ctrblk;
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-
-	le128_to_be128(&ctrblk, iv);
-	le128_inc(iv);
-
-	__cast6_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
-	u128_xor(dst, src, (u128 *)&ctrblk);
-}
-
-static const struct common_glue_ctx cast6_enc = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAST6_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = cast6_ecb_enc_8way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = __cast6_encrypt }
-	} }
-};
-
-static const struct common_glue_ctx cast6_ctr = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAST6_PARALLEL_BLOCKS,
-		.fn_u = { .ctr = cast6_ctr_8way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ctr = cast6_crypt_ctr }
-	} }
-};
-
-static const struct common_glue_ctx cast6_enc_xts = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAST6_PARALLEL_BLOCKS,
-		.fn_u = { .xts = cast6_xts_enc_8way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = cast6_xts_enc }
-	} }
-};
-
-static const struct common_glue_ctx cast6_dec = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAST6_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = cast6_ecb_dec_8way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = __cast6_decrypt }
-	} }
-};
-
-static const struct common_glue_ctx cast6_dec_cbc = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAST6_PARALLEL_BLOCKS,
-		.fn_u = { .cbc = cast6_cbc_dec_8way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .cbc = __cast6_decrypt }
-	} }
-};
-
-static const struct common_glue_ctx cast6_dec_xts = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = CAST6_PARALLEL_BLOCKS,
-		.fn_u = { .xts = cast6_xts_dec_8way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = cast6_xts_dec }
-	} }
-};
-
 static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&cast6_enc, req);
+	ECB_WALK_START(req, CAST6_BLOCK_SIZE, CAST6_PARALLEL_BLOCKS);
+	ECB_BLOCK(CAST6_PARALLEL_BLOCKS, cast6_ecb_enc_8way);
+	ECB_BLOCK(1, __cast6_encrypt);
+	ECB_WALK_END();
 }
 
 static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&cast6_dec, req);
+	ECB_WALK_START(req, CAST6_BLOCK_SIZE, CAST6_PARALLEL_BLOCKS);
+	ECB_BLOCK(CAST6_PARALLEL_BLOCKS, cast6_ecb_dec_8way);
+	ECB_BLOCK(1, __cast6_decrypt);
+	ECB_WALK_END();
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_req_128bit(__cast6_encrypt, req);
+	CBC_WALK_START(req, CAST6_BLOCK_SIZE, -1);
+	CBC_ENC_BLOCK(__cast6_encrypt);
+	CBC_WALK_END();
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_req_128bit(&cast6_dec_cbc, req);
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	return glue_ctr_req_128bit(&cast6_ctr, req);
-}
-
-struct cast6_xts_ctx {
-	struct cast6_ctx tweak_ctx;
-	struct cast6_ctx crypt_ctx;
-};
-
-static int xts_cast6_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			    unsigned int keylen)
-{
-	struct cast6_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 = __cast6_setkey(&ctx->crypt_ctx, key, keylen / 2);
-	if (err)
-		return err;
-
-	/* second half of xts-key is for tweak */
-	return __cast6_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2);
-}
-
-static int xts_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&cast6_enc_xts, req, __cast6_encrypt,
-				   &ctx->tweak_ctx, &ctx->crypt_ctx, false);
-}
-
-static int xts_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&cast6_dec_xts, req, __cast6_encrypt,
-				   &ctx->tweak_ctx, &ctx->crypt_ctx, true);
+	CBC_WALK_START(req, CAST6_BLOCK_SIZE, CAST6_PARALLEL_BLOCKS);
+	CBC_DEC_BLOCK(CAST6_PARALLEL_BLOCKS, cast6_cbc_dec_8way);
+	CBC_DEC_BLOCK(1, __cast6_decrypt);
+	CBC_WALK_END();
 }
 
 static struct skcipher_alg cast6_algs[] = {
@@ -234,35 +90,6 @@ static struct skcipher_alg cast6_algs[] = {
 		.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,
 	},
 };
 
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
index 89830e531350..e7cb68a3db3b 100644
--- a/arch/x86/crypto/des3_ede_glue.c
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -6,8 +6,6 @@
  *
  * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
  *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
- * CTR part based on code (crypto/ctr.c) by:
- *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
  */
 
 #include <crypto/algapi.h>
@@ -253,94 +251,6 @@ static int cbc_decrypt(struct skcipher_request *req)
 	return err;
 }
 
-static void ctr_crypt_final(struct des3_ede_x86_ctx *ctx,
-			    struct skcipher_walk *walk)
-{
-	u8 *ctrblk = walk->iv;
-	u8 keystream[DES3_EDE_BLOCK_SIZE];
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	unsigned int nbytes = walk->nbytes;
-
-	des3_ede_enc_blk(ctx, keystream, ctrblk);
-	crypto_xor_cpy(dst, keystream, src, nbytes);
-
-	crypto_inc(ctrblk, DES3_EDE_BLOCK_SIZE);
-}
-
-static unsigned int __ctr_crypt(struct des3_ede_x86_ctx *ctx,
-				struct skcipher_walk *walk)
-{
-	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	__be64 *src = (__be64 *)walk->src.virt.addr;
-	__be64 *dst = (__be64 *)walk->dst.virt.addr;
-	u64 ctrblk = be64_to_cpu(*(__be64 *)walk->iv);
-	__be64 ctrblocks[3];
-
-	/* Process four block batch */
-	if (nbytes >= bsize * 3) {
-		do {
-			/* create ctrblks for parallel encrypt */
-			ctrblocks[0] = cpu_to_be64(ctrblk++);
-			ctrblocks[1] = cpu_to_be64(ctrblk++);
-			ctrblocks[2] = cpu_to_be64(ctrblk++);
-
-			des3_ede_enc_blk_3way(ctx, (u8 *)ctrblocks,
-					      (u8 *)ctrblocks);
-
-			dst[0] = src[0] ^ ctrblocks[0];
-			dst[1] = src[1] ^ ctrblocks[1];
-			dst[2] = src[2] ^ ctrblocks[2];
-
-			src += 3;
-			dst += 3;
-		} while ((nbytes -= bsize * 3) >= bsize * 3);
-
-		if (nbytes < bsize)
-			goto done;
-	}
-
-	/* Handle leftovers */
-	do {
-		ctrblocks[0] = cpu_to_be64(ctrblk++);
-
-		des3_ede_enc_blk(ctx, (u8 *)ctrblocks, (u8 *)ctrblocks);
-
-		dst[0] = src[0] ^ ctrblocks[0];
-
-		src += 1;
-		dst += 1;
-	} while ((nbytes -= bsize) >= bsize);
-
-done:
-	*(__be64 *)walk->iv = cpu_to_be64(ctrblk);
-	return nbytes;
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	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;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes) >= DES3_EDE_BLOCK_SIZE) {
-		nbytes = __ctr_crypt(ctx, &walk);
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	if (nbytes) {
-		ctr_crypt_final(ctx, &walk);
-		err = skcipher_walk_done(&walk, 0);
-	}
-
-	return err;
-}
-
 static int des3_ede_x86_setkey(struct crypto_tfm *tfm, const u8 *key,
 			       unsigned int keylen)
 {
@@ -428,20 +338,6 @@ static struct skcipher_alg des3_ede_skciphers[] = {
 		.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,
 	}
 };
 
diff --git a/arch/x86/crypto/ecb_cbc_helpers.h b/arch/x86/crypto/ecb_cbc_helpers.h
new file mode 100644
index 000000000000..eaa15c7b29d6
--- /dev/null
+++ b/arch/x86/crypto/ecb_cbc_helpers.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _CRYPTO_ECB_CBC_HELPER_H
+#define _CRYPTO_ECB_CBC_HELPER_H
+
+#include <crypto/internal/skcipher.h>
+#include <asm/fpu/api.h>
+
+/*
+ * Mode helpers to instantiate parameterized skcipher ECB/CBC modes without
+ * having to rely on indirect calls and retpolines.
+ */
+
+#define ECB_WALK_START(req, bsize, fpu_blocks) do {			\
+	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));	\
+	const int __bsize = (bsize);					\
+	struct skcipher_walk walk;					\
+	int err = skcipher_walk_virt(&walk, (req), false);		\
+	while (walk.nbytes > 0) {					\
+		unsigned int nbytes = walk.nbytes;			\
+		bool do_fpu = (fpu_blocks) != -1 &&			\
+			      nbytes >= (fpu_blocks) * __bsize;		\
+		const u8 *src = walk.src.virt.addr;			\
+		u8 *dst = walk.dst.virt.addr;				\
+		u8 __maybe_unused buf[(bsize)];				\
+		if (do_fpu) kernel_fpu_begin()
+
+#define CBC_WALK_START(req, bsize, fpu_blocks)				\
+	ECB_WALK_START(req, bsize, fpu_blocks)
+
+#define ECB_WALK_ADVANCE(blocks) do {					\
+	dst += (blocks) * __bsize;					\
+	src += (blocks) * __bsize;					\
+	nbytes -= (blocks) * __bsize;					\
+} while (0)
+
+#define ECB_BLOCK(blocks, func) do {					\
+	while (nbytes >= (blocks) * __bsize) {				\
+		(func)(ctx, dst, src);					\
+		ECB_WALK_ADVANCE(blocks);				\
+	}								\
+} while (0)
+
+#define CBC_ENC_BLOCK(func) do {					\
+	const u8 *__iv = walk.iv;					\
+	while (nbytes >= __bsize) {					\
+		crypto_xor_cpy(dst, src, __iv, __bsize);		\
+		(func)(ctx, dst, dst);					\
+		__iv = dst;						\
+		ECB_WALK_ADVANCE(1);					\
+	}								\
+	memcpy(walk.iv, __iv, __bsize);					\
+} while (0)
+
+#define CBC_DEC_BLOCK(blocks, func) do {				\
+	while (nbytes >= (blocks) * __bsize) {				\
+		const u8 *__iv = src + ((blocks) - 1) * __bsize;	\
+		if (dst == src)						\
+			__iv = memcpy(buf, __iv, __bsize);		\
+		(func)(ctx, dst, src);					\
+		crypto_xor(dst, walk.iv, __bsize);			\
+		memcpy(walk.iv, __iv, __bsize);				\
+		ECB_WALK_ADVANCE(blocks);				\
+	}								\
+} while (0)
+
+#define ECB_WALK_END()							\
+		if (do_fpu) kernel_fpu_end();				\
+		err = skcipher_walk_done(&walk, nbytes);		\
+	}								\
+	return err;							\
+} while (0)
+
+#define CBC_WALK_END() ECB_WALK_END()
+
+#endif
diff --git a/arch/x86/crypto/glue_helper-asm-avx.S b/arch/x86/crypto/glue_helper-asm-avx.S
index d08fc575ef7f..3da385271227 100644
--- a/arch/x86/crypto/glue_helper-asm-avx.S
+++ b/arch/x86/crypto/glue_helper-asm-avx.S
@@ -34,107 +34,3 @@
 	vpxor (5*16)(src), x6, x6; \
 	vpxor (6*16)(src), x7, x7; \
 	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
-
-#define inc_le128(x, minus_one, tmp) \
-	vpcmpeqq minus_one, x, tmp; \
-	vpsubq minus_one, x, x; \
-	vpslldq $8, tmp, tmp; \
-	vpsubq tmp, x, x;
-
-#define load_ctr_8way(iv, bswap, x0, x1, x2, x3, x4, x5, x6, x7, t0, t1, t2) \
-	vpcmpeqd t0, t0, t0; \
-	vpsrldq $8, t0, t0; /* low: -1, high: 0 */ \
-	vmovdqa bswap, t1; \
-	\
-	/* load IV and byteswap */ \
-	vmovdqu (iv), x7; \
-	vpshufb t1, x7, x0; \
-	\
-	/* construct IVs */ \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x1; \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x2; \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x3; \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x4; \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x5; \
-	inc_le128(x7, t0, t2); \
-	vpshufb t1, x7, x6; \
-	inc_le128(x7, t0, t2); \
-	vmovdqa x7, t2; \
-	vpshufb t1, x7, x7; \
-	inc_le128(t2, t0, t1); \
-	vmovdqu t2, (iv);
-
-#define store_ctr_8way(src, dst, x0, x1, x2, x3, x4, x5, x6, x7) \
-	vpxor (0*16)(src), x0, x0; \
-	vpxor (1*16)(src), x1, x1; \
-	vpxor (2*16)(src), x2, x2; \
-	vpxor (3*16)(src), x3, x3; \
-	vpxor (4*16)(src), x4, x4; \
-	vpxor (5*16)(src), x5, x5; \
-	vpxor (6*16)(src), x6, x6; \
-	vpxor (7*16)(src), x7, x7; \
-	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
-
-#define gf128mul_x_ble(iv, mask, tmp) \
-	vpsrad $31, iv, tmp; \
-	vpaddq iv, iv, iv; \
-	vpshufd $0x13, tmp, tmp; \
-	vpand mask, tmp, tmp; \
-	vpxor tmp, iv, iv;
-
-#define load_xts_8way(iv, src, dst, x0, x1, x2, x3, x4, x5, x6, x7, tiv, t0, \
-		      t1, xts_gf128mul_and_shl1_mask) \
-	vmovdqa xts_gf128mul_and_shl1_mask, t0; \
-	\
-	/* load IV */ \
-	vmovdqu (iv), tiv; \
-	vpxor (0*16)(src), tiv, x0; \
-	vmovdqu tiv, (0*16)(dst); \
-	\
-	/* construct and store IVs, also xor with source */ \
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (1*16)(src), tiv, x1; \
-	vmovdqu tiv, (1*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (2*16)(src), tiv, x2; \
-	vmovdqu tiv, (2*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (3*16)(src), tiv, x3; \
-	vmovdqu tiv, (3*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (4*16)(src), tiv, x4; \
-	vmovdqu tiv, (4*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (5*16)(src), tiv, x5; \
-	vmovdqu tiv, (5*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (6*16)(src), tiv, x6; \
-	vmovdqu tiv, (6*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vpxor (7*16)(src), tiv, x7; \
-	vmovdqu tiv, (7*16)(dst); \
-	\
-	gf128mul_x_ble(tiv, t0, t1); \
-	vmovdqu tiv, (iv);
-
-#define store_xts_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7) \
-	vpxor (0*16)(dst), x0, x0; \
-	vpxor (1*16)(dst), x1, x1; \
-	vpxor (2*16)(dst), x2, x2; \
-	vpxor (3*16)(dst), x3, x3; \
-	vpxor (4*16)(dst), x4, x4; \
-	vpxor (5*16)(dst), x5, x5; \
-	vpxor (6*16)(dst), x6, x6; \
-	vpxor (7*16)(dst), x7, x7; \
-	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
diff --git a/arch/x86/crypto/glue_helper-asm-avx2.S b/arch/x86/crypto/glue_helper-asm-avx2.S
index d84508c85c13..c77e9049431f 100644
--- a/arch/x86/crypto/glue_helper-asm-avx2.S
+++ b/arch/x86/crypto/glue_helper-asm-avx2.S
@@ -37,139 +37,3 @@
 	vpxor (5*32+16)(src), x6, x6; \
 	vpxor (6*32+16)(src), x7, x7; \
 	store_16way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
-
-#define inc_le128(x, minus_one, tmp) \
-	vpcmpeqq minus_one, x, tmp; \
-	vpsubq minus_one, x, x; \
-	vpslldq $8, tmp, tmp; \
-	vpsubq tmp, x, x;
-
-#define add2_le128(x, minus_one, minus_two, tmp1, tmp2) \
-	vpcmpeqq minus_one, x, tmp1; \
-	vpcmpeqq minus_two, x, tmp2; \
-	vpsubq minus_two, x, x; \
-	vpor tmp2, tmp1, tmp1; \
-	vpslldq $8, tmp1, tmp1; \
-	vpsubq tmp1, x, x;
-
-#define load_ctr_16way(iv, bswap, x0, x1, x2, x3, x4, x5, x6, x7, t0, t0x, t1, \
-		       t1x, t2, t2x, t3, t3x, t4, t5) \
-	vpcmpeqd t0, t0, t0; \
-	vpsrldq $8, t0, t0; /* ab: -1:0 ; cd: -1:0 */ \
-	vpaddq t0, t0, t4; /* ab: -2:0 ; cd: -2:0 */\
-	\
-	/* load IV and byteswap */ \
-	vmovdqu (iv), t2x; \
-	vmovdqa t2x, t3x; \
-	inc_le128(t2x, t0x, t1x); \
-	vbroadcasti128 bswap, t1; \
-	vinserti128 $1, t2x, t3, t2; /* ab: le0 ; cd: le1 */ \
-	vpshufb t1, t2, x0; \
-	\
-	/* construct IVs */ \
-	add2_le128(t2, t0, t4, t3, t5); /* ab: le2 ; cd: le3 */ \
-	vpshufb t1, t2, x1; \
-	add2_le128(t2, t0, t4, t3, t5); \
-	vpshufb t1, t2, x2; \
-	add2_le128(t2, t0, t4, t3, t5); \
-	vpshufb t1, t2, x3; \
-	add2_le128(t2, t0, t4, t3, t5); \
-	vpshufb t1, t2, x4; \
-	add2_le128(t2, t0, t4, t3, t5); \
-	vpshufb t1, t2, x5; \
-	add2_le128(t2, t0, t4, t3, t5); \
-	vpshufb t1, t2, x6; \
-	add2_le128(t2, t0, t4, t3, t5); \
-	vpshufb t1, t2, x7; \
-	vextracti128 $1, t2, t2x; \
-	inc_le128(t2x, t0x, t3x); \
-	vmovdqu t2x, (iv);
-
-#define store_ctr_16way(src, dst, x0, x1, x2, x3, x4, x5, x6, x7) \
-	vpxor (0*32)(src), x0, x0; \
-	vpxor (1*32)(src), x1, x1; \
-	vpxor (2*32)(src), x2, x2; \
-	vpxor (3*32)(src), x3, x3; \
-	vpxor (4*32)(src), x4, x4; \
-	vpxor (5*32)(src), x5, x5; \
-	vpxor (6*32)(src), x6, x6; \
-	vpxor (7*32)(src), x7, x7; \
-	store_16way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
-
-#define gf128mul_x_ble(iv, mask, tmp) \
-	vpsrad $31, iv, tmp; \
-	vpaddq iv, iv, iv; \
-	vpshufd $0x13, tmp, tmp; \
-	vpand mask, tmp, tmp; \
-	vpxor tmp, iv, iv;
-
-#define gf128mul_x2_ble(iv, mask1, mask2, tmp0, tmp1) \
-	vpsrad $31, iv, tmp0; \
-	vpaddq iv, iv, tmp1; \
-	vpsllq $2, iv, iv; \
-	vpshufd $0x13, tmp0, tmp0; \
-	vpsrad $31, tmp1, tmp1; \
-	vpand mask2, tmp0, tmp0; \
-	vpshufd $0x13, tmp1, tmp1; \
-	vpxor tmp0, iv, iv; \
-	vpand mask1, tmp1, tmp1; \
-	vpxor tmp1, iv, iv;
-
-#define load_xts_16way(iv, src, dst, x0, x1, x2, x3, x4, x5, x6, x7, tiv, \
-		       tivx, t0, t0x, t1, t1x, t2, t2x, t3, \
-		       xts_gf128mul_and_shl1_mask_0, \
-		       xts_gf128mul_and_shl1_mask_1) \
-	vbroadcasti128 xts_gf128mul_and_shl1_mask_0, t1; \
-	\
-	/* load IV and construct second IV */ \
-	vmovdqu (iv), tivx; \
-	vmovdqa tivx, t0x; \
-	gf128mul_x_ble(tivx, t1x, t2x); \
-	vbroadcasti128 xts_gf128mul_and_shl1_mask_1, t2; \
-	vinserti128 $1, tivx, t0, tiv; \
-	vpxor (0*32)(src), tiv, x0; \
-	vmovdqu tiv, (0*32)(dst); \
-	\
-	/* construct and store IVs, also xor with source */ \
-	gf128mul_x2_ble(tiv, t1, t2, t0, t3); \
-	vpxor (1*32)(src), tiv, x1; \
-	vmovdqu tiv, (1*32)(dst); \
-	\
-	gf128mul_x2_ble(tiv, t1, t2, t0, t3); \
-	vpxor (2*32)(src), tiv, x2; \
-	vmovdqu tiv, (2*32)(dst); \
-	\
-	gf128mul_x2_ble(tiv, t1, t2, t0, t3); \
-	vpxor (3*32)(src), tiv, x3; \
-	vmovdqu tiv, (3*32)(dst); \
-	\
-	gf128mul_x2_ble(tiv, t1, t2, t0, t3); \
-	vpxor (4*32)(src), tiv, x4; \
-	vmovdqu tiv, (4*32)(dst); \
-	\
-	gf128mul_x2_ble(tiv, t1, t2, t0, t3); \
-	vpxor (5*32)(src), tiv, x5; \
-	vmovdqu tiv, (5*32)(dst); \
-	\
-	gf128mul_x2_ble(tiv, t1, t2, t0, t3); \
-	vpxor (6*32)(src), tiv, x6; \
-	vmovdqu tiv, (6*32)(dst); \
-	\
-	gf128mul_x2_ble(tiv, t1, t2, t0, t3); \
-	vpxor (7*32)(src), tiv, x7; \
-	vmovdqu tiv, (7*32)(dst); \
-	\
-	vextracti128 $1, tiv, tivx; \
-	gf128mul_x_ble(tivx, t1x, t2x); \
-	vmovdqu tivx, (iv);
-
-#define store_xts_16way(dst, x0, x1, x2, x3, x4, x5, x6, x7) \
-	vpxor (0*32)(dst), x0, x0; \
-	vpxor (1*32)(dst), x1, x1; \
-	vpxor (2*32)(dst), x2, x2; \
-	vpxor (3*32)(dst), x3, x3; \
-	vpxor (4*32)(dst), x4, x4; \
-	vpxor (5*32)(dst), x5, x5; \
-	vpxor (6*32)(dst), x6, x6; \
-	vpxor (7*32)(dst), x7, x7; \
-	store_16way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
deleted file mode 100644
index d3d91a0abf88..000000000000
--- a/arch/x86/crypto/glue_helper.c
+++ /dev/null
@@ -1,381 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Shared glue code for 128bit block ciphers
- *
- * Copyright © 2012-2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
- *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
- * CTR part based on code (crypto/ctr.c) by:
- *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
- */
-
-#include <linux/module.h>
-#include <crypto/b128ops.h>
-#include <crypto/gf128mul.h>
-#include <crypto/internal/skcipher.h>
-#include <crypto/scatterwalk.h>
-#include <crypto/xts.h>
-#include <asm/crypto/glue_helper.h>
-
-int glue_ecb_req_128bit(const struct common_glue_ctx *gctx,
-			struct skcipher_request *req)
-{
-	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;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	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,
-					     &walk, fpu_enabled, nbytes);
-		for (i = 0; i < gctx->num_funcs; i++) {
-			func_bytes = bsize * gctx->funcs[i].num_blocks;
-
-			if (nbytes < func_bytes)
-				continue;
-
-			/* 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)
-				break;
-		}
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	glue_fpu_end(fpu_enabled);
-	return err;
-}
-EXPORT_SYMBOL_GPL(glue_ecb_req_128bit);
-
-int glue_cbc_encrypt_req_128bit(const common_glue_func_t fn,
-				struct skcipher_request *req)
-{
-	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
-	const unsigned int bsize = 128 / 8;
-	struct skcipher_walk walk;
-	unsigned int nbytes;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = 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_req_128bit);
-
-int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx,
-				struct skcipher_request *req)
-{
-	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;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	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;
-
-		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;
-
-		last_iv = *src;
-
-		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 {
-				src -= num_blocks - 1;
-				dst -= num_blocks - 1;
-
-				gctx->funcs[i].fn_u.cbc(ctx, (u8 *)dst,
-							(const u8 *)src);
-
-				nbytes -= func_bytes;
-				if (nbytes < bsize)
-					goto done;
-
-				u128_xor(dst, dst, --src);
-				dst--;
-			} while (nbytes >= func_bytes);
-		}
-done:
-		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_req_128bit);
-
-int glue_ctr_req_128bit(const struct common_glue_ctx *gctx,
-			struct skcipher_request *req)
-{
-	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;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	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;
-
-		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					     &walk, fpu_enabled, nbytes);
-
-		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;
-
-			if (nbytes < func_bytes)
-				continue;
-
-			/* Process multi-block batch */
-			do {
-				gctx->funcs[i].fn_u.ctr(ctx, (u8 *)dst,
-							(const u8 *)src,
-							&ctrblk);
-				src += num_blocks;
-				dst += num_blocks;
-				nbytes -= func_bytes;
-			} while (nbytes >= func_bytes);
-
-			if (nbytes < bsize)
-				break;
-		}
-
-		le128_to_be128((be128 *)walk.iv, &ctrblk);
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-
-	glue_fpu_end(fpu_enabled);
-
-	if (nbytes) {
-		le128 ctrblk;
-		u128 tmp;
-
-		be128_to_le128(&ctrblk, (be128 *)walk.iv);
-		memcpy(&tmp, walk.src.virt.addr, nbytes);
-		gctx->funcs[gctx->num_funcs - 1].fn_u.ctr(ctx, (u8 *)&tmp,
-							  (const u8 *)&tmp,
-							  &ctrblk);
-		memcpy(walk.dst.virt.addr, &tmp, nbytes);
-		le128_to_be128((be128 *)walk.iv, &ctrblk);
-
-		err = skcipher_walk_done(&walk, 0);
-	}
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(glue_ctr_req_128bit);
-
-static unsigned int __glue_xts_req_128bit(const struct common_glue_ctx *gctx,
-					  void *ctx,
-					  struct skcipher_walk *walk)
-{
-	const unsigned int bsize = 128 / 8;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = walk->src.virt.addr;
-	u128 *dst = 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, (u8 *)dst,
-							(const u8 *)src,
-							walk->iv);
-
-				src += num_blocks;
-				dst += num_blocks;
-				nbytes -= func_bytes;
-			} while (nbytes >= func_bytes);
-
-			if (nbytes < bsize)
-				goto done;
-		}
-	}
-
-done:
-	return nbytes;
-}
-
-int glue_xts_req_128bit(const struct common_glue_ctx *gctx,
-			struct skcipher_request *req,
-			common_glue_func_t tweak_fn, void *tweak_ctx,
-			void *crypt_ctx, bool decrypt)
-{
-	const bool cts = (req->cryptlen % XTS_BLOCK_SIZE);
-	const unsigned int bsize = 128 / 8;
-	struct skcipher_request subreq;
-	struct skcipher_walk walk;
-	bool fpu_enabled = false;
-	unsigned int nbytes, tail;
-	int err;
-
-	if (req->cryptlen < XTS_BLOCK_SIZE)
-		return -EINVAL;
-
-	if (unlikely(cts)) {
-		struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-
-		tail = req->cryptlen % XTS_BLOCK_SIZE + XTS_BLOCK_SIZE;
-
-		skcipher_request_set_tfm(&subreq, tfm);
-		skcipher_request_set_callback(&subreq,
-					      crypto_skcipher_get_flags(tfm),
-					      NULL, NULL);
-		skcipher_request_set_crypt(&subreq, req->src, req->dst,
-					   req->cryptlen - tail, req->iv);
-		req = &subreq;
-	}
-
-	err = skcipher_walk_virt(&walk, req, false);
-	nbytes = walk.nbytes;
-	if (err)
-		return err;
-
-	/* set minimum length to bsize, for tweak_fn */
-	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);
-
-	while (nbytes) {
-		nbytes = __glue_xts_req_128bit(gctx, crypt_ctx, &walk);
-
-		err = skcipher_walk_done(&walk, nbytes);
-		nbytes = walk.nbytes;
-	}
-
-	if (unlikely(cts)) {
-		u8 *next_tweak, *final_tweak = req->iv;
-		struct scatterlist *src, *dst;
-		struct scatterlist s[2], d[2];
-		le128 b[2];
-
-		dst = src = scatterwalk_ffwd(s, req->src, req->cryptlen);
-		if (req->dst != req->src)
-			dst = scatterwalk_ffwd(d, req->dst, req->cryptlen);
-
-		if (decrypt) {
-			next_tweak = memcpy(b, req->iv, XTS_BLOCK_SIZE);
-			gf128mul_x_ble(b, b);
-		} else {
-			next_tweak = req->iv;
-		}
-
-		skcipher_request_set_crypt(&subreq, src, dst, XTS_BLOCK_SIZE,
-					   next_tweak);
-
-		err = skcipher_walk_virt(&walk, req, false) ?:
-		      skcipher_walk_done(&walk,
-				__glue_xts_req_128bit(gctx, crypt_ctx, &walk));
-		if (err)
-			goto out;
-
-		scatterwalk_map_and_copy(b, dst, 0, XTS_BLOCK_SIZE, 0);
-		memcpy(b + 1, b, tail - XTS_BLOCK_SIZE);
-		scatterwalk_map_and_copy(b, src, XTS_BLOCK_SIZE,
-					 tail - XTS_BLOCK_SIZE, 0);
-		scatterwalk_map_and_copy(b, dst, 0, tail, 1);
-
-		skcipher_request_set_crypt(&subreq, dst, dst, XTS_BLOCK_SIZE,
-					   final_tweak);
-
-		err = skcipher_walk_virt(&walk, req, false) ?:
-		      skcipher_walk_done(&walk,
-				__glue_xts_req_128bit(gctx, crypt_ctx, &walk));
-	}
-
-out:
-	glue_fpu_end(fpu_enabled);
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(glue_xts_req_128bit);
-
-void glue_xts_crypt_128bit_one(const void *ctx, u8 *dst, const u8 *src,
-			       le128 *iv, common_glue_func_t fn)
-{
-	le128 ivblk = *iv;
-
-	/* generate next IV */
-	gf128mul_x_ble(iv, &ivblk);
-
-	/* CC <- T xor C */
-	u128_xor((u128 *)dst, (const u128 *)src, (u128 *)&ivblk);
-
-	/* PP <- D(Key2,CC) */
-	fn(ctx, dst, dst);
-
-	/* P <- T xor PP */
-	u128_xor((u128 *)dst, (u128 *)dst, (u128 *)&ivblk);
-}
-EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit_one);
-
-MODULE_LICENSE("GPL");
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index ba9e4c1e7f5c..b7ee24df7fba 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -18,10 +18,6 @@
 .align 16
 .Lbswap128_mask:
 	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
-.section	.rodata.cst16.xts_gf128mul_and_shl1_mask, "aM", @progbits, 16
-.align 16
-.Lxts_gf128mul_and_shl1_mask:
-	.byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0
 
 .text
 
@@ -715,67 +711,3 @@ SYM_FUNC_START(serpent_cbc_dec_8way_avx)
 	FRAME_END
 	ret;
 SYM_FUNC_END(serpent_cbc_dec_8way_avx)
-
-SYM_FUNC_START(serpent_ctr_8way_avx)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst
-	 *	%rdx: src
-	 *	%rcx: iv (little endian, 128bit)
-	 */
-	FRAME_BEGIN
-
-	load_ctr_8way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2,
-		      RD2, RK0, RK1, RK2);
-
-	call __serpent_enc_blk8_avx;
-
-	store_ctr_8way(%rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(serpent_ctr_8way_avx)
-
-SYM_FUNC_START(serpent_xts_enc_8way_avx)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst
-	 *	%rdx: src
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-	FRAME_BEGIN
-
-	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
-	load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
-		      RK0, RK1, RK2, .Lxts_gf128mul_and_shl1_mask);
-
-	call __serpent_enc_blk8_avx;
-
-	/* dst <= regs xor IVs(in dst) */
-	store_xts_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(serpent_xts_enc_8way_avx)
-
-SYM_FUNC_START(serpent_xts_dec_8way_avx)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst
-	 *	%rdx: src
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-	FRAME_BEGIN
-
-	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
-	load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
-		      RK0, RK1, RK2, .Lxts_gf128mul_and_shl1_mask);
-
-	call __serpent_dec_blk8_avx;
-
-	/* dst <= regs xor IVs(in dst) */
-	store_xts_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(serpent_xts_dec_8way_avx)
diff --git a/arch/x86/crypto/serpent-avx.h b/arch/x86/crypto/serpent-avx.h
new file mode 100644
index 000000000000..23f3361a0e72
--- /dev/null
+++ b/arch/x86/crypto/serpent-avx.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_X86_SERPENT_AVX_H
+#define ASM_X86_SERPENT_AVX_H
+
+#include <crypto/b128ops.h>
+#include <crypto/serpent.h>
+#include <linux/types.h>
+
+struct crypto_skcipher;
+
+#define SERPENT_PARALLEL_BLOCKS 8
+
+asmlinkage void serpent_ecb_enc_8way_avx(const void *ctx, u8 *dst,
+					 const u8 *src);
+asmlinkage void serpent_ecb_dec_8way_avx(const void *ctx, u8 *dst,
+					 const u8 *src);
+
+asmlinkage void serpent_cbc_dec_8way_avx(const void *ctx, u8 *dst,
+					 const u8 *src);
+
+#endif
diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S
index c9648aeae705..9161b6e441f3 100644
--- a/arch/x86/crypto/serpent-avx2-asm_64.S
+++ b/arch/x86/crypto/serpent-avx2-asm_64.S
@@ -20,16 +20,6 @@
 .Lbswap128_mask:
 	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
 
-.section	.rodata.cst16.xts_gf128mul_and_shl1_mask_0, "aM", @progbits, 16
-.align 16
-.Lxts_gf128mul_and_shl1_mask_0:
-	.byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0
-
-.section	.rodata.cst16.xts_gf128mul_and_shl1_mask_1, "aM", @progbits, 16
-.align 16
-.Lxts_gf128mul_and_shl1_mask_1:
-	.byte 0x0e, 1, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0
-
 .text
 
 #define CTX %rdi
@@ -734,80 +724,3 @@ SYM_FUNC_START(serpent_cbc_dec_16way)
 	FRAME_END
 	ret;
 SYM_FUNC_END(serpent_cbc_dec_16way)
-
-SYM_FUNC_START(serpent_ctr_16way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (16 blocks)
-	 *	%rdx: src (16 blocks)
-	 *	%rcx: iv (little endian, 128bit)
-	 */
-	FRAME_BEGIN
-
-	vzeroupper;
-
-	load_ctr_16way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2,
-		       RD2, RK0, RK0x, RK1, RK1x, RK2, RK2x, RK3, RK3x, RNOT,
-		       tp);
-
-	call __serpent_enc_blk16;
-
-	store_ctr_16way(%rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
-
-	vzeroupper;
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(serpent_ctr_16way)
-
-SYM_FUNC_START(serpent_xts_enc_16way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (16 blocks)
-	 *	%rdx: src (16 blocks)
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-	FRAME_BEGIN
-
-	vzeroupper;
-
-	load_xts_16way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2,
-		       RD2, RK0, RK0x, RK1, RK1x, RK2, RK2x, RK3, RK3x, RNOT,
-		       .Lxts_gf128mul_and_shl1_mask_0,
-		       .Lxts_gf128mul_and_shl1_mask_1);
-
-	call __serpent_enc_blk16;
-
-	store_xts_16way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
-
-	vzeroupper;
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(serpent_xts_enc_16way)
-
-SYM_FUNC_START(serpent_xts_dec_16way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst (16 blocks)
-	 *	%rdx: src (16 blocks)
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-	FRAME_BEGIN
-
-	vzeroupper;
-
-	load_xts_16way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2,
-		       RD2, RK0, RK0x, RK1, RK1x, RK2, RK2x, RK3, RK3x, RNOT,
-		       .Lxts_gf128mul_and_shl1_mask_0,
-		       .Lxts_gf128mul_and_shl1_mask_1);
-
-	call __serpent_dec_blk16;
-
-	store_xts_16way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
-
-	vzeroupper;
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(serpent_xts_dec_16way)
diff --git a/arch/x86/include/asm/crypto/serpent-sse2.h b/arch/x86/crypto/serpent-sse2.h
index 860ca248914b..860ca248914b 100644
--- a/arch/x86/include/asm/crypto/serpent-sse2.h
+++ b/arch/x86/crypto/serpent-sse2.h
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index f973ace44ad3..ccf0b5fa4933 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -12,9 +12,9 @@
 #include <crypto/algapi.h>
 #include <crypto/internal/simd.h>
 #include <crypto/serpent.h>
-#include <crypto/xts.h>
-#include <asm/crypto/glue_helper.h>
-#include <asm/crypto/serpent-avx.h>
+
+#include "serpent-avx.h"
+#include "ecb_cbc_helpers.h"
 
 #define SERPENT_AVX2_PARALLEL_BLOCKS 16
 
@@ -23,158 +23,44 @@ asmlinkage void serpent_ecb_enc_16way(const void *ctx, u8 *dst, const u8 *src);
 asmlinkage void serpent_ecb_dec_16way(const void *ctx, u8 *dst, const u8 *src);
 asmlinkage void serpent_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src);
 
-asmlinkage void serpent_ctr_16way(const void *ctx, u8 *dst, const u8 *src,
-				  le128 *iv);
-asmlinkage void serpent_xts_enc_16way(const void *ctx, u8 *dst, const u8 *src,
-				      le128 *iv);
-asmlinkage void serpent_xts_dec_16way(const void *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,
-
-	.funcs = { {
-		.num_blocks = 16,
-		.fn_u = { .ecb = serpent_ecb_enc_16way }
-	}, {
-		.num_blocks = 8,
-		.fn_u = { .ecb = serpent_ecb_enc_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = __serpent_encrypt }
-	} }
-};
-
-static const struct common_glue_ctx serpent_ctr = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = 8,
-
-	.funcs = { {
-		.num_blocks = 16,
-		.fn_u = { .ctr = serpent_ctr_16way }
-	},  {
-		.num_blocks = 8,
-		.fn_u = { .ctr = serpent_ctr_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ctr = __serpent_crypt_ctr }
-	} }
-};
-
-static const struct common_glue_ctx serpent_enc_xts = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = 8,
-
-	.funcs = { {
-		.num_blocks = 16,
-		.fn_u = { .xts = serpent_xts_enc_16way }
-	}, {
-		.num_blocks = 8,
-		.fn_u = { .xts = serpent_xts_enc_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = serpent_xts_enc }
-	} }
-};
-
-static const struct common_glue_ctx serpent_dec = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = 8,
-
-	.funcs = { {
-		.num_blocks = 16,
-		.fn_u = { .ecb = serpent_ecb_dec_16way }
-	}, {
-		.num_blocks = 8,
-		.fn_u = { .ecb = serpent_ecb_dec_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = __serpent_decrypt }
-	} }
-};
-
-static const struct common_glue_ctx serpent_dec_cbc = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = 8,
-
-	.funcs = { {
-		.num_blocks = 16,
-		.fn_u = { .cbc = serpent_cbc_dec_16way }
-	}, {
-		.num_blocks = 8,
-		.fn_u = { .cbc = serpent_cbc_dec_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .cbc = __serpent_decrypt }
-	} }
-};
-
-static const struct common_glue_ctx serpent_dec_xts = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = 8,
-
-	.funcs = { {
-		.num_blocks = 16,
-		.fn_u = { .xts = serpent_xts_dec_16way }
-	}, {
-		.num_blocks = 8,
-		.fn_u = { .xts = serpent_xts_dec_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = serpent_xts_dec }
-	} }
-};
-
 static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&serpent_enc, req);
+	ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS);
+	ECB_BLOCK(SERPENT_AVX2_PARALLEL_BLOCKS, serpent_ecb_enc_16way);
+	ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_ecb_enc_8way_avx);
+	ECB_BLOCK(1, __serpent_encrypt);
+	ECB_WALK_END();
 }
 
 static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&serpent_dec, req);
+	ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS);
+	ECB_BLOCK(SERPENT_AVX2_PARALLEL_BLOCKS, serpent_ecb_dec_16way);
+	ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_ecb_dec_8way_avx);
+	ECB_BLOCK(1, __serpent_decrypt);
+	ECB_WALK_END();
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_req_128bit(__serpent_encrypt, req);
+	CBC_WALK_START(req, SERPENT_BLOCK_SIZE, -1);
+	CBC_ENC_BLOCK(__serpent_encrypt);
+	CBC_WALK_END();
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_req_128bit(&serpent_dec_cbc, req);
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	return glue_ctr_req_128bit(&serpent_ctr, req);
-}
-
-static int xts_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&serpent_enc_xts, req,
-				   __serpent_encrypt, &ctx->tweak_ctx,
-				   &ctx->crypt_ctx, false);
-}
-
-static int xts_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&serpent_dec_xts, req,
-				   __serpent_encrypt, &ctx->tweak_ctx,
-				   &ctx->crypt_ctx, true);
+	CBC_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS);
+	CBC_DEC_BLOCK(SERPENT_AVX2_PARALLEL_BLOCKS, serpent_cbc_dec_16way);
+	CBC_DEC_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_cbc_dec_8way_avx);
+	CBC_DEC_BLOCK(1, __serpent_decrypt);
+	CBC_WALK_END();
 }
 
 static struct skcipher_alg serpent_algs[] = {
@@ -205,35 +91,6 @@ static struct skcipher_alg serpent_algs[] = {
 		.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,
 	},
 };
 
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index 7806d1cbe854..6c248e1ea4ef 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -15,9 +15,9 @@
 #include <crypto/algapi.h>
 #include <crypto/internal/simd.h>
 #include <crypto/serpent.h>
-#include <crypto/xts.h>
-#include <asm/crypto/glue_helper.h>
-#include <asm/crypto/serpent-avx.h>
+
+#include "serpent-avx.h"
+#include "ecb_cbc_helpers.h"
 
 /* 8-way parallel cipher functions */
 asmlinkage void serpent_ecb_enc_8way_avx(const void *ctx, u8 *dst,
@@ -32,191 +32,41 @@ asmlinkage void serpent_cbc_dec_8way_avx(const void *ctx, u8 *dst,
 					 const u8 *src);
 EXPORT_SYMBOL_GPL(serpent_cbc_dec_8way_avx);
 
-asmlinkage void serpent_ctr_8way_avx(const void *ctx, u8 *dst, const u8 *src,
-				     le128 *iv);
-EXPORT_SYMBOL_GPL(serpent_ctr_8way_avx);
-
-asmlinkage void serpent_xts_enc_8way_avx(const void *ctx, u8 *dst,
-					 const u8 *src, le128 *iv);
-EXPORT_SYMBOL_GPL(serpent_xts_enc_8way_avx);
-
-asmlinkage void serpent_xts_dec_8way_avx(const void *ctx, u8 *dst,
-					 const u8 *src, le128 *iv);
-EXPORT_SYMBOL_GPL(serpent_xts_dec_8way_avx);
-
-void __serpent_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv)
-{
-	be128 ctrblk;
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-
-	le128_to_be128(&ctrblk, iv);
-	le128_inc(iv);
-
-	__serpent_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
-	u128_xor(dst, src, (u128 *)&ctrblk);
-}
-EXPORT_SYMBOL_GPL(__serpent_crypt_ctr);
-
-void serpent_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	glue_xts_crypt_128bit_one(ctx, dst, src, iv, __serpent_encrypt);
-}
-EXPORT_SYMBOL_GPL(serpent_xts_enc);
-
-void serpent_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	glue_xts_crypt_128bit_one(ctx, dst, src, iv, __serpent_decrypt);
-}
-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,
-	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = SERPENT_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = serpent_ecb_enc_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = __serpent_encrypt }
-	} }
-};
-
-static const struct common_glue_ctx serpent_ctr = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = SERPENT_PARALLEL_BLOCKS,
-		.fn_u = { .ctr = serpent_ctr_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ctr = __serpent_crypt_ctr }
-	} }
-};
-
-static const struct common_glue_ctx serpent_enc_xts = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = SERPENT_PARALLEL_BLOCKS,
-		.fn_u = { .xts = serpent_xts_enc_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = serpent_xts_enc }
-	} }
-};
-
-static const struct common_glue_ctx serpent_dec = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = SERPENT_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = serpent_ecb_dec_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = __serpent_decrypt }
-	} }
-};
-
-static const struct common_glue_ctx serpent_dec_cbc = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = SERPENT_PARALLEL_BLOCKS,
-		.fn_u = { .cbc = serpent_cbc_dec_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .cbc = __serpent_decrypt }
-	} }
-};
-
-static const struct common_glue_ctx serpent_dec_xts = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = SERPENT_PARALLEL_BLOCKS,
-		.fn_u = { .xts = serpent_xts_dec_8way_avx }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = serpent_xts_dec }
-	} }
-};
-
 static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&serpent_enc, req);
+	ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS);
+	ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_ecb_enc_8way_avx);
+	ECB_BLOCK(1, __serpent_encrypt);
+	ECB_WALK_END();
 }
 
 static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&serpent_dec, req);
+	ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS);
+	ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_ecb_dec_8way_avx);
+	ECB_BLOCK(1, __serpent_decrypt);
+	ECB_WALK_END();
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_req_128bit(__serpent_encrypt, req);
+	CBC_WALK_START(req, SERPENT_BLOCK_SIZE, -1);
+	CBC_ENC_BLOCK(__serpent_encrypt);
+	CBC_WALK_END();
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_req_128bit(&serpent_dec_cbc, req);
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	return glue_ctr_req_128bit(&serpent_ctr, req);
-}
-
-static int xts_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&serpent_enc_xts, req,
-				   __serpent_encrypt, &ctx->tweak_ctx,
-				   &ctx->crypt_ctx, false);
-}
-
-static int xts_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&serpent_dec_xts, req,
-				   __serpent_encrypt, &ctx->tweak_ctx,
-				   &ctx->crypt_ctx, true);
+	CBC_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS);
+	CBC_DEC_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_cbc_dec_8way_avx);
+	CBC_DEC_BLOCK(1, __serpent_decrypt);
+	CBC_WALK_END();
 }
 
 static struct skcipher_alg serpent_algs[] = {
@@ -247,35 +97,6 @@ static struct skcipher_alg serpent_algs[] = {
 		.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,
 	},
 };
 
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 4fed8d26b91a..d78f37e9b2cf 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -10,8 +10,6 @@
  *
  * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
  *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
- * CTR part based on code (crypto/ctr.c) by:
- *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
  */
 
 #include <linux/module.h>
@@ -22,8 +20,9 @@
 #include <crypto/b128ops.h>
 #include <crypto/internal/simd.h>
 #include <crypto/serpent.h>
-#include <asm/crypto/serpent-sse2.h>
-#include <asm/crypto/glue_helper.h>
+
+#include "serpent-sse2.h"
+#include "ecb_cbc_helpers.h"
 
 static int serpent_setkey_skcipher(struct crypto_skcipher *tfm,
 				   const u8 *key, unsigned int keylen)
@@ -31,130 +30,46 @@ static int serpent_setkey_skcipher(struct crypto_skcipher *tfm,
 	return __serpent_setkey(crypto_skcipher_ctx(tfm), key, keylen);
 }
 
-static void serpent_decrypt_cbc_xway(const void *ctx, u8 *d, const u8 *s)
-{
-	u128 ivs[SERPENT_PARALLEL_BLOCKS - 1];
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-	unsigned int j;
-
-	for (j = 0; j < SERPENT_PARALLEL_BLOCKS - 1; j++)
-		ivs[j] = src[j];
-
-	serpent_dec_blk_xway(ctx, (u8 *)dst, (u8 *)src);
-
-	for (j = 0; j < SERPENT_PARALLEL_BLOCKS - 1; j++)
-		u128_xor(dst + (j + 1), dst + (j + 1), ivs + j);
-}
-
-static void serpent_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv)
-{
-	be128 ctrblk;
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-
-	le128_to_be128(&ctrblk, iv);
-	le128_inc(iv);
-
-	__serpent_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
-	u128_xor(dst, src, (u128 *)&ctrblk);
-}
-
-static void serpent_crypt_ctr_xway(const void *ctx, u8 *d, const u8 *s,
-				   le128 *iv)
+static void serpent_decrypt_cbc_xway(const void *ctx, u8 *dst, const u8 *src)
 {
-	be128 ctrblks[SERPENT_PARALLEL_BLOCKS];
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-	unsigned int i;
-
-	for (i = 0; i < SERPENT_PARALLEL_BLOCKS; i++) {
-		if (dst != src)
-			dst[i] = src[i];
-
-		le128_to_be128(&ctrblks[i], iv);
-		le128_inc(iv);
-	}
+	u8 buf[SERPENT_PARALLEL_BLOCKS - 1][SERPENT_BLOCK_SIZE];
+	const u8 *s = src;
 
-	serpent_enc_blk_xway_xor(ctx, (u8 *)dst, (u8 *)ctrblks);
+	if (dst == src)
+		s = memcpy(buf, src, sizeof(buf));
+	serpent_dec_blk_xway(ctx, dst, src);
+	crypto_xor(dst + SERPENT_BLOCK_SIZE, s, sizeof(buf));
 }
 
-static const struct common_glue_ctx serpent_enc = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = SERPENT_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = serpent_enc_blk_xway }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = __serpent_encrypt }
-	} }
-};
-
-static const struct common_glue_ctx serpent_ctr = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = SERPENT_PARALLEL_BLOCKS,
-		.fn_u = { .ctr = serpent_crypt_ctr_xway }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ctr = serpent_crypt_ctr }
-	} }
-};
-
-static const struct common_glue_ctx serpent_dec = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = SERPENT_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = serpent_dec_blk_xway }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = __serpent_decrypt }
-	} }
-};
-
-static const struct common_glue_ctx serpent_dec_cbc = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = SERPENT_PARALLEL_BLOCKS,
-		.fn_u = { .cbc = serpent_decrypt_cbc_xway }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .cbc = __serpent_decrypt }
-	} }
-};
-
 static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&serpent_enc, req);
+	ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS);
+	ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_enc_blk_xway);
+	ECB_BLOCK(1, __serpent_encrypt);
+	ECB_WALK_END();
 }
 
 static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&serpent_dec, req);
+	ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS);
+	ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_dec_blk_xway);
+	ECB_BLOCK(1, __serpent_decrypt);
+	ECB_WALK_END();
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_req_128bit(__serpent_encrypt,
-					   req);
+	CBC_WALK_START(req, SERPENT_BLOCK_SIZE, -1);
+	CBC_ENC_BLOCK(__serpent_encrypt);
+	CBC_WALK_END();
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_req_128bit(&serpent_dec_cbc, req);
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	return glue_ctr_req_128bit(&serpent_ctr, req);
+	CBC_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS);
+	CBC_DEC_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_decrypt_cbc_xway);
+	CBC_DEC_BLOCK(1, __serpent_decrypt);
+	CBC_WALK_END();
 }
 
 static struct skcipher_alg serpent_algs[] = {
@@ -185,21 +100,6 @@ static struct skcipher_alg serpent_algs[] = {
 		.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,
 	},
 };
 
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
index a5151393bb2f..37e63b3c664e 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -19,11 +19,6 @@
 .Lbswap128_mask:
 	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
 
-.section	.rodata.cst16.xts_gf128mul_and_shl1_mask, "aM", @progbits, 16
-.align 16
-.Lxts_gf128mul_and_shl1_mask:
-	.byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0
-
 .text
 
 /* structure of crypto context */
@@ -379,78 +374,3 @@ SYM_FUNC_START(twofish_cbc_dec_8way)
 	FRAME_END
 	ret;
 SYM_FUNC_END(twofish_cbc_dec_8way)
-
-SYM_FUNC_START(twofish_ctr_8way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst
-	 *	%rdx: src
-	 *	%rcx: iv (little endian, 128bit)
-	 */
-	FRAME_BEGIN
-
-	pushq %r12;
-
-	movq %rsi, %r11;
-	movq %rdx, %r12;
-
-	load_ctr_8way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2,
-		      RD2, RX0, RX1, RY0);
-
-	call __twofish_enc_blk8;
-
-	store_ctr_8way(%r12, %r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
-
-	popq %r12;
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(twofish_ctr_8way)
-
-SYM_FUNC_START(twofish_xts_enc_8way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst
-	 *	%rdx: src
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-	FRAME_BEGIN
-
-	movq %rsi, %r11;
-
-	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
-	load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
-		      RX0, RX1, RY0, .Lxts_gf128mul_and_shl1_mask);
-
-	call __twofish_enc_blk8;
-
-	/* dst <= regs xor IVs(in dst) */
-	store_xts_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(twofish_xts_enc_8way)
-
-SYM_FUNC_START(twofish_xts_dec_8way)
-	/* input:
-	 *	%rdi: ctx, CTX
-	 *	%rsi: dst
-	 *	%rdx: src
-	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
-	 */
-	FRAME_BEGIN
-
-	movq %rsi, %r11;
-
-	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
-	load_xts_8way(%rcx, %rdx, %rsi, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2,
-		      RX0, RX1, RY0, .Lxts_gf128mul_and_shl1_mask);
-
-	call __twofish_dec_blk8;
-
-	/* dst <= regs xor IVs(in dst) */
-	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
-
-	FRAME_END
-	ret;
-SYM_FUNC_END(twofish_xts_dec_8way)
diff --git a/arch/x86/include/asm/crypto/twofish.h b/arch/x86/crypto/twofish.h
index 2c377a8042e1..12df400e6d53 100644
--- a/arch/x86/include/asm/crypto/twofish.h
+++ b/arch/x86/crypto/twofish.h
@@ -17,9 +17,5 @@ asmlinkage void twofish_dec_blk_3way(const void *ctx, u8 *dst, const u8 *src);
 
 /* helpers from twofish_x86_64-3way module */
 extern void twofish_dec_blk_cbc_3way(const void *ctx, u8 *dst, const u8 *src);
-extern void twofish_enc_blk_ctr(const void *ctx, u8 *dst, const u8 *src,
-				le128 *iv);
-extern void twofish_enc_blk_ctr_3way(const void *ctx, u8 *dst, const u8 *src,
-				     le128 *iv);
 
 #endif /* ASM_X86_TWOFISH_H */
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index 2dbc8ce3730e..3eb3440b477a 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -15,9 +15,9 @@
 #include <crypto/algapi.h>
 #include <crypto/internal/simd.h>
 #include <crypto/twofish.h>
-#include <crypto/xts.h>
-#include <asm/crypto/glue_helper.h>
-#include <asm/crypto/twofish.h>
+
+#include "twofish.h"
+#include "ecb_cbc_helpers.h"
 
 #define TWOFISH_PARALLEL_BLOCKS 8
 
@@ -26,13 +26,6 @@ asmlinkage void twofish_ecb_enc_8way(const void *ctx, u8 *dst, const u8 *src);
 asmlinkage void twofish_ecb_dec_8way(const void *ctx, u8 *dst, const u8 *src);
 
 asmlinkage void twofish_cbc_dec_8way(const void *ctx, u8 *dst, const u8 *src);
-asmlinkage void twofish_ctr_8way(const void *ctx, u8 *dst, const u8 *src,
-				 le128 *iv);
-
-asmlinkage void twofish_xts_enc_8way(const void *ctx, u8 *dst, const u8 *src,
-				     le128 *iv);
-asmlinkage void twofish_xts_dec_8way(const void *ctx, u8 *dst, const u8 *src,
-				     le128 *iv);
 
 static int twofish_setkey_skcipher(struct crypto_skcipher *tfm,
 				   const u8 *key, unsigned int keylen)
@@ -45,171 +38,38 @@ static inline void twofish_enc_blk_3way(const void *ctx, u8 *dst, const u8 *src)
 	__twofish_enc_blk_3way(ctx, dst, src, false);
 }
 
-static void twofish_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	glue_xts_crypt_128bit_one(ctx, dst, src, iv, twofish_enc_blk);
-}
-
-static void twofish_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv)
-{
-	glue_xts_crypt_128bit_one(ctx, dst, src, iv, 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);
-	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);
-	if (err)
-		return err;
-
-	/* second half of xts-key is for tweak */
-	return __twofish_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2);
-}
-
-static const struct common_glue_ctx twofish_enc = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = TWOFISH_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = twofish_ecb_enc_8way }
-	}, {
-		.num_blocks = 3,
-		.fn_u = { .ecb = twofish_enc_blk_3way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = twofish_enc_blk }
-	} }
-};
-
-static const struct common_glue_ctx twofish_ctr = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = TWOFISH_PARALLEL_BLOCKS,
-		.fn_u = { .ctr = twofish_ctr_8way }
-	}, {
-		.num_blocks = 3,
-		.fn_u = { .ctr = twofish_enc_blk_ctr_3way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ctr = twofish_enc_blk_ctr }
-	} }
-};
-
-static const struct common_glue_ctx twofish_enc_xts = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = TWOFISH_PARALLEL_BLOCKS,
-		.fn_u = { .xts = twofish_xts_enc_8way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = twofish_xts_enc }
-	} }
-};
-
-static const struct common_glue_ctx twofish_dec = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = TWOFISH_PARALLEL_BLOCKS,
-		.fn_u = { .ecb = twofish_ecb_dec_8way }
-	}, {
-		.num_blocks = 3,
-		.fn_u = { .ecb = twofish_dec_blk_3way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = twofish_dec_blk }
-	} }
-};
-
-static const struct common_glue_ctx twofish_dec_cbc = {
-	.num_funcs = 3,
-	.fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = TWOFISH_PARALLEL_BLOCKS,
-		.fn_u = { .cbc = twofish_cbc_dec_8way }
-	}, {
-		.num_blocks = 3,
-		.fn_u = { .cbc = twofish_dec_blk_cbc_3way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .cbc = twofish_dec_blk }
-	} }
-};
-
-static const struct common_glue_ctx twofish_dec_xts = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS,
-
-	.funcs = { {
-		.num_blocks = TWOFISH_PARALLEL_BLOCKS,
-		.fn_u = { .xts = twofish_xts_dec_8way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .xts = twofish_xts_dec }
-	} }
-};
-
 static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&twofish_enc, req);
+	ECB_WALK_START(req, TF_BLOCK_SIZE, TWOFISH_PARALLEL_BLOCKS);
+	ECB_BLOCK(TWOFISH_PARALLEL_BLOCKS, twofish_ecb_enc_8way);
+	ECB_BLOCK(3, twofish_enc_blk_3way);
+	ECB_BLOCK(1, twofish_enc_blk);
+	ECB_WALK_END();
 }
 
 static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&twofish_dec, req);
+	ECB_WALK_START(req, TF_BLOCK_SIZE, TWOFISH_PARALLEL_BLOCKS);
+	ECB_BLOCK(TWOFISH_PARALLEL_BLOCKS, twofish_ecb_dec_8way);
+	ECB_BLOCK(3, twofish_dec_blk_3way);
+	ECB_BLOCK(1, twofish_dec_blk);
+	ECB_WALK_END();
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_req_128bit(twofish_enc_blk, req);
+	CBC_WALK_START(req, TF_BLOCK_SIZE, -1);
+	CBC_ENC_BLOCK(twofish_enc_blk);
+	CBC_WALK_END();
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_req_128bit(&twofish_dec_cbc, req);
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	return glue_ctr_req_128bit(&twofish_ctr, req);
-}
-
-static int xts_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&twofish_enc_xts, req, twofish_enc_blk,
-				   &ctx->tweak_ctx, &ctx->crypt_ctx, false);
-}
-
-static int xts_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return glue_xts_req_128bit(&twofish_dec_xts, req, twofish_enc_blk,
-				   &ctx->tweak_ctx, &ctx->crypt_ctx, true);
+	CBC_WALK_START(req, TF_BLOCK_SIZE, TWOFISH_PARALLEL_BLOCKS);
+	CBC_DEC_BLOCK(TWOFISH_PARALLEL_BLOCKS, twofish_cbc_dec_8way);
+	CBC_DEC_BLOCK(3, twofish_dec_blk_cbc_3way);
+	CBC_DEC_BLOCK(1, twofish_dec_blk);
+	CBC_WALK_END();
 }
 
 static struct skcipher_alg twofish_algs[] = {
@@ -240,35 +100,6 @@ static struct skcipher_alg twofish_algs[] = {
 		.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,
 	},
 };
 
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 768af6075479..03725696397c 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -5,17 +5,16 @@
  * Copyright (c) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
  */
 
-#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 "twofish.h"
+#include "ecb_cbc_helpers.h"
+
 EXPORT_SYMBOL_GPL(__twofish_enc_blk_3way);
 EXPORT_SYMBOL_GPL(twofish_dec_blk_3way);
 
@@ -30,143 +29,48 @@ static inline void twofish_enc_blk_3way(const void *ctx, u8 *dst, const u8 *src)
 	__twofish_enc_blk_3way(ctx, dst, src, false);
 }
 
-static inline void twofish_enc_blk_xor_3way(const void *ctx, u8 *dst,
-					    const u8 *src)
-{
-	__twofish_enc_blk_3way(ctx, dst, src, true);
-}
-
-void twofish_dec_blk_cbc_3way(const void *ctx, u8 *d, const u8 *s)
+void twofish_dec_blk_cbc_3way(const void *ctx, u8 *dst, const u8 *src)
 {
-	u128 ivs[2];
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-
-	ivs[0] = src[0];
-	ivs[1] = src[1];
+	u8 buf[2][TF_BLOCK_SIZE];
+	const u8 *s = src;
 
-	twofish_dec_blk_3way(ctx, (u8 *)dst, (u8 *)src);
+	if (dst == src)
+		s = memcpy(buf, src, sizeof(buf));
+	twofish_dec_blk_3way(ctx, dst, src);
+	crypto_xor(dst + TF_BLOCK_SIZE, s, sizeof(buf));
 
-	u128_xor(&dst[1], &dst[1], &ivs[0]);
-	u128_xor(&dst[2], &dst[2], &ivs[1]);
 }
 EXPORT_SYMBOL_GPL(twofish_dec_blk_cbc_3way);
 
-void twofish_enc_blk_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv)
-{
-	be128 ctrblk;
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-
-	if (dst != src)
-		*dst = *src;
-
-	le128_to_be128(&ctrblk, iv);
-	le128_inc(iv);
-
-	twofish_enc_blk(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
-	u128_xor(dst, dst, (u128 *)&ctrblk);
-}
-EXPORT_SYMBOL_GPL(twofish_enc_blk_ctr);
-
-void twofish_enc_blk_ctr_3way(const void *ctx, u8 *d, const u8 *s, le128 *iv)
-{
-	be128 ctrblks[3];
-	u128 *dst = (u128 *)d;
-	const u128 *src = (const u128 *)s;
-
-	if (dst != src) {
-		dst[0] = src[0];
-		dst[1] = src[1];
-		dst[2] = src[2];
-	}
-
-	le128_to_be128(&ctrblks[0], iv);
-	le128_inc(iv);
-	le128_to_be128(&ctrblks[1], iv);
-	le128_inc(iv);
-	le128_to_be128(&ctrblks[2], iv);
-	le128_inc(iv);
-
-	twofish_enc_blk_xor_3way(ctx, (u8 *)dst, (u8 *)ctrblks);
-}
-EXPORT_SYMBOL_GPL(twofish_enc_blk_ctr_3way);
-
-static const struct common_glue_ctx twofish_enc = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = -1,
-
-	.funcs = { {
-		.num_blocks = 3,
-		.fn_u = { .ecb = twofish_enc_blk_3way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = twofish_enc_blk }
-	} }
-};
-
-static const struct common_glue_ctx twofish_ctr = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = -1,
-
-	.funcs = { {
-		.num_blocks = 3,
-		.fn_u = { .ctr = twofish_enc_blk_ctr_3way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ctr = twofish_enc_blk_ctr }
-	} }
-};
-
-static const struct common_glue_ctx twofish_dec = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = -1,
-
-	.funcs = { {
-		.num_blocks = 3,
-		.fn_u = { .ecb = twofish_dec_blk_3way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .ecb = twofish_dec_blk }
-	} }
-};
-
-static const struct common_glue_ctx twofish_dec_cbc = {
-	.num_funcs = 2,
-	.fpu_blocks_limit = -1,
-
-	.funcs = { {
-		.num_blocks = 3,
-		.fn_u = { .cbc = twofish_dec_blk_cbc_3way }
-	}, {
-		.num_blocks = 1,
-		.fn_u = { .cbc = twofish_dec_blk }
-	} }
-};
-
 static int ecb_encrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&twofish_enc, req);
+	ECB_WALK_START(req, TF_BLOCK_SIZE, -1);
+	ECB_BLOCK(3, twofish_enc_blk_3way);
+	ECB_BLOCK(1, twofish_enc_blk);
+	ECB_WALK_END();
 }
 
 static int ecb_decrypt(struct skcipher_request *req)
 {
-	return glue_ecb_req_128bit(&twofish_dec, req);
+	ECB_WALK_START(req, TF_BLOCK_SIZE, -1);
+	ECB_BLOCK(3, twofish_dec_blk_3way);
+	ECB_BLOCK(1, twofish_dec_blk);
+	ECB_WALK_END();
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
 {
-	return glue_cbc_encrypt_req_128bit(twofish_enc_blk, req);
+	CBC_WALK_START(req, TF_BLOCK_SIZE, -1);
+	CBC_ENC_BLOCK(twofish_enc_blk);
+	CBC_WALK_END();
 }
 
 static int cbc_decrypt(struct skcipher_request *req)
 {
-	return glue_cbc_decrypt_req_128bit(&twofish_dec_cbc, req);
-}
-
-static int ctr_crypt(struct skcipher_request *req)
-{
-	return glue_ctr_req_128bit(&twofish_ctr, req);
+	CBC_WALK_START(req, TF_BLOCK_SIZE, -1);
+	CBC_DEC_BLOCK(3, twofish_dec_blk_cbc_3way);
+	CBC_DEC_BLOCK(1, twofish_dec_blk);
+	CBC_WALK_END();
 }
 
 static struct skcipher_alg tf_skciphers[] = {
@@ -195,20 +99,6 @@ static struct skcipher_alg tf_skciphers[] = {
 		.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,
 	},
 };
 
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
deleted file mode 100644
index 777c0f63418c..000000000000
--- a/arch/x86/include/asm/crypto/glue_helper.h
+++ /dev/null
@@ -1,118 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Shared glue code for 128bit block ciphers
- */
-
-#ifndef _CRYPTO_GLUE_HELPER_H
-#define _CRYPTO_GLUE_HELPER_H
-
-#include <crypto/internal/skcipher.h>
-#include <linux/kernel.h>
-#include <asm/fpu/api.h>
-#include <crypto/b128ops.h>
-
-typedef void (*common_glue_func_t)(const void *ctx, u8 *dst, const u8 *src);
-typedef void (*common_glue_cbc_func_t)(const void *ctx, u8 *dst, const u8 *src);
-typedef void (*common_glue_ctr_func_t)(const void *ctx, u8 *dst, const u8 *src,
-				       le128 *iv);
-typedef void (*common_glue_xts_func_t)(const void *ctx, u8 *dst, const u8 *src,
-				       le128 *iv);
-
-struct common_glue_func_entry {
-	unsigned int num_blocks; /* number of blocks that @fn will process */
-	union {
-		common_glue_func_t ecb;
-		common_glue_cbc_func_t cbc;
-		common_glue_ctr_func_t ctr;
-		common_glue_xts_func_t xts;
-	} fn_u;
-};
-
-struct common_glue_ctx {
-	unsigned int num_funcs;
-	int fpu_blocks_limit; /* -1 means fpu not needed at all */
-
-	/*
-	 * First funcs entry must have largest num_blocks and last funcs entry
-	 * must have num_blocks == 1!
-	 */
-	struct common_glue_func_entry funcs[];
-};
-
-static inline bool glue_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);
-
-	kernel_fpu_begin();
-	return true;
-}
-
-static inline void glue_fpu_end(bool fpu_enabled)
-{
-	if (fpu_enabled)
-		kernel_fpu_end();
-}
-
-static inline void le128_to_be128(be128 *dst, const le128 *src)
-{
-	dst->a = cpu_to_be64(le64_to_cpu(src->a));
-	dst->b = cpu_to_be64(le64_to_cpu(src->b));
-}
-
-static inline void be128_to_le128(le128 *dst, const be128 *src)
-{
-	dst->a = cpu_to_le64(be64_to_cpu(src->a));
-	dst->b = cpu_to_le64(be64_to_cpu(src->b));
-}
-
-static inline void le128_inc(le128 *i)
-{
-	u64 a = le64_to_cpu(i->a);
-	u64 b = le64_to_cpu(i->b);
-
-	b++;
-	if (!b)
-		a++;
-
-	i->a = cpu_to_le64(a);
-	i->b = cpu_to_le64(b);
-}
-
-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,
-			       common_glue_func_t tweak_fn, void *tweak_ctx,
-			       void *crypt_ctx, bool decrypt);
-
-extern void glue_xts_crypt_128bit_one(const void *ctx, u8 *dst,
-				      const u8 *src, le128 *iv,
-				      common_glue_func_t fn);
-
-#endif /* _CRYPTO_GLUE_HELPER_H */
diff --git a/arch/x86/include/asm/crypto/serpent-avx.h b/arch/x86/include/asm/crypto/serpent-avx.h
deleted file mode 100644
index 251c2c89d7cf..000000000000
--- a/arch/x86/include/asm/crypto/serpent-avx.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_X86_SERPENT_AVX_H
-#define ASM_X86_SERPENT_AVX_H
-
-#include <crypto/b128ops.h>
-#include <crypto/serpent.h>
-#include <linux/types.h>
-
-struct crypto_skcipher;
-
-#define SERPENT_PARALLEL_BLOCKS 8
-
-struct serpent_xts_ctx {
-	struct serpent_ctx tweak_ctx;
-	struct serpent_ctx crypt_ctx;
-};
-
-asmlinkage void serpent_ecb_enc_8way_avx(const void *ctx, u8 *dst,
-					 const u8 *src);
-asmlinkage void serpent_ecb_dec_8way_avx(const void *ctx, u8 *dst,
-					 const u8 *src);
-
-asmlinkage void serpent_cbc_dec_8way_avx(const void *ctx, u8 *dst,
-					 const u8 *src);
-asmlinkage void serpent_ctr_8way_avx(const void *ctx, u8 *dst, const u8 *src,
-				     le128 *iv);
-
-asmlinkage void serpent_xts_enc_8way_avx(const void *ctx, u8 *dst,
-					 const u8 *src, le128 *iv);
-asmlinkage void serpent_xts_dec_8way_avx(const void *ctx, u8 *dst,
-					 const u8 *src, le128 *iv);
-
-extern void __serpent_crypt_ctr(const void *ctx, u8 *dst, const u8 *src,
-				le128 *iv);
-
-extern void serpent_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv);
-extern void serpent_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv);
-
-extern int xts_serpent_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			      unsigned int keylen);
-
-#endif
diff --git a/crypto/Kconfig b/crypto/Kconfig
index a367fcfeb5d4..15c9c28d9f53 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -210,11 +210,6 @@ config CRYPTO_SIMD
 	tristate
 	select CRYPTO_CRYPTD
 
-config CRYPTO_GLUE_HELPER_X86
-	tristate
-	depends on X86
-	select CRYPTO_SKCIPHER
-
 config CRYPTO_ENGINE
 	tristate
 
@@ -822,19 +817,6 @@ config CRYPTO_MICHAEL_MIC
 	  should not be used for other purposes because of the weakness
 	  of the algorithm.
 
-config CRYPTO_RMD128
-	tristate "RIPEMD-128 digest algorithm"
-	select CRYPTO_HASH
-	help
-	  RIPEMD-128 (ISO/IEC 10118-3:2004).
-
-	  RIPEMD-128 is a 128-bit cryptographic hash function. It should only
-	  be used as a secure replacement for RIPEMD. For other use cases,
-	  RIPEMD-160 should be used.
-
-	  Developed by Hans Dobbertin, Antoon Bosselaers and Bart Preneel.
-	  See <https://homes.esat.kuleuven.be/~bosselae/ripemd160.html>
-
 config CRYPTO_RMD160
 	tristate "RIPEMD-160 digest algorithm"
 	select CRYPTO_HASH
@@ -852,30 +834,6 @@ config CRYPTO_RMD160
 	  Developed by Hans Dobbertin, Antoon Bosselaers and Bart Preneel.
 	  See <https://homes.esat.kuleuven.be/~bosselae/ripemd160.html>
 
-config CRYPTO_RMD256
-	tristate "RIPEMD-256 digest algorithm"
-	select CRYPTO_HASH
-	help
-	  RIPEMD-256 is an optional extension of RIPEMD-128 with a
-	  256 bit hash. It is intended for applications that require
-	  longer hash-results, without needing a larger security level
-	  (than RIPEMD-128).
-
-	  Developed by Hans Dobbertin, Antoon Bosselaers and Bart Preneel.
-	  See <https://homes.esat.kuleuven.be/~bosselae/ripemd160.html>
-
-config CRYPTO_RMD320
-	tristate "RIPEMD-320 digest algorithm"
-	select CRYPTO_HASH
-	help
-	  RIPEMD-320 is an optional extension of RIPEMD-160 with a
-	  320 bit hash. It is intended for applications that require
-	  longer hash-results, without needing a larger security level
-	  (than RIPEMD-160).
-
-	  Developed by Hans Dobbertin, Antoon Bosselaers and Bart Preneel.
-	  See <https://homes.esat.kuleuven.be/~bosselae/ripemd160.html>
-
 config CRYPTO_SHA1
 	tristate "SHA1 digest algorithm"
 	select CRYPTO_HASH
@@ -1051,19 +1009,6 @@ config CRYPTO_STREEBOG
 	  https://tc26.ru/upload/iblock/fed/feddbb4d26b685903faa2ba11aea43f6.pdf
 	  https://tools.ietf.org/html/rfc6986
 
-config CRYPTO_TGR192
-	tristate "Tiger digest algorithms"
-	select CRYPTO_HASH
-	help
-	  Tiger hash algorithm 192, 160 and 128-bit hashes
-
-	  Tiger is a hash function optimized for 64-bit processors while
-	  still having decent performance on 32-bit processors.
-	  Tiger was developed by Ross Anderson and Eli Biham.
-
-	  See also:
-	  <https://www.cs.technion.ac.il/~biham/Reports/Tiger/>.
-
 config CRYPTO_WP512
 	tristate "Whirlpool digest algorithms"
 	select CRYPTO_HASH
@@ -1133,7 +1078,6 @@ config CRYPTO_AES_NI_INTEL
 	select CRYPTO_LIB_AES
 	select CRYPTO_ALGAPI
 	select CRYPTO_SKCIPHER
-	select CRYPTO_GLUE_HELPER_X86 if 64BIT
 	select CRYPTO_SIMD
 	help
 	  Use Intel AES-NI instructions for AES algorithm.
@@ -1256,6 +1200,7 @@ config CRYPTO_BLOWFISH_X86_64
 	depends on X86 && 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_BLOWFISH_COMMON
+	imply CRYPTO_CTR
 	help
 	  Blowfish cipher algorithm (x86_64), by Bruce Schneier.
 
@@ -1286,7 +1231,7 @@ config CRYPTO_CAMELLIA_X86_64
 	depends on X86 && 64BIT
 	depends on CRYPTO
 	select CRYPTO_SKCIPHER
-	select CRYPTO_GLUE_HELPER_X86
+	imply CRYPTO_CTR
 	help
 	  Camellia cipher algorithm module (x86_64).
 
@@ -1304,9 +1249,8 @@ config CRYPTO_CAMELLIA_AESNI_AVX_X86_64
 	depends on CRYPTO
 	select CRYPTO_SKCIPHER
 	select CRYPTO_CAMELLIA_X86_64
-	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SIMD
-	select CRYPTO_XTS
+	imply CRYPTO_XTS
 	help
 	  Camellia cipher algorithm module (x86_64/AES-NI/AVX).
 
@@ -1372,6 +1316,7 @@ config CRYPTO_CAST5_AVX_X86_64
 	select CRYPTO_CAST5
 	select CRYPTO_CAST_COMMON
 	select CRYPTO_SIMD
+	imply CRYPTO_CTR
 	help
 	  The CAST5 encryption algorithm (synonymous with CAST-128) is
 	  described in RFC2144.
@@ -1393,9 +1338,9 @@ config CRYPTO_CAST6_AVX_X86_64
 	select CRYPTO_SKCIPHER
 	select CRYPTO_CAST6
 	select CRYPTO_CAST_COMMON
-	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SIMD
-	select CRYPTO_XTS
+	imply CRYPTO_XTS
+	imply CRYPTO_CTR
 	help
 	  The CAST6 encryption algorithm (synonymous with CAST-256) is
 	  described in RFC2612.
@@ -1425,6 +1370,7 @@ config CRYPTO_DES3_EDE_X86_64
 	depends on X86 && 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
+	imply CRYPTO_CTR
 	help
 	  Triple DES EDE (FIPS 46-3) algorithm.
 
@@ -1454,18 +1400,6 @@ config CRYPTO_KHAZAD
 	  See also:
 	  <http://www.larc.usp.br/~pbarreto/KhazadPage.html>
 
-config CRYPTO_SALSA20
-	tristate "Salsa20 stream cipher algorithm"
-	select CRYPTO_SKCIPHER
-	help
-	  Salsa20 stream cipher algorithm.
-
-	  Salsa20 is a stream cipher submitted to eSTREAM, the ECRYPT
-	  Stream Cipher Project. See <https://www.ecrypt.eu.org/stream/>
-
-	  The Salsa20 stream cipher algorithm is designed by Daniel J.
-	  Bernstein <djb@cr.yp.to>. See <https://cr.yp.to/snuffle.html>
-
 config CRYPTO_CHACHA20
 	tristate "ChaCha stream cipher algorithms"
 	select CRYPTO_LIB_CHACHA_GENERIC
@@ -1526,8 +1460,7 @@ config CRYPTO_SERPENT
 	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
 
 	  Keys are allowed to be from 0 to 256 bits in length, in steps
-	  of 8 bits.  Also includes the 'Tnepres' algorithm, a reversed
-	  variant of Serpent for compatibility with old kerneli.org code.
+	  of 8 bits.
 
 	  See also:
 	  <https://www.cl.cam.ac.uk/~rja14/serpent.html>
@@ -1536,9 +1469,9 @@ config CRYPTO_SERPENT_SSE2_X86_64
 	tristate "Serpent cipher algorithm (x86_64/SSE2)"
 	depends on X86 && 64BIT
 	select CRYPTO_SKCIPHER
-	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SERPENT
 	select CRYPTO_SIMD
+	imply CRYPTO_CTR
 	help
 	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
 
@@ -1555,9 +1488,9 @@ config CRYPTO_SERPENT_SSE2_586
 	tristate "Serpent cipher algorithm (i586/SSE2)"
 	depends on X86 && !64BIT
 	select CRYPTO_SKCIPHER
-	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SERPENT
 	select CRYPTO_SIMD
+	imply CRYPTO_CTR
 	help
 	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
 
@@ -1574,10 +1507,10 @@ config CRYPTO_SERPENT_AVX_X86_64
 	tristate "Serpent cipher algorithm (x86_64/AVX)"
 	depends on X86 && 64BIT
 	select CRYPTO_SKCIPHER
-	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SERPENT
 	select CRYPTO_SIMD
-	select CRYPTO_XTS
+	imply CRYPTO_XTS
+	imply CRYPTO_CTR
 	help
 	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
 
@@ -1675,6 +1608,7 @@ config CRYPTO_TWOFISH_586
 	depends on (X86 || UML_X86) && !64BIT
 	select CRYPTO_ALGAPI
 	select CRYPTO_TWOFISH_COMMON
+	imply CRYPTO_CTR
 	help
 	  Twofish cipher algorithm.
 
@@ -1691,6 +1625,7 @@ config CRYPTO_TWOFISH_X86_64
 	depends on (X86 || UML_X86) && 64BIT
 	select CRYPTO_ALGAPI
 	select CRYPTO_TWOFISH_COMMON
+	imply CRYPTO_CTR
 	help
 	  Twofish cipher algorithm (x86_64).
 
@@ -1708,7 +1643,6 @@ config CRYPTO_TWOFISH_X86_64_3WAY
 	select CRYPTO_SKCIPHER
 	select CRYPTO_TWOFISH_COMMON
 	select CRYPTO_TWOFISH_X86_64
-	select CRYPTO_GLUE_HELPER_X86
 	help
 	  Twofish cipher algorithm (x86_64, 3-way parallel).
 
@@ -1727,11 +1661,11 @@ config CRYPTO_TWOFISH_AVX_X86_64
 	tristate "Twofish cipher algorithm (x86_64/AVX)"
 	depends on X86 && 64BIT
 	select CRYPTO_SKCIPHER
-	select CRYPTO_GLUE_HELPER_X86
 	select CRYPTO_SIMD
 	select CRYPTO_TWOFISH_COMMON
 	select CRYPTO_TWOFISH_X86_64
 	select CRYPTO_TWOFISH_X86_64_3WAY
+	imply CRYPTO_XTS
 	help
 	  Twofish cipher algorithm (x86_64/AVX).
 
diff --git a/crypto/Makefile b/crypto/Makefile
index b279483fba50..cf23affb1678 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -67,9 +67,7 @@ obj-$(CONFIG_CRYPTO_XCBC) += xcbc.o
 obj-$(CONFIG_CRYPTO_NULL2) += crypto_null.o
 obj-$(CONFIG_CRYPTO_MD4) += md4.o
 obj-$(CONFIG_CRYPTO_MD5) += md5.o
-obj-$(CONFIG_CRYPTO_RMD128) += rmd128.o
 obj-$(CONFIG_CRYPTO_RMD160) += rmd160.o
-obj-$(CONFIG_CRYPTO_RMD256) += rmd256.o
 obj-$(CONFIG_CRYPTO_RMD320) += rmd320.o
 obj-$(CONFIG_CRYPTO_SHA1) += sha1_generic.o
 obj-$(CONFIG_CRYPTO_SHA256) += sha256_generic.o
@@ -79,7 +77,6 @@ obj-$(CONFIG_CRYPTO_SM3) += sm3_generic.o
 obj-$(CONFIG_CRYPTO_STREEBOG) += streebog_generic.o
 obj-$(CONFIG_CRYPTO_WP512) += wp512.o
 CFLAGS_wp512.o := $(call cc-option,-fno-schedule-insns)  # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149
-obj-$(CONFIG_CRYPTO_TGR192) += tgr192.o
 obj-$(CONFIG_CRYPTO_BLAKE2B) += blake2b_generic.o
 obj-$(CONFIG_CRYPTO_BLAKE2S) += blake2s_generic.o
 obj-$(CONFIG_CRYPTO_GF128MUL) += gf128mul.o
@@ -141,7 +138,6 @@ obj-$(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_SALSA20) += salsa20_generic.o
 obj-$(CONFIG_CRYPTO_CHACHA20) += chacha_generic.o
 obj-$(CONFIG_CRYPTO_POLY1305) += poly1305_generic.o
 obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o
diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index ce4d5725342c..84450130cb6b 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -32,6 +32,7 @@
 
 #include <crypto/b128ops.h>
 #include <crypto/chacha.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/poly1305.h>
 #include <crypto/internal/skcipher.h>
@@ -616,3 +617,4 @@ MODULE_DESCRIPTION("Adiantum length-preserving encryption mode");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
 MODULE_ALIAS_CRYPTO("adiantum");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c
index c475c1129ff2..3f512efaba3a 100644
--- a/crypto/ansi_cprng.c
+++ b/crypto/ansi_cprng.c
@@ -7,6 +7,7 @@
  *  (C) Neil Horman <nhorman@tuxdriver.com>
  */
 
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/rng.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -470,3 +471,4 @@ subsys_initcall(prng_mod_init);
 module_exit(prng_mod_fini);
 MODULE_ALIAS_CRYPTO("stdrng");
 MODULE_ALIAS_CRYPTO("ansi_cprng");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/blake2b_generic.c b/crypto/blake2b_generic.c
index a2ffe60e06d3..6704c0355889 100644
--- a/crypto/blake2b_generic.c
+++ b/crypto/blake2b_generic.c
@@ -1,55 +1,27 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR Apache-2.0)
 /*
- * BLAKE2b reference source code package - reference C implementations
+ * Generic implementation of the BLAKE2b digest algorithm.  Based on the BLAKE2b
+ * reference implementation, but it has been heavily modified for use in the
+ * kernel.  The reference implementation was:
  *
- * Copyright 2012, Samuel Neves <sneves@dei.uc.pt>.  You may use this under the
- * terms of the CC0, the OpenSSL Licence, or the Apache Public License 2.0, at
- * your option.  The terms of these licenses can be found at:
+ *	Copyright 2012, Samuel Neves <sneves@dei.uc.pt>.  You may use this under
+ *	the terms of the CC0, the OpenSSL Licence, or the Apache Public License
+ *	2.0, at your option.  The terms of these licenses can be found at:
  *
- * - CC0 1.0 Universal : http://creativecommons.org/publicdomain/zero/1.0
- * - OpenSSL license   : https://www.openssl.org/source/license.html
- * - Apache 2.0        : https://www.apache.org/licenses/LICENSE-2.0
+ *	- CC0 1.0 Universal : http://creativecommons.org/publicdomain/zero/1.0
+ *	- OpenSSL license   : https://www.openssl.org/source/license.html
+ *	- Apache 2.0        : https://www.apache.org/licenses/LICENSE-2.0
  *
- * More information about the BLAKE2 hash function can be found at
- * https://blake2.net.
- *
- * Note: the original sources have been modified for inclusion in linux kernel
- * in terms of coding style, using generic helpers and simplifications of error
- * handling.
+ * More information about BLAKE2 can be found at https://blake2.net.
  */
 
 #include <asm/unaligned.h>
 #include <linux/module.h>
-#include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
+#include <crypto/internal/blake2b.h>
 #include <crypto/internal/hash.h>
 
-#define BLAKE2B_160_DIGEST_SIZE		(160 / 8)
-#define BLAKE2B_256_DIGEST_SIZE		(256 / 8)
-#define BLAKE2B_384_DIGEST_SIZE		(384 / 8)
-#define BLAKE2B_512_DIGEST_SIZE		(512 / 8)
-
-enum blake2b_constant {
-	BLAKE2B_BLOCKBYTES    = 128,
-	BLAKE2B_KEYBYTES      = 64,
-};
-
-struct blake2b_state {
-	u64      h[8];
-	u64      t[2];
-	u64      f[2];
-	u8       buf[BLAKE2B_BLOCKBYTES];
-	size_t   buflen;
-};
-
-static const u64 blake2b_IV[8] = {
-	0x6a09e667f3bcc908ULL, 0xbb67ae8584caa73bULL,
-	0x3c6ef372fe94f82bULL, 0xa54ff53a5f1d36f1ULL,
-	0x510e527fade682d1ULL, 0x9b05688c2b3e6c1fULL,
-	0x1f83d9abfb41bd6bULL, 0x5be0cd19137e2179ULL
-};
-
 static const u8 blake2b_sigma[12][16] = {
 	{  0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15 },
 	{ 14, 10,  4,  8,  9, 15, 13,  6,  1, 12,  0,  2, 11,  7,  5,  3 },
@@ -95,8 +67,8 @@ static void blake2b_increment_counter(struct blake2b_state *S, const u64 inc)
 		G(r,7,v[ 3],v[ 4],v[ 9],v[14]); \
 	} while (0)
 
-static void blake2b_compress(struct blake2b_state *S,
-			     const u8 block[BLAKE2B_BLOCKBYTES])
+static void blake2b_compress_one_generic(struct blake2b_state *S,
+					 const u8 block[BLAKE2B_BLOCK_SIZE])
 {
 	u64 m[16];
 	u64 v[16];
@@ -108,14 +80,14 @@ static void blake2b_compress(struct blake2b_state *S,
 	for (i = 0; i < 8; ++i)
 		v[i] = S->h[i];
 
-	v[ 8] = blake2b_IV[0];
-	v[ 9] = blake2b_IV[1];
-	v[10] = blake2b_IV[2];
-	v[11] = blake2b_IV[3];
-	v[12] = blake2b_IV[4] ^ S->t[0];
-	v[13] = blake2b_IV[5] ^ S->t[1];
-	v[14] = blake2b_IV[6] ^ S->f[0];
-	v[15] = blake2b_IV[7] ^ S->f[1];
+	v[ 8] = BLAKE2B_IV0;
+	v[ 9] = BLAKE2B_IV1;
+	v[10] = BLAKE2B_IV2;
+	v[11] = BLAKE2B_IV3;
+	v[12] = BLAKE2B_IV4 ^ S->t[0];
+	v[13] = BLAKE2B_IV5 ^ S->t[1];
+	v[14] = BLAKE2B_IV6 ^ S->f[0];
+	v[15] = BLAKE2B_IV7 ^ S->f[1];
 
 	ROUND(0);
 	ROUND(1);
@@ -139,159 +111,54 @@ static void blake2b_compress(struct blake2b_state *S,
 #undef G
 #undef ROUND
 
-struct blake2b_tfm_ctx {
-	u8 key[BLAKE2B_KEYBYTES];
-	unsigned int keylen;
-};
-
-static int blake2b_setkey(struct crypto_shash *tfm, const u8 *key,
-			  unsigned int keylen)
+void blake2b_compress_generic(struct blake2b_state *state,
+			      const u8 *block, size_t nblocks, u32 inc)
 {
-	struct blake2b_tfm_ctx *tctx = crypto_shash_ctx(tfm);
-
-	if (keylen == 0 || keylen > BLAKE2B_KEYBYTES)
-		return -EINVAL;
-
-	memcpy(tctx->key, key, keylen);
-	tctx->keylen = keylen;
-
-	return 0;
+	do {
+		blake2b_increment_counter(state, inc);
+		blake2b_compress_one_generic(state, block);
+		block += BLAKE2B_BLOCK_SIZE;
+	} while (--nblocks);
 }
+EXPORT_SYMBOL(blake2b_compress_generic);
 
-static int blake2b_init(struct shash_desc *desc)
+static int crypto_blake2b_update_generic(struct shash_desc *desc,
+					 const u8 *in, unsigned int inlen)
 {
-	struct blake2b_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
-	struct blake2b_state *state = shash_desc_ctx(desc);
-	const int digestsize = crypto_shash_digestsize(desc->tfm);
-
-	memset(state, 0, sizeof(*state));
-	memcpy(state->h, blake2b_IV, sizeof(state->h));
-
-	/* Parameter block is all zeros except index 0, no xor for 1..7 */
-	state->h[0] ^= 0x01010000 | tctx->keylen << 8 | digestsize;
-
-	if (tctx->keylen) {
-		/*
-		 * Prefill the buffer with the key, next call to _update or
-		 * _final will process it
-		 */
-		memcpy(state->buf, tctx->key, tctx->keylen);
-		state->buflen = BLAKE2B_BLOCKBYTES;
-	}
-	return 0;
+	return crypto_blake2b_update(desc, in, inlen, blake2b_compress_generic);
 }
 
-static int blake2b_update(struct shash_desc *desc, const u8 *in,
-			  unsigned int inlen)
+static int crypto_blake2b_final_generic(struct shash_desc *desc, u8 *out)
 {
-	struct blake2b_state *state = shash_desc_ctx(desc);
-	const size_t left = state->buflen;
-	const size_t fill = BLAKE2B_BLOCKBYTES - left;
-
-	if (!inlen)
-		return 0;
-
-	if (inlen > fill) {
-		state->buflen = 0;
-		/* Fill buffer */
-		memcpy(state->buf + left, in, fill);
-		blake2b_increment_counter(state, BLAKE2B_BLOCKBYTES);
-		/* Compress */
-		blake2b_compress(state, state->buf);
-		in += fill;
-		inlen -= fill;
-		while (inlen > BLAKE2B_BLOCKBYTES) {
-			blake2b_increment_counter(state, BLAKE2B_BLOCKBYTES);
-			blake2b_compress(state, in);
-			in += BLAKE2B_BLOCKBYTES;
-			inlen -= BLAKE2B_BLOCKBYTES;
-		}
-	}
-	memcpy(state->buf + state->buflen, in, inlen);
-	state->buflen += inlen;
-
-	return 0;
+	return crypto_blake2b_final(desc, out, blake2b_compress_generic);
 }
 
-static int blake2b_final(struct shash_desc *desc, u8 *out)
-{
-	struct blake2b_state *state = shash_desc_ctx(desc);
-	const int digestsize = crypto_shash_digestsize(desc->tfm);
-	size_t i;
-
-	blake2b_increment_counter(state, state->buflen);
-	/* Set last block */
-	state->f[0] = (u64)-1;
-	/* Padding */
-	memset(state->buf + state->buflen, 0, BLAKE2B_BLOCKBYTES - state->buflen);
-	blake2b_compress(state, state->buf);
-
-	/* Avoid temporary buffer and switch the internal output to LE order */
-	for (i = 0; i < ARRAY_SIZE(state->h); i++)
-		__cpu_to_le64s(&state->h[i]);
-
-	memcpy(out, state->h, digestsize);
-	return 0;
-}
+#define BLAKE2B_ALG(name, driver_name, digest_size)			\
+	{								\
+		.base.cra_name		= name,				\
+		.base.cra_driver_name	= driver_name,			\
+		.base.cra_priority	= 100,				\
+		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,	\
+		.base.cra_blocksize	= BLAKE2B_BLOCK_SIZE,		\
+		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx), \
+		.base.cra_module	= THIS_MODULE,			\
+		.digestsize		= digest_size,			\
+		.setkey			= crypto_blake2b_setkey,	\
+		.init			= crypto_blake2b_init,		\
+		.update			= crypto_blake2b_update_generic, \
+		.final			= crypto_blake2b_final_generic,	\
+		.descsize		= sizeof(struct blake2b_state),	\
+	}
 
 static struct shash_alg blake2b_algs[] = {
-	{
-		.base.cra_name		= "blake2b-160",
-		.base.cra_driver_name	= "blake2b-160-generic",
-		.base.cra_priority	= 100,
-		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-		.base.cra_blocksize	= BLAKE2B_BLOCKBYTES,
-		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx),
-		.base.cra_module	= THIS_MODULE,
-		.digestsize		= BLAKE2B_160_DIGEST_SIZE,
-		.setkey			= blake2b_setkey,
-		.init			= blake2b_init,
-		.update			= blake2b_update,
-		.final			= blake2b_final,
-		.descsize		= sizeof(struct blake2b_state),
-	}, {
-		.base.cra_name		= "blake2b-256",
-		.base.cra_driver_name	= "blake2b-256-generic",
-		.base.cra_priority	= 100,
-		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-		.base.cra_blocksize	= BLAKE2B_BLOCKBYTES,
-		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx),
-		.base.cra_module	= THIS_MODULE,
-		.digestsize		= BLAKE2B_256_DIGEST_SIZE,
-		.setkey			= blake2b_setkey,
-		.init			= blake2b_init,
-		.update			= blake2b_update,
-		.final			= blake2b_final,
-		.descsize		= sizeof(struct blake2b_state),
-	}, {
-		.base.cra_name		= "blake2b-384",
-		.base.cra_driver_name	= "blake2b-384-generic",
-		.base.cra_priority	= 100,
-		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-		.base.cra_blocksize	= BLAKE2B_BLOCKBYTES,
-		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx),
-		.base.cra_module	= THIS_MODULE,
-		.digestsize		= BLAKE2B_384_DIGEST_SIZE,
-		.setkey			= blake2b_setkey,
-		.init			= blake2b_init,
-		.update			= blake2b_update,
-		.final			= blake2b_final,
-		.descsize		= sizeof(struct blake2b_state),
-	}, {
-		.base.cra_name		= "blake2b-512",
-		.base.cra_driver_name	= "blake2b-512-generic",
-		.base.cra_priority	= 100,
-		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-		.base.cra_blocksize	= BLAKE2B_BLOCKBYTES,
-		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx),
-		.base.cra_module	= THIS_MODULE,
-		.digestsize		= BLAKE2B_512_DIGEST_SIZE,
-		.setkey			= blake2b_setkey,
-		.init			= blake2b_init,
-		.update			= blake2b_update,
-		.final			= blake2b_final,
-		.descsize		= sizeof(struct blake2b_state),
-	}
+	BLAKE2B_ALG("blake2b-160", "blake2b-160-generic",
+		    BLAKE2B_160_HASH_SIZE),
+	BLAKE2B_ALG("blake2b-256", "blake2b-256-generic",
+		    BLAKE2B_256_HASH_SIZE),
+	BLAKE2B_ALG("blake2b-384", "blake2b-384-generic",
+		    BLAKE2B_384_HASH_SIZE),
+	BLAKE2B_ALG("blake2b-512", "blake2b-512-generic",
+		    BLAKE2B_512_HASH_SIZE),
 };
 
 static int __init blake2b_mod_init(void)
diff --git a/crypto/blake2s_generic.c b/crypto/blake2s_generic.c
index 005783ff45ad..72fe480f9bd6 100644
--- a/crypto/blake2s_generic.c
+++ b/crypto/blake2s_generic.c
@@ -1,149 +1,55 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
+ * shash interface to the generic implementation of BLAKE2s
+ *
  * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  */
 
 #include <crypto/internal/blake2s.h>
-#include <crypto/internal/simd.h>
 #include <crypto/internal/hash.h>
 
 #include <linux/types.h>
-#include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 
-static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key,
-				 unsigned int keylen)
+static int crypto_blake2s_update_generic(struct shash_desc *desc,
+					 const u8 *in, unsigned int inlen)
 {
-	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm);
-
-	if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE)
-		return -EINVAL;
-
-	memcpy(tctx->key, key, keylen);
-	tctx->keylen = keylen;
-
-	return 0;
+	return crypto_blake2s_update(desc, in, inlen, blake2s_compress_generic);
 }
 
-static int crypto_blake2s_init(struct shash_desc *desc)
+static int crypto_blake2s_final_generic(struct shash_desc *desc, u8 *out)
 {
-	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
-	struct blake2s_state *state = shash_desc_ctx(desc);
-	const int outlen = crypto_shash_digestsize(desc->tfm);
-
-	if (tctx->keylen)
-		blake2s_init_key(state, outlen, tctx->key, tctx->keylen);
-	else
-		blake2s_init(state, outlen);
-
-	return 0;
+	return crypto_blake2s_final(desc, out, blake2s_compress_generic);
 }
 
-static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in,
-				 unsigned int inlen)
-{
-	struct blake2s_state *state = shash_desc_ctx(desc);
-	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
-
-	if (unlikely(!inlen))
-		return 0;
-	if (inlen > fill) {
-		memcpy(state->buf + state->buflen, in, fill);
-		blake2s_compress_generic(state, state->buf, 1, BLAKE2S_BLOCK_SIZE);
-		state->buflen = 0;
-		in += fill;
-		inlen -= fill;
-	}
-	if (inlen > BLAKE2S_BLOCK_SIZE) {
-		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
-		/* Hash one less (full) block than strictly possible */
-		blake2s_compress_generic(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE);
-		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
-		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+#define BLAKE2S_ALG(name, driver_name, digest_size)			\
+	{								\
+		.base.cra_name		= name,				\
+		.base.cra_driver_name	= driver_name,			\
+		.base.cra_priority	= 100,				\
+		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,	\
+		.base.cra_blocksize	= BLAKE2S_BLOCK_SIZE,		\
+		.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx), \
+		.base.cra_module	= THIS_MODULE,			\
+		.digestsize		= digest_size,			\
+		.setkey			= crypto_blake2s_setkey,	\
+		.init			= crypto_blake2s_init,		\
+		.update			= crypto_blake2s_update_generic, \
+		.final			= crypto_blake2s_final_generic,	\
+		.descsize		= sizeof(struct blake2s_state),	\
 	}
-	memcpy(state->buf + state->buflen, in, inlen);
-	state->buflen += inlen;
-
-	return 0;
-}
-
-static int crypto_blake2s_final(struct shash_desc *desc, u8 *out)
-{
-	struct blake2s_state *state = shash_desc_ctx(desc);
-
-	blake2s_set_lastblock(state);
-	memset(state->buf + state->buflen, 0,
-	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
-	blake2s_compress_generic(state, state->buf, 1, state->buflen);
-	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
-	memcpy(out, state->h, state->outlen);
-	memzero_explicit(state, sizeof(*state));
-
-	return 0;
-}
-
-static struct shash_alg blake2s_algs[] = {{
-	.base.cra_name		= "blake2s-128",
-	.base.cra_driver_name	= "blake2s-128-generic",
-	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
-	.base.cra_priority	= 200,
-	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-
-	.digestsize		= BLAKE2S_128_HASH_SIZE,
-	.setkey			= crypto_blake2s_setkey,
-	.init			= crypto_blake2s_init,
-	.update			= crypto_blake2s_update,
-	.final			= crypto_blake2s_final,
-	.descsize		= sizeof(struct blake2s_state),
-}, {
-	.base.cra_name		= "blake2s-160",
-	.base.cra_driver_name	= "blake2s-160-generic",
-	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
-	.base.cra_priority	= 200,
-	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-
-	.digestsize		= BLAKE2S_160_HASH_SIZE,
-	.setkey			= crypto_blake2s_setkey,
-	.init			= crypto_blake2s_init,
-	.update			= crypto_blake2s_update,
-	.final			= crypto_blake2s_final,
-	.descsize		= sizeof(struct blake2s_state),
-}, {
-	.base.cra_name		= "blake2s-224",
-	.base.cra_driver_name	= "blake2s-224-generic",
-	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
-	.base.cra_priority	= 200,
-	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-
-	.digestsize		= BLAKE2S_224_HASH_SIZE,
-	.setkey			= crypto_blake2s_setkey,
-	.init			= crypto_blake2s_init,
-	.update			= crypto_blake2s_update,
-	.final			= crypto_blake2s_final,
-	.descsize		= sizeof(struct blake2s_state),
-}, {
-	.base.cra_name		= "blake2s-256",
-	.base.cra_driver_name	= "blake2s-256-generic",
-	.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-	.base.cra_ctxsize	= sizeof(struct blake2s_tfm_ctx),
-	.base.cra_priority	= 200,
-	.base.cra_blocksize     = BLAKE2S_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
 
-	.digestsize		= BLAKE2S_256_HASH_SIZE,
-	.setkey			= crypto_blake2s_setkey,
-	.init			= crypto_blake2s_init,
-	.update			= crypto_blake2s_update,
-	.final			= crypto_blake2s_final,
-	.descsize		= sizeof(struct blake2s_state),
-}};
+static struct shash_alg blake2s_algs[] = {
+	BLAKE2S_ALG("blake2s-128", "blake2s-128-generic",
+		    BLAKE2S_128_HASH_SIZE),
+	BLAKE2S_ALG("blake2s-160", "blake2s-160-generic",
+		    BLAKE2S_160_HASH_SIZE),
+	BLAKE2S_ALG("blake2s-224", "blake2s-224-generic",
+		    BLAKE2S_224_HASH_SIZE),
+	BLAKE2S_ALG("blake2s-256", "blake2s-256-generic",
+		    BLAKE2S_256_HASH_SIZE),
+};
 
 static int __init blake2s_mod_init(void)
 {
diff --git a/crypto/blowfish_generic.c b/crypto/blowfish_generic.c
index c3c2041fe0c5..003b52c6880e 100644
--- a/crypto/blowfish_generic.c
+++ b/crypto/blowfish_generic.c
@@ -14,7 +14,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <asm/byteorder.h>
+#include <asm/unaligned.h>
 #include <linux/crypto.h>
 #include <linux/types.h>
 #include <crypto/blowfish.h>
@@ -36,12 +36,10 @@
 static void bf_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct bf_ctx *ctx = crypto_tfm_ctx(tfm);
-	const __be32 *in_blk = (const __be32 *)src;
-	__be32 *const out_blk = (__be32 *)dst;
 	const u32 *P = ctx->p;
 	const u32 *S = ctx->s;
-	u32 yl = be32_to_cpu(in_blk[0]);
-	u32 yr = be32_to_cpu(in_blk[1]);
+	u32 yl = get_unaligned_be32(src);
+	u32 yr = get_unaligned_be32(src + 4);
 
 	ROUND(yr, yl, 0);
 	ROUND(yl, yr, 1);
@@ -63,19 +61,17 @@ static void bf_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 	yl ^= P[16];
 	yr ^= P[17];
 
-	out_blk[0] = cpu_to_be32(yr);
-	out_blk[1] = cpu_to_be32(yl);
+	put_unaligned_be32(yr, dst);
+	put_unaligned_be32(yl, dst + 4);
 }
 
 static void bf_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct bf_ctx *ctx = crypto_tfm_ctx(tfm);
-	const __be32 *in_blk = (const __be32 *)src;
-	__be32 *const out_blk = (__be32 *)dst;
 	const u32 *P = ctx->p;
 	const u32 *S = ctx->s;
-	u32 yl = be32_to_cpu(in_blk[0]);
-	u32 yr = be32_to_cpu(in_blk[1]);
+	u32 yl = get_unaligned_be32(src);
+	u32 yr = get_unaligned_be32(src + 4);
 
 	ROUND(yr, yl, 17);
 	ROUND(yl, yr, 16);
@@ -97,8 +93,8 @@ static void bf_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 	yl ^= P[1];
 	yr ^= P[0];
 
-	out_blk[0] = cpu_to_be32(yr);
-	out_blk[1] = cpu_to_be32(yl);
+	put_unaligned_be32(yr, dst);
+	put_unaligned_be32(yl, dst + 4);
 }
 
 static struct crypto_alg alg = {
@@ -108,7 +104,6 @@ static struct crypto_alg alg = {
 	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		=	BF_BLOCK_SIZE,
 	.cra_ctxsize		=	sizeof(struct bf_ctx),
-	.cra_alignmask		=	3,
 	.cra_module		=	THIS_MODULE,
 	.cra_u			=	{ .cipher = {
 	.cia_min_keysize	=	BF_MIN_KEY_SIZE,
diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c
index 0b9f409f7370..fd1a88af9e77 100644
--- a/crypto/camellia_generic.c
+++ b/crypto/camellia_generic.c
@@ -9,14 +9,6 @@
  *  https://info.isl.ntt.co.jp/crypt/eng/camellia/specifications.html
  */
 
-/*
- *
- * NOTE --- NOTE --- NOTE --- NOTE
- * This implementation assumes that all memory addresses passed
- * as parameters are four-byte aligned.
- *
- */
-
 #include <linux/crypto.h>
 #include <linux/errno.h>
 #include <linux/init.h>
@@ -994,16 +986,14 @@ camellia_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 static void camellia_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	const struct camellia_ctx *cctx = crypto_tfm_ctx(tfm);
-	const __be32 *src = (const __be32 *)in;
-	__be32 *dst = (__be32 *)out;
 	unsigned int max;
 
 	u32 tmp[4];
 
-	tmp[0] = be32_to_cpu(src[0]);
-	tmp[1] = be32_to_cpu(src[1]);
-	tmp[2] = be32_to_cpu(src[2]);
-	tmp[3] = be32_to_cpu(src[3]);
+	tmp[0] = get_unaligned_be32(in);
+	tmp[1] = get_unaligned_be32(in + 4);
+	tmp[2] = get_unaligned_be32(in + 8);
+	tmp[3] = get_unaligned_be32(in + 12);
 
 	if (cctx->key_length == 16)
 		max = 24;
@@ -1013,25 +1003,23 @@ static void camellia_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 	camellia_do_encrypt(cctx->key_table, tmp, max);
 
 	/* do_encrypt returns 0,1 swapped with 2,3 */
-	dst[0] = cpu_to_be32(tmp[2]);
-	dst[1] = cpu_to_be32(tmp[3]);
-	dst[2] = cpu_to_be32(tmp[0]);
-	dst[3] = cpu_to_be32(tmp[1]);
+	put_unaligned_be32(tmp[2], out);
+	put_unaligned_be32(tmp[3], out + 4);
+	put_unaligned_be32(tmp[0], out + 8);
+	put_unaligned_be32(tmp[1], out + 12);
 }
 
 static void camellia_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	const struct camellia_ctx *cctx = crypto_tfm_ctx(tfm);
-	const __be32 *src = (const __be32 *)in;
-	__be32 *dst = (__be32 *)out;
 	unsigned int max;
 
 	u32 tmp[4];
 
-	tmp[0] = be32_to_cpu(src[0]);
-	tmp[1] = be32_to_cpu(src[1]);
-	tmp[2] = be32_to_cpu(src[2]);
-	tmp[3] = be32_to_cpu(src[3]);
+	tmp[0] = get_unaligned_be32(in);
+	tmp[1] = get_unaligned_be32(in + 4);
+	tmp[2] = get_unaligned_be32(in + 8);
+	tmp[3] = get_unaligned_be32(in + 12);
 
 	if (cctx->key_length == 16)
 		max = 24;
@@ -1041,10 +1029,10 @@ static void camellia_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 	camellia_do_decrypt(cctx->key_table, tmp, max);
 
 	/* do_decrypt returns 0,1 swapped with 2,3 */
-	dst[0] = cpu_to_be32(tmp[2]);
-	dst[1] = cpu_to_be32(tmp[3]);
-	dst[2] = cpu_to_be32(tmp[0]);
-	dst[3] = cpu_to_be32(tmp[1]);
+	put_unaligned_be32(tmp[2], out);
+	put_unaligned_be32(tmp[3], out + 4);
+	put_unaligned_be32(tmp[0], out + 8);
+	put_unaligned_be32(tmp[1], out + 12);
 }
 
 static struct crypto_alg camellia_alg = {
@@ -1054,7 +1042,6 @@ static struct crypto_alg camellia_alg = {
 	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		=	CAMELLIA_BLOCK_SIZE,
 	.cra_ctxsize		=	sizeof(struct camellia_ctx),
-	.cra_alignmask		=	3,
 	.cra_module		=	THIS_MODULE,
 	.cra_u			=	{
 		.cipher = {
diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c
index 4095085d4e51..0257c14cefc2 100644
--- a/crypto/cast5_generic.c
+++ b/crypto/cast5_generic.c
@@ -13,7 +13,7 @@
 */
 
 
-#include <asm/byteorder.h>
+#include <asm/unaligned.h>
 #include <linux/init.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
@@ -302,8 +302,6 @@ static const u32 sb8[256] = {
 
 void __cast5_encrypt(struct cast5_ctx *c, u8 *outbuf, const u8 *inbuf)
 {
-	const __be32 *src = (const __be32 *)inbuf;
-	__be32 *dst = (__be32 *)outbuf;
 	u32 l, r, t;
 	u32 I;			/* used by the Fx macros */
 	u32 *Km;
@@ -315,8 +313,8 @@ void __cast5_encrypt(struct cast5_ctx *c, u8 *outbuf, const u8 *inbuf)
 	/* (L0,R0) <-- (m1...m64).  (Split the plaintext into left and
 	 * right 32-bit halves L0 = m1...m32 and R0 = m33...m64.)
 	 */
-	l = be32_to_cpu(src[0]);
-	r = be32_to_cpu(src[1]);
+	l = get_unaligned_be32(inbuf);
+	r = get_unaligned_be32(inbuf + 4);
 
 	/* (16 rounds) for i from 1 to 16, compute Li and Ri as follows:
 	 *  Li = Ri-1;
@@ -347,8 +345,8 @@ void __cast5_encrypt(struct cast5_ctx *c, u8 *outbuf, const u8 *inbuf)
 
 	/* c1...c64 <-- (R16,L16).  (Exchange final blocks L16, R16 and
 	 *  concatenate to form the ciphertext.) */
-	dst[0] = cpu_to_be32(r);
-	dst[1] = cpu_to_be32(l);
+	put_unaligned_be32(r, outbuf);
+	put_unaligned_be32(l, outbuf + 4);
 }
 EXPORT_SYMBOL_GPL(__cast5_encrypt);
 
@@ -359,8 +357,6 @@ static void cast5_encrypt(struct crypto_tfm *tfm, u8 *outbuf, const u8 *inbuf)
 
 void __cast5_decrypt(struct cast5_ctx *c, u8 *outbuf, const u8 *inbuf)
 {
-	const __be32 *src = (const __be32 *)inbuf;
-	__be32 *dst = (__be32 *)outbuf;
 	u32 l, r, t;
 	u32 I;
 	u32 *Km;
@@ -369,8 +365,8 @@ void __cast5_decrypt(struct cast5_ctx *c, u8 *outbuf, const u8 *inbuf)
 	Km = c->Km;
 	Kr = c->Kr;
 
-	l = be32_to_cpu(src[0]);
-	r = be32_to_cpu(src[1]);
+	l = get_unaligned_be32(inbuf);
+	r = get_unaligned_be32(inbuf + 4);
 
 	if (!(c->rr)) {
 		t = l; l = r; r = t ^ F1(r, Km[15], Kr[15]);
@@ -391,8 +387,8 @@ void __cast5_decrypt(struct cast5_ctx *c, u8 *outbuf, const u8 *inbuf)
 	t = l; l = r; r = t ^ F2(r, Km[1], Kr[1]);
 	t = l; l = r; r = t ^ F1(r, Km[0], Kr[0]);
 
-	dst[0] = cpu_to_be32(r);
-	dst[1] = cpu_to_be32(l);
+	put_unaligned_be32(r, outbuf);
+	put_unaligned_be32(l, outbuf + 4);
 }
 EXPORT_SYMBOL_GPL(__cast5_decrypt);
 
@@ -513,7 +509,6 @@ static struct crypto_alg alg = {
 	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		= CAST5_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct cast5_ctx),
-	.cra_alignmask		= 3,
 	.cra_module		= THIS_MODULE,
 	.cra_u			= {
 		.cipher = {
diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c
index c77ff6c8a2b2..75346380aa0b 100644
--- a/crypto/cast6_generic.c
+++ b/crypto/cast6_generic.c
@@ -10,7 +10,7 @@
  */
 
 
-#include <asm/byteorder.h>
+#include <asm/unaligned.h>
 #include <linux/init.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
@@ -172,16 +172,14 @@ static inline void QBAR(u32 *block, const u8 *Kr, const u32 *Km)
 void __cast6_encrypt(const void *ctx, u8 *outbuf, const u8 *inbuf)
 {
 	const struct cast6_ctx *c = ctx;
-	const __be32 *src = (const __be32 *)inbuf;
-	__be32 *dst = (__be32 *)outbuf;
 	u32 block[4];
 	const u32 *Km;
 	const u8 *Kr;
 
-	block[0] = be32_to_cpu(src[0]);
-	block[1] = be32_to_cpu(src[1]);
-	block[2] = be32_to_cpu(src[2]);
-	block[3] = be32_to_cpu(src[3]);
+	block[0] = get_unaligned_be32(inbuf);
+	block[1] = get_unaligned_be32(inbuf + 4);
+	block[2] = get_unaligned_be32(inbuf + 8);
+	block[3] = get_unaligned_be32(inbuf + 12);
 
 	Km = c->Km[0]; Kr = c->Kr[0]; Q(block, Kr, Km);
 	Km = c->Km[1]; Kr = c->Kr[1]; Q(block, Kr, Km);
@@ -196,10 +194,10 @@ void __cast6_encrypt(const void *ctx, u8 *outbuf, const u8 *inbuf)
 	Km = c->Km[10]; Kr = c->Kr[10]; QBAR(block, Kr, Km);
 	Km = c->Km[11]; Kr = c->Kr[11]; QBAR(block, Kr, Km);
 
-	dst[0] = cpu_to_be32(block[0]);
-	dst[1] = cpu_to_be32(block[1]);
-	dst[2] = cpu_to_be32(block[2]);
-	dst[3] = cpu_to_be32(block[3]);
+	put_unaligned_be32(block[0], outbuf);
+	put_unaligned_be32(block[1], outbuf + 4);
+	put_unaligned_be32(block[2], outbuf + 8);
+	put_unaligned_be32(block[3], outbuf + 12);
 }
 EXPORT_SYMBOL_GPL(__cast6_encrypt);
 
@@ -211,16 +209,14 @@ static void cast6_encrypt(struct crypto_tfm *tfm, u8 *outbuf, const u8 *inbuf)
 void __cast6_decrypt(const void *ctx, u8 *outbuf, const u8 *inbuf)
 {
 	const struct cast6_ctx *c = ctx;
-	const __be32 *src = (const __be32 *)inbuf;
-	__be32 *dst = (__be32 *)outbuf;
 	u32 block[4];
 	const u32 *Km;
 	const u8 *Kr;
 
-	block[0] = be32_to_cpu(src[0]);
-	block[1] = be32_to_cpu(src[1]);
-	block[2] = be32_to_cpu(src[2]);
-	block[3] = be32_to_cpu(src[3]);
+	block[0] = get_unaligned_be32(inbuf);
+	block[1] = get_unaligned_be32(inbuf + 4);
+	block[2] = get_unaligned_be32(inbuf + 8);
+	block[3] = get_unaligned_be32(inbuf + 12);
 
 	Km = c->Km[11]; Kr = c->Kr[11]; Q(block, Kr, Km);
 	Km = c->Km[10]; Kr = c->Kr[10]; Q(block, Kr, Km);
@@ -235,10 +231,10 @@ void __cast6_decrypt(const void *ctx, u8 *outbuf, const u8 *inbuf)
 	Km = c->Km[1]; Kr = c->Kr[1]; QBAR(block, Kr, Km);
 	Km = c->Km[0]; Kr = c->Kr[0]; QBAR(block, Kr, Km);
 
-	dst[0] = cpu_to_be32(block[0]);
-	dst[1] = cpu_to_be32(block[1]);
-	dst[2] = cpu_to_be32(block[2]);
-	dst[3] = cpu_to_be32(block[3]);
+	put_unaligned_be32(block[0], outbuf);
+	put_unaligned_be32(block[1], outbuf + 4);
+	put_unaligned_be32(block[2], outbuf + 8);
+	put_unaligned_be32(block[3], outbuf + 12);
 }
 EXPORT_SYMBOL_GPL(__cast6_decrypt);
 
@@ -254,7 +250,6 @@ static struct crypto_alg alg = {
 	.cra_flags = CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize = CAST6_BLOCK_SIZE,
 	.cra_ctxsize = sizeof(struct cast6_ctx),
-	.cra_alignmask = 3,
 	.cra_module = THIS_MODULE,
 	.cra_u = {
 		  .cipher = {
diff --git a/crypto/cbc.c b/crypto/cbc.c
index 0d9509dff891..6c03e96b945f 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -6,6 +6,7 @@
  */
 
 #include <crypto/algapi.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 494d70901186..6b815ece51c6 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -6,6 +6,7 @@
  */
 
 #include <crypto/internal/aead.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
@@ -954,3 +955,4 @@ MODULE_ALIAS_CRYPTO("ccm_base");
 MODULE_ALIAS_CRYPTO("rfc4309");
 MODULE_ALIAS_CRYPTO("ccm");
 MODULE_ALIAS_CRYPTO("cbcmac");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/cfb.c b/crypto/cfb.c
index 4e5219bbcd19..0d664dfb47bc 100644
--- a/crypto/cfb.c
+++ b/crypto/cfb.c
@@ -20,6 +20,7 @@
  */
 
 #include <crypto/algapi.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -250,3 +251,4 @@ module_exit(crypto_cfb_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CFB block cipher mode of operation");
 MODULE_ALIAS_CRYPTO("cfb");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/cipher.c b/crypto/cipher.c
index fd78150deb1c..b47141ed4a9f 100644
--- a/crypto/cipher.c
+++ b/crypto/cipher.c
@@ -9,6 +9,7 @@
  */
 
 #include <crypto/algapi.h>
+#include <crypto/internal/cipher.h>
 #include <linux/kernel.h>
 #include <linux/crypto.h>
 #include <linux/errno.h>
@@ -53,7 +54,7 @@ int crypto_cipher_setkey(struct crypto_cipher *tfm,
 
 	return cia->cia_setkey(crypto_cipher_tfm(tfm), key, keylen);
 }
-EXPORT_SYMBOL_GPL(crypto_cipher_setkey);
+EXPORT_SYMBOL_NS_GPL(crypto_cipher_setkey, CRYPTO_INTERNAL);
 
 static inline void cipher_crypt_one(struct crypto_cipher *tfm,
 				    u8 *dst, const u8 *src, bool enc)
@@ -81,11 +82,11 @@ void crypto_cipher_encrypt_one(struct crypto_cipher *tfm,
 {
 	cipher_crypt_one(tfm, dst, src, true);
 }
-EXPORT_SYMBOL_GPL(crypto_cipher_encrypt_one);
+EXPORT_SYMBOL_NS_GPL(crypto_cipher_encrypt_one, CRYPTO_INTERNAL);
 
 void crypto_cipher_decrypt_one(struct crypto_cipher *tfm,
 			       u8 *dst, const u8 *src)
 {
 	cipher_crypt_one(tfm, dst, src, false);
 }
-EXPORT_SYMBOL_GPL(crypto_cipher_decrypt_one);
+EXPORT_SYMBOL_NS_GPL(crypto_cipher_decrypt_one, CRYPTO_INTERNAL);
diff --git a/crypto/cmac.c b/crypto/cmac.c
index df36be1efb81..f4a5d3bfb376 100644
--- a/crypto/cmac.c
+++ b/crypto/cmac.c
@@ -11,6 +11,7 @@
  *   Author: Kazunori Miyazawa <miyazawa@linux-ipv6.org>
  */
 
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/hash.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -313,3 +314,4 @@ module_exit(crypto_cmac_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CMAC keyed hash algorithm");
 MODULE_ALIAS_CRYPTO("cmac");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/ctr.c b/crypto/ctr.c
index c39fcffba27f..23c698b22013 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -7,6 +7,7 @@
 
 #include <crypto/algapi.h>
 #include <crypto/ctr.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -358,3 +359,4 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CTR block cipher mode of operation");
 MODULE_ALIAS_CRYPTO("rfc3686");
 MODULE_ALIAS_CRYPTO("ctr");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/drbg.c b/crypto/drbg.c
index 3132967a1749..1b4587e0ddad 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -98,6 +98,7 @@
  */
 
 #include <crypto/drbg.h>
+#include <crypto/internal/cipher.h>
 #include <linux/kernel.h>
 
 /***************************************************************
@@ -2161,3 +2162,4 @@ MODULE_DESCRIPTION("NIST SP800-90A Deterministic Random Bit Generator (DRBG) "
 		   CRYPTO_DRBG_HMAC_STRING
 		   CRYPTO_DRBG_CTR_STRING);
 MODULE_ALIAS_CRYPTO("stdrng");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/ecb.c b/crypto/ecb.c
index 69a687cbdf21..71fbb0543d64 100644
--- a/crypto/ecb.c
+++ b/crypto/ecb.c
@@ -6,6 +6,7 @@
  */
 
 #include <crypto/algapi.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
diff --git a/crypto/ecdh_helper.c b/crypto/ecdh_helper.c
index 66fcb2ea8154..fca63b559f65 100644
--- a/crypto/ecdh_helper.c
+++ b/crypto/ecdh_helper.c
@@ -67,6 +67,9 @@ int crypto_ecdh_decode_key(const char *buf, unsigned int len,
 	if (secret.type != CRYPTO_KPP_SECRET_TYPE_ECDH)
 		return -EINVAL;
 
+	if (unlikely(len < secret.len))
+		return -EINVAL;
+
 	ptr = ecdh_unpack_data(&params->curve_id, ptr, sizeof(params->curve_id));
 	ptr = ecdh_unpack_data(&params->key_size, ptr, sizeof(params->key_size));
 	if (secret.len != crypto_ecdh_key_len(params))
diff --git a/crypto/essiv.c b/crypto/essiv.c
index d012be23d496..8bcc5bdcb2a9 100644
--- a/crypto/essiv.c
+++ b/crypto/essiv.c
@@ -30,6 +30,7 @@
 
 #include <crypto/authenc.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
@@ -643,3 +644,4 @@ module_exit(essiv_module_exit);
 MODULE_DESCRIPTION("ESSIV skcipher/aead wrapper for block encryption");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_CRYPTO("essiv");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c
index 58f935315cf8..c36ea0c8be98 100644
--- a/crypto/fcrypt.c
+++ b/crypto/fcrypt.c
@@ -396,7 +396,6 @@ static struct crypto_alg fcrypt_alg = {
 	.cra_blocksize		=	8,
 	.cra_ctxsize		=	sizeof(struct fcrypt_ctx),
 	.cra_module		=	THIS_MODULE,
-	.cra_alignmask		=	3,
 	.cra_u			=	{ .cipher = {
 	.cia_min_keysize	=	8,
 	.cia_max_keysize	=	8,
diff --git a/crypto/keywrap.c b/crypto/keywrap.c
index 0355cce21b1e..3517773bc7f7 100644
--- a/crypto/keywrap.c
+++ b/crypto/keywrap.c
@@ -85,6 +85,7 @@
 #include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 
 struct crypto_kw_block {
@@ -316,3 +317,4 @@ MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Stephan Mueller <smueller@chronox.de>");
 MODULE_DESCRIPTION("Key Wrapping (RFC3394 / NIST SP800-38F)");
 MODULE_ALIAS_CRYPTO("kw");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/michael_mic.c b/crypto/michael_mic.c
index 63350c4ad461..f4c31049601c 100644
--- a/crypto/michael_mic.c
+++ b/crypto/michael_mic.c
@@ -7,7 +7,7 @@
  * Copyright (c) 2004 Jouni Malinen <j@w1.fi>
  */
 #include <crypto/internal/hash.h>
-#include <asm/byteorder.h>
+#include <asm/unaligned.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/string.h>
@@ -19,7 +19,7 @@ struct michael_mic_ctx {
 };
 
 struct michael_mic_desc_ctx {
-	u8 pending[4];
+	__le32 pending;
 	size_t pending_len;
 
 	u32 l, r;
@@ -60,13 +60,12 @@ static int michael_update(struct shash_desc *desc, const u8 *data,
 			   unsigned int len)
 {
 	struct michael_mic_desc_ctx *mctx = shash_desc_ctx(desc);
-	const __le32 *src;
 
 	if (mctx->pending_len) {
 		int flen = 4 - mctx->pending_len;
 		if (flen > len)
 			flen = len;
-		memcpy(&mctx->pending[mctx->pending_len], data, flen);
+		memcpy((u8 *)&mctx->pending + mctx->pending_len, data, flen);
 		mctx->pending_len += flen;
 		data += flen;
 		len -= flen;
@@ -74,23 +73,21 @@ static int michael_update(struct shash_desc *desc, const u8 *data,
 		if (mctx->pending_len < 4)
 			return 0;
 
-		src = (const __le32 *)mctx->pending;
-		mctx->l ^= le32_to_cpup(src);
+		mctx->l ^= le32_to_cpu(mctx->pending);
 		michael_block(mctx->l, mctx->r);
 		mctx->pending_len = 0;
 	}
 
-	src = (const __le32 *)data;
-
 	while (len >= 4) {
-		mctx->l ^= le32_to_cpup(src++);
+		mctx->l ^= get_unaligned_le32(data);
 		michael_block(mctx->l, mctx->r);
+		data += 4;
 		len -= 4;
 	}
 
 	if (len > 0) {
 		mctx->pending_len = len;
-		memcpy(mctx->pending, src, len);
+		memcpy(&mctx->pending, data, len);
 	}
 
 	return 0;
@@ -100,8 +97,7 @@ static int michael_update(struct shash_desc *desc, const u8 *data,
 static int michael_final(struct shash_desc *desc, u8 *out)
 {
 	struct michael_mic_desc_ctx *mctx = shash_desc_ctx(desc);
-	u8 *data = mctx->pending;
-	__le32 *dst = (__le32 *)out;
+	u8 *data = (u8 *)&mctx->pending;
 
 	/* Last block and padding (0x5a, 4..7 x 0) */
 	switch (mctx->pending_len) {
@@ -123,8 +119,8 @@ static int michael_final(struct shash_desc *desc, u8 *out)
 	/* l ^= 0; */
 	michael_block(mctx->l, mctx->r);
 
-	dst[0] = cpu_to_le32(mctx->l);
-	dst[1] = cpu_to_le32(mctx->r);
+	put_unaligned_le32(mctx->l, out);
+	put_unaligned_le32(mctx->r, out + 4);
 
 	return 0;
 }
@@ -135,13 +131,11 @@ static int michael_setkey(struct crypto_shash *tfm, const u8 *key,
 {
 	struct michael_mic_ctx *mctx = crypto_shash_ctx(tfm);
 
-	const __le32 *data = (const __le32 *)key;
-
 	if (keylen != 8)
 		return -EINVAL;
 
-	mctx->l = le32_to_cpu(data[0]);
-	mctx->r = le32_to_cpu(data[1]);
+	mctx->l = get_unaligned_le32(key);
+	mctx->r = get_unaligned_le32(key + 4);
 	return 0;
 }
 
@@ -156,7 +150,6 @@ static struct shash_alg alg = {
 		.cra_name		=	"michael_mic",
 		.cra_driver_name	=	"michael_mic-generic",
 		.cra_blocksize		=	8,
-		.cra_alignmask		=	3,
 		.cra_ctxsize		=	sizeof(struct michael_mic_ctx),
 		.cra_module		=	THIS_MODULE,
 	}
diff --git a/crypto/ofb.c b/crypto/ofb.c
index 2ec68e3f2c55..b630fdecceee 100644
--- a/crypto/ofb.c
+++ b/crypto/ofb.c
@@ -8,6 +8,7 @@
  */
 
 #include <crypto/algapi.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -102,3 +103,4 @@ module_exit(crypto_ofb_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("OFB block cipher mode of operation");
 MODULE_ALIAS_CRYPTO("ofb");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/pcbc.c b/crypto/pcbc.c
index ae921fb74dc9..7030f59e46b6 100644
--- a/crypto/pcbc.c
+++ b/crypto/pcbc.c
@@ -10,6 +10,7 @@
  */
 
 #include <crypto/algapi.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -191,3 +192,4 @@ module_exit(crypto_pcbc_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("PCBC block cipher mode of operation");
 MODULE_ALIAS_CRYPTO("pcbc");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/ripemd.h b/crypto/ripemd.h
index 93edbf52197d..b977785e2a62 100644
--- a/crypto/ripemd.h
+++ b/crypto/ripemd.h
@@ -6,29 +6,15 @@
 #ifndef _CRYPTO_RMD_H
 #define _CRYPTO_RMD_H
 
-#define RMD128_DIGEST_SIZE      16
-#define RMD128_BLOCK_SIZE       64
-
 #define RMD160_DIGEST_SIZE      20
 #define RMD160_BLOCK_SIZE       64
 
-#define RMD256_DIGEST_SIZE      32
-#define RMD256_BLOCK_SIZE       64
-
-#define RMD320_DIGEST_SIZE      40
-#define RMD320_BLOCK_SIZE       64
-
 /* initial values  */
 #define RMD_H0  0x67452301UL
 #define RMD_H1  0xefcdab89UL
 #define RMD_H2  0x98badcfeUL
 #define RMD_H3  0x10325476UL
 #define RMD_H4  0xc3d2e1f0UL
-#define RMD_H5  0x76543210UL
-#define RMD_H6  0xfedcba98UL
-#define RMD_H7  0x89abcdefUL
-#define RMD_H8  0x01234567UL
-#define RMD_H9  0x3c2d1e0fUL
 
 /* constants */
 #define RMD_K1  0x00000000UL
diff --git a/crypto/rmd128.c b/crypto/rmd128.c
deleted file mode 100644
index 29308fb97e7e..000000000000
--- a/crypto/rmd128.c
+++ /dev/null
@@ -1,323 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cryptographic API.
- *
- * RIPEMD-128 - RACE Integrity Primitives Evaluation Message Digest.
- *
- * Based on the reference implementation by Antoon Bosselaers, ESAT-COSIC
- *
- * Copyright (c) 2008 Adrian-Ken Rueegsegger <ken@codelabs.ch>
- */
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <asm/byteorder.h>
-
-#include "ripemd.h"
-
-struct rmd128_ctx {
-	u64 byte_count;
-	u32 state[4];
-	__le32 buffer[16];
-};
-
-#define K1  RMD_K1
-#define K2  RMD_K2
-#define K3  RMD_K3
-#define K4  RMD_K4
-#define KK1 RMD_K6
-#define KK2 RMD_K7
-#define KK3 RMD_K8
-#define KK4 RMD_K1
-
-#define F1(x, y, z) (x ^ y ^ z)		/* XOR */
-#define F2(x, y, z) (z ^ (x & (y ^ z)))	/* x ? y : z */
-#define F3(x, y, z) ((x | ~y) ^ z)
-#define F4(x, y, z) (y ^ (z & (x ^ y)))	/* z ? x : y */
-
-#define ROUND(a, b, c, d, f, k, x, s)  { \
-	(a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k);	\
-	(a) = rol32((a), (s)); \
-}
-
-static void rmd128_transform(u32 *state, const __le32 *in)
-{
-	u32 aa, bb, cc, dd, aaa, bbb, ccc, ddd;
-
-	/* Initialize left lane */
-	aa = state[0];
-	bb = state[1];
-	cc = state[2];
-	dd = state[3];
-
-	/* Initialize right lane */
-	aaa = state[0];
-	bbb = state[1];
-	ccc = state[2];
-	ddd = state[3];
-
-	/* round 1: left lane */
-	ROUND(aa, bb, cc, dd, F1, K1, in[0],  11);
-	ROUND(dd, aa, bb, cc, F1, K1, in[1],  14);
-	ROUND(cc, dd, aa, bb, F1, K1, in[2],  15);
-	ROUND(bb, cc, dd, aa, F1, K1, in[3],  12);
-	ROUND(aa, bb, cc, dd, F1, K1, in[4],   5);
-	ROUND(dd, aa, bb, cc, F1, K1, in[5],   8);
-	ROUND(cc, dd, aa, bb, F1, K1, in[6],   7);
-	ROUND(bb, cc, dd, aa, F1, K1, in[7],   9);
-	ROUND(aa, bb, cc, dd, F1, K1, in[8],  11);
-	ROUND(dd, aa, bb, cc, F1, K1, in[9],  13);
-	ROUND(cc, dd, aa, bb, F1, K1, in[10], 14);
-	ROUND(bb, cc, dd, aa, F1, K1, in[11], 15);
-	ROUND(aa, bb, cc, dd, F1, K1, in[12],  6);
-	ROUND(dd, aa, bb, cc, F1, K1, in[13],  7);
-	ROUND(cc, dd, aa, bb, F1, K1, in[14],  9);
-	ROUND(bb, cc, dd, aa, F1, K1, in[15],  8);
-
-	/* round 2: left lane */
-	ROUND(aa, bb, cc, dd, F2, K2, in[7],   7);
-	ROUND(dd, aa, bb, cc, F2, K2, in[4],   6);
-	ROUND(cc, dd, aa, bb, F2, K2, in[13],  8);
-	ROUND(bb, cc, dd, aa, F2, K2, in[1],  13);
-	ROUND(aa, bb, cc, dd, F2, K2, in[10], 11);
-	ROUND(dd, aa, bb, cc, F2, K2, in[6],   9);
-	ROUND(cc, dd, aa, bb, F2, K2, in[15],  7);
-	ROUND(bb, cc, dd, aa, F2, K2, in[3],  15);
-	ROUND(aa, bb, cc, dd, F2, K2, in[12],  7);
-	ROUND(dd, aa, bb, cc, F2, K2, in[0],  12);
-	ROUND(cc, dd, aa, bb, F2, K2, in[9],  15);
-	ROUND(bb, cc, dd, aa, F2, K2, in[5],   9);
-	ROUND(aa, bb, cc, dd, F2, K2, in[2],  11);
-	ROUND(dd, aa, bb, cc, F2, K2, in[14],  7);
-	ROUND(cc, dd, aa, bb, F2, K2, in[11], 13);
-	ROUND(bb, cc, dd, aa, F2, K2, in[8],  12);
-
-	/* round 3: left lane */
-	ROUND(aa, bb, cc, dd, F3, K3, in[3],  11);
-	ROUND(dd, aa, bb, cc, F3, K3, in[10], 13);
-	ROUND(cc, dd, aa, bb, F3, K3, in[14],  6);
-	ROUND(bb, cc, dd, aa, F3, K3, in[4],   7);
-	ROUND(aa, bb, cc, dd, F3, K3, in[9],  14);
-	ROUND(dd, aa, bb, cc, F3, K3, in[15],  9);
-	ROUND(cc, dd, aa, bb, F3, K3, in[8],  13);
-	ROUND(bb, cc, dd, aa, F3, K3, in[1],  15);
-	ROUND(aa, bb, cc, dd, F3, K3, in[2],  14);
-	ROUND(dd, aa, bb, cc, F3, K3, in[7],   8);
-	ROUND(cc, dd, aa, bb, F3, K3, in[0],  13);
-	ROUND(bb, cc, dd, aa, F3, K3, in[6],   6);
-	ROUND(aa, bb, cc, dd, F3, K3, in[13],  5);
-	ROUND(dd, aa, bb, cc, F3, K3, in[11], 12);
-	ROUND(cc, dd, aa, bb, F3, K3, in[5],   7);
-	ROUND(bb, cc, dd, aa, F3, K3, in[12],  5);
-
-	/* round 4: left lane */
-	ROUND(aa, bb, cc, dd, F4, K4, in[1],  11);
-	ROUND(dd, aa, bb, cc, F4, K4, in[9],  12);
-	ROUND(cc, dd, aa, bb, F4, K4, in[11], 14);
-	ROUND(bb, cc, dd, aa, F4, K4, in[10], 15);
-	ROUND(aa, bb, cc, dd, F4, K4, in[0],  14);
-	ROUND(dd, aa, bb, cc, F4, K4, in[8],  15);
-	ROUND(cc, dd, aa, bb, F4, K4, in[12],  9);
-	ROUND(bb, cc, dd, aa, F4, K4, in[4],   8);
-	ROUND(aa, bb, cc, dd, F4, K4, in[13],  9);
-	ROUND(dd, aa, bb, cc, F4, K4, in[3],  14);
-	ROUND(cc, dd, aa, bb, F4, K4, in[7],   5);
-	ROUND(bb, cc, dd, aa, F4, K4, in[15],  6);
-	ROUND(aa, bb, cc, dd, F4, K4, in[14],  8);
-	ROUND(dd, aa, bb, cc, F4, K4, in[5],   6);
-	ROUND(cc, dd, aa, bb, F4, K4, in[6],   5);
-	ROUND(bb, cc, dd, aa, F4, K4, in[2],  12);
-
-	/* round 1: right lane */
-	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[5],   8);
-	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[14],  9);
-	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[7],   9);
-	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[0],  11);
-	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[9],  13);
-	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[2],  15);
-	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[11], 15);
-	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[4],   5);
-	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[13],  7);
-	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[6],   7);
-	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[15],  8);
-	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[8],  11);
-	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[1],  14);
-	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[10], 14);
-	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[3],  12);
-	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[12],  6);
-
-	/* round 2: right lane */
-	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[6],   9);
-	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[11], 13);
-	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[3],  15);
-	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[7],   7);
-	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[0],  12);
-	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[13],  8);
-	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[5],   9);
-	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[10], 11);
-	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[14],  7);
-	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[15],  7);
-	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[8],  12);
-	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[12],  7);
-	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[4],   6);
-	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[9],  15);
-	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[1],  13);
-	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[2],  11);
-
-	/* round 3: right lane */
-	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[15],  9);
-	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[5],   7);
-	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[1],  15);
-	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[3],  11);
-	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[7],   8);
-	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[14],  6);
-	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[6],   6);
-	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[9],  14);
-	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[11], 12);
-	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[8],  13);
-	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[12],  5);
-	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[2],  14);
-	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[10], 13);
-	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[0],  13);
-	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[4],   7);
-	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[13],  5);
-
-	/* round 4: right lane */
-	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[8],  15);
-	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[6],   5);
-	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[4],   8);
-	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[1],  11);
-	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[3],  14);
-	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[11], 14);
-	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[15],  6);
-	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[0],  14);
-	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[5],   6);
-	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[12],  9);
-	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[2],  12);
-	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[13],  9);
-	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[9],  12);
-	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[7],   5);
-	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[10], 15);
-	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[14],  8);
-
-	/* combine results */
-	ddd += cc + state[1];		/* final result for state[0] */
-	state[1] = state[2] + dd + aaa;
-	state[2] = state[3] + aa + bbb;
-	state[3] = state[0] + bb + ccc;
-	state[0] = ddd;
-}
-
-static int rmd128_init(struct shash_desc *desc)
-{
-	struct rmd128_ctx *rctx = shash_desc_ctx(desc);
-
-	rctx->byte_count = 0;
-
-	rctx->state[0] = RMD_H0;
-	rctx->state[1] = RMD_H1;
-	rctx->state[2] = RMD_H2;
-	rctx->state[3] = RMD_H3;
-
-	memset(rctx->buffer, 0, sizeof(rctx->buffer));
-
-	return 0;
-}
-
-static int rmd128_update(struct shash_desc *desc, const u8 *data,
-			 unsigned int len)
-{
-	struct rmd128_ctx *rctx = shash_desc_ctx(desc);
-	const u32 avail = sizeof(rctx->buffer) - (rctx->byte_count & 0x3f);
-
-	rctx->byte_count += len;
-
-	/* Enough space in buffer? If so copy and we're done */
-	if (avail > len) {
-		memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
-		       data, len);
-		goto out;
-	}
-
-	memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
-	       data, avail);
-
-	rmd128_transform(rctx->state, rctx->buffer);
-	data += avail;
-	len -= avail;
-
-	while (len >= sizeof(rctx->buffer)) {
-		memcpy(rctx->buffer, data, sizeof(rctx->buffer));
-		rmd128_transform(rctx->state, rctx->buffer);
-		data += sizeof(rctx->buffer);
-		len -= sizeof(rctx->buffer);
-	}
-
-	memcpy(rctx->buffer, data, len);
-
-out:
-	return 0;
-}
-
-/* Add padding and return the message digest. */
-static int rmd128_final(struct shash_desc *desc, u8 *out)
-{
-	struct rmd128_ctx *rctx = shash_desc_ctx(desc);
-	u32 i, index, padlen;
-	__le64 bits;
-	__le32 *dst = (__le32 *)out;
-	static const u8 padding[64] = { 0x80, };
-
-	bits = cpu_to_le64(rctx->byte_count << 3);
-
-	/* Pad out to 56 mod 64 */
-	index = rctx->byte_count & 0x3f;
-	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
-	rmd128_update(desc, padding, padlen);
-
-	/* Append length */
-	rmd128_update(desc, (const u8 *)&bits, sizeof(bits));
-
-	/* Store state in digest */
-	for (i = 0; i < 4; i++)
-		dst[i] = cpu_to_le32p(&rctx->state[i]);
-
-	/* Wipe context */
-	memset(rctx, 0, sizeof(*rctx));
-
-	return 0;
-}
-
-static struct shash_alg alg = {
-	.digestsize	=	RMD128_DIGEST_SIZE,
-	.init		=	rmd128_init,
-	.update		=	rmd128_update,
-	.final		=	rmd128_final,
-	.descsize	=	sizeof(struct rmd128_ctx),
-	.base		=	{
-		.cra_name	 =	"rmd128",
-		.cra_driver_name =	"rmd128-generic",
-		.cra_blocksize	 =	RMD128_BLOCK_SIZE,
-		.cra_module	 =	THIS_MODULE,
-	}
-};
-
-static int __init rmd128_mod_init(void)
-{
-	return crypto_register_shash(&alg);
-}
-
-static void __exit rmd128_mod_fini(void)
-{
-	crypto_unregister_shash(&alg);
-}
-
-subsys_initcall(rmd128_mod_init);
-module_exit(rmd128_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
-MODULE_DESCRIPTION("RIPEMD-128 Message Digest");
-MODULE_ALIAS_CRYPTO("rmd128");
diff --git a/crypto/rmd256.c b/crypto/rmd256.c
deleted file mode 100644
index 3c730e9de5fd..000000000000
--- a/crypto/rmd256.c
+++ /dev/null
@@ -1,342 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cryptographic API.
- *
- * RIPEMD-256 - RACE Integrity Primitives Evaluation Message Digest.
- *
- * Based on the reference implementation by Antoon Bosselaers, ESAT-COSIC
- *
- * Copyright (c) 2008 Adrian-Ken Rueegsegger <ken@codelabs.ch>
- */
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <asm/byteorder.h>
-
-#include "ripemd.h"
-
-struct rmd256_ctx {
-	u64 byte_count;
-	u32 state[8];
-	__le32 buffer[16];
-};
-
-#define K1  RMD_K1
-#define K2  RMD_K2
-#define K3  RMD_K3
-#define K4  RMD_K4
-#define KK1 RMD_K6
-#define KK2 RMD_K7
-#define KK3 RMD_K8
-#define KK4 RMD_K1
-
-#define F1(x, y, z) (x ^ y ^ z)		/* XOR */
-#define F2(x, y, z) (z ^ (x & (y ^ z)))	/* x ? y : z */
-#define F3(x, y, z) ((x | ~y) ^ z)
-#define F4(x, y, z) (y ^ (z & (x ^ y)))	/* z ? x : y */
-
-#define ROUND(a, b, c, d, f, k, x, s)  { \
-	(a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \
-	(a) = rol32((a), (s)); \
-}
-
-static void rmd256_transform(u32 *state, const __le32 *in)
-{
-	u32 aa, bb, cc, dd, aaa, bbb, ccc, ddd;
-
-	/* Initialize left lane */
-	aa = state[0];
-	bb = state[1];
-	cc = state[2];
-	dd = state[3];
-
-	/* Initialize right lane */
-	aaa = state[4];
-	bbb = state[5];
-	ccc = state[6];
-	ddd = state[7];
-
-	/* round 1: left lane */
-	ROUND(aa, bb, cc, dd, F1, K1, in[0],  11);
-	ROUND(dd, aa, bb, cc, F1, K1, in[1],  14);
-	ROUND(cc, dd, aa, bb, F1, K1, in[2],  15);
-	ROUND(bb, cc, dd, aa, F1, K1, in[3],  12);
-	ROUND(aa, bb, cc, dd, F1, K1, in[4],   5);
-	ROUND(dd, aa, bb, cc, F1, K1, in[5],   8);
-	ROUND(cc, dd, aa, bb, F1, K1, in[6],   7);
-	ROUND(bb, cc, dd, aa, F1, K1, in[7],   9);
-	ROUND(aa, bb, cc, dd, F1, K1, in[8],  11);
-	ROUND(dd, aa, bb, cc, F1, K1, in[9],  13);
-	ROUND(cc, dd, aa, bb, F1, K1, in[10], 14);
-	ROUND(bb, cc, dd, aa, F1, K1, in[11], 15);
-	ROUND(aa, bb, cc, dd, F1, K1, in[12],  6);
-	ROUND(dd, aa, bb, cc, F1, K1, in[13],  7);
-	ROUND(cc, dd, aa, bb, F1, K1, in[14],  9);
-	ROUND(bb, cc, dd, aa, F1, K1, in[15],  8);
-
-	/* round 1: right lane */
-	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[5],   8);
-	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[14],  9);
-	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[7],   9);
-	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[0],  11);
-	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[9],  13);
-	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[2],  15);
-	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[11], 15);
-	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[4],   5);
-	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[13],  7);
-	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[6],   7);
-	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[15],  8);
-	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[8],  11);
-	ROUND(aaa, bbb, ccc, ddd, F4, KK1, in[1],  14);
-	ROUND(ddd, aaa, bbb, ccc, F4, KK1, in[10], 14);
-	ROUND(ccc, ddd, aaa, bbb, F4, KK1, in[3],  12);
-	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[12],  6);
-
-	/* Swap contents of "a" registers */
-	swap(aa, aaa);
-
-	/* round 2: left lane */
-	ROUND(aa, bb, cc, dd, F2, K2, in[7],   7);
-	ROUND(dd, aa, bb, cc, F2, K2, in[4],   6);
-	ROUND(cc, dd, aa, bb, F2, K2, in[13],  8);
-	ROUND(bb, cc, dd, aa, F2, K2, in[1],  13);
-	ROUND(aa, bb, cc, dd, F2, K2, in[10], 11);
-	ROUND(dd, aa, bb, cc, F2, K2, in[6],   9);
-	ROUND(cc, dd, aa, bb, F2, K2, in[15],  7);
-	ROUND(bb, cc, dd, aa, F2, K2, in[3],  15);
-	ROUND(aa, bb, cc, dd, F2, K2, in[12],  7);
-	ROUND(dd, aa, bb, cc, F2, K2, in[0],  12);
-	ROUND(cc, dd, aa, bb, F2, K2, in[9],  15);
-	ROUND(bb, cc, dd, aa, F2, K2, in[5],   9);
-	ROUND(aa, bb, cc, dd, F2, K2, in[2],  11);
-	ROUND(dd, aa, bb, cc, F2, K2, in[14],  7);
-	ROUND(cc, dd, aa, bb, F2, K2, in[11], 13);
-	ROUND(bb, cc, dd, aa, F2, K2, in[8],  12);
-
-	/* round 2: right lane */
-	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[6],   9);
-	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[11], 13);
-	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[3],  15);
-	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[7],   7);
-	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[0],  12);
-	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[13],  8);
-	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[5],   9);
-	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[10], 11);
-	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[14],  7);
-	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[15],  7);
-	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[8],  12);
-	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[12],  7);
-	ROUND(aaa, bbb, ccc, ddd, F3, KK2, in[4],   6);
-	ROUND(ddd, aaa, bbb, ccc, F3, KK2, in[9],  15);
-	ROUND(ccc, ddd, aaa, bbb, F3, KK2, in[1],  13);
-	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[2],  11);
-
-	/* Swap contents of "b" registers */
-	swap(bb, bbb);
-
-	/* round 3: left lane */
-	ROUND(aa, bb, cc, dd, F3, K3, in[3],  11);
-	ROUND(dd, aa, bb, cc, F3, K3, in[10], 13);
-	ROUND(cc, dd, aa, bb, F3, K3, in[14],  6);
-	ROUND(bb, cc, dd, aa, F3, K3, in[4],   7);
-	ROUND(aa, bb, cc, dd, F3, K3, in[9],  14);
-	ROUND(dd, aa, bb, cc, F3, K3, in[15],  9);
-	ROUND(cc, dd, aa, bb, F3, K3, in[8],  13);
-	ROUND(bb, cc, dd, aa, F3, K3, in[1],  15);
-	ROUND(aa, bb, cc, dd, F3, K3, in[2],  14);
-	ROUND(dd, aa, bb, cc, F3, K3, in[7],   8);
-	ROUND(cc, dd, aa, bb, F3, K3, in[0],  13);
-	ROUND(bb, cc, dd, aa, F3, K3, in[6],   6);
-	ROUND(aa, bb, cc, dd, F3, K3, in[13],  5);
-	ROUND(dd, aa, bb, cc, F3, K3, in[11], 12);
-	ROUND(cc, dd, aa, bb, F3, K3, in[5],   7);
-	ROUND(bb, cc, dd, aa, F3, K3, in[12],  5);
-
-	/* round 3: right lane */
-	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[15],  9);
-	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[5],   7);
-	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[1],  15);
-	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[3],  11);
-	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[7],   8);
-	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[14],  6);
-	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[6],   6);
-	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[9],  14);
-	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[11], 12);
-	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[8],  13);
-	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[12],  5);
-	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[2],  14);
-	ROUND(aaa, bbb, ccc, ddd, F2, KK3, in[10], 13);
-	ROUND(ddd, aaa, bbb, ccc, F2, KK3, in[0],  13);
-	ROUND(ccc, ddd, aaa, bbb, F2, KK3, in[4],   7);
-	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[13],  5);
-
-	/* Swap contents of "c" registers */
-	swap(cc, ccc);
-
-	/* round 4: left lane */
-	ROUND(aa, bb, cc, dd, F4, K4, in[1],  11);
-	ROUND(dd, aa, bb, cc, F4, K4, in[9],  12);
-	ROUND(cc, dd, aa, bb, F4, K4, in[11], 14);
-	ROUND(bb, cc, dd, aa, F4, K4, in[10], 15);
-	ROUND(aa, bb, cc, dd, F4, K4, in[0],  14);
-	ROUND(dd, aa, bb, cc, F4, K4, in[8],  15);
-	ROUND(cc, dd, aa, bb, F4, K4, in[12],  9);
-	ROUND(bb, cc, dd, aa, F4, K4, in[4],   8);
-	ROUND(aa, bb, cc, dd, F4, K4, in[13],  9);
-	ROUND(dd, aa, bb, cc, F4, K4, in[3],  14);
-	ROUND(cc, dd, aa, bb, F4, K4, in[7],   5);
-	ROUND(bb, cc, dd, aa, F4, K4, in[15],  6);
-	ROUND(aa, bb, cc, dd, F4, K4, in[14],  8);
-	ROUND(dd, aa, bb, cc, F4, K4, in[5],   6);
-	ROUND(cc, dd, aa, bb, F4, K4, in[6],   5);
-	ROUND(bb, cc, dd, aa, F4, K4, in[2],  12);
-
-	/* round 4: right lane */
-	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[8],  15);
-	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[6],   5);
-	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[4],   8);
-	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[1],  11);
-	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[3],  14);
-	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[11], 14);
-	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[15],  6);
-	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[0],  14);
-	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[5],   6);
-	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[12],  9);
-	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[2],  12);
-	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[13],  9);
-	ROUND(aaa, bbb, ccc, ddd, F1, KK4, in[9],  12);
-	ROUND(ddd, aaa, bbb, ccc, F1, KK4, in[7],   5);
-	ROUND(ccc, ddd, aaa, bbb, F1, KK4, in[10], 15);
-	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[14],  8);
-
-	/* Swap contents of "d" registers */
-	swap(dd, ddd);
-
-	/* combine results */
-	state[0] += aa;
-	state[1] += bb;
-	state[2] += cc;
-	state[3] += dd;
-	state[4] += aaa;
-	state[5] += bbb;
-	state[6] += ccc;
-	state[7] += ddd;
-}
-
-static int rmd256_init(struct shash_desc *desc)
-{
-	struct rmd256_ctx *rctx = shash_desc_ctx(desc);
-
-	rctx->byte_count = 0;
-
-	rctx->state[0] = RMD_H0;
-	rctx->state[1] = RMD_H1;
-	rctx->state[2] = RMD_H2;
-	rctx->state[3] = RMD_H3;
-	rctx->state[4] = RMD_H5;
-	rctx->state[5] = RMD_H6;
-	rctx->state[6] = RMD_H7;
-	rctx->state[7] = RMD_H8;
-
-	memset(rctx->buffer, 0, sizeof(rctx->buffer));
-
-	return 0;
-}
-
-static int rmd256_update(struct shash_desc *desc, const u8 *data,
-			 unsigned int len)
-{
-	struct rmd256_ctx *rctx = shash_desc_ctx(desc);
-	const u32 avail = sizeof(rctx->buffer) - (rctx->byte_count & 0x3f);
-
-	rctx->byte_count += len;
-
-	/* Enough space in buffer? If so copy and we're done */
-	if (avail > len) {
-		memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
-		       data, len);
-		goto out;
-	}
-
-	memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
-	       data, avail);
-
-	rmd256_transform(rctx->state, rctx->buffer);
-	data += avail;
-	len -= avail;
-
-	while (len >= sizeof(rctx->buffer)) {
-		memcpy(rctx->buffer, data, sizeof(rctx->buffer));
-		rmd256_transform(rctx->state, rctx->buffer);
-		data += sizeof(rctx->buffer);
-		len -= sizeof(rctx->buffer);
-	}
-
-	memcpy(rctx->buffer, data, len);
-
-out:
-	return 0;
-}
-
-/* Add padding and return the message digest. */
-static int rmd256_final(struct shash_desc *desc, u8 *out)
-{
-	struct rmd256_ctx *rctx = shash_desc_ctx(desc);
-	u32 i, index, padlen;
-	__le64 bits;
-	__le32 *dst = (__le32 *)out;
-	static const u8 padding[64] = { 0x80, };
-
-	bits = cpu_to_le64(rctx->byte_count << 3);
-
-	/* Pad out to 56 mod 64 */
-	index = rctx->byte_count & 0x3f;
-	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
-	rmd256_update(desc, padding, padlen);
-
-	/* Append length */
-	rmd256_update(desc, (const u8 *)&bits, sizeof(bits));
-
-	/* Store state in digest */
-	for (i = 0; i < 8; i++)
-		dst[i] = cpu_to_le32p(&rctx->state[i]);
-
-	/* Wipe context */
-	memset(rctx, 0, sizeof(*rctx));
-
-	return 0;
-}
-
-static struct shash_alg alg = {
-	.digestsize	=	RMD256_DIGEST_SIZE,
-	.init		=	rmd256_init,
-	.update		=	rmd256_update,
-	.final		=	rmd256_final,
-	.descsize	=	sizeof(struct rmd256_ctx),
-	.base		=	{
-		.cra_name	 =	"rmd256",
-		.cra_driver_name =	"rmd256-generic",
-		.cra_blocksize	 =	RMD256_BLOCK_SIZE,
-		.cra_module	 =	THIS_MODULE,
-	}
-};
-
-static int __init rmd256_mod_init(void)
-{
-	return crypto_register_shash(&alg);
-}
-
-static void __exit rmd256_mod_fini(void)
-{
-	crypto_unregister_shash(&alg);
-}
-
-subsys_initcall(rmd256_mod_init);
-module_exit(rmd256_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
-MODULE_DESCRIPTION("RIPEMD-256 Message Digest");
-MODULE_ALIAS_CRYPTO("rmd256");
diff --git a/crypto/rmd320.c b/crypto/rmd320.c
deleted file mode 100644
index c919ad6c4705..000000000000
--- a/crypto/rmd320.c
+++ /dev/null
@@ -1,391 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cryptographic API.
- *
- * RIPEMD-320 - RACE Integrity Primitives Evaluation Message Digest.
- *
- * Based on the reference implementation by Antoon Bosselaers, ESAT-COSIC
- *
- * Copyright (c) 2008 Adrian-Ken Rueegsegger <ken@codelabs.ch>
- */
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <asm/byteorder.h>
-
-#include "ripemd.h"
-
-struct rmd320_ctx {
-	u64 byte_count;
-	u32 state[10];
-	__le32 buffer[16];
-};
-
-#define K1  RMD_K1
-#define K2  RMD_K2
-#define K3  RMD_K3
-#define K4  RMD_K4
-#define K5  RMD_K5
-#define KK1 RMD_K6
-#define KK2 RMD_K7
-#define KK3 RMD_K8
-#define KK4 RMD_K9
-#define KK5 RMD_K1
-
-#define F1(x, y, z) (x ^ y ^ z)		/* XOR */
-#define F2(x, y, z) (z ^ (x & (y ^ z)))	/* x ? y : z */
-#define F3(x, y, z) ((x | ~y) ^ z)
-#define F4(x, y, z) (y ^ (z & (x ^ y)))	/* z ? x : y */
-#define F5(x, y, z) (x ^ (y | ~z))
-
-#define ROUND(a, b, c, d, e, f, k, x, s)  { \
-	(a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \
-	(a) = rol32((a), (s)) + (e); \
-	(c) = rol32((c), 10); \
-}
-
-static void rmd320_transform(u32 *state, const __le32 *in)
-{
-	u32 aa, bb, cc, dd, ee, aaa, bbb, ccc, ddd, eee;
-
-	/* Initialize left lane */
-	aa = state[0];
-	bb = state[1];
-	cc = state[2];
-	dd = state[3];
-	ee = state[4];
-
-	/* Initialize right lane */
-	aaa = state[5];
-	bbb = state[6];
-	ccc = state[7];
-	ddd = state[8];
-	eee = state[9];
-
-	/* round 1: left lane */
-	ROUND(aa, bb, cc, dd, ee, F1, K1, in[0],  11);
-	ROUND(ee, aa, bb, cc, dd, F1, K1, in[1],  14);
-	ROUND(dd, ee, aa, bb, cc, F1, K1, in[2],  15);
-	ROUND(cc, dd, ee, aa, bb, F1, K1, in[3],  12);
-	ROUND(bb, cc, dd, ee, aa, F1, K1, in[4],   5);
-	ROUND(aa, bb, cc, dd, ee, F1, K1, in[5],   8);
-	ROUND(ee, aa, bb, cc, dd, F1, K1, in[6],   7);
-	ROUND(dd, ee, aa, bb, cc, F1, K1, in[7],   9);
-	ROUND(cc, dd, ee, aa, bb, F1, K1, in[8],  11);
-	ROUND(bb, cc, dd, ee, aa, F1, K1, in[9],  13);
-	ROUND(aa, bb, cc, dd, ee, F1, K1, in[10], 14);
-	ROUND(ee, aa, bb, cc, dd, F1, K1, in[11], 15);
-	ROUND(dd, ee, aa, bb, cc, F1, K1, in[12],  6);
-	ROUND(cc, dd, ee, aa, bb, F1, K1, in[13],  7);
-	ROUND(bb, cc, dd, ee, aa, F1, K1, in[14],  9);
-	ROUND(aa, bb, cc, dd, ee, F1, K1, in[15],  8);
-
-	/* round 1: right lane */
-	ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[5],   8);
-	ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[14],  9);
-	ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[7],   9);
-	ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[0],  11);
-	ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[9],  13);
-	ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[2],  15);
-	ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[11], 15);
-	ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[4],   5);
-	ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[13],  7);
-	ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[6],   7);
-	ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[15],  8);
-	ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[8],  11);
-	ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[1],  14);
-	ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[10], 14);
-	ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[3],  12);
-	ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[12],  6);
-
-	/* Swap contents of "a" registers */
-	swap(aa, aaa);
-
-	/* round 2: left lane" */
-	ROUND(ee, aa, bb, cc, dd, F2, K2, in[7],   7);
-	ROUND(dd, ee, aa, bb, cc, F2, K2, in[4],   6);
-	ROUND(cc, dd, ee, aa, bb, F2, K2, in[13],  8);
-	ROUND(bb, cc, dd, ee, aa, F2, K2, in[1],  13);
-	ROUND(aa, bb, cc, dd, ee, F2, K2, in[10], 11);
-	ROUND(ee, aa, bb, cc, dd, F2, K2, in[6],   9);
-	ROUND(dd, ee, aa, bb, cc, F2, K2, in[15],  7);
-	ROUND(cc, dd, ee, aa, bb, F2, K2, in[3],  15);
-	ROUND(bb, cc, dd, ee, aa, F2, K2, in[12],  7);
-	ROUND(aa, bb, cc, dd, ee, F2, K2, in[0],  12);
-	ROUND(ee, aa, bb, cc, dd, F2, K2, in[9],  15);
-	ROUND(dd, ee, aa, bb, cc, F2, K2, in[5],   9);
-	ROUND(cc, dd, ee, aa, bb, F2, K2, in[2],  11);
-	ROUND(bb, cc, dd, ee, aa, F2, K2, in[14],  7);
-	ROUND(aa, bb, cc, dd, ee, F2, K2, in[11], 13);
-	ROUND(ee, aa, bb, cc, dd, F2, K2, in[8],  12);
-
-	/* round 2: right lane */
-	ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[6],   9);
-	ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[11], 13);
-	ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[3],  15);
-	ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[7],   7);
-	ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[0],  12);
-	ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[13],  8);
-	ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[5],   9);
-	ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[10], 11);
-	ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[14],  7);
-	ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[15],  7);
-	ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[8],  12);
-	ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[12],  7);
-	ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[4],   6);
-	ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[9],  15);
-	ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[1],  13);
-	ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[2],  11);
-
-	/* Swap contents of "b" registers */
-	swap(bb, bbb);
-
-	/* round 3: left lane" */
-	ROUND(dd, ee, aa, bb, cc, F3, K3, in[3],  11);
-	ROUND(cc, dd, ee, aa, bb, F3, K3, in[10], 13);
-	ROUND(bb, cc, dd, ee, aa, F3, K3, in[14],  6);
-	ROUND(aa, bb, cc, dd, ee, F3, K3, in[4],   7);
-	ROUND(ee, aa, bb, cc, dd, F3, K3, in[9],  14);
-	ROUND(dd, ee, aa, bb, cc, F3, K3, in[15],  9);
-	ROUND(cc, dd, ee, aa, bb, F3, K3, in[8],  13);
-	ROUND(bb, cc, dd, ee, aa, F3, K3, in[1],  15);
-	ROUND(aa, bb, cc, dd, ee, F3, K3, in[2],  14);
-	ROUND(ee, aa, bb, cc, dd, F3, K3, in[7],   8);
-	ROUND(dd, ee, aa, bb, cc, F3, K3, in[0],  13);
-	ROUND(cc, dd, ee, aa, bb, F3, K3, in[6],   6);
-	ROUND(bb, cc, dd, ee, aa, F3, K3, in[13],  5);
-	ROUND(aa, bb, cc, dd, ee, F3, K3, in[11], 12);
-	ROUND(ee, aa, bb, cc, dd, F3, K3, in[5],   7);
-	ROUND(dd, ee, aa, bb, cc, F3, K3, in[12],  5);
-
-	/* round 3: right lane */
-	ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[15],  9);
-	ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[5],   7);
-	ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[1],  15);
-	ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[3],  11);
-	ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[7],   8);
-	ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[14],  6);
-	ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[6],   6);
-	ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[9],  14);
-	ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[11], 12);
-	ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[8],  13);
-	ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[12],  5);
-	ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[2],  14);
-	ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[10], 13);
-	ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[0],  13);
-	ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[4],   7);
-	ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[13],  5);
-
-	/* Swap contents of "c" registers */
-	swap(cc, ccc);
-
-	/* round 4: left lane" */
-	ROUND(cc, dd, ee, aa, bb, F4, K4, in[1],  11);
-	ROUND(bb, cc, dd, ee, aa, F4, K4, in[9],  12);
-	ROUND(aa, bb, cc, dd, ee, F4, K4, in[11], 14);
-	ROUND(ee, aa, bb, cc, dd, F4, K4, in[10], 15);
-	ROUND(dd, ee, aa, bb, cc, F4, K4, in[0],  14);
-	ROUND(cc, dd, ee, aa, bb, F4, K4, in[8],  15);
-	ROUND(bb, cc, dd, ee, aa, F4, K4, in[12],  9);
-	ROUND(aa, bb, cc, dd, ee, F4, K4, in[4],   8);
-	ROUND(ee, aa, bb, cc, dd, F4, K4, in[13],  9);
-	ROUND(dd, ee, aa, bb, cc, F4, K4, in[3],  14);
-	ROUND(cc, dd, ee, aa, bb, F4, K4, in[7],   5);
-	ROUND(bb, cc, dd, ee, aa, F4, K4, in[15],  6);
-	ROUND(aa, bb, cc, dd, ee, F4, K4, in[14],  8);
-	ROUND(ee, aa, bb, cc, dd, F4, K4, in[5],   6);
-	ROUND(dd, ee, aa, bb, cc, F4, K4, in[6],   5);
-	ROUND(cc, dd, ee, aa, bb, F4, K4, in[2],  12);
-
-	/* round 4: right lane */
-	ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[8],  15);
-	ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[6],   5);
-	ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[4],   8);
-	ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[1],  11);
-	ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[3],  14);
-	ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[11], 14);
-	ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[15],  6);
-	ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[0],  14);
-	ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[5],   6);
-	ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[12],  9);
-	ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[2],  12);
-	ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[13],  9);
-	ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[9],  12);
-	ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[7],   5);
-	ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[10], 15);
-	ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[14],  8);
-
-	/* Swap contents of "d" registers */
-	swap(dd, ddd);
-
-	/* round 5: left lane" */
-	ROUND(bb, cc, dd, ee, aa, F5, K5, in[4],   9);
-	ROUND(aa, bb, cc, dd, ee, F5, K5, in[0],  15);
-	ROUND(ee, aa, bb, cc, dd, F5, K5, in[5],   5);
-	ROUND(dd, ee, aa, bb, cc, F5, K5, in[9],  11);
-	ROUND(cc, dd, ee, aa, bb, F5, K5, in[7],   6);
-	ROUND(bb, cc, dd, ee, aa, F5, K5, in[12],  8);
-	ROUND(aa, bb, cc, dd, ee, F5, K5, in[2],  13);
-	ROUND(ee, aa, bb, cc, dd, F5, K5, in[10], 12);
-	ROUND(dd, ee, aa, bb, cc, F5, K5, in[14],  5);
-	ROUND(cc, dd, ee, aa, bb, F5, K5, in[1],  12);
-	ROUND(bb, cc, dd, ee, aa, F5, K5, in[3],  13);
-	ROUND(aa, bb, cc, dd, ee, F5, K5, in[8],  14);
-	ROUND(ee, aa, bb, cc, dd, F5, K5, in[11], 11);
-	ROUND(dd, ee, aa, bb, cc, F5, K5, in[6],   8);
-	ROUND(cc, dd, ee, aa, bb, F5, K5, in[15],  5);
-	ROUND(bb, cc, dd, ee, aa, F5, K5, in[13],  6);
-
-	/* round 5: right lane */
-	ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[12],  8);
-	ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[15],  5);
-	ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[10], 12);
-	ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[4],   9);
-	ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[1],  12);
-	ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[5],   5);
-	ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[8],  14);
-	ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[7],   6);
-	ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[6],   8);
-	ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[2],  13);
-	ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[13],  6);
-	ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[14],  5);
-	ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[0],  15);
-	ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[3],  13);
-	ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[9],  11);
-	ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[11], 11);
-
-	/* Swap contents of "e" registers */
-	swap(ee, eee);
-
-	/* combine results */
-	state[0] += aa;
-	state[1] += bb;
-	state[2] += cc;
-	state[3] += dd;
-	state[4] += ee;
-	state[5] += aaa;
-	state[6] += bbb;
-	state[7] += ccc;
-	state[8] += ddd;
-	state[9] += eee;
-}
-
-static int rmd320_init(struct shash_desc *desc)
-{
-	struct rmd320_ctx *rctx = shash_desc_ctx(desc);
-
-	rctx->byte_count = 0;
-
-	rctx->state[0] = RMD_H0;
-	rctx->state[1] = RMD_H1;
-	rctx->state[2] = RMD_H2;
-	rctx->state[3] = RMD_H3;
-	rctx->state[4] = RMD_H4;
-	rctx->state[5] = RMD_H5;
-	rctx->state[6] = RMD_H6;
-	rctx->state[7] = RMD_H7;
-	rctx->state[8] = RMD_H8;
-	rctx->state[9] = RMD_H9;
-
-	memset(rctx->buffer, 0, sizeof(rctx->buffer));
-
-	return 0;
-}
-
-static int rmd320_update(struct shash_desc *desc, const u8 *data,
-			 unsigned int len)
-{
-	struct rmd320_ctx *rctx = shash_desc_ctx(desc);
-	const u32 avail = sizeof(rctx->buffer) - (rctx->byte_count & 0x3f);
-
-	rctx->byte_count += len;
-
-	/* Enough space in buffer? If so copy and we're done */
-	if (avail > len) {
-		memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
-		       data, len);
-		goto out;
-	}
-
-	memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail),
-	       data, avail);
-
-	rmd320_transform(rctx->state, rctx->buffer);
-	data += avail;
-	len -= avail;
-
-	while (len >= sizeof(rctx->buffer)) {
-		memcpy(rctx->buffer, data, sizeof(rctx->buffer));
-		rmd320_transform(rctx->state, rctx->buffer);
-		data += sizeof(rctx->buffer);
-		len -= sizeof(rctx->buffer);
-	}
-
-	memcpy(rctx->buffer, data, len);
-
-out:
-	return 0;
-}
-
-/* Add padding and return the message digest. */
-static int rmd320_final(struct shash_desc *desc, u8 *out)
-{
-	struct rmd320_ctx *rctx = shash_desc_ctx(desc);
-	u32 i, index, padlen;
-	__le64 bits;
-	__le32 *dst = (__le32 *)out;
-	static const u8 padding[64] = { 0x80, };
-
-	bits = cpu_to_le64(rctx->byte_count << 3);
-
-	/* Pad out to 56 mod 64 */
-	index = rctx->byte_count & 0x3f;
-	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
-	rmd320_update(desc, padding, padlen);
-
-	/* Append length */
-	rmd320_update(desc, (const u8 *)&bits, sizeof(bits));
-
-	/* Store state in digest */
-	for (i = 0; i < 10; i++)
-		dst[i] = cpu_to_le32p(&rctx->state[i]);
-
-	/* Wipe context */
-	memset(rctx, 0, sizeof(*rctx));
-
-	return 0;
-}
-
-static struct shash_alg alg = {
-	.digestsize	=	RMD320_DIGEST_SIZE,
-	.init		=	rmd320_init,
-	.update		=	rmd320_update,
-	.final		=	rmd320_final,
-	.descsize	=	sizeof(struct rmd320_ctx),
-	.base		=	{
-		.cra_name	 =	"rmd320",
-		.cra_driver_name =	"rmd320-generic",
-		.cra_blocksize	 =	RMD320_BLOCK_SIZE,
-		.cra_module	 =	THIS_MODULE,
-	}
-};
-
-static int __init rmd320_mod_init(void)
-{
-	return crypto_register_shash(&alg);
-}
-
-static void __exit rmd320_mod_fini(void)
-{
-	crypto_unregister_shash(&alg);
-}
-
-subsys_initcall(rmd320_mod_init);
-module_exit(rmd320_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
-MODULE_DESCRIPTION("RIPEMD-320 Message Digest");
-MODULE_ALIAS_CRYPTO("rmd320");
diff --git a/crypto/salsa20_generic.c b/crypto/salsa20_generic.c
deleted file mode 100644
index 3418869dabef..000000000000
--- a/crypto/salsa20_generic.c
+++ /dev/null
@@ -1,212 +0,0 @@
-/*
- * Salsa20: Salsa20 stream cipher algorithm
- *
- * Copyright (c) 2007 Tan Swee Heng <thesweeheng@gmail.com>
- *
- * Derived from:
- * - salsa20.c: Public domain C code by Daniel J. Bernstein <djb@cr.yp.to>
- *
- * Salsa20 is a stream cipher candidate in eSTREAM, the ECRYPT Stream
- * Cipher Project. It is designed by Daniel J. Bernstein <djb@cr.yp.to>.
- * More information about eSTREAM and Salsa20 can be found here:
- *   https://www.ecrypt.eu.org/stream/
- *   https://cr.yp.to/snuffle.html
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <asm/unaligned.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/module.h>
-
-#define SALSA20_IV_SIZE        8
-#define SALSA20_MIN_KEY_SIZE  16
-#define SALSA20_MAX_KEY_SIZE  32
-#define SALSA20_BLOCK_SIZE    64
-
-struct salsa20_ctx {
-	u32 initial_state[16];
-};
-
-static void salsa20_block(u32 *state, __le32 *stream)
-{
-	u32 x[16];
-	int i;
-
-	memcpy(x, state, sizeof(x));
-
-	for (i = 0; i < 20; i += 2) {
-		x[ 4] ^= rol32((x[ 0] + x[12]),  7);
-		x[ 8] ^= rol32((x[ 4] + x[ 0]),  9);
-		x[12] ^= rol32((x[ 8] + x[ 4]), 13);
-		x[ 0] ^= rol32((x[12] + x[ 8]), 18);
-		x[ 9] ^= rol32((x[ 5] + x[ 1]),  7);
-		x[13] ^= rol32((x[ 9] + x[ 5]),  9);
-		x[ 1] ^= rol32((x[13] + x[ 9]), 13);
-		x[ 5] ^= rol32((x[ 1] + x[13]), 18);
-		x[14] ^= rol32((x[10] + x[ 6]),  7);
-		x[ 2] ^= rol32((x[14] + x[10]),  9);
-		x[ 6] ^= rol32((x[ 2] + x[14]), 13);
-		x[10] ^= rol32((x[ 6] + x[ 2]), 18);
-		x[ 3] ^= rol32((x[15] + x[11]),  7);
-		x[ 7] ^= rol32((x[ 3] + x[15]),  9);
-		x[11] ^= rol32((x[ 7] + x[ 3]), 13);
-		x[15] ^= rol32((x[11] + x[ 7]), 18);
-		x[ 1] ^= rol32((x[ 0] + x[ 3]),  7);
-		x[ 2] ^= rol32((x[ 1] + x[ 0]),  9);
-		x[ 3] ^= rol32((x[ 2] + x[ 1]), 13);
-		x[ 0] ^= rol32((x[ 3] + x[ 2]), 18);
-		x[ 6] ^= rol32((x[ 5] + x[ 4]),  7);
-		x[ 7] ^= rol32((x[ 6] + x[ 5]),  9);
-		x[ 4] ^= rol32((x[ 7] + x[ 6]), 13);
-		x[ 5] ^= rol32((x[ 4] + x[ 7]), 18);
-		x[11] ^= rol32((x[10] + x[ 9]),  7);
-		x[ 8] ^= rol32((x[11] + x[10]),  9);
-		x[ 9] ^= rol32((x[ 8] + x[11]), 13);
-		x[10] ^= rol32((x[ 9] + x[ 8]), 18);
-		x[12] ^= rol32((x[15] + x[14]),  7);
-		x[13] ^= rol32((x[12] + x[15]),  9);
-		x[14] ^= rol32((x[13] + x[12]), 13);
-		x[15] ^= rol32((x[14] + x[13]), 18);
-	}
-
-	for (i = 0; i < 16; i++)
-		stream[i] = cpu_to_le32(x[i] + state[i]);
-
-	if (++state[8] == 0)
-		state[9]++;
-}
-
-static void salsa20_docrypt(u32 *state, u8 *dst, const u8 *src,
-			    unsigned int bytes)
-{
-	__le32 stream[SALSA20_BLOCK_SIZE / sizeof(__le32)];
-
-	while (bytes >= SALSA20_BLOCK_SIZE) {
-		salsa20_block(state, stream);
-		crypto_xor_cpy(dst, src, (const u8 *)stream,
-			       SALSA20_BLOCK_SIZE);
-		bytes -= SALSA20_BLOCK_SIZE;
-		dst += SALSA20_BLOCK_SIZE;
-		src += SALSA20_BLOCK_SIZE;
-	}
-	if (bytes) {
-		salsa20_block(state, stream);
-		crypto_xor_cpy(dst, src, (const u8 *)stream, bytes);
-	}
-}
-
-static void salsa20_init(u32 *state, const struct salsa20_ctx *ctx,
-			 const u8 *iv)
-{
-	memcpy(state, ctx->initial_state, sizeof(ctx->initial_state));
-	state[6] = get_unaligned_le32(iv + 0);
-	state[7] = get_unaligned_le32(iv + 4);
-}
-
-static int salsa20_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			  unsigned int keysize)
-{
-	static const char sigma[16] = "expand 32-byte k";
-	static const char tau[16] = "expand 16-byte k";
-	struct salsa20_ctx *ctx = crypto_skcipher_ctx(tfm);
-	const char *constants;
-
-	if (keysize != SALSA20_MIN_KEY_SIZE &&
-	    keysize != SALSA20_MAX_KEY_SIZE)
-		return -EINVAL;
-
-	ctx->initial_state[1] = get_unaligned_le32(key + 0);
-	ctx->initial_state[2] = get_unaligned_le32(key + 4);
-	ctx->initial_state[3] = get_unaligned_le32(key + 8);
-	ctx->initial_state[4] = get_unaligned_le32(key + 12);
-	if (keysize == 32) { /* recommended */
-		key += 16;
-		constants = sigma;
-	} else { /* keysize == 16 */
-		constants = tau;
-	}
-	ctx->initial_state[11] = get_unaligned_le32(key + 0);
-	ctx->initial_state[12] = get_unaligned_le32(key + 4);
-	ctx->initial_state[13] = get_unaligned_le32(key + 8);
-	ctx->initial_state[14] = get_unaligned_le32(key + 12);
-	ctx->initial_state[0]  = get_unaligned_le32(constants + 0);
-	ctx->initial_state[5]  = get_unaligned_le32(constants + 4);
-	ctx->initial_state[10] = get_unaligned_le32(constants + 8);
-	ctx->initial_state[15] = get_unaligned_le32(constants + 12);
-
-	/* space for the nonce; it will be overridden for each request */
-	ctx->initial_state[6] = 0;
-	ctx->initial_state[7] = 0;
-
-	/* initial block number */
-	ctx->initial_state[8] = 0;
-	ctx->initial_state[9] = 0;
-
-	return 0;
-}
-
-static int salsa20_crypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	const struct salsa20_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	u32 state[16];
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	salsa20_init(state, ctx, req->iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
-
-		salsa20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
-				nbytes);
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-	}
-
-	return err;
-}
-
-static struct skcipher_alg alg = {
-	.base.cra_name		= "salsa20",
-	.base.cra_driver_name	= "salsa20-generic",
-	.base.cra_priority	= 100,
-	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct salsa20_ctx),
-	.base.cra_module	= THIS_MODULE,
-
-	.min_keysize		= SALSA20_MIN_KEY_SIZE,
-	.max_keysize		= SALSA20_MAX_KEY_SIZE,
-	.ivsize			= SALSA20_IV_SIZE,
-	.chunksize		= SALSA20_BLOCK_SIZE,
-	.setkey			= salsa20_setkey,
-	.encrypt		= salsa20_crypt,
-	.decrypt		= salsa20_crypt,
-};
-
-static int __init salsa20_generic_mod_init(void)
-{
-	return crypto_register_skcipher(&alg);
-}
-
-static void __exit salsa20_generic_mod_fini(void)
-{
-	crypto_unregister_skcipher(&alg);
-}
-
-subsys_initcall(salsa20_generic_mod_init);
-module_exit(salsa20_generic_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm");
-MODULE_ALIAS_CRYPTO("salsa20");
-MODULE_ALIAS_CRYPTO("salsa20-generic");
diff --git a/crypto/serpent_generic.c b/crypto/serpent_generic.c
index 492c1d0bfe06..236c87547a17 100644
--- a/crypto/serpent_generic.c
+++ b/crypto/serpent_generic.c
@@ -5,17 +5,12 @@
  * Serpent Cipher Algorithm.
  *
  * Copyright (C) 2002 Dag Arne Osvik <osvik@ii.uib.no>
- *               2003 Herbert Valerio Riedel <hvr@gnu.org>
- *
- * Added tnepres support:
- *		Ruben Jesus Garcia Hernandez <ruben@ugr.es>, 18.10.2004
- *              Based on code by hvr
  */
 
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/errno.h>
-#include <asm/byteorder.h>
+#include <asm/unaligned.h>
 #include <linux/crypto.h>
 #include <linux/types.h>
 #include <crypto/serpent.h>
@@ -453,19 +448,12 @@ void __serpent_encrypt(const void *c, u8 *dst, const u8 *src)
 {
 	const struct serpent_ctx *ctx = c;
 	const u32 *k = ctx->expkey;
-	const __le32 *s = (const __le32 *)src;
-	__le32	*d = (__le32 *)dst;
 	u32	r0, r1, r2, r3, r4;
 
-/*
- * Note: The conversions between u8* and u32* might cause trouble
- * on architectures with stricter alignment rules than x86
- */
-
-	r0 = le32_to_cpu(s[0]);
-	r1 = le32_to_cpu(s[1]);
-	r2 = le32_to_cpu(s[2]);
-	r3 = le32_to_cpu(s[3]);
+	r0 = get_unaligned_le32(src);
+	r1 = get_unaligned_le32(src + 4);
+	r2 = get_unaligned_le32(src + 8);
+	r3 = get_unaligned_le32(src + 12);
 
 					K(r0, r1, r2, r3, 0);
 	S0(r0, r1, r2, r3, r4);		LK(r2, r1, r3, r0, r4, 1);
@@ -501,10 +489,10 @@ void __serpent_encrypt(const void *c, u8 *dst, const u8 *src)
 	S6(r0, r1, r3, r2, r4);		LK(r3, r4, r1, r2, r0, 31);
 	S7(r3, r4, r1, r2, r0);		K(r0, r1, r2, r3, 32);
 
-	d[0] = cpu_to_le32(r0);
-	d[1] = cpu_to_le32(r1);
-	d[2] = cpu_to_le32(r2);
-	d[3] = cpu_to_le32(r3);
+	put_unaligned_le32(r0, dst);
+	put_unaligned_le32(r1, dst + 4);
+	put_unaligned_le32(r2, dst + 8);
+	put_unaligned_le32(r3, dst + 12);
 }
 EXPORT_SYMBOL_GPL(__serpent_encrypt);
 
@@ -519,14 +507,12 @@ void __serpent_decrypt(const void *c, u8 *dst, const u8 *src)
 {
 	const struct serpent_ctx *ctx = c;
 	const u32 *k = ctx->expkey;
-	const __le32 *s = (const __le32 *)src;
-	__le32	*d = (__le32 *)dst;
 	u32	r0, r1, r2, r3, r4;
 
-	r0 = le32_to_cpu(s[0]);
-	r1 = le32_to_cpu(s[1]);
-	r2 = le32_to_cpu(s[2]);
-	r3 = le32_to_cpu(s[3]);
+	r0 = get_unaligned_le32(src);
+	r1 = get_unaligned_le32(src + 4);
+	r2 = get_unaligned_le32(src + 8);
+	r3 = get_unaligned_le32(src + 12);
 
 					K(r0, r1, r2, r3, 32);
 	SI7(r0, r1, r2, r3, r4);	KL(r1, r3, r0, r4, r2, 31);
@@ -562,10 +548,10 @@ void __serpent_decrypt(const void *c, u8 *dst, const u8 *src)
 	SI1(r3, r1, r2, r0, r4);	KL(r4, r1, r2, r0, r3, 1);
 	SI0(r4, r1, r2, r0, r3);	K(r2, r3, r1, r4, 0);
 
-	d[0] = cpu_to_le32(r2);
-	d[1] = cpu_to_le32(r3);
-	d[2] = cpu_to_le32(r1);
-	d[3] = cpu_to_le32(r4);
+	put_unaligned_le32(r2, dst);
+	put_unaligned_le32(r3, dst + 4);
+	put_unaligned_le32(r1, dst + 8);
+	put_unaligned_le32(r4, dst + 12);
 }
 EXPORT_SYMBOL_GPL(__serpent_decrypt);
 
@@ -576,66 +562,13 @@ static void serpent_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 	__serpent_decrypt(ctx, dst, src);
 }
 
-static int tnepres_setkey(struct crypto_tfm *tfm, const u8 *key,
-			  unsigned int keylen)
-{
-	u8 rev_key[SERPENT_MAX_KEY_SIZE];
-	int i;
-
-	for (i = 0; i < keylen; ++i)
-		rev_key[keylen - i - 1] = key[i];
-
-	return serpent_setkey(tfm, rev_key, keylen);
-}
-
-static void tnepres_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
-{
-	const u32 * const s = (const u32 * const)src;
-	u32 * const d = (u32 * const)dst;
-
-	u32 rs[4], rd[4];
-
-	rs[0] = swab32(s[3]);
-	rs[1] = swab32(s[2]);
-	rs[2] = swab32(s[1]);
-	rs[3] = swab32(s[0]);
-
-	serpent_encrypt(tfm, (u8 *)rd, (u8 *)rs);
-
-	d[0] = swab32(rd[3]);
-	d[1] = swab32(rd[2]);
-	d[2] = swab32(rd[1]);
-	d[3] = swab32(rd[0]);
-}
-
-static void tnepres_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
-{
-	const u32 * const s = (const u32 * const)src;
-	u32 * const d = (u32 * const)dst;
-
-	u32 rs[4], rd[4];
-
-	rs[0] = swab32(s[3]);
-	rs[1] = swab32(s[2]);
-	rs[2] = swab32(s[1]);
-	rs[3] = swab32(s[0]);
-
-	serpent_decrypt(tfm, (u8 *)rd, (u8 *)rs);
-
-	d[0] = swab32(rd[3]);
-	d[1] = swab32(rd[2]);
-	d[2] = swab32(rd[1]);
-	d[3] = swab32(rd[0]);
-}
-
-static struct crypto_alg srp_algs[2] = { {
+static struct crypto_alg srp_alg = {
 	.cra_name		=	"serpent",
 	.cra_driver_name	=	"serpent-generic",
 	.cra_priority		=	100,
 	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		=	SERPENT_BLOCK_SIZE,
 	.cra_ctxsize		=	sizeof(struct serpent_ctx),
-	.cra_alignmask		=	3,
 	.cra_module		=	THIS_MODULE,
 	.cra_u			=	{ .cipher = {
 	.cia_min_keysize	=	SERPENT_MIN_KEY_SIZE,
@@ -643,38 +576,23 @@ static struct crypto_alg srp_algs[2] = { {
 	.cia_setkey		=	serpent_setkey,
 	.cia_encrypt		=	serpent_encrypt,
 	.cia_decrypt		=	serpent_decrypt } }
-}, {
-	.cra_name		=	"tnepres",
-	.cra_driver_name	=	"tnepres-generic",
-	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
-	.cra_blocksize		=	SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct serpent_ctx),
-	.cra_alignmask		=	3,
-	.cra_module		=	THIS_MODULE,
-	.cra_u			=	{ .cipher = {
-	.cia_min_keysize	=	SERPENT_MIN_KEY_SIZE,
-	.cia_max_keysize	=	SERPENT_MAX_KEY_SIZE,
-	.cia_setkey		=	tnepres_setkey,
-	.cia_encrypt		=	tnepres_encrypt,
-	.cia_decrypt		=	tnepres_decrypt } }
-} };
+};
 
 static int __init serpent_mod_init(void)
 {
-	return crypto_register_algs(srp_algs, ARRAY_SIZE(srp_algs));
+	return crypto_register_alg(&srp_alg);
 }
 
 static void __exit serpent_mod_fini(void)
 {
-	crypto_unregister_algs(srp_algs, ARRAY_SIZE(srp_algs));
+	crypto_unregister_alg(&srp_alg);
 }
 
 subsys_initcall(serpent_mod_init);
 module_exit(serpent_mod_fini);
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Serpent and tnepres (kerneli compatible serpent reversed) Cipher Algorithm");
+MODULE_DESCRIPTION("Serpent Cipher Algorithm");
 MODULE_AUTHOR("Dag Arne Osvik <osvik@ii.uib.no>");
-MODULE_ALIAS_CRYPTO("tnepres");
 MODULE_ALIAS_CRYPTO("serpent");
 MODULE_ALIAS_CRYPTO("serpent-generic");
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index b4dae640de9f..a15376245416 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -10,6 +10,7 @@
  */
 
 #include <crypto/internal/aead.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/bug.h>
@@ -490,12 +491,6 @@ int skcipher_walk_virt(struct skcipher_walk *walk,
 }
 EXPORT_SYMBOL_GPL(skcipher_walk_virt);
 
-void skcipher_walk_atomise(struct skcipher_walk *walk)
-{
-	walk->flags &= ~SKCIPHER_WALK_SLEEP;
-}
-EXPORT_SYMBOL_GPL(skcipher_walk_atomise);
-
 int skcipher_walk_async(struct skcipher_walk *walk,
 			struct skcipher_request *req)
 {
@@ -986,3 +981,4 @@ EXPORT_SYMBOL_GPL(skcipher_alloc_instance_simple);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Symmetric key cipher type");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index a647bb298fbc..6b7c158dc508 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -70,8 +70,8 @@ static const char *check[] = {
 	"des", "md5", "des3_ede", "rot13", "sha1", "sha224", "sha256", "sm3",
 	"blowfish", "twofish", "serpent", "sha384", "sha512", "md4", "aes",
 	"cast6", "arc4", "michael_mic", "deflate", "crc32c", "tea", "xtea",
-	"khazad", "wp512", "wp384", "wp256", "tnepres", "xeta",  "fcrypt",
-	"camellia", "seed", "salsa20", "rmd128", "rmd160", "rmd256", "rmd320",
+	"khazad", "wp512", "wp384", "wp256", "xeta",  "fcrypt",
+	"camellia", "seed", "rmd160",
 	"lzo", "lzo-rle", "cts", "sha3-224", "sha3-256", "sha3-384",
 	"sha3-512", "streebog256", "streebog512",
 	NULL
@@ -199,8 +199,8 @@ static int test_mb_aead_jiffies(struct test_mb_aead_data *data, int enc,
 			goto out;
 	}
 
-	pr_cont("%d operations in %d seconds (%ld bytes)\n",
-		bcount * num_mb, secs, (long)bcount * blen * num_mb);
+	pr_cont("%d operations in %d seconds (%llu bytes)\n",
+		bcount * num_mb, secs, (u64)bcount * blen * num_mb);
 
 out:
 	kfree(rc);
@@ -471,8 +471,8 @@ static int test_aead_jiffies(struct aead_request *req, int enc,
 			return ret;
 	}
 
-	printk("%d operations in %d seconds (%ld bytes)\n",
-	       bcount, secs, (long)bcount * blen);
+	pr_cont("%d operations in %d seconds (%llu bytes)\n",
+	        bcount, secs, (u64)bcount * blen);
 	return 0;
 }
 
@@ -764,8 +764,8 @@ static int test_mb_ahash_jiffies(struct test_mb_ahash_data *data, int blen,
 			goto out;
 	}
 
-	pr_cont("%d operations in %d seconds (%ld bytes)\n",
-		bcount * num_mb, secs, (long)bcount * blen * num_mb);
+	pr_cont("%d operations in %d seconds (%llu bytes)\n",
+		bcount * num_mb, secs, (u64)bcount * blen * num_mb);
 
 out:
 	kfree(rc);
@@ -1201,8 +1201,8 @@ static int test_mb_acipher_jiffies(struct test_mb_skcipher_data *data, int enc,
 			goto out;
 	}
 
-	pr_cont("%d operations in %d seconds (%ld bytes)\n",
-		bcount * num_mb, secs, (long)bcount * blen * num_mb);
+	pr_cont("%d operations in %d seconds (%llu bytes)\n",
+		bcount * num_mb, secs, (u64)bcount * blen * num_mb);
 
 out:
 	kfree(rc);
@@ -1441,8 +1441,8 @@ static int test_acipher_jiffies(struct skcipher_request *req, int enc,
 			return ret;
 	}
 
-	pr_cont("%d operations in %d seconds (%ld bytes)\n",
-		bcount, secs, (long)bcount * blen);
+	pr_cont("%d operations in %d seconds (%llu bytes)\n",
+		bcount, secs, (u64)bcount * blen);
 	return 0;
 }
 
@@ -1806,27 +1806,11 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		ret += tcrypt_test("wp256");
 		break;
 
-	case 25:
-		ret += tcrypt_test("ecb(tnepres)");
-		break;
-
 	case 26:
 		ret += tcrypt_test("ecb(anubis)");
 		ret += tcrypt_test("cbc(anubis)");
 		break;
 
-	case 27:
-		ret += tcrypt_test("tgr192");
-		break;
-
-	case 28:
-		ret += tcrypt_test("tgr160");
-		break;
-
-	case 29:
-		ret += tcrypt_test("tgr128");
-		break;
-
 	case 30:
 		ret += tcrypt_test("ecb(xeta)");
 		break;
@@ -1847,10 +1831,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		ret += tcrypt_test("sha224");
 		break;
 
-	case 34:
-		ret += tcrypt_test("salsa20");
-		break;
-
 	case 35:
 		ret += tcrypt_test("gcm(aes)");
 		break;
@@ -1867,22 +1847,10 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		ret += tcrypt_test("cts(cbc(aes))");
 		break;
 
-        case 39:
-		ret += tcrypt_test("rmd128");
-		break;
-
         case 40:
 		ret += tcrypt_test("rmd160");
 		break;
 
-	case 41:
-		ret += tcrypt_test("rmd256");
-		break;
-
-	case 42:
-		ret += tcrypt_test("rmd320");
-		break;
-
 	case 43:
 		ret += tcrypt_test("ecb(seed)");
 		break;
@@ -1955,10 +1923,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		ret += tcrypt_test("xcbc(aes)");
 		break;
 
-	case 107:
-		ret += tcrypt_test("hmac(rmd128)");
-		break;
-
 	case 108:
 		ret += tcrypt_test("hmac(rmd160)");
 		break;
@@ -2181,11 +2145,6 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 				speed_template_32_48_64);
 		break;
 
-	case 206:
-		test_cipher_speed("salsa20", ENCRYPT, sec, NULL, 0,
-				  speed_template_16_32);
-		break;
-
 	case 207:
 		test_cipher_speed("ecb(serpent)", ENCRYPT, sec, NULL, 0,
 				  speed_template_16_32);
@@ -2393,38 +2352,14 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		test_hash_speed("wp512", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
 		fallthrough;
-	case 310:
-		test_hash_speed("tgr128", sec, generic_hash_speed_template);
-		if (mode > 300 && mode < 400) break;
-		fallthrough;
-	case 311:
-		test_hash_speed("tgr160", sec, generic_hash_speed_template);
-		if (mode > 300 && mode < 400) break;
-		fallthrough;
-	case 312:
-		test_hash_speed("tgr192", sec, generic_hash_speed_template);
-		if (mode > 300 && mode < 400) break;
-		fallthrough;
 	case 313:
 		test_hash_speed("sha224", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
 		fallthrough;
-	case 314:
-		test_hash_speed("rmd128", sec, generic_hash_speed_template);
-		if (mode > 300 && mode < 400) break;
-		fallthrough;
 	case 315:
 		test_hash_speed("rmd160", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
 		fallthrough;
-	case 316:
-		test_hash_speed("rmd256", sec, generic_hash_speed_template);
-		if (mode > 300 && mode < 400) break;
-		fallthrough;
-	case 317:
-		test_hash_speed("rmd320", sec, generic_hash_speed_template);
-		if (mode > 300 && mode < 400) break;
-		fallthrough;
 	case 318:
 		klen = 16;
 		test_hash_speed("ghash", sec, generic_hash_speed_template);
@@ -2517,38 +2452,14 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		test_ahash_speed("wp512", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
 		fallthrough;
-	case 410:
-		test_ahash_speed("tgr128", sec, generic_hash_speed_template);
-		if (mode > 400 && mode < 500) break;
-		fallthrough;
-	case 411:
-		test_ahash_speed("tgr160", sec, generic_hash_speed_template);
-		if (mode > 400 && mode < 500) break;
-		fallthrough;
-	case 412:
-		test_ahash_speed("tgr192", sec, generic_hash_speed_template);
-		if (mode > 400 && mode < 500) break;
-		fallthrough;
 	case 413:
 		test_ahash_speed("sha224", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
 		fallthrough;
-	case 414:
-		test_ahash_speed("rmd128", sec, generic_hash_speed_template);
-		if (mode > 400 && mode < 500) break;
-		fallthrough;
 	case 415:
 		test_ahash_speed("rmd160", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
 		fallthrough;
-	case 416:
-		test_ahash_speed("rmd256", sec, generic_hash_speed_template);
-		if (mode > 400 && mode < 500) break;
-		fallthrough;
-	case 417:
-		test_ahash_speed("rmd320", sec, generic_hash_speed_template);
-		if (mode > 400 && mode < 500) break;
-		fallthrough;
 	case 418:
 		test_ahash_speed("sha3-224", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 321e38eef51b..93359999c94b 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -33,10 +33,13 @@
 #include <crypto/akcipher.h>
 #include <crypto/kpp.h>
 #include <crypto/acompress.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/simd.h>
 
 #include "internal.h"
 
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
+
 static bool notests;
 module_param(notests, bool, 0644);
 MODULE_PARM_DESC(notests, "disable crypto self-tests");
@@ -4874,12 +4877,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.cipher = __VECS(tea_tv_template)
 		}
 	}, {
-		.alg = "ecb(tnepres)",
-		.test = alg_test_skcipher,
-		.suite = {
-			.cipher = __VECS(tnepres_tv_template)
-		}
-	}, {
 		.alg = "ecb(twofish)",
 		.test = alg_test_skcipher,
 		.suite = {
@@ -4955,12 +4952,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.hash = __VECS(hmac_md5_tv_template)
 		}
 	}, {
-		.alg = "hmac(rmd128)",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(hmac_rmd128_tv_template)
-		}
-	}, {
 		.alg = "hmac(rmd160)",
 		.test = alg_test_hash,
 		.suite = {
@@ -5273,30 +5264,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
-		.alg = "rmd128",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(rmd128_tv_template)
-		}
-	}, {
 		.alg = "rmd160",
 		.test = alg_test_hash,
 		.suite = {
 			.hash = __VECS(rmd160_tv_template)
 		}
 	}, {
-		.alg = "rmd256",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(rmd256_tv_template)
-		}
-	}, {
-		.alg = "rmd320",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(rmd320_tv_template)
-		}
-	}, {
 		.alg = "rsa",
 		.test = alg_test_akcipher,
 		.fips_allowed = 1,
@@ -5304,12 +5277,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.akcipher = __VECS(rsa_tv_template)
 		}
 	}, {
-		.alg = "salsa20",
-		.test = alg_test_skcipher,
-		.suite = {
-			.cipher = __VECS(salsa20_stream_tv_template)
-		}
-	}, {
 		.alg = "sha1",
 		.test = alg_test_hash,
 		.fips_allowed = 1,
@@ -5397,24 +5364,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.hash = __VECS(streebog512_tv_template)
 		}
 	}, {
-		.alg = "tgr128",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(tgr128_tv_template)
-		}
-	}, {
-		.alg = "tgr160",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(tgr160_tv_template)
-		}
-	}, {
-		.alg = "tgr192",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(tgr192_tv_template)
-		}
-	}, {
 		.alg = "vmac64(aes)",
 		.test = alg_test_hash,
 		.suite = {
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 8c83811c0e35..ced56ea0c9b4 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -3141,66 +3141,6 @@ static const struct hash_testvec md5_tv_template[] = {
 };
 
 /*
- * RIPEMD-128 test vectors from ISO/IEC 10118-3:2004(E)
- */
-static const struct hash_testvec rmd128_tv_template[] = {
-	{
-		.digest	= "\xcd\xf2\x62\x13\xa1\x50\xdc\x3e"
-			  "\xcb\x61\x0f\x18\xf6\xb3\x8b\x46",
-	}, {
-		.plaintext = "a",
-		.psize	= 1,
-		.digest	= "\x86\xbe\x7a\xfa\x33\x9d\x0f\xc7"
-			  "\xcf\xc7\x85\xe7\x2f\x57\x8d\x33",
-	}, {
-		.plaintext = "abc",
-		.psize	= 3,
-		.digest	= "\xc1\x4a\x12\x19\x9c\x66\xe4\xba"
-			  "\x84\x63\x6b\x0f\x69\x14\x4c\x77",
-	}, {
-		.plaintext = "message digest",
-		.psize	= 14,
-		.digest	= "\x9e\x32\x7b\x3d\x6e\x52\x30\x62"
-			  "\xaf\xc1\x13\x2d\x7d\xf9\xd1\xb8",
-	}, {
-		.plaintext = "abcdefghijklmnopqrstuvwxyz",
-		.psize	= 26,
-		.digest	= "\xfd\x2a\xa6\x07\xf7\x1d\xc8\xf5"
-			  "\x10\x71\x49\x22\xb3\x71\x83\x4e",
-	}, {
-		.plaintext = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcde"
-			     "fghijklmnopqrstuvwxyz0123456789",
-		.psize	= 62,
-		.digest	= "\xd1\xe9\x59\xeb\x17\x9c\x91\x1f"
-			  "\xae\xa4\x62\x4c\x60\xc5\xc7\x02",
-	}, {
-		.plaintext = "1234567890123456789012345678901234567890"
-			     "1234567890123456789012345678901234567890",
-		.psize	= 80,
-		.digest	= "\x3f\x45\xef\x19\x47\x32\xc2\xdb"
-			  "\xb2\xc4\xa2\xc7\x69\x79\x5f\xa3",
-	}, {
-		.plaintext = "abcdbcdecdefdefgefghfghighij"
-			     "hijkijkljklmklmnlmnomnopnopq",
-		.psize	= 56,
-		.digest	= "\xa1\xaa\x06\x89\xd0\xfa\xfa\x2d"
-			  "\xdc\x22\xe8\x8b\x49\x13\x3a\x06",
-	}, {
-		.plaintext = "abcdefghbcdefghicdefghijdefghijkefghijklfghi"
-			     "jklmghijklmnhijklmnoijklmnopjklmnopqklmnopqr"
-			     "lmnopqrsmnopqrstnopqrstu",
-		.psize	= 112,
-		.digest	= "\xd4\xec\xc9\x13\xe1\xdf\x77\x6b"
-			  "\xf4\x8d\xe9\xd5\x5b\x1f\x25\x46",
-	}, {
-		.plaintext = "abcdbcdecdefdefgefghfghighijhijk",
-		.psize	= 32,
-		.digest	= "\x13\xfc\x13\xe8\xef\xff\x34\x7d"
-			  "\xe1\x93\xff\x46\xdb\xac\xcf\xd4",
-	}
-};
-
-/*
  * RIPEMD-160 test vectors from ISO/IEC 10118-3:2004(E)
  */
 static const struct hash_testvec rmd160_tv_template[] = {
@@ -3260,134 +3200,6 @@ static const struct hash_testvec rmd160_tv_template[] = {
 	}
 };
 
-/*
- * RIPEMD-256 test vectors
- */
-static const struct hash_testvec rmd256_tv_template[] = {
-	{
-		.digest	= "\x02\xba\x4c\x4e\x5f\x8e\xcd\x18"
-			  "\x77\xfc\x52\xd6\x4d\x30\xe3\x7a"
-			  "\x2d\x97\x74\xfb\x1e\x5d\x02\x63"
-			  "\x80\xae\x01\x68\xe3\xc5\x52\x2d",
-	}, {
-		.plaintext = "a",
-		.psize	= 1,
-		.digest	= "\xf9\x33\x3e\x45\xd8\x57\xf5\xd9"
-			  "\x0a\x91\xba\xb7\x0a\x1e\xba\x0c"
-			  "\xfb\x1b\xe4\xb0\x78\x3c\x9a\xcf"
-			  "\xcd\x88\x3a\x91\x34\x69\x29\x25",
-	}, {
-		.plaintext = "abc",
-		.psize	= 3,
-		.digest	= "\xaf\xbd\x6e\x22\x8b\x9d\x8c\xbb"
-			  "\xce\xf5\xca\x2d\x03\xe6\xdb\xa1"
-			  "\x0a\xc0\xbc\x7d\xcb\xe4\x68\x0e"
-			  "\x1e\x42\xd2\xe9\x75\x45\x9b\x65",
-	}, {
-		.plaintext = "message digest",
-		.psize	= 14,
-		.digest	= "\x87\xe9\x71\x75\x9a\x1c\xe4\x7a"
-			  "\x51\x4d\x5c\x91\x4c\x39\x2c\x90"
-			  "\x18\xc7\xc4\x6b\xc1\x44\x65\x55"
-			  "\x4a\xfc\xdf\x54\xa5\x07\x0c\x0e",
-	}, {
-		.plaintext = "abcdefghijklmnopqrstuvwxyz",
-		.psize	= 26,
-		.digest	= "\x64\x9d\x30\x34\x75\x1e\xa2\x16"
-			  "\x77\x6b\xf9\xa1\x8a\xcc\x81\xbc"
-			  "\x78\x96\x11\x8a\x51\x97\x96\x87"
-			  "\x82\xdd\x1f\xd9\x7d\x8d\x51\x33",
-	}, {
-		.plaintext = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcde"
-			     "fghijklmnopqrstuvwxyz0123456789",
-		.psize	= 62,
-		.digest	= "\x57\x40\xa4\x08\xac\x16\xb7\x20"
-			  "\xb8\x44\x24\xae\x93\x1c\xbb\x1f"
-			  "\xe3\x63\xd1\xd0\xbf\x40\x17\xf1"
-			  "\xa8\x9f\x7e\xa6\xde\x77\xa0\xb8",
-	}, {
-		.plaintext = "1234567890123456789012345678901234567890"
-			     "1234567890123456789012345678901234567890",
-		.psize	= 80,
-		.digest	= "\x06\xfd\xcc\x7a\x40\x95\x48\xaa"
-			  "\xf9\x13\x68\xc0\x6a\x62\x75\xb5"
-			  "\x53\xe3\xf0\x99\xbf\x0e\xa4\xed"
-			  "\xfd\x67\x78\xdf\x89\xa8\x90\xdd",
-	}, {
-		.plaintext = "abcdbcdecdefdefgefghfghighij"
-			     "hijkijkljklmklmnlmnomnopnopq",
-		.psize	= 56,
-		.digest	= "\x38\x43\x04\x55\x83\xaa\xc6\xc8"
-			  "\xc8\xd9\x12\x85\x73\xe7\xa9\x80"
-			  "\x9a\xfb\x2a\x0f\x34\xcc\xc3\x6e"
-			  "\xa9\xe7\x2f\x16\xf6\x36\x8e\x3f",
-	}
-};
-
-/*
- * RIPEMD-320 test vectors
- */
-static const struct hash_testvec rmd320_tv_template[] = {
-	{
-		.digest	= "\x22\xd6\x5d\x56\x61\x53\x6c\xdc\x75\xc1"
-			  "\xfd\xf5\xc6\xde\x7b\x41\xb9\xf2\x73\x25"
-			  "\xeb\xc6\x1e\x85\x57\x17\x7d\x70\x5a\x0e"
-			  "\xc8\x80\x15\x1c\x3a\x32\xa0\x08\x99\xb8",
-	}, {
-		.plaintext = "a",
-		.psize	= 1,
-		.digest	= "\xce\x78\x85\x06\x38\xf9\x26\x58\xa5\xa5"
-			  "\x85\x09\x75\x79\x92\x6d\xda\x66\x7a\x57"
-			  "\x16\x56\x2c\xfc\xf6\xfb\xe7\x7f\x63\x54"
-			  "\x2f\x99\xb0\x47\x05\xd6\x97\x0d\xff\x5d",
-	}, {
-		.plaintext = "abc",
-		.psize	= 3,
-		.digest	= "\xde\x4c\x01\xb3\x05\x4f\x89\x30\xa7\x9d"
-			  "\x09\xae\x73\x8e\x92\x30\x1e\x5a\x17\x08"
-			  "\x5b\xef\xfd\xc1\xb8\xd1\x16\x71\x3e\x74"
-			  "\xf8\x2f\xa9\x42\xd6\x4c\xdb\xc4\x68\x2d",
-	}, {
-		.plaintext = "message digest",
-		.psize	= 14,
-		.digest	= "\x3a\x8e\x28\x50\x2e\xd4\x5d\x42\x2f\x68"
-			  "\x84\x4f\x9d\xd3\x16\xe7\xb9\x85\x33\xfa"
-			  "\x3f\x2a\x91\xd2\x9f\x84\xd4\x25\xc8\x8d"
-			  "\x6b\x4e\xff\x72\x7d\xf6\x6a\x7c\x01\x97",
-	}, {
-		.plaintext = "abcdefghijklmnopqrstuvwxyz",
-		.psize	= 26,
-		.digest	= "\xca\xbd\xb1\x81\x0b\x92\x47\x0a\x20\x93"
-			  "\xaa\x6b\xce\x05\x95\x2c\x28\x34\x8c\xf4"
-			  "\x3f\xf6\x08\x41\x97\x51\x66\xbb\x40\xed"
-			  "\x23\x40\x04\xb8\x82\x44\x63\xe6\xb0\x09",
-	}, {
-		.plaintext = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcde"
-			     "fghijklmnopqrstuvwxyz0123456789",
-		.psize	= 62,
-		.digest	= "\xed\x54\x49\x40\xc8\x6d\x67\xf2\x50\xd2"
-			  "\x32\xc3\x0b\x7b\x3e\x57\x70\xe0\xc6\x0c"
-			  "\x8c\xb9\xa4\xca\xfe\x3b\x11\x38\x8a\xf9"
-			  "\x92\x0e\x1b\x99\x23\x0b\x84\x3c\x86\xa4",
-	}, {
-		.plaintext = "1234567890123456789012345678901234567890"
-			     "1234567890123456789012345678901234567890",
-		.psize	= 80,
-		.digest	= "\x55\x78\x88\xaf\x5f\x6d\x8e\xd6\x2a\xb6"
-			  "\x69\x45\xc6\xd2\xa0\xa4\x7e\xcd\x53\x41"
-			  "\xe9\x15\xeb\x8f\xea\x1d\x05\x24\x95\x5f"
-			  "\x82\x5d\xc7\x17\xe4\xa0\x08\xab\x2d\x42",
-	}, {
-		.plaintext = "abcdbcdecdefdefgefghfghighij"
-			     "hijkijkljklmklmnlmnomnopnopq",
-		.psize	= 56,
-		.digest	= "\xd0\x34\xa7\x95\x0c\xf7\x22\x02\x1b\xa4"
-			  "\xb8\x4d\xf7\x69\xa5\xde\x20\x60\xe2\x59"
-			  "\xdf\x4c\x9b\xb4\xa4\x26\x8c\x0e\x93\x5b"
-			  "\xbc\x74\x70\xa9\x69\xc9\xd0\x72\xa1\xac",
-	}
-};
-
 static const struct hash_testvec crct10dif_tv_template[] = {
 	{
 		.plaintext	= "abc",
@@ -5138,132 +4950,6 @@ static const struct hash_testvec wp256_tv_template[] = {
 	},
 };
 
-/*
- * TIGER test vectors from Tiger website
- */
-static const struct hash_testvec tgr192_tv_template[] = {
-	{
-		.plaintext = "",
-		.psize	= 0,
-		.digest = "\x24\xf0\x13\x0c\x63\xac\x93\x32"
-			  "\x16\x16\x6e\x76\xb1\xbb\x92\x5f"
-			  "\xf3\x73\xde\x2d\x49\x58\x4e\x7a",
-	}, {
-		.plaintext = "abc",
-		.psize	= 3,
-		.digest = "\xf2\x58\xc1\xe8\x84\x14\xab\x2a"
-			  "\x52\x7a\xb5\x41\xff\xc5\xb8\xbf"
-			  "\x93\x5f\x7b\x95\x1c\x13\x29\x51",
-	}, {
-		.plaintext = "Tiger",
-		.psize	= 5,
-		.digest = "\x9f\x00\xf5\x99\x07\x23\x00\xdd"
-			  "\x27\x6a\xbb\x38\xc8\xeb\x6d\xec"
-			  "\x37\x79\x0c\x11\x6f\x9d\x2b\xdf",
-	}, {
-		.plaintext = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+-",
-		.psize	= 64,
-		.digest = "\x87\xfb\x2a\x90\x83\x85\x1c\xf7"
-			  "\x47\x0d\x2c\xf8\x10\xe6\xdf\x9e"
-			  "\xb5\x86\x44\x50\x34\xa5\xa3\x86",
-	}, {
-		.plaintext = "ABCDEFGHIJKLMNOPQRSTUVWXYZ=abcdefghijklmnopqrstuvwxyz+0123456789",
-		.psize	= 64,
-		.digest = "\x46\x7d\xb8\x08\x63\xeb\xce\x48"
-			  "\x8d\xf1\xcd\x12\x61\x65\x5d\xe9"
-			  "\x57\x89\x65\x65\x97\x5f\x91\x97",
-	}, {
-		.plaintext = "Tiger - A Fast New Hash Function, "
-			   "by Ross Anderson and Eli Biham, "
-			   "proceedings of Fast Software Encryption 3, "
-			   "Cambridge, 1996.",
-		.psize  = 125,
-		.digest = "\x3d\x9a\xeb\x03\xd1\xbd\x1a\x63"
-			  "\x57\xb2\x77\x4d\xfd\x6d\x5b\x24"
-			  "\xdd\x68\x15\x1d\x50\x39\x74\xfc",
-	},
-};
-
-static const struct hash_testvec tgr160_tv_template[] = {
-	{
-		.plaintext = "",
-		.psize	= 0,
-		.digest = "\x24\xf0\x13\x0c\x63\xac\x93\x32"
-			  "\x16\x16\x6e\x76\xb1\xbb\x92\x5f"
-			  "\xf3\x73\xde\x2d",
-	}, {
-		.plaintext = "abc",
-		.psize	= 3,
-		.digest = "\xf2\x58\xc1\xe8\x84\x14\xab\x2a"
-			  "\x52\x7a\xb5\x41\xff\xc5\xb8\xbf"
-			  "\x93\x5f\x7b\x95",
-	}, {
-		.plaintext = "Tiger",
-		.psize	= 5,
-		.digest = "\x9f\x00\xf5\x99\x07\x23\x00\xdd"
-			  "\x27\x6a\xbb\x38\xc8\xeb\x6d\xec"
-			  "\x37\x79\x0c\x11",
-	}, {
-		.plaintext = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+-",
-		.psize	= 64,
-		.digest = "\x87\xfb\x2a\x90\x83\x85\x1c\xf7"
-			  "\x47\x0d\x2c\xf8\x10\xe6\xdf\x9e"
-			  "\xb5\x86\x44\x50",
-	}, {
-		.plaintext = "ABCDEFGHIJKLMNOPQRSTUVWXYZ=abcdefghijklmnopqrstuvwxyz+0123456789",
-		.psize	= 64,
-		.digest = "\x46\x7d\xb8\x08\x63\xeb\xce\x48"
-			  "\x8d\xf1\xcd\x12\x61\x65\x5d\xe9"
-			  "\x57\x89\x65\x65",
-	}, {
-		.plaintext = "Tiger - A Fast New Hash Function, "
-			   "by Ross Anderson and Eli Biham, "
-			   "proceedings of Fast Software Encryption 3, "
-			   "Cambridge, 1996.",
-		.psize  = 125,
-		.digest = "\x3d\x9a\xeb\x03\xd1\xbd\x1a\x63"
-			  "\x57\xb2\x77\x4d\xfd\x6d\x5b\x24"
-			  "\xdd\x68\x15\x1d",
-	},
-};
-
-static const struct hash_testvec tgr128_tv_template[] = {
-	{
-		.plaintext = "",
-		.psize	= 0,
-		.digest = "\x24\xf0\x13\x0c\x63\xac\x93\x32"
-			  "\x16\x16\x6e\x76\xb1\xbb\x92\x5f",
-	}, {
-		.plaintext = "abc",
-		.psize	= 3,
-		.digest = "\xf2\x58\xc1\xe8\x84\x14\xab\x2a"
-			  "\x52\x7a\xb5\x41\xff\xc5\xb8\xbf",
-	}, {
-		.plaintext = "Tiger",
-		.psize	= 5,
-		.digest = "\x9f\x00\xf5\x99\x07\x23\x00\xdd"
-			  "\x27\x6a\xbb\x38\xc8\xeb\x6d\xec",
-	}, {
-		.plaintext = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+-",
-		.psize	= 64,
-		.digest = "\x87\xfb\x2a\x90\x83\x85\x1c\xf7"
-			  "\x47\x0d\x2c\xf8\x10\xe6\xdf\x9e",
-	}, {
-		.plaintext = "ABCDEFGHIJKLMNOPQRSTUVWXYZ=abcdefghijklmnopqrstuvwxyz+0123456789",
-		.psize	= 64,
-		.digest = "\x46\x7d\xb8\x08\x63\xeb\xce\x48"
-			  "\x8d\xf1\xcd\x12\x61\x65\x5d\xe9",
-	}, {
-		.plaintext = "Tiger - A Fast New Hash Function, "
-			   "by Ross Anderson and Eli Biham, "
-			   "proceedings of Fast Software Encryption 3, "
-			   "Cambridge, 1996.",
-		.psize  = 125,
-		.digest = "\x3d\x9a\xeb\x03\xd1\xbd\x1a\x63"
-			  "\x57\xb2\x77\x4d\xfd\x6d\x5b\x24",
-	},
-};
-
 static const struct hash_testvec ghash_tv_template[] =
 {
 	{
@@ -5453,83 +5139,6 @@ static const struct hash_testvec hmac_md5_tv_template[] =
 };
 
 /*
- * HMAC-RIPEMD128 test vectors from RFC2286
- */
-static const struct hash_testvec hmac_rmd128_tv_template[] = {
-	{
-		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b",
-		.ksize	= 16,
-		.plaintext = "Hi There",
-		.psize	= 8,
-		.digest	= "\xfb\xf6\x1f\x94\x92\xaa\x4b\xbf"
-			  "\x81\xc1\x72\xe8\x4e\x07\x34\xdb",
-	}, {
-		.key	= "Jefe",
-		.ksize	= 4,
-		.plaintext = "what do ya want for nothing?",
-		.psize	= 28,
-		.digest	= "\x87\x5f\x82\x88\x62\xb6\xb3\x34"
-			  "\xb4\x27\xc5\x5f\x9f\x7f\xf0\x9b",
-	}, {
-		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa",
-		.ksize	= 16,
-		.plaintext = "\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd"
-			"\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd"
-			"\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd"
-			"\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd",
-		.psize	= 50,
-		.digest	= "\x09\xf0\xb2\x84\x6d\x2f\x54\x3d"
-			  "\xa3\x63\xcb\xec\x8d\x62\xa3\x8d",
-	}, {
-		.key	= "\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",
-		.ksize	= 25,
-		.plaintext = "\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd"
-			"\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd"
-			"\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd"
-			"\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd",
-		.psize	= 50,
-		.digest	= "\xbd\xbb\xd7\xcf\x03\xe4\x4b\x5a"
-			  "\xa6\x0a\xf8\x15\xbe\x4d\x22\x94",
-	}, {
-		.key	= "\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c\x0c",
-		.ksize	= 16,
-		.plaintext = "Test With Truncation",
-		.psize	= 20,
-		.digest	= "\xe7\x98\x08\xf2\x4b\x25\xfd\x03"
-			  "\x1c\x15\x5f\x0d\x55\x1d\x9a\x3a",
-	}, {
-		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa",
-		.ksize	= 80,
-		.plaintext = "Test Using Larger Than Block-Size Key - Hash Key First",
-		.psize	= 54,
-		.digest	= "\xdc\x73\x29\x28\xde\x98\x10\x4a"
-			  "\x1f\x59\xd3\x73\xc1\x50\xac\xbb",
-	}, {
-		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
-			"\xaa\xaa",
-		.ksize	= 80,
-		.plaintext = "Test Using Larger Than Block-Size Key and Larger Than One "
-			   "Block-Size Data",
-		.psize	= 73,
-		.digest	= "\x5c\x6b\xec\x96\x79\x3e\x16\xd4"
-			  "\x06\x90\xc2\x37\x63\x5f\x30\xc5",
-	},
-};
-
-/*
  * HMAC-RIPEMD160 test vectors from RFC2286
  */
 static const struct hash_testvec hmac_rmd160_tv_template[] = {
@@ -11806,85 +11415,6 @@ static const struct cipher_testvec serpent_tv_template[] = {
 	},
 };
 
-static const struct cipher_testvec tnepres_tv_template[] = {
-	{ /* KeySize=0 */
-		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ctext	= "\x41\xcc\x6b\x31\x59\x31\x45\x97"
-			  "\x6d\x6f\xbb\x38\x4b\x37\x21\x28",
-		.len	= 16,
-	},
-	{ /* KeySize=128, PT=0, I=1 */
-		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.key    = "\x80\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen   = 16,
-		.ctext	= "\x49\xaf\xbf\xad\x9d\x5a\x34\x05"
-			  "\x2c\xd8\xff\xa5\x98\x6b\xd2\xdd",
-		.len	= 16,
-	}, { /* KeySize=128 */
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.klen	= 16,
-		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ctext	= "\xea\xf4\xd7\xfc\xd8\x01\x34\x47"
-			  "\x81\x45\x0b\xfa\x0c\xd6\xad\x6e",
-		.len	= 16,
-	}, { /* KeySize=128, I=121 */
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80",
-		.klen	= 16,
-		.ptext	= zeroed_string,
-		.ctext	= "\x3d\xda\xbf\xc0\x06\xda\xab\x06"
-			  "\x46\x2a\xf4\xef\x81\x54\x4e\x26",
-		.len	= 16,
-	}, { /* KeySize=192, PT=0, I=1 */
-		.key	= "\x80\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,
-		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ctext	= "\xe7\x8e\x54\x02\xc7\x19\x55\x68"
-			  "\xac\x36\x78\xf7\xa3\xf6\x0c\x66",
-		.len	= 16,
-	}, { /* KeySize=256, PT=0, I=1 */
-		.key	= "\x80\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,
-		.ptext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			  "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ctext	= "\xab\xed\x96\xe7\x66\xbf\x28\xcb"
-			  "\xc0\xeb\xd2\x1a\x82\xef\x08\x19",
-		.len	= 16,
-	}, { /* KeySize=256, I=257 */
-		.key	= "\x1f\x1e\x1d\x1c\x1b\x1a\x19\x18"
-			  "\x17\x16\x15\x14\x13\x12\x11\x10"
-			  "\x0f\x0e\x0d\x0c\x0b\x0a\x09\x08"
-			  "\x07\x06\x05\x04\x03\x02\x01\x00",
-		.klen	= 32,
-		.ptext	= "\x0f\x0e\x0d\x0c\x0b\x0a\x09\x08"
-			  "\x07\x06\x05\x04\x03\x02\x01\x00",
-		.ctext	= "\x5c\xe7\x1c\x70\xd2\x88\x2e\x5b"
-			  "\xb8\x32\xe4\x33\xf8\x9f\x26\xde",
-		.len	= 16,
-	}, { /* KeySize=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,
-		.ptext	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.ctext	= "\x64\xa9\x1a\x37\xed\x9f\xe7\x49"
-			  "\xa8\x4e\x76\xd6\xf5\x0d\x78\xee",
-		.len	= 16,
-	}
-};
-
 static const struct cipher_testvec serpent_cbc_tv_template[] = {
 	{ /* Generated with Crypto++ */
 		.key	= "\x85\x62\x3F\x1C\xF9\xD6\x1C\xF9"
@@ -24800,1168 +24330,6 @@ static const struct cipher_testvec seed_tv_template[] = {
 	}
 };
 
-static const struct cipher_testvec salsa20_stream_tv_template[] = {
-	/*
-	* Testvectors from verified.test-vectors submitted to ECRYPT.
-	* They are truncated to size 39, 64, 111, 129 to test a variety
-	* of input length.
-	*/
-	{ /* Set 3, vector 0 */
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			"\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F",
-		.klen	= 16,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ptext	= "\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"
-			"\x00\x00\x00\x00\x00\x00\x00",
-		.ctext	= "\x2D\xD5\xC3\xF7\xBA\x2B\x20\xF7"
-			 "\x68\x02\x41\x0C\x68\x86\x88\x89"
-			 "\x5A\xD8\xC1\xBD\x4E\xA6\xC9\xB1"
-			 "\x40\xFB\x9B\x90\xE2\x10\x49\xBF"
-			 "\x58\x3F\x52\x79\x70\xEB\xC1",
-		.len	= 39,
-	}, { /* Set 5, vector 0 */
-		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
-			"\x00\x00\x00\x00\x00\x00\x00\x00",
-		.klen	= 16,
-		.iv     = "\x80\x00\x00\x00\x00\x00\x00\x00",
-		.ptext	= "\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"
-			"\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",
-		.ctext	= "\xB6\x6C\x1E\x44\x46\xDD\x95\x57"
-			 "\xE5\x78\xE2\x23\xB0\xB7\x68\x01"
-			 "\x7B\x23\xB2\x67\xBB\x02\x34\xAE"
-			 "\x46\x26\xBF\x44\x3F\x21\x97\x76"
-			 "\x43\x6F\xB1\x9F\xD0\xE8\x86\x6F"
-			 "\xCD\x0D\xE9\xA9\x53\x8F\x4A\x09"
-			 "\xCA\x9A\xC0\x73\x2E\x30\xBC\xF9"
-			 "\x8E\x4F\x13\xE4\xB9\xE2\x01\xD9",
-		.len	= 64,
-	}, { /* Set 3, vector 27 */
-		.key	= "\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",
-		.klen	= 32,
-		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ptext	= "\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"
-			"\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"
-			"\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"
-			"\x00\x00\x00\x00\x00\x00\x00\x00"
-			"\x00\x00\x00\x00\x00\x00\x00",
-		.ctext	= "\xAE\x39\x50\x8E\xAC\x9A\xEC\xE7"
-			 "\xBF\x97\xBB\x20\xB9\xDE\xE4\x1F"
-			 "\x87\xD9\x47\xF8\x28\x91\x35\x98"
-			 "\xDB\x72\xCC\x23\x29\x48\x56\x5E"
-			 "\x83\x7E\x0B\xF3\x7D\x5D\x38\x7B"
-			 "\x2D\x71\x02\xB4\x3B\xB5\xD8\x23"
-			 "\xB0\x4A\xDF\x3C\xEC\xB6\xD9\x3B"
-			 "\x9B\xA7\x52\xBE\xC5\xD4\x50\x59"
-			 "\x15\x14\xB4\x0E\x40\xE6\x53\xD1"
-			 "\x83\x9C\x5B\xA0\x92\x29\x6B\x5E"
-			 "\x96\x5B\x1E\x2F\xD3\xAC\xC1\x92"
-			 "\xB1\x41\x3F\x19\x2F\xC4\x3B\xC6"
-			 "\x95\x46\x45\x54\xE9\x75\x03\x08"
-			 "\x44\xAF\xE5\x8A\x81\x12\x09",
-		.len	= 111,
-	}, { /* Set 5, vector 27 */
-		.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\x10\x00\x00\x00\x00",
-		.ptext	= "\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"
-			"\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"
-			"\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"
-			"\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"
-			"\x00",
-		.ctext	= "\xD2\xDB\x1A\x5C\xF1\xC1\xAC\xDB"
-			 "\xE8\x1A\x7A\x43\x40\xEF\x53\x43"
-			 "\x5E\x7F\x4B\x1A\x50\x52\x3F\x8D"
-			 "\x28\x3D\xCF\x85\x1D\x69\x6E\x60"
-			 "\xF2\xDE\x74\x56\x18\x1B\x84\x10"
-			 "\xD4\x62\xBA\x60\x50\xF0\x61\xF2"
-			 "\x1C\x78\x7F\xC1\x24\x34\xAF\x58"
-			 "\xBF\x2C\x59\xCA\x90\x77\xF3\xB0"
-			 "\x5B\x4A\xDF\x89\xCE\x2C\x2F\xFC"
-			 "\x67\xF0\xE3\x45\xE8\xB3\xB3\x75"
-			 "\xA0\x95\x71\xA1\x29\x39\x94\xCA"
-			 "\x45\x2F\xBD\xCB\x10\xB6\xBE\x9F"
-			 "\x8E\xF9\xB2\x01\x0A\x5A\x0A\xB7"
-			 "\x6B\x9D\x70\x8E\x4B\xD6\x2F\xCD"
-			 "\x2E\x40\x48\x75\xE9\xE2\x21\x45"
-			 "\x0B\xC9\xB6\xB5\x66\xBC\x9A\x59"
-			 "\x5A",
-		.len	= 129,
-	}, { /* large test vector generated using Crypto++ */
-		.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,
-		.iv =	"\x00\x00\x00\x00\x00\x00\x00\x00"
-			"\x00\x00\x00\x00\x00\x00\x00\x00",
-		.ptext =
-			"\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\x03\x06\x09\x0c\x0f\x12\x15"
-			"\x18\x1b\x1e\x21\x24\x27\x2a\x2d"
-			"\x30\x33\x36\x39\x3c\x3f\x42\x45"
-			"\x48\x4b\x4e\x51\x54\x57\x5a\x5d"
-			"\x60\x63\x66\x69\x6c\x6f\x72\x75"
-			"\x78\x7b\x7e\x81\x84\x87\x8a\x8d"
-			"\x90\x93\x96\x99\x9c\x9f\xa2\xa5"
-			"\xa8\xab\xae\xb1\xb4\xb7\xba\xbd"
-			"\xc0\xc3\xc6\xc9\xcc\xcf\xd2\xd5"
-			"\xd8\xdb\xde\xe1\xe4\xe7\xea\xed"
-			"\xf0\xf3\xf6\xf9\xfc\xff\x02\x05"
-			"\x08\x0b\x0e\x11\x14\x17\x1a\x1d"
-			"\x20\x23\x26\x29\x2c\x2f\x32\x35"
-			"\x38\x3b\x3e\x41\x44\x47\x4a\x4d"
-			"\x50\x53\x56\x59\x5c\x5f\x62\x65"
-			"\x68\x6b\x6e\x71\x74\x77\x7a\x7d"
-			"\x80\x83\x86\x89\x8c\x8f\x92\x95"
-			"\x98\x9b\x9e\xa1\xa4\xa7\xaa\xad"
-			"\xb0\xb3\xb6\xb9\xbc\xbf\xc2\xc5"
-			"\xc8\xcb\xce\xd1\xd4\xd7\xda\xdd"
-			"\xe0\xe3\xe6\xe9\xec\xef\xf2\xf5"
-			"\xf8\xfb\xfe\x01\x04\x07\x0a\x0d"
-			"\x10\x13\x16\x19\x1c\x1f\x22\x25"
-			"\x28\x2b\x2e\x31\x34\x37\x3a\x3d"
-			"\x40\x43\x46\x49\x4c\x4f\x52\x55"
-			"\x58\x5b\x5e\x61\x64\x67\x6a\x6d"
-			"\x70\x73\x76\x79\x7c\x7f\x82\x85"
-			"\x88\x8b\x8e\x91\x94\x97\x9a\x9d"
-			"\xa0\xa3\xa6\xa9\xac\xaf\xb2\xb5"
-			"\xb8\xbb\xbe\xc1\xc4\xc7\xca\xcd"
-			"\xd0\xd3\xd6\xd9\xdc\xdf\xe2\xe5"
-			"\xe8\xeb\xee\xf1\xf4\xf7\xfa\xfd"
-			"\x00\x05\x0a\x0f\x14\x19\x1e\x23"
-			"\x28\x2d\x32\x37\x3c\x41\x46\x4b"
-			"\x50\x55\x5a\x5f\x64\x69\x6e\x73"
-			"\x78\x7d\x82\x87\x8c\x91\x96\x9b"
-			"\xa0\xa5\xaa\xaf\xb4\xb9\xbe\xc3"
-			"\xc8\xcd\xd2\xd7\xdc\xe1\xe6\xeb"
-			"\xf0\xf5\xfa\xff\x04\x09\x0e\x13"
-			"\x18\x1d\x22\x27\x2c\x31\x36\x3b"
-			"\x40\x45\x4a\x4f\x54\x59\x5e\x63"
-			"\x68\x6d\x72\x77\x7c\x81\x86\x8b"
-			"\x90\x95\x9a\x9f\xa4\xa9\xae\xb3"
-			"\xb8\xbd\xc2\xc7\xcc\xd1\xd6\xdb"
-			"\xe0\xe5\xea\xef\xf4\xf9\xfe\x03"
-			"\x08\x0d\x12\x17\x1c\x21\x26\x2b"
-			"\x30\x35\x3a\x3f\x44\x49\x4e\x53"
-			"\x58\x5d\x62\x67\x6c\x71\x76\x7b"
-			"\x80\x85\x8a\x8f\x94\x99\x9e\xa3"
-			"\xa8\xad\xb2\xb7\xbc\xc1\xc6\xcb"
-			"\xd0\xd5\xda\xdf\xe4\xe9\xee\xf3"
-			"\xf8\xfd\x02\x07\x0c\x11\x16\x1b"
-			"\x20\x25\x2a\x2f\x34\x39\x3e\x43"
-			"\x48\x4d\x52\x57\x5c\x61\x66\x6b"
-			"\x70\x75\x7a\x7f\x84\x89\x8e\x93"
-			"\x98\x9d\xa2\xa7\xac\xb1\xb6\xbb"
-			"\xc0\xc5\xca\xcf\xd4\xd9\xde\xe3"
-			"\xe8\xed\xf2\xf7\xfc\x01\x06\x0b"
-			"\x10\x15\x1a\x1f\x24\x29\x2e\x33"
-			"\x38\x3d\x42\x47\x4c\x51\x56\x5b"
-			"\x60\x65\x6a\x6f\x74\x79\x7e\x83"
-			"\x88\x8d\x92\x97\x9c\xa1\xa6\xab"
-			"\xb0\xb5\xba\xbf\xc4\xc9\xce\xd3"
-			"\xd8\xdd\xe2\xe7\xec\xf1\xf6\xfb"
-			"\x00\x07\x0e\x15\x1c\x23\x2a\x31"
-			"\x38\x3f\x46\x4d\x54\x5b\x62\x69"
-			"\x70\x77\x7e\x85\x8c\x93\x9a\xa1"
-			"\xa8\xaf\xb6\xbd\xc4\xcb\xd2\xd9"
-			"\xe0\xe7\xee\xf5\xfc\x03\x0a\x11"
-			"\x18\x1f\x26\x2d\x34\x3b\x42\x49"
-			"\x50\x57\x5e\x65\x6c\x73\x7a\x81"
-			"\x88\x8f\x96\x9d\xa4\xab\xb2\xb9"
-			"\xc0\xc7\xce\xd5\xdc\xe3\xea\xf1"
-			"\xf8\xff\x06\x0d\x14\x1b\x22\x29"
-			"\x30\x37\x3e\x45\x4c\x53\x5a\x61"
-			"\x68\x6f\x76\x7d\x84\x8b\x92\x99"
-			"\xa0\xa7\xae\xb5\xbc\xc3\xca\xd1"
-			"\xd8\xdf\xe6\xed\xf4\xfb\x02\x09"
-			"\x10\x17\x1e\x25\x2c\x33\x3a\x41"
-			"\x48\x4f\x56\x5d\x64\x6b\x72\x79"
-			"\x80\x87\x8e\x95\x9c\xa3\xaa\xb1"
-			"\xb8\xbf\xc6\xcd\xd4\xdb\xe2\xe9"
-			"\xf0\xf7\xfe\x05\x0c\x13\x1a\x21"
-			"\x28\x2f\x36\x3d\x44\x4b\x52\x59"
-			"\x60\x67\x6e\x75\x7c\x83\x8a\x91"
-			"\x98\x9f\xa6\xad\xb4\xbb\xc2\xc9"
-			"\xd0\xd7\xde\xe5\xec\xf3\xfa\x01"
-			"\x08\x0f\x16\x1d\x24\x2b\x32\x39"
-			"\x40\x47\x4e\x55\x5c\x63\x6a\x71"
-			"\x78\x7f\x86\x8d\x94\x9b\xa2\xa9"
-			"\xb0\xb7\xbe\xc5\xcc\xd3\xda\xe1"
-			"\xe8\xef\xf6\xfd\x04\x0b\x12\x19"
-			"\x20\x27\x2e\x35\x3c\x43\x4a\x51"
-			"\x58\x5f\x66\x6d\x74\x7b\x82\x89"
-			"\x90\x97\x9e\xa5\xac\xb3\xba\xc1"
-			"\xc8\xcf\xd6\xdd\xe4\xeb\xf2\xf9"
-			"\x00\x09\x12\x1b\x24\x2d\x36\x3f"
-			"\x48\x51\x5a\x63\x6c\x75\x7e\x87"
-			"\x90\x99\xa2\xab\xb4\xbd\xc6\xcf"
-			"\xd8\xe1\xea\xf3\xfc\x05\x0e\x17"
-			"\x20\x29\x32\x3b\x44\x4d\x56\x5f"
-			"\x68\x71\x7a\x83\x8c\x95\x9e\xa7"
-			"\xb0\xb9\xc2\xcb\xd4\xdd\xe6\xef"
-			"\xf8\x01\x0a\x13\x1c\x25\x2e\x37"
-			"\x40\x49\x52\x5b\x64\x6d\x76\x7f"
-			"\x88\x91\x9a\xa3\xac\xb5\xbe\xc7"
-			"\xd0\xd9\xe2\xeb\xf4\xfd\x06\x0f"
-			"\x18\x21\x2a\x33\x3c\x45\x4e\x57"
-			"\x60\x69\x72\x7b\x84\x8d\x96\x9f"
-			"\xa8\xb1\xba\xc3\xcc\xd5\xde\xe7"
-			"\xf0\xf9\x02\x0b\x14\x1d\x26\x2f"
-			"\x38\x41\x4a\x53\x5c\x65\x6e\x77"
-			"\x80\x89\x92\x9b\xa4\xad\xb6\xbf"
-			"\xc8\xd1\xda\xe3\xec\xf5\xfe\x07"
-			"\x10\x19\x22\x2b\x34\x3d\x46\x4f"
-			"\x58\x61\x6a\x73\x7c\x85\x8e\x97"
-			"\xa0\xa9\xb2\xbb\xc4\xcd\xd6\xdf"
-			"\xe8\xf1\xfa\x03\x0c\x15\x1e\x27"
-			"\x30\x39\x42\x4b\x54\x5d\x66\x6f"
-			"\x78\x81\x8a\x93\x9c\xa5\xae\xb7"
-			"\xc0\xc9\xd2\xdb\xe4\xed\xf6\xff"
-			"\x08\x11\x1a\x23\x2c\x35\x3e\x47"
-			"\x50\x59\x62\x6b\x74\x7d\x86\x8f"
-			"\x98\xa1\xaa\xb3\xbc\xc5\xce\xd7"
-			"\xe0\xe9\xf2\xfb\x04\x0d\x16\x1f"
-			"\x28\x31\x3a\x43\x4c\x55\x5e\x67"
-			"\x70\x79\x82\x8b\x94\x9d\xa6\xaf"
-			"\xb8\xc1\xca\xd3\xdc\xe5\xee\xf7"
-			"\x00\x0b\x16\x21\x2c\x37\x42\x4d"
-			"\x58\x63\x6e\x79\x84\x8f\x9a\xa5"
-			"\xb0\xbb\xc6\xd1\xdc\xe7\xf2\xfd"
-			"\x08\x13\x1e\x29\x34\x3f\x4a\x55"
-			"\x60\x6b\x76\x81\x8c\x97\xa2\xad"
-			"\xb8\xc3\xce\xd9\xe4\xef\xfa\x05"
-			"\x10\x1b\x26\x31\x3c\x47\x52\x5d"
-			"\x68\x73\x7e\x89\x94\x9f\xaa\xb5"
-			"\xc0\xcb\xd6\xe1\xec\xf7\x02\x0d"
-			"\x18\x23\x2e\x39\x44\x4f\x5a\x65"
-			"\x70\x7b\x86\x91\x9c\xa7\xb2\xbd"
-			"\xc8\xd3\xde\xe9\xf4\xff\x0a\x15"
-			"\x20\x2b\x36\x41\x4c\x57\x62\x6d"
-			"\x78\x83\x8e\x99\xa4\xaf\xba\xc5"
-			"\xd0\xdb\xe6\xf1\xfc\x07\x12\x1d"
-			"\x28\x33\x3e\x49\x54\x5f\x6a\x75"
-			"\x80\x8b\x96\xa1\xac\xb7\xc2\xcd"
-			"\xd8\xe3\xee\xf9\x04\x0f\x1a\x25"
-			"\x30\x3b\x46\x51\x5c\x67\x72\x7d"
-			"\x88\x93\x9e\xa9\xb4\xbf\xca\xd5"
-			"\xe0\xeb\xf6\x01\x0c\x17\x22\x2d"
-			"\x38\x43\x4e\x59\x64\x6f\x7a\x85"
-			"\x90\x9b\xa6\xb1\xbc\xc7\xd2\xdd"
-			"\xe8\xf3\xfe\x09\x14\x1f\x2a\x35"
-			"\x40\x4b\x56\x61\x6c\x77\x82\x8d"
-			"\x98\xa3\xae\xb9\xc4\xcf\xda\xe5"
-			"\xf0\xfb\x06\x11\x1c\x27\x32\x3d"
-			"\x48\x53\x5e\x69\x74\x7f\x8a\x95"
-			"\xa0\xab\xb6\xc1\xcc\xd7\xe2\xed"
-			"\xf8\x03\x0e\x19\x24\x2f\x3a\x45"
-			"\x50\x5b\x66\x71\x7c\x87\x92\x9d"
-			"\xa8\xb3\xbe\xc9\xd4\xdf\xea\xf5"
-			"\x00\x0d\x1a\x27\x34\x41\x4e\x5b"
-			"\x68\x75\x82\x8f\x9c\xa9\xb6\xc3"
-			"\xd0\xdd\xea\xf7\x04\x11\x1e\x2b"
-			"\x38\x45\x52\x5f\x6c\x79\x86\x93"
-			"\xa0\xad\xba\xc7\xd4\xe1\xee\xfb"
-			"\x08\x15\x22\x2f\x3c\x49\x56\x63"
-			"\x70\x7d\x8a\x97\xa4\xb1\xbe\xcb"
-			"\xd8\xe5\xf2\xff\x0c\x19\x26\x33"
-			"\x40\x4d\x5a\x67\x74\x81\x8e\x9b"
-			"\xa8\xb5\xc2\xcf\xdc\xe9\xf6\x03"
-			"\x10\x1d\x2a\x37\x44\x51\x5e\x6b"
-			"\x78\x85\x92\x9f\xac\xb9\xc6\xd3"
-			"\xe0\xed\xfa\x07\x14\x21\x2e\x3b"
-			"\x48\x55\x62\x6f\x7c\x89\x96\xa3"
-			"\xb0\xbd\xca\xd7\xe4\xf1\xfe\x0b"
-			"\x18\x25\x32\x3f\x4c\x59\x66\x73"
-			"\x80\x8d\x9a\xa7\xb4\xc1\xce\xdb"
-			"\xe8\xf5\x02\x0f\x1c\x29\x36\x43"
-			"\x50\x5d\x6a\x77\x84\x91\x9e\xab"
-			"\xb8\xc5\xd2\xdf\xec\xf9\x06\x13"
-			"\x20\x2d\x3a\x47\x54\x61\x6e\x7b"
-			"\x88\x95\xa2\xaf\xbc\xc9\xd6\xe3"
-			"\xf0\xfd\x0a\x17\x24\x31\x3e\x4b"
-			"\x58\x65\x72\x7f\x8c\x99\xa6\xb3"
-			"\xc0\xcd\xda\xe7\xf4\x01\x0e\x1b"
-			"\x28\x35\x42\x4f\x5c\x69\x76\x83"
-			"\x90\x9d\xaa\xb7\xc4\xd1\xde\xeb"
-			"\xf8\x05\x12\x1f\x2c\x39\x46\x53"
-			"\x60\x6d\x7a\x87\x94\xa1\xae\xbb"
-			"\xc8\xd5\xe2\xef\xfc\x09\x16\x23"
-			"\x30\x3d\x4a\x57\x64\x71\x7e\x8b"
-			"\x98\xa5\xb2\xbf\xcc\xd9\xe6\xf3"
-			"\x00\x0f\x1e\x2d\x3c\x4b\x5a\x69"
-			"\x78\x87\x96\xa5\xb4\xc3\xd2\xe1"
-			"\xf0\xff\x0e\x1d\x2c\x3b\x4a\x59"
-			"\x68\x77\x86\x95\xa4\xb3\xc2\xd1"
-			"\xe0\xef\xfe\x0d\x1c\x2b\x3a\x49"
-			"\x58\x67\x76\x85\x94\xa3\xb2\xc1"
-			"\xd0\xdf\xee\xfd\x0c\x1b\x2a\x39"
-			"\x48\x57\x66\x75\x84\x93\xa2\xb1"
-			"\xc0\xcf\xde\xed\xfc\x0b\x1a\x29"
-			"\x38\x47\x56\x65\x74\x83\x92\xa1"
-			"\xb0\xbf\xce\xdd\xec\xfb\x0a\x19"
-			"\x28\x37\x46\x55\x64\x73\x82\x91"
-			"\xa0\xaf\xbe\xcd\xdc\xeb\xfa\x09"
-			"\x18\x27\x36\x45\x54\x63\x72\x81"
-			"\x90\x9f\xae\xbd\xcc\xdb\xea\xf9"
-			"\x08\x17\x26\x35\x44\x53\x62\x71"
-			"\x80\x8f\x9e\xad\xbc\xcb\xda\xe9"
-			"\xf8\x07\x16\x25\x34\x43\x52\x61"
-			"\x70\x7f\x8e\x9d\xac\xbb\xca\xd9"
-			"\xe8\xf7\x06\x15\x24\x33\x42\x51"
-			"\x60\x6f\x7e\x8d\x9c\xab\xba\xc9"
-			"\xd8\xe7\xf6\x05\x14\x23\x32\x41"
-			"\x50\x5f\x6e\x7d\x8c\x9b\xaa\xb9"
-			"\xc8\xd7\xe6\xf5\x04\x13\x22\x31"
-			"\x40\x4f\x5e\x6d\x7c\x8b\x9a\xa9"
-			"\xb8\xc7\xd6\xe5\xf4\x03\x12\x21"
-			"\x30\x3f\x4e\x5d\x6c\x7b\x8a\x99"
-			"\xa8\xb7\xc6\xd5\xe4\xf3\x02\x11"
-			"\x20\x2f\x3e\x4d\x5c\x6b\x7a\x89"
-			"\x98\xa7\xb6\xc5\xd4\xe3\xf2\x01"
-			"\x10\x1f\x2e\x3d\x4c\x5b\x6a\x79"
-			"\x88\x97\xa6\xb5\xc4\xd3\xe2\xf1"
-			"\x00\x11\x22\x33\x44\x55\x66\x77"
-			"\x88\x99\xaa\xbb\xcc\xdd\xee\xff"
-			"\x10\x21\x32\x43\x54\x65\x76\x87"
-			"\x98\xa9\xba\xcb\xdc\xed\xfe\x0f"
-			"\x20\x31\x42\x53\x64\x75\x86\x97"
-			"\xa8\xb9\xca\xdb\xec\xfd\x0e\x1f"
-			"\x30\x41\x52\x63\x74\x85\x96\xa7"
-			"\xb8\xc9\xda\xeb\xfc\x0d\x1e\x2f"
-			"\x40\x51\x62\x73\x84\x95\xa6\xb7"
-			"\xc8\xd9\xea\xfb\x0c\x1d\x2e\x3f"
-			"\x50\x61\x72\x83\x94\xa5\xb6\xc7"
-			"\xd8\xe9\xfa\x0b\x1c\x2d\x3e\x4f"
-			"\x60\x71\x82\x93\xa4\xb5\xc6\xd7"
-			"\xe8\xf9\x0a\x1b\x2c\x3d\x4e\x5f"
-			"\x70\x81\x92\xa3\xb4\xc5\xd6\xe7"
-			"\xf8\x09\x1a\x2b\x3c\x4d\x5e\x6f"
-			"\x80\x91\xa2\xb3\xc4\xd5\xe6\xf7"
-			"\x08\x19\x2a\x3b\x4c\x5d\x6e\x7f"
-			"\x90\xa1\xb2\xc3\xd4\xe5\xf6\x07"
-			"\x18\x29\x3a\x4b\x5c\x6d\x7e\x8f"
-			"\xa0\xb1\xc2\xd3\xe4\xf5\x06\x17"
-			"\x28\x39\x4a\x5b\x6c\x7d\x8e\x9f"
-			"\xb0\xc1\xd2\xe3\xf4\x05\x16\x27"
-			"\x38\x49\x5a\x6b\x7c\x8d\x9e\xaf"
-			"\xc0\xd1\xe2\xf3\x04\x15\x26\x37"
-			"\x48\x59\x6a\x7b\x8c\x9d\xae\xbf"
-			"\xd0\xe1\xf2\x03\x14\x25\x36\x47"
-			"\x58\x69\x7a\x8b\x9c\xad\xbe\xcf"
-			"\xe0\xf1\x02\x13\x24\x35\x46\x57"
-			"\x68\x79\x8a\x9b\xac\xbd\xce\xdf"
-			"\xf0\x01\x12\x23\x34\x45\x56\x67"
-			"\x78\x89\x9a\xab\xbc\xcd\xde\xef"
-			"\x00\x13\x26\x39\x4c\x5f\x72\x85"
-			"\x98\xab\xbe\xd1\xe4\xf7\x0a\x1d"
-			"\x30\x43\x56\x69\x7c\x8f\xa2\xb5"
-			"\xc8\xdb\xee\x01\x14\x27\x3a\x4d"
-			"\x60\x73\x86\x99\xac\xbf\xd2\xe5"
-			"\xf8\x0b\x1e\x31\x44\x57\x6a\x7d"
-			"\x90\xa3\xb6\xc9\xdc\xef\x02\x15"
-			"\x28\x3b\x4e\x61\x74\x87\x9a\xad"
-			"\xc0\xd3\xe6\xf9\x0c\x1f\x32\x45"
-			"\x58\x6b\x7e\x91\xa4\xb7\xca\xdd"
-			"\xf0\x03\x16\x29\x3c\x4f\x62\x75"
-			"\x88\x9b\xae\xc1\xd4\xe7\xfa\x0d"
-			"\x20\x33\x46\x59\x6c\x7f\x92\xa5"
-			"\xb8\xcb\xde\xf1\x04\x17\x2a\x3d"
-			"\x50\x63\x76\x89\x9c\xaf\xc2\xd5"
-			"\xe8\xfb\x0e\x21\x34\x47\x5a\x6d"
-			"\x80\x93\xa6\xb9\xcc\xdf\xf2\x05"
-			"\x18\x2b\x3e\x51\x64\x77\x8a\x9d"
-			"\xb0\xc3\xd6\xe9\xfc\x0f\x22\x35"
-			"\x48\x5b\x6e\x81\x94\xa7\xba\xcd"
-			"\xe0\xf3\x06\x19\x2c\x3f\x52\x65"
-			"\x78\x8b\x9e\xb1\xc4\xd7\xea\xfd"
-			"\x10\x23\x36\x49\x5c\x6f\x82\x95"
-			"\xa8\xbb\xce\xe1\xf4\x07\x1a\x2d"
-			"\x40\x53\x66\x79\x8c\x9f\xb2\xc5"
-			"\xd8\xeb\xfe\x11\x24\x37\x4a\x5d"
-			"\x70\x83\x96\xa9\xbc\xcf\xe2\xf5"
-			"\x08\x1b\x2e\x41\x54\x67\x7a\x8d"
-			"\xa0\xb3\xc6\xd9\xec\xff\x12\x25"
-			"\x38\x4b\x5e\x71\x84\x97\xaa\xbd"
-			"\xd0\xe3\xf6\x09\x1c\x2f\x42\x55"
-			"\x68\x7b\x8e\xa1\xb4\xc7\xda\xed"
-			"\x00\x15\x2a\x3f\x54\x69\x7e\x93"
-			"\xa8\xbd\xd2\xe7\xfc\x11\x26\x3b"
-			"\x50\x65\x7a\x8f\xa4\xb9\xce\xe3"
-			"\xf8\x0d\x22\x37\x4c\x61\x76\x8b"
-			"\xa0\xb5\xca\xdf\xf4\x09\x1e\x33"
-			"\x48\x5d\x72\x87\x9c\xb1\xc6\xdb"
-			"\xf0\x05\x1a\x2f\x44\x59\x6e\x83"
-			"\x98\xad\xc2\xd7\xec\x01\x16\x2b"
-			"\x40\x55\x6a\x7f\x94\xa9\xbe\xd3"
-			"\xe8\xfd\x12\x27\x3c\x51\x66\x7b"
-			"\x90\xa5\xba\xcf\xe4\xf9\x0e\x23"
-			"\x38\x4d\x62\x77\x8c\xa1\xb6\xcb"
-			"\xe0\xf5\x0a\x1f\x34\x49\x5e\x73"
-			"\x88\x9d\xb2\xc7\xdc\xf1\x06\x1b"
-			"\x30\x45\x5a\x6f\x84\x99\xae\xc3"
-			"\xd8\xed\x02\x17\x2c\x41\x56\x6b"
-			"\x80\x95\xaa\xbf\xd4\xe9\xfe\x13"
-			"\x28\x3d\x52\x67\x7c\x91\xa6\xbb"
-			"\xd0\xe5\xfa\x0f\x24\x39\x4e\x63"
-			"\x78\x8d\xa2\xb7\xcc\xe1\xf6\x0b"
-			"\x20\x35\x4a\x5f\x74\x89\x9e\xb3"
-			"\xc8\xdd\xf2\x07\x1c\x31\x46\x5b"
-			"\x70\x85\x9a\xaf\xc4\xd9\xee\x03"
-			"\x18\x2d\x42\x57\x6c\x81\x96\xab"
-			"\xc0\xd5\xea\xff\x14\x29\x3e\x53"
-			"\x68\x7d\x92\xa7\xbc\xd1\xe6\xfb"
-			"\x10\x25\x3a\x4f\x64\x79\x8e\xa3"
-			"\xb8\xcd\xe2\xf7\x0c\x21\x36\x4b"
-			"\x60\x75\x8a\x9f\xb4\xc9\xde\xf3"
-			"\x08\x1d\x32\x47\x5c\x71\x86\x9b"
-			"\xb0\xc5\xda\xef\x04\x19\x2e\x43"
-			"\x58\x6d\x82\x97\xac\xc1\xd6\xeb"
-			"\x00\x17\x2e\x45\x5c\x73\x8a\xa1"
-			"\xb8\xcf\xe6\xfd\x14\x2b\x42\x59"
-			"\x70\x87\x9e\xb5\xcc\xe3\xfa\x11"
-			"\x28\x3f\x56\x6d\x84\x9b\xb2\xc9"
-			"\xe0\xf7\x0e\x25\x3c\x53\x6a\x81"
-			"\x98\xaf\xc6\xdd\xf4\x0b\x22\x39"
-			"\x50\x67\x7e\x95\xac\xc3\xda\xf1"
-			"\x08\x1f\x36\x4d\x64\x7b\x92\xa9"
-			"\xc0\xd7\xee\x05\x1c\x33\x4a\x61"
-			"\x78\x8f\xa6\xbd\xd4\xeb\x02\x19"
-			"\x30\x47\x5e\x75\x8c\xa3\xba\xd1"
-			"\xe8\xff\x16\x2d\x44\x5b\x72\x89"
-			"\xa0\xb7\xce\xe5\xfc\x13\x2a\x41"
-			"\x58\x6f\x86\x9d\xb4\xcb\xe2\xf9"
-			"\x10\x27\x3e\x55\x6c\x83\x9a\xb1"
-			"\xc8\xdf\xf6\x0d\x24\x3b\x52\x69"
-			"\x80\x97\xae\xc5\xdc\xf3\x0a\x21"
-			"\x38\x4f\x66\x7d\x94\xab\xc2\xd9"
-			"\xf0\x07\x1e\x35\x4c\x63\x7a\x91"
-			"\xa8\xbf\xd6\xed\x04\x1b\x32\x49"
-			"\x60\x77\x8e\xa5\xbc\xd3\xea\x01"
-			"\x18\x2f\x46\x5d\x74\x8b\xa2\xb9"
-			"\xd0\xe7\xfe\x15\x2c\x43\x5a\x71"
-			"\x88\x9f\xb6\xcd\xe4\xfb\x12\x29"
-			"\x40\x57\x6e\x85\x9c\xb3\xca\xe1"
-			"\xf8\x0f\x26\x3d\x54\x6b\x82\x99"
-			"\xb0\xc7\xde\xf5\x0c\x23\x3a\x51"
-			"\x68\x7f\x96\xad\xc4\xdb\xf2\x09"
-			"\x20\x37\x4e\x65\x7c\x93\xaa\xc1"
-			"\xd8\xef\x06\x1d\x34\x4b\x62\x79"
-			"\x90\xa7\xbe\xd5\xec\x03\x1a\x31"
-			"\x48\x5f\x76\x8d\xa4\xbb\xd2\xe9"
-			"\x00\x19\x32\x4b\x64\x7d\x96\xaf"
-			"\xc8\xe1\xfa\x13\x2c\x45\x5e\x77"
-			"\x90\xa9\xc2\xdb\xf4\x0d\x26\x3f"
-			"\x58\x71\x8a\xa3\xbc\xd5\xee\x07"
-			"\x20\x39\x52\x6b\x84\x9d\xb6\xcf"
-			"\xe8\x01\x1a\x33\x4c\x65\x7e\x97"
-			"\xb0\xc9\xe2\xfb\x14\x2d\x46\x5f"
-			"\x78\x91\xaa\xc3\xdc\xf5\x0e\x27"
-			"\x40\x59\x72\x8b\xa4\xbd\xd6\xef"
-			"\x08\x21\x3a\x53\x6c\x85\x9e\xb7"
-			"\xd0\xe9\x02\x1b\x34\x4d\x66\x7f"
-			"\x98\xb1\xca\xe3\xfc\x15\x2e\x47"
-			"\x60\x79\x92\xab\xc4\xdd\xf6\x0f"
-			"\x28\x41\x5a\x73\x8c\xa5\xbe\xd7"
-			"\xf0\x09\x22\x3b\x54\x6d\x86\x9f"
-			"\xb8\xd1\xea\x03\x1c\x35\x4e\x67"
-			"\x80\x99\xb2\xcb\xe4\xfd\x16\x2f"
-			"\x48\x61\x7a\x93\xac\xc5\xde\xf7"
-			"\x10\x29\x42\x5b\x74\x8d\xa6\xbf"
-			"\xd8\xf1\x0a\x23\x3c\x55\x6e\x87"
-			"\xa0\xb9\xd2\xeb\x04\x1d\x36\x4f"
-			"\x68\x81\x9a\xb3\xcc\xe5\xfe\x17"
-			"\x30\x49\x62\x7b\x94\xad\xc6\xdf"
-			"\xf8\x11\x2a\x43\x5c\x75\x8e\xa7"
-			"\xc0\xd9\xf2\x0b\x24\x3d\x56\x6f"
-			"\x88\xa1\xba\xd3\xec\x05\x1e\x37"
-			"\x50\x69\x82\x9b\xb4\xcd\xe6\xff"
-			"\x18\x31\x4a\x63\x7c\x95\xae\xc7"
-			"\xe0\xf9\x12\x2b\x44\x5d\x76\x8f"
-			"\xa8\xc1\xda\xf3\x0c\x25\x3e\x57"
-			"\x70\x89\xa2\xbb\xd4\xed\x06\x1f"
-			"\x38\x51\x6a\x83\x9c\xb5\xce\xe7"
-			"\x00\x1b\x36\x51\x6c\x87\xa2\xbd"
-			"\xd8\xf3\x0e\x29\x44\x5f\x7a\x95"
-			"\xb0\xcb\xe6\x01\x1c\x37\x52\x6d"
-			"\x88\xa3\xbe\xd9\xf4\x0f\x2a\x45"
-			"\x60\x7b\x96\xb1\xcc\xe7\x02\x1d"
-			"\x38\x53\x6e\x89\xa4\xbf\xda\xf5"
-			"\x10\x2b\x46\x61\x7c\x97\xb2\xcd"
-			"\xe8\x03\x1e\x39\x54\x6f\x8a\xa5"
-			"\xc0\xdb\xf6\x11\x2c\x47\x62\x7d"
-			"\x98\xb3\xce\xe9\x04\x1f\x3a\x55"
-			"\x70\x8b\xa6\xc1\xdc\xf7\x12\x2d"
-			"\x48\x63\x7e\x99\xb4\xcf\xea\x05"
-			"\x20\x3b\x56\x71\x8c\xa7\xc2\xdd"
-			"\xf8\x13\x2e\x49\x64\x7f\x9a\xb5"
-			"\xd0\xeb\x06\x21\x3c\x57\x72\x8d"
-			"\xa8\xc3\xde\xf9\x14\x2f\x4a\x65"
-			"\x80\x9b\xb6\xd1\xec\x07\x22\x3d"
-			"\x58\x73\x8e\xa9\xc4\xdf\xfa\x15"
-			"\x30\x4b\x66\x81\x9c\xb7\xd2\xed"
-			"\x08\x23\x3e\x59\x74\x8f\xaa\xc5"
-			"\xe0\xfb\x16\x31\x4c\x67\x82\x9d"
-			"\xb8\xd3\xee\x09\x24\x3f\x5a\x75"
-			"\x90\xab\xc6\xe1\xfc\x17\x32\x4d"
-			"\x68\x83\x9e\xb9\xd4\xef\x0a\x25"
-			"\x40\x5b\x76\x91\xac\xc7\xe2\xfd"
-			"\x18\x33\x4e\x69\x84\x9f\xba\xd5"
-			"\xf0\x0b\x26\x41\x5c\x77\x92\xad"
-			"\xc8\xe3\xfe\x19\x34\x4f\x6a\x85"
-			"\xa0\xbb\xd6\xf1\x0c\x27\x42\x5d"
-			"\x78\x93\xae\xc9\xe4\xff\x1a\x35"
-			"\x50\x6b\x86\xa1\xbc\xd7\xf2\x0d"
-			"\x28\x43\x5e\x79\x94\xaf\xca\xe5"
-			"\x00\x1d\x3a\x57\x74\x91\xae\xcb"
-			"\xe8\x05\x22\x3f\x5c\x79\x96\xb3"
-			"\xd0\xed\x0a\x27\x44\x61\x7e\x9b"
-			"\xb8\xd5\xf2\x0f\x2c\x49\x66\x83"
-			"\xa0\xbd\xda\xf7\x14\x31\x4e\x6b"
-			"\x88\xa5\xc2\xdf\xfc\x19\x36\x53"
-			"\x70\x8d\xaa\xc7\xe4\x01\x1e\x3b"
-			"\x58\x75\x92\xaf\xcc\xe9\x06\x23"
-			"\x40\x5d\x7a\x97\xb4\xd1\xee\x0b"
-			"\x28\x45\x62\x7f\x9c\xb9\xd6\xf3"
-			"\x10\x2d\x4a\x67\x84\xa1\xbe\xdb"
-			"\xf8\x15\x32\x4f\x6c\x89\xa6\xc3"
-			"\xe0\xfd\x1a\x37\x54\x71\x8e\xab"
-			"\xc8\xe5\x02\x1f\x3c\x59\x76\x93"
-			"\xb0\xcd\xea\x07\x24\x41\x5e\x7b"
-			"\x98\xb5\xd2\xef\x0c\x29\x46\x63"
-			"\x80\x9d\xba\xd7\xf4\x11\x2e\x4b"
-			"\x68\x85\xa2\xbf\xdc\xf9\x16\x33"
-			"\x50\x6d\x8a\xa7\xc4\xe1\xfe\x1b"
-			"\x38\x55\x72\x8f\xac\xc9\xe6\x03"
-			"\x20\x3d\x5a\x77\x94\xb1\xce\xeb"
-			"\x08\x25\x42\x5f\x7c\x99\xb6\xd3"
-			"\xf0\x0d\x2a\x47\x64\x81\x9e\xbb"
-			"\xd8\xf5\x12\x2f\x4c\x69\x86\xa3"
-			"\xc0\xdd\xfa\x17\x34\x51\x6e\x8b"
-			"\xa8\xc5\xe2\xff\x1c\x39\x56\x73"
-			"\x90\xad\xca\xe7\x04\x21\x3e\x5b"
-			"\x78\x95\xb2\xcf\xec\x09\x26\x43"
-			"\x60\x7d\x9a\xb7\xd4\xf1\x0e\x2b"
-			"\x48\x65\x82\x9f\xbc\xd9\xf6\x13"
-			"\x30\x4d\x6a\x87\xa4\xc1\xde\xfb"
-			"\x18\x35\x52\x6f\x8c\xa9\xc6\xe3"
-			"\x00\x1f\x3e\x5d\x7c\x9b\xba\xd9"
-			"\xf8\x17\x36\x55\x74\x93\xb2\xd1"
-			"\xf0\x0f\x2e\x4d\x6c\x8b\xaa\xc9"
-			"\xe8\x07\x26\x45\x64\x83\xa2\xc1"
-			"\xe0\xff\x1e\x3d\x5c\x7b\x9a\xb9"
-			"\xd8\xf7\x16\x35\x54\x73\x92\xb1"
-			"\xd0\xef\x0e\x2d\x4c\x6b\x8a\xa9"
-			"\xc8\xe7\x06\x25\x44\x63\x82\xa1"
-			"\xc0\xdf\xfe\x1d\x3c\x5b\x7a\x99"
-			"\xb8\xd7\xf6\x15\x34\x53\x72\x91"
-			"\xb0\xcf\xee\x0d\x2c\x4b\x6a\x89"
-			"\xa8\xc7\xe6\x05\x24\x43\x62\x81"
-			"\xa0\xbf\xde\xfd\x1c\x3b\x5a\x79"
-			"\x98\xb7\xd6\xf5\x14\x33\x52\x71"
-			"\x90\xaf\xce\xed\x0c\x2b\x4a\x69"
-			"\x88\xa7\xc6\xe5\x04\x23\x42\x61"
-			"\x80\x9f\xbe\xdd\xfc\x1b\x3a\x59"
-			"\x78\x97\xb6\xd5\xf4\x13\x32\x51"
-			"\x70\x8f\xae\xcd\xec\x0b\x2a\x49"
-			"\x68\x87\xa6\xc5\xe4\x03\x22\x41"
-			"\x60\x7f\x9e\xbd\xdc\xfb\x1a\x39"
-			"\x58\x77\x96\xb5\xd4\xf3\x12\x31"
-			"\x50\x6f\x8e\xad\xcc\xeb\x0a\x29"
-			"\x48\x67\x86\xa5\xc4\xe3\x02\x21"
-			"\x40\x5f\x7e\x9d\xbc\xdb\xfa\x19"
-			"\x38\x57\x76\x95\xb4\xd3\xf2\x11"
-			"\x30\x4f\x6e\x8d\xac\xcb\xea\x09"
-			"\x28\x47\x66\x85\xa4\xc3\xe2\x01"
-			"\x20\x3f\x5e\x7d\x9c\xbb\xda\xf9"
-			"\x18\x37\x56\x75\x94\xb3\xd2\xf1"
-			"\x10\x2f\x4e\x6d\x8c\xab\xca\xe9"
-			"\x08\x27\x46\x65\x84\xa3\xc2\xe1"
-			"\x00\x21\x42\x63",
-		.ctext =
-			"\xb5\x81\xf5\x64\x18\x73\xe3\xf0"
-			"\x4c\x13\xf2\x77\x18\x60\x65\x5e"
-			"\x29\x01\xce\x98\x55\x53\xf9\x0c"
-			"\x2a\x08\xd5\x09\xb3\x57\x55\x56"
-			"\xc5\xe9\x56\x90\xcb\x6a\xa3\xc0"
-			"\xff\xc4\x79\xb4\xd2\x97\x5d\xc4"
-			"\x43\xd1\xfe\x94\x7b\x88\x06\x5a"
-			"\xb2\x9e\x2c\xfc\x44\x03\xb7\x90"
-			"\xa0\xc1\xba\x6a\x33\xb8\xc7\xb2"
-			"\x9d\xe1\x12\x4f\xc0\x64\xd4\x01"
-			"\xfe\x8c\x7a\x66\xf7\xe6\x5a\x91"
-			"\xbb\xde\x56\x86\xab\x65\x21\x30"
-			"\x00\x84\x65\x24\xa5\x7d\x85\xb4"
-			"\xe3\x17\xed\x3a\xb7\x6f\xb4\x0b"
-			"\x0b\xaf\x15\xae\x5a\x8f\xf2\x0c"
-			"\x2f\x27\xf4\x09\xd8\xd2\x96\xb7"
-			"\x71\xf2\xc5\x99\x4d\x7e\x7f\x75"
-			"\x77\x89\x30\x8b\x59\xdb\xa2\xb2"
-			"\xa0\xf3\x19\x39\x2b\xc5\x7e\x3f"
-			"\x4f\xd9\xd3\x56\x28\x97\x44\xdc"
-			"\xc0\x8b\x77\x24\xd9\x52\xe7\xc5"
-			"\xaf\xf6\x7d\x59\xb2\x44\x05\x1d"
-			"\xb1\xb0\x11\xa5\x0f\xec\x33\xe1"
-			"\x6d\x1b\x4e\x1f\xff\x57\x91\xb4"
-			"\x5b\x9a\x96\xc5\x53\xbc\xae\x20"
-			"\x3c\xbb\x14\xe2\xe8\x22\x33\xc1"
-			"\x5e\x76\x9e\x46\x99\xf6\x2a\x15"
-			"\xc6\x97\x02\xa0\x66\x43\xd1\xa6"
-			"\x31\xa6\x9f\xfb\xf4\xd3\x69\xe5"
-			"\xcd\x76\x95\xb8\x7a\x82\x7f\x21"
-			"\x45\xff\x3f\xce\x55\xf6\x95\x10"
-			"\x08\x77\x10\x43\xc6\xf3\x09\xe5"
-			"\x68\xe7\x3c\xad\x00\x52\x45\x0d"
-			"\xfe\x2d\xc6\xc2\x94\x8c\x12\x1d"
-			"\xe6\x25\xae\x98\x12\x8e\x19\x9c"
-			"\x81\x68\xb1\x11\xf6\x69\xda\xe3"
-			"\x62\x08\x18\x7a\x25\x49\x28\xac"
-			"\xba\x71\x12\x0b\xe4\xa2\xe5\xc7"
-			"\x5d\x8e\xec\x49\x40\x21\xbf\x5a"
-			"\x98\xf3\x02\x68\x55\x03\x7f\x8a"
-			"\xe5\x94\x0c\x32\x5c\x07\x82\x63"
-			"\xaf\x6f\x91\x40\x84\x8e\x52\x25"
-			"\xd0\xb0\x29\x53\x05\xe2\x50\x7a"
-			"\x34\xeb\xc9\x46\x20\xa8\x3d\xde"
-			"\x7f\x16\x5f\x36\xc5\x2e\xdc\xd1"
-			"\x15\x47\xc7\x50\x40\x6d\x91\xc5"
-			"\xe7\x93\x95\x1a\xd3\x57\xbc\x52"
-			"\x33\xee\x14\x19\x22\x52\x89\xa7"
-			"\x4a\x25\x56\x77\x4b\xca\xcf\x0a"
-			"\xe1\xf5\x35\x85\x30\x7e\x59\x4a"
-			"\xbd\x14\x5b\xdf\xe3\x46\xcb\xac"
-			"\x1f\x6c\x96\x0e\xf4\x81\xd1\x99"
-			"\xca\x88\x63\x3d\x02\x58\x6b\xa9"
-			"\xe5\x9f\xb3\x00\xb2\x54\xc6\x74"
-			"\x1c\xbf\x46\xab\x97\xcc\xf8\x54"
-			"\x04\x07\x08\x52\xe6\xc0\xda\x93"
-			"\x74\x7d\x93\x99\x5d\x78\x68\xa6"
-			"\x2e\x6b\xd3\x6a\x69\xcc\x12\x6b"
-			"\xd4\xc7\xa5\xc6\xe7\xf6\x03\x04"
-			"\x5d\xcd\x61\x5e\x17\x40\xdc\xd1"
-			"\x5c\xf5\x08\xdf\x5c\x90\x85\xa4"
-			"\xaf\xf6\x78\xbb\x0d\xf1\xf4\xa4"
-			"\x54\x26\x72\x9e\x61\xfa\x86\xcf"
-			"\xe8\x9e\xa1\xe0\xc7\x48\x23\xae"
-			"\x5a\x90\xae\x75\x0a\x74\x18\x89"
-			"\x05\xb1\x92\xb2\x7f\xd0\x1b\xa6"
-			"\x62\x07\x25\x01\xc7\xc2\x4f\xf9"
-			"\xe8\xfe\x63\x95\x80\x07\xb4\x26"
-			"\xcc\xd1\x26\xb6\xc4\x3f\x9e\xcb"
-			"\x8e\x3b\x2e\x44\x16\xd3\x10\x9a"
-			"\x95\x08\xeb\xc8\xcb\xeb\xbf\x6f"
-			"\x0b\xcd\x1f\xc8\xca\x86\xaa\xec"
-			"\x33\xe6\x69\xf4\x45\x25\x86\x3a"
-			"\x22\x94\x4f\x00\x23\x6a\x44\xc2"
-			"\x49\x97\x33\xab\x36\x14\x0a\x70"
-			"\x24\xc3\xbe\x04\x3b\x79\xa0\xf9"
-			"\xb8\xe7\x76\x29\x22\x83\xd7\xf2"
-			"\x94\xf4\x41\x49\xba\x5f\x7b\x07"
-			"\xb5\xfb\xdb\x03\x1a\x9f\xb6\x4c"
-			"\xc2\x2e\x37\x40\x49\xc3\x38\x16"
-			"\xe2\x4f\x77\x82\xb0\x68\x4c\x71"
-			"\x1d\x57\x61\x9c\xd9\x4e\x54\x99"
-			"\x47\x13\x28\x73\x3c\xbb\x00\x90"
-			"\xf3\x4d\xc9\x0e\xfd\xe7\xb1\x71"
-			"\xd3\x15\x79\xbf\xcc\x26\x2f\xbd"
-			"\xad\x6c\x50\x69\x6c\x3e\x6d\x80"
-			"\x9a\xea\x78\xaf\x19\xb2\x0d\x4d"
-			"\xad\x04\x07\xae\x22\x90\x4a\x93"
-			"\x32\x0e\x36\x9b\x1b\x46\xba\x3b"
-			"\xb4\xac\xc6\xd1\xa2\x31\x53\x3b"
-			"\x2a\x3d\x45\xfe\x03\x61\x10\x85"
-			"\x17\x69\xa6\x78\xcc\x6c\x87\x49"
-			"\x53\xf9\x80\x10\xde\x80\xa2\x41"
-			"\x6a\xc3\x32\x02\xad\x6d\x3c\x56"
-			"\x00\x71\x51\x06\xa7\xbd\xfb\xef"
-			"\x3c\xb5\x9f\xfc\x48\x7d\x53\x7c"
-			"\x66\xb0\x49\x23\xc4\x47\x10\x0e"
-			"\xe5\x6c\x74\x13\xe6\xc5\x3f\xaa"
-			"\xde\xff\x07\x44\xdd\x56\x1b\xad"
-			"\x09\x77\xfb\x5b\x12\xb8\x0d\x38"
-			"\x17\x37\x35\x7b\x9b\xbc\xfe\xd4"
-			"\x7e\x8b\xda\x7e\x5b\x04\xa7\x22"
-			"\xa7\x31\xa1\x20\x86\xc7\x1b\x99"
-			"\xdb\xd1\x89\xf4\x94\xa3\x53\x69"
-			"\x8d\xe7\xe8\x74\x11\x8d\x74\xd6"
-			"\x07\x37\x91\x9f\xfd\x67\x50\x3a"
-			"\xc9\xe1\xf4\x36\xd5\xa0\x47\xd1"
-			"\xf9\xe5\x39\xa3\x31\xac\x07\x36"
-			"\x23\xf8\x66\x18\x14\x28\x34\x0f"
-			"\xb8\xd0\xe7\x29\xb3\x04\x4b\x55"
-			"\x01\x41\xb2\x75\x8d\xcb\x96\x85"
-			"\x3a\xfb\xab\x2b\x9e\xfa\x58\x20"
-			"\x44\x1f\xc0\x14\x22\x75\x61\xe8"
-			"\xaa\x19\xcf\xf1\x82\x56\xf4\xd7"
-			"\x78\x7b\x3d\x5f\xb3\x9e\x0b\x8a"
-			"\x57\x50\xdb\x17\x41\x65\x4d\xa3"
-			"\x02\xc9\x9c\x9c\x53\xfb\x39\x39"
-			"\x9b\x1d\x72\x24\xda\xb7\x39\xbe"
-			"\x13\x3b\xfa\x29\xda\x9e\x54\x64"
-			"\x6e\xba\xd8\xa1\xcb\xb3\x36\xfa"
-			"\xcb\x47\x85\xe9\x61\x38\xbc\xbe"
-			"\xc5\x00\x38\x2a\x54\xf7\xc4\xb9"
-			"\xb3\xd3\x7b\xa0\xa0\xf8\x72\x7f"
-			"\x8c\x8e\x82\x0e\xc6\x1c\x75\x9d"
-			"\xca\x8e\x61\x87\xde\xad\x80\xd2"
-			"\xf5\xf9\x80\xef\x15\x75\xaf\xf5"
-			"\x80\xfb\xff\x6d\x1e\x25\xb7\x40"
-			"\x61\x6a\x39\x5a\x6a\xb5\x31\xab"
-			"\x97\x8a\x19\x89\x44\x40\xc0\xa6"
-			"\xb4\x4e\x30\x32\x7b\x13\xe7\x67"
-			"\xa9\x8b\x57\x04\xc2\x01\xa6\xf4"
-			"\x28\x99\xad\x2c\x76\xa3\x78\xc2"
-			"\x4a\xe6\xca\x5c\x50\x6a\xc1\xb0"
-			"\x62\x4b\x10\x8e\x7c\x17\x43\xb3"
-			"\x17\x66\x1c\x3e\x8d\x69\xf0\x5a"
-			"\x71\xf5\x97\xdc\xd1\x45\xdd\x28"
-			"\xf3\x5d\xdf\x53\x7b\x11\xe5\xbc"
-			"\x4c\xdb\x1b\x51\x6b\xe9\xfb\x3d"
-			"\xc1\xc3\x2c\xb9\x71\xf5\xb6\xb2"
-			"\x13\x36\x79\x80\x53\xe8\xd3\xa6"
-			"\x0a\xaf\xfd\x56\x97\xf7\x40\x8e"
-			"\x45\xce\xf8\xb0\x9e\x5c\x33\x82"
-			"\xb0\x44\x56\xfc\x05\x09\xe9\x2a"
-			"\xac\x26\x80\x14\x1d\xc8\x3a\x35"
-			"\x4c\x82\x97\xfd\x76\xb7\xa9\x0a"
-			"\x35\x58\x79\x8e\x0f\x66\xea\xaf"
-			"\x51\x6c\x09\xa9\x6e\x9b\xcb\x9a"
-			"\x31\x47\xa0\x2f\x7c\x71\xb4\x4a"
-			"\x11\xaa\x8c\x66\xc5\x64\xe6\x3a"
-			"\x54\xda\x24\x6a\xc4\x41\x65\x46"
-			"\x82\xa0\x0a\x0f\x5f\xfb\x25\xd0"
-			"\x2c\x91\xa7\xee\xc4\x81\x07\x86"
-			"\x75\x5e\x33\x69\x97\xe4\x2c\xa8"
-			"\x9d\x9f\x0b\x6a\xbe\xad\x98\xda"
-			"\x6d\x94\x41\xda\x2c\x1e\x89\xc4"
-			"\xc2\xaf\x1e\x00\x05\x0b\x83\x60"
-			"\xbd\x43\xea\x15\x23\x7f\xb9\xac"
-			"\xee\x4f\x2c\xaf\x2a\xf3\xdf\xd0"
-			"\xf3\x19\x31\xbb\x4a\x74\x84\x17"
-			"\x52\x32\x2c\x7d\x61\xe4\xcb\xeb"
-			"\x80\x38\x15\x52\xcb\x6f\xea\xe5"
-			"\x73\x9c\xd9\x24\x69\xc6\x95\x32"
-			"\x21\xc8\x11\xe4\xdc\x36\xd7\x93"
-			"\x38\x66\xfb\xb2\x7f\x3a\xb9\xaf"
-			"\x31\xdd\x93\x75\x78\x8a\x2c\x94"
-			"\x87\x1a\x58\xec\x9e\x7d\x4d\xba"
-			"\xe1\xe5\x4d\xfc\xbc\xa4\x2a\x14"
-			"\xef\xcc\xa7\xec\xab\x43\x09\x18"
-			"\xd3\xab\x68\xd1\x07\x99\x44\x47"
-			"\xd6\x83\x85\x3b\x30\xea\xa9\x6b"
-			"\x63\xea\xc4\x07\xfb\x43\x2f\xa4"
-			"\xaa\xb0\xab\x03\x89\xce\x3f\x8c"
-			"\x02\x7c\x86\x54\xbc\x88\xaf\x75"
-			"\xd2\xdc\x63\x17\xd3\x26\xf6\x96"
-			"\xa9\x3c\xf1\x61\x8c\x11\x18\xcc"
-			"\xd6\xea\x5b\xe2\xcd\xf0\xf1\xb2"
-			"\xe5\x35\x90\x1f\x85\x4c\x76\x5b"
-			"\x66\xce\x44\xa4\x32\x9f\xe6\x7b"
-			"\x71\x6e\x9f\x58\x15\x67\x72\x87"
-			"\x64\x8e\x3a\x44\x45\xd4\x76\xfa"
-			"\xc2\xf6\xef\x85\x05\x18\x7a\x9b"
-			"\xba\x41\x54\xac\xf0\xfc\x59\x12"
-			"\x3f\xdf\xa0\xe5\x8a\x65\xfd\x3a"
-			"\x62\x8d\x83\x2c\x03\xbe\x05\x76"
-			"\x2e\x53\x49\x97\x94\x33\xae\x40"
-			"\x81\x15\xdb\x6e\xad\xaa\xf5\x4b"
-			"\xe3\x98\x70\xdf\xe0\x7c\xcd\xdb"
-			"\x02\xd4\x7d\x2f\xc1\xe6\xb4\xf3"
-			"\xd7\x0d\x7a\xd9\x23\x9e\x87\x2d"
-			"\xce\x87\xad\xcc\x72\x05\x00\x29"
-			"\xdc\x73\x7f\x64\xc1\x15\x0e\xc2"
-			"\xdf\xa7\x5f\xeb\x41\xa1\xcd\xef"
-			"\x5c\x50\x79\x2a\x56\x56\x71\x8c"
-			"\xac\xc0\x79\x50\x69\xca\x59\x32"
-			"\x65\xf2\x54\xe4\x52\x38\x76\xd1"
-			"\x5e\xde\x26\x9e\xfb\x75\x2e\x11"
-			"\xb5\x10\xf4\x17\x73\xf5\x89\xc7"
-			"\x4f\x43\x5c\x8e\x7c\xb9\x05\x52"
-			"\x24\x40\x99\xfe\x9b\x85\x0b\x6c"
-			"\x22\x3e\x8b\xae\x86\xa1\xd2\x79"
-			"\x05\x68\x6b\xab\xe3\x41\x49\xed"
-			"\x15\xa1\x8d\x40\x2d\x61\xdf\x1a"
-			"\x59\xc9\x26\x8b\xef\x30\x4c\x88"
-			"\x4b\x10\xf8\x8d\xa6\x92\x9f\x4b"
-			"\xf3\xc4\x53\x0b\x89\x5d\x28\x92"
-			"\xcf\x78\xb2\xc0\x5d\xed\x7e\xfc"
-			"\xc0\x12\x23\x5f\x5a\x78\x86\x43"
-			"\x6e\x27\xf7\x5a\xa7\x6a\xed\x19"
-			"\x04\xf0\xb3\x12\xd1\xbd\x0e\x89"
-			"\x6e\xbc\x96\xa8\xd8\x49\x39\x9f"
-			"\x7e\x67\xf0\x2e\x3e\x01\xa9\xba"
-			"\xec\x8b\x62\x8e\xcb\x4a\x70\x43"
-			"\xc7\xc2\xc4\xca\x82\x03\x73\xe9"
-			"\x11\xdf\xcf\x54\xea\xc9\xb0\x95"
-			"\x51\xc0\x13\x3d\x92\x05\xfa\xf4"
-			"\xa9\x34\xc8\xce\x6c\x3d\x54\xcc"
-			"\xc4\xaf\xf1\xdc\x11\x44\x26\xa2"
-			"\xaf\xf1\x85\x75\x7d\x03\x61\x68"
-			"\x4e\x78\xc6\x92\x7d\x86\x7d\x77"
-			"\xdc\x71\x72\xdb\xc6\xae\xa1\xcb"
-			"\x70\x9a\x0b\x19\xbe\x4a\x6c\x2a"
-			"\xe2\xba\x6c\x64\x9a\x13\x28\xdf"
-			"\x85\x75\xe6\x43\xf6\x87\x08\x68"
-			"\x6e\xba\x6e\x79\x9f\x04\xbc\x23"
-			"\x50\xf6\x33\x5c\x1f\x24\x25\xbe"
-			"\x33\x47\x80\x45\x56\xa3\xa7\xd7"
-			"\x7a\xb1\x34\x0b\x90\x3c\x9c\xad"
-			"\x44\x5f\x9e\x0e\x9d\xd4\xbd\x93"
-			"\x5e\xfa\x3c\xe0\xb0\xd9\xed\xf3"
-			"\xd6\x2e\xff\x24\xd8\x71\x6c\xed"
-			"\xaf\x55\xeb\x22\xac\x93\x68\x32"
-			"\x05\x5b\x47\xdd\xc6\x4a\xcb\xc7"
-			"\x10\xe1\x3c\x92\x1a\xf3\x23\x78"
-			"\x2b\xa1\xd2\x80\xf4\x12\xb1\x20"
-			"\x8f\xff\x26\x35\xdd\xfb\xc7\x4e"
-			"\x78\xf1\x2d\x50\x12\x77\xa8\x60"
-			"\x7c\x0f\xf5\x16\x2f\x63\x70\x2a"
-			"\xc0\x96\x80\x4e\x0a\xb4\x93\x35"
-			"\x5d\x1d\x3f\x56\xf7\x2f\xbb\x90"
-			"\x11\x16\x8f\xa2\xec\x47\xbe\xac"
-			"\x56\x01\x26\x56\xb1\x8c\xb2\x10"
-			"\xf9\x1a\xca\xf5\xd1\xb7\x39\x20"
-			"\x63\xf1\x69\x20\x4f\x13\x12\x1f"
-			"\x5b\x65\xfc\x98\xf7\xc4\x7a\xbe"
-			"\xf7\x26\x4d\x2b\x84\x7b\x42\xad"
-			"\xd8\x7a\x0a\xb4\xd8\x74\xbf\xc1"
-			"\xf0\x6e\xb4\x29\xa3\xbb\xca\x46"
-			"\x67\x70\x6a\x2d\xce\x0e\xa2\x8a"
-			"\xa9\x87\xbf\x05\xc4\xc1\x04\xa3"
-			"\xab\xd4\x45\x43\x8c\xb6\x02\xb0"
-			"\x41\xc8\xfc\x44\x3d\x59\xaa\x2e"
-			"\x44\x21\x2a\x8d\x88\x9d\x57\xf4"
-			"\xa0\x02\x77\xb8\xa6\xa0\xe6\x75"
-			"\x5c\x82\x65\x3e\x03\x5c\x29\x8f"
-			"\x38\x55\xab\x33\x26\xef\x9f\x43"
-			"\x52\xfd\x68\xaf\x36\xb4\xbb\x9a"
-			"\x58\x09\x09\x1b\xc3\x65\x46\x46"
-			"\x1d\xa7\x94\x18\x23\x50\x2c\xca"
-			"\x2c\x55\x19\x97\x01\x9d\x93\x3b"
-			"\x63\x86\xf2\x03\x67\x45\xd2\x72"
-			"\x28\x52\x6c\xf4\xe3\x1c\xb5\x11"
-			"\x13\xf1\xeb\x21\xc7\xd9\x56\x82"
-			"\x2b\x82\x39\xbd\x69\x54\xed\x62"
-			"\xc3\xe2\xde\x73\xd4\x6a\x12\xae"
-			"\x13\x21\x7f\x4b\x5b\xfc\xbf\xe8"
-			"\x2b\xbe\x56\xba\x68\x8b\x9a\xb1"
-			"\x6e\xfa\xbf\x7e\x5a\x4b\xf1\xac"
-			"\x98\x65\x85\xd1\x93\x53\xd3\x7b"
-			"\x09\xdd\x4b\x10\x6d\x84\xb0\x13"
-			"\x65\xbd\xcf\x52\x09\xc4\x85\xe2"
-			"\x84\x74\x15\x65\xb7\xf7\x51\xaf"
-			"\x55\xad\xa4\xd1\x22\x54\x70\x94"
-			"\xa0\x1c\x90\x41\xfd\x99\xd7\x5a"
-			"\x31\xef\xaa\x25\xd0\x7f\x4f\xea"
-			"\x1d\x55\x42\xe5\x49\xb0\xd0\x46"
-			"\x62\x36\x43\xb2\x82\x15\x75\x50"
-			"\xa4\x72\xeb\x54\x27\x1f\x8a\xe4"
-			"\x7d\xe9\x66\xc5\xf1\x53\xa4\xd1"
-			"\x0c\xeb\xb8\xf8\xbc\xd4\xe2\xe7"
-			"\xe1\xf8\x4b\xcb\xa9\xa1\xaf\x15"
-			"\x83\xcb\x72\xd0\x33\x79\x00\x2d"
-			"\x9f\xd7\xf1\x2e\x1e\x10\xe4\x45"
-			"\xc0\x75\x3a\x39\xea\x68\xf7\x5d"
-			"\x1b\x73\x8f\xe9\x8e\x0f\x72\x47"
-			"\xae\x35\x0a\x31\x7a\x14\x4d\x4a"
-			"\x6f\x47\xf7\x7e\x91\x6e\x74\x8b"
-			"\x26\x47\xf9\xc3\xf9\xde\x70\xf5"
-			"\x61\xab\xa9\x27\x9f\x82\xe4\x9c"
-			"\x89\x91\x3f\x2e\x6a\xfd\xb5\x49"
-			"\xe9\xfd\x59\x14\x36\x49\x40\x6d"
-			"\x32\xd8\x85\x42\xf3\xa5\xdf\x0c"
-			"\xa8\x27\xd7\x54\xe2\x63\x2f\xf2"
-			"\x7e\x8b\x8b\xe7\xf1\x9a\x95\x35"
-			"\x43\xdc\x3a\xe4\xb6\xf4\xd0\xdf"
-			"\x9c\xcb\x94\xf3\x21\xa0\x77\x50"
-			"\xe2\xc6\xc4\xc6\x5f\x09\x64\x5b"
-			"\x92\x90\xd8\xe1\xd1\xed\x4b\x42"
-			"\xd7\x37\xaf\x65\x3d\x11\x39\xb6"
-			"\x24\x8a\x60\xae\xd6\x1e\xbf\x0e"
-			"\x0d\xd7\xdc\x96\x0e\x65\x75\x4e"
-			"\x29\x06\x9d\xa4\x51\x3a\x10\x63"
-			"\x8f\x17\x07\xd5\x8e\x3c\xf4\x28"
-			"\x00\x5a\x5b\x05\x19\xd8\xc0\x6c"
-			"\xe5\x15\xe4\x9c\x9d\x71\x9d\x5e"
-			"\x94\x29\x1a\xa7\x80\xfa\x0e\x33"
-			"\x03\xdd\xb7\x3e\x9a\xa9\x26\x18"
-			"\x37\xa9\x64\x08\x4d\x94\x5a\x88"
-			"\xca\x35\xce\x81\x02\xe3\x1f\x1b"
-			"\x89\x1a\x77\x85\xe3\x41\x6d\x32"
-			"\x42\x19\x23\x7d\xc8\x73\xee\x25"
-			"\x85\x0d\xf8\x31\x25\x79\x1b\x6f"
-			"\x79\x25\xd2\xd8\xd4\x23\xfd\xf7"
-			"\x82\x36\x6a\x0c\x46\x22\x15\xe9"
-			"\xff\x72\x41\x91\x91\x7d\x3a\xb7"
-			"\xdd\x65\x99\x70\xf6\x8d\x84\xf8"
-			"\x67\x15\x20\x11\xd6\xb2\x55\x7b"
-			"\xdb\x87\xee\xef\x55\x89\x2a\x59"
-			"\x2b\x07\x8f\x43\x8a\x59\x3c\x01"
-			"\x8b\x65\x54\xa1\x66\xd5\x38\xbd"
-			"\xc6\x30\xa9\xcc\x49\xb6\xa8\x1b"
-			"\xb8\xc0\x0e\xe3\x45\x28\xe2\xff"
-			"\x41\x9f\x7e\x7c\xd1\xae\x9e\x25"
-			"\x3f\x4c\x7c\x7c\xf4\xa8\x26\x4d"
-			"\x5c\xfd\x4b\x27\x18\xf9\x61\x76"
-			"\x48\xba\x0c\x6b\xa9\x4d\xfc\xf5"
-			"\x3b\x35\x7e\x2f\x4a\xa9\xc2\x9a"
-			"\xae\xab\x86\x09\x89\xc9\xc2\x40"
-			"\x39\x2c\x81\xb3\xb8\x17\x67\xc2"
-			"\x0d\x32\x4a\x3a\x67\x81\xd7\x1a"
-			"\x34\x52\xc5\xdb\x0a\xf5\x63\x39"
-			"\xea\x1f\xe1\x7c\xa1\x9e\xc1\x35"
-			"\xe3\xb1\x18\x45\x67\xf9\x22\x38"
-			"\x95\xd9\x34\x34\x86\xc6\x41\x94"
-			"\x15\xf9\x5b\x41\xa6\x87\x8b\xf8"
-			"\xd5\xe1\x1b\xe2\x5b\xf3\x86\x10"
-			"\xff\xe6\xae\x69\x76\xbc\x0d\xb4"
-			"\x09\x90\x0c\xa2\x65\x0c\xad\x74"
-			"\xf5\xd7\xff\xda\xc1\xce\x85\xbe"
-			"\x00\xa7\xff\x4d\x2f\x65\xd3\x8c"
-			"\x86\x2d\x05\xe8\xed\x3e\x6b\x8b"
-			"\x0f\x3d\x83\x8c\xf1\x1d\x5b\x96"
-			"\x2e\xb1\x9c\xc2\x98\xe1\x70\xb9"
-			"\xba\x5c\x8a\x43\xd6\x34\xa7\x2d"
-			"\xc9\x92\xae\xf2\xa5\x7b\x05\x49"
-			"\xa7\x33\x34\x86\xca\xe4\x96\x23"
-			"\x76\x5b\xf2\xc6\xf1\x51\x28\x42"
-			"\x7b\xcc\x76\x8f\xfa\xa2\xad\x31"
-			"\xd4\xd6\x7a\x6d\x25\x25\x54\xe4"
-			"\x3f\x50\x59\xe1\x5c\x05\xb7\x27"
-			"\x48\xbf\x07\xec\x1b\x13\xbe\x2b"
-			"\xa1\x57\x2b\xd5\xab\xd7\xd0\x4c"
-			"\x1e\xcb\x71\x9b\xc5\x90\x85\xd3"
-			"\xde\x59\xec\x71\xeb\x89\xbb\xd0"
-			"\x09\x50\xe1\x16\x3f\xfd\x1c\x34"
-			"\xc3\x1c\xa1\x10\x77\x53\x98\xef"
-			"\xf2\xfd\xa5\x01\x59\xc2\x9b\x26"
-			"\xc7\x42\xd9\x49\xda\x58\x2b\x6e"
-			"\x9f\x53\x19\x76\x7e\xd9\xc9\x0e"
-			"\x68\xc8\x7f\x51\x22\x42\xef\x49"
-			"\xa4\x55\xb6\x36\xac\x09\xc7\x31"
-			"\x88\x15\x4b\x2e\x8f\x3a\x08\xf7"
-			"\xd8\xf7\xa8\xc5\xa9\x33\xa6\x45"
-			"\xe4\xc4\x94\x76\xf3\x0d\x8f\x7e"
-			"\xc8\xf6\xbc\x23\x0a\xb6\x4c\xd3"
-			"\x6a\xcd\x36\xc2\x90\x5c\x5c\x3c"
-			"\x65\x7b\xc2\xd6\xcc\xe6\x0d\x87"
-			"\x73\x2e\x71\x79\x16\x06\x63\x28"
-			"\x09\x15\xd8\x89\x38\x38\x3d\xb5"
-			"\x42\x1c\x08\x24\xf7\x2a\xd2\x9d"
-			"\xc8\xca\xef\xf9\x27\xd8\x07\x86"
-			"\xf7\x43\x0b\x55\x15\x3f\x9f\x83"
-			"\xef\xdc\x49\x9d\x2a\xc1\x54\x62"
-			"\xbd\x9b\x66\x55\x9f\xb7\x12\xf3"
-			"\x1b\x4d\x9d\x2a\x5c\xed\x87\x75"
-			"\x87\x26\xec\x61\x2c\xb4\x0f\x89"
-			"\xb0\xfb\x2e\x68\x5d\x15\xc7\x8d"
-			"\x2e\xc0\xd9\xec\xaf\x4f\xd2\x25"
-			"\x29\xe8\xd2\x26\x2b\x67\xe9\xfc"
-			"\x2b\xa8\x67\x96\x12\x1f\x5b\x96"
-			"\xc6\x14\x53\xaf\x44\xea\xd6\xe2"
-			"\x94\x98\xe4\x12\x93\x4c\x92\xe0"
-			"\x18\xa5\x8d\x2d\xe4\x71\x3c\x47"
-			"\x4c\xf7\xe6\x47\x9e\xc0\x68\xdf"
-			"\xd4\xf5\x5a\x74\xb1\x2b\x29\x03"
-			"\x19\x07\xaf\x90\x62\x5c\x68\x98"
-			"\x48\x16\x11\x02\x9d\xee\xb4\x9b"
-			"\xe5\x42\x7f\x08\xfd\x16\x32\x0b"
-			"\xd0\xb3\xfa\x2b\xb7\x99\xf9\x29"
-			"\xcd\x20\x45\x9f\xb3\x1a\x5d\xa2"
-			"\xaf\x4d\xe0\xbd\x42\x0d\xbc\x74"
-			"\x99\x9c\x8e\x53\x1a\xb4\x3e\xbd"
-			"\xa2\x9a\x2d\xf7\xf8\x39\x0f\x67"
-			"\x63\xfc\x6b\xc0\xaf\xb3\x4b\x4f"
-			"\x55\xc4\xcf\xa7\xc8\x04\x11\x3e"
-			"\x14\x32\xbb\x1b\x38\x77\xd6\x7f"
-			"\x54\x4c\xdf\x75\xf3\x07\x2d\x33"
-			"\x9b\xa8\x20\xe1\x7b\x12\xb5\xf3"
-			"\xef\x2f\xce\x72\xe5\x24\x60\xc1"
-			"\x30\xe2\xab\xa1\x8e\x11\x09\xa8"
-			"\x21\x33\x44\xfe\x7f\x35\x32\x93"
-			"\x39\xa7\xad\x8b\x79\x06\xb2\xcb"
-			"\x4e\xa9\x5f\xc7\xba\x74\x29\xec"
-			"\x93\xa0\x4e\x54\x93\xc0\xbc\x55"
-			"\x64\xf0\x48\xe5\x57\x99\xee\x75"
-			"\xd6\x79\x0f\x66\xb7\xc6\x57\x76"
-			"\xf7\xb7\xf3\x9c\xc5\x60\xe8\x7f"
-			"\x83\x76\xd6\x0e\xaa\xe6\x90\x39"
-			"\x1d\xa6\x32\x6a\x34\xe3\x55\xf8"
-			"\x58\xa0\x58\x7d\x33\xe0\x22\x39"
-			"\x44\x64\x87\x86\x5a\x2f\xa7\x7e"
-			"\x0f\x38\xea\xb0\x30\xcc\x61\xa5"
-			"\x6a\x32\xae\x1e\xf7\xe9\xd0\xa9"
-			"\x0c\x32\x4b\xb5\x49\x28\xab\x85"
-			"\x2f\x8e\x01\x36\x38\x52\xd0\xba"
-			"\xd6\x02\x78\xf8\x0e\x3e\x9c\x8b"
-			"\x6b\x45\x99\x3f\x5c\xfe\x58\xf1"
-			"\x5c\x94\x04\xe1\xf5\x18\x6d\x51"
-			"\xb2\x5d\x18\x20\xb6\xc2\x9a\x42"
-			"\x1d\xb3\xab\x3c\xb6\x3a\x13\x03"
-			"\xb2\x46\x82\x4f\xfc\x64\xbc\x4f"
-			"\xca\xfa\x9c\xc0\xd5\xa7\xbd\x11"
-			"\xb7\xe4\x5a\xf6\x6f\x4d\x4d\x54"
-			"\xea\xa4\x98\x66\xd4\x22\x3b\xd3"
-			"\x8f\x34\x47\xd9\x7c\xf4\x72\x3b"
-			"\x4d\x02\x77\xf6\xd6\xdd\x08\x0a"
-			"\x81\xe1\x86\x89\x3e\x56\x10\x3c"
-			"\xba\xd7\x81\x8c\x08\xbc\x8b\xe2"
-			"\x53\xec\xa7\x89\xee\xc8\x56\xb5"
-			"\x36\x2c\xb2\x03\xba\x99\xdd\x7c"
-			"\x48\xa0\xb0\xbc\x91\x33\xe9\xa8"
-			"\xcb\xcd\xcf\x59\x5f\x1f\x15\xe2"
-			"\x56\xf5\x4e\x01\x35\x27\x45\x77"
-			"\x47\xc8\xbc\xcb\x7e\x39\xc1\x97"
-			"\x28\xd3\x84\xfc\x2c\x3e\xc8\xad"
-			"\x9c\xf8\x8a\x61\x9c\x28\xaa\xc5"
-			"\x99\x20\x43\x85\x9d\xa5\xe2\x8b"
-			"\xb8\xae\xeb\xd0\x32\x0d\x52\x78"
-			"\x09\x56\x3f\xc7\xd8\x7e\x26\xfc"
-			"\x37\xfb\x6f\x04\xfc\xfa\x92\x10"
-			"\xac\xf8\x3e\x21\xdc\x8c\x21\x16"
-			"\x7d\x67\x6e\xf6\xcd\xda\xb6\x98"
-			"\x23\xab\x23\x3c\xb2\x10\xa0\x53"
-			"\x5a\x56\x9f\xc5\xd0\xff\xbb\xe4"
-			"\x98\x3c\x69\x1e\xdb\x38\x8f\x7e"
-			"\x0f\xd2\x98\x88\x81\x8b\x45\x67"
-			"\xea\x33\xf1\xeb\xe9\x97\x55\x2e"
-			"\xd9\xaa\xeb\x5a\xec\xda\xe1\x68"
-			"\xa8\x9d\x3c\x84\x7c\x05\x3d\x62"
-			"\x87\x8f\x03\x21\x28\x95\x0c\x89"
-			"\x25\x22\x4a\xb0\x93\xa9\x50\xa2"
-			"\x2f\x57\x6e\x18\x42\x19\x54\x0c"
-			"\x55\x67\xc6\x11\x49\xf4\x5c\xd2"
-			"\xe9\x3d\xdd\x8b\x48\x71\x21\x00"
-			"\xc3\x9a\x6c\x85\x74\x28\x83\x4a"
-			"\x1b\x31\x05\xe1\x06\x92\xe7\xda"
-			"\x85\x73\x78\x45\x20\x7f\xae\x13"
-			"\x7c\x33\x06\x22\xf4\x83\xf9\x35"
-			"\x3f\x6c\x71\xa8\x4e\x48\xbe\x9b"
-			"\xce\x8a\xba\xda\xbe\x28\x08\xf7"
-			"\xe2\x14\x8c\x71\xea\x72\xf9\x33"
-			"\xf2\x88\x3f\xd7\xbb\x69\x6c\x29"
-			"\x19\xdc\x84\xce\x1f\x12\x4f\xc8"
-			"\xaf\xa5\x04\xba\x5a\xab\xb0\xd9"
-			"\x14\x1f\x6c\x68\x98\x39\x89\x7a"
-			"\xd9\xd8\x2f\xdf\xa8\x47\x4a\x25"
-			"\xe2\xfb\x33\xf4\x59\x78\xe1\x68"
-			"\x85\xcf\xfe\x59\x20\xd4\x05\x1d"
-			"\x80\x99\xae\xbc\xca\xae\x0f\x2f"
-			"\x65\x43\x34\x8e\x7e\xac\xd3\x93"
-			"\x2f\xac\x6d\x14\x3d\x02\x07\x70"
-			"\x9d\xa4\xf3\x1b\x5c\x36\xfc\x01"
-			"\x73\x34\x85\x0c\x6c\xd6\xf1\xbd"
-			"\x3f\xdf\xee\xf5\xd9\xba\x56\xef"
-			"\xf4\x9b\x6b\xee\x9f\x5a\x78\x6d"
-			"\x32\x19\xf4\xf7\xf8\x4c\x69\x0b"
-			"\x4b\xbc\xbb\xb7\xf2\x85\xaf\x70"
-			"\x75\x24\x6c\x54\xa7\x0e\x4d\x1d"
-			"\x01\xbf\x08\xac\xcf\x7f\x2c\xe3"
-			"\x14\x89\x5e\x70\x5a\x99\x92\xcd"
-			"\x01\x84\xc8\xd2\xab\xe5\x4f\x58"
-			"\xe7\x0f\x2f\x0e\xff\x68\xea\xfd"
-			"\x15\xb3\x17\xe6\xb0\xe7\x85\xd8"
-			"\x23\x2e\x05\xc7\xc9\xc4\x46\x1f"
-			"\xe1\x9e\x49\x20\x23\x24\x4d\x7e"
-			"\x29\x65\xff\xf4\xb6\xfd\x1a\x85"
-			"\xc4\x16\xec\xfc\xea\x7b\xd6\x2c"
-			"\x43\xf8\xb7\xbf\x79\xc0\x85\xcd"
-			"\xef\xe1\x98\xd3\xa5\xf7\x90\x8c"
-			"\xe9\x7f\x80\x6b\xd2\xac\x4c\x30"
-			"\xa7\xc6\x61\x6c\xd2\xf9\x2c\xff"
-			"\x30\xbc\x22\x81\x7d\x93\x12\xe4"
-			"\x0a\xcd\xaf\xdd\xe8\xab\x0a\x1e"
-			"\x13\xa4\x27\xc3\x5f\xf7\x4b\xbb"
-			"\x37\x09\x4b\x91\x6f\x92\x4f\xaf"
-			"\x52\xee\xdf\xef\x09\x6f\xf7\x5c"
-			"\x6e\x12\x17\x72\x63\x57\xc7\xba"
-			"\x3b\x6b\x38\x32\x73\x1b\x9c\x80"
-			"\xc1\x7a\xc6\xcf\xcd\x35\xc0\x6b"
-			"\x31\x1a\x6b\xe9\xd8\x2c\x29\x3f"
-			"\x96\xfb\xb6\xcd\x13\x91\x3b\xc2"
-			"\xd2\xa3\x31\x8d\xa4\xcd\x57\xcd"
-			"\x13\x3d\x64\xfd\x06\xce\xe6\xdc"
-			"\x0c\x24\x43\x31\x40\x57\xf1\x72"
-			"\x17\xe3\x3a\x63\x6d\x35\xcf\x5d"
-			"\x97\x40\x59\xdd\xf7\x3c\x02\xf7"
-			"\x1c\x7e\x05\xbb\xa9\x0d\x01\xb1"
-			"\x8e\xc0\x30\xa9\x53\x24\xc9\x89"
-			"\x84\x6d\xaa\xd0\xcd\x91\xc2\x4d"
-			"\x91\xb0\x89\xe2\xbf\x83\x44\xaa"
-			"\x28\x72\x23\xa0\xc2\xad\xad\x1c"
-			"\xfc\x3f\x09\x7a\x0b\xdc\xc5\x1b"
-			"\x87\x13\xc6\x5b\x59\x8d\xf2\xc8"
-			"\xaf\xdf\x11\x95",
-		.len	= 4100,
-	},
-};
-
 static const struct cipher_testvec chacha20_tv_template[] = {
 	{ /* RFC7539 A.2. Test Vector #1 */
 		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
diff --git a/crypto/tgr192.c b/crypto/tgr192.c
deleted file mode 100644
index aa29c529b44e..000000000000
--- a/crypto/tgr192.c
+++ /dev/null
@@ -1,682 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cryptographic API.
- *
- * Tiger hashing Algorithm
- *
- *      Copyright (C) 1998 Free Software Foundation, Inc.
- *
- * The Tiger algorithm was developed by Ross Anderson and Eli Biham.
- * It was optimized for 64-bit processors while still delievering
- * decent performance on 32 and 16-bit processors.
- *
- * This version is derived from the GnuPG implementation and the
- * Tiger-Perl interface written by Rafael Sevilla
- *
- * Adapted for Linux Kernel Crypto  by Aaron Grothe 
- * ajgrothe@yahoo.com, February 22, 2005
- */
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <asm/byteorder.h>
-#include <asm/unaligned.h>
-
-#define TGR192_DIGEST_SIZE 24
-#define TGR160_DIGEST_SIZE 20
-#define TGR128_DIGEST_SIZE 16
-
-#define TGR192_BLOCK_SIZE  64
-
-struct tgr192_ctx {
-	u64 a, b, c;
-	u8 hash[64];
-	int count;
-	u32 nblocks;
-};
-
-static const u64 sbox1[256] = {
-	0x02aab17cf7e90c5eULL, 0xac424b03e243a8ecULL, 0x72cd5be30dd5fcd3ULL,
-	0x6d019b93f6f97f3aULL, 0xcd9978ffd21f9193ULL, 0x7573a1c9708029e2ULL,
-	0xb164326b922a83c3ULL, 0x46883eee04915870ULL, 0xeaace3057103ece6ULL,
-	0xc54169b808a3535cULL, 0x4ce754918ddec47cULL, 0x0aa2f4dfdc0df40cULL,
-	0x10b76f18a74dbefaULL, 0xc6ccb6235ad1ab6aULL, 0x13726121572fe2ffULL,
-	0x1a488c6f199d921eULL, 0x4bc9f9f4da0007caULL, 0x26f5e6f6e85241c7ULL,
-	0x859079dbea5947b6ULL, 0x4f1885c5c99e8c92ULL, 0xd78e761ea96f864bULL,
-	0x8e36428c52b5c17dULL, 0x69cf6827373063c1ULL, 0xb607c93d9bb4c56eULL,
-	0x7d820e760e76b5eaULL, 0x645c9cc6f07fdc42ULL, 0xbf38a078243342e0ULL,
-	0x5f6b343c9d2e7d04ULL, 0xf2c28aeb600b0ec6ULL, 0x6c0ed85f7254bcacULL,
-	0x71592281a4db4fe5ULL, 0x1967fa69ce0fed9fULL, 0xfd5293f8b96545dbULL,
-	0xc879e9d7f2a7600bULL, 0x860248920193194eULL, 0xa4f9533b2d9cc0b3ULL,
-	0x9053836c15957613ULL, 0xdb6dcf8afc357bf1ULL, 0x18beea7a7a370f57ULL,
-	0x037117ca50b99066ULL, 0x6ab30a9774424a35ULL, 0xf4e92f02e325249bULL,
-	0x7739db07061ccae1ULL, 0xd8f3b49ceca42a05ULL, 0xbd56be3f51382f73ULL,
-	0x45faed5843b0bb28ULL, 0x1c813d5c11bf1f83ULL, 0x8af0e4b6d75fa169ULL,
-	0x33ee18a487ad9999ULL, 0x3c26e8eab1c94410ULL, 0xb510102bc0a822f9ULL,
-	0x141eef310ce6123bULL, 0xfc65b90059ddb154ULL, 0xe0158640c5e0e607ULL,
-	0x884e079826c3a3cfULL, 0x930d0d9523c535fdULL, 0x35638d754e9a2b00ULL,
-	0x4085fccf40469dd5ULL, 0xc4b17ad28be23a4cULL, 0xcab2f0fc6a3e6a2eULL,
-	0x2860971a6b943fcdULL, 0x3dde6ee212e30446ULL, 0x6222f32ae01765aeULL,
-	0x5d550bb5478308feULL, 0xa9efa98da0eda22aULL, 0xc351a71686c40da7ULL,
-	0x1105586d9c867c84ULL, 0xdcffee85fda22853ULL, 0xccfbd0262c5eef76ULL,
-	0xbaf294cb8990d201ULL, 0xe69464f52afad975ULL, 0x94b013afdf133e14ULL,
-	0x06a7d1a32823c958ULL, 0x6f95fe5130f61119ULL, 0xd92ab34e462c06c0ULL,
-	0xed7bde33887c71d2ULL, 0x79746d6e6518393eULL, 0x5ba419385d713329ULL,
-	0x7c1ba6b948a97564ULL, 0x31987c197bfdac67ULL, 0xde6c23c44b053d02ULL,
-	0x581c49fed002d64dULL, 0xdd474d6338261571ULL, 0xaa4546c3e473d062ULL,
-	0x928fce349455f860ULL, 0x48161bbacaab94d9ULL, 0x63912430770e6f68ULL,
-	0x6ec8a5e602c6641cULL, 0x87282515337ddd2bULL, 0x2cda6b42034b701bULL,
-	0xb03d37c181cb096dULL, 0xe108438266c71c6fULL, 0x2b3180c7eb51b255ULL,
-	0xdf92b82f96c08bbcULL, 0x5c68c8c0a632f3baULL, 0x5504cc861c3d0556ULL,
-	0xabbfa4e55fb26b8fULL, 0x41848b0ab3baceb4ULL, 0xb334a273aa445d32ULL,
-	0xbca696f0a85ad881ULL, 0x24f6ec65b528d56cULL, 0x0ce1512e90f4524aULL,
-	0x4e9dd79d5506d35aULL, 0x258905fac6ce9779ULL, 0x2019295b3e109b33ULL,
-	0xf8a9478b73a054ccULL, 0x2924f2f934417eb0ULL, 0x3993357d536d1bc4ULL,
-	0x38a81ac21db6ff8bULL, 0x47c4fbf17d6016bfULL, 0x1e0faadd7667e3f5ULL,
-	0x7abcff62938beb96ULL, 0xa78dad948fc179c9ULL, 0x8f1f98b72911e50dULL,
-	0x61e48eae27121a91ULL, 0x4d62f7ad31859808ULL, 0xeceba345ef5ceaebULL,
-	0xf5ceb25ebc9684ceULL, 0xf633e20cb7f76221ULL, 0xa32cdf06ab8293e4ULL,
-	0x985a202ca5ee2ca4ULL, 0xcf0b8447cc8a8fb1ULL, 0x9f765244979859a3ULL,
-	0xa8d516b1a1240017ULL, 0x0bd7ba3ebb5dc726ULL, 0xe54bca55b86adb39ULL,
-	0x1d7a3afd6c478063ULL, 0x519ec608e7669eddULL, 0x0e5715a2d149aa23ULL,
-	0x177d4571848ff194ULL, 0xeeb55f3241014c22ULL, 0x0f5e5ca13a6e2ec2ULL,
-	0x8029927b75f5c361ULL, 0xad139fabc3d6e436ULL, 0x0d5df1a94ccf402fULL,
-	0x3e8bd948bea5dfc8ULL, 0xa5a0d357bd3ff77eULL, 0xa2d12e251f74f645ULL,
-	0x66fd9e525e81a082ULL, 0x2e0c90ce7f687a49ULL, 0xc2e8bcbeba973bc5ULL,
-	0x000001bce509745fULL, 0x423777bbe6dab3d6ULL, 0xd1661c7eaef06eb5ULL,
-	0xa1781f354daacfd8ULL, 0x2d11284a2b16affcULL, 0xf1fc4f67fa891d1fULL,
-	0x73ecc25dcb920adaULL, 0xae610c22c2a12651ULL, 0x96e0a810d356b78aULL,
-	0x5a9a381f2fe7870fULL, 0xd5ad62ede94e5530ULL, 0xd225e5e8368d1427ULL,
-	0x65977b70c7af4631ULL, 0x99f889b2de39d74fULL, 0x233f30bf54e1d143ULL,
-	0x9a9675d3d9a63c97ULL, 0x5470554ff334f9a8ULL, 0x166acb744a4f5688ULL,
-	0x70c74caab2e4aeadULL, 0xf0d091646f294d12ULL, 0x57b82a89684031d1ULL,
-	0xefd95a5a61be0b6bULL, 0x2fbd12e969f2f29aULL, 0x9bd37013feff9fe8ULL,
-	0x3f9b0404d6085a06ULL, 0x4940c1f3166cfe15ULL, 0x09542c4dcdf3defbULL,
-	0xb4c5218385cd5ce3ULL, 0xc935b7dc4462a641ULL, 0x3417f8a68ed3b63fULL,
-	0xb80959295b215b40ULL, 0xf99cdaef3b8c8572ULL, 0x018c0614f8fcb95dULL,
-	0x1b14accd1a3acdf3ULL, 0x84d471f200bb732dULL, 0xc1a3110e95e8da16ULL,
-	0x430a7220bf1a82b8ULL, 0xb77e090d39df210eULL, 0x5ef4bd9f3cd05e9dULL,
-	0x9d4ff6da7e57a444ULL, 0xda1d60e183d4a5f8ULL, 0xb287c38417998e47ULL,
-	0xfe3edc121bb31886ULL, 0xc7fe3ccc980ccbefULL, 0xe46fb590189bfd03ULL,
-	0x3732fd469a4c57dcULL, 0x7ef700a07cf1ad65ULL, 0x59c64468a31d8859ULL,
-	0x762fb0b4d45b61f6ULL, 0x155baed099047718ULL, 0x68755e4c3d50baa6ULL,
-	0xe9214e7f22d8b4dfULL, 0x2addbf532eac95f4ULL, 0x32ae3909b4bd0109ULL,
-	0x834df537b08e3450ULL, 0xfa209da84220728dULL, 0x9e691d9b9efe23f7ULL,
-	0x0446d288c4ae8d7fULL, 0x7b4cc524e169785bULL, 0x21d87f0135ca1385ULL,
-	0xcebb400f137b8aa5ULL, 0x272e2b66580796beULL, 0x3612264125c2b0deULL,
-	0x057702bdad1efbb2ULL, 0xd4babb8eacf84be9ULL, 0x91583139641bc67bULL,
-	0x8bdc2de08036e024ULL, 0x603c8156f49f68edULL, 0xf7d236f7dbef5111ULL,
-	0x9727c4598ad21e80ULL, 0xa08a0896670a5fd7ULL, 0xcb4a8f4309eba9cbULL,
-	0x81af564b0f7036a1ULL, 0xc0b99aa778199abdULL, 0x959f1ec83fc8e952ULL,
-	0x8c505077794a81b9ULL, 0x3acaaf8f056338f0ULL, 0x07b43f50627a6778ULL,
-	0x4a44ab49f5eccc77ULL, 0x3bc3d6e4b679ee98ULL, 0x9cc0d4d1cf14108cULL,
-	0x4406c00b206bc8a0ULL, 0x82a18854c8d72d89ULL, 0x67e366b35c3c432cULL,
-	0xb923dd61102b37f2ULL, 0x56ab2779d884271dULL, 0xbe83e1b0ff1525afULL,
-	0xfb7c65d4217e49a9ULL, 0x6bdbe0e76d48e7d4ULL, 0x08df828745d9179eULL,
-	0x22ea6a9add53bd34ULL, 0xe36e141c5622200aULL, 0x7f805d1b8cb750eeULL,
-	0xafe5c7a59f58e837ULL, 0xe27f996a4fb1c23cULL, 0xd3867dfb0775f0d0ULL,
-	0xd0e673de6e88891aULL, 0x123aeb9eafb86c25ULL, 0x30f1d5d5c145b895ULL,
-	0xbb434a2dee7269e7ULL, 0x78cb67ecf931fa38ULL, 0xf33b0372323bbf9cULL,
-	0x52d66336fb279c74ULL, 0x505f33ac0afb4eaaULL, 0xe8a5cd99a2cce187ULL,
-	0x534974801e2d30bbULL, 0x8d2d5711d5876d90ULL, 0x1f1a412891bc038eULL,
-	0xd6e2e71d82e56648ULL, 0x74036c3a497732b7ULL, 0x89b67ed96361f5abULL,
-	0xffed95d8f1ea02a2ULL, 0xe72b3bd61464d43dULL, 0xa6300f170bdc4820ULL,
-	0xebc18760ed78a77aULL
-};
-
-static const u64 sbox2[256] = {
-	0xe6a6be5a05a12138ULL, 0xb5a122a5b4f87c98ULL, 0x563c6089140b6990ULL,
-	0x4c46cb2e391f5dd5ULL, 0xd932addbc9b79434ULL, 0x08ea70e42015aff5ULL,
-	0xd765a6673e478cf1ULL, 0xc4fb757eab278d99ULL, 0xdf11c6862d6e0692ULL,
-	0xddeb84f10d7f3b16ULL, 0x6f2ef604a665ea04ULL, 0x4a8e0f0ff0e0dfb3ULL,
-	0xa5edeef83dbcba51ULL, 0xfc4f0a2a0ea4371eULL, 0xe83e1da85cb38429ULL,
-	0xdc8ff882ba1b1ce2ULL, 0xcd45505e8353e80dULL, 0x18d19a00d4db0717ULL,
-	0x34a0cfeda5f38101ULL, 0x0be77e518887caf2ULL, 0x1e341438b3c45136ULL,
-	0xe05797f49089ccf9ULL, 0xffd23f9df2591d14ULL, 0x543dda228595c5cdULL,
-	0x661f81fd99052a33ULL, 0x8736e641db0f7b76ULL, 0x15227725418e5307ULL,
-	0xe25f7f46162eb2faULL, 0x48a8b2126c13d9feULL, 0xafdc541792e76eeaULL,
-	0x03d912bfc6d1898fULL, 0x31b1aafa1b83f51bULL, 0xf1ac2796e42ab7d9ULL,
-	0x40a3a7d7fcd2ebacULL, 0x1056136d0afbbcc5ULL, 0x7889e1dd9a6d0c85ULL,
-	0xd33525782a7974aaULL, 0xa7e25d09078ac09bULL, 0xbd4138b3eac6edd0ULL,
-	0x920abfbe71eb9e70ULL, 0xa2a5d0f54fc2625cULL, 0xc054e36b0b1290a3ULL,
-	0xf6dd59ff62fe932bULL, 0x3537354511a8ac7dULL, 0xca845e9172fadcd4ULL,
-	0x84f82b60329d20dcULL, 0x79c62ce1cd672f18ULL, 0x8b09a2add124642cULL,
-	0xd0c1e96a19d9e726ULL, 0x5a786a9b4ba9500cULL, 0x0e020336634c43f3ULL,
-	0xc17b474aeb66d822ULL, 0x6a731ae3ec9baac2ULL, 0x8226667ae0840258ULL,
-	0x67d4567691caeca5ULL, 0x1d94155c4875adb5ULL, 0x6d00fd985b813fdfULL,
-	0x51286efcb774cd06ULL, 0x5e8834471fa744afULL, 0xf72ca0aee761ae2eULL,
-	0xbe40e4cdaee8e09aULL, 0xe9970bbb5118f665ULL, 0x726e4beb33df1964ULL,
-	0x703b000729199762ULL, 0x4631d816f5ef30a7ULL, 0xb880b5b51504a6beULL,
-	0x641793c37ed84b6cULL, 0x7b21ed77f6e97d96ULL, 0x776306312ef96b73ULL,
-	0xae528948e86ff3f4ULL, 0x53dbd7f286a3f8f8ULL, 0x16cadce74cfc1063ULL,
-	0x005c19bdfa52c6ddULL, 0x68868f5d64d46ad3ULL, 0x3a9d512ccf1e186aULL,
-	0x367e62c2385660aeULL, 0xe359e7ea77dcb1d7ULL, 0x526c0773749abe6eULL,
-	0x735ae5f9d09f734bULL, 0x493fc7cc8a558ba8ULL, 0xb0b9c1533041ab45ULL,
-	0x321958ba470a59bdULL, 0x852db00b5f46c393ULL, 0x91209b2bd336b0e5ULL,
-	0x6e604f7d659ef19fULL, 0xb99a8ae2782ccb24ULL, 0xccf52ab6c814c4c7ULL,
-	0x4727d9afbe11727bULL, 0x7e950d0c0121b34dULL, 0x756f435670ad471fULL,
-	0xf5add442615a6849ULL, 0x4e87e09980b9957aULL, 0x2acfa1df50aee355ULL,
-	0xd898263afd2fd556ULL, 0xc8f4924dd80c8fd6ULL, 0xcf99ca3d754a173aULL,
-	0xfe477bacaf91bf3cULL, 0xed5371f6d690c12dULL, 0x831a5c285e687094ULL,
-	0xc5d3c90a3708a0a4ULL, 0x0f7f903717d06580ULL, 0x19f9bb13b8fdf27fULL,
-	0xb1bd6f1b4d502843ULL, 0x1c761ba38fff4012ULL, 0x0d1530c4e2e21f3bULL,
-	0x8943ce69a7372c8aULL, 0xe5184e11feb5ce66ULL, 0x618bdb80bd736621ULL,
-	0x7d29bad68b574d0bULL, 0x81bb613e25e6fe5bULL, 0x071c9c10bc07913fULL,
-	0xc7beeb7909ac2d97ULL, 0xc3e58d353bc5d757ULL, 0xeb017892f38f61e8ULL,
-	0xd4effb9c9b1cc21aULL, 0x99727d26f494f7abULL, 0xa3e063a2956b3e03ULL,
-	0x9d4a8b9a4aa09c30ULL, 0x3f6ab7d500090fb4ULL, 0x9cc0f2a057268ac0ULL,
-	0x3dee9d2dedbf42d1ULL, 0x330f49c87960a972ULL, 0xc6b2720287421b41ULL,
-	0x0ac59ec07c00369cULL, 0xef4eac49cb353425ULL, 0xf450244eef0129d8ULL,
-	0x8acc46e5caf4deb6ULL, 0x2ffeab63989263f7ULL, 0x8f7cb9fe5d7a4578ULL,
-	0x5bd8f7644e634635ULL, 0x427a7315bf2dc900ULL, 0x17d0c4aa2125261cULL,
-	0x3992486c93518e50ULL, 0xb4cbfee0a2d7d4c3ULL, 0x7c75d6202c5ddd8dULL,
-	0xdbc295d8e35b6c61ULL, 0x60b369d302032b19ULL, 0xce42685fdce44132ULL,
-	0x06f3ddb9ddf65610ULL, 0x8ea4d21db5e148f0ULL, 0x20b0fce62fcd496fULL,
-	0x2c1b912358b0ee31ULL, 0xb28317b818f5a308ULL, 0xa89c1e189ca6d2cfULL,
-	0x0c6b18576aaadbc8ULL, 0xb65deaa91299fae3ULL, 0xfb2b794b7f1027e7ULL,
-	0x04e4317f443b5bebULL, 0x4b852d325939d0a6ULL, 0xd5ae6beefb207ffcULL,
-	0x309682b281c7d374ULL, 0xbae309a194c3b475ULL, 0x8cc3f97b13b49f05ULL,
-	0x98a9422ff8293967ULL, 0x244b16b01076ff7cULL, 0xf8bf571c663d67eeULL,
-	0x1f0d6758eee30da1ULL, 0xc9b611d97adeb9b7ULL, 0xb7afd5887b6c57a2ULL,
-	0x6290ae846b984fe1ULL, 0x94df4cdeacc1a5fdULL, 0x058a5bd1c5483affULL,
-	0x63166cc142ba3c37ULL, 0x8db8526eb2f76f40ULL, 0xe10880036f0d6d4eULL,
-	0x9e0523c9971d311dULL, 0x45ec2824cc7cd691ULL, 0x575b8359e62382c9ULL,
-	0xfa9e400dc4889995ULL, 0xd1823ecb45721568ULL, 0xdafd983b8206082fULL,
-	0xaa7d29082386a8cbULL, 0x269fcd4403b87588ULL, 0x1b91f5f728bdd1e0ULL,
-	0xe4669f39040201f6ULL, 0x7a1d7c218cf04adeULL, 0x65623c29d79ce5ceULL,
-	0x2368449096c00bb1ULL, 0xab9bf1879da503baULL, 0xbc23ecb1a458058eULL,
-	0x9a58df01bb401eccULL, 0xa070e868a85f143dULL, 0x4ff188307df2239eULL,
-	0x14d565b41a641183ULL, 0xee13337452701602ULL, 0x950e3dcf3f285e09ULL,
-	0x59930254b9c80953ULL, 0x3bf299408930da6dULL, 0xa955943f53691387ULL,
-	0xa15edecaa9cb8784ULL, 0x29142127352be9a0ULL, 0x76f0371fff4e7afbULL,
-	0x0239f450274f2228ULL, 0xbb073af01d5e868bULL, 0xbfc80571c10e96c1ULL,
-	0xd267088568222e23ULL, 0x9671a3d48e80b5b0ULL, 0x55b5d38ae193bb81ULL,
-	0x693ae2d0a18b04b8ULL, 0x5c48b4ecadd5335fULL, 0xfd743b194916a1caULL,
-	0x2577018134be98c4ULL, 0xe77987e83c54a4adULL, 0x28e11014da33e1b9ULL,
-	0x270cc59e226aa213ULL, 0x71495f756d1a5f60ULL, 0x9be853fb60afef77ULL,
-	0xadc786a7f7443dbfULL, 0x0904456173b29a82ULL, 0x58bc7a66c232bd5eULL,
-	0xf306558c673ac8b2ULL, 0x41f639c6b6c9772aULL, 0x216defe99fda35daULL,
-	0x11640cc71c7be615ULL, 0x93c43694565c5527ULL, 0xea038e6246777839ULL,
-	0xf9abf3ce5a3e2469ULL, 0x741e768d0fd312d2ULL, 0x0144b883ced652c6ULL,
-	0xc20b5a5ba33f8552ULL, 0x1ae69633c3435a9dULL, 0x97a28ca4088cfdecULL,
-	0x8824a43c1e96f420ULL, 0x37612fa66eeea746ULL, 0x6b4cb165f9cf0e5aULL,
-	0x43aa1c06a0abfb4aULL, 0x7f4dc26ff162796bULL, 0x6cbacc8e54ed9b0fULL,
-	0xa6b7ffefd2bb253eULL, 0x2e25bc95b0a29d4fULL, 0x86d6a58bdef1388cULL,
-	0xded74ac576b6f054ULL, 0x8030bdbc2b45805dULL, 0x3c81af70e94d9289ULL,
-	0x3eff6dda9e3100dbULL, 0xb38dc39fdfcc8847ULL, 0x123885528d17b87eULL,
-	0xf2da0ed240b1b642ULL, 0x44cefadcd54bf9a9ULL, 0x1312200e433c7ee6ULL,
-	0x9ffcc84f3a78c748ULL, 0xf0cd1f72248576bbULL, 0xec6974053638cfe4ULL,
-	0x2ba7b67c0cec4e4cULL, 0xac2f4df3e5ce32edULL, 0xcb33d14326ea4c11ULL,
-	0xa4e9044cc77e58bcULL, 0x5f513293d934fcefULL, 0x5dc9645506e55444ULL,
-	0x50de418f317de40aULL, 0x388cb31a69dde259ULL, 0x2db4a83455820a86ULL,
-	0x9010a91e84711ae9ULL, 0x4df7f0b7b1498371ULL, 0xd62a2eabc0977179ULL,
-	0x22fac097aa8d5c0eULL
-};
-
-static const u64 sbox3[256] = {
-	0xf49fcc2ff1daf39bULL, 0x487fd5c66ff29281ULL, 0xe8a30667fcdca83fULL,
-	0x2c9b4be3d2fcce63ULL, 0xda3ff74b93fbbbc2ULL, 0x2fa165d2fe70ba66ULL,
-	0xa103e279970e93d4ULL, 0xbecdec77b0e45e71ULL, 0xcfb41e723985e497ULL,
-	0xb70aaa025ef75017ULL, 0xd42309f03840b8e0ULL, 0x8efc1ad035898579ULL,
-	0x96c6920be2b2abc5ULL, 0x66af4163375a9172ULL, 0x2174abdcca7127fbULL,
-	0xb33ccea64a72ff41ULL, 0xf04a4933083066a5ULL, 0x8d970acdd7289af5ULL,
-	0x8f96e8e031c8c25eULL, 0xf3fec02276875d47ULL, 0xec7bf310056190ddULL,
-	0xf5adb0aebb0f1491ULL, 0x9b50f8850fd58892ULL, 0x4975488358b74de8ULL,
-	0xa3354ff691531c61ULL, 0x0702bbe481d2c6eeULL, 0x89fb24057deded98ULL,
-	0xac3075138596e902ULL, 0x1d2d3580172772edULL, 0xeb738fc28e6bc30dULL,
-	0x5854ef8f63044326ULL, 0x9e5c52325add3bbeULL, 0x90aa53cf325c4623ULL,
-	0xc1d24d51349dd067ULL, 0x2051cfeea69ea624ULL, 0x13220f0a862e7e4fULL,
-	0xce39399404e04864ULL, 0xd9c42ca47086fcb7ULL, 0x685ad2238a03e7ccULL,
-	0x066484b2ab2ff1dbULL, 0xfe9d5d70efbf79ecULL, 0x5b13b9dd9c481854ULL,
-	0x15f0d475ed1509adULL, 0x0bebcd060ec79851ULL, 0xd58c6791183ab7f8ULL,
-	0xd1187c5052f3eee4ULL, 0xc95d1192e54e82ffULL, 0x86eea14cb9ac6ca2ULL,
-	0x3485beb153677d5dULL, 0xdd191d781f8c492aULL, 0xf60866baa784ebf9ULL,
-	0x518f643ba2d08c74ULL, 0x8852e956e1087c22ULL, 0xa768cb8dc410ae8dULL,
-	0x38047726bfec8e1aULL, 0xa67738b4cd3b45aaULL, 0xad16691cec0dde19ULL,
-	0xc6d4319380462e07ULL, 0xc5a5876d0ba61938ULL, 0x16b9fa1fa58fd840ULL,
-	0x188ab1173ca74f18ULL, 0xabda2f98c99c021fULL, 0x3e0580ab134ae816ULL,
-	0x5f3b05b773645abbULL, 0x2501a2be5575f2f6ULL, 0x1b2f74004e7e8ba9ULL,
-	0x1cd7580371e8d953ULL, 0x7f6ed89562764e30ULL, 0xb15926ff596f003dULL,
-	0x9f65293da8c5d6b9ULL, 0x6ecef04dd690f84cULL, 0x4782275fff33af88ULL,
-	0xe41433083f820801ULL, 0xfd0dfe409a1af9b5ULL, 0x4325a3342cdb396bULL,
-	0x8ae77e62b301b252ULL, 0xc36f9e9f6655615aULL, 0x85455a2d92d32c09ULL,
-	0xf2c7dea949477485ULL, 0x63cfb4c133a39ebaULL, 0x83b040cc6ebc5462ULL,
-	0x3b9454c8fdb326b0ULL, 0x56f56a9e87ffd78cULL, 0x2dc2940d99f42bc6ULL,
-	0x98f7df096b096e2dULL, 0x19a6e01e3ad852bfULL, 0x42a99ccbdbd4b40bULL,
-	0xa59998af45e9c559ULL, 0x366295e807d93186ULL, 0x6b48181bfaa1f773ULL,
-	0x1fec57e2157a0a1dULL, 0x4667446af6201ad5ULL, 0xe615ebcacfb0f075ULL,
-	0xb8f31f4f68290778ULL, 0x22713ed6ce22d11eULL, 0x3057c1a72ec3c93bULL,
-	0xcb46acc37c3f1f2fULL, 0xdbb893fd02aaf50eULL, 0x331fd92e600b9fcfULL,
-	0xa498f96148ea3ad6ULL, 0xa8d8426e8b6a83eaULL, 0xa089b274b7735cdcULL,
-	0x87f6b3731e524a11ULL, 0x118808e5cbc96749ULL, 0x9906e4c7b19bd394ULL,
-	0xafed7f7e9b24a20cULL, 0x6509eadeeb3644a7ULL, 0x6c1ef1d3e8ef0edeULL,
-	0xb9c97d43e9798fb4ULL, 0xa2f2d784740c28a3ULL, 0x7b8496476197566fULL,
-	0x7a5be3e6b65f069dULL, 0xf96330ed78be6f10ULL, 0xeee60de77a076a15ULL,
-	0x2b4bee4aa08b9bd0ULL, 0x6a56a63ec7b8894eULL, 0x02121359ba34fef4ULL,
-	0x4cbf99f8283703fcULL, 0x398071350caf30c8ULL, 0xd0a77a89f017687aULL,
-	0xf1c1a9eb9e423569ULL, 0x8c7976282dee8199ULL, 0x5d1737a5dd1f7abdULL,
-	0x4f53433c09a9fa80ULL, 0xfa8b0c53df7ca1d9ULL, 0x3fd9dcbc886ccb77ULL,
-	0xc040917ca91b4720ULL, 0x7dd00142f9d1dcdfULL, 0x8476fc1d4f387b58ULL,
-	0x23f8e7c5f3316503ULL, 0x032a2244e7e37339ULL, 0x5c87a5d750f5a74bULL,
-	0x082b4cc43698992eULL, 0xdf917becb858f63cULL, 0x3270b8fc5bf86ddaULL,
-	0x10ae72bb29b5dd76ULL, 0x576ac94e7700362bULL, 0x1ad112dac61efb8fULL,
-	0x691bc30ec5faa427ULL, 0xff246311cc327143ULL, 0x3142368e30e53206ULL,
-	0x71380e31e02ca396ULL, 0x958d5c960aad76f1ULL, 0xf8d6f430c16da536ULL,
-	0xc8ffd13f1be7e1d2ULL, 0x7578ae66004ddbe1ULL, 0x05833f01067be646ULL,
-	0xbb34b5ad3bfe586dULL, 0x095f34c9a12b97f0ULL, 0x247ab64525d60ca8ULL,
-	0xdcdbc6f3017477d1ULL, 0x4a2e14d4decad24dULL, 0xbdb5e6d9be0a1eebULL,
-	0x2a7e70f7794301abULL, 0xdef42d8a270540fdULL, 0x01078ec0a34c22c1ULL,
-	0xe5de511af4c16387ULL, 0x7ebb3a52bd9a330aULL, 0x77697857aa7d6435ULL,
-	0x004e831603ae4c32ULL, 0xe7a21020ad78e312ULL, 0x9d41a70c6ab420f2ULL,
-	0x28e06c18ea1141e6ULL, 0xd2b28cbd984f6b28ULL, 0x26b75f6c446e9d83ULL,
-	0xba47568c4d418d7fULL, 0xd80badbfe6183d8eULL, 0x0e206d7f5f166044ULL,
-	0xe258a43911cbca3eULL, 0x723a1746b21dc0bcULL, 0xc7caa854f5d7cdd3ULL,
-	0x7cac32883d261d9cULL, 0x7690c26423ba942cULL, 0x17e55524478042b8ULL,
-	0xe0be477656a2389fULL, 0x4d289b5e67ab2da0ULL, 0x44862b9c8fbbfd31ULL,
-	0xb47cc8049d141365ULL, 0x822c1b362b91c793ULL, 0x4eb14655fb13dfd8ULL,
-	0x1ecbba0714e2a97bULL, 0x6143459d5cde5f14ULL, 0x53a8fbf1d5f0ac89ULL,
-	0x97ea04d81c5e5b00ULL, 0x622181a8d4fdb3f3ULL, 0xe9bcd341572a1208ULL,
-	0x1411258643cce58aULL, 0x9144c5fea4c6e0a4ULL, 0x0d33d06565cf620fULL,
-	0x54a48d489f219ca1ULL, 0xc43e5eac6d63c821ULL, 0xa9728b3a72770dafULL,
-	0xd7934e7b20df87efULL, 0xe35503b61a3e86e5ULL, 0xcae321fbc819d504ULL,
-	0x129a50b3ac60bfa6ULL, 0xcd5e68ea7e9fb6c3ULL, 0xb01c90199483b1c7ULL,
-	0x3de93cd5c295376cULL, 0xaed52edf2ab9ad13ULL, 0x2e60f512c0a07884ULL,
-	0xbc3d86a3e36210c9ULL, 0x35269d9b163951ceULL, 0x0c7d6e2ad0cdb5faULL,
-	0x59e86297d87f5733ULL, 0x298ef221898db0e7ULL, 0x55000029d1a5aa7eULL,
-	0x8bc08ae1b5061b45ULL, 0xc2c31c2b6c92703aULL, 0x94cc596baf25ef42ULL,
-	0x0a1d73db22540456ULL, 0x04b6a0f9d9c4179aULL, 0xeffdafa2ae3d3c60ULL,
-	0xf7c8075bb49496c4ULL, 0x9cc5c7141d1cd4e3ULL, 0x78bd1638218e5534ULL,
-	0xb2f11568f850246aULL, 0xedfabcfa9502bc29ULL, 0x796ce5f2da23051bULL,
-	0xaae128b0dc93537cULL, 0x3a493da0ee4b29aeULL, 0xb5df6b2c416895d7ULL,
-	0xfcabbd25122d7f37ULL, 0x70810b58105dc4b1ULL, 0xe10fdd37f7882a90ULL,
-	0x524dcab5518a3f5cULL, 0x3c9e85878451255bULL, 0x4029828119bd34e2ULL,
-	0x74a05b6f5d3ceccbULL, 0xb610021542e13ecaULL, 0x0ff979d12f59e2acULL,
-	0x6037da27e4f9cc50ULL, 0x5e92975a0df1847dULL, 0xd66de190d3e623feULL,
-	0x5032d6b87b568048ULL, 0x9a36b7ce8235216eULL, 0x80272a7a24f64b4aULL,
-	0x93efed8b8c6916f7ULL, 0x37ddbff44cce1555ULL, 0x4b95db5d4b99bd25ULL,
-	0x92d3fda169812fc0ULL, 0xfb1a4a9a90660bb6ULL, 0x730c196946a4b9b2ULL,
-	0x81e289aa7f49da68ULL, 0x64669a0f83b1a05fULL, 0x27b3ff7d9644f48bULL,
-	0xcc6b615c8db675b3ULL, 0x674f20b9bcebbe95ULL, 0x6f31238275655982ULL,
-	0x5ae488713e45cf05ULL, 0xbf619f9954c21157ULL, 0xeabac46040a8eae9ULL,
-	0x454c6fe9f2c0c1cdULL, 0x419cf6496412691cULL, 0xd3dc3bef265b0f70ULL,
-	0x6d0e60f5c3578a9eULL
-};
-
-static const u64 sbox4[256] = {
-	0x5b0e608526323c55ULL, 0x1a46c1a9fa1b59f5ULL, 0xa9e245a17c4c8ffaULL,
-	0x65ca5159db2955d7ULL, 0x05db0a76ce35afc2ULL, 0x81eac77ea9113d45ULL,
-	0x528ef88ab6ac0a0dULL, 0xa09ea253597be3ffULL, 0x430ddfb3ac48cd56ULL,
-	0xc4b3a67af45ce46fULL, 0x4ececfd8fbe2d05eULL, 0x3ef56f10b39935f0ULL,
-	0x0b22d6829cd619c6ULL, 0x17fd460a74df2069ULL, 0x6cf8cc8e8510ed40ULL,
-	0xd6c824bf3a6ecaa7ULL, 0x61243d581a817049ULL, 0x048bacb6bbc163a2ULL,
-	0xd9a38ac27d44cc32ULL, 0x7fddff5baaf410abULL, 0xad6d495aa804824bULL,
-	0xe1a6a74f2d8c9f94ULL, 0xd4f7851235dee8e3ULL, 0xfd4b7f886540d893ULL,
-	0x247c20042aa4bfdaULL, 0x096ea1c517d1327cULL, 0xd56966b4361a6685ULL,
-	0x277da5c31221057dULL, 0x94d59893a43acff7ULL, 0x64f0c51ccdc02281ULL,
-	0x3d33bcc4ff6189dbULL, 0xe005cb184ce66af1ULL, 0xff5ccd1d1db99beaULL,
-	0xb0b854a7fe42980fULL, 0x7bd46a6a718d4b9fULL, 0xd10fa8cc22a5fd8cULL,
-	0xd31484952be4bd31ULL, 0xc7fa975fcb243847ULL, 0x4886ed1e5846c407ULL,
-	0x28cddb791eb70b04ULL, 0xc2b00be2f573417fULL, 0x5c9590452180f877ULL,
-	0x7a6bddfff370eb00ULL, 0xce509e38d6d9d6a4ULL, 0xebeb0f00647fa702ULL,
-	0x1dcc06cf76606f06ULL, 0xe4d9f28ba286ff0aULL, 0xd85a305dc918c262ULL,
-	0x475b1d8732225f54ULL, 0x2d4fb51668ccb5feULL, 0xa679b9d9d72bba20ULL,
-	0x53841c0d912d43a5ULL, 0x3b7eaa48bf12a4e8ULL, 0x781e0e47f22f1ddfULL,
-	0xeff20ce60ab50973ULL, 0x20d261d19dffb742ULL, 0x16a12b03062a2e39ULL,
-	0x1960eb2239650495ULL, 0x251c16fed50eb8b8ULL, 0x9ac0c330f826016eULL,
-	0xed152665953e7671ULL, 0x02d63194a6369570ULL, 0x5074f08394b1c987ULL,
-	0x70ba598c90b25ce1ULL, 0x794a15810b9742f6ULL, 0x0d5925e9fcaf8c6cULL,
-	0x3067716cd868744eULL, 0x910ab077e8d7731bULL, 0x6a61bbdb5ac42f61ULL,
-	0x93513efbf0851567ULL, 0xf494724b9e83e9d5ULL, 0xe887e1985c09648dULL,
-	0x34b1d3c675370cfdULL, 0xdc35e433bc0d255dULL, 0xd0aab84234131be0ULL,
-	0x08042a50b48b7eafULL, 0x9997c4ee44a3ab35ULL, 0x829a7b49201799d0ULL,
-	0x263b8307b7c54441ULL, 0x752f95f4fd6a6ca6ULL, 0x927217402c08c6e5ULL,
-	0x2a8ab754a795d9eeULL, 0xa442f7552f72943dULL, 0x2c31334e19781208ULL,
-	0x4fa98d7ceaee6291ULL, 0x55c3862f665db309ULL, 0xbd0610175d53b1f3ULL,
-	0x46fe6cb840413f27ULL, 0x3fe03792df0cfa59ULL, 0xcfe700372eb85e8fULL,
-	0xa7be29e7adbce118ULL, 0xe544ee5cde8431ddULL, 0x8a781b1b41f1873eULL,
-	0xa5c94c78a0d2f0e7ULL, 0x39412e2877b60728ULL, 0xa1265ef3afc9a62cULL,
-	0xbcc2770c6a2506c5ULL, 0x3ab66dd5dce1ce12ULL, 0xe65499d04a675b37ULL,
-	0x7d8f523481bfd216ULL, 0x0f6f64fcec15f389ULL, 0x74efbe618b5b13c8ULL,
-	0xacdc82b714273e1dULL, 0xdd40bfe003199d17ULL, 0x37e99257e7e061f8ULL,
-	0xfa52626904775aaaULL, 0x8bbbf63a463d56f9ULL, 0xf0013f1543a26e64ULL,
-	0xa8307e9f879ec898ULL, 0xcc4c27a4150177ccULL, 0x1b432f2cca1d3348ULL,
-	0xde1d1f8f9f6fa013ULL, 0x606602a047a7ddd6ULL, 0xd237ab64cc1cb2c7ULL,
-	0x9b938e7225fcd1d3ULL, 0xec4e03708e0ff476ULL, 0xfeb2fbda3d03c12dULL,
-	0xae0bced2ee43889aULL, 0x22cb8923ebfb4f43ULL, 0x69360d013cf7396dULL,
-	0x855e3602d2d4e022ULL, 0x073805bad01f784cULL, 0x33e17a133852f546ULL,
-	0xdf4874058ac7b638ULL, 0xba92b29c678aa14aULL, 0x0ce89fc76cfaadcdULL,
-	0x5f9d4e0908339e34ULL, 0xf1afe9291f5923b9ULL, 0x6e3480f60f4a265fULL,
-	0xeebf3a2ab29b841cULL, 0xe21938a88f91b4adULL, 0x57dfeff845c6d3c3ULL,
-	0x2f006b0bf62caaf2ULL, 0x62f479ef6f75ee78ULL, 0x11a55ad41c8916a9ULL,
-	0xf229d29084fed453ULL, 0x42f1c27b16b000e6ULL, 0x2b1f76749823c074ULL,
-	0x4b76eca3c2745360ULL, 0x8c98f463b91691bdULL, 0x14bcc93cf1ade66aULL,
-	0x8885213e6d458397ULL, 0x8e177df0274d4711ULL, 0xb49b73b5503f2951ULL,
-	0x10168168c3f96b6bULL, 0x0e3d963b63cab0aeULL, 0x8dfc4b5655a1db14ULL,
-	0xf789f1356e14de5cULL, 0x683e68af4e51dac1ULL, 0xc9a84f9d8d4b0fd9ULL,
-	0x3691e03f52a0f9d1ULL, 0x5ed86e46e1878e80ULL, 0x3c711a0e99d07150ULL,
-	0x5a0865b20c4e9310ULL, 0x56fbfc1fe4f0682eULL, 0xea8d5de3105edf9bULL,
-	0x71abfdb12379187aULL, 0x2eb99de1bee77b9cULL, 0x21ecc0ea33cf4523ULL,
-	0x59a4d7521805c7a1ULL, 0x3896f5eb56ae7c72ULL, 0xaa638f3db18f75dcULL,
-	0x9f39358dabe9808eULL, 0xb7defa91c00b72acULL, 0x6b5541fd62492d92ULL,
-	0x6dc6dee8f92e4d5bULL, 0x353f57abc4beea7eULL, 0x735769d6da5690ceULL,
-	0x0a234aa642391484ULL, 0xf6f9508028f80d9dULL, 0xb8e319a27ab3f215ULL,
-	0x31ad9c1151341a4dULL, 0x773c22a57bef5805ULL, 0x45c7561a07968633ULL,
-	0xf913da9e249dbe36ULL, 0xda652d9b78a64c68ULL, 0x4c27a97f3bc334efULL,
-	0x76621220e66b17f4ULL, 0x967743899acd7d0bULL, 0xf3ee5bcae0ed6782ULL,
-	0x409f753600c879fcULL, 0x06d09a39b5926db6ULL, 0x6f83aeb0317ac588ULL,
-	0x01e6ca4a86381f21ULL, 0x66ff3462d19f3025ULL, 0x72207c24ddfd3bfbULL,
-	0x4af6b6d3e2ece2ebULL, 0x9c994dbec7ea08deULL, 0x49ace597b09a8bc4ULL,
-	0xb38c4766cf0797baULL, 0x131b9373c57c2a75ULL, 0xb1822cce61931e58ULL,
-	0x9d7555b909ba1c0cULL, 0x127fafdd937d11d2ULL, 0x29da3badc66d92e4ULL,
-	0xa2c1d57154c2ecbcULL, 0x58c5134d82f6fe24ULL, 0x1c3ae3515b62274fULL,
-	0xe907c82e01cb8126ULL, 0xf8ed091913e37fcbULL, 0x3249d8f9c80046c9ULL,
-	0x80cf9bede388fb63ULL, 0x1881539a116cf19eULL, 0x5103f3f76bd52457ULL,
-	0x15b7e6f5ae47f7a8ULL, 0xdbd7c6ded47e9ccfULL, 0x44e55c410228bb1aULL,
-	0xb647d4255edb4e99ULL, 0x5d11882bb8aafc30ULL, 0xf5098bbb29d3212aULL,
-	0x8fb5ea14e90296b3ULL, 0x677b942157dd025aULL, 0xfb58e7c0a390acb5ULL,
-	0x89d3674c83bd4a01ULL, 0x9e2da4df4bf3b93bULL, 0xfcc41e328cab4829ULL,
-	0x03f38c96ba582c52ULL, 0xcad1bdbd7fd85db2ULL, 0xbbb442c16082ae83ULL,
-	0xb95fe86ba5da9ab0ULL, 0xb22e04673771a93fULL, 0x845358c9493152d8ULL,
-	0xbe2a488697b4541eULL, 0x95a2dc2dd38e6966ULL, 0xc02c11ac923c852bULL,
-	0x2388b1990df2a87bULL, 0x7c8008fa1b4f37beULL, 0x1f70d0c84d54e503ULL,
-	0x5490adec7ece57d4ULL, 0x002b3c27d9063a3aULL, 0x7eaea3848030a2bfULL,
-	0xc602326ded2003c0ULL, 0x83a7287d69a94086ULL, 0xc57a5fcb30f57a8aULL,
-	0xb56844e479ebe779ULL, 0xa373b40f05dcbce9ULL, 0xd71a786e88570ee2ULL,
-	0x879cbacdbde8f6a0ULL, 0x976ad1bcc164a32fULL, 0xab21e25e9666d78bULL,
-	0x901063aae5e5c33cULL, 0x9818b34448698d90ULL, 0xe36487ae3e1e8abbULL,
-	0xafbdf931893bdcb4ULL, 0x6345a0dc5fbbd519ULL, 0x8628fe269b9465caULL,
-	0x1e5d01603f9c51ecULL, 0x4de44006a15049b7ULL, 0xbf6c70e5f776cbb1ULL,
-	0x411218f2ef552bedULL, 0xcb0c0708705a36a3ULL, 0xe74d14754f986044ULL,
-	0xcd56d9430ea8280eULL, 0xc12591d7535f5065ULL, 0xc83223f1720aef96ULL,
-	0xc3a0396f7363a51fULL
-};
-
-
-static void tgr192_round(u64 * ra, u64 * rb, u64 * rc, u64 x, int mul)
-{
-	u64 a = *ra;
-	u64 b = *rb;
-	u64 c = *rc;
-
-	c ^= x;
-	a -= sbox1[c         & 0xff] ^ sbox2[(c >> 16) & 0xff]
-	   ^ sbox3[(c >> 32) & 0xff] ^ sbox4[(c >> 48) & 0xff];
-	b += sbox4[(c >>  8) & 0xff] ^ sbox3[(c >> 24) & 0xff]
-	   ^ sbox2[(c >> 40) & 0xff] ^ sbox1[(c >> 56) & 0xff];
-	b *= mul;
-
-	*ra = a;
-	*rb = b;
-	*rc = c;
-}
-
-
-static void tgr192_pass(u64 * ra, u64 * rb, u64 * rc, u64 * x, int mul)
-{
-	u64 a = *ra;
-	u64 b = *rb;
-	u64 c = *rc;
-
-	tgr192_round(&a, &b, &c, x[0], mul);
-	tgr192_round(&b, &c, &a, x[1], mul);
-	tgr192_round(&c, &a, &b, x[2], mul);
-	tgr192_round(&a, &b, &c, x[3], mul);
-	tgr192_round(&b, &c, &a, x[4], mul);
-	tgr192_round(&c, &a, &b, x[5], mul);
-	tgr192_round(&a, &b, &c, x[6], mul);
-	tgr192_round(&b, &c, &a, x[7], mul);
-
-	*ra = a;
-	*rb = b;
-	*rc = c;
-}
-
-
-static void tgr192_key_schedule(u64 * x)
-{
-	x[0] -= x[7] ^ 0xa5a5a5a5a5a5a5a5ULL;
-	x[1] ^= x[0];
-	x[2] += x[1];
-	x[3] -= x[2] ^ ((~x[1]) << 19);
-	x[4] ^= x[3];
-	x[5] += x[4];
-	x[6] -= x[5] ^ ((~x[4]) >> 23);
-	x[7] ^= x[6];
-	x[0] += x[7];
-	x[1] -= x[0] ^ ((~x[7]) << 19);
-	x[2] ^= x[1];
-	x[3] += x[2];
-	x[4] -= x[3] ^ ((~x[2]) >> 23);
-	x[5] ^= x[4];
-	x[6] += x[5];
-	x[7] -= x[6] ^ 0x0123456789abcdefULL;
-}
-
-
-/****************
- * Transform the message DATA which consists of 512 bytes (8 words)
- */
-
-static void tgr192_transform(struct tgr192_ctx *tctx, const u8 * data)
-{
-	u64 a, b, c, aa, bb, cc;
-	u64 x[8];
-	int i;
-
-	for (i = 0; i < 8; i++)
-		x[i] = get_unaligned_le64(data + i * sizeof(__le64));
-
-	/* save */
-	a = aa = tctx->a;
-	b = bb = tctx->b;
-	c = cc = tctx->c;
-
-	tgr192_pass(&a, &b, &c, x, 5);
-	tgr192_key_schedule(x);
-	tgr192_pass(&c, &a, &b, x, 7);
-	tgr192_key_schedule(x);
-	tgr192_pass(&b, &c, &a, x, 9);
-
-
-	/* feedforward */
-	a ^= aa;
-	b -= bb;
-	c += cc;
-	/* store */
-	tctx->a = a;
-	tctx->b = b;
-	tctx->c = c;
-}
-
-static int tgr192_init(struct shash_desc *desc)
-{
-	struct tgr192_ctx *tctx = shash_desc_ctx(desc);
-
-	tctx->a = 0x0123456789abcdefULL;
-	tctx->b = 0xfedcba9876543210ULL;
-	tctx->c = 0xf096a5b4c3b2e187ULL;
-	tctx->nblocks = 0;
-	tctx->count = 0;
-
-	return 0;
-}
-
-
-/* Update the message digest with the contents
- * of INBUF with length INLEN. */
-static int tgr192_update(struct shash_desc *desc, const u8 *inbuf,
-			  unsigned int len)
-{
-	struct tgr192_ctx *tctx = shash_desc_ctx(desc);
-
-	if (tctx->count == 64) {	/* flush the buffer */
-		tgr192_transform(tctx, tctx->hash);
-		tctx->count = 0;
-		tctx->nblocks++;
-	}
-	if (!inbuf) {
-		return 0;
-	}
-	if (tctx->count) {
-		for (; len && tctx->count < 64; len--) {
-			tctx->hash[tctx->count++] = *inbuf++;
-		}
-		tgr192_update(desc, NULL, 0);
-		if (!len) {
-			return 0;
-		}
-
-	}
-
-	while (len >= 64) {
-		tgr192_transform(tctx, inbuf);
-		tctx->count = 0;
-		tctx->nblocks++;
-		len -= 64;
-		inbuf += 64;
-	}
-	for (; len && tctx->count < 64; len--) {
-		tctx->hash[tctx->count++] = *inbuf++;
-	}
-
-	return 0;
-}
-
-
-
-/* The routine terminates the computation */
-static int tgr192_final(struct shash_desc *desc, u8 * out)
-{
-	struct tgr192_ctx *tctx = shash_desc_ctx(desc);
-	__be64 *dst = (__be64 *)out;
-	__be64 *be64p;
-	__le32 *le32p;
-	u32 t, msb, lsb;
-
-	tgr192_update(desc, NULL, 0); /* flush */
-
-	msb = 0;
-	t = tctx->nblocks;
-	if ((lsb = t << 6) < t) { /* multiply by 64 to make a byte count */
-		msb++;
-	}
-	msb += t >> 26;
-	t = lsb;
-	if ((lsb = t + tctx->count) < t) {	/* add the count */
-		msb++;
-	}
-	t = lsb;
-	if ((lsb = t << 3) < t)	{ /* multiply by 8 to make a bit count */
-		msb++;
-	}
-	msb += t >> 29;
-
-	if (tctx->count < 56) {	/* enough room */
-		tctx->hash[tctx->count++] = 0x01;	/* pad */
-		while (tctx->count < 56) {
-			tctx->hash[tctx->count++] = 0;	/* pad */
-		}
-	} else {		/* need one extra block */
-		tctx->hash[tctx->count++] = 0x01;	/* pad character */
-		while (tctx->count < 64) {
-			tctx->hash[tctx->count++] = 0;
-		}
-		tgr192_update(desc, NULL, 0); /* flush */
-		memset(tctx->hash, 0, 56);    /* fill next block with zeroes */
-	}
-	/* append the 64 bit count */
-	le32p = (__le32 *)&tctx->hash[56];
-	le32p[0] = cpu_to_le32(lsb);
-	le32p[1] = cpu_to_le32(msb);
-
-	tgr192_transform(tctx, tctx->hash);
-
-	be64p = (__be64 *)tctx->hash;
-	dst[0] = be64p[0] = cpu_to_be64(tctx->a);
-	dst[1] = be64p[1] = cpu_to_be64(tctx->b);
-	dst[2] = be64p[2] = cpu_to_be64(tctx->c);
-
-	return 0;
-}
-
-static int tgr160_final(struct shash_desc *desc, u8 * out)
-{
-	u8 D[64];
-
-	tgr192_final(desc, D);
-	memcpy(out, D, TGR160_DIGEST_SIZE);
-	memzero_explicit(D, TGR192_DIGEST_SIZE);
-
-	return 0;
-}
-
-static int tgr128_final(struct shash_desc *desc, u8 * out)
-{
-	u8 D[64];
-
-	tgr192_final(desc, D);
-	memcpy(out, D, TGR128_DIGEST_SIZE);
-	memzero_explicit(D, TGR192_DIGEST_SIZE);
-
-	return 0;
-}
-
-static struct shash_alg tgr_algs[3] = { {
-	.digestsize	=	TGR192_DIGEST_SIZE,
-	.init		=	tgr192_init,
-	.update		=	tgr192_update,
-	.final		=	tgr192_final,
-	.descsize	=	sizeof(struct tgr192_ctx),
-	.base		=	{
-		.cra_name	 =	"tgr192",
-		.cra_driver_name =	"tgr192-generic",
-		.cra_blocksize	 =	TGR192_BLOCK_SIZE,
-		.cra_module	 =	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	TGR160_DIGEST_SIZE,
-	.init		=	tgr192_init,
-	.update		=	tgr192_update,
-	.final		=	tgr160_final,
-	.descsize	=	sizeof(struct tgr192_ctx),
-	.base		=	{
-		.cra_name	 =	"tgr160",
-		.cra_driver_name =	"tgr160-generic",
-		.cra_blocksize	 =	TGR192_BLOCK_SIZE,
-		.cra_module	 =	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	TGR128_DIGEST_SIZE,
-	.init		=	tgr192_init,
-	.update		=	tgr192_update,
-	.final		=	tgr128_final,
-	.descsize	=	sizeof(struct tgr192_ctx),
-	.base		=	{
-		.cra_name	 =	"tgr128",
-		.cra_driver_name =	"tgr128-generic",
-		.cra_blocksize	 =	TGR192_BLOCK_SIZE,
-		.cra_module	 =	THIS_MODULE,
-	}
-} };
-
-static int __init tgr192_mod_init(void)
-{
-	return crypto_register_shashes(tgr_algs, ARRAY_SIZE(tgr_algs));
-}
-
-static void __exit tgr192_mod_fini(void)
-{
-	crypto_unregister_shashes(tgr_algs, ARRAY_SIZE(tgr_algs));
-}
-
-MODULE_ALIAS_CRYPTO("tgr192");
-MODULE_ALIAS_CRYPTO("tgr160");
-MODULE_ALIAS_CRYPTO("tgr128");
-
-subsys_initcall(tgr192_mod_init);
-module_exit(tgr192_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Tiger Message Digest Algorithm");
diff --git a/crypto/twofish_generic.c b/crypto/twofish_generic.c
index 4f7c033224f9..86b2f067a416 100644
--- a/crypto/twofish_generic.c
+++ b/crypto/twofish_generic.c
@@ -24,7 +24,7 @@
  * Third Edition.
  */
 
-#include <asm/byteorder.h>
+#include <asm/unaligned.h>
 #include <crypto/twofish.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -83,11 +83,11 @@
  * whitening subkey number m. */
 
 #define INPACK(n, x, m) \
-   x = le32_to_cpu(src[n]) ^ ctx->w[m]
+   x = get_unaligned_le32(in + (n) * 4) ^ ctx->w[m]
 
 #define OUTUNPACK(n, x, m) \
    x ^= ctx->w[m]; \
-   dst[n] = cpu_to_le32(x)
+   put_unaligned_le32(x, out + (n) * 4)
 
 
 
@@ -95,8 +95,6 @@
 static void twofish_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	struct twofish_ctx *ctx = crypto_tfm_ctx(tfm);
-	const __le32 *src = (const __le32 *)in;
-	__le32 *dst = (__le32 *)out;
 
 	/* The four 32-bit chunks of the text. */
 	u32 a, b, c, d;
@@ -132,8 +130,6 @@ static void twofish_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 static void twofish_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	struct twofish_ctx *ctx = crypto_tfm_ctx(tfm);
-	const __le32 *src = (const __le32 *)in;
-	__le32 *dst = (__le32 *)out;
   
 	/* The four 32-bit chunks of the text. */
 	u32 a, b, c, d;
@@ -172,7 +168,6 @@ static struct crypto_alg alg = {
 	.cra_flags          =   CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize      =   TF_BLOCK_SIZE,
 	.cra_ctxsize        =   sizeof(struct twofish_ctx),
-	.cra_alignmask      =	3,
 	.cra_module         =   THIS_MODULE,
 	.cra_u              =   { .cipher = {
 	.cia_min_keysize    =   TF_MIN_KEY_SIZE,
diff --git a/crypto/vmac.c b/crypto/vmac.c
index 9b565d1040d6..4633b2dda1e0 100644
--- a/crypto/vmac.c
+++ b/crypto/vmac.c
@@ -36,6 +36,7 @@
 #include <linux/scatterlist.h>
 #include <asm/byteorder.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/hash.h>
 
 /*
@@ -693,3 +694,4 @@ module_exit(vmac_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("VMAC hash algorithm");
 MODULE_ALIAS_CRYPTO("vmac64");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/xcbc.c b/crypto/xcbc.c
index af3b7eb5d7c7..6074c5c1da49 100644
--- a/crypto/xcbc.c
+++ b/crypto/xcbc.c
@@ -6,6 +6,7 @@
  * 	Kazunori Miyazawa <miyazawa@linux-ipv6.org>
  */
 
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/hash.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -272,3 +273,4 @@ module_exit(crypto_xcbc_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("XCBC keyed hash algorithm");
 MODULE_ALIAS_CRYPTO("xcbc");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/crypto/xor.c b/crypto/xor.c
index 8f899f898ec9..8e72e5d5db0d 100644
--- a/crypto/xor.c
+++ b/crypto/xor.c
@@ -95,7 +95,7 @@ do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
 	for (i = 0; i < 3; i++) {
 		start = ktime_get();
 		for (j = 0; j < REPS; j++) {
-			mb(); /* prevent loop optimzation */
+			mb(); /* prevent loop optimization */
 			tmpl->do_2(BENCH_SIZE, b1, b2);
 			mb();
 		}
diff --git a/crypto/xts.c b/crypto/xts.c
index ad45b009774b..6c12f30dbdd6 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -7,6 +7,7 @@
  * Based on ecb.c
  * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
  */
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/err.h>
@@ -464,3 +465,4 @@ module_exit(xts_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("XTS block cipher mode");
 MODULE_ALIAS_CRYPTO("xts");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/drivers/char/hw_random/ingenic-trng.c b/drivers/char/hw_random/ingenic-trng.c
index 954a8411d67d..0eb80f786f4d 100644
--- a/drivers/char/hw_random/ingenic-trng.c
+++ b/drivers/char/hw_random/ingenic-trng.c
@@ -113,13 +113,17 @@ static int ingenic_trng_probe(struct platform_device *pdev)
 	ret = hwrng_register(&trng->rng);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to register hwrng\n");
-		return ret;
+		goto err_unprepare_clk;
 	}
 
 	platform_set_drvdata(pdev, trng);
 
 	dev_info(&pdev->dev, "Ingenic DTRNG driver registered\n");
 	return 0;
+
+err_unprepare_clk:
+	clk_disable_unprepare(trng->clk);
+	return ret;
 }
 
 static int ingenic_trng_remove(struct platform_device *pdev)
diff --git a/drivers/char/hw_random/iproc-rng200.c b/drivers/char/hw_random/iproc-rng200.c
index 01583faf9893..a43743887db1 100644
--- a/drivers/char/hw_random/iproc-rng200.c
+++ b/drivers/char/hw_random/iproc-rng200.c
@@ -28,7 +28,6 @@
 #define RNG_CTRL_OFFSET					0x00
 #define RNG_CTRL_RNG_RBGEN_MASK				0x00001FFF
 #define RNG_CTRL_RNG_RBGEN_ENABLE			0x00000001
-#define RNG_CTRL_RNG_RBGEN_DISABLE			0x00000000
 
 #define RNG_SOFT_RESET_OFFSET				0x04
 #define RNG_SOFT_RESET					0x00000001
@@ -54,15 +53,24 @@ struct iproc_rng200_dev {
 
 #define to_rng_priv(rng)	container_of(rng, struct iproc_rng200_dev, rng)
 
-static void iproc_rng200_restart(void __iomem *rng_base)
+static void iproc_rng200_enable_set(void __iomem *rng_base, bool enable)
 {
-	uint32_t val;
+	u32 val;
 
-	/* Disable RBG */
 	val = ioread32(rng_base + RNG_CTRL_OFFSET);
 	val &= ~RNG_CTRL_RNG_RBGEN_MASK;
-	val |= RNG_CTRL_RNG_RBGEN_DISABLE;
+
+	if (enable)
+		val |= RNG_CTRL_RNG_RBGEN_ENABLE;
+
 	iowrite32(val, rng_base + RNG_CTRL_OFFSET);
+}
+
+static void iproc_rng200_restart(void __iomem *rng_base)
+{
+	uint32_t val;
+
+	iproc_rng200_enable_set(rng_base, false);
 
 	/* Clear all interrupt status */
 	iowrite32(0xFFFFFFFFUL, rng_base + RNG_INT_STATUS_OFFSET);
@@ -84,11 +92,7 @@ static void iproc_rng200_restart(void __iomem *rng_base)
 	val &= ~RBG_SOFT_RESET;
 	iowrite32(val, rng_base + RBG_SOFT_RESET_OFFSET);
 
-	/* Enable RBG */
-	val = ioread32(rng_base + RNG_CTRL_OFFSET);
-	val &= ~RNG_CTRL_RNG_RBGEN_MASK;
-	val |= RNG_CTRL_RNG_RBGEN_ENABLE;
-	iowrite32(val, rng_base + RNG_CTRL_OFFSET);
+	iproc_rng200_enable_set(rng_base, true);
 }
 
 static int iproc_rng200_read(struct hwrng *rng, void *buf, size_t max,
@@ -155,13 +159,8 @@ static int iproc_rng200_read(struct hwrng *rng, void *buf, size_t max,
 static int iproc_rng200_init(struct hwrng *rng)
 {
 	struct iproc_rng200_dev *priv = to_rng_priv(rng);
-	uint32_t val;
 
-	/* Setup RNG. */
-	val = ioread32(priv->base + RNG_CTRL_OFFSET);
-	val &= ~RNG_CTRL_RNG_RBGEN_MASK;
-	val |= RNG_CTRL_RNG_RBGEN_ENABLE;
-	iowrite32(val, priv->base + RNG_CTRL_OFFSET);
+	iproc_rng200_enable_set(priv->base, true);
 
 	return 0;
 }
@@ -169,13 +168,8 @@ static int iproc_rng200_init(struct hwrng *rng)
 static void iproc_rng200_cleanup(struct hwrng *rng)
 {
 	struct iproc_rng200_dev *priv = to_rng_priv(rng);
-	uint32_t val;
 
-	/* Disable RNG hardware */
-	val = ioread32(priv->base + RNG_CTRL_OFFSET);
-	val &= ~RNG_CTRL_RNG_RBGEN_MASK;
-	val |= RNG_CTRL_RNG_RBGEN_DISABLE;
-	iowrite32(val, priv->base + RNG_CTRL_OFFSET);
+	iproc_rng200_enable_set(priv->base, false);
 }
 
 static int iproc_rng200_probe(struct platform_device *pdev)
diff --git a/drivers/char/hw_random/optee-rng.c b/drivers/char/hw_random/optee-rng.c
index a99d82949981..135a82590923 100644
--- a/drivers/char/hw_random/optee-rng.c
+++ b/drivers/char/hw_random/optee-rng.c
@@ -243,7 +243,7 @@ static int optee_rng_probe(struct device *dev)
 	if (err)
 		goto out_sess;
 
-	err = hwrng_register(&pvt_data.optee_rng);
+	err = devm_hwrng_register(dev, &pvt_data.optee_rng);
 	if (err) {
 		dev_err(dev, "hwrng registration failed (%d)\n", err);
 		goto out_sess;
@@ -263,7 +263,6 @@ out_ctx:
 
 static int optee_rng_remove(struct device *dev)
 {
-	hwrng_unregister(&pvt_data.optee_rng);
 	tee_client_close_session(pvt_data.ctx, pvt_data.session_id);
 	tee_client_close_context(pvt_data.ctx);
 
diff --git a/drivers/char/hw_random/timeriomem-rng.c b/drivers/char/hw_random/timeriomem-rng.c
index e262445fed5f..8ea1fc831eb7 100644
--- a/drivers/char/hw_random/timeriomem-rng.c
+++ b/drivers/char/hw_random/timeriomem-rng.c
@@ -69,7 +69,7 @@ static int timeriomem_rng_read(struct hwrng *hwrng, void *data,
 		 */
 		if (retval > 0)
 			usleep_range(period_us,
-					period_us + min(1, period_us / 100));
+					period_us + max(1, period_us / 100));
 
 		*(u32 *)data = readl(priv->io_base);
 		retval += sizeof(u32);
@@ -169,7 +169,7 @@ static int timeriomem_rng_probe(struct platform_device *pdev)
 	priv->present = 1;
 	complete(&priv->completion);
 
-	err = hwrng_register(&priv->rng_ops);
+	err = devm_hwrng_register(&pdev->dev, &priv->rng_ops);
 	if (err) {
 		dev_err(&pdev->dev, "problem registering\n");
 		return err;
@@ -185,7 +185,6 @@ static int timeriomem_rng_remove(struct platform_device *pdev)
 {
 	struct timeriomem_rng_private *priv = platform_get_drvdata(pdev);
 
-	hwrng_unregister(&priv->rng_ops);
 	hrtimer_cancel(&priv->timer);
 
 	return 0;
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index e535f28a8028..9a4c275a1335 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -348,7 +348,7 @@ config CRYPTO_DEV_PPC4XX
 
 config HW_RANDOM_PPC4XX
 	bool "PowerPC 4xx generic true random number generator support"
-	depends on CRYPTO_DEV_PPC4XX && HW_RANDOM
+	depends on CRYPTO_DEV_PPC4XX && HW_RANDOM=y
 	default y
 	help
 	 This option provides the kernel-side support for the TRNG hardware
@@ -404,24 +404,6 @@ config CRYPTO_DEV_OMAP_DES
 
 endif # CRYPTO_DEV_OMAP
 
-config CRYPTO_DEV_PICOXCELL
-	tristate "Support for picoXcell IPSEC and Layer2 crypto engines"
-	depends on (ARCH_PICOXCELL || COMPILE_TEST) && HAVE_CLK
-	select CRYPTO_AEAD
-	select CRYPTO_AES
-	select CRYPTO_AUTHENC
-	select CRYPTO_SKCIPHER
-	select CRYPTO_LIB_DES
-	select CRYPTO_CBC
-	select CRYPTO_ECB
-	select CRYPTO_SEQIV
-	help
-	  This option enables support for the hardware offload engines in the
-	  Picochip picoXcell SoC devices. Select this for IPSEC ESP offload
-	  and for 3gpp Layer 2 ciphering support.
-
-	  Saying m here will build a module named picoxcell_crypto.
-
 config CRYPTO_DEV_SAHARA
 	tristate "Support for SAHARA crypto accelerator"
 	depends on ARCH_MXC && OF
@@ -773,21 +755,6 @@ config CRYPTO_DEV_ZYNQMP_AES
 	  accelerator. Select this if you want to use the ZynqMP module
 	  for AES algorithms.
 
-config CRYPTO_DEV_MEDIATEK
-	tristate "MediaTek's EIP97 Cryptographic Engine driver"
-	depends on (ARM && ARCH_MEDIATEK) || COMPILE_TEST
-	select CRYPTO_LIB_AES
-	select CRYPTO_AEAD
-	select CRYPTO_SKCIPHER
-	select CRYPTO_SHA1
-	select CRYPTO_SHA256
-	select CRYPTO_SHA512
-	select CRYPTO_HMAC
-	help
-	  This driver allows you to utilize the hardware crypto accelerator
-	  EIP97 which can be found on the MT7623 MT2701, MT8521p, etc ....
-	  Select this if you want to use it for AES/SHA1/SHA2 algorithms.
-
 source "drivers/crypto/chelsio/Kconfig"
 
 source "drivers/crypto/virtio/Kconfig"
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index fff9a70348e1..fa22cb19e242 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_CRYPTO_DEV_HIFN_795X) += hifn_795x.o
 obj-$(CONFIG_CRYPTO_DEV_IMGTEC_HASH) += img-hash.o
 obj-$(CONFIG_CRYPTO_DEV_IXP4XX) += ixp4xx_crypto.o
 obj-$(CONFIG_CRYPTO_DEV_MARVELL) += marvell/
-obj-$(CONFIG_CRYPTO_DEV_MEDIATEK) += mediatek/
 obj-$(CONFIG_CRYPTO_DEV_MXS_DCP) += mxs-dcp.o
 obj-$(CONFIG_CRYPTO_DEV_NIAGARA2) += n2_crypto.o
 n2_crypto-y := n2_core.o n2_asm.o
@@ -31,7 +30,6 @@ obj-$(CONFIG_CRYPTO_DEV_OMAP_DES) += omap-des.o
 obj-$(CONFIG_CRYPTO_DEV_OMAP_SHAM) += omap-sham.o
 obj-$(CONFIG_CRYPTO_DEV_PADLOCK_AES) += padlock-aes.o
 obj-$(CONFIG_CRYPTO_DEV_PADLOCK_SHA) += padlock-sha.o
-obj-$(CONFIG_CRYPTO_DEV_PICOXCELL) += picoxcell_crypto.o
 obj-$(CONFIG_CRYPTO_DEV_PPC4XX) += amcc/
 obj-$(CONFIG_CRYPTO_DEV_QAT) += qat/
 obj-$(CONFIG_CRYPTO_DEV_QCE) += qce/
diff --git a/drivers/crypto/allwinner/Kconfig b/drivers/crypto/allwinner/Kconfig
index 180c8a9db819..856fb2045656 100644
--- a/drivers/crypto/allwinner/Kconfig
+++ b/drivers/crypto/allwinner/Kconfig
@@ -32,6 +32,15 @@ config CRYPTO_DEV_SUN4I_SS_PRNG
 	  Select this option if you want to provide kernel-side support for
 	  the Pseudo-Random Number Generator found in the Security System.
 
+config CRYPTO_DEV_SUN4I_SS_DEBUG
+	bool "Enable sun4i-ss stats"
+	depends on CRYPTO_DEV_SUN4I_SS
+	depends on DEBUG_FS
+	help
+	  Say y to enable sun4i-ss debug stats.
+	  This will create /sys/kernel/debug/sun4i-ss/stats for displaying
+	  the number of requests per algorithm.
+
 config CRYPTO_DEV_SUN8I_CE
 	tristate "Support for Allwinner Crypto Engine cryptographic offloader"
 	select CRYPTO_SKCIPHER
diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c
index b72de8939497..c2e6f5ed1d79 100644
--- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c
@@ -20,6 +20,7 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq)
 	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
 	struct sun4i_cipher_req_ctx *ctx = skcipher_request_ctx(areq);
 	u32 mode = ctx->mode;
+	void *backup_iv = NULL;
 	/* when activating SS, the default FIFO space is SS_RX_DEFAULT(32) */
 	u32 rx_cnt = SS_RX_DEFAULT;
 	u32 tx_cnt = 0;
@@ -30,9 +31,13 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq)
 	unsigned int ileft = areq->cryptlen;
 	unsigned int oleft = areq->cryptlen;
 	unsigned int todo;
+	unsigned long pi = 0, po = 0; /* progress for in and out */
+	bool miter_err;
 	struct sg_mapping_iter mi, mo;
 	unsigned int oi, oo; /* offset for in and out */
 	unsigned long flags;
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct sun4i_ss_alg_template *algt;
 
 	if (!areq->cryptlen)
 		return 0;
@@ -42,52 +47,77 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq)
 		return -EINVAL;
 	}
 
+	if (areq->iv && ivsize > 0 && mode & SS_DECRYPTION) {
+		backup_iv = kzalloc(ivsize, GFP_KERNEL);
+		if (!backup_iv)
+			return -ENOMEM;
+		scatterwalk_map_and_copy(backup_iv, areq->src, areq->cryptlen - ivsize, ivsize, 0);
+	}
+
+	if (IS_ENABLED(CONFIG_CRYPTO_DEV_SUN4I_SS_DEBUG)) {
+		algt = container_of(alg, struct sun4i_ss_alg_template, alg.crypto);
+		algt->stat_opti++;
+		algt->stat_bytes += areq->cryptlen;
+	}
+
 	spin_lock_irqsave(&ss->slock, flags);
 
-	for (i = 0; i < op->keylen; i += 4)
-		writel(*(op->key + i / 4), ss->base + SS_KEY0 + i);
+	for (i = 0; i < op->keylen / 4; i++)
+		writesl(ss->base + SS_KEY0 + i * 4, &op->key[i], 1);
 
 	if (areq->iv) {
 		for (i = 0; i < 4 && i < ivsize / 4; i++) {
 			v = *(u32 *)(areq->iv + i * 4);
-			writel(v, ss->base + SS_IV0 + i * 4);
+			writesl(ss->base + SS_IV0 + i * 4, &v, 1);
 		}
 	}
 	writel(mode, ss->base + SS_CTL);
 
-	sg_miter_start(&mi, areq->src, sg_nents(areq->src),
-		       SG_MITER_FROM_SG | SG_MITER_ATOMIC);
-	sg_miter_start(&mo, areq->dst, sg_nents(areq->dst),
-		       SG_MITER_TO_SG | SG_MITER_ATOMIC);
-	sg_miter_next(&mi);
-	sg_miter_next(&mo);
-	if (!mi.addr || !mo.addr) {
-		dev_err_ratelimited(ss->dev, "ERROR: sg_miter return null\n");
-		err = -EINVAL;
-		goto release_ss;
-	}
 
 	ileft = areq->cryptlen / 4;
 	oleft = areq->cryptlen / 4;
 	oi = 0;
 	oo = 0;
 	do {
-		todo = min(rx_cnt, ileft);
-		todo = min_t(size_t, todo, (mi.length - oi) / 4);
-		if (todo) {
-			ileft -= todo;
-			writesl(ss->base + SS_RXFIFO, mi.addr + oi, todo);
-			oi += todo * 4;
-		}
-		if (oi == mi.length) {
-			sg_miter_next(&mi);
-			oi = 0;
+		if (ileft) {
+			sg_miter_start(&mi, areq->src, sg_nents(areq->src),
+					SG_MITER_FROM_SG | SG_MITER_ATOMIC);
+			if (pi)
+				sg_miter_skip(&mi, pi);
+			miter_err = sg_miter_next(&mi);
+			if (!miter_err || !mi.addr) {
+				dev_err_ratelimited(ss->dev, "ERROR: sg_miter return null\n");
+				err = -EINVAL;
+				goto release_ss;
+			}
+			todo = min(rx_cnt, ileft);
+			todo = min_t(size_t, todo, (mi.length - oi) / 4);
+			if (todo) {
+				ileft -= todo;
+				writesl(ss->base + SS_RXFIFO, mi.addr + oi, todo);
+				oi += todo * 4;
+			}
+			if (oi == mi.length) {
+				pi += mi.length;
+				oi = 0;
+			}
+			sg_miter_stop(&mi);
 		}
 
 		spaces = readl(ss->base + SS_FCSR);
 		rx_cnt = SS_RXFIFO_SPACES(spaces);
 		tx_cnt = SS_TXFIFO_SPACES(spaces);
 
+		sg_miter_start(&mo, areq->dst, sg_nents(areq->dst),
+			       SG_MITER_TO_SG | SG_MITER_ATOMIC);
+		if (po)
+			sg_miter_skip(&mo, po);
+		miter_err = sg_miter_next(&mo);
+		if (!miter_err || !mo.addr) {
+			dev_err_ratelimited(ss->dev, "ERROR: sg_miter return null\n");
+			err = -EINVAL;
+			goto release_ss;
+		}
 		todo = min(tx_cnt, oleft);
 		todo = min_t(size_t, todo, (mo.length - oo) / 4);
 		if (todo) {
@@ -96,33 +126,41 @@ static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq)
 			oo += todo * 4;
 		}
 		if (oo == mo.length) {
-			sg_miter_next(&mo);
 			oo = 0;
+			po += mo.length;
 		}
+		sg_miter_stop(&mo);
 	} while (oleft);
 
 	if (areq->iv) {
-		for (i = 0; i < 4 && i < ivsize / 4; i++) {
-			v = readl(ss->base + SS_IV0 + i * 4);
-			*(u32 *)(areq->iv + i * 4) = v;
+		if (mode & SS_DECRYPTION) {
+			memcpy(areq->iv, backup_iv, ivsize);
+			kfree_sensitive(backup_iv);
+		} else {
+			scatterwalk_map_and_copy(areq->iv, areq->dst, areq->cryptlen - ivsize,
+						 ivsize, 0);
 		}
 	}
 
 release_ss:
-	sg_miter_stop(&mi);
-	sg_miter_stop(&mo);
 	writel(0, ss->base + SS_CTL);
 	spin_unlock_irqrestore(&ss->slock, flags);
 	return err;
 }
 
-
 static int noinline_for_stack sun4i_ss_cipher_poll_fallback(struct skcipher_request *areq)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
 	struct sun4i_tfm_ctx *op = crypto_skcipher_ctx(tfm);
 	struct sun4i_cipher_req_ctx *ctx = skcipher_request_ctx(areq);
 	int err;
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct sun4i_ss_alg_template *algt;
+
+	if (IS_ENABLED(CONFIG_CRYPTO_DEV_SUN4I_SS_DEBUG)) {
+		algt = container_of(alg, struct sun4i_ss_alg_template, alg.crypto);
+		algt->stat_fb++;
+	}
 
 	skcipher_request_set_tfm(&ctx->fallback_req, op->fallback_tfm);
 	skcipher_request_set_callback(&ctx->fallback_req, areq->base.flags,
@@ -161,13 +199,16 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 	unsigned int ileft = areq->cryptlen;
 	unsigned int oleft = areq->cryptlen;
 	unsigned int todo;
+	void *backup_iv = NULL;
 	struct sg_mapping_iter mi, mo;
+	unsigned long pi = 0, po = 0; /* progress for in and out */
+	bool miter_err;
 	unsigned int oi, oo;	/* offset for in and out */
 	unsigned int ob = 0;	/* offset in buf */
 	unsigned int obo = 0;	/* offset in bufo*/
 	unsigned int obl = 0;	/* length of data in bufo */
 	unsigned long flags;
-	bool need_fallback;
+	bool need_fallback = false;
 
 	if (!areq->cryptlen)
 		return 0;
@@ -186,12 +227,12 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 	 * we can use the SS optimized function
 	 */
 	while (in_sg && no_chunk == 1) {
-		if (in_sg->length % 4)
+		if ((in_sg->length | in_sg->offset) & 3u)
 			no_chunk = 0;
 		in_sg = sg_next(in_sg);
 	}
 	while (out_sg && no_chunk == 1) {
-		if (out_sg->length % 4)
+		if ((out_sg->length | out_sg->offset) & 3u)
 			no_chunk = 0;
 		out_sg = sg_next(out_sg);
 	}
@@ -202,30 +243,31 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 	if (need_fallback)
 		return sun4i_ss_cipher_poll_fallback(areq);
 
+	if (areq->iv && ivsize > 0 && mode & SS_DECRYPTION) {
+		backup_iv = kzalloc(ivsize, GFP_KERNEL);
+		if (!backup_iv)
+			return -ENOMEM;
+		scatterwalk_map_and_copy(backup_iv, areq->src, areq->cryptlen - ivsize, ivsize, 0);
+	}
+
+	if (IS_ENABLED(CONFIG_CRYPTO_DEV_SUN4I_SS_DEBUG)) {
+		algt->stat_req++;
+		algt->stat_bytes += areq->cryptlen;
+	}
+
 	spin_lock_irqsave(&ss->slock, flags);
 
-	for (i = 0; i < op->keylen; i += 4)
-		writel(*(op->key + i / 4), ss->base + SS_KEY0 + i);
+	for (i = 0; i < op->keylen / 4; i++)
+		writesl(ss->base + SS_KEY0 + i * 4, &op->key[i], 1);
 
 	if (areq->iv) {
 		for (i = 0; i < 4 && i < ivsize / 4; i++) {
 			v = *(u32 *)(areq->iv + i * 4);
-			writel(v, ss->base + SS_IV0 + i * 4);
+			writesl(ss->base + SS_IV0 + i * 4, &v, 1);
 		}
 	}
 	writel(mode, ss->base + SS_CTL);
 
-	sg_miter_start(&mi, areq->src, sg_nents(areq->src),
-		       SG_MITER_FROM_SG | SG_MITER_ATOMIC);
-	sg_miter_start(&mo, areq->dst, sg_nents(areq->dst),
-		       SG_MITER_TO_SG | SG_MITER_ATOMIC);
-	sg_miter_next(&mi);
-	sg_miter_next(&mo);
-	if (!mi.addr || !mo.addr) {
-		dev_err_ratelimited(ss->dev, "ERROR: sg_miter return null\n");
-		err = -EINVAL;
-		goto release_ss;
-	}
 	ileft = areq->cryptlen;
 	oleft = areq->cryptlen;
 	oi = 0;
@@ -233,8 +275,16 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 
 	while (oleft) {
 		if (ileft) {
-			char buf[4 * SS_RX_MAX];/* buffer for linearize SG src */
-
+			sg_miter_start(&mi, areq->src, sg_nents(areq->src),
+				       SG_MITER_FROM_SG | SG_MITER_ATOMIC);
+			if (pi)
+				sg_miter_skip(&mi, pi);
+			miter_err = sg_miter_next(&mi);
+			if (!miter_err || !mi.addr) {
+				dev_err_ratelimited(ss->dev, "ERROR: sg_miter return null\n");
+				err = -EINVAL;
+				goto release_ss;
+			}
 			/*
 			 * todo is the number of consecutive 4byte word that we
 			 * can read from current SG
@@ -256,52 +306,57 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 				 */
 				todo = min(rx_cnt * 4 - ob, ileft);
 				todo = min_t(size_t, todo, mi.length - oi);
-				memcpy(buf + ob, mi.addr + oi, todo);
+				memcpy(ss->buf + ob, mi.addr + oi, todo);
 				ileft -= todo;
 				oi += todo;
 				ob += todo;
 				if (!(ob % 4)) {
-					writesl(ss->base + SS_RXFIFO, buf,
+					writesl(ss->base + SS_RXFIFO, ss->buf,
 						ob / 4);
 					ob = 0;
 				}
 			}
 			if (oi == mi.length) {
-				sg_miter_next(&mi);
+				pi += mi.length;
 				oi = 0;
 			}
+			sg_miter_stop(&mi);
 		}
 
 		spaces = readl(ss->base + SS_FCSR);
 		rx_cnt = SS_RXFIFO_SPACES(spaces);
 		tx_cnt = SS_TXFIFO_SPACES(spaces);
-		dev_dbg(ss->dev,
-			"%x %u/%zu %u/%u cnt=%u %u/%zu %u/%u cnt=%u %u\n",
-			mode,
-			oi, mi.length, ileft, areq->cryptlen, rx_cnt,
-			oo, mo.length, oleft, areq->cryptlen, tx_cnt, ob);
 
 		if (!tx_cnt)
 			continue;
+		sg_miter_start(&mo, areq->dst, sg_nents(areq->dst),
+			       SG_MITER_TO_SG | SG_MITER_ATOMIC);
+		if (po)
+			sg_miter_skip(&mo, po);
+		miter_err = sg_miter_next(&mo);
+		if (!miter_err || !mo.addr) {
+			dev_err_ratelimited(ss->dev, "ERROR: sg_miter return null\n");
+			err = -EINVAL;
+			goto release_ss;
+		}
 		/* todo in 4bytes word */
 		todo = min(tx_cnt, oleft / 4);
 		todo = min_t(size_t, todo, (mo.length - oo) / 4);
+
 		if (todo) {
 			readsl(ss->base + SS_TXFIFO, mo.addr + oo, todo);
 			oleft -= todo * 4;
 			oo += todo * 4;
 			if (oo == mo.length) {
-				sg_miter_next(&mo);
+				po += mo.length;
 				oo = 0;
 			}
 		} else {
-			char bufo[4 * SS_TX_MAX]; /* buffer for linearize SG dst */
-
 			/*
 			 * read obl bytes in bufo, we read at maximum for
 			 * emptying the device
 			 */
-			readsl(ss->base + SS_TXFIFO, bufo, tx_cnt);
+			readsl(ss->base + SS_TXFIFO, ss->bufo, tx_cnt);
 			obl = tx_cnt * 4;
 			obo = 0;
 			do {
@@ -313,28 +368,31 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 				 */
 				todo = min_t(size_t,
 					     mo.length - oo, obl - obo);
-				memcpy(mo.addr + oo, bufo + obo, todo);
+				memcpy(mo.addr + oo, ss->bufo + obo, todo);
 				oleft -= todo;
 				obo += todo;
 				oo += todo;
 				if (oo == mo.length) {
+					po += mo.length;
 					sg_miter_next(&mo);
 					oo = 0;
 				}
 			} while (obo < obl);
 			/* bufo must be fully used here */
 		}
+		sg_miter_stop(&mo);
 	}
 	if (areq->iv) {
-		for (i = 0; i < 4 && i < ivsize / 4; i++) {
-			v = readl(ss->base + SS_IV0 + i * 4);
-			*(u32 *)(areq->iv + i * 4) = v;
+		if (mode & SS_DECRYPTION) {
+			memcpy(areq->iv, backup_iv, ivsize);
+			kfree_sensitive(backup_iv);
+		} else {
+			scatterwalk_map_and_copy(areq->iv, areq->dst, areq->cryptlen - ivsize,
+						 ivsize, 0);
 		}
 	}
 
 release_ss:
-	sg_miter_stop(&mi);
-	sg_miter_stop(&mo);
 	writel(0, ss->base + SS_CTL);
 	spin_unlock_irqrestore(&ss->slock, flags);
 
@@ -503,7 +561,6 @@ int sun4i_ss_cipher_init(struct crypto_tfm *tfm)
 				    sizeof(struct sun4i_cipher_req_ctx) +
 				    crypto_skcipher_reqsize(op->fallback_tfm));
 
-
 	err = pm_runtime_get_sync(op->ss->dev);
 	if (err < 0)
 		goto error_pm;
@@ -590,5 +647,4 @@ int sun4i_ss_des3_setkey(struct crypto_skcipher *tfm, const u8 *key,
 	crypto_skcipher_set_flags(op->fallback_tfm, tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
 
 	return crypto_skcipher_setkey(op->fallback_tfm, key, keylen);
-
 }
diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c
index a2b67f7f8a81..709905ec4680 100644
--- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c
@@ -10,6 +10,7 @@
  */
 #include <linux/clk.h>
 #include <linux/crypto.h>
+#include <linux/debugfs.h>
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -234,6 +235,51 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 #endif
 };
 
+static int sun4i_ss_dbgfs_read(struct seq_file *seq, void *v)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(ss_algs); i++) {
+		if (!ss_algs[i].ss)
+			continue;
+		switch (ss_algs[i].type) {
+		case CRYPTO_ALG_TYPE_SKCIPHER:
+			seq_printf(seq, "%s %s reqs=%lu opti=%lu fallback=%lu tsize=%lu\n",
+				   ss_algs[i].alg.crypto.base.cra_driver_name,
+				   ss_algs[i].alg.crypto.base.cra_name,
+				   ss_algs[i].stat_req, ss_algs[i].stat_opti, ss_algs[i].stat_fb,
+				   ss_algs[i].stat_bytes);
+			break;
+		case CRYPTO_ALG_TYPE_RNG:
+			seq_printf(seq, "%s %s reqs=%lu tsize=%lu\n",
+				   ss_algs[i].alg.rng.base.cra_driver_name,
+				   ss_algs[i].alg.rng.base.cra_name,
+				   ss_algs[i].stat_req, ss_algs[i].stat_bytes);
+			break;
+		case CRYPTO_ALG_TYPE_AHASH:
+			seq_printf(seq, "%s %s reqs=%lu\n",
+				   ss_algs[i].alg.hash.halg.base.cra_driver_name,
+				   ss_algs[i].alg.hash.halg.base.cra_name,
+				   ss_algs[i].stat_req);
+			break;
+		}
+	}
+	return 0;
+}
+
+static int sun4i_ss_dbgfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sun4i_ss_dbgfs_read, inode->i_private);
+}
+
+static const struct file_operations sun4i_ss_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.open = sun4i_ss_dbgfs_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 /*
  * Power management strategy: The device is suspended unless a TFM exists for
  * one of the algorithms proposed by this driver.
@@ -454,6 +500,12 @@ static int sun4i_ss_probe(struct platform_device *pdev)
 			break;
 		}
 	}
+
+	/* Ignore error of debugfs */
+	ss->dbgfs_dir = debugfs_create_dir("sun4i-ss", NULL);
+	ss->dbgfs_stats = debugfs_create_file("stats", 0444, ss->dbgfs_dir, ss,
+					      &sun4i_ss_debugfs_fops);
+
 	return 0;
 error_alg:
 	i--;
diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c
index 1dff48558f53..c1b4585e9bbc 100644
--- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c
@@ -191,8 +191,10 @@ static int sun4i_hash(struct ahash_request *areq)
 	u32 spaces, rx_cnt = SS_RX_DEFAULT, bf[32] = {0}, v, ivmode = 0;
 	struct sun4i_req_ctx *op = ahash_request_ctx(areq);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	struct ahash_alg *alg = __crypto_ahash_alg(tfm->base.__crt_alg);
 	struct sun4i_tfm_ctx *tfmctx = crypto_ahash_ctx(tfm);
 	struct sun4i_ss_ctx *ss = tfmctx->ss;
+	struct sun4i_ss_alg_template *algt;
 	struct scatterlist *in_sg = areq->src;
 	struct sg_mapping_iter mi;
 	int in_r, err = 0;
@@ -398,6 +400,10 @@ static int sun4i_hash(struct ahash_request *areq)
  */
 
 hash_final:
+	if (IS_ENABLED(CONFIG_CRYPTO_DEV_SUN4I_SS_DEBUG)) {
+		algt = container_of(alg, struct sun4i_ss_alg_template, alg.hash);
+		algt->stat_req++;
+	}
 
 	/* write the remaining words of the wait buffer */
 	if (op->len) {
diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-prng.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-prng.c
index 729aafdbea84..443160a114bb 100644
--- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-prng.c
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-prng.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 #include "sun4i-ss.h"
 
 int sun4i_ss_prng_seed(struct crypto_rng *tfm, const u8 *seed,
@@ -32,6 +33,11 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src,
 	if (err < 0)
 		return err;
 
+	if (IS_ENABLED(CONFIG_CRYPTO_DEV_SUN4I_SS_DEBUG)) {
+		algt->stat_req++;
+		algt->stat_bytes += todo;
+	}
+
 	spin_lock_bh(&ss->slock);
 
 	writel(mode, ss->base + SS_CTL);
diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h
index 5c291e4a6857..0fee6f4e2d90 100644
--- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h
@@ -148,10 +148,14 @@ struct sun4i_ss_ctx {
 	struct reset_control *reset;
 	struct device *dev;
 	struct resource *res;
+	char buf[4 * SS_RX_MAX];/* buffer for linearize SG src */
+	char bufo[4 * SS_TX_MAX]; /* buffer for linearize SG dst */
 	spinlock_t slock; /* control the use of the device */
 #ifdef CONFIG_CRYPTO_DEV_SUN4I_SS_PRNG
 	u32 seed[SS_SEED_LEN / BITS_PER_LONG];
 #endif
+	struct dentry *dbgfs_dir;
+	struct dentry *dbgfs_stats;
 };
 
 struct sun4i_ss_alg_template {
@@ -163,6 +167,10 @@ struct sun4i_ss_alg_template {
 		struct rng_alg rng;
 	} alg;
 	struct sun4i_ss_ctx *ss;
+	unsigned long stat_req;
+	unsigned long stat_fb;
+	unsigned long stat_bytes;
+	unsigned long stat_opti;
 };
 
 struct sun4i_tfm_ctx {
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 30390a7324b2..851b149f7170 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -42,7 +42,7 @@
 
 /* ================= Device Structure ================== */
 
-struct device_private iproc_priv;
+struct bcm_device_private iproc_priv;
 
 /* ==================== Parameters ===================== */
 
@@ -471,10 +471,8 @@ static int handle_skcipher_req(struct iproc_reqctx_s *rctx)
 static void handle_skcipher_resp(struct iproc_reqctx_s *rctx)
 {
 	struct spu_hw *spu = &iproc_priv.spu;
-#ifdef DEBUG
 	struct crypto_async_request *areq = rctx->parent;
 	struct skcipher_request *req = skcipher_request_cast(areq);
-#endif
 	struct iproc_ctx_s *ctx = rctx->ctx;
 	u32 payload_len;
 
@@ -996,13 +994,11 @@ static int ahash_req_done(struct iproc_reqctx_s *rctx)
 static void handle_ahash_resp(struct iproc_reqctx_s *rctx)
 {
 	struct iproc_ctx_s *ctx = rctx->ctx;
-#ifdef DEBUG
 	struct crypto_async_request *areq = rctx->parent;
 	struct ahash_request *req = ahash_request_cast(areq);
 	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
 	unsigned int blocksize =
 		crypto_tfm_alg_blocksize(crypto_ahash_tfm(ahash));
-#endif
 	/*
 	 * Save hash to use as input to next op if incremental. Might be copying
 	 * too much, but that's easier than figuring out actual digest size here
diff --git a/drivers/crypto/bcm/cipher.h b/drivers/crypto/bcm/cipher.h
index 0ad5892b445d..71281a3bdbdc 100644
--- a/drivers/crypto/bcm/cipher.h
+++ b/drivers/crypto/bcm/cipher.h
@@ -420,7 +420,7 @@ struct spu_hw {
 	u32 num_chan;
 };
 
-struct device_private {
+struct bcm_device_private {
 	struct platform_device *pdev;
 
 	struct spu_hw spu;
@@ -467,6 +467,6 @@ struct device_private {
 	struct mbox_chan **mbox;
 };
 
-extern struct device_private iproc_priv;
+extern struct bcm_device_private iproc_priv;
 
 #endif
diff --git a/drivers/crypto/bcm/spu.c b/drivers/crypto/bcm/spu.c
index fe126f95c702..007abf92cc05 100644
--- a/drivers/crypto/bcm/spu.c
+++ b/drivers/crypto/bcm/spu.c
@@ -41,7 +41,7 @@ void spum_dump_msg_hdr(u8 *buf, unsigned int buf_len)
 	packet_log("SPU Message header %p len: %u\n", buf, buf_len);
 
 	/* ========== Decode MH ========== */
-	packet_log("  MH 0x%08x\n", be32_to_cpu(*((u32 *)ptr)));
+	packet_log("  MH 0x%08x\n", be32_to_cpup((__be32 *)ptr));
 	if (spuh->mh.flags & MH_SCTX_PRES)
 		packet_log("    SCTX  present\n");
 	if (spuh->mh.flags & MH_BDESC_PRES)
@@ -273,22 +273,21 @@ void spum_dump_msg_hdr(u8 *buf, unsigned int buf_len)
 
 	/* ========== Decode BDESC ========== */
 	if (spuh->mh.flags & MH_BDESC_PRES) {
-#ifdef DEBUG
 		struct BDESC_HEADER *bdesc = (struct BDESC_HEADER *)ptr;
-#endif
-		packet_log("  BDESC[0] 0x%08x\n", be32_to_cpu(*((u32 *)ptr)));
+
+		packet_log("  BDESC[0] 0x%08x\n", be32_to_cpup((__be32 *)ptr));
 		packet_log("    OffsetMAC:%u LengthMAC:%u\n",
 			   be16_to_cpu(bdesc->offset_mac),
 			   be16_to_cpu(bdesc->length_mac));
 		ptr += sizeof(u32);
 
-		packet_log("  BDESC[1] 0x%08x\n", be32_to_cpu(*((u32 *)ptr)));
+		packet_log("  BDESC[1] 0x%08x\n", be32_to_cpup((__be32 *)ptr));
 		packet_log("    OffsetCrypto:%u LengthCrypto:%u\n",
 			   be16_to_cpu(bdesc->offset_crypto),
 			   be16_to_cpu(bdesc->length_crypto));
 		ptr += sizeof(u32);
 
-		packet_log("  BDESC[2] 0x%08x\n", be32_to_cpu(*((u32 *)ptr)));
+		packet_log("  BDESC[2] 0x%08x\n", be32_to_cpup((__be32 *)ptr));
 		packet_log("    OffsetICV:%u OffsetIV:%u\n",
 			   be16_to_cpu(bdesc->offset_icv),
 			   be16_to_cpu(bdesc->offset_iv));
@@ -297,10 +296,9 @@ void spum_dump_msg_hdr(u8 *buf, unsigned int buf_len)
 
 	/* ========== Decode BD ========== */
 	if (spuh->mh.flags & MH_BD_PRES) {
-#ifdef DEBUG
 		struct BD_HEADER *bd = (struct BD_HEADER *)ptr;
-#endif
-		packet_log("  BD[0] 0x%08x\n", be32_to_cpu(*((u32 *)ptr)));
+
+		packet_log("  BD[0] 0x%08x\n", be32_to_cpup((__be32 *)ptr));
 		packet_log("    Size:%ubytes PrevLength:%u\n",
 			   be16_to_cpu(bd->size), be16_to_cpu(bd->prev_length));
 		ptr += 4;
@@ -1056,9 +1054,9 @@ void spum_request_pad(u8 *pad_start,
 
 			/* add the size at the end as required per alg */
 			if (auth_alg == HASH_ALG_MD5)
-				*(u64 *)ptr = cpu_to_le64((u64)total_sent * 8);
+				*(__le64 *)ptr = cpu_to_le64(total_sent * 8ull);
 			else		/* SHA1, SHA2-224, SHA2-256 */
-				*(u64 *)ptr = cpu_to_be64((u64)total_sent * 8);
+				*(__be64 *)ptr = cpu_to_be64(total_sent * 8ull);
 			ptr += sizeof(u64);
 		}
 	}
diff --git a/drivers/crypto/bcm/spu2.c b/drivers/crypto/bcm/spu2.c
index c860ffb0b4c3..2db35b5ccaa2 100644
--- a/drivers/crypto/bcm/spu2.c
+++ b/drivers/crypto/bcm/spu2.c
@@ -964,7 +964,6 @@ u32 spu2_create_request(u8 *spu_hdr,
 	unsigned int cipher_offset = aead_parms->assoc_size +
 			aead_parms->aad_pad_len + aead_parms->iv_len;
 
-#ifdef DEBUG
 	/* total size of the data following OMD (without STAT word padding) */
 	unsigned int real_db_size = spu_real_db_size(aead_parms->assoc_size,
 						 aead_parms->iv_len,
@@ -973,7 +972,6 @@ u32 spu2_create_request(u8 *spu_hdr,
 						 aead_parms->aad_pad_len,
 						 aead_parms->data_pad_len,
 						 hash_parms->pad_len);
-#endif
 	unsigned int assoc_size = aead_parms->assoc_size;
 
 	if (req_opts->is_aead &&
@@ -1263,9 +1261,9 @@ void spu2_request_pad(u8 *pad_start, u32 gcm_padding, u32 hash_pad_len,
 
 		/* add the size at the end as required per alg */
 		if (auth_alg == HASH_ALG_MD5)
-			*(u64 *)ptr = cpu_to_le64((u64)total_sent * 8);
+			*(__le64 *)ptr = cpu_to_le64(total_sent * 8ull);
 		else		/* SHA1, SHA2-224, SHA2-256 */
-			*(u64 *)ptr = cpu_to_be64((u64)total_sent * 8);
+			*(__be64 *)ptr = cpu_to_be64(total_sent * 8ull);
 		ptr += sizeof(u64);
 	}
 
diff --git a/drivers/crypto/bcm/spu2.h b/drivers/crypto/bcm/spu2.h
index 6e666bfb3cfc..a76d4e054466 100644
--- a/drivers/crypto/bcm/spu2.h
+++ b/drivers/crypto/bcm/spu2.h
@@ -73,10 +73,10 @@ enum spu2_ret_md_opts {
 
 /* Fixed Metadata format */
 struct SPU2_FMD {
-	u64 ctrl0;
-	u64 ctrl1;
-	u64 ctrl2;
-	u64 ctrl3;
+	__le64 ctrl0;
+	__le64 ctrl1;
+	__le64 ctrl2;
+	__le64 ctrl3;
 };
 
 #define FMD_SIZE  sizeof(struct SPU2_FMD)
diff --git a/drivers/crypto/bcm/spum.h b/drivers/crypto/bcm/spum.h
index 6116ad1dd26e..f062f75808de 100644
--- a/drivers/crypto/bcm/spum.h
+++ b/drivers/crypto/bcm/spum.h
@@ -69,18 +69,18 @@
 
 /* Buffer Descriptor Header [BDESC]. SPU in big-endian mode. */
 struct BDESC_HEADER {
-	u16 offset_mac;		/* word 0 [31-16] */
-	u16 length_mac;		/* word 0 [15-0]  */
-	u16 offset_crypto;	/* word 1 [31-16] */
-	u16 length_crypto;	/* word 1 [15-0]  */
-	u16 offset_icv;		/* word 2 [31-16] */
-	u16 offset_iv;		/* word 2 [15-0]  */
+	__be16 offset_mac;		/* word 0 [31-16] */
+	__be16 length_mac;		/* word 0 [15-0]  */
+	__be16 offset_crypto;		/* word 1 [31-16] */
+	__be16 length_crypto;		/* word 1 [15-0]  */
+	__be16 offset_icv;		/* word 2 [31-16] */
+	__be16 offset_iv;		/* word 2 [15-0]  */
 };
 
 /* Buffer Data Header [BD]. SPU in big-endian mode. */
 struct BD_HEADER {
-	u16 size;
-	u16 prev_length;
+	__be16 size;
+	__be16 prev_length;
 };
 
 /* Command Context Header. SPU-M in big endian mode. */
@@ -144,13 +144,13 @@ struct MHEADER {
 /* Generic Mode Security Context Structure [SCTX] */
 struct SCTX {
 /* word 0: protocol flags */
-	u32 proto_flags;
+	__be32 proto_flags;
 
 /* word 1: cipher flags */
-	u32 cipher_flags;
+	__be32 cipher_flags;
 
 /* word 2: Extended cipher flags */
-	u32 ecf;
+	__be32 ecf;
 
 };
 
diff --git a/drivers/crypto/bcm/util.c b/drivers/crypto/bcm/util.c
index 2b304fc78059..c4669a96eaec 100644
--- a/drivers/crypto/bcm/util.c
+++ b/drivers/crypto/bcm/util.c
@@ -268,6 +268,7 @@ do_shash_err:
 	return rc;
 }
 
+#ifdef DEBUG
 /* Dump len bytes of a scatterlist starting at skip bytes into the sg */
 void __dump_sg(struct scatterlist *sg, unsigned int skip, unsigned int len)
 {
@@ -289,6 +290,7 @@ void __dump_sg(struct scatterlist *sg, unsigned int skip, unsigned int len)
 	if (debug_logging_sleep)
 		msleep(debug_logging_sleep);
 }
+#endif
 
 /* Returns the name for a given cipher alg/mode */
 char *spu_alg_name(enum spu_cipher_alg alg, enum spu_cipher_mode mode)
@@ -348,7 +350,7 @@ char *spu_alg_name(enum spu_cipher_alg alg, enum spu_cipher_mode mode)
 static ssize_t spu_debugfs_read(struct file *filp, char __user *ubuf,
 				size_t count, loff_t *offp)
 {
-	struct device_private *ipriv;
+	struct bcm_device_private *ipriv;
 	char *buf;
 	ssize_t ret, out_offset, out_count;
 	int i;
diff --git a/drivers/crypto/bcm/util.h b/drivers/crypto/bcm/util.h
index a89b2b9c1f52..61c256384816 100644
--- a/drivers/crypto/bcm/util.h
+++ b/drivers/crypto/bcm/util.h
@@ -58,12 +58,26 @@ void __dump_sg(struct scatterlist *sg, unsigned int skip, unsigned int len);
 
 #else /* !DEBUG_ON */
 
-#define flow_log(...) do {} while (0)
-#define flow_dump(msg, var, var_len) do {} while (0)
-#define packet_log(...) do {} while (0)
-#define packet_dump(msg, var, var_len) do {} while (0)
-
-#define dump_sg(sg, skip, len) do {} while (0)
+static inline void flow_log(const char *format, ...)
+{
+}
+
+static inline void flow_dump(const char *msg, const void *var, size_t var_len)
+{
+}
+
+static inline void packet_log(const char *format, ...)
+{
+}
+
+static inline void packet_dump(const char *msg, const void *var, size_t var_len)
+{
+}
+
+static inline void dump_sg(struct scatterlist *sg, unsigned int skip,
+			   unsigned int len)
+{
+}
 
 #endif /* DEBUG_ON */
 
diff --git a/drivers/crypto/caam/debugfs.c b/drivers/crypto/caam/debugfs.c
index 8ebf18398166..806bb20d2aa1 100644
--- a/drivers/crypto/caam/debugfs.c
+++ b/drivers/crypto/caam/debugfs.c
@@ -19,8 +19,8 @@ static int caam_debugfs_u32_get(void *data, u64 *val)
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u32_ro, caam_debugfs_u32_get, NULL, "%llu\n");
-DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u64_ro, caam_debugfs_u64_get, NULL, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(caam_fops_u32_ro, caam_debugfs_u32_get, NULL, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(caam_fops_u64_ro, caam_debugfs_u64_get, NULL, "%llu\n");
 
 #ifdef CONFIG_CAAM_QI
 /*
diff --git a/drivers/crypto/cavium/cpt/cptvf_main.c b/drivers/crypto/cavium/cpt/cptvf_main.c
index f016448e43bb..112b12a32542 100644
--- a/drivers/crypto/cavium/cpt/cptvf_main.c
+++ b/drivers/crypto/cavium/cpt/cptvf_main.c
@@ -233,10 +233,10 @@ static int alloc_command_queues(struct cpt_vf *cptvf,
 
 			c_size = (rem_q_size > qcsize_bytes) ? qcsize_bytes :
 					rem_q_size;
-			curr->head = (u8 *)dma_alloc_coherent(&pdev->dev,
-							      c_size + CPT_NEXT_CHUNK_PTR_SIZE,
-							      &curr->dma_addr,
-							      GFP_KERNEL);
+			curr->head = dma_alloc_coherent(&pdev->dev,
+							c_size + CPT_NEXT_CHUNK_PTR_SIZE,
+							&curr->dma_addr,
+							GFP_KERNEL);
 			if (!curr->head) {
 				dev_err(&pdev->dev, "Command Q (%d) chunk (%d) allocation failed\n",
 					i, queue->nchunks);
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index cdfee501fbd9..78833491f534 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -921,7 +921,7 @@ static int cc_cipher_process(struct skcipher_request *req,
 			return crypto_skcipher_decrypt(subreq);
 	}
 
-	/* The IV we are handed may be allocted from the stack so
+	/* The IV we are handed may be allocated from the stack so
 	 * we must copy it to a DMAable buffer before use.
 	 */
 	req_ctx->iv = kmemdup(iv, ivsize, flags);
diff --git a/drivers/crypto/ccree/cc_driver.h b/drivers/crypto/ccree/cc_driver.h
index 5f1d4602eb8f..f49579aa1452 100644
--- a/drivers/crypto/ccree/cc_driver.h
+++ b/drivers/crypto/ccree/cc_driver.h
@@ -23,7 +23,6 @@
 #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>
 
diff --git a/drivers/crypto/geode-aes.c b/drivers/crypto/geode-aes.c
index f4f18bfc2247..4ee010f39912 100644
--- a/drivers/crypto/geode-aes.c
+++ b/drivers/crypto/geode-aes.c
@@ -10,6 +10,7 @@
 #include <linux/spinlock.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 
 #include <linux/io.h>
@@ -434,3 +435,4 @@ module_pci_driver(geode_aes_driver);
 MODULE_AUTHOR("Advanced Micro Devices, Inc.");
 MODULE_DESCRIPTION("Geode LX Hardware AES driver");
 MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/drivers/crypto/hisilicon/hpre/hpre.h b/drivers/crypto/hisilicon/hpre/hpre.h
index f69252b24671..181c109b19f7 100644
--- a/drivers/crypto/hisilicon/hpre/hpre.h
+++ b/drivers/crypto/hisilicon/hpre/hpre.h
@@ -14,8 +14,7 @@ enum {
 	HPRE_CLUSTER0,
 	HPRE_CLUSTER1,
 	HPRE_CLUSTER2,
-	HPRE_CLUSTER3,
-	HPRE_CLUSTERS_NUM,
+	HPRE_CLUSTER3
 };
 
 enum hpre_ctrl_dbgfs_file {
@@ -36,7 +35,10 @@ enum hpre_dfx_dbgfs_file {
 	HPRE_DFX_FILE_NUM
 };
 
-#define HPRE_DEBUGFS_FILE_NUM    (HPRE_DEBUG_FILE_NUM + HPRE_CLUSTERS_NUM - 1)
+#define HPRE_CLUSTERS_NUM_V2		(HPRE_CLUSTER3 + 1)
+#define HPRE_CLUSTERS_NUM_V3		1
+#define HPRE_CLUSTERS_NUM_MAX		HPRE_CLUSTERS_NUM_V2
+#define HPRE_DEBUGFS_FILE_NUM (HPRE_DEBUG_FILE_NUM + HPRE_CLUSTERS_NUM_MAX - 1)
 
 struct hpre_debugfs_file {
 	int index;
diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c
index e5c991913f09..e7a2c70eb9cf 100644
--- a/drivers/crypto/hisilicon/hpre/hpre_main.c
+++ b/drivers/crypto/hisilicon/hpre/hpre_main.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/topology.h>
+#include <linux/uacce.h>
 #include "hpre.h"
 
 #define HPRE_QUEUE_NUM_V2		1024
@@ -29,13 +30,14 @@
 #define HPRE_BD_ARUSR_CFG		0x301030
 #define HPRE_BD_AWUSR_CFG		0x301034
 #define HPRE_TYPES_ENB			0x301038
+#define HPRE_RSA_ENB			BIT(0)
+#define HPRE_ECC_ENB			BIT(1)
 #define HPRE_DATA_RUSER_CFG		0x30103c
 #define HPRE_DATA_WUSER_CFG		0x301040
 #define HPRE_INT_MASK			0x301400
 #define HPRE_INT_STATUS			0x301800
 #define HPRE_CORE_INT_ENABLE		0
 #define HPRE_CORE_INT_DISABLE		0x003fffff
-#define HPRE_RAS_ECC_1BIT_TH		0x30140c
 #define HPRE_RDCHN_INI_ST		0x301a00
 #define HPRE_CLSTR_BASE			0x302000
 #define HPRE_CORE_EN_OFFSET		0x04
@@ -45,7 +47,7 @@
 #define HPRE_CORE_IS_SCHD_OFFSET	0x90
 
 #define HPRE_RAS_CE_ENB			0x301410
-#define HPRE_HAC_RAS_CE_ENABLE		0x1
+#define HPRE_HAC_RAS_CE_ENABLE		(BIT(0) | BIT(22) | BIT(23))
 #define HPRE_RAS_NFE_ENB		0x301414
 #define HPRE_HAC_RAS_NFE_ENABLE		0x3ffffe
 #define HPRE_RAS_FE_ENB			0x301418
@@ -73,7 +75,8 @@
 #define HPRE_QM_AXI_CFG_MASK		0xffff
 #define HPRE_QM_VFG_AX_MASK		0xff
 #define HPRE_BD_USR_MASK		0x3
-#define HPRE_CLUSTER_CORE_MASK		0xf
+#define HPRE_CLUSTER_CORE_MASK_V2	0xf
+#define HPRE_CLUSTER_CORE_MASK_V3	0xff
 
 #define HPRE_AM_OOO_SHUTDOWN_ENB	0x301044
 #define HPRE_AM_OOO_SHUTDOWN_ENABLE	BIT(0)
@@ -86,6 +89,11 @@
 #define HPRE_QM_PM_FLR			BIT(11)
 #define HPRE_QM_SRIOV_FLR		BIT(12)
 
+#define HPRE_CLUSTERS_NUM(qm)		\
+	(((qm)->ver >= QM_HW_V3) ? HPRE_CLUSTERS_NUM_V3 : HPRE_CLUSTERS_NUM_V2)
+#define HPRE_CLUSTER_CORE_MASK(qm)	\
+	(((qm)->ver >= QM_HW_V3) ? HPRE_CLUSTER_CORE_MASK_V3 :\
+		HPRE_CLUSTER_CORE_MASK_V2)
 #define HPRE_VIA_MSI_DSM		1
 #define HPRE_SQE_MASK_OFFSET		8
 #define HPRE_SQE_MASK_LEN		24
@@ -129,7 +137,11 @@ static const struct hpre_hw_error hpre_hw_errors[] = {
 	{ .int_msk = BIT(9), .msg = "cluster4_shb_timeout_int_set" },
 	{ .int_msk = GENMASK(15, 10), .msg = "ooo_rdrsp_err_int_set" },
 	{ .int_msk = GENMASK(21, 16), .msg = "ooo_wrrsp_err_int_set" },
-	{ /* sentinel */ }
+	{ .int_msk = BIT(22), .msg = "pt_rng_timeout_int_set"},
+	{ .int_msk = BIT(23), .msg = "sva_fsm_timeout_int_set"},
+	{
+		/* sentinel */
+	}
 };
 
 static const u64 hpre_cluster_offsets[] = {
@@ -178,6 +190,19 @@ static const char *hpre_dfx_files[HPRE_DFX_FILE_NUM] = {
 	"invalid_req_cnt"
 };
 
+static const struct kernel_param_ops hpre_uacce_mode_ops = {
+	.set = uacce_mode_set,
+	.get = param_get_int,
+};
+
+/*
+ * uacce_mode = 0 means hpre only register to crypto,
+ * uacce_mode = 1 means hpre both register to crypto and uacce.
+ */
+static u32 uacce_mode = UACCE_MODE_NOUACCE;
+module_param_cb(uacce_mode, &hpre_uacce_mode_ops, &uacce_mode, 0444);
+MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC);
+
 static int pf_q_num_set(const char *val, const struct kernel_param *kp)
 {
 	return q_num_set(val, kp, HPRE_PCI_DEVICE_ID);
@@ -214,6 +239,30 @@ struct hisi_qp *hpre_create_qp(void)
 	return NULL;
 }
 
+static void hpre_pasid_enable(struct hisi_qm *qm)
+{
+	u32 val;
+
+	val = readl_relaxed(qm->io_base + HPRE_DATA_RUSER_CFG);
+	val |= BIT(HPRE_PASID_EN_BIT);
+	writel_relaxed(val, qm->io_base + HPRE_DATA_RUSER_CFG);
+	val = readl_relaxed(qm->io_base + HPRE_DATA_WUSER_CFG);
+	val |= BIT(HPRE_PASID_EN_BIT);
+	writel_relaxed(val, qm->io_base + HPRE_DATA_WUSER_CFG);
+}
+
+static void hpre_pasid_disable(struct hisi_qm *qm)
+{
+	u32 val;
+
+	val = readl_relaxed(qm->io_base +  HPRE_DATA_RUSER_CFG);
+	val &= ~BIT(HPRE_PASID_EN_BIT);
+	writel_relaxed(val, qm->io_base + HPRE_DATA_RUSER_CFG);
+	val = readl_relaxed(qm->io_base + HPRE_DATA_WUSER_CFG);
+	val &= ~BIT(HPRE_PASID_EN_BIT);
+	writel_relaxed(val, qm->io_base + HPRE_DATA_WUSER_CFG);
+}
+
 static int hpre_cfg_by_dsm(struct hisi_qm *qm)
 {
 	struct device *dev = &qm->pdev->dev;
@@ -238,8 +287,40 @@ static int hpre_cfg_by_dsm(struct hisi_qm *qm)
 	return 0;
 }
 
+static int hpre_set_cluster(struct hisi_qm *qm)
+{
+	u32 cluster_core_mask = HPRE_CLUSTER_CORE_MASK(qm);
+	u8 clusters_num = HPRE_CLUSTERS_NUM(qm);
+	struct device *dev = &qm->pdev->dev;
+	unsigned long offset;
+	u32 val = 0;
+	int ret, i;
+
+	for (i = 0; i < clusters_num; i++) {
+		offset = i * HPRE_CLSTR_ADDR_INTRVL;
+
+		/* clusters initiating */
+		writel(cluster_core_mask,
+		       HPRE_ADDR(qm, offset + HPRE_CORE_ENB));
+		writel(0x1, HPRE_ADDR(qm, offset + HPRE_CORE_INI_CFG));
+		ret = readl_relaxed_poll_timeout(HPRE_ADDR(qm, offset +
+					HPRE_CORE_INI_STATUS), val,
+					((val & cluster_core_mask) ==
+					cluster_core_mask),
+					HPRE_REG_RD_INTVRL_US,
+					HPRE_REG_RD_TMOUT_US);
+		if (ret) {
+			dev_err(dev,
+				"cluster %d int st status timeout!\n", i);
+			return -ETIMEDOUT;
+		}
+	}
+
+	return 0;
+}
+
 /*
- * For Hi1620, we shoul disable FLR triggered by hardware (BME/PM/SRIOV).
+ * For Kunpeng 920, we shoul disable FLR triggered by hardware (BME/PM/SRIOV).
  * Or it may stay in D3 state when we bind and unbind hpre quickly,
  * as it does FLR triggered by hardware.
  */
@@ -257,9 +338,8 @@ static void disable_flr_of_bme(struct hisi_qm *qm)
 static int hpre_set_user_domain_and_cache(struct hisi_qm *qm)
 {
 	struct device *dev = &qm->pdev->dev;
-	unsigned long offset;
-	int ret, i;
 	u32 val;
+	int ret;
 
 	writel(HPRE_QM_USR_CFG_MASK, HPRE_ADDR(qm, QM_ARUSER_M_CFG_ENABLE));
 	writel(HPRE_QM_USR_CFG_MASK, HPRE_ADDR(qm, QM_AWUSER_M_CFG_ENABLE));
@@ -270,11 +350,15 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm)
 	val |= BIT(HPRE_TIMEOUT_ABNML_BIT);
 	writel_relaxed(val, HPRE_ADDR(qm, HPRE_QM_ABNML_INT_MASK));
 
-	writel(0x1, HPRE_ADDR(qm, HPRE_TYPES_ENB));
+	if (qm->ver >= QM_HW_V3)
+		writel(HPRE_RSA_ENB | HPRE_ECC_ENB,
+			HPRE_ADDR(qm, HPRE_TYPES_ENB));
+	else
+		writel(HPRE_RSA_ENB, HPRE_ADDR(qm, HPRE_TYPES_ENB));
+
 	writel(HPRE_QM_VFG_AX_MASK, HPRE_ADDR(qm, HPRE_VFG_AXCACHE));
 	writel(0x0, HPRE_ADDR(qm, HPRE_BD_ENDIAN));
 	writel(0x0, HPRE_ADDR(qm, HPRE_INT_MASK));
-	writel(0x0, HPRE_ADDR(qm, HPRE_RAS_ECC_1BIT_TH));
 	writel(0x0, HPRE_ADDR(qm, HPRE_POISON_BYPASS));
 	writel(0x0, HPRE_ADDR(qm, HPRE_COMM_CNT_CLR_CE));
 	writel(0x0, HPRE_ADDR(qm, HPRE_ECC_BYPASS));
@@ -291,37 +375,29 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm)
 		return -ETIMEDOUT;
 	}
 
-	for (i = 0; i < HPRE_CLUSTERS_NUM; i++) {
-		offset = i * HPRE_CLSTR_ADDR_INTRVL;
+	ret = hpre_set_cluster(qm);
+	if (ret)
+		return -ETIMEDOUT;
 
-		/* clusters initiating */
-		writel(HPRE_CLUSTER_CORE_MASK,
-		       HPRE_ADDR(qm, offset + HPRE_CORE_ENB));
-		writel(0x1, HPRE_ADDR(qm, offset + HPRE_CORE_INI_CFG));
-		ret = readl_relaxed_poll_timeout(HPRE_ADDR(qm, offset +
-					HPRE_CORE_INI_STATUS), val,
-					((val & HPRE_CLUSTER_CORE_MASK) ==
-					HPRE_CLUSTER_CORE_MASK),
-					HPRE_REG_RD_INTVRL_US,
-					HPRE_REG_RD_TMOUT_US);
-		if (ret) {
-			dev_err(dev,
-				"cluster %d int st status timeout!\n", i);
-			return -ETIMEDOUT;
-		}
-	}
+	/* This setting is only needed by Kunpeng 920. */
+	if (qm->ver == QM_HW_V2) {
+		ret = hpre_cfg_by_dsm(qm);
+		if (ret)
+			dev_err(dev, "acpi_evaluate_dsm err.\n");
 
-	ret = hpre_cfg_by_dsm(qm);
-	if (ret)
-		dev_err(dev, "acpi_evaluate_dsm err.\n");
+		disable_flr_of_bme(qm);
 
-	disable_flr_of_bme(qm);
+		/* Enable data buffer pasid */
+		if (qm->use_sva)
+			hpre_pasid_enable(qm);
+	}
 
 	return ret;
 }
 
 static void hpre_cnt_regs_clear(struct hisi_qm *qm)
 {
+	u8 clusters_num = HPRE_CLUSTERS_NUM(qm);
 	unsigned long offset;
 	int i;
 
@@ -330,7 +406,7 @@ static void hpre_cnt_regs_clear(struct hisi_qm *qm)
 	writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF);
 
 	/* clear clusterX/cluster_ctrl */
-	for (i = 0; i < HPRE_CLUSTERS_NUM; i++) {
+	for (i = 0; i < clusters_num; i++) {
 		offset = HPRE_CLSTR_BASE + i * HPRE_CLSTR_ADDR_INTRVL;
 		writel(0x0, qm->io_base + offset + HPRE_CLUSTER_INQURY);
 	}
@@ -629,13 +705,14 @@ static int hpre_pf_comm_regs_debugfs_init(struct hisi_qm *qm)
 
 static int hpre_cluster_debugfs_init(struct hisi_qm *qm)
 {
+	u8 clusters_num = HPRE_CLUSTERS_NUM(qm);
 	struct device *dev = &qm->pdev->dev;
 	char buf[HPRE_DBGFS_VAL_MAX_LEN];
 	struct debugfs_regset32 *regset;
 	struct dentry *tmp_d;
 	int i, ret;
 
-	for (i = 0; i < HPRE_CLUSTERS_NUM; i++) {
+	for (i = 0; i < clusters_num; i++) {
 		ret = snprintf(buf, HPRE_DBGFS_VAL_MAX_LEN, "cluster%d", i);
 		if (ret < 0)
 			return -EINVAL;
@@ -734,6 +811,11 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 		return -EINVAL;
 	}
 
+	if (pdev->revision >= QM_HW_V3)
+		qm->algs = "rsa\ndh\necdh\nx25519\nx448\necdsa\nsm2\n";
+	else
+		qm->algs = "rsa\ndh\n";
+	qm->mode = uacce_mode;
 	qm->pdev = pdev;
 	qm->ver = pdev->revision;
 	qm->sqe_size = HPRE_SQE_SIZE;
@@ -799,6 +881,7 @@ static const struct hisi_qm_err_ini hpre_err_ini = {
 		.fe			= 0,
 		.ecc_2bits_mask		= HPRE_CORE_ECC_2BIT_ERR |
 					  HPRE_OOO_ECC_2BIT_ERR,
+		.dev_ce_mask		= HPRE_HAC_RAS_CE_ENABLE,
 		.msi_wr_port		= HPRE_WR_MSI_PORT,
 		.acpi_rst		= "HRST",
 	}
@@ -872,6 +955,14 @@ static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_with_qm_start;
 	}
 
+	if (qm->uacce) {
+		ret = uacce_register(qm->uacce);
+		if (ret) {
+			pci_err(pdev, "failed to register uacce (%d)!\n", ret);
+			goto err_with_alg_register;
+		}
+	}
+
 	if (qm->fun_type == QM_HW_PF && vfs_num) {
 		ret = hisi_qm_sriov_enable(pdev, vfs_num);
 		if (ret < 0)
@@ -904,20 +995,24 @@ static void hpre_remove(struct pci_dev *pdev)
 	hisi_qm_wait_task_finish(qm, &hpre_devices);
 	hisi_qm_alg_unregister(qm, &hpre_devices);
 	if (qm->fun_type == QM_HW_PF && qm->vfs_num) {
-		ret = hisi_qm_sriov_disable(pdev, qm->is_frozen);
+		ret = hisi_qm_sriov_disable(pdev, true);
 		if (ret) {
 			pci_err(pdev, "Disable SRIOV fail!\n");
 			return;
 		}
 	}
+
+	hpre_debugfs_exit(qm);
+	hisi_qm_stop(qm, QM_NORMAL);
+
 	if (qm->fun_type == QM_HW_PF) {
+		if (qm->use_sva && qm->ver == QM_HW_V2)
+			hpre_pasid_disable(qm);
 		hpre_cnt_regs_clear(qm);
 		qm->debug.curr_qm_qp_num = 0;
+		hisi_qm_dev_err_uninit(qm);
 	}
 
-	hpre_debugfs_exit(qm);
-	hisi_qm_stop(qm, QM_NORMAL);
-	hisi_qm_dev_err_uninit(qm);
 	hisi_qm_uninit(qm);
 }
 
diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index f21ccae0e8ea..13cb4216561a 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -54,6 +54,8 @@
 #define QM_SQ_PRIORITY_SHIFT		0
 #define QM_SQ_ORDERS_SHIFT		4
 #define QM_SQ_TYPE_SHIFT		8
+#define QM_QC_PASID_ENABLE		0x1
+#define QM_QC_PASID_ENABLE_SHIFT	7
 
 #define QM_SQ_TYPE_MASK			GENMASK(3, 0)
 #define QM_SQ_TAIL_IDX(sqc)		((le16_to_cpu((sqc)->w11) >> 6) & 0x1)
@@ -120,7 +122,7 @@
 #define QM_CQC_VFT_VALID		(1ULL << 28)
 
 #define QM_SQC_VFT_BASE_SHIFT_V2	28
-#define QM_SQC_VFT_BASE_MASK_V2		GENMASK(5, 0)
+#define QM_SQC_VFT_BASE_MASK_V2		GENMASK(15, 0)
 #define QM_SQC_VFT_NUM_SHIFT_V2		45
 #define QM_SQC_VFT_NUM_MASK_v2		GENMASK(9, 0)
 
@@ -147,7 +149,6 @@
 #define QM_RAS_CE_TIMES_PER_IRQ		1
 #define QM_RAS_MSI_INT_SEL		0x1040f4
 
-#define QM_DEV_RESET_FLAG		0
 #define QM_RESET_WAIT_TIMEOUT		400
 #define QM_PEH_VENDOR_ID		0x1000d8
 #define ACC_VENDOR_ID_VALUE		0x5a5a
@@ -185,6 +186,10 @@
 #define QM_SQE_ADDR_MASK		GENMASK(7, 0)
 #define QM_EQ_DEPTH			(1024 * 2)
 
+#define QM_DRIVER_REMOVING		0
+#define QM_RST_SCHED			1
+#define QM_RESETTING			2
+
 #define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \
 	(((hop_num) << QM_CQ_HOP_NUM_SHIFT)	| \
 	((pg_sz) << QM_CQ_PAGE_SIZE_SHIFT)	| \
@@ -619,6 +624,9 @@ static void qm_cq_head_update(struct hisi_qp *qp)
 
 static void qm_poll_qp(struct hisi_qp *qp, struct hisi_qm *qm)
 {
+	if (unlikely(atomic_read(&qp->qp_status.flags) == QP_STOP))
+		return;
+
 	if (qp->event_cb) {
 		qp->event_cb(qp);
 		return;
@@ -717,7 +725,7 @@ static irqreturn_t qm_aeq_irq(int irq, void *data)
 			dev_err(&qm->pdev->dev, "%s overflow\n",
 				qm_fifo_overflow[type]);
 		else
-			dev_err(&qm->pdev->dev, "unknown error type %d\n",
+			dev_err(&qm->pdev->dev, "unknown error type %u\n",
 				type);
 
 		if (qm->status.aeq_head == QM_Q_DEPTH - 1) {
@@ -1121,7 +1129,7 @@ static int dump_show(struct hisi_qm *qm, void *info,
 
 	dev_info(dev, "%s DUMP\n", info_name);
 	for (i = 0; i < info_size; i += BYTE_PER_DW) {
-		pr_info("DW%d: %02X%02X %02X%02X\n", i / BYTE_PER_DW,
+		pr_info("DW%u: %02X%02X %02X%02X\n", i / BYTE_PER_DW,
 			info_buf[i], info_buf[i + 1UL],
 			info_buf[i + 2UL], info_buf[i + 3UL]);
 	}
@@ -1154,7 +1162,7 @@ static int qm_sqc_dump(struct hisi_qm *qm, const char *s)
 
 	ret = kstrtou32(s, 0, &qp_id);
 	if (ret || qp_id >= qm->qp_num) {
-		dev_err(dev, "Please input qp num (0-%d)", qm->qp_num - 1);
+		dev_err(dev, "Please input qp num (0-%u)", qm->qp_num - 1);
 		return -EINVAL;
 	}
 
@@ -1200,7 +1208,7 @@ static int qm_cqc_dump(struct hisi_qm *qm, const char *s)
 
 	ret = kstrtou32(s, 0, &qp_id);
 	if (ret || qp_id >= qm->qp_num) {
-		dev_err(dev, "Please input qp num (0-%d)", qm->qp_num - 1);
+		dev_err(dev, "Please input qp num (0-%u)", qm->qp_num - 1);
 		return -EINVAL;
 	}
 
@@ -1279,7 +1287,7 @@ static int q_dump_param_parse(struct hisi_qm *qm, char *s,
 
 	ret = kstrtou32(presult, 0, q_id);
 	if (ret || *q_id >= qp_num) {
-		dev_err(dev, "Please input qp num (0-%d)", qp_num - 1);
+		dev_err(dev, "Please input qp num (0-%u)", qp_num - 1);
 		return -EINVAL;
 	}
 
@@ -1604,7 +1612,7 @@ static void qm_log_hw_error(struct hisi_qm *qm, u32 error_status)
 
 static enum acc_err_result qm_hw_error_handle_v2(struct hisi_qm *qm)
 {
-	u32 error_status, tmp;
+	u32 error_status, tmp, val;
 
 	/* read err sts */
 	tmp = readl(qm->io_base + QM_ABNORMAL_INT_STATUS);
@@ -1615,9 +1623,13 @@ static enum acc_err_result qm_hw_error_handle_v2(struct hisi_qm *qm)
 			qm->err_status.is_qm_ecc_mbit = true;
 
 		qm_log_hw_error(qm, error_status);
-		if (error_status == QM_DB_RANDOM_INVALID) {
+		val = error_status | QM_DB_RANDOM_INVALID | QM_BASE_CE;
+		/* ce error does not need to be reset */
+		if (val == (QM_DB_RANDOM_INVALID | QM_BASE_CE)) {
 			writel(error_status, qm->io_base +
 			       QM_ABNORMAL_INT_SOURCE);
+			writel(qm->err_ini->err_info.nfe,
+			       qm->io_base + QM_RAS_NFE_ENABLE);
 			return ACC_ERR_RECOVERED;
 		}
 
@@ -1685,6 +1697,7 @@ static struct hisi_qp *qm_create_qp_nolock(struct hisi_qm *qm, u8 alg_type)
 	qp->req_cb = NULL;
 	qp->qp_id = qp_id;
 	qp->alg_type = alg_type;
+	qp->is_in_kernel = true;
 	qm->qp_in_used++;
 	atomic_set(&qp->qp_status.flags, QP_INIT);
 
@@ -1747,12 +1760,6 @@ static int qm_sq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid)
 	sqc = kzalloc(sizeof(struct qm_sqc), GFP_KERNEL);
 	if (!sqc)
 		return -ENOMEM;
-	sqc_dma = dma_map_single(dev, sqc, sizeof(struct qm_sqc),
-				 DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, sqc_dma)) {
-		kfree(sqc);
-		return -ENOMEM;
-	}
 
 	INIT_QC_COMMON(sqc, qp->sqe_dma, pasid);
 	if (ver == QM_HW_V1) {
@@ -1765,6 +1772,17 @@ static int qm_sq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid)
 	sqc->cq_num = cpu_to_le16(qp_id);
 	sqc->w13 = cpu_to_le16(QM_MK_SQC_W13(0, 1, qp->alg_type));
 
+	if (ver >= QM_HW_V3 && qm->use_sva && !qp->is_in_kernel)
+		sqc->w11 = cpu_to_le16(QM_QC_PASID_ENABLE <<
+				       QM_QC_PASID_ENABLE_SHIFT);
+
+	sqc_dma = dma_map_single(dev, sqc, sizeof(struct qm_sqc),
+				 DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, sqc_dma)) {
+		kfree(sqc);
+		return -ENOMEM;
+	}
+
 	ret = qm_mb(qm, QM_MB_CMD_SQC, sqc_dma, qp_id, 0);
 	dma_unmap_single(dev, sqc_dma, sizeof(struct qm_sqc), DMA_TO_DEVICE);
 	kfree(sqc);
@@ -1784,12 +1802,6 @@ static int qm_cq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid)
 	cqc = kzalloc(sizeof(struct qm_cqc), GFP_KERNEL);
 	if (!cqc)
 		return -ENOMEM;
-	cqc_dma = dma_map_single(dev, cqc, sizeof(struct qm_cqc),
-				 DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, cqc_dma)) {
-		kfree(cqc);
-		return -ENOMEM;
-	}
 
 	INIT_QC_COMMON(cqc, qp->cqe_dma, pasid);
 	if (ver == QM_HW_V1) {
@@ -1802,6 +1814,16 @@ static int qm_cq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid)
 	}
 	cqc->dw6 = cpu_to_le32(1 << QM_CQ_PHASE_SHIFT | 1 << QM_CQ_FLAG_SHIFT);
 
+	if (ver >= QM_HW_V3 && qm->use_sva && !qp->is_in_kernel)
+		cqc->w11 = cpu_to_le16(QM_QC_PASID_ENABLE);
+
+	cqc_dma = dma_map_single(dev, cqc, sizeof(struct qm_cqc),
+				 DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, cqc_dma)) {
+		kfree(cqc);
+		return -ENOMEM;
+	}
+
 	ret = qm_mb(qm, QM_MB_CMD_CQC, cqc_dma, qp_id, 0);
 	dma_unmap_single(dev, cqc_dma, sizeof(struct qm_cqc), DMA_TO_DEVICE);
 	kfree(cqc);
@@ -1865,6 +1887,28 @@ int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg)
 EXPORT_SYMBOL_GPL(hisi_qm_start_qp);
 
 /**
+ * qp_stop_fail_cb() - call request cb.
+ * @qp: stopped failed qp.
+ *
+ * Callback function should be called whether task completed or not.
+ */
+static void qp_stop_fail_cb(struct hisi_qp *qp)
+{
+	int qp_used = atomic_read(&qp->qp_status.used);
+	u16 cur_tail = qp->qp_status.sq_tail;
+	u16 cur_head = (cur_tail + QM_Q_DEPTH - qp_used) % QM_Q_DEPTH;
+	struct hisi_qm *qm = qp->qm;
+	u16 pos;
+	int i;
+
+	for (i = 0; i < qp_used; i++) {
+		pos = (i + cur_head) % QM_Q_DEPTH;
+		qp->req_cb(qp, qp->sqe + (u32)(qm->sqe_size * pos));
+		atomic_dec(&qp->qp_status.used);
+	}
+}
+
+/**
  * qm_drain_qp() - Drain a qp.
  * @qp: The qp we want to drain.
  *
@@ -1959,6 +2003,9 @@ static int qm_stop_qp_nolock(struct hisi_qp *qp)
 	else
 		flush_work(&qp->qm->work);
 
+	if (unlikely(qp->is_resetting && atomic_read(&qp->qp_status.used)))
+		qp_stop_fail_cb(qp);
+
 	dev_dbg(dev, "stop queue %u!", qp->qp_id);
 
 	return 0;
@@ -2065,6 +2112,7 @@ static int hisi_qm_uacce_get_queue(struct uacce_device *uacce,
 	qp->uacce_q = q;
 	qp->event_cb = qm_qp_event_notifier;
 	qp->pasid = arg;
+	qp->is_in_kernel = false;
 
 	return 0;
 }
@@ -2206,7 +2254,7 @@ static int qm_alloc_uacce(struct hisi_qm *qm)
 	if (IS_ERR(uacce))
 		return PTR_ERR(uacce);
 
-	if (uacce->flags & UACCE_DEV_SVA) {
+	if (uacce->flags & UACCE_DEV_SVA && qm->mode == UACCE_MODE_SVA) {
 		qm->use_sva = true;
 	} else {
 		/* only consider sva case */
@@ -2248,17 +2296,15 @@ static int qm_alloc_uacce(struct hisi_qm *qm)
  */
 static int qm_frozen(struct hisi_qm *qm)
 {
-	down_write(&qm->qps_lock);
-
-	if (qm->is_frozen) {
-		up_write(&qm->qps_lock);
+	if (test_bit(QM_DRIVER_REMOVING, &qm->misc_ctl))
 		return 0;
-	}
+
+	down_write(&qm->qps_lock);
 
 	if (!qm->qp_in_used) {
 		qm->qp_in_used = qm->qp_num;
-		qm->is_frozen = true;
 		up_write(&qm->qps_lock);
+		set_bit(QM_DRIVER_REMOVING, &qm->misc_ctl);
 		return 0;
 	}
 
@@ -2311,6 +2357,10 @@ void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list)
 		msleep(WAIT_PERIOD);
 	}
 
+	while (test_bit(QM_RST_SCHED, &qm->misc_ctl) ||
+	       test_bit(QM_RESETTING, &qm->misc_ctl))
+		msleep(WAIT_PERIOD);
+
 	udelay(REMOVE_WAIT_DELAY);
 }
 EXPORT_SYMBOL_GPL(hisi_qm_wait_task_finish);
@@ -2439,7 +2489,7 @@ static void hisi_qm_pre_init(struct hisi_qm *qm)
 	mutex_init(&qm->mailbox_lock);
 	init_rwsem(&qm->qps_lock);
 	qm->qp_in_used = 0;
-	qm->is_frozen = false;
+	qm->misc_ctl = false;
 }
 
 static void hisi_qm_pci_uninit(struct hisi_qm *qm)
@@ -2558,15 +2608,9 @@ static int qm_eq_ctx_cfg(struct hisi_qm *qm)
 	dma_addr_t eqc_dma;
 	int ret;
 
-	eqc = kzalloc(sizeof(struct qm_eqc), GFP_KERNEL); //todo
+	eqc = kzalloc(sizeof(struct qm_eqc), GFP_KERNEL);
 	if (!eqc)
 		return -ENOMEM;
-	eqc_dma = dma_map_single(dev, eqc, sizeof(struct qm_eqc),
-				 DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, eqc_dma)) {
-		kfree(eqc);
-		return -ENOMEM;
-	}
 
 	eqc->base_l = cpu_to_le32(lower_32_bits(qm->eqe_dma));
 	eqc->base_h = cpu_to_le32(upper_32_bits(qm->eqe_dma));
@@ -2574,6 +2618,13 @@ static int qm_eq_ctx_cfg(struct hisi_qm *qm)
 		eqc->dw3 = cpu_to_le32(QM_EQE_AEQE_SIZE);
 	eqc->dw6 = cpu_to_le32((QM_EQ_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT));
 
+	eqc_dma = dma_map_single(dev, eqc, sizeof(struct qm_eqc),
+				 DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, eqc_dma)) {
+		kfree(eqc);
+		return -ENOMEM;
+	}
+
 	ret = qm_mb(qm, QM_MB_CMD_EQC, eqc_dma, 0, 0);
 	dma_unmap_single(dev, eqc_dma, sizeof(struct qm_eqc), DMA_TO_DEVICE);
 	kfree(eqc);
@@ -2591,6 +2642,11 @@ static int qm_aeq_ctx_cfg(struct hisi_qm *qm)
 	aeqc = kzalloc(sizeof(struct qm_aeqc), GFP_KERNEL);
 	if (!aeqc)
 		return -ENOMEM;
+
+	aeqc->base_l = cpu_to_le32(lower_32_bits(qm->aeqe_dma));
+	aeqc->base_h = cpu_to_le32(upper_32_bits(qm->aeqe_dma));
+	aeqc->dw6 = cpu_to_le32((QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT));
+
 	aeqc_dma = dma_map_single(dev, aeqc, sizeof(struct qm_aeqc),
 				  DMA_TO_DEVICE);
 	if (dma_mapping_error(dev, aeqc_dma)) {
@@ -2598,10 +2654,6 @@ static int qm_aeq_ctx_cfg(struct hisi_qm *qm)
 		return -ENOMEM;
 	}
 
-	aeqc->base_l = cpu_to_le32(lower_32_bits(qm->aeqe_dma));
-	aeqc->base_h = cpu_to_le32(upper_32_bits(qm->aeqe_dma));
-	aeqc->dw6 = cpu_to_le32((QM_Q_DEPTH - 1) | (1 << QM_EQC_PHASE_SHIFT));
-
 	ret = qm_mb(qm, QM_MB_CMD_AEQC, aeqc_dma, 0, 0);
 	dma_unmap_single(dev, aeqc_dma, sizeof(struct qm_aeqc), DMA_TO_DEVICE);
 	kfree(aeqc);
@@ -2677,7 +2729,7 @@ int hisi_qm_start(struct hisi_qm *qm)
 		return -EPERM;
 	}
 
-	dev_dbg(dev, "qm start with %d queue pairs\n", qm->qp_num);
+	dev_dbg(dev, "qm start with %u queue pairs\n", qm->qp_num);
 
 	if (!qm->qp_num) {
 		dev_err(dev, "qp_num should not be 0\n");
@@ -3112,7 +3164,7 @@ int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num,
 
 	mutex_unlock(&qm_list->lock);
 	if (ret)
-		pr_info("Failed to create qps, node[%d], alg[%d], qp[%d]!\n",
+		pr_info("Failed to create qps, node[%d], alg[%u], qp[%d]!\n",
 			node, alg_type, qp_num);
 
 err:
@@ -3248,7 +3300,7 @@ EXPORT_SYMBOL_GPL(hisi_qm_sriov_disable);
 int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs)
 {
 	if (num_vfs == 0)
-		return hisi_qm_sriov_disable(pdev, 0);
+		return hisi_qm_sriov_disable(pdev, false);
 	else
 		return hisi_qm_sriov_enable(pdev, num_vfs);
 }
@@ -3269,12 +3321,19 @@ static enum acc_err_result qm_dev_err_handle(struct hisi_qm *qm)
 		if (err_sts & qm->err_ini->err_info.ecc_2bits_mask)
 			qm->err_status.is_dev_ecc_mbit = true;
 
-		if (!qm->err_ini->log_dev_hw_err) {
-			dev_err(&qm->pdev->dev, "Device doesn't support log hw error!\n");
-			return ACC_ERR_NEED_RESET;
+		if (qm->err_ini->log_dev_hw_err)
+			qm->err_ini->log_dev_hw_err(qm, err_sts);
+
+		/* ce error does not need to be reset */
+		if ((err_sts | qm->err_ini->err_info.dev_ce_mask) ==
+		     qm->err_ini->err_info.dev_ce_mask) {
+			if (qm->err_ini->clear_dev_hw_err_status)
+				qm->err_ini->clear_dev_hw_err_status(qm,
+								err_sts);
+
+			return ACC_ERR_RECOVERED;
 		}
 
-		qm->err_ini->log_dev_hw_err(qm, err_sts);
 		return ACC_ERR_NEED_RESET;
 	}
 
@@ -3313,7 +3372,7 @@ pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev,
 	if (pdev->is_virtfn)
 		return PCI_ERS_RESULT_NONE;
 
-	pci_info(pdev, "PCI error detected, state(=%d)!!\n", state);
+	pci_info(pdev, "PCI error detected, state(=%u)!!\n", state);
 	if (state == pci_channel_io_perm_failure)
 		return PCI_ERS_RESULT_DISCONNECT;
 
@@ -3465,7 +3524,7 @@ static int qm_reset_prepare_ready(struct hisi_qm *qm)
 	int delay = 0;
 
 	/* All reset requests need to be queued for processing */
-	while (test_and_set_bit(QM_DEV_RESET_FLAG, &pf_qm->reset_flag)) {
+	while (test_and_set_bit(QM_RESETTING, &pf_qm->misc_ctl)) {
 		msleep(++delay);
 		if (delay > QM_RESET_WAIT_TIMEOUT)
 			return -EBUSY;
@@ -3489,6 +3548,7 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm)
 		ret = qm_vf_reset_prepare(qm, QM_SOFT_RESET);
 		if (ret) {
 			pci_err(pdev, "Fails to stop VFs!\n");
+			clear_bit(QM_RESETTING, &qm->misc_ctl);
 			return ret;
 		}
 	}
@@ -3496,9 +3556,12 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm)
 	ret = hisi_qm_stop(qm, QM_SOFT_RESET);
 	if (ret) {
 		pci_err(pdev, "Fails to stop QM!\n");
+		clear_bit(QM_RESETTING, &qm->misc_ctl);
 		return ret;
 	}
 
+	clear_bit(QM_RST_SCHED, &qm->misc_ctl);
+
 	return 0;
 }
 
@@ -3736,7 +3799,7 @@ static int qm_controller_reset_done(struct hisi_qm *qm)
 	hisi_qm_dev_err_init(qm);
 	qm_restart_done(qm);
 
-	clear_bit(QM_DEV_RESET_FLAG, &qm->reset_flag);
+	clear_bit(QM_RESETTING, &qm->misc_ctl);
 
 	return 0;
 }
@@ -3749,18 +3812,23 @@ static int qm_controller_reset(struct hisi_qm *qm)
 	pci_info(pdev, "Controller resetting...\n");
 
 	ret = qm_controller_reset_prepare(qm);
-	if (ret)
+	if (ret) {
+		clear_bit(QM_RST_SCHED, &qm->misc_ctl);
 		return ret;
+	}
 
 	ret = qm_soft_reset(qm);
 	if (ret) {
 		pci_err(pdev, "Controller reset failed (%d)\n", ret);
+		clear_bit(QM_RESETTING, &qm->misc_ctl);
 		return ret;
 	}
 
 	ret = qm_controller_reset_done(qm);
-	if (ret)
+	if (ret) {
+		clear_bit(QM_RESETTING, &qm->misc_ctl);
 		return ret;
+	}
 
 	pci_info(pdev, "Controller reset complete\n");
 
@@ -3867,8 +3935,6 @@ static bool qm_flr_reset_complete(struct pci_dev *pdev)
 		return false;
 	}
 
-	clear_bit(QM_DEV_RESET_FLAG, &qm->reset_flag);
-
 	return true;
 }
 
@@ -3912,6 +3978,8 @@ void hisi_qm_reset_done(struct pci_dev *pdev)
 flr_done:
 	if (qm_flr_reset_complete(pdev))
 		pci_info(pdev, "FLR reset complete\n");
+
+	clear_bit(QM_RESETTING, &qm->misc_ctl);
 }
 EXPORT_SYMBOL_GPL(hisi_qm_reset_done);
 
@@ -3922,7 +3990,9 @@ static irqreturn_t qm_abnormal_irq(int irq, void *data)
 
 	atomic64_inc(&qm->debug.dfx.abnormal_irq_cnt);
 	ret = qm_process_dev_error(qm);
-	if (ret == ACC_ERR_NEED_RESET)
+	if (ret == ACC_ERR_NEED_RESET &&
+	    !test_bit(QM_DRIVER_REMOVING, &qm->misc_ctl) &&
+	    !test_and_set_bit(QM_RST_SCHED, &qm->misc_ctl))
 		schedule_work(&qm->rst_work);
 
 	return IRQ_HANDLED;
@@ -3934,21 +4004,20 @@ static int qm_irq_register(struct hisi_qm *qm)
 	int ret;
 
 	ret = request_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR),
-			  qm_irq, IRQF_SHARED, qm->dev_name, qm);
+			  qm_irq, 0, qm->dev_name, qm);
 	if (ret)
 		return ret;
 
 	if (qm->ver != QM_HW_V1) {
 		ret = request_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR),
-				  qm_aeq_irq, IRQF_SHARED, qm->dev_name, qm);
+				  qm_aeq_irq, 0, qm->dev_name, qm);
 		if (ret)
 			goto err_aeq_irq;
 
 		if (qm->fun_type == QM_HW_PF) {
 			ret = request_irq(pci_irq_vector(pdev,
 					  QM_ABNORMAL_EVENT_IRQ_VECTOR),
-					  qm_abnormal_irq, IRQF_SHARED,
-					  qm->dev_name, qm);
+					  qm_abnormal_irq, 0, qm->dev_name, qm);
 			if (ret)
 				goto err_abonormal_irq;
 		}
@@ -4004,6 +4073,9 @@ int hisi_qm_alg_register(struct hisi_qm *qm, struct hisi_qm_list *qm_list)
 {
 	int flag = 0;
 	int ret = 0;
+	/* HW V2 not support both use uacce sva mode and hardware crypto algs */
+	if (qm->ver <= QM_HW_V2 && qm->use_sva)
+		return 0;
 
 	mutex_lock(&qm_list->lock);
 	if (list_empty(&qm_list->list))
@@ -4035,6 +4107,9 @@ EXPORT_SYMBOL_GPL(hisi_qm_alg_register);
  */
 void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list)
 {
+	if (qm->ver <= QM_HW_V2 && qm->use_sva)
+		return;
+
 	mutex_lock(&qm_list->lock);
 	list_del(&qm->list);
 	mutex_unlock(&qm_list->lock);
diff --git a/drivers/crypto/hisilicon/qm.h b/drivers/crypto/hisilicon/qm.h
index 8624d1288afe..54967c6b9c78 100644
--- a/drivers/crypto/hisilicon/qm.h
+++ b/drivers/crypto/hisilicon/qm.h
@@ -85,6 +85,11 @@
 /* page number for queue file region */
 #define QM_DOORBELL_PAGE_NR		1
 
+/* uacce mode of the driver */
+#define UACCE_MODE_NOUACCE		0 /* don't use uacce */
+#define UACCE_MODE_SVA			1 /* use uacce sva mode */
+#define UACCE_MODE_DESC	"0(default) means only register to crypto, 1 means both register to crypto and uacce"
+
 enum qm_stop_reason {
 	QM_NORMAL,
 	QM_SOFT_RESET,
@@ -168,6 +173,7 @@ struct hisi_qm_err_info {
 	char *acpi_rst;
 	u32 msi_wr_port;
 	u32 ecc_2bits_mask;
+	u32 dev_ce_mask;
 	u32 ce;
 	u32 nfe;
 	u32 fe;
@@ -225,7 +231,7 @@ struct hisi_qm {
 	struct hisi_qm_status status;
 	const struct hisi_qm_err_ini *err_ini;
 	struct hisi_qm_err_status err_status;
-	unsigned long reset_flag;
+	unsigned long misc_ctl; /* driver removing and reset sched */
 
 	struct rw_semaphore qps_lock;
 	struct idr qp_idr;
@@ -249,6 +255,7 @@ struct hisi_qm {
 	resource_size_t phys_base;
 	resource_size_t phys_size;
 	struct uacce_device *uacce;
+	int mode;
 };
 
 struct hisi_qp_status {
@@ -282,6 +289,7 @@ struct hisi_qp {
 
 	struct hisi_qm *qm;
 	bool is_resetting;
+	bool is_in_kernel;
 	u16 pasid;
 	struct uacce_queue *uacce_q;
 };
@@ -299,7 +307,7 @@ static inline int q_num_set(const char *val, const struct kernel_param *kp,
 
 	if (!pdev) {
 		q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2);
-		pr_info("No device found currently, suppose queue number is %d\n",
+		pr_info("No device found currently, suppose queue number is %u\n",
 			q_num);
 	} else {
 		if (pdev->revision == QM_HW_V1)
@@ -333,6 +341,27 @@ static inline int vfs_num_set(const char *val, const struct kernel_param *kp)
 	return param_set_int(val, kp);
 }
 
+static inline int mode_set(const char *val, const struct kernel_param *kp)
+{
+	u32 n;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+
+	ret = kstrtou32(val, 10, &n);
+	if (ret != 0 || (n != UACCE_MODE_SVA &&
+			 n != UACCE_MODE_NOUACCE))
+		return -EINVAL;
+
+	return param_set_int(val, kp);
+}
+
+static inline int uacce_mode_set(const char *val, const struct kernel_param *kp)
+{
+	return mode_set(val, kp);
+}
+
 static inline void hisi_qm_init_list(struct hisi_qm_list *qm_list)
 {
 	INIT_LIST_HEAD(&qm_list->list);
diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c
index b35c1c2271a3..dc68ba76f65e 100644
--- a/drivers/crypto/hisilicon/sec2/sec_main.c
+++ b/drivers/crypto/hisilicon/sec2/sec_main.c
@@ -13,6 +13,7 @@
 #include <linux/pci.h>
 #include <linux/seq_file.h>
 #include <linux/topology.h>
+#include <linux/uacce.h>
 
 #include "sec.h"
 
@@ -74,6 +75,16 @@
 
 #define SEC_USER0_SMMU_NORMAL		(BIT(23) | BIT(15))
 #define SEC_USER1_SMMU_NORMAL		(BIT(31) | BIT(23) | BIT(15) | BIT(7))
+#define SEC_USER1_ENABLE_CONTEXT_SSV	BIT(24)
+#define SEC_USER1_ENABLE_DATA_SSV	BIT(16)
+#define SEC_USER1_WB_CONTEXT_SSV	BIT(8)
+#define SEC_USER1_WB_DATA_SSV		BIT(0)
+#define SEC_USER1_SVA_SET		(SEC_USER1_ENABLE_CONTEXT_SSV | \
+					SEC_USER1_ENABLE_DATA_SSV | \
+					SEC_USER1_WB_CONTEXT_SSV |  \
+					SEC_USER1_WB_DATA_SSV)
+#define SEC_USER1_SMMU_SVA		(SEC_USER1_SMMU_NORMAL | SEC_USER1_SVA_SET)
+#define SEC_USER1_SMMU_MASK		(~SEC_USER1_SVA_SET)
 #define SEC_CORE_INT_STATUS_M_ECC	BIT(2)
 
 #define SEC_DELAY_10_US			10
@@ -233,6 +244,18 @@ struct hisi_qp **sec_create_qps(void)
 	return NULL;
 }
 
+static const struct kernel_param_ops sec_uacce_mode_ops = {
+	.set = uacce_mode_set,
+	.get = param_get_int,
+};
+
+/*
+ * uacce_mode = 0 means sec only register to crypto,
+ * uacce_mode = 1 means sec both register to crypto and uacce.
+ */
+static u32 uacce_mode = UACCE_MODE_NOUACCE;
+module_param_cb(uacce_mode, &sec_uacce_mode_ops, &uacce_mode, 0444);
+MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC);
 
 static const struct pci_device_id sec_dev_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, SEC_PF_PCI_DEVICE_ID) },
@@ -299,7 +322,11 @@ static int sec_engine_init(struct hisi_qm *qm)
 	writel_relaxed(reg, SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL0_REG));
 
 	reg = readl_relaxed(SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL1_REG));
-	reg |= SEC_USER1_SMMU_NORMAL;
+	reg &= SEC_USER1_SMMU_MASK;
+	if (qm->use_sva && qm->ver == QM_HW_V2)
+		reg |= SEC_USER1_SMMU_SVA;
+	else
+		reg |= SEC_USER1_SMMU_NORMAL;
 	writel_relaxed(reg, SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL1_REG));
 
 	writel(SEC_SINGLE_PORT_MAX_TRANS,
@@ -725,6 +752,7 @@ static const struct hisi_qm_err_ini sec_err_ini = {
 				  QM_ACC_WB_NOT_READY_TIMEOUT,
 		.fe		= 0,
 		.ecc_2bits_mask	= SEC_CORE_INT_STATUS_M_ECC,
+		.dev_ce_mask	= SEC_RAS_CE_ENB_MSK,
 		.msi_wr_port	= BIT(0),
 		.acpi_rst	= "SRST",
 	}
@@ -758,6 +786,8 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 
 	qm->pdev = pdev;
 	qm->ver = pdev->revision;
+	qm->algs = "cipher\ndigest\naead\n";
+	qm->mode = uacce_mode;
 	qm->sqe_size = SEC_SQE_SIZE;
 	qm->dev_name = sec_name;
 
@@ -885,6 +915,14 @@ static int sec_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_qm_stop;
 	}
 
+	if (qm->uacce) {
+		ret = uacce_register(qm->uacce);
+		if (ret) {
+			pci_err(pdev, "failed to register uacce (%d)!\n", ret);
+			goto err_alg_unregister;
+		}
+	}
+
 	if (qm->fun_type == QM_HW_PF && vfs_num) {
 		ret = hisi_qm_sriov_enable(pdev, vfs_num);
 		if (ret < 0)
@@ -912,7 +950,7 @@ static void sec_remove(struct pci_dev *pdev)
 	hisi_qm_wait_task_finish(qm, &sec_devices);
 	hisi_qm_alg_unregister(qm, &sec_devices);
 	if (qm->fun_type == QM_HW_PF && qm->vfs_num)
-		hisi_qm_sriov_disable(pdev, qm->is_frozen);
+		hisi_qm_sriov_disable(pdev, true);
 
 	sec_debugfs_exit(qm);
 
diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c
index 4fb5a32bf830..02c445722445 100644
--- a/drivers/crypto/hisilicon/zip/zip_main.c
+++ b/drivers/crypto/hisilicon/zip/zip_main.c
@@ -66,6 +66,7 @@
 #define HZIP_CORE_INT_STATUS_M_ECC	BIT(1)
 #define HZIP_CORE_SRAM_ECC_ERR_INFO	0x301148
 #define HZIP_CORE_INT_RAS_CE_ENB	0x301160
+#define HZIP_CORE_INT_RAS_CE_ENABLE	0x1
 #define HZIP_CORE_INT_RAS_NFE_ENB	0x301164
 #define HZIP_CORE_INT_RAS_FE_ENB        0x301168
 #define HZIP_CORE_INT_RAS_NFE_ENABLE	0x7FE
@@ -211,6 +212,19 @@ static const struct debugfs_reg32 hzip_dfx_regs[] = {
 	{"HZIP_DECOMP_LZ77_CURR_ST       ",  0x9cull},
 };
 
+static const struct kernel_param_ops zip_uacce_mode_ops = {
+	.set = uacce_mode_set,
+	.get = param_get_int,
+};
+
+/*
+ * uacce_mode = 0 means zip only register to crypto,
+ * uacce_mode = 1 means zip both register to crypto and uacce.
+ */
+static u32 uacce_mode = UACCE_MODE_NOUACCE;
+module_param_cb(uacce_mode, &zip_uacce_mode_ops, &uacce_mode, 0444);
+MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC);
+
 static int pf_q_num_set(const char *val, const struct kernel_param *kp)
 {
 	return q_num_set(val, kp, PCI_DEVICE_ID_ZIP_PF);
@@ -279,7 +293,7 @@ static int hisi_zip_set_user_domain_and_cache(struct hisi_qm *qm)
 	writel(AXUSER_BASE, base + HZIP_SGL_RUSER_32_63);
 	writel(AXUSER_BASE, base + HZIP_BD_WUSER_32_63);
 
-	if (qm->use_sva) {
+	if (qm->use_sva && qm->ver == QM_HW_V2) {
 		writel(AXUSER_BASE | AXUSER_SSV, base + HZIP_DATA_RUSER_32_63);
 		writel(AXUSER_BASE | AXUSER_SSV, base + HZIP_DATA_WUSER_32_63);
 	} else {
@@ -314,7 +328,8 @@ static void hisi_zip_hw_error_enable(struct hisi_qm *qm)
 	writel(HZIP_CORE_INT_MASK_ALL, qm->io_base + HZIP_CORE_INT_SOURCE);
 
 	/* configure error type */
-	writel(0x1, qm->io_base + HZIP_CORE_INT_RAS_CE_ENB);
+	writel(HZIP_CORE_INT_RAS_CE_ENABLE,
+	       qm->io_base + HZIP_CORE_INT_RAS_CE_ENB);
 	writel(0x0, qm->io_base + HZIP_CORE_INT_RAS_FE_ENB);
 	writel(HZIP_CORE_INT_RAS_NFE_ENABLE,
 	       qm->io_base + HZIP_CORE_INT_RAS_NFE_ENB);
@@ -714,6 +729,7 @@ static const struct hisi_qm_err_ini hisi_zip_err_ini = {
 					  QM_ACC_WB_NOT_READY_TIMEOUT,
 		.fe			= 0,
 		.ecc_2bits_mask		= HZIP_CORE_INT_STATUS_M_ECC,
+		.dev_ce_mask		= HZIP_CORE_INT_RAS_CE_ENABLE,
 		.msi_wr_port		= HZIP_WR_PORT,
 		.acpi_rst		= "ZRST",
 	}
@@ -752,6 +768,7 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 	qm->pdev = pdev;
 	qm->ver = pdev->revision;
 	qm->algs = "zlib\ngzip";
+	qm->mode = uacce_mode;
 	qm->sqe_size = HZIP_SQE_SIZE;
 	qm->dev_name = hisi_zip_name;
 
@@ -887,7 +904,7 @@ static void hisi_zip_remove(struct pci_dev *pdev)
 	hisi_qm_alg_unregister(qm, &zip_devices);
 
 	if (qm->fun_type == QM_HW_PF && qm->vfs_num)
-		hisi_qm_sriov_disable(pdev, qm->is_frozen);
+		hisi_qm_sriov_disable(pdev, true);
 
 	hisi_zip_debugfs_exit(qm);
 	hisi_qm_stop(qm, QM_NORMAL);
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 2e1562108a85..6364583b88b2 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -1166,11 +1166,8 @@ static int safexcel_request_ring_irq(void *pdev, int irqid,
 		dev = &plf_pdev->dev;
 		irq = platform_get_irq_byname(plf_pdev, irq_name);
 
-		if (irq < 0) {
-			dev_err(dev, "unable to get IRQ '%s' (err %d)\n",
-				irq_name, irq);
+		if (irq < 0)
 			return irq;
-		}
 	} else {
 		return -ENXIO;
 	}
@@ -1999,3 +1996,4 @@ MODULE_AUTHOR("Ofer Heifetz <oferh@marvell.com>");
 MODULE_AUTHOR("Igal Liberman <igall@marvell.com>");
 MODULE_DESCRIPTION("Support for SafeXcel cryptographic engines: EIP97 & EIP197");
 MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 50fb6d90a2e0..bc60b5802256 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -13,6 +13,7 @@
 #include <crypto/sha3.h>
 #include <crypto/skcipher.h>
 #include <crypto/sm3.h>
+#include <crypto/internal/cipher.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmapool.h>
diff --git a/drivers/crypto/keembay/Kconfig b/drivers/crypto/keembay/Kconfig
index f2e17b0c4fa0..00cf8f028cb9 100644
--- a/drivers/crypto/keembay/Kconfig
+++ b/drivers/crypto/keembay/Kconfig
@@ -38,3 +38,34 @@ config CRYPTO_DEV_KEEMBAY_OCS_AES_SM4_CTS
 	  Provides OCS version of cts(cbc(aes)) and cts(cbc(sm4)).
 
 	  Intel does not recommend use of CTS mode with AES/SM4.
+
+config CRYPTO_DEV_KEEMBAY_OCS_HCU
+	tristate "Support for Intel Keem Bay OCS HCU HW acceleration"
+	select CRYPTO_HASH
+	select CRYPTO_ENGINE
+	depends on HAS_IOMEM
+	depends on ARCH_KEEMBAY || COMPILE_TEST
+	depends on OF || COMPILE_TEST
+	help
+	  Support for Intel Keem Bay Offload and Crypto Subsystem (OCS) Hash
+	  Control Unit (HCU) hardware acceleration for use with Crypto API.
+
+	  Provides OCS HCU hardware acceleration of sha256, sha384, sha512, and
+	  sm3, as well as the HMAC variant of these algorithms.
+
+	  Say Y or M if you're building for the Intel Keem Bay SoC. If compiled
+	  as a module, the module will be called keembay-ocs-hcu.
+
+	  If unsure, say N.
+
+config CRYPTO_DEV_KEEMBAY_OCS_HCU_HMAC_SHA224
+	bool "Enable sha224 and hmac(sha224) support in Intel Keem Bay OCS HCU"
+	depends on CRYPTO_DEV_KEEMBAY_OCS_HCU
+	help
+	  Enables support for sha224 and hmac(sha224) algorithms in the Intel
+	  Keem Bay OCS HCU driver. Intel recommends not to use these
+	  algorithms.
+
+	  Provides OCS HCU hardware acceleration of sha224 and hmac(224).
+
+	  If unsure, say N.
diff --git a/drivers/crypto/keembay/Makefile b/drivers/crypto/keembay/Makefile
index f21e2c4ab3b3..aea03d4432c4 100644
--- a/drivers/crypto/keembay/Makefile
+++ b/drivers/crypto/keembay/Makefile
@@ -3,3 +3,6 @@
 #
 obj-$(CONFIG_CRYPTO_DEV_KEEMBAY_OCS_AES_SM4) += keembay-ocs-aes.o
 keembay-ocs-aes-objs := keembay-ocs-aes-core.o ocs-aes.o
+
+obj-$(CONFIG_CRYPTO_DEV_KEEMBAY_OCS_HCU) += keembay-ocs-hcu.o
+keembay-ocs-hcu-objs := keembay-ocs-hcu-core.o ocs-hcu.o
diff --git a/drivers/crypto/keembay/keembay-ocs-hcu-core.c b/drivers/crypto/keembay/keembay-ocs-hcu-core.c
new file mode 100644
index 000000000000..c4b97b4160e9
--- /dev/null
+++ b/drivers/crypto/keembay/keembay-ocs-hcu-core.c
@@ -0,0 +1,1264 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Keem Bay OCS HCU Crypto Driver.
+ *
+ * Copyright (C) 2018-2020 Intel Corporation
+ */
+
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+
+#include <crypto/engine.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/sha2.h>
+#include <crypto/sm3.h>
+#include <crypto/hmac.h>
+#include <crypto/internal/hash.h>
+
+#include "ocs-hcu.h"
+
+#define DRV_NAME	"keembay-ocs-hcu"
+
+/* Flag marking a final request. */
+#define REQ_FINAL			BIT(0)
+/* Flag marking a HMAC request. */
+#define REQ_FLAGS_HMAC			BIT(1)
+/* Flag set when HW HMAC is being used. */
+#define REQ_FLAGS_HMAC_HW		BIT(2)
+/* Flag set when SW HMAC is being used. */
+#define REQ_FLAGS_HMAC_SW		BIT(3)
+
+/**
+ * struct ocs_hcu_ctx: OCS HCU Transform context.
+ * @engine_ctx:	 Crypto Engine context.
+ * @hcu_dev:	 The OCS HCU device used by the transformation.
+ * @key:	 The key (used only for HMAC transformations).
+ * @key_len:	 The length of the key.
+ * @is_sm3_tfm:  Whether or not this is an SM3 transformation.
+ * @is_hmac_tfm: Whether or not this is a HMAC transformation.
+ */
+struct ocs_hcu_ctx {
+	struct crypto_engine_ctx engine_ctx;
+	struct ocs_hcu_dev *hcu_dev;
+	u8 key[SHA512_BLOCK_SIZE];
+	size_t key_len;
+	bool is_sm3_tfm;
+	bool is_hmac_tfm;
+};
+
+/**
+ * struct ocs_hcu_rctx - Context for the request.
+ * @hcu_dev:	    OCS HCU device to be used to service the request.
+ * @flags:	    Flags tracking request status.
+ * @algo:	    Algorithm to use for the request.
+ * @blk_sz:	    Block size of the transformation / request.
+ * @dig_sz:	    Digest size of the transformation / request.
+ * @dma_list:	    OCS DMA linked list.
+ * @hash_ctx:	    OCS HCU hashing context.
+ * @buffer:	    Buffer to store: partial block of data and SW HMAC
+ *		    artifacts (ipad, opad, etc.).
+ * @buf_cnt:	    Number of bytes currently stored in the buffer.
+ * @buf_dma_addr:   The DMA address of @buffer (when mapped).
+ * @buf_dma_count:  The number of bytes in @buffer currently DMA-mapped.
+ * @sg:		    Head of the scatterlist entries containing data.
+ * @sg_data_total:  Total data in the SG list at any time.
+ * @sg_data_offset: Offset into the data of the current individual SG node.
+ * @sg_dma_nents:   Number of sg entries mapped in dma_list.
+ */
+struct ocs_hcu_rctx {
+	struct ocs_hcu_dev	*hcu_dev;
+	u32			flags;
+	enum ocs_hcu_algo	algo;
+	size_t			blk_sz;
+	size_t			dig_sz;
+	struct ocs_hcu_dma_list	*dma_list;
+	struct ocs_hcu_hash_ctx	hash_ctx;
+	/*
+	 * Buffer is double the block size because we need space for SW HMAC
+	 * artifacts, i.e:
+	 * - ipad (1 block) + a possible partial block of data.
+	 * - opad (1 block) + digest of H(k ^ ipad || m)
+	 */
+	u8			buffer[2 * SHA512_BLOCK_SIZE];
+	size_t			buf_cnt;
+	dma_addr_t		buf_dma_addr;
+	size_t			buf_dma_count;
+	struct scatterlist	*sg;
+	unsigned int		sg_data_total;
+	unsigned int		sg_data_offset;
+	unsigned int		sg_dma_nents;
+};
+
+/**
+ * struct ocs_hcu_drv - Driver data
+ * @dev_list:	The list of HCU devices.
+ * @lock:	The lock protecting dev_list.
+ */
+struct ocs_hcu_drv {
+	struct list_head dev_list;
+	spinlock_t lock; /* Protects dev_list. */
+};
+
+static struct ocs_hcu_drv ocs_hcu = {
+	.dev_list = LIST_HEAD_INIT(ocs_hcu.dev_list),
+	.lock = __SPIN_LOCK_UNLOCKED(ocs_hcu.lock),
+};
+
+/*
+ * Return the total amount of data in the request; that is: the data in the
+ * request buffer + the data in the sg list.
+ */
+static inline unsigned int kmb_get_total_data(struct ocs_hcu_rctx *rctx)
+{
+	return rctx->sg_data_total + rctx->buf_cnt;
+}
+
+/* Move remaining content of scatter-gather list to context buffer. */
+static int flush_sg_to_ocs_buffer(struct ocs_hcu_rctx *rctx)
+{
+	size_t count;
+
+	if (rctx->sg_data_total > (sizeof(rctx->buffer) - rctx->buf_cnt)) {
+		WARN(1, "%s: sg data does not fit in buffer\n", __func__);
+		return -EINVAL;
+	}
+
+	while (rctx->sg_data_total) {
+		if (!rctx->sg) {
+			WARN(1, "%s: unexpected NULL sg\n", __func__);
+			return -EINVAL;
+		}
+		/*
+		 * If current sg has been fully processed, skip to the next
+		 * one.
+		 */
+		if (rctx->sg_data_offset == rctx->sg->length) {
+			rctx->sg = sg_next(rctx->sg);
+			rctx->sg_data_offset = 0;
+			continue;
+		}
+		/*
+		 * Determine the maximum data available to copy from the node.
+		 * Minimum of the length left in the sg node, or the total data
+		 * in the request.
+		 */
+		count = min(rctx->sg->length - rctx->sg_data_offset,
+			    rctx->sg_data_total);
+		/* Copy from scatter-list entry to context buffer. */
+		scatterwalk_map_and_copy(&rctx->buffer[rctx->buf_cnt],
+					 rctx->sg, rctx->sg_data_offset,
+					 count, 0);
+
+		rctx->sg_data_offset += count;
+		rctx->sg_data_total -= count;
+		rctx->buf_cnt += count;
+	}
+
+	return 0;
+}
+
+static struct ocs_hcu_dev *kmb_ocs_hcu_find_dev(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ocs_hcu_ctx *tctx = crypto_ahash_ctx(tfm);
+
+	/* If the HCU device for the request was previously set, return it. */
+	if (tctx->hcu_dev)
+		return tctx->hcu_dev;
+
+	/*
+	 * Otherwise, get the first HCU device available (there should be one
+	 * and only one device).
+	 */
+	spin_lock_bh(&ocs_hcu.lock);
+	tctx->hcu_dev = list_first_entry_or_null(&ocs_hcu.dev_list,
+						 struct ocs_hcu_dev,
+						 list);
+	spin_unlock_bh(&ocs_hcu.lock);
+
+	return tctx->hcu_dev;
+}
+
+/* Free OCS DMA linked list and DMA-able context buffer. */
+static void kmb_ocs_hcu_dma_cleanup(struct ahash_request *req,
+				    struct ocs_hcu_rctx *rctx)
+{
+	struct ocs_hcu_dev *hcu_dev = rctx->hcu_dev;
+	struct device *dev = hcu_dev->dev;
+
+	/* Unmap rctx->buffer (if mapped). */
+	if (rctx->buf_dma_count) {
+		dma_unmap_single(dev, rctx->buf_dma_addr, rctx->buf_dma_count,
+				 DMA_TO_DEVICE);
+		rctx->buf_dma_count = 0;
+	}
+
+	/* Unmap req->src (if mapped). */
+	if (rctx->sg_dma_nents) {
+		dma_unmap_sg(dev, req->src, rctx->sg_dma_nents, DMA_TO_DEVICE);
+		rctx->sg_dma_nents = 0;
+	}
+
+	/* Free dma_list (if allocated). */
+	if (rctx->dma_list) {
+		ocs_hcu_dma_list_free(hcu_dev, rctx->dma_list);
+		rctx->dma_list = NULL;
+	}
+}
+
+/*
+ * Prepare for DMA operation:
+ * - DMA-map request context buffer (if needed)
+ * - DMA-map SG list (only the entries to be processed, see note below)
+ * - Allocate OCS HCU DMA linked list (number of elements =  SG entries to
+ *   process + context buffer (if not empty)).
+ * - Add DMA-mapped request context buffer to OCS HCU DMA list.
+ * - Add SG entries to DMA list.
+ *
+ * Note: if this is a final request, we process all the data in the SG list,
+ * otherwise we can only process up to the maximum amount of block-aligned data
+ * (the remainder will be put into the context buffer and processed in the next
+ * request).
+ */
+static int kmb_ocs_dma_prepare(struct ahash_request *req)
+{
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+	struct device *dev = rctx->hcu_dev->dev;
+	unsigned int remainder = 0;
+	unsigned int total;
+	size_t nents;
+	size_t count;
+	int rc;
+	int i;
+
+	/* This function should be called only when there is data to process. */
+	total = kmb_get_total_data(rctx);
+	if (!total)
+		return -EINVAL;
+
+	/*
+	 * If this is not a final DMA (terminated DMA), the data passed to the
+	 * HCU must be aligned to the block size; compute the remainder data to
+	 * be processed in the next request.
+	 */
+	if (!(rctx->flags & REQ_FINAL))
+		remainder = total % rctx->blk_sz;
+
+	/* Determine the number of scatter gather list entries to process. */
+	nents = sg_nents_for_len(req->src, rctx->sg_data_total - remainder);
+
+	/* If there are entries to process, map them. */
+	if (nents) {
+		rctx->sg_dma_nents = dma_map_sg(dev, req->src, nents,
+						DMA_TO_DEVICE);
+		if (!rctx->sg_dma_nents) {
+			dev_err(dev, "Failed to MAP SG\n");
+			rc = -ENOMEM;
+			goto cleanup;
+		}
+		/*
+		 * The value returned by dma_map_sg() can be < nents; so update
+		 * nents accordingly.
+		 */
+		nents = rctx->sg_dma_nents;
+	}
+
+	/*
+	 * If context buffer is not empty, map it and add extra DMA entry for
+	 * it.
+	 */
+	if (rctx->buf_cnt) {
+		rctx->buf_dma_addr = dma_map_single(dev, rctx->buffer,
+						    rctx->buf_cnt,
+						    DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, rctx->buf_dma_addr)) {
+			dev_err(dev, "Failed to map request context buffer\n");
+			rc = -ENOMEM;
+			goto cleanup;
+		}
+		rctx->buf_dma_count = rctx->buf_cnt;
+		/* Increase number of dma entries. */
+		nents++;
+	}
+
+	/* Allocate OCS HCU DMA list. */
+	rctx->dma_list = ocs_hcu_dma_list_alloc(rctx->hcu_dev, nents);
+	if (!rctx->dma_list) {
+		rc = -ENOMEM;
+		goto cleanup;
+	}
+
+	/* Add request context buffer (if previously DMA-mapped) */
+	if (rctx->buf_dma_count) {
+		rc = ocs_hcu_dma_list_add_tail(rctx->hcu_dev, rctx->dma_list,
+					       rctx->buf_dma_addr,
+					       rctx->buf_dma_count);
+		if (rc)
+			goto cleanup;
+	}
+
+	/* Add the SG nodes to be processed to the DMA linked list. */
+	for_each_sg(req->src, rctx->sg, rctx->sg_dma_nents, i) {
+		/*
+		 * The number of bytes to add to the list entry is the minimum
+		 * between:
+		 * - The DMA length of the SG entry.
+		 * - The data left to be processed.
+		 */
+		count = min(rctx->sg_data_total - remainder,
+			    sg_dma_len(rctx->sg) - rctx->sg_data_offset);
+		/*
+		 * Do not create a zero length DMA descriptor. Check in case of
+		 * zero length SG node.
+		 */
+		if (count == 0)
+			continue;
+		/* Add sg to HCU DMA list. */
+		rc = ocs_hcu_dma_list_add_tail(rctx->hcu_dev,
+					       rctx->dma_list,
+					       rctx->sg->dma_address,
+					       count);
+		if (rc)
+			goto cleanup;
+
+		/* Update amount of data remaining in SG list. */
+		rctx->sg_data_total -= count;
+
+		/*
+		 * If  remaining data is equal to remainder (note: 'less than'
+		 * case should never happen in practice), we are done: update
+		 * offset and exit the loop.
+		 */
+		if (rctx->sg_data_total <= remainder) {
+			WARN_ON(rctx->sg_data_total < remainder);
+			rctx->sg_data_offset += count;
+			break;
+		}
+
+		/*
+		 * If we get here is because we need to process the next sg in
+		 * the list; set offset within the sg to 0.
+		 */
+		rctx->sg_data_offset = 0;
+	}
+
+	return 0;
+cleanup:
+	dev_err(dev, "Failed to prepare DMA.\n");
+	kmb_ocs_hcu_dma_cleanup(req, rctx);
+
+	return rc;
+}
+
+static void kmb_ocs_hcu_secure_cleanup(struct ahash_request *req)
+{
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+
+	/* Clear buffer of any data. */
+	memzero_explicit(rctx->buffer, sizeof(rctx->buffer));
+}
+
+static int kmb_ocs_hcu_handle_queue(struct ahash_request *req)
+{
+	struct ocs_hcu_dev *hcu_dev = kmb_ocs_hcu_find_dev(req);
+
+	if (!hcu_dev)
+		return -ENOENT;
+
+	return crypto_transfer_hash_request_to_engine(hcu_dev->engine, req);
+}
+
+static int prepare_ipad(struct ahash_request *req)
+{
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ocs_hcu_ctx *ctx = crypto_ahash_ctx(tfm);
+	int i;
+
+	WARN(rctx->buf_cnt, "%s: Context buffer is not empty\n", __func__);
+	WARN(!(rctx->flags & REQ_FLAGS_HMAC_SW),
+	     "%s: HMAC_SW flag is not set\n", __func__);
+	/*
+	 * Key length must be equal to block size. If key is shorter,
+	 * we pad it with zero (note: key cannot be longer, since
+	 * longer keys are hashed by kmb_ocs_hcu_setkey()).
+	 */
+	if (ctx->key_len > rctx->blk_sz) {
+		WARN(1, "%s: Invalid key length in tfm context\n", __func__);
+		return -EINVAL;
+	}
+	memzero_explicit(&ctx->key[ctx->key_len],
+			 rctx->blk_sz - ctx->key_len);
+	ctx->key_len = rctx->blk_sz;
+	/*
+	 * Prepare IPAD for HMAC. Only done for first block.
+	 * HMAC(k,m) = H(k ^ opad || H(k ^ ipad || m))
+	 * k ^ ipad will be first hashed block.
+	 * k ^ opad will be calculated in the final request.
+	 * Only needed if not using HW HMAC.
+	 */
+	for (i = 0; i < rctx->blk_sz; i++)
+		rctx->buffer[i] = ctx->key[i] ^ HMAC_IPAD_VALUE;
+	rctx->buf_cnt = rctx->blk_sz;
+
+	return 0;
+}
+
+static int kmb_ocs_hcu_do_one_request(struct crypto_engine *engine, void *areq)
+{
+	struct ahash_request *req = container_of(areq, struct ahash_request,
+						 base);
+	struct ocs_hcu_dev *hcu_dev = kmb_ocs_hcu_find_dev(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+	struct ocs_hcu_ctx *tctx = crypto_ahash_ctx(tfm);
+	int rc;
+	int i;
+
+	if (!hcu_dev) {
+		rc = -ENOENT;
+		goto error;
+	}
+
+	/*
+	 * If hardware HMAC flag is set, perform HMAC in hardware.
+	 *
+	 * NOTE: this flag implies REQ_FINAL && kmb_get_total_data(rctx)
+	 */
+	if (rctx->flags & REQ_FLAGS_HMAC_HW) {
+		/* Map input data into the HCU DMA linked list. */
+		rc = kmb_ocs_dma_prepare(req);
+		if (rc)
+			goto error;
+
+		rc = ocs_hcu_hmac(hcu_dev, rctx->algo, tctx->key, tctx->key_len,
+				  rctx->dma_list, req->result, rctx->dig_sz);
+
+		/* Unmap data and free DMA list regardless of return code. */
+		kmb_ocs_hcu_dma_cleanup(req, rctx);
+
+		/* Process previous return code. */
+		if (rc)
+			goto error;
+
+		goto done;
+	}
+
+	/* Handle update request case. */
+	if (!(rctx->flags & REQ_FINAL)) {
+		/* Update should always have input data. */
+		if (!kmb_get_total_data(rctx))
+			return -EINVAL;
+
+		/* Map input data into the HCU DMA linked list. */
+		rc = kmb_ocs_dma_prepare(req);
+		if (rc)
+			goto error;
+
+		/* Do hashing step. */
+		rc = ocs_hcu_hash_update(hcu_dev, &rctx->hash_ctx,
+					 rctx->dma_list);
+
+		/* Unmap data and free DMA list regardless of return code. */
+		kmb_ocs_hcu_dma_cleanup(req, rctx);
+
+		/* Process previous return code. */
+		if (rc)
+			goto error;
+
+		/*
+		 * Reset request buffer count (data in the buffer was just
+		 * processed).
+		 */
+		rctx->buf_cnt = 0;
+		/*
+		 * Move remaining sg data into the request buffer, so that it
+		 * will be processed during the next request.
+		 *
+		 * NOTE: we have remaining data if kmb_get_total_data() was not
+		 * a multiple of block size.
+		 */
+		rc = flush_sg_to_ocs_buffer(rctx);
+		if (rc)
+			goto error;
+
+		goto done;
+	}
+
+	/* If we get here, this is a final request. */
+
+	/* If there is data to process, use finup. */
+	if (kmb_get_total_data(rctx)) {
+		/* Map input data into the HCU DMA linked list. */
+		rc = kmb_ocs_dma_prepare(req);
+		if (rc)
+			goto error;
+
+		/* Do hashing step. */
+		rc = ocs_hcu_hash_finup(hcu_dev, &rctx->hash_ctx,
+					rctx->dma_list,
+					req->result, rctx->dig_sz);
+		/* Free DMA list regardless of return code. */
+		kmb_ocs_hcu_dma_cleanup(req, rctx);
+
+		/* Process previous return code. */
+		if (rc)
+			goto error;
+
+	} else {  /* Otherwise (if we have no data), use final. */
+		rc = ocs_hcu_hash_final(hcu_dev, &rctx->hash_ctx, req->result,
+					rctx->dig_sz);
+		if (rc)
+			goto error;
+	}
+
+	/*
+	 * If we are finalizing a SW HMAC request, we just computed the result
+	 * of: H(k ^ ipad || m).
+	 *
+	 * We now need to complete the HMAC calculation with the OPAD step,
+	 * that is, we need to compute H(k ^ opad || digest), where digest is
+	 * the digest we just obtained, i.e., H(k ^ ipad || m).
+	 */
+	if (rctx->flags & REQ_FLAGS_HMAC_SW) {
+		/*
+		 * Compute k ^ opad and store it in the request buffer (which
+		 * is not used anymore at this point).
+		 * Note: key has been padded / hashed already (so keylen ==
+		 * blksz) .
+		 */
+		WARN_ON(tctx->key_len != rctx->blk_sz);
+		for (i = 0; i < rctx->blk_sz; i++)
+			rctx->buffer[i] = tctx->key[i] ^ HMAC_OPAD_VALUE;
+		/* Now append the digest to the rest of the buffer. */
+		for (i = 0; (i < rctx->dig_sz); i++)
+			rctx->buffer[rctx->blk_sz + i] = req->result[i];
+
+		/* Now hash the buffer to obtain the final HMAC. */
+		rc = ocs_hcu_digest(hcu_dev, rctx->algo, rctx->buffer,
+				    rctx->blk_sz + rctx->dig_sz, req->result,
+				    rctx->dig_sz);
+		if (rc)
+			goto error;
+	}
+
+	/* Perform secure clean-up. */
+	kmb_ocs_hcu_secure_cleanup(req);
+done:
+	crypto_finalize_hash_request(hcu_dev->engine, req, 0);
+
+	return 0;
+
+error:
+	kmb_ocs_hcu_secure_cleanup(req);
+	return rc;
+}
+
+static int kmb_ocs_hcu_init(struct ahash_request *req)
+{
+	struct ocs_hcu_dev *hcu_dev = kmb_ocs_hcu_find_dev(req);
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ocs_hcu_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	if (!hcu_dev)
+		return -ENOENT;
+
+	/* Initialize entire request context to zero. */
+	memset(rctx, 0, sizeof(*rctx));
+
+	rctx->hcu_dev = hcu_dev;
+	rctx->dig_sz = crypto_ahash_digestsize(tfm);
+
+	switch (rctx->dig_sz) {
+#ifdef CONFIG_CRYPTO_DEV_KEEMBAY_OCS_HCU_HMAC_SHA224
+	case SHA224_DIGEST_SIZE:
+		rctx->blk_sz = SHA224_BLOCK_SIZE;
+		rctx->algo = OCS_HCU_ALGO_SHA224;
+		break;
+#endif /* CONFIG_CRYPTO_DEV_KEEMBAY_OCS_HCU_HMAC_SHA224 */
+	case SHA256_DIGEST_SIZE:
+		rctx->blk_sz = SHA256_BLOCK_SIZE;
+		/*
+		 * SHA256 and SM3 have the same digest size: use info from tfm
+		 * context to find out which one we should use.
+		 */
+		rctx->algo = ctx->is_sm3_tfm ? OCS_HCU_ALGO_SM3 :
+					       OCS_HCU_ALGO_SHA256;
+		break;
+	case SHA384_DIGEST_SIZE:
+		rctx->blk_sz = SHA384_BLOCK_SIZE;
+		rctx->algo = OCS_HCU_ALGO_SHA384;
+		break;
+	case SHA512_DIGEST_SIZE:
+		rctx->blk_sz = SHA512_BLOCK_SIZE;
+		rctx->algo = OCS_HCU_ALGO_SHA512;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Initialize intermediate data. */
+	ocs_hcu_hash_init(&rctx->hash_ctx, rctx->algo);
+
+	/* If this a HMAC request, set HMAC flag. */
+	if (ctx->is_hmac_tfm)
+		rctx->flags |= REQ_FLAGS_HMAC;
+
+	return 0;
+}
+
+static int kmb_ocs_hcu_update(struct ahash_request *req)
+{
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+	int rc;
+
+	if (!req->nbytes)
+		return 0;
+
+	rctx->sg_data_total = req->nbytes;
+	rctx->sg_data_offset = 0;
+	rctx->sg = req->src;
+
+	/*
+	 * If we are doing HMAC, then we must use SW-assisted HMAC, since HW
+	 * HMAC does not support context switching (there it can only be used
+	 * with finup() or digest()).
+	 */
+	if (rctx->flags & REQ_FLAGS_HMAC &&
+	    !(rctx->flags & REQ_FLAGS_HMAC_SW)) {
+		rctx->flags |= REQ_FLAGS_HMAC_SW;
+		rc = prepare_ipad(req);
+		if (rc)
+			return rc;
+	}
+
+	/*
+	 * If remaining sg_data fits into ctx buffer, just copy it there; we'll
+	 * process it at the next update() or final().
+	 */
+	if (rctx->sg_data_total <= (sizeof(rctx->buffer) - rctx->buf_cnt))
+		return flush_sg_to_ocs_buffer(rctx);
+
+	return kmb_ocs_hcu_handle_queue(req);
+}
+
+/* Common logic for kmb_ocs_hcu_final() and kmb_ocs_hcu_finup(). */
+static int kmb_ocs_hcu_fin_common(struct ahash_request *req)
+{
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ocs_hcu_ctx *ctx = crypto_ahash_ctx(tfm);
+	int rc;
+
+	rctx->flags |= REQ_FINAL;
+
+	/*
+	 * If this is a HMAC request and, so far, we didn't have to switch to
+	 * SW HMAC, check if we can use HW HMAC.
+	 */
+	if (rctx->flags & REQ_FLAGS_HMAC &&
+	    !(rctx->flags & REQ_FLAGS_HMAC_SW)) {
+		/*
+		 * If we are here, it means we never processed any data so far,
+		 * so we can use HW HMAC, but only if there is some data to
+		 * process (since OCS HW MAC does not support zero-length
+		 * messages) and the key length is supported by the hardware
+		 * (OCS HCU HW only supports length <= 64); if HW HMAC cannot
+		 * be used, fall back to SW-assisted HMAC.
+		 */
+		if (kmb_get_total_data(rctx) &&
+		    ctx->key_len <= OCS_HCU_HW_KEY_LEN) {
+			rctx->flags |= REQ_FLAGS_HMAC_HW;
+		} else {
+			rctx->flags |= REQ_FLAGS_HMAC_SW;
+			rc = prepare_ipad(req);
+			if (rc)
+				return rc;
+		}
+	}
+
+	return kmb_ocs_hcu_handle_queue(req);
+}
+
+static int kmb_ocs_hcu_final(struct ahash_request *req)
+{
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+
+	rctx->sg_data_total = 0;
+	rctx->sg_data_offset = 0;
+	rctx->sg = NULL;
+
+	return kmb_ocs_hcu_fin_common(req);
+}
+
+static int kmb_ocs_hcu_finup(struct ahash_request *req)
+{
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+
+	rctx->sg_data_total = req->nbytes;
+	rctx->sg_data_offset = 0;
+	rctx->sg = req->src;
+
+	return kmb_ocs_hcu_fin_common(req);
+}
+
+static int kmb_ocs_hcu_digest(struct ahash_request *req)
+{
+	int rc = 0;
+	struct ocs_hcu_dev *hcu_dev = kmb_ocs_hcu_find_dev(req);
+
+	if (!hcu_dev)
+		return -ENOENT;
+
+	rc = kmb_ocs_hcu_init(req);
+	if (rc)
+		return rc;
+
+	rc = kmb_ocs_hcu_finup(req);
+
+	return rc;
+}
+
+static int kmb_ocs_hcu_export(struct ahash_request *req, void *out)
+{
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+
+	/* Intermediate data is always stored and applied per request. */
+	memcpy(out, rctx, sizeof(*rctx));
+
+	return 0;
+}
+
+static int kmb_ocs_hcu_import(struct ahash_request *req, const void *in)
+{
+	struct ocs_hcu_rctx *rctx = ahash_request_ctx(req);
+
+	/* Intermediate data is always stored and applied per request. */
+	memcpy(rctx, in, sizeof(*rctx));
+
+	return 0;
+}
+
+static int kmb_ocs_hcu_setkey(struct crypto_ahash *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	unsigned int digestsize = crypto_ahash_digestsize(tfm);
+	struct ocs_hcu_ctx *ctx = crypto_ahash_ctx(tfm);
+	size_t blk_sz = crypto_ahash_blocksize(tfm);
+	struct crypto_ahash *ahash_tfm;
+	struct ahash_request *req;
+	struct crypto_wait wait;
+	struct scatterlist sg;
+	const char *alg_name;
+	int rc;
+
+	/*
+	 * Key length must be equal to block size:
+	 * - If key is shorter, we are done for now (the key will be padded
+	 *   later on); this is to maximize the use of HW HMAC (which works
+	 *   only for keys <= 64 bytes).
+	 * - If key is longer, we hash it.
+	 */
+	if (keylen <= blk_sz) {
+		memcpy(ctx->key, key, keylen);
+		ctx->key_len = keylen;
+		return 0;
+	}
+
+	switch (digestsize) {
+#ifdef CONFIG_CRYPTO_DEV_KEEMBAY_OCS_HCU_HMAC_SHA224
+	case SHA224_DIGEST_SIZE:
+		alg_name = "sha224-keembay-ocs";
+		break;
+#endif /* CONFIG_CRYPTO_DEV_KEEMBAY_OCS_HCU_HMAC_SHA224 */
+	case SHA256_DIGEST_SIZE:
+		alg_name = ctx->is_sm3_tfm ? "sm3-keembay-ocs" :
+					     "sha256-keembay-ocs";
+		break;
+	case SHA384_DIGEST_SIZE:
+		alg_name = "sha384-keembay-ocs";
+		break;
+	case SHA512_DIGEST_SIZE:
+		alg_name = "sha512-keembay-ocs";
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ahash_tfm = crypto_alloc_ahash(alg_name, 0, 0);
+	if (IS_ERR(ahash_tfm))
+		return PTR_ERR(ahash_tfm);
+
+	req = ahash_request_alloc(ahash_tfm, GFP_KERNEL);
+	if (!req) {
+		rc = -ENOMEM;
+		goto err_free_ahash;
+	}
+
+	crypto_init_wait(&wait);
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				   crypto_req_done, &wait);
+	crypto_ahash_clear_flags(ahash_tfm, ~0);
+
+	sg_init_one(&sg, key, keylen);
+	ahash_request_set_crypt(req, &sg, ctx->key, keylen);
+
+	rc = crypto_wait_req(crypto_ahash_digest(req), &wait);
+	if (rc == 0)
+		ctx->key_len = digestsize;
+
+	ahash_request_free(req);
+err_free_ahash:
+	crypto_free_ahash(ahash_tfm);
+
+	return rc;
+}
+
+/* Set request size and initialize tfm context. */
+static void __cra_init(struct crypto_tfm *tfm, struct ocs_hcu_ctx *ctx)
+{
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct ocs_hcu_rctx));
+
+	/* Init context to 0. */
+	memzero_explicit(ctx, sizeof(*ctx));
+	/* Set engine ops. */
+	ctx->engine_ctx.op.do_one_request = kmb_ocs_hcu_do_one_request;
+}
+
+static int kmb_ocs_hcu_sha_cra_init(struct crypto_tfm *tfm)
+{
+	struct ocs_hcu_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	__cra_init(tfm, ctx);
+
+	return 0;
+}
+
+static int kmb_ocs_hcu_sm3_cra_init(struct crypto_tfm *tfm)
+{
+	struct ocs_hcu_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	__cra_init(tfm, ctx);
+
+	ctx->is_sm3_tfm = true;
+
+	return 0;
+}
+
+static int kmb_ocs_hcu_hmac_sm3_cra_init(struct crypto_tfm *tfm)
+{
+	struct ocs_hcu_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	__cra_init(tfm, ctx);
+
+	ctx->is_sm3_tfm = true;
+	ctx->is_hmac_tfm = true;
+
+	return 0;
+}
+
+static int kmb_ocs_hcu_hmac_cra_init(struct crypto_tfm *tfm)
+{
+	struct ocs_hcu_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	__cra_init(tfm, ctx);
+
+	ctx->is_hmac_tfm = true;
+
+	return 0;
+}
+
+/* Function called when 'tfm' is de-initialized. */
+static void kmb_ocs_hcu_hmac_cra_exit(struct crypto_tfm *tfm)
+{
+	struct ocs_hcu_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	/* Clear the key. */
+	memzero_explicit(ctx->key, sizeof(ctx->key));
+}
+
+static struct ahash_alg ocs_hcu_algs[] = {
+#ifdef CONFIG_CRYPTO_DEV_KEEMBAY_OCS_HCU_HMAC_SHA224
+{
+	.init		= kmb_ocs_hcu_init,
+	.update		= kmb_ocs_hcu_update,
+	.final		= kmb_ocs_hcu_final,
+	.finup		= kmb_ocs_hcu_finup,
+	.digest		= kmb_ocs_hcu_digest,
+	.export		= kmb_ocs_hcu_export,
+	.import		= kmb_ocs_hcu_import,
+	.halg = {
+		.digestsize	= SHA224_DIGEST_SIZE,
+		.statesize	= sizeof(struct ocs_hcu_rctx),
+		.base	= {
+			.cra_name		= "sha224",
+			.cra_driver_name	= "sha224-keembay-ocs",
+			.cra_priority		= 255,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= SHA224_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct ocs_hcu_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= kmb_ocs_hcu_sha_cra_init,
+		}
+	}
+},
+{
+	.init		= kmb_ocs_hcu_init,
+	.update		= kmb_ocs_hcu_update,
+	.final		= kmb_ocs_hcu_final,
+	.finup		= kmb_ocs_hcu_finup,
+	.digest		= kmb_ocs_hcu_digest,
+	.export		= kmb_ocs_hcu_export,
+	.import		= kmb_ocs_hcu_import,
+	.setkey		= kmb_ocs_hcu_setkey,
+	.halg = {
+		.digestsize	= SHA224_DIGEST_SIZE,
+		.statesize	= sizeof(struct ocs_hcu_rctx),
+		.base	= {
+			.cra_name		= "hmac(sha224)",
+			.cra_driver_name	= "hmac-sha224-keembay-ocs",
+			.cra_priority		= 255,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= SHA224_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct ocs_hcu_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= kmb_ocs_hcu_hmac_cra_init,
+			.cra_exit		= kmb_ocs_hcu_hmac_cra_exit,
+		}
+	}
+},
+#endif /* CONFIG_CRYPTO_DEV_KEEMBAY_OCS_HCU_HMAC_SHA224 */
+{
+	.init		= kmb_ocs_hcu_init,
+	.update		= kmb_ocs_hcu_update,
+	.final		= kmb_ocs_hcu_final,
+	.finup		= kmb_ocs_hcu_finup,
+	.digest		= kmb_ocs_hcu_digest,
+	.export		= kmb_ocs_hcu_export,
+	.import		= kmb_ocs_hcu_import,
+	.halg = {
+		.digestsize	= SHA256_DIGEST_SIZE,
+		.statesize	= sizeof(struct ocs_hcu_rctx),
+		.base	= {
+			.cra_name		= "sha256",
+			.cra_driver_name	= "sha256-keembay-ocs",
+			.cra_priority		= 255,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= SHA256_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct ocs_hcu_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= kmb_ocs_hcu_sha_cra_init,
+		}
+	}
+},
+{
+	.init		= kmb_ocs_hcu_init,
+	.update		= kmb_ocs_hcu_update,
+	.final		= kmb_ocs_hcu_final,
+	.finup		= kmb_ocs_hcu_finup,
+	.digest		= kmb_ocs_hcu_digest,
+	.export		= kmb_ocs_hcu_export,
+	.import		= kmb_ocs_hcu_import,
+	.setkey		= kmb_ocs_hcu_setkey,
+	.halg = {
+		.digestsize	= SHA256_DIGEST_SIZE,
+		.statesize	= sizeof(struct ocs_hcu_rctx),
+		.base	= {
+			.cra_name		= "hmac(sha256)",
+			.cra_driver_name	= "hmac-sha256-keembay-ocs",
+			.cra_priority		= 255,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= SHA256_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct ocs_hcu_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= kmb_ocs_hcu_hmac_cra_init,
+			.cra_exit		= kmb_ocs_hcu_hmac_cra_exit,
+		}
+	}
+},
+{
+	.init		= kmb_ocs_hcu_init,
+	.update		= kmb_ocs_hcu_update,
+	.final		= kmb_ocs_hcu_final,
+	.finup		= kmb_ocs_hcu_finup,
+	.digest		= kmb_ocs_hcu_digest,
+	.export		= kmb_ocs_hcu_export,
+	.import		= kmb_ocs_hcu_import,
+	.halg = {
+		.digestsize	= SM3_DIGEST_SIZE,
+		.statesize	= sizeof(struct ocs_hcu_rctx),
+		.base	= {
+			.cra_name		= "sm3",
+			.cra_driver_name	= "sm3-keembay-ocs",
+			.cra_priority		= 255,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= SM3_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct ocs_hcu_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= kmb_ocs_hcu_sm3_cra_init,
+		}
+	}
+},
+{
+	.init		= kmb_ocs_hcu_init,
+	.update		= kmb_ocs_hcu_update,
+	.final		= kmb_ocs_hcu_final,
+	.finup		= kmb_ocs_hcu_finup,
+	.digest		= kmb_ocs_hcu_digest,
+	.export		= kmb_ocs_hcu_export,
+	.import		= kmb_ocs_hcu_import,
+	.setkey		= kmb_ocs_hcu_setkey,
+	.halg = {
+		.digestsize	= SM3_DIGEST_SIZE,
+		.statesize	= sizeof(struct ocs_hcu_rctx),
+		.base	= {
+			.cra_name		= "hmac(sm3)",
+			.cra_driver_name	= "hmac-sm3-keembay-ocs",
+			.cra_priority		= 255,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= SM3_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct ocs_hcu_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= kmb_ocs_hcu_hmac_sm3_cra_init,
+			.cra_exit		= kmb_ocs_hcu_hmac_cra_exit,
+		}
+	}
+},
+{
+	.init		= kmb_ocs_hcu_init,
+	.update		= kmb_ocs_hcu_update,
+	.final		= kmb_ocs_hcu_final,
+	.finup		= kmb_ocs_hcu_finup,
+	.digest		= kmb_ocs_hcu_digest,
+	.export		= kmb_ocs_hcu_export,
+	.import		= kmb_ocs_hcu_import,
+	.halg = {
+		.digestsize	= SHA384_DIGEST_SIZE,
+		.statesize	= sizeof(struct ocs_hcu_rctx),
+		.base	= {
+			.cra_name		= "sha384",
+			.cra_driver_name	= "sha384-keembay-ocs",
+			.cra_priority		= 255,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= SHA384_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct ocs_hcu_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= kmb_ocs_hcu_sha_cra_init,
+		}
+	}
+},
+{
+	.init		= kmb_ocs_hcu_init,
+	.update		= kmb_ocs_hcu_update,
+	.final		= kmb_ocs_hcu_final,
+	.finup		= kmb_ocs_hcu_finup,
+	.digest		= kmb_ocs_hcu_digest,
+	.export		= kmb_ocs_hcu_export,
+	.import		= kmb_ocs_hcu_import,
+	.setkey		= kmb_ocs_hcu_setkey,
+	.halg = {
+		.digestsize	= SHA384_DIGEST_SIZE,
+		.statesize	= sizeof(struct ocs_hcu_rctx),
+		.base	= {
+			.cra_name		= "hmac(sha384)",
+			.cra_driver_name	= "hmac-sha384-keembay-ocs",
+			.cra_priority		= 255,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= SHA384_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct ocs_hcu_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= kmb_ocs_hcu_hmac_cra_init,
+			.cra_exit		= kmb_ocs_hcu_hmac_cra_exit,
+		}
+	}
+},
+{
+	.init		= kmb_ocs_hcu_init,
+	.update		= kmb_ocs_hcu_update,
+	.final		= kmb_ocs_hcu_final,
+	.finup		= kmb_ocs_hcu_finup,
+	.digest		= kmb_ocs_hcu_digest,
+	.export		= kmb_ocs_hcu_export,
+	.import		= kmb_ocs_hcu_import,
+	.halg = {
+		.digestsize	= SHA512_DIGEST_SIZE,
+		.statesize	= sizeof(struct ocs_hcu_rctx),
+		.base	= {
+			.cra_name		= "sha512",
+			.cra_driver_name	= "sha512-keembay-ocs",
+			.cra_priority		= 255,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= SHA512_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct ocs_hcu_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= kmb_ocs_hcu_sha_cra_init,
+		}
+	}
+},
+{
+	.init		= kmb_ocs_hcu_init,
+	.update		= kmb_ocs_hcu_update,
+	.final		= kmb_ocs_hcu_final,
+	.finup		= kmb_ocs_hcu_finup,
+	.digest		= kmb_ocs_hcu_digest,
+	.export		= kmb_ocs_hcu_export,
+	.import		= kmb_ocs_hcu_import,
+	.setkey		= kmb_ocs_hcu_setkey,
+	.halg = {
+		.digestsize	= SHA512_DIGEST_SIZE,
+		.statesize	= sizeof(struct ocs_hcu_rctx),
+		.base	= {
+			.cra_name		= "hmac(sha512)",
+			.cra_driver_name	= "hmac-sha512-keembay-ocs",
+			.cra_priority		= 255,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= SHA512_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(struct ocs_hcu_ctx),
+			.cra_alignmask		= 0,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= kmb_ocs_hcu_hmac_cra_init,
+			.cra_exit		= kmb_ocs_hcu_hmac_cra_exit,
+		}
+	}
+},
+};
+
+/* Device tree driver match. */
+static const struct of_device_id kmb_ocs_hcu_of_match[] = {
+	{
+		.compatible = "intel,keembay-ocs-hcu",
+	},
+	{}
+};
+
+static int kmb_ocs_hcu_remove(struct platform_device *pdev)
+{
+	struct ocs_hcu_dev *hcu_dev;
+	int rc;
+
+	hcu_dev = platform_get_drvdata(pdev);
+	if (!hcu_dev)
+		return -ENODEV;
+
+	crypto_unregister_ahashes(ocs_hcu_algs, ARRAY_SIZE(ocs_hcu_algs));
+
+	rc = crypto_engine_exit(hcu_dev->engine);
+
+	spin_lock_bh(&ocs_hcu.lock);
+	list_del(&hcu_dev->list);
+	spin_unlock_bh(&ocs_hcu.lock);
+
+	return rc;
+}
+
+static int kmb_ocs_hcu_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ocs_hcu_dev *hcu_dev;
+	struct resource *hcu_mem;
+	int rc;
+
+	hcu_dev = devm_kzalloc(dev, sizeof(*hcu_dev), GFP_KERNEL);
+	if (!hcu_dev)
+		return -ENOMEM;
+
+	hcu_dev->dev = dev;
+
+	platform_set_drvdata(pdev, hcu_dev);
+	rc = dma_set_mask_and_coherent(&pdev->dev, OCS_HCU_DMA_BIT_MASK);
+	if (rc)
+		return rc;
+
+	/* Get the memory address and remap. */
+	hcu_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!hcu_mem) {
+		dev_err(dev, "Could not retrieve io mem resource.\n");
+		return -ENODEV;
+	}
+
+	hcu_dev->io_base = devm_ioremap_resource(dev, hcu_mem);
+	if (IS_ERR(hcu_dev->io_base)) {
+		dev_err(dev, "Could not io-remap mem resource.\n");
+		return PTR_ERR(hcu_dev->io_base);
+	}
+
+	init_completion(&hcu_dev->irq_done);
+
+	/* Get and request IRQ. */
+	hcu_dev->irq = platform_get_irq(pdev, 0);
+	if (hcu_dev->irq < 0)
+		return hcu_dev->irq;
+
+	rc = devm_request_threaded_irq(&pdev->dev, hcu_dev->irq,
+				       ocs_hcu_irq_handler, NULL, 0,
+				       "keembay-ocs-hcu", hcu_dev);
+	if (rc < 0) {
+		dev_err(dev, "Could not request IRQ.\n");
+		return rc;
+	}
+
+	INIT_LIST_HEAD(&hcu_dev->list);
+
+	spin_lock_bh(&ocs_hcu.lock);
+	list_add_tail(&hcu_dev->list, &ocs_hcu.dev_list);
+	spin_unlock_bh(&ocs_hcu.lock);
+
+	/* Initialize crypto engine */
+	hcu_dev->engine = crypto_engine_alloc_init(dev, 1);
+	if (!hcu_dev->engine)
+		goto list_del;
+
+	rc = crypto_engine_start(hcu_dev->engine);
+	if (rc) {
+		dev_err(dev, "Could not start engine.\n");
+		goto cleanup;
+	}
+
+	/* Security infrastructure guarantees OCS clock is enabled. */
+
+	rc = crypto_register_ahashes(ocs_hcu_algs, ARRAY_SIZE(ocs_hcu_algs));
+	if (rc) {
+		dev_err(dev, "Could not register algorithms.\n");
+		goto cleanup;
+	}
+
+	return 0;
+
+cleanup:
+	crypto_engine_exit(hcu_dev->engine);
+list_del:
+	spin_lock_bh(&ocs_hcu.lock);
+	list_del(&hcu_dev->list);
+	spin_unlock_bh(&ocs_hcu.lock);
+
+	return rc;
+}
+
+/* The OCS driver is a platform device. */
+static struct platform_driver kmb_ocs_hcu_driver = {
+	.probe = kmb_ocs_hcu_probe,
+	.remove = kmb_ocs_hcu_remove,
+	.driver = {
+			.name = DRV_NAME,
+			.of_match_table = kmb_ocs_hcu_of_match,
+		},
+};
+
+module_platform_driver(kmb_ocs_hcu_driver);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/keembay/ocs-aes.c b/drivers/crypto/keembay/ocs-aes.c
index cc286adb1c4a..be9f32fc8f42 100644
--- a/drivers/crypto/keembay/ocs-aes.c
+++ b/drivers/crypto/keembay/ocs-aes.c
@@ -958,14 +958,14 @@ int ocs_aes_gcm_op(struct ocs_aes_dev *aes_dev,
 	ocs_aes_write_last_data_blk_len(aes_dev, src_size);
 
 	/* Write ciphertext bit length */
-	bit_len = src_size * 8;
+	bit_len = (u64)src_size * 8;
 	val = bit_len & 0xFFFFFFFF;
 	iowrite32(val, aes_dev->base_reg + AES_MULTIPURPOSE2_0_OFFSET);
 	val = bit_len >> 32;
 	iowrite32(val, aes_dev->base_reg + AES_MULTIPURPOSE2_1_OFFSET);
 
 	/* Write aad bit length */
-	bit_len = aad_size * 8;
+	bit_len = (u64)aad_size * 8;
 	val = bit_len & 0xFFFFFFFF;
 	iowrite32(val, aes_dev->base_reg + AES_MULTIPURPOSE2_2_OFFSET);
 	val = bit_len >> 32;
@@ -1080,15 +1080,15 @@ static int ocs_aes_ccm_write_b0(const struct ocs_aes_dev *aes_dev,
 	/*
 	 * q is the octet length of Q.
 	 * q can only be an element of {2, 3, 4, 5, 6, 7, 8} and is encoded as
-	 * q - 1 == iv[0]
+	 * q - 1 == iv[0] & 0x7;
 	 */
 	b0[0] |= iv[0] & 0x7;
 	/*
 	 * Copy the Nonce N from IV to B0; N is located in iv[1]..iv[15 - q]
 	 * and must be copied to b0[1]..b0[15-q].
-	 * q == iv[0] + 1
+	 * q == (iv[0] & 0x7) + 1
 	 */
-	q = iv[0] + 1;
+	q = (iv[0] & 0x7) + 1;
 	for (i = 1; i <= 15 - q; i++)
 		b0[i] = iv[i];
 	/*
diff --git a/drivers/crypto/keembay/ocs-hcu.c b/drivers/crypto/keembay/ocs-hcu.c
new file mode 100644
index 000000000000..81eecacf603a
--- /dev/null
+++ b/drivers/crypto/keembay/ocs-hcu.c
@@ -0,0 +1,840 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Keem Bay OCS HCU Crypto Driver.
+ *
+ * Copyright (C) 2018-2020 Intel Corporation
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/iopoll.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+
+#include <crypto/sha2.h>
+
+#include "ocs-hcu.h"
+
+/* Registers. */
+#define OCS_HCU_MODE			0x00
+#define OCS_HCU_CHAIN			0x04
+#define OCS_HCU_OPERATION		0x08
+#define OCS_HCU_KEY_0			0x0C
+#define OCS_HCU_ISR			0x50
+#define OCS_HCU_IER			0x54
+#define OCS_HCU_STATUS			0x58
+#define OCS_HCU_MSG_LEN_LO		0x60
+#define OCS_HCU_MSG_LEN_HI		0x64
+#define OCS_HCU_KEY_BYTE_ORDER_CFG	0x80
+#define OCS_HCU_DMA_SRC_ADDR		0x400
+#define OCS_HCU_DMA_SRC_SIZE		0x408
+#define OCS_HCU_DMA_DST_SIZE		0x40C
+#define OCS_HCU_DMA_DMA_MODE		0x410
+#define OCS_HCU_DMA_NEXT_SRC_DESCR	0x418
+#define OCS_HCU_DMA_MSI_ISR		0x480
+#define OCS_HCU_DMA_MSI_IER		0x484
+#define OCS_HCU_DMA_MSI_MASK		0x488
+
+/* Register bit definitions. */
+#define HCU_MODE_ALGO_SHIFT		16
+#define HCU_MODE_HMAC_SHIFT		22
+
+#define HCU_STATUS_BUSY			BIT(0)
+
+#define HCU_BYTE_ORDER_SWAP		BIT(0)
+
+#define HCU_IRQ_HASH_DONE		BIT(2)
+#define HCU_IRQ_HASH_ERR_MASK		(BIT(3) | BIT(1) | BIT(0))
+
+#define HCU_DMA_IRQ_SRC_DONE		BIT(0)
+#define HCU_DMA_IRQ_SAI_ERR		BIT(2)
+#define HCU_DMA_IRQ_BAD_COMP_ERR	BIT(3)
+#define HCU_DMA_IRQ_INBUF_RD_ERR	BIT(4)
+#define HCU_DMA_IRQ_INBUF_WD_ERR	BIT(5)
+#define HCU_DMA_IRQ_OUTBUF_WR_ERR	BIT(6)
+#define HCU_DMA_IRQ_OUTBUF_RD_ERR	BIT(7)
+#define HCU_DMA_IRQ_CRD_ERR		BIT(8)
+#define HCU_DMA_IRQ_ERR_MASK		(HCU_DMA_IRQ_SAI_ERR | \
+					 HCU_DMA_IRQ_BAD_COMP_ERR | \
+					 HCU_DMA_IRQ_INBUF_RD_ERR | \
+					 HCU_DMA_IRQ_INBUF_WD_ERR | \
+					 HCU_DMA_IRQ_OUTBUF_WR_ERR | \
+					 HCU_DMA_IRQ_OUTBUF_RD_ERR | \
+					 HCU_DMA_IRQ_CRD_ERR)
+
+#define HCU_DMA_SNOOP_MASK		(0x7 << 28)
+#define HCU_DMA_SRC_LL_EN		BIT(25)
+#define HCU_DMA_EN			BIT(31)
+
+#define OCS_HCU_ENDIANNESS_VALUE	0x2A
+
+#define HCU_DMA_MSI_UNMASK		BIT(0)
+#define HCU_DMA_MSI_DISABLE		0
+#define HCU_IRQ_DISABLE			0
+
+#define OCS_HCU_START			BIT(0)
+#define OCS_HCU_TERMINATE		BIT(1)
+
+#define OCS_LL_DMA_FLAG_TERMINATE	BIT(31)
+
+#define OCS_HCU_HW_KEY_LEN_U32		(OCS_HCU_HW_KEY_LEN / sizeof(u32))
+
+#define HCU_DATA_WRITE_ENDIANNESS_OFFSET	26
+
+#define OCS_HCU_NUM_CHAINS_SHA256_224_SM3	(SHA256_DIGEST_SIZE / sizeof(u32))
+#define OCS_HCU_NUM_CHAINS_SHA384_512		(SHA512_DIGEST_SIZE / sizeof(u32))
+
+/*
+ * While polling on a busy HCU, wait maximum 200us between one check and the
+ * other.
+ */
+#define OCS_HCU_WAIT_BUSY_RETRY_DELAY_US	200
+/* Wait on a busy HCU for maximum 1 second. */
+#define OCS_HCU_WAIT_BUSY_TIMEOUT_US		1000000
+
+/**
+ * struct ocs_hcu_dma_list - An entry in an OCS DMA linked list.
+ * @src_addr:  Source address of the data.
+ * @src_len:   Length of data to be fetched.
+ * @nxt_desc:  Next descriptor to fetch.
+ * @ll_flags:  Flags (Freeze @ terminate) for the DMA engine.
+ */
+struct ocs_hcu_dma_entry {
+	u32 src_addr;
+	u32 src_len;
+	u32 nxt_desc;
+	u32 ll_flags;
+};
+
+/**
+ * struct ocs_dma_list - OCS-specific DMA linked list.
+ * @head:	The head of the list (points to the array backing the list).
+ * @tail:	The current tail of the list; NULL if the list is empty.
+ * @dma_addr:	The DMA address of @head (i.e., the DMA address of the backing
+ *		array).
+ * @max_nents:	Maximum number of entries in the list (i.e., number of elements
+ *		in the backing array).
+ *
+ * The OCS DMA list is an array-backed list of OCS DMA descriptors. The array
+ * backing the list is allocated with dma_alloc_coherent() and pointed by
+ * @head.
+ */
+struct ocs_hcu_dma_list {
+	struct ocs_hcu_dma_entry	*head;
+	struct ocs_hcu_dma_entry	*tail;
+	dma_addr_t			dma_addr;
+	size_t				max_nents;
+};
+
+static inline u32 ocs_hcu_num_chains(enum ocs_hcu_algo algo)
+{
+	switch (algo) {
+	case OCS_HCU_ALGO_SHA224:
+	case OCS_HCU_ALGO_SHA256:
+	case OCS_HCU_ALGO_SM3:
+		return OCS_HCU_NUM_CHAINS_SHA256_224_SM3;
+	case OCS_HCU_ALGO_SHA384:
+	case OCS_HCU_ALGO_SHA512:
+		return OCS_HCU_NUM_CHAINS_SHA384_512;
+	default:
+		return 0;
+	};
+}
+
+static inline u32 ocs_hcu_digest_size(enum ocs_hcu_algo algo)
+{
+	switch (algo) {
+	case OCS_HCU_ALGO_SHA224:
+		return SHA224_DIGEST_SIZE;
+	case OCS_HCU_ALGO_SHA256:
+	case OCS_HCU_ALGO_SM3:
+		/* SM3 shares the same block size. */
+		return SHA256_DIGEST_SIZE;
+	case OCS_HCU_ALGO_SHA384:
+		return SHA384_DIGEST_SIZE;
+	case OCS_HCU_ALGO_SHA512:
+		return SHA512_DIGEST_SIZE;
+	default:
+		return 0;
+	}
+}
+
+/**
+ * ocs_hcu_wait_busy() - Wait for HCU OCS hardware to became usable.
+ * @hcu_dev:	OCS HCU device to wait for.
+ *
+ * Return: 0 if device free, -ETIMEOUT if device busy and internal timeout has
+ *	   expired.
+ */
+static int ocs_hcu_wait_busy(struct ocs_hcu_dev *hcu_dev)
+{
+	long val;
+
+	return readl_poll_timeout(hcu_dev->io_base + OCS_HCU_STATUS, val,
+				  !(val & HCU_STATUS_BUSY),
+				  OCS_HCU_WAIT_BUSY_RETRY_DELAY_US,
+				  OCS_HCU_WAIT_BUSY_TIMEOUT_US);
+}
+
+static void ocs_hcu_done_irq_en(struct ocs_hcu_dev *hcu_dev)
+{
+	/* Clear any pending interrupts. */
+	writel(0xFFFFFFFF, hcu_dev->io_base + OCS_HCU_ISR);
+	hcu_dev->irq_err = false;
+	/* Enable error and HCU done interrupts. */
+	writel(HCU_IRQ_HASH_DONE | HCU_IRQ_HASH_ERR_MASK,
+	       hcu_dev->io_base + OCS_HCU_IER);
+}
+
+static void ocs_hcu_dma_irq_en(struct ocs_hcu_dev *hcu_dev)
+{
+	/* Clear any pending interrupts. */
+	writel(0xFFFFFFFF, hcu_dev->io_base + OCS_HCU_DMA_MSI_ISR);
+	hcu_dev->irq_err = false;
+	/* Only operating on DMA source completion and error interrupts. */
+	writel(HCU_DMA_IRQ_ERR_MASK | HCU_DMA_IRQ_SRC_DONE,
+	       hcu_dev->io_base + OCS_HCU_DMA_MSI_IER);
+	/* Unmask */
+	writel(HCU_DMA_MSI_UNMASK, hcu_dev->io_base + OCS_HCU_DMA_MSI_MASK);
+}
+
+static void ocs_hcu_irq_dis(struct ocs_hcu_dev *hcu_dev)
+{
+	writel(HCU_IRQ_DISABLE, hcu_dev->io_base + OCS_HCU_IER);
+	writel(HCU_DMA_MSI_DISABLE, hcu_dev->io_base + OCS_HCU_DMA_MSI_IER);
+}
+
+static int ocs_hcu_wait_and_disable_irq(struct ocs_hcu_dev *hcu_dev)
+{
+	int rc;
+
+	rc = wait_for_completion_interruptible(&hcu_dev->irq_done);
+	if (rc)
+		goto exit;
+
+	if (hcu_dev->irq_err) {
+		/* Unset flag and return error. */
+		hcu_dev->irq_err = false;
+		rc = -EIO;
+		goto exit;
+	}
+
+exit:
+	ocs_hcu_irq_dis(hcu_dev);
+
+	return rc;
+}
+
+/**
+ * ocs_hcu_get_intermediate_data() - Get intermediate data.
+ * @hcu_dev:	The target HCU device.
+ * @data:	Where to store the intermediate.
+ * @algo:	The algorithm being used.
+ *
+ * This function is used to save the current hashing process state in order to
+ * continue it in the future.
+ *
+ * Note: once all data has been processed, the intermediate data actually
+ * contains the hashing result. So this function is also used to retrieve the
+ * final result of a hashing process.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+static int ocs_hcu_get_intermediate_data(struct ocs_hcu_dev *hcu_dev,
+					 struct ocs_hcu_idata *data,
+					 enum ocs_hcu_algo algo)
+{
+	const int n = ocs_hcu_num_chains(algo);
+	u32 *chain;
+	int rc;
+	int i;
+
+	/* Data not requested. */
+	if (!data)
+		return -EINVAL;
+
+	chain = (u32 *)data->digest;
+
+	/* Ensure that the OCS is no longer busy before reading the chains. */
+	rc = ocs_hcu_wait_busy(hcu_dev);
+	if (rc)
+		return rc;
+
+	/*
+	 * This loops is safe because data->digest is an array of
+	 * SHA512_DIGEST_SIZE bytes and the maximum value returned by
+	 * ocs_hcu_num_chains() is OCS_HCU_NUM_CHAINS_SHA384_512 which is equal
+	 * to SHA512_DIGEST_SIZE / sizeof(u32).
+	 */
+	for (i = 0; i < n; i++)
+		chain[i] = readl(hcu_dev->io_base + OCS_HCU_CHAIN);
+
+	data->msg_len_lo = readl(hcu_dev->io_base + OCS_HCU_MSG_LEN_LO);
+	data->msg_len_hi = readl(hcu_dev->io_base + OCS_HCU_MSG_LEN_HI);
+
+	return 0;
+}
+
+/**
+ * ocs_hcu_set_intermediate_data() - Set intermediate data.
+ * @hcu_dev:	The target HCU device.
+ * @data:	The intermediate data to be set.
+ * @algo:	The algorithm being used.
+ *
+ * This function is used to continue a previous hashing process.
+ */
+static void ocs_hcu_set_intermediate_data(struct ocs_hcu_dev *hcu_dev,
+					  const struct ocs_hcu_idata *data,
+					  enum ocs_hcu_algo algo)
+{
+	const int n = ocs_hcu_num_chains(algo);
+	u32 *chain = (u32 *)data->digest;
+	int i;
+
+	/*
+	 * This loops is safe because data->digest is an array of
+	 * SHA512_DIGEST_SIZE bytes and the maximum value returned by
+	 * ocs_hcu_num_chains() is OCS_HCU_NUM_CHAINS_SHA384_512 which is equal
+	 * to SHA512_DIGEST_SIZE / sizeof(u32).
+	 */
+	for (i = 0; i < n; i++)
+		writel(chain[i], hcu_dev->io_base + OCS_HCU_CHAIN);
+
+	writel(data->msg_len_lo, hcu_dev->io_base + OCS_HCU_MSG_LEN_LO);
+	writel(data->msg_len_hi, hcu_dev->io_base + OCS_HCU_MSG_LEN_HI);
+}
+
+static int ocs_hcu_get_digest(struct ocs_hcu_dev *hcu_dev,
+			      enum ocs_hcu_algo algo, u8 *dgst, size_t dgst_len)
+{
+	u32 *chain;
+	int rc;
+	int i;
+
+	if (!dgst)
+		return -EINVAL;
+
+	/* Length of the output buffer must match the algo digest size. */
+	if (dgst_len != ocs_hcu_digest_size(algo))
+		return -EINVAL;
+
+	/* Ensure that the OCS is no longer busy before reading the chains. */
+	rc = ocs_hcu_wait_busy(hcu_dev);
+	if (rc)
+		return rc;
+
+	chain = (u32 *)dgst;
+	for (i = 0; i < dgst_len / sizeof(u32); i++)
+		chain[i] = readl(hcu_dev->io_base + OCS_HCU_CHAIN);
+
+	return 0;
+}
+
+/**
+ * ocs_hcu_hw_cfg() - Configure the HCU hardware.
+ * @hcu_dev:	The HCU device to configure.
+ * @algo:	The algorithm to be used by the HCU device.
+ * @use_hmac:	Whether or not HW HMAC should be used.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+static int ocs_hcu_hw_cfg(struct ocs_hcu_dev *hcu_dev, enum ocs_hcu_algo algo,
+			  bool use_hmac)
+{
+	u32 cfg;
+	int rc;
+
+	if (algo != OCS_HCU_ALGO_SHA256 && algo != OCS_HCU_ALGO_SHA224 &&
+	    algo != OCS_HCU_ALGO_SHA384 && algo != OCS_HCU_ALGO_SHA512 &&
+	    algo != OCS_HCU_ALGO_SM3)
+		return -EINVAL;
+
+	rc = ocs_hcu_wait_busy(hcu_dev);
+	if (rc)
+		return rc;
+
+	/* Ensure interrupts are disabled. */
+	ocs_hcu_irq_dis(hcu_dev);
+
+	/* Configure endianness, hashing algorithm and HW HMAC (if needed) */
+	cfg = OCS_HCU_ENDIANNESS_VALUE << HCU_DATA_WRITE_ENDIANNESS_OFFSET;
+	cfg |= algo << HCU_MODE_ALGO_SHIFT;
+	if (use_hmac)
+		cfg |= BIT(HCU_MODE_HMAC_SHIFT);
+
+	writel(cfg, hcu_dev->io_base + OCS_HCU_MODE);
+
+	return 0;
+}
+
+/**
+ * ocs_hcu_clear_key() - Clear key stored in OCS HMAC KEY registers.
+ * @hcu_dev:	The OCS HCU device whose key registers should be cleared.
+ */
+static void ocs_hcu_clear_key(struct ocs_hcu_dev *hcu_dev)
+{
+	int reg_off;
+
+	/* Clear OCS_HCU_KEY_[0..15] */
+	for (reg_off = 0; reg_off < OCS_HCU_HW_KEY_LEN; reg_off += sizeof(u32))
+		writel(0, hcu_dev->io_base + OCS_HCU_KEY_0 + reg_off);
+}
+
+/**
+ * ocs_hcu_write_key() - Write key to OCS HMAC KEY registers.
+ * @hcu_dev:	The OCS HCU device the key should be written to.
+ * @key:	The key to be written.
+ * @len:	The size of the key to write. It must be OCS_HCU_HW_KEY_LEN.
+ *
+ * Return:	0 on success, negative error code otherwise.
+ */
+static int ocs_hcu_write_key(struct ocs_hcu_dev *hcu_dev, const u8 *key, size_t len)
+{
+	u32 key_u32[OCS_HCU_HW_KEY_LEN_U32];
+	int i;
+
+	if (len > OCS_HCU_HW_KEY_LEN)
+		return -EINVAL;
+
+	/* Copy key into temporary u32 array. */
+	memcpy(key_u32, key, len);
+
+	/*
+	 * Hardware requires all the bytes of the HW Key vector to be
+	 * written. So pad with zero until we reach OCS_HCU_HW_KEY_LEN.
+	 */
+	memzero_explicit((u8 *)key_u32 + len, OCS_HCU_HW_KEY_LEN - len);
+
+	/*
+	 * OCS hardware expects the MSB of the key to be written at the highest
+	 * address of the HCU Key vector; in other word, the key must be
+	 * written in reverse order.
+	 *
+	 * Therefore, we first enable byte swapping for the HCU key vector;
+	 * so that bytes of 32-bit word written to OCS_HCU_KEY_[0..15] will be
+	 * swapped:
+	 * 3 <---> 0, 2 <---> 1.
+	 */
+	writel(HCU_BYTE_ORDER_SWAP,
+	       hcu_dev->io_base + OCS_HCU_KEY_BYTE_ORDER_CFG);
+	/*
+	 * And then we write the 32-bit words composing the key starting from
+	 * the end of the key.
+	 */
+	for (i = 0; i < OCS_HCU_HW_KEY_LEN_U32; i++)
+		writel(key_u32[OCS_HCU_HW_KEY_LEN_U32 - 1 - i],
+		       hcu_dev->io_base + OCS_HCU_KEY_0 + (sizeof(u32) * i));
+
+	memzero_explicit(key_u32, OCS_HCU_HW_KEY_LEN);
+
+	return 0;
+}
+
+/**
+ * ocs_hcu_ll_dma_start() - Start OCS HCU hashing via DMA
+ * @hcu_dev:	The OCS HCU device to use.
+ * @dma_list:	The OCS DMA list mapping the data to hash.
+ * @finalize:	Whether or not this is the last hashing operation and therefore
+ *		the final hash should be compute even if data is not
+ *		block-aligned.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+static int ocs_hcu_ll_dma_start(struct ocs_hcu_dev *hcu_dev,
+				const struct ocs_hcu_dma_list *dma_list,
+				bool finalize)
+{
+	u32 cfg = HCU_DMA_SNOOP_MASK | HCU_DMA_SRC_LL_EN | HCU_DMA_EN;
+	int rc;
+
+	if (!dma_list)
+		return -EINVAL;
+
+	/*
+	 * For final requests we use HCU_DONE IRQ to be notified when all input
+	 * data has been processed by the HCU; however, we cannot do so for
+	 * non-final requests, because we don't get a HCU_DONE IRQ when we
+	 * don't terminate the operation.
+	 *
+	 * Therefore, for non-final requests, we use the DMA IRQ, which
+	 * triggers when DMA has finishing feeding all the input data to the
+	 * HCU, but the HCU may still be processing it. This is fine, since we
+	 * will wait for the HCU processing to be completed when we try to read
+	 * intermediate results, in ocs_hcu_get_intermediate_data().
+	 */
+	if (finalize)
+		ocs_hcu_done_irq_en(hcu_dev);
+	else
+		ocs_hcu_dma_irq_en(hcu_dev);
+
+	reinit_completion(&hcu_dev->irq_done);
+	writel(dma_list->dma_addr, hcu_dev->io_base + OCS_HCU_DMA_NEXT_SRC_DESCR);
+	writel(0, hcu_dev->io_base + OCS_HCU_DMA_SRC_SIZE);
+	writel(0, hcu_dev->io_base + OCS_HCU_DMA_DST_SIZE);
+
+	writel(OCS_HCU_START, hcu_dev->io_base + OCS_HCU_OPERATION);
+
+	writel(cfg, hcu_dev->io_base + OCS_HCU_DMA_DMA_MODE);
+
+	if (finalize)
+		writel(OCS_HCU_TERMINATE, hcu_dev->io_base + OCS_HCU_OPERATION);
+
+	rc = ocs_hcu_wait_and_disable_irq(hcu_dev);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+struct ocs_hcu_dma_list *ocs_hcu_dma_list_alloc(struct ocs_hcu_dev *hcu_dev,
+						int max_nents)
+{
+	struct ocs_hcu_dma_list *dma_list;
+
+	dma_list = kmalloc(sizeof(*dma_list), GFP_KERNEL);
+	if (!dma_list)
+		return NULL;
+
+	/* Total size of the DMA list to allocate. */
+	dma_list->head = dma_alloc_coherent(hcu_dev->dev,
+					    sizeof(*dma_list->head) * max_nents,
+					    &dma_list->dma_addr, GFP_KERNEL);
+	if (!dma_list->head) {
+		kfree(dma_list);
+		return NULL;
+	}
+	dma_list->max_nents = max_nents;
+	dma_list->tail = NULL;
+
+	return dma_list;
+}
+
+void ocs_hcu_dma_list_free(struct ocs_hcu_dev *hcu_dev,
+			   struct ocs_hcu_dma_list *dma_list)
+{
+	if (!dma_list)
+		return;
+
+	dma_free_coherent(hcu_dev->dev,
+			  sizeof(*dma_list->head) * dma_list->max_nents,
+			  dma_list->head, dma_list->dma_addr);
+
+	kfree(dma_list);
+}
+
+/* Add a new DMA entry at the end of the OCS DMA list. */
+int ocs_hcu_dma_list_add_tail(struct ocs_hcu_dev *hcu_dev,
+			      struct ocs_hcu_dma_list *dma_list,
+			      dma_addr_t addr, u32 len)
+{
+	struct device *dev = hcu_dev->dev;
+	struct ocs_hcu_dma_entry *old_tail;
+	struct ocs_hcu_dma_entry *new_tail;
+
+	if (!len)
+		return 0;
+
+	if (!dma_list)
+		return -EINVAL;
+
+	if (addr & ~OCS_HCU_DMA_BIT_MASK) {
+		dev_err(dev,
+			"Unexpected error: Invalid DMA address for OCS HCU\n");
+		return -EINVAL;
+	}
+
+	old_tail = dma_list->tail;
+	new_tail = old_tail ? old_tail + 1 : dma_list->head;
+
+	/* Check if list is full. */
+	if (new_tail - dma_list->head >= dma_list->max_nents)
+		return -ENOMEM;
+
+	/*
+	 * If there was an old tail (i.e., this is not the first element we are
+	 * adding), un-terminate the old tail and make it point to the new one.
+	 */
+	if (old_tail) {
+		old_tail->ll_flags &= ~OCS_LL_DMA_FLAG_TERMINATE;
+		/*
+		 * The old tail 'nxt_desc' must point to the DMA address of the
+		 * new tail.
+		 */
+		old_tail->nxt_desc = dma_list->dma_addr +
+				     sizeof(*dma_list->tail) * (new_tail -
+								dma_list->head);
+	}
+
+	new_tail->src_addr = (u32)addr;
+	new_tail->src_len = (u32)len;
+	new_tail->ll_flags = OCS_LL_DMA_FLAG_TERMINATE;
+	new_tail->nxt_desc = 0;
+
+	/* Update list tail with new tail. */
+	dma_list->tail = new_tail;
+
+	return 0;
+}
+
+/**
+ * ocs_hcu_hash_init() - Initialize hash operation context.
+ * @ctx:	The context to initialize.
+ * @algo:	The hashing algorithm to use.
+ *
+ * Return:	0 on success, negative error code otherwise.
+ */
+int ocs_hcu_hash_init(struct ocs_hcu_hash_ctx *ctx, enum ocs_hcu_algo algo)
+{
+	if (!ctx)
+		return -EINVAL;
+
+	ctx->algo = algo;
+	ctx->idata.msg_len_lo = 0;
+	ctx->idata.msg_len_hi = 0;
+	/* No need to set idata.digest to 0. */
+
+	return 0;
+}
+
+/**
+ * ocs_hcu_digest() - Perform a hashing iteration.
+ * @hcu_dev:	The OCS HCU device to use.
+ * @ctx:	The OCS HCU hashing context.
+ * @dma_list:	The OCS DMA list mapping the input data to process.
+ *
+ * Return: 0 on success; negative error code otherwise.
+ */
+int ocs_hcu_hash_update(struct ocs_hcu_dev *hcu_dev,
+			struct ocs_hcu_hash_ctx *ctx,
+			const struct ocs_hcu_dma_list *dma_list)
+{
+	int rc;
+
+	if (!hcu_dev || !ctx)
+		return -EINVAL;
+
+	/* Configure the hardware for the current request. */
+	rc = ocs_hcu_hw_cfg(hcu_dev, ctx->algo, false);
+	if (rc)
+		return rc;
+
+	/* If we already processed some data, idata needs to be set. */
+	if (ctx->idata.msg_len_lo || ctx->idata.msg_len_hi)
+		ocs_hcu_set_intermediate_data(hcu_dev, &ctx->idata, ctx->algo);
+
+	/* Start linked-list DMA hashing. */
+	rc = ocs_hcu_ll_dma_start(hcu_dev, dma_list, false);
+	if (rc)
+		return rc;
+
+	/* Update idata and return. */
+	return ocs_hcu_get_intermediate_data(hcu_dev, &ctx->idata, ctx->algo);
+}
+
+/**
+ * ocs_hcu_hash_final() - Update and finalize hash computation.
+ * @hcu_dev:	The OCS HCU device to use.
+ * @ctx:	The OCS HCU hashing context.
+ * @dma_list:	The OCS DMA list mapping the input data to process.
+ * @dgst:	The buffer where to save the computed digest.
+ * @dgst_len:	The length of @dgst.
+ *
+ * Return: 0 on success; negative error code otherwise.
+ */
+int ocs_hcu_hash_finup(struct ocs_hcu_dev *hcu_dev,
+		       const struct ocs_hcu_hash_ctx *ctx,
+		       const struct ocs_hcu_dma_list *dma_list,
+		       u8 *dgst, size_t dgst_len)
+{
+	int rc;
+
+	if (!hcu_dev || !ctx)
+		return -EINVAL;
+
+	/* Configure the hardware for the current request. */
+	rc = ocs_hcu_hw_cfg(hcu_dev, ctx->algo, false);
+	if (rc)
+		return rc;
+
+	/* If we already processed some data, idata needs to be set. */
+	if (ctx->idata.msg_len_lo || ctx->idata.msg_len_hi)
+		ocs_hcu_set_intermediate_data(hcu_dev, &ctx->idata, ctx->algo);
+
+	/* Start linked-list DMA hashing. */
+	rc = ocs_hcu_ll_dma_start(hcu_dev, dma_list, true);
+	if (rc)
+		return rc;
+
+	/* Get digest and return. */
+	return ocs_hcu_get_digest(hcu_dev, ctx->algo, dgst, dgst_len);
+}
+
+/**
+ * ocs_hcu_hash_final() - Finalize hash computation.
+ * @hcu_dev:		The OCS HCU device to use.
+ * @ctx:		The OCS HCU hashing context.
+ * @dgst:		The buffer where to save the computed digest.
+ * @dgst_len:		The length of @dgst.
+ *
+ * Return: 0 on success; negative error code otherwise.
+ */
+int ocs_hcu_hash_final(struct ocs_hcu_dev *hcu_dev,
+		       const struct ocs_hcu_hash_ctx *ctx, u8 *dgst,
+		       size_t dgst_len)
+{
+	int rc;
+
+	if (!hcu_dev || !ctx)
+		return -EINVAL;
+
+	/* Configure the hardware for the current request. */
+	rc = ocs_hcu_hw_cfg(hcu_dev, ctx->algo, false);
+	if (rc)
+		return rc;
+
+	/* If we already processed some data, idata needs to be set. */
+	if (ctx->idata.msg_len_lo || ctx->idata.msg_len_hi)
+		ocs_hcu_set_intermediate_data(hcu_dev, &ctx->idata, ctx->algo);
+
+	/*
+	 * Enable HCU interrupts, so that HCU_DONE will be triggered once the
+	 * final hash is computed.
+	 */
+	ocs_hcu_done_irq_en(hcu_dev);
+	reinit_completion(&hcu_dev->irq_done);
+	writel(OCS_HCU_TERMINATE, hcu_dev->io_base + OCS_HCU_OPERATION);
+
+	rc = ocs_hcu_wait_and_disable_irq(hcu_dev);
+	if (rc)
+		return rc;
+
+	/* Get digest and return. */
+	return ocs_hcu_get_digest(hcu_dev, ctx->algo, dgst, dgst_len);
+}
+
+/**
+ * ocs_hcu_digest() - Compute hash digest.
+ * @hcu_dev:		The OCS HCU device to use.
+ * @algo:		The hash algorithm to use.
+ * @data:		The input data to process.
+ * @data_len:		The length of @data.
+ * @dgst:		The buffer where to save the computed digest.
+ * @dgst_len:		The length of @dgst.
+ *
+ * Return: 0 on success; negative error code otherwise.
+ */
+int ocs_hcu_digest(struct ocs_hcu_dev *hcu_dev, enum ocs_hcu_algo algo,
+		   void *data, size_t data_len, u8 *dgst, size_t dgst_len)
+{
+	struct device *dev = hcu_dev->dev;
+	dma_addr_t dma_handle;
+	u32 reg;
+	int rc;
+
+	/* Configure the hardware for the current request. */
+	rc = ocs_hcu_hw_cfg(hcu_dev, algo, false);
+	if (rc)
+		return rc;
+
+	dma_handle = dma_map_single(dev, data, data_len, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, dma_handle))
+		return -EIO;
+
+	reg = HCU_DMA_SNOOP_MASK | HCU_DMA_EN;
+
+	ocs_hcu_done_irq_en(hcu_dev);
+
+	reinit_completion(&hcu_dev->irq_done);
+
+	writel(dma_handle, hcu_dev->io_base + OCS_HCU_DMA_SRC_ADDR);
+	writel(data_len, hcu_dev->io_base + OCS_HCU_DMA_SRC_SIZE);
+	writel(OCS_HCU_START, hcu_dev->io_base + OCS_HCU_OPERATION);
+	writel(reg, hcu_dev->io_base + OCS_HCU_DMA_DMA_MODE);
+
+	writel(OCS_HCU_TERMINATE, hcu_dev->io_base + OCS_HCU_OPERATION);
+
+	rc = ocs_hcu_wait_and_disable_irq(hcu_dev);
+	if (rc)
+		return rc;
+
+	dma_unmap_single(dev, dma_handle, data_len, DMA_TO_DEVICE);
+
+	return ocs_hcu_get_digest(hcu_dev, algo, dgst, dgst_len);
+}
+
+/**
+ * ocs_hcu_hmac() - Compute HMAC.
+ * @hcu_dev:		The OCS HCU device to use.
+ * @algo:		The hash algorithm to use with HMAC.
+ * @key:		The key to use.
+ * @dma_list:	The OCS DMA list mapping the input data to process.
+ * @key_len:		The length of @key.
+ * @dgst:		The buffer where to save the computed HMAC.
+ * @dgst_len:		The length of @dgst.
+ *
+ * Return: 0 on success; negative error code otherwise.
+ */
+int ocs_hcu_hmac(struct ocs_hcu_dev *hcu_dev, enum ocs_hcu_algo algo,
+		 const u8 *key, size_t key_len,
+		 const struct ocs_hcu_dma_list *dma_list,
+		 u8 *dgst, size_t dgst_len)
+{
+	int rc;
+
+	/* Ensure 'key' is not NULL. */
+	if (!key || key_len == 0)
+		return -EINVAL;
+
+	/* Configure the hardware for the current request. */
+	rc = ocs_hcu_hw_cfg(hcu_dev, algo, true);
+	if (rc)
+		return rc;
+
+	rc = ocs_hcu_write_key(hcu_dev, key, key_len);
+	if (rc)
+		return rc;
+
+	rc = ocs_hcu_ll_dma_start(hcu_dev, dma_list, true);
+
+	/* Clear HW key before processing return code. */
+	ocs_hcu_clear_key(hcu_dev);
+
+	if (rc)
+		return rc;
+
+	return ocs_hcu_get_digest(hcu_dev, algo, dgst, dgst_len);
+}
+
+irqreturn_t ocs_hcu_irq_handler(int irq, void *dev_id)
+{
+	struct ocs_hcu_dev *hcu_dev = dev_id;
+	u32 hcu_irq;
+	u32 dma_irq;
+
+	/* Read and clear the HCU interrupt. */
+	hcu_irq = readl(hcu_dev->io_base + OCS_HCU_ISR);
+	writel(hcu_irq, hcu_dev->io_base + OCS_HCU_ISR);
+
+	/* Read and clear the HCU DMA interrupt. */
+	dma_irq = readl(hcu_dev->io_base + OCS_HCU_DMA_MSI_ISR);
+	writel(dma_irq, hcu_dev->io_base + OCS_HCU_DMA_MSI_ISR);
+
+	/* Check for errors. */
+	if (hcu_irq & HCU_IRQ_HASH_ERR_MASK || dma_irq & HCU_DMA_IRQ_ERR_MASK) {
+		hcu_dev->irq_err = true;
+		goto complete;
+	}
+
+	/* Check for DONE IRQs. */
+	if (hcu_irq & HCU_IRQ_HASH_DONE || dma_irq & HCU_DMA_IRQ_SRC_DONE)
+		goto complete;
+
+	return IRQ_NONE;
+
+complete:
+	complete(&hcu_dev->irq_done);
+
+	return IRQ_HANDLED;
+}
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/keembay/ocs-hcu.h b/drivers/crypto/keembay/ocs-hcu.h
new file mode 100644
index 000000000000..fbbbb92a0592
--- /dev/null
+++ b/drivers/crypto/keembay/ocs-hcu.h
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Intel Keem Bay OCS HCU Crypto Driver.
+ *
+ * Copyright (C) 2018-2020 Intel Corporation
+ */
+
+#include <linux/dma-mapping.h>
+
+#ifndef _CRYPTO_OCS_HCU_H
+#define _CRYPTO_OCS_HCU_H
+
+#define OCS_HCU_DMA_BIT_MASK		DMA_BIT_MASK(32)
+
+#define OCS_HCU_HW_KEY_LEN		64
+
+struct ocs_hcu_dma_list;
+
+enum ocs_hcu_algo {
+	OCS_HCU_ALGO_SHA256 = 2,
+	OCS_HCU_ALGO_SHA224 = 3,
+	OCS_HCU_ALGO_SHA384 = 4,
+	OCS_HCU_ALGO_SHA512 = 5,
+	OCS_HCU_ALGO_SM3    = 6,
+};
+
+/**
+ * struct ocs_hcu_dev - OCS HCU device context.
+ * @list:	List of device contexts.
+ * @dev:	OCS HCU device.
+ * @io_base:	Base address of OCS HCU registers.
+ * @engine:	Crypto engine for the device.
+ * @irq:	IRQ number.
+ * @irq_done:	Completion for IRQ.
+ * @irq_err:	Flag indicating an IRQ error has happened.
+ */
+struct ocs_hcu_dev {
+	struct list_head list;
+	struct device *dev;
+	void __iomem *io_base;
+	struct crypto_engine *engine;
+	int irq;
+	struct completion irq_done;
+	bool irq_err;
+};
+
+/**
+ * struct ocs_hcu_idata - Intermediate data generated by the HCU.
+ * @msg_len_lo: Length of data the HCU has operated on in bits, low 32b.
+ * @msg_len_hi: Length of data the HCU has operated on in bits, high 32b.
+ * @digest: The digest read from the HCU. If the HCU is terminated, it will
+ *	    contain the actual hash digest. Otherwise it is the intermediate
+ *	    state.
+ */
+struct ocs_hcu_idata {
+	u32 msg_len_lo;
+	u32 msg_len_hi;
+	u8  digest[SHA512_DIGEST_SIZE];
+};
+
+/**
+ * struct ocs_hcu_hash_ctx - Context for OCS HCU hashing operation.
+ * @algo:	The hashing algorithm being used.
+ * @idata:	The current intermediate data.
+ */
+struct ocs_hcu_hash_ctx {
+	enum ocs_hcu_algo	algo;
+	struct ocs_hcu_idata	idata;
+};
+
+irqreturn_t ocs_hcu_irq_handler(int irq, void *dev_id);
+
+struct ocs_hcu_dma_list *ocs_hcu_dma_list_alloc(struct ocs_hcu_dev *hcu_dev,
+						int max_nents);
+
+void ocs_hcu_dma_list_free(struct ocs_hcu_dev *hcu_dev,
+			   struct ocs_hcu_dma_list *dma_list);
+
+int ocs_hcu_dma_list_add_tail(struct ocs_hcu_dev *hcu_dev,
+			      struct ocs_hcu_dma_list *dma_list,
+			      dma_addr_t addr, u32 len);
+
+int ocs_hcu_hash_init(struct ocs_hcu_hash_ctx *ctx, enum ocs_hcu_algo algo);
+
+int ocs_hcu_hash_update(struct ocs_hcu_dev *hcu_dev,
+			struct ocs_hcu_hash_ctx *ctx,
+			const struct ocs_hcu_dma_list *dma_list);
+
+int ocs_hcu_hash_finup(struct ocs_hcu_dev *hcu_dev,
+		       const struct ocs_hcu_hash_ctx *ctx,
+		       const struct ocs_hcu_dma_list *dma_list,
+		       u8 *dgst, size_t dgst_len);
+
+int ocs_hcu_hash_final(struct ocs_hcu_dev *hcu_dev,
+		       const struct ocs_hcu_hash_ctx *ctx, u8 *dgst,
+		       size_t dgst_len);
+
+int ocs_hcu_digest(struct ocs_hcu_dev *hcu_dev, enum ocs_hcu_algo algo,
+		   void *data, size_t data_len, u8 *dgst, size_t dgst_len);
+
+int ocs_hcu_hmac(struct ocs_hcu_dev *hcu_dev, enum ocs_hcu_algo algo,
+		 const u8 *key, size_t key_len,
+		 const struct ocs_hcu_dma_list *dma_list,
+		 u8 *dgst, size_t dgst_len);
+
+#endif /* _CRYPTO_OCS_HCU_H */
diff --git a/drivers/crypto/marvell/Kconfig b/drivers/crypto/marvell/Kconfig
index 13063384f958..9125199f1702 100644
--- a/drivers/crypto/marvell/Kconfig
+++ b/drivers/crypto/marvell/Kconfig
@@ -35,3 +35,18 @@ config CRYPTO_DEV_OCTEONTX_CPT
 
 		To compile this driver as module, choose M here:
 		the modules will be called octeontx-cpt and octeontx-cptvf
+
+config CRYPTO_DEV_OCTEONTX2_CPT
+	tristate "Marvell OcteonTX2 CPT driver"
+	depends on ARCH_THUNDER2 || COMPILE_TEST
+	depends on PCI_MSI && 64BIT
+	depends on CRYPTO_LIB_AES
+	depends on NET_VENDOR_MARVELL
+	select OCTEONTX2_MBOX
+	select CRYPTO_DEV_MARVELL
+	select CRYPTO_SKCIPHER
+	select CRYPTO_HASH
+	select CRYPTO_AEAD
+	help
+		This driver allows you to utilize the Marvell Cryptographic
+		Accelerator Unit(CPT) found in OcteonTX2 series of processors.
diff --git a/drivers/crypto/marvell/Makefile b/drivers/crypto/marvell/Makefile
index 6c6a1519b0f1..39db6d9c0aaf 100644
--- a/drivers/crypto/marvell/Makefile
+++ b/drivers/crypto/marvell/Makefile
@@ -2,3 +2,4 @@
 
 obj-$(CONFIG_CRYPTO_DEV_MARVELL_CESA) += cesa/
 obj-$(CONFIG_CRYPTO_DEV_OCTEONTX_CPT) += octeontx/
+obj-$(CONFIG_CRYPTO_DEV_OCTEONTX2_CPT) += octeontx2/
diff --git a/drivers/crypto/marvell/cesa/cesa.c b/drivers/crypto/marvell/cesa/cesa.c
index 06211858bf2e..f14aac532f53 100644
--- a/drivers/crypto/marvell/cesa/cesa.c
+++ b/drivers/crypto/marvell/cesa/cesa.c
@@ -381,10 +381,10 @@ static int mv_cesa_get_sram(struct platform_device *pdev, int idx)
 	engine->pool = of_gen_pool_get(cesa->dev->of_node,
 				       "marvell,crypto-srams", idx);
 	if (engine->pool) {
-		engine->sram = gen_pool_dma_alloc(engine->pool,
-						  cesa->sram_size,
-						  &engine->sram_dma);
-		if (engine->sram)
+		engine->sram_pool = gen_pool_dma_alloc(engine->pool,
+						       cesa->sram_size,
+						       &engine->sram_dma);
+		if (engine->sram_pool)
 			return 0;
 
 		engine->pool = NULL;
@@ -422,7 +422,7 @@ static void mv_cesa_put_sram(struct platform_device *pdev, int idx)
 	struct mv_cesa_engine *engine = &cesa->engines[idx];
 
 	if (engine->pool)
-		gen_pool_free(engine->pool, (unsigned long)engine->sram,
+		gen_pool_free(engine->pool, (unsigned long)engine->sram_pool,
 			      cesa->sram_size);
 	else
 		dma_unmap_resource(cesa->dev, engine->sram_dma,
diff --git a/drivers/crypto/marvell/cesa/cesa.h b/drivers/crypto/marvell/cesa/cesa.h
index fa56b45620c7..c1007f2ba79c 100644
--- a/drivers/crypto/marvell/cesa/cesa.h
+++ b/drivers/crypto/marvell/cesa/cesa.h
@@ -428,6 +428,7 @@ struct mv_cesa_dev {
  * @id:			engine id
  * @regs:		engine registers
  * @sram:		SRAM memory region
+ * @sram_pool:		SRAM memory region from pool
  * @sram_dma:		DMA address of the SRAM memory region
  * @lock:		engine lock
  * @req:		current crypto request
@@ -448,7 +449,10 @@ struct mv_cesa_dev {
 struct mv_cesa_engine {
 	int id;
 	void __iomem *regs;
-	void __iomem *sram;
+	union {
+		void __iomem *sram;
+		void *sram_pool;
+	};
 	dma_addr_t sram_dma;
 	spinlock_t lock;
 	struct crypto_async_request *req;
@@ -867,6 +871,31 @@ int mv_cesa_dma_add_op_transfers(struct mv_cesa_tdma_chain *chain,
 				 struct mv_cesa_sg_dma_iter *sgiter,
 				 gfp_t gfp_flags);
 
+size_t mv_cesa_sg_copy(struct mv_cesa_engine *engine,
+		       struct scatterlist *sgl, unsigned int nents,
+		       unsigned int sram_off, size_t buflen, off_t skip,
+		       bool to_sram);
+
+static inline size_t mv_cesa_sg_copy_to_sram(struct mv_cesa_engine *engine,
+					     struct scatterlist *sgl,
+					     unsigned int nents,
+					     unsigned int sram_off,
+					     size_t buflen, off_t skip)
+{
+	return mv_cesa_sg_copy(engine, sgl, nents, sram_off, buflen, skip,
+			       true);
+}
+
+static inline size_t mv_cesa_sg_copy_from_sram(struct mv_cesa_engine *engine,
+					       struct scatterlist *sgl,
+					       unsigned int nents,
+					       unsigned int sram_off,
+					       size_t buflen, off_t skip)
+{
+	return mv_cesa_sg_copy(engine, sgl, nents, sram_off, buflen, skip,
+			       false);
+}
+
 /* Algorithm definitions */
 
 extern struct ahash_alg mv_md5_alg;
diff --git a/drivers/crypto/marvell/cesa/cipher.c b/drivers/crypto/marvell/cesa/cipher.c
index b4a6ff9dd6d5..b739d3b873dc 100644
--- a/drivers/crypto/marvell/cesa/cipher.c
+++ b/drivers/crypto/marvell/cesa/cipher.c
@@ -89,22 +89,29 @@ static void mv_cesa_skcipher_std_step(struct skcipher_request *req)
 			    CESA_SA_SRAM_PAYLOAD_SIZE);
 
 	mv_cesa_adjust_op(engine, &sreq->op);
-	memcpy_toio(engine->sram, &sreq->op, sizeof(sreq->op));
+	if (engine->pool)
+		memcpy(engine->sram_pool, &sreq->op, sizeof(sreq->op));
+	else
+		memcpy_toio(engine->sram, &sreq->op, sizeof(sreq->op));
 
-	len = sg_pcopy_to_buffer(req->src, creq->src_nents,
-				 engine->sram + CESA_SA_DATA_SRAM_OFFSET,
-				 len, sreq->offset);
+	len = mv_cesa_sg_copy_to_sram(engine, req->src, creq->src_nents,
+				      CESA_SA_DATA_SRAM_OFFSET, len,
+				      sreq->offset);
 
 	sreq->size = len;
 	mv_cesa_set_crypt_op_len(&sreq->op, len);
 
 	/* FIXME: only update enc_len field */
 	if (!sreq->skip_ctx) {
-		memcpy_toio(engine->sram, &sreq->op, sizeof(sreq->op));
+		if (engine->pool)
+			memcpy(engine->sram_pool, &sreq->op, sizeof(sreq->op));
+		else
+			memcpy_toio(engine->sram, &sreq->op, sizeof(sreq->op));
 		sreq->skip_ctx = true;
-	} else {
+	} else if (engine->pool)
+		memcpy(engine->sram_pool, &sreq->op, sizeof(sreq->op.desc));
+	else
 		memcpy_toio(engine->sram, &sreq->op, sizeof(sreq->op.desc));
-	}
 
 	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
 	writel_relaxed(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
@@ -121,9 +128,9 @@ static int mv_cesa_skcipher_std_process(struct skcipher_request *req,
 	struct mv_cesa_engine *engine = creq->base.engine;
 	size_t len;
 
-	len = sg_pcopy_from_buffer(req->dst, creq->dst_nents,
-				   engine->sram + CESA_SA_DATA_SRAM_OFFSET,
-				   sreq->size, sreq->offset);
+	len = mv_cesa_sg_copy_from_sram(engine, req->dst, creq->dst_nents,
+					CESA_SA_DATA_SRAM_OFFSET, sreq->size,
+					sreq->offset);
 
 	sreq->offset += len;
 	if (sreq->offset < req->cryptlen)
@@ -214,11 +221,14 @@ mv_cesa_skcipher_complete(struct crypto_async_request *req)
 		basereq = &creq->base;
 		memcpy(skreq->iv, basereq->chain.last->op->ctx.skcipher.iv,
 		       ivsize);
-	} else {
+	} else if (engine->pool)
+		memcpy(skreq->iv,
+		       engine->sram_pool + CESA_SA_CRYPT_IV_SRAM_OFFSET,
+		       ivsize);
+	else
 		memcpy_fromio(skreq->iv,
 			      engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,
 			      ivsize);
-	}
 }
 
 static const struct mv_cesa_req_ops mv_cesa_skcipher_req_ops = {
diff --git a/drivers/crypto/marvell/cesa/hash.c b/drivers/crypto/marvell/cesa/hash.c
index 8cf9fd518d86..c72b0672fc71 100644
--- a/drivers/crypto/marvell/cesa/hash.c
+++ b/drivers/crypto/marvell/cesa/hash.c
@@ -168,7 +168,12 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req)
 	int i;
 
 	mv_cesa_adjust_op(engine, &creq->op_tmpl);
-	memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
+	if (engine->pool)
+		memcpy(engine->sram_pool, &creq->op_tmpl,
+		       sizeof(creq->op_tmpl));
+	else
+		memcpy_toio(engine->sram, &creq->op_tmpl,
+			    sizeof(creq->op_tmpl));
 
 	if (!sreq->offset) {
 		digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req));
@@ -177,9 +182,14 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req)
 				       engine->regs + CESA_IVDIG(i));
 	}
 
-	if (creq->cache_ptr)
-		memcpy_toio(engine->sram + CESA_SA_DATA_SRAM_OFFSET,
-			    creq->cache, creq->cache_ptr);
+	if (creq->cache_ptr) {
+		if (engine->pool)
+			memcpy(engine->sram_pool + CESA_SA_DATA_SRAM_OFFSET,
+			       creq->cache, creq->cache_ptr);
+		else
+			memcpy_toio(engine->sram + CESA_SA_DATA_SRAM_OFFSET,
+				    creq->cache, creq->cache_ptr);
+	}
 
 	len = min_t(size_t, req->nbytes + creq->cache_ptr - sreq->offset,
 		    CESA_SA_SRAM_PAYLOAD_SIZE);
@@ -190,12 +200,10 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req)
 	}
 
 	if (len - creq->cache_ptr)
-		sreq->offset += sg_pcopy_to_buffer(req->src, creq->src_nents,
-						   engine->sram +
-						   CESA_SA_DATA_SRAM_OFFSET +
-						   creq->cache_ptr,
-						   len - creq->cache_ptr,
-						   sreq->offset);
+		sreq->offset += mv_cesa_sg_copy_to_sram(
+			engine, req->src, creq->src_nents,
+			CESA_SA_DATA_SRAM_OFFSET + creq->cache_ptr,
+			len - creq->cache_ptr, sreq->offset);
 
 	op = &creq->op_tmpl;
 
@@ -220,16 +228,28 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req)
 			if (len + trailerlen > CESA_SA_SRAM_PAYLOAD_SIZE) {
 				len &= CESA_HASH_BLOCK_SIZE_MSK;
 				new_cache_ptr = 64 - trailerlen;
-				memcpy_fromio(creq->cache,
-					      engine->sram +
-					      CESA_SA_DATA_SRAM_OFFSET + len,
-					      new_cache_ptr);
+				if (engine->pool)
+					memcpy(creq->cache,
+					       engine->sram_pool +
+					       CESA_SA_DATA_SRAM_OFFSET + len,
+					       new_cache_ptr);
+				else
+					memcpy_fromio(creq->cache,
+						      engine->sram +
+						      CESA_SA_DATA_SRAM_OFFSET +
+						      len,
+						      new_cache_ptr);
 			} else {
 				i = mv_cesa_ahash_pad_req(creq, creq->cache);
 				len += i;
-				memcpy_toio(engine->sram + len +
-					    CESA_SA_DATA_SRAM_OFFSET,
-					    creq->cache, i);
+				if (engine->pool)
+					memcpy(engine->sram_pool + len +
+					       CESA_SA_DATA_SRAM_OFFSET,
+					       creq->cache, i);
+				else
+					memcpy_toio(engine->sram + len +
+						    CESA_SA_DATA_SRAM_OFFSET,
+						    creq->cache, i);
 			}
 
 			if (frag_mode == CESA_SA_DESC_CFG_LAST_FRAG)
@@ -243,7 +263,10 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req)
 	mv_cesa_update_op_cfg(op, frag_mode, CESA_SA_DESC_CFG_FRAG_MSK);
 
 	/* FIXME: only update enc_len field */
-	memcpy_toio(engine->sram, op, sizeof(*op));
+	if (engine->pool)
+		memcpy(engine->sram_pool, op, sizeof(*op));
+	else
+		memcpy_toio(engine->sram, op, sizeof(*op));
 
 	if (frag_mode == CESA_SA_DESC_CFG_FIRST_FRAG)
 		mv_cesa_update_op_cfg(op, CESA_SA_DESC_CFG_MID_FRAG,
diff --git a/drivers/crypto/marvell/cesa/tdma.c b/drivers/crypto/marvell/cesa/tdma.c
index 5d9c48fb72b2..f0b5537038c2 100644
--- a/drivers/crypto/marvell/cesa/tdma.c
+++ b/drivers/crypto/marvell/cesa/tdma.c
@@ -177,7 +177,7 @@ int mv_cesa_tdma_process(struct mv_cesa_engine *engine, u32 status)
 
 	/*
 	 * Save the last request in error to engine->req, so that the core
-	 * knows which request was fautly
+	 * knows which request was faulty
 	 */
 	if (res) {
 		spin_lock_bh(&engine->lock);
@@ -350,3 +350,53 @@ int mv_cesa_dma_add_op_transfers(struct mv_cesa_tdma_chain *chain,
 
 	return 0;
 }
+
+size_t mv_cesa_sg_copy(struct mv_cesa_engine *engine,
+		       struct scatterlist *sgl, unsigned int nents,
+		       unsigned int sram_off, size_t buflen, off_t skip,
+		       bool to_sram)
+{
+	unsigned int sg_flags = SG_MITER_ATOMIC;
+	struct sg_mapping_iter miter;
+	unsigned int offset = 0;
+
+	if (to_sram)
+		sg_flags |= SG_MITER_FROM_SG;
+	else
+		sg_flags |= SG_MITER_TO_SG;
+
+	sg_miter_start(&miter, sgl, nents, sg_flags);
+
+	if (!sg_miter_skip(&miter, skip))
+		return 0;
+
+	while ((offset < buflen) && sg_miter_next(&miter)) {
+		unsigned int len;
+
+		len = min(miter.length, buflen - offset);
+
+		if (to_sram) {
+			if (engine->pool)
+				memcpy(engine->sram_pool + sram_off + offset,
+				       miter.addr, len);
+			else
+				memcpy_toio(engine->sram + sram_off + offset,
+					    miter.addr, len);
+		} else {
+			if (engine->pool)
+				memcpy(miter.addr,
+				       engine->sram_pool + sram_off + offset,
+				       len);
+			else
+				memcpy_fromio(miter.addr,
+					      engine->sram + sram_off + offset,
+					      len);
+		}
+
+		offset += len;
+	}
+
+	sg_miter_stop(&miter);
+
+	return offset;
+}
diff --git a/drivers/crypto/marvell/octeontx2/Makefile b/drivers/crypto/marvell/octeontx2/Makefile
new file mode 100644
index 000000000000..b9c6201019e0
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_CRYPTO_DEV_OCTEONTX2_CPT) += octeontx2-cpt.o octeontx2-cptvf.o
+
+octeontx2-cpt-objs := otx2_cptpf_main.o otx2_cptpf_mbox.o \
+		      otx2_cpt_mbox_common.o otx2_cptpf_ucode.o otx2_cptlf.o
+octeontx2-cptvf-objs := otx2_cptvf_main.o otx2_cptvf_mbox.o otx2_cptlf.o \
+			otx2_cpt_mbox_common.o otx2_cptvf_reqmgr.o \
+			otx2_cptvf_algs.o
+
+ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h
new file mode 100644
index 000000000000..3518fac29834
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPT_COMMON_H
+#define __OTX2_CPT_COMMON_H
+
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/crypto.h>
+#include "otx2_cpt_hw_types.h"
+#include "rvu.h"
+#include "mbox.h"
+
+#define OTX2_CPT_MAX_VFS_NUM 128
+#define OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs) \
+		(((blk) << 20) | ((slot) << 12) | (offs))
+#define OTX2_CPT_RVU_PFFUNC(pf, func)	\
+		((((pf) & RVU_PFVF_PF_MASK) << RVU_PFVF_PF_SHIFT) | \
+		(((func) & RVU_PFVF_FUNC_MASK) << RVU_PFVF_FUNC_SHIFT))
+
+#define OTX2_CPT_INVALID_CRYPTO_ENG_GRP 0xFF
+#define OTX2_CPT_NAME_LENGTH 64
+#define OTX2_CPT_DMA_MINALIGN 128
+
+#define BAD_OTX2_CPT_ENG_TYPE OTX2_CPT_MAX_ENG_TYPES
+
+enum otx2_cpt_eng_type {
+	OTX2_CPT_AE_TYPES = 1,
+	OTX2_CPT_SE_TYPES = 2,
+	OTX2_CPT_IE_TYPES = 3,
+	OTX2_CPT_MAX_ENG_TYPES,
+};
+
+/* Take mbox id from end of CPT mbox range in AF (range 0xA00 - 0xBFF) */
+#define MBOX_MSG_GET_ENG_GRP_NUM        0xBFF
+#define MBOX_MSG_GET_CAPS               0xBFD
+#define MBOX_MSG_GET_KVF_LIMITS         0xBFC
+
+/*
+ * Message request and response to get engine group number
+ * which has attached a given type of engines (SE, AE, IE)
+ * This messages are only used between CPT PF <=> CPT VF
+ */
+struct otx2_cpt_egrp_num_msg {
+	struct mbox_msghdr hdr;
+	u8 eng_type;
+};
+
+struct otx2_cpt_egrp_num_rsp {
+	struct mbox_msghdr hdr;
+	u8 eng_type;
+	u8 eng_grp_num;
+};
+
+/*
+ * Message request and response to get kernel crypto limits
+ * This messages are only used between CPT PF <-> CPT VF
+ */
+struct otx2_cpt_kvf_limits_msg {
+	struct mbox_msghdr hdr;
+};
+
+struct otx2_cpt_kvf_limits_rsp {
+	struct mbox_msghdr hdr;
+	u8 kvf_limits;
+};
+
+/* CPT HW capabilities */
+union otx2_cpt_eng_caps {
+	u64 u;
+	struct {
+		u64 reserved_0_4:5;
+		u64 mul:1;
+		u64 sha1_sha2:1;
+		u64 chacha20:1;
+		u64 zuc_snow3g:1;
+		u64 sha3:1;
+		u64 aes:1;
+		u64 kasumi:1;
+		u64 des:1;
+		u64 crc:1;
+		u64 reserved_14_63:50;
+	};
+};
+
+/*
+ * Message request and response to get HW capabilities for each
+ * engine type (SE, IE, AE).
+ * This messages are only used between CPT PF <=> CPT VF
+ */
+struct otx2_cpt_caps_msg {
+	struct mbox_msghdr hdr;
+};
+
+struct otx2_cpt_caps_rsp {
+	struct mbox_msghdr hdr;
+	u16 cpt_pf_drv_version;
+	u8 cpt_revision;
+	union otx2_cpt_eng_caps eng_caps[OTX2_CPT_MAX_ENG_TYPES];
+};
+
+static inline void otx2_cpt_write64(void __iomem *reg_base, u64 blk, u64 slot,
+				    u64 offs, u64 val)
+{
+	writeq_relaxed(val, reg_base +
+		       OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs));
+}
+
+static inline u64 otx2_cpt_read64(void __iomem *reg_base, u64 blk, u64 slot,
+				  u64 offs)
+{
+	return readq_relaxed(reg_base +
+			     OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs));
+}
+
+int otx2_cpt_send_ready_msg(struct otx2_mbox *mbox, struct pci_dev *pdev);
+int otx2_cpt_send_mbox_msg(struct otx2_mbox *mbox, struct pci_dev *pdev);
+
+int otx2_cpt_send_af_reg_requests(struct otx2_mbox *mbox,
+				  struct pci_dev *pdev);
+int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox,
+			     struct pci_dev *pdev, u64 reg, u64 *val);
+int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			      u64 reg, u64 val);
+int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			 u64 reg, u64 *val);
+int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			  u64 reg, u64 val);
+struct otx2_cptlfs_info;
+int otx2_cpt_attach_rscrs_msg(struct otx2_cptlfs_info *lfs);
+int otx2_cpt_detach_rsrcs_msg(struct otx2_cptlfs_info *lfs);
+int otx2_cpt_msix_offset_msg(struct otx2_cptlfs_info *lfs);
+
+#endif /* __OTX2_CPT_COMMON_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_hw_types.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_hw_types.h
new file mode 100644
index 000000000000..ecafc42f37a2
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_hw_types.h
@@ -0,0 +1,464 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPT_HW_TYPES_H
+#define __OTX2_CPT_HW_TYPES_H
+
+#include <linux/types.h>
+
+/* Device IDs */
+#define OTX2_CPT_PCI_PF_DEVICE_ID 0xA0FD
+#define OTX2_CPT_PCI_VF_DEVICE_ID 0xA0FE
+
+/* Mailbox interrupts offset */
+#define OTX2_CPT_PF_MBOX_INT	6
+#define OTX2_CPT_PF_INT_VEC_E_MBOXX(x, a) ((x) + (a))
+
+/* Maximum supported microcode groups */
+#define OTX2_CPT_MAX_ENGINE_GROUPS 8
+
+/* CPT instruction size in bytes */
+#define OTX2_CPT_INST_SIZE	64
+/*
+ * CPT VF MSIX vectors and their offsets
+ */
+#define OTX2_CPT_VF_MSIX_VECTORS 1
+#define OTX2_CPT_VF_INTR_MBOX_MASK BIT(0)
+
+/* CPT LF MSIX vectors */
+#define OTX2_CPT_LF_MSIX_VECTORS 2
+
+/* OcteonTX2 CPT PF registers */
+#define OTX2_CPT_PF_CONSTANTS           (0x0)
+#define OTX2_CPT_PF_RESET               (0x100)
+#define OTX2_CPT_PF_DIAG                (0x120)
+#define OTX2_CPT_PF_BIST_STATUS         (0x160)
+#define OTX2_CPT_PF_ECC0_CTL            (0x200)
+#define OTX2_CPT_PF_ECC0_FLIP           (0x210)
+#define OTX2_CPT_PF_ECC0_INT            (0x220)
+#define OTX2_CPT_PF_ECC0_INT_W1S        (0x230)
+#define OTX2_CPT_PF_ECC0_ENA_W1S        (0x240)
+#define OTX2_CPT_PF_ECC0_ENA_W1C        (0x250)
+#define OTX2_CPT_PF_MBOX_INTX(b)        (0x400 | (b) << 3)
+#define OTX2_CPT_PF_MBOX_INT_W1SX(b)    (0x420 | (b) << 3)
+#define OTX2_CPT_PF_MBOX_ENA_W1CX(b)    (0x440 | (b) << 3)
+#define OTX2_CPT_PF_MBOX_ENA_W1SX(b)    (0x460 | (b) << 3)
+#define OTX2_CPT_PF_EXEC_INT            (0x500)
+#define OTX2_CPT_PF_EXEC_INT_W1S        (0x520)
+#define OTX2_CPT_PF_EXEC_ENA_W1C        (0x540)
+#define OTX2_CPT_PF_EXEC_ENA_W1S        (0x560)
+#define OTX2_CPT_PF_GX_EN(b)            (0x600 | (b) << 3)
+#define OTX2_CPT_PF_EXEC_INFO           (0x700)
+#define OTX2_CPT_PF_EXEC_BUSY           (0x800)
+#define OTX2_CPT_PF_EXEC_INFO0          (0x900)
+#define OTX2_CPT_PF_EXEC_INFO1          (0x910)
+#define OTX2_CPT_PF_INST_REQ_PC         (0x10000)
+#define OTX2_CPT_PF_INST_LATENCY_PC     (0x10020)
+#define OTX2_CPT_PF_RD_REQ_PC           (0x10040)
+#define OTX2_CPT_PF_RD_LATENCY_PC       (0x10060)
+#define OTX2_CPT_PF_RD_UC_PC            (0x10080)
+#define OTX2_CPT_PF_ACTIVE_CYCLES_PC    (0x10100)
+#define OTX2_CPT_PF_EXE_CTL             (0x4000000)
+#define OTX2_CPT_PF_EXE_STATUS          (0x4000008)
+#define OTX2_CPT_PF_EXE_CLK             (0x4000010)
+#define OTX2_CPT_PF_EXE_DBG_CTL         (0x4000018)
+#define OTX2_CPT_PF_EXE_DBG_DATA        (0x4000020)
+#define OTX2_CPT_PF_EXE_BIST_STATUS     (0x4000028)
+#define OTX2_CPT_PF_EXE_REQ_TIMER       (0x4000030)
+#define OTX2_CPT_PF_EXE_MEM_CTL         (0x4000038)
+#define OTX2_CPT_PF_EXE_PERF_CTL        (0x4001000)
+#define OTX2_CPT_PF_EXE_DBG_CNTX(b)     (0x4001100 | (b) << 3)
+#define OTX2_CPT_PF_EXE_PERF_EVENT_CNT  (0x4001180)
+#define OTX2_CPT_PF_EXE_EPCI_INBX_CNT(b)  (0x4001200 | (b) << 3)
+#define OTX2_CPT_PF_EXE_EPCI_OUTBX_CNT(b) (0x4001240 | (b) << 3)
+#define OTX2_CPT_PF_ENGX_UCODE_BASE(b)  (0x4002000 | (b) << 3)
+#define OTX2_CPT_PF_QX_CTL(b)           (0x8000000 | (b) << 20)
+#define OTX2_CPT_PF_QX_GMCTL(b)         (0x8000020 | (b) << 20)
+#define OTX2_CPT_PF_QX_CTL2(b)          (0x8000100 | (b) << 20)
+#define OTX2_CPT_PF_VFX_MBOXX(b, c)     (0x8001000 | (b) << 20 | \
+					 (c) << 8)
+
+/* OcteonTX2 CPT LF registers */
+#define OTX2_CPT_LF_CTL                 (0x10)
+#define OTX2_CPT_LF_DONE_WAIT           (0x30)
+#define OTX2_CPT_LF_INPROG              (0x40)
+#define OTX2_CPT_LF_DONE                (0x50)
+#define OTX2_CPT_LF_DONE_ACK            (0x60)
+#define OTX2_CPT_LF_DONE_INT_ENA_W1S    (0x90)
+#define OTX2_CPT_LF_DONE_INT_ENA_W1C    (0xa0)
+#define OTX2_CPT_LF_MISC_INT            (0xb0)
+#define OTX2_CPT_LF_MISC_INT_W1S        (0xc0)
+#define OTX2_CPT_LF_MISC_INT_ENA_W1S    (0xd0)
+#define OTX2_CPT_LF_MISC_INT_ENA_W1C    (0xe0)
+#define OTX2_CPT_LF_Q_BASE              (0xf0)
+#define OTX2_CPT_LF_Q_SIZE              (0x100)
+#define OTX2_CPT_LF_Q_INST_PTR          (0x110)
+#define OTX2_CPT_LF_Q_GRP_PTR           (0x120)
+#define OTX2_CPT_LF_NQX(a)              (0x400 | (a) << 3)
+#define OTX2_CPT_RVU_FUNC_BLKADDR_SHIFT 20
+/* LMT LF registers */
+#define OTX2_CPT_LMT_LFBASE             BIT_ULL(OTX2_CPT_RVU_FUNC_BLKADDR_SHIFT)
+#define OTX2_CPT_LMT_LF_LMTLINEX(a)     (OTX2_CPT_LMT_LFBASE | 0x000 | \
+					 (a) << 12)
+/* RVU VF registers */
+#define OTX2_RVU_VF_INT                 (0x20)
+#define OTX2_RVU_VF_INT_W1S             (0x28)
+#define OTX2_RVU_VF_INT_ENA_W1S         (0x30)
+#define OTX2_RVU_VF_INT_ENA_W1C         (0x38)
+
+/*
+ * Enumeration otx2_cpt_ucode_error_code_e
+ *
+ * Enumerates ucode errors
+ */
+enum otx2_cpt_ucode_comp_code_e {
+	OTX2_CPT_UCC_SUCCESS = 0x00,
+	OTX2_CPT_UCC_INVALID_OPCODE = 0x01,
+
+	/* Scatter gather */
+	OTX2_CPT_UCC_SG_WRITE_LENGTH = 0x02,
+	OTX2_CPT_UCC_SG_LIST = 0x03,
+	OTX2_CPT_UCC_SG_NOT_SUPPORTED = 0x04,
+
+};
+
+/*
+ * Enumeration otx2_cpt_comp_e
+ *
+ * OcteonTX2 CPT Completion Enumeration
+ * Enumerates the values of CPT_RES_S[COMPCODE].
+ */
+enum otx2_cpt_comp_e {
+	OTX2_CPT_COMP_E_NOTDONE = 0x00,
+	OTX2_CPT_COMP_E_GOOD = 0x01,
+	OTX2_CPT_COMP_E_FAULT = 0x02,
+	OTX2_CPT_COMP_E_HWERR = 0x04,
+	OTX2_CPT_COMP_E_INSTERR = 0x05,
+	OTX2_CPT_COMP_E_LAST_ENTRY = 0x06
+};
+
+/*
+ * Enumeration otx2_cpt_vf_int_vec_e
+ *
+ * OcteonTX2 CPT VF MSI-X Vector Enumeration
+ * Enumerates the MSI-X interrupt vectors.
+ */
+enum otx2_cpt_vf_int_vec_e {
+	OTX2_CPT_VF_INT_VEC_E_MBOX = 0x00
+};
+
+/*
+ * Enumeration otx2_cpt_lf_int_vec_e
+ *
+ * OcteonTX2 CPT LF MSI-X Vector Enumeration
+ * Enumerates the MSI-X interrupt vectors.
+ */
+enum otx2_cpt_lf_int_vec_e {
+	OTX2_CPT_LF_INT_VEC_E_MISC = 0x00,
+	OTX2_CPT_LF_INT_VEC_E_DONE = 0x01
+};
+
+/*
+ * Structure otx2_cpt_inst_s
+ *
+ * CPT Instruction Structure
+ * This structure specifies the instruction layout. Instructions are
+ * stored in memory as little-endian unless CPT()_PF_Q()_CTL[INST_BE] is set.
+ * cpt_inst_s_s
+ * Word 0
+ * doneint:1 Done interrupt.
+ *	0 = No interrupts related to this instruction.
+ *	1 = When the instruction completes, CPT()_VQ()_DONE[DONE] will be
+ *	incremented,and based on the rules described there an interrupt may
+ *	occur.
+ * Word 1
+ * res_addr [127: 64] Result IOVA.
+ *	If nonzero, specifies where to write CPT_RES_S.
+ *	If zero, no result structure will be written.
+ *	Address must be 16-byte aligned.
+ *	Bits <63:49> are ignored by hardware; software should use a
+ *	sign-extended bit <48> for forward compatibility.
+ * Word 2
+ *  grp:10 [171:162] If [WQ_PTR] is nonzero, the SSO guest-group to use when
+ *	CPT submits work SSO.
+ *	For the SSO to not discard the add-work request, FPA_PF_MAP() must map
+ *	[GRP] and CPT()_PF_Q()_GMCTL[GMID] as valid.
+ *  tt:2 [161:160] If [WQ_PTR] is nonzero, the SSO tag type to use when CPT
+ *	submits work to SSO
+ *  tag:32 [159:128] If [WQ_PTR] is nonzero, the SSO tag to use when CPT
+ *	submits work to SSO.
+ * Word 3
+ *  wq_ptr [255:192] If [WQ_PTR] is nonzero, it is a pointer to a
+ *	work-queue entry that CPT submits work to SSO after all context,
+ *	output data, and result write operations are visible to other
+ *	CNXXXX units and the cores. Bits <2:0> must be zero.
+ *	Bits <63:49> are ignored by hardware; software should
+ *	use a sign-extended bit <48> for forward compatibility.
+ *	Internal:
+ *	Bits <63:49>, <2:0> are ignored by hardware, treated as always 0x0.
+ * Word 4
+ *  ei0; [319:256] Engine instruction word 0. Passed to the AE/SE.
+ * Word 5
+ *  ei1; [383:320] Engine instruction word 1. Passed to the AE/SE.
+ * Word 6
+ *  ei2; [447:384] Engine instruction word 1. Passed to the AE/SE.
+ * Word 7
+ *  ei3; [511:448] Engine instruction word 1. Passed to the AE/SE.
+ *
+ */
+union otx2_cpt_inst_s {
+	u64 u[8];
+
+	struct {
+		/* Word 0 */
+		u64 nixtxl:3;
+		u64 doneint:1;
+		u64 nixtx_addr:60;
+		/* Word 1 */
+		u64 res_addr;
+		/* Word 2 */
+		u64 tag:32;
+		u64 tt:2;
+		u64 grp:10;
+		u64 reserved_172_175:4;
+		u64 rvu_pf_func:16;
+		/* Word 3 */
+		u64 qord:1;
+		u64 reserved_194_193:2;
+		u64 wq_ptr:61;
+		/* Word 4 */
+		u64 ei0;
+		/* Word 5 */
+		u64 ei1;
+		/* Word 6 */
+		u64 ei2;
+		/* Word 7 */
+		u64 ei3;
+	} s;
+};
+
+/*
+ * Structure otx2_cpt_res_s
+ *
+ * CPT Result Structure
+ * The CPT coprocessor writes the result structure after it completes a
+ * CPT_INST_S instruction. The result structure is exactly 16 bytes, and
+ * each instruction completion produces exactly one result structure.
+ *
+ * This structure is stored in memory as little-endian unless
+ * CPT()_PF_Q()_CTL[INST_BE] is set.
+ * cpt_res_s_s
+ * Word 0
+ *  doneint:1 [16:16] Done interrupt. This bit is copied from the
+ *	corresponding instruction's CPT_INST_S[DONEINT].
+ *  compcode:8 [7:0] Indicates completion/error status of the CPT coprocessor
+ *	for the	associated instruction, as enumerated by CPT_COMP_E.
+ *	Core software may write the memory location containing [COMPCODE] to
+ *	0x0 before ringing the doorbell, and then poll for completion by
+ *	checking for a nonzero value.
+ *	Once the core observes a nonzero [COMPCODE] value in this case,the CPT
+ *	coprocessor will have also completed L2/DRAM write operations.
+ * Word 1
+ *  reserved
+ *
+ */
+union otx2_cpt_res_s {
+	u64 u[2];
+
+	struct {
+		u64 compcode:8;
+		u64 uc_compcode:8;
+		u64 doneint:1;
+		u64 reserved_17_63:47;
+		u64 reserved_64_127;
+	} s;
+};
+
+/*
+ * Register (RVU_PF_BAR0) cpt#_af_constants1
+ *
+ * CPT AF Constants Register
+ * This register contains implementation-related parameters of CPT.
+ */
+union otx2_cptx_af_constants1 {
+	u64 u;
+	struct otx2_cptx_af_constants1_s {
+		u64 se:16;
+		u64 ie:16;
+		u64 ae:16;
+		u64 reserved_48_63:16;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_misc_int
+ *
+ * This register contain the per-queue miscellaneous interrupts.
+ *
+ */
+union otx2_cptx_lf_misc_int {
+	u64 u;
+	struct otx2_cptx_lf_misc_int_s {
+		u64 reserved_0:1;
+		u64 nqerr:1;
+		u64 irde:1;
+		u64 nwrp:1;
+		u64 reserved_4:1;
+		u64 hwerr:1;
+		u64 fault:1;
+		u64 reserved_7_63:57;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_misc_int_ena_w1s
+ *
+ * This register sets interrupt enable bits.
+ *
+ */
+union otx2_cptx_lf_misc_int_ena_w1s {
+	u64 u;
+	struct otx2_cptx_lf_misc_int_ena_w1s_s {
+		u64 reserved_0:1;
+		u64 nqerr:1;
+		u64 irde:1;
+		u64 nwrp:1;
+		u64 reserved_4:1;
+		u64 hwerr:1;
+		u64 fault:1;
+		u64 reserved_7_63:57;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_ctl
+ *
+ * This register configures the queue.
+ *
+ * When the queue is not execution-quiescent (see CPT_LF_INPROG[EENA,INFLIGHT]),
+ * software must only write this register with [ENA]=0.
+ */
+union otx2_cptx_lf_ctl {
+	u64 u;
+	struct otx2_cptx_lf_ctl_s {
+		u64 ena:1;
+		u64 fc_ena:1;
+		u64 fc_up_crossing:1;
+		u64 reserved_3:1;
+		u64 fc_hyst_bits:4;
+		u64 reserved_8_63:56;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_done_wait
+ *
+ * This register specifies the per-queue interrupt coalescing settings.
+ */
+union otx2_cptx_lf_done_wait {
+	u64 u;
+	struct otx2_cptx_lf_done_wait_s {
+		u64 num_wait:20;
+		u64 reserved_20_31:12;
+		u64 time_wait:16;
+		u64 reserved_48_63:16;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_done
+ *
+ * This register contain the per-queue instruction done count.
+ */
+union otx2_cptx_lf_done {
+	u64 u;
+	struct otx2_cptx_lf_done_s {
+		u64 done:20;
+		u64 reserved_20_63:44;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_inprog
+ *
+ * These registers contain the per-queue instruction in flight registers.
+ *
+ */
+union otx2_cptx_lf_inprog {
+	u64 u;
+	struct otx2_cptx_lf_inprog_s {
+		u64 inflight:9;
+		u64 reserved_9_15:7;
+		u64 eena:1;
+		u64 grp_drp:1;
+		u64 reserved_18_30:13;
+		u64 grb_partial:1;
+		u64 grb_cnt:8;
+		u64 gwb_cnt:8;
+		u64 reserved_48_63:16;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_q_base
+ *
+ * CPT initializes these CSR fields to these values on any CPT_LF_Q_BASE write:
+ * _ CPT_LF_Q_INST_PTR[XQ_XOR]=0.
+ * _ CPT_LF_Q_INST_PTR[NQ_PTR]=2.
+ * _ CPT_LF_Q_INST_PTR[DQ_PTR]=2.
+ * _ CPT_LF_Q_GRP_PTR[XQ_XOR]=0.
+ * _ CPT_LF_Q_GRP_PTR[NQ_PTR]=1.
+ * _ CPT_LF_Q_GRP_PTR[DQ_PTR]=1.
+ */
+union otx2_cptx_lf_q_base {
+	u64 u;
+	struct otx2_cptx_lf_q_base_s {
+		u64 fault:1;
+		u64 reserved_1_6:6;
+		u64 addr:46;
+		u64 reserved_53_63:11;
+	} s;
+};
+
+/*
+ * RVU_PFVF_BAR2 - cpt_lf_q_size
+ *
+ * CPT initializes these CSR fields to these values on any CPT_LF_Q_SIZE write:
+ * _ CPT_LF_Q_INST_PTR[XQ_XOR]=0.
+ * _ CPT_LF_Q_INST_PTR[NQ_PTR]=2.
+ * _ CPT_LF_Q_INST_PTR[DQ_PTR]=2.
+ * _ CPT_LF_Q_GRP_PTR[XQ_XOR]=0.
+ * _ CPT_LF_Q_GRP_PTR[NQ_PTR]=1.
+ * _ CPT_LF_Q_GRP_PTR[DQ_PTR]=1.
+ */
+union otx2_cptx_lf_q_size {
+	u64 u;
+	struct otx2_cptx_lf_q_size_s {
+		u64 size_div40:15;
+		u64 reserved_15_63:49;
+	} s;
+};
+
+/*
+ * RVU_PF_BAR0 - cpt_af_lf_ctl
+ *
+ * This register configures queues. This register should be written only
+ * when the queue is execution-quiescent (see CPT_LF_INPROG[INFLIGHT]).
+ */
+union otx2_cptx_af_lf_ctrl {
+	u64 u;
+	struct otx2_cptx_af_lf_ctrl_s {
+		u64 pri:1;
+		u64 reserved_1_8:8;
+		u64 pf_func_inst:1;
+		u64 cont_err:1;
+		u64 reserved_11_15:5;
+		u64 nixtx_en:1;
+		u64 reserved_17_47:31;
+		u64 grp:8;
+		u64 reserved_56_63:8;
+	} s;
+};
+
+#endif /* __OTX2_CPT_HW_TYPES_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c
new file mode 100644
index 000000000000..51cb6404ded7
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptlf.h"
+
+int otx2_cpt_send_mbox_msg(struct otx2_mbox *mbox, struct pci_dev *pdev)
+{
+	int ret;
+
+	otx2_mbox_msg_send(mbox, 0);
+	ret = otx2_mbox_wait_for_rsp(mbox, 0);
+	if (ret == -EIO) {
+		dev_err(&pdev->dev, "RVU MBOX timeout.\n");
+		return ret;
+	} else if (ret) {
+		dev_err(&pdev->dev, "RVU MBOX error: %d.\n", ret);
+		return -EFAULT;
+	}
+	return ret;
+}
+
+int otx2_cpt_send_ready_msg(struct otx2_mbox *mbox, struct pci_dev *pdev)
+{
+	struct mbox_msghdr *req;
+
+	req = otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct ready_msg_rsp));
+	if (req == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+	req->id = MBOX_MSG_READY;
+	req->sig = OTX2_MBOX_REQ_SIG;
+	req->pcifunc = 0;
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+
+int otx2_cpt_send_af_reg_requests(struct otx2_mbox *mbox, struct pci_dev *pdev)
+{
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+
+int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			     u64 reg, u64 *val)
+{
+	struct cpt_rd_wr_reg_msg *reg_msg;
+
+	reg_msg = (struct cpt_rd_wr_reg_msg *)
+			otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*reg_msg),
+						sizeof(*reg_msg));
+	if (reg_msg == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	reg_msg->hdr.id = MBOX_MSG_CPT_RD_WR_REGISTER;
+	reg_msg->hdr.sig = OTX2_MBOX_REQ_SIG;
+	reg_msg->hdr.pcifunc = 0;
+
+	reg_msg->is_write = 0;
+	reg_msg->reg_offset = reg;
+	reg_msg->ret_val = val;
+
+	return 0;
+}
+
+int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			      u64 reg, u64 val)
+{
+	struct cpt_rd_wr_reg_msg *reg_msg;
+
+	reg_msg = (struct cpt_rd_wr_reg_msg *)
+			otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*reg_msg),
+						sizeof(*reg_msg));
+	if (reg_msg == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	reg_msg->hdr.id = MBOX_MSG_CPT_RD_WR_REGISTER;
+	reg_msg->hdr.sig = OTX2_MBOX_REQ_SIG;
+	reg_msg->hdr.pcifunc = 0;
+
+	reg_msg->is_write = 1;
+	reg_msg->reg_offset = reg;
+	reg_msg->val = val;
+
+	return 0;
+}
+
+int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			 u64 reg, u64 *val)
+{
+	int ret;
+
+	ret = otx2_cpt_add_read_af_reg(mbox, pdev, reg, val);
+	if (ret)
+		return ret;
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+
+int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+			  u64 reg, u64 val)
+{
+	int ret;
+
+	ret = otx2_cpt_add_write_af_reg(mbox, pdev, reg, val);
+	if (ret)
+		return ret;
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+
+int otx2_cpt_attach_rscrs_msg(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_mbox *mbox = lfs->mbox;
+	struct rsrc_attach *req;
+	int ret;
+
+	req = (struct rsrc_attach *)
+			otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+						sizeof(struct msg_rsp));
+	if (req == NULL) {
+		dev_err(&lfs->pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	req->hdr.id = MBOX_MSG_ATTACH_RESOURCES;
+	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = 0;
+	req->cptlfs = lfs->lfs_num;
+	ret = otx2_cpt_send_mbox_msg(mbox, lfs->pdev);
+	if (ret)
+		return ret;
+
+	if (!lfs->are_lfs_attached)
+		ret = -EINVAL;
+
+	return ret;
+}
+
+int otx2_cpt_detach_rsrcs_msg(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_mbox *mbox = lfs->mbox;
+	struct rsrc_detach *req;
+	int ret;
+
+	req = (struct rsrc_detach *)
+				otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+							sizeof(struct msg_rsp));
+	if (req == NULL) {
+		dev_err(&lfs->pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	req->hdr.id = MBOX_MSG_DETACH_RESOURCES;
+	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = 0;
+	ret = otx2_cpt_send_mbox_msg(mbox, lfs->pdev);
+	if (ret)
+		return ret;
+
+	if (lfs->are_lfs_attached)
+		ret = -EINVAL;
+
+	return ret;
+}
+
+int otx2_cpt_msix_offset_msg(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_mbox *mbox = lfs->mbox;
+	struct pci_dev *pdev = lfs->pdev;
+	struct mbox_msghdr *req;
+	int ret, i;
+
+	req = otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct msix_offset_rsp));
+	if (req == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+
+	req->id = MBOX_MSG_MSIX_OFFSET;
+	req->sig = OTX2_MBOX_REQ_SIG;
+	req->pcifunc = 0;
+	ret = otx2_cpt_send_mbox_msg(mbox, pdev);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		if (lfs->lf[i].msix_offset == MSIX_VECTOR_INVALID) {
+			dev_err(&pdev->dev,
+				"Invalid msix offset %d for LF %d\n",
+				lfs->lf[i].msix_offset, i);
+			return -EINVAL;
+		}
+	}
+	return ret;
+}
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h
new file mode 100644
index 000000000000..dbb1ee746f4c
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_reqmgr.h
@@ -0,0 +1,197 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPT_REQMGR_H
+#define __OTX2_CPT_REQMGR_H
+
+#include "otx2_cpt_common.h"
+
+/* Completion code size and initial value */
+#define OTX2_CPT_COMPLETION_CODE_SIZE 8
+#define OTX2_CPT_COMPLETION_CODE_INIT OTX2_CPT_COMP_E_NOTDONE
+/*
+ * Maximum total number of SG buffers is 100, we divide it equally
+ * between input and output
+ */
+#define OTX2_CPT_MAX_SG_IN_CNT  50
+#define OTX2_CPT_MAX_SG_OUT_CNT 50
+
+/* DMA mode direct or SG */
+#define OTX2_CPT_DMA_MODE_DIRECT 0
+#define OTX2_CPT_DMA_MODE_SG     1
+
+/* Context source CPTR or DPTR */
+#define OTX2_CPT_FROM_CPTR 0
+#define OTX2_CPT_FROM_DPTR 1
+
+#define OTX2_CPT_MAX_REQ_SIZE 65535
+
+union otx2_cpt_opcode {
+	u16 flags;
+	struct {
+		u8 major;
+		u8 minor;
+	} s;
+};
+
+struct otx2_cptvf_request {
+	u32 param1;
+	u32 param2;
+	u16 dlen;
+	union otx2_cpt_opcode opcode;
+};
+
+/*
+ * CPT_INST_S software command definitions
+ * Words EI (0-3)
+ */
+union otx2_cpt_iq_cmd_word0 {
+	u64 u;
+	struct {
+		__be16 opcode;
+		__be16 param1;
+		__be16 param2;
+		__be16 dlen;
+	} s;
+};
+
+union otx2_cpt_iq_cmd_word3 {
+	u64 u;
+	struct {
+		u64 cptr:61;
+		u64 grp:3;
+	} s;
+};
+
+struct otx2_cpt_iq_command {
+	union otx2_cpt_iq_cmd_word0 cmd;
+	u64 dptr;
+	u64 rptr;
+	union otx2_cpt_iq_cmd_word3 cptr;
+};
+
+struct otx2_cpt_pending_entry {
+	void *completion_addr;	/* Completion address */
+	void *info;
+	/* Kernel async request callback */
+	void (*callback)(int status, void *arg1, void *arg2);
+	struct crypto_async_request *areq; /* Async request callback arg */
+	u8 resume_sender;	/* Notify sender to resume sending requests */
+	u8 busy;		/* Entry status (free/busy) */
+};
+
+struct otx2_cpt_pending_queue {
+	struct otx2_cpt_pending_entry *head; /* Head of the queue */
+	u32 front;		/* Process work from here */
+	u32 rear;		/* Append new work here */
+	u32 pending_count;	/* Pending requests count */
+	u32 qlen;		/* Queue length */
+	spinlock_t lock;	/* Queue lock */
+};
+
+struct otx2_cpt_buf_ptr {
+	u8 *vptr;
+	dma_addr_t dma_addr;
+	u16 size;
+};
+
+union otx2_cpt_ctrl_info {
+	u32 flags;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u32 reserved_6_31:26;
+		u32 grp:3;	/* Group bits */
+		u32 dma_mode:2;	/* DMA mode */
+		u32 se_req:1;	/* To SE core */
+#else
+		u32 se_req:1;	/* To SE core */
+		u32 dma_mode:2;	/* DMA mode */
+		u32 grp:3;	/* Group bits */
+		u32 reserved_6_31:26;
+#endif
+	} s;
+};
+
+struct otx2_cpt_req_info {
+	/* Kernel async request callback */
+	void (*callback)(int status, void *arg1, void *arg2);
+	struct crypto_async_request *areq; /* Async request callback arg */
+	struct otx2_cptvf_request req;/* Request information (core specific) */
+	union otx2_cpt_ctrl_info ctrl;/* User control information */
+	struct otx2_cpt_buf_ptr in[OTX2_CPT_MAX_SG_IN_CNT];
+	struct otx2_cpt_buf_ptr out[OTX2_CPT_MAX_SG_OUT_CNT];
+	u8 *iv_out;     /* IV to send back */
+	u16 rlen;	/* Output length */
+	u8 in_cnt;	/* Number of input buffers */
+	u8 out_cnt;	/* Number of output buffers */
+	u8 req_type;	/* Type of request */
+	u8 is_enc;	/* Is a request an encryption request */
+	u8 is_trunc_hmac;/* Is truncated hmac used */
+};
+
+struct otx2_cpt_inst_info {
+	struct otx2_cpt_pending_entry *pentry;
+	struct otx2_cpt_req_info *req;
+	struct pci_dev *pdev;
+	void *completion_addr;
+	u8 *out_buffer;
+	u8 *in_buffer;
+	dma_addr_t dptr_baddr;
+	dma_addr_t rptr_baddr;
+	dma_addr_t comp_baddr;
+	unsigned long time_in;
+	u32 dlen;
+	u32 dma_len;
+	u8 extra_time;
+};
+
+struct otx2_cpt_sglist_component {
+	__be16 len0;
+	__be16 len1;
+	__be16 len2;
+	__be16 len3;
+	__be64 ptr0;
+	__be64 ptr1;
+	__be64 ptr2;
+	__be64 ptr3;
+};
+
+static inline void otx2_cpt_info_destroy(struct pci_dev *pdev,
+					 struct otx2_cpt_inst_info *info)
+{
+	struct otx2_cpt_req_info *req;
+	int i;
+
+	if (info->dptr_baddr)
+		dma_unmap_single(&pdev->dev, info->dptr_baddr,
+				 info->dma_len, DMA_BIDIRECTIONAL);
+
+	if (info->req) {
+		req = info->req;
+		for (i = 0; i < req->out_cnt; i++) {
+			if (req->out[i].dma_addr)
+				dma_unmap_single(&pdev->dev,
+						 req->out[i].dma_addr,
+						 req->out[i].size,
+						 DMA_BIDIRECTIONAL);
+		}
+
+		for (i = 0; i < req->in_cnt; i++) {
+			if (req->in[i].dma_addr)
+				dma_unmap_single(&pdev->dev,
+						 req->in[i].dma_addr,
+						 req->in[i].size,
+						 DMA_BIDIRECTIONAL);
+		}
+	}
+	kfree(info);
+}
+
+struct otx2_cptlf_wqe;
+int otx2_cpt_do_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+			int cpu_num);
+void otx2_cpt_post_process(struct otx2_cptlf_wqe *wqe);
+int otx2_cpt_get_kcrypto_eng_grp_num(struct pci_dev *pdev);
+
+#endif /* __OTX2_CPT_REQMGR_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c
new file mode 100644
index 000000000000..823a4571fd67
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c
@@ -0,0 +1,428 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptlf.h"
+#include "rvu_reg.h"
+
+#define CPT_TIMER_HOLD 0x03F
+#define CPT_COUNT_HOLD 32
+
+static void cptlf_do_set_done_time_wait(struct otx2_cptlf_info *lf,
+					int time_wait)
+{
+	union otx2_cptx_lf_done_wait done_wait;
+
+	done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				      OTX2_CPT_LF_DONE_WAIT);
+	done_wait.s.time_wait = time_wait;
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_DONE_WAIT, done_wait.u);
+}
+
+static void cptlf_do_set_done_num_wait(struct otx2_cptlf_info *lf, int num_wait)
+{
+	union otx2_cptx_lf_done_wait done_wait;
+
+	done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				      OTX2_CPT_LF_DONE_WAIT);
+	done_wait.s.num_wait = num_wait;
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_DONE_WAIT, done_wait.u);
+}
+
+static void cptlf_set_done_time_wait(struct otx2_cptlfs_info *lfs,
+				     int time_wait)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		cptlf_do_set_done_time_wait(&lfs->lf[slot], time_wait);
+}
+
+static void cptlf_set_done_num_wait(struct otx2_cptlfs_info *lfs, int num_wait)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		cptlf_do_set_done_num_wait(&lfs->lf[slot], num_wait);
+}
+
+static int cptlf_set_pri(struct otx2_cptlf_info *lf, int pri)
+{
+	struct otx2_cptlfs_info *lfs = lf->lfs;
+	union otx2_cptx_af_lf_ctrl lf_ctrl;
+	int ret;
+
+	ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev,
+				   CPT_AF_LFX_CTL(lf->slot),
+				   &lf_ctrl.u);
+	if (ret)
+		return ret;
+
+	lf_ctrl.s.pri = pri ? 1 : 0;
+
+	ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev,
+				    CPT_AF_LFX_CTL(lf->slot),
+				    lf_ctrl.u);
+	return ret;
+}
+
+static int cptlf_set_eng_grps_mask(struct otx2_cptlf_info *lf,
+				   int eng_grps_mask)
+{
+	struct otx2_cptlfs_info *lfs = lf->lfs;
+	union otx2_cptx_af_lf_ctrl lf_ctrl;
+	int ret;
+
+	ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev,
+				   CPT_AF_LFX_CTL(lf->slot),
+				   &lf_ctrl.u);
+	if (ret)
+		return ret;
+
+	lf_ctrl.s.grp = eng_grps_mask;
+
+	ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev,
+				    CPT_AF_LFX_CTL(lf->slot),
+				    lf_ctrl.u);
+	return ret;
+}
+
+static int cptlf_set_grp_and_pri(struct otx2_cptlfs_info *lfs,
+				 int eng_grp_mask, int pri)
+{
+	int slot, ret = 0;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		ret = cptlf_set_pri(&lfs->lf[slot], pri);
+		if (ret)
+			return ret;
+
+		ret = cptlf_set_eng_grps_mask(&lfs->lf[slot], eng_grp_mask);
+		if (ret)
+			return ret;
+	}
+	return ret;
+}
+
+static void cptlf_hw_init(struct otx2_cptlfs_info *lfs)
+{
+	/* Disable instruction queues */
+	otx2_cptlf_disable_iqueues(lfs);
+
+	/* Set instruction queues base addresses */
+	otx2_cptlf_set_iqueues_base_addr(lfs);
+
+	/* Set instruction queues sizes */
+	otx2_cptlf_set_iqueues_size(lfs);
+
+	/* Set done interrupts time wait */
+	cptlf_set_done_time_wait(lfs, CPT_TIMER_HOLD);
+
+	/* Set done interrupts num wait */
+	cptlf_set_done_num_wait(lfs, CPT_COUNT_HOLD);
+
+	/* Enable instruction queues */
+	otx2_cptlf_enable_iqueues(lfs);
+}
+
+static void cptlf_hw_cleanup(struct otx2_cptlfs_info *lfs)
+{
+	/* Disable instruction queues */
+	otx2_cptlf_disable_iqueues(lfs);
+}
+
+static void cptlf_set_misc_intrs(struct otx2_cptlfs_info *lfs, u8 enable)
+{
+	union otx2_cptx_lf_misc_int_ena_w1s irq_misc = { .u = 0x0 };
+	u64 reg = enable ? OTX2_CPT_LF_MISC_INT_ENA_W1S :
+			   OTX2_CPT_LF_MISC_INT_ENA_W1C;
+	int slot;
+
+	irq_misc.s.fault = 0x1;
+	irq_misc.s.hwerr = 0x1;
+	irq_misc.s.irde = 0x1;
+	irq_misc.s.nqerr = 0x1;
+	irq_misc.s.nwrp = 0x1;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot, reg,
+				 irq_misc.u);
+}
+
+static void cptlf_enable_intrs(struct otx2_cptlfs_info *lfs)
+{
+	int slot;
+
+	/* Enable done interrupts */
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot,
+				 OTX2_CPT_LF_DONE_INT_ENA_W1S, 0x1);
+	/* Enable Misc interrupts */
+	cptlf_set_misc_intrs(lfs, true);
+}
+
+static void cptlf_disable_intrs(struct otx2_cptlfs_info *lfs)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot,
+				 OTX2_CPT_LF_DONE_INT_ENA_W1C, 0x1);
+	cptlf_set_misc_intrs(lfs, false);
+}
+
+static inline int cptlf_read_done_cnt(struct otx2_cptlf_info *lf)
+{
+	union otx2_cptx_lf_done irq_cnt;
+
+	irq_cnt.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				    OTX2_CPT_LF_DONE);
+	return irq_cnt.s.done;
+}
+
+static irqreturn_t cptlf_misc_intr_handler(int __always_unused irq, void *arg)
+{
+	union otx2_cptx_lf_misc_int irq_misc, irq_misc_ack;
+	struct otx2_cptlf_info *lf = arg;
+	struct device *dev;
+
+	dev = &lf->lfs->pdev->dev;
+	irq_misc.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				     OTX2_CPT_LF_MISC_INT);
+	irq_misc_ack.u = 0x0;
+
+	if (irq_misc.s.fault) {
+		dev_err(dev, "Memory error detected while executing CPT_INST_S, LF %d.\n",
+			lf->slot);
+		irq_misc_ack.s.fault = 0x1;
+
+	} else if (irq_misc.s.hwerr) {
+		dev_err(dev, "HW error from an engine executing CPT_INST_S, LF %d.",
+			lf->slot);
+		irq_misc_ack.s.hwerr = 0x1;
+
+	} else if (irq_misc.s.nwrp) {
+		dev_err(dev, "SMMU fault while writing CPT_RES_S to CPT_INST_S[RES_ADDR], LF %d.\n",
+			lf->slot);
+		irq_misc_ack.s.nwrp = 0x1;
+
+	} else if (irq_misc.s.irde) {
+		dev_err(dev, "Memory error when accessing instruction memory queue CPT_LF_Q_BASE[ADDR].\n");
+		irq_misc_ack.s.irde = 0x1;
+
+	} else if (irq_misc.s.nqerr) {
+		dev_err(dev, "Error enqueuing an instruction received at CPT_LF_NQ.\n");
+		irq_misc_ack.s.nqerr = 0x1;
+
+	} else {
+		dev_err(dev, "Unhandled interrupt in CPT LF %d\n", lf->slot);
+		return IRQ_NONE;
+	}
+
+	/* Acknowledge interrupts */
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_MISC_INT, irq_misc_ack.u);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t cptlf_done_intr_handler(int irq, void *arg)
+{
+	union otx2_cptx_lf_done_wait done_wait;
+	struct otx2_cptlf_info *lf = arg;
+	int irq_cnt;
+
+	/* Read the number of completed requests */
+	irq_cnt = cptlf_read_done_cnt(lf);
+	if (irq_cnt) {
+		done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0,
+					      lf->slot, OTX2_CPT_LF_DONE_WAIT);
+		/* Acknowledge the number of completed requests */
+		otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				 OTX2_CPT_LF_DONE_ACK, irq_cnt);
+
+		otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				 OTX2_CPT_LF_DONE_WAIT, done_wait.u);
+		if (unlikely(!lf->wqe)) {
+			dev_err(&lf->lfs->pdev->dev, "No work for LF %d\n",
+				lf->slot);
+			return IRQ_NONE;
+		}
+
+		/* Schedule processing of completed requests */
+		tasklet_hi_schedule(&lf->wqe->work);
+	}
+	return IRQ_HANDLED;
+}
+
+void otx2_cptlf_unregister_interrupts(struct otx2_cptlfs_info *lfs)
+{
+	int i, offs, vector;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++) {
+			if (!lfs->lf[i].is_irq_reg[offs])
+				continue;
+
+			vector = pci_irq_vector(lfs->pdev,
+						lfs->lf[i].msix_offset + offs);
+			free_irq(vector, &lfs->lf[i]);
+			lfs->lf[i].is_irq_reg[offs] = false;
+		}
+	}
+	cptlf_disable_intrs(lfs);
+}
+
+static int cptlf_do_register_interrrupts(struct otx2_cptlfs_info *lfs,
+					 int lf_num, int irq_offset,
+					 irq_handler_t handler)
+{
+	int ret, vector;
+
+	vector = pci_irq_vector(lfs->pdev, lfs->lf[lf_num].msix_offset +
+				irq_offset);
+	ret = request_irq(vector, handler, 0,
+			  lfs->lf[lf_num].irq_name[irq_offset],
+			  &lfs->lf[lf_num]);
+	if (ret)
+		return ret;
+
+	lfs->lf[lf_num].is_irq_reg[irq_offset] = true;
+
+	return ret;
+}
+
+int otx2_cptlf_register_interrupts(struct otx2_cptlfs_info *lfs)
+{
+	int irq_offs, ret, i;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		irq_offs = OTX2_CPT_LF_INT_VEC_E_MISC;
+		snprintf(lfs->lf[i].irq_name[irq_offs], 32, "CPTLF Misc%d", i);
+		ret = cptlf_do_register_interrrupts(lfs, i, irq_offs,
+						    cptlf_misc_intr_handler);
+		if (ret)
+			goto free_irq;
+
+		irq_offs = OTX2_CPT_LF_INT_VEC_E_DONE;
+		snprintf(lfs->lf[i].irq_name[irq_offs], 32, "OTX2_CPTLF Done%d",
+			 i);
+		ret = cptlf_do_register_interrrupts(lfs, i, irq_offs,
+						    cptlf_done_intr_handler);
+		if (ret)
+			goto free_irq;
+	}
+	cptlf_enable_intrs(lfs);
+	return 0;
+
+free_irq:
+	otx2_cptlf_unregister_interrupts(lfs);
+	return ret;
+}
+
+void otx2_cptlf_free_irqs_affinity(struct otx2_cptlfs_info *lfs)
+{
+	int slot, offs;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++)
+			irq_set_affinity_hint(pci_irq_vector(lfs->pdev,
+					      lfs->lf[slot].msix_offset +
+					      offs), NULL);
+		free_cpumask_var(lfs->lf[slot].affinity_mask);
+	}
+}
+
+int otx2_cptlf_set_irqs_affinity(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_cptlf_info *lf = lfs->lf;
+	int slot, offs, ret;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		if (!zalloc_cpumask_var(&lf[slot].affinity_mask, GFP_KERNEL)) {
+			dev_err(&lfs->pdev->dev,
+				"cpumask allocation failed for LF %d", slot);
+			ret = -ENOMEM;
+			goto free_affinity_mask;
+		}
+
+		cpumask_set_cpu(cpumask_local_spread(slot,
+				dev_to_node(&lfs->pdev->dev)),
+				lf[slot].affinity_mask);
+
+		for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++) {
+			ret = irq_set_affinity_hint(pci_irq_vector(lfs->pdev,
+						lf[slot].msix_offset + offs),
+						lf[slot].affinity_mask);
+			if (ret)
+				goto free_affinity_mask;
+		}
+	}
+	return 0;
+
+free_affinity_mask:
+	otx2_cptlf_free_irqs_affinity(lfs);
+	return ret;
+}
+
+int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_mask, int pri,
+		    int lfs_num)
+{
+	int slot, ret;
+
+	if (!lfs->pdev || !lfs->reg_base)
+		return -EINVAL;
+
+	lfs->lfs_num = lfs_num;
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		lfs->lf[slot].lfs = lfs;
+		lfs->lf[slot].slot = slot;
+		lfs->lf[slot].lmtline = lfs->reg_base +
+			OTX2_CPT_RVU_FUNC_ADDR_S(BLKADDR_LMT, slot,
+						 OTX2_CPT_LMT_LF_LMTLINEX(0));
+		lfs->lf[slot].ioreg = lfs->reg_base +
+			OTX2_CPT_RVU_FUNC_ADDR_S(BLKADDR_CPT0, slot,
+						 OTX2_CPT_LF_NQX(0));
+	}
+	/* Send request to attach LFs */
+	ret = otx2_cpt_attach_rscrs_msg(lfs);
+	if (ret)
+		goto clear_lfs_num;
+
+	ret = otx2_cpt_alloc_instruction_queues(lfs);
+	if (ret) {
+		dev_err(&lfs->pdev->dev,
+			"Allocating instruction queues failed\n");
+		goto detach_rsrcs;
+	}
+	cptlf_hw_init(lfs);
+	/*
+	 * Allow each LF to execute requests destined to any of 8 engine
+	 * groups and set queue priority of each LF to high
+	 */
+	ret = cptlf_set_grp_and_pri(lfs, eng_grp_mask, pri);
+	if (ret)
+		goto free_iq;
+
+	return 0;
+
+free_iq:
+	otx2_cpt_free_instruction_queues(lfs);
+	cptlf_hw_cleanup(lfs);
+detach_rsrcs:
+	otx2_cpt_detach_rsrcs_msg(lfs);
+clear_lfs_num:
+	lfs->lfs_num = 0;
+	return ret;
+}
+
+void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs)
+{
+	lfs->lfs_num = 0;
+	/* Cleanup LFs hardware side */
+	cptlf_hw_cleanup(lfs);
+	/* Send request to detach LFs */
+	otx2_cpt_detach_rsrcs_msg(lfs);
+}
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.h b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h
new file mode 100644
index 000000000000..314e97354100
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h
@@ -0,0 +1,353 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+#ifndef __OTX2_CPTLF_H
+#define __OTX2_CPTLF_H
+
+#include <linux/soc/marvell/octeontx2/asm.h>
+#include <mbox.h>
+#include <rvu.h>
+#include "otx2_cpt_common.h"
+#include "otx2_cpt_reqmgr.h"
+
+/*
+ * CPT instruction and pending queues user requested length in CPT_INST_S msgs
+ */
+#define OTX2_CPT_USER_REQUESTED_QLEN_MSGS 8200
+
+/*
+ * CPT instruction queue size passed to HW is in units of 40*CPT_INST_S
+ * messages.
+ */
+#define OTX2_CPT_SIZE_DIV40 (OTX2_CPT_USER_REQUESTED_QLEN_MSGS/40)
+
+/*
+ * CPT instruction and pending queues length in CPT_INST_S messages
+ */
+#define OTX2_CPT_INST_QLEN_MSGS	((OTX2_CPT_SIZE_DIV40 - 1) * 40)
+
+/* CPT instruction queue length in bytes */
+#define OTX2_CPT_INST_QLEN_BYTES (OTX2_CPT_SIZE_DIV40 * 40 * \
+				  OTX2_CPT_INST_SIZE)
+
+/* CPT instruction group queue length in bytes */
+#define OTX2_CPT_INST_GRP_QLEN_BYTES (OTX2_CPT_SIZE_DIV40 * 16)
+
+/* CPT FC length in bytes */
+#define OTX2_CPT_Q_FC_LEN 128
+
+/* CPT instruction queue alignment */
+#define OTX2_CPT_INST_Q_ALIGNMENT  128
+
+/* Mask which selects all engine groups */
+#define OTX2_CPT_ALL_ENG_GRPS_MASK 0xFF
+
+/* Maximum LFs supported in OcteonTX2 for CPT */
+#define OTX2_CPT_MAX_LFS_NUM    64
+
+/* Queue priority */
+#define OTX2_CPT_QUEUE_HI_PRIO  0x1
+#define OTX2_CPT_QUEUE_LOW_PRIO 0x0
+
+enum otx2_cptlf_state {
+	OTX2_CPTLF_IN_RESET,
+	OTX2_CPTLF_STARTED,
+};
+
+struct otx2_cpt_inst_queue {
+	u8 *vaddr;
+	u8 *real_vaddr;
+	dma_addr_t dma_addr;
+	dma_addr_t real_dma_addr;
+	u32 size;
+};
+
+struct otx2_cptlfs_info;
+struct otx2_cptlf_wqe {
+	struct tasklet_struct work;
+	struct otx2_cptlfs_info *lfs;
+	u8 lf_num;
+};
+
+struct otx2_cptlf_info {
+	struct otx2_cptlfs_info *lfs;           /* Ptr to cptlfs_info struct */
+	void __iomem *lmtline;                  /* Address of LMTLINE */
+	void __iomem *ioreg;                    /* LMTLINE send register */
+	int msix_offset;                        /* MSI-X interrupts offset */
+	cpumask_var_t affinity_mask;            /* IRQs affinity mask */
+	u8 irq_name[OTX2_CPT_LF_MSIX_VECTORS][32];/* Interrupts name */
+	u8 is_irq_reg[OTX2_CPT_LF_MSIX_VECTORS];  /* Is interrupt registered */
+	u8 slot;                                /* Slot number of this LF */
+
+	struct otx2_cpt_inst_queue iqueue;/* Instruction queue */
+	struct otx2_cpt_pending_queue pqueue; /* Pending queue */
+	struct otx2_cptlf_wqe *wqe;       /* Tasklet work info */
+};
+
+struct otx2_cptlfs_info {
+	/* Registers start address of VF/PF LFs are attached to */
+	void __iomem *reg_base;
+	struct pci_dev *pdev;   /* Device LFs are attached to */
+	struct otx2_cptlf_info lf[OTX2_CPT_MAX_LFS_NUM];
+	struct otx2_mbox *mbox;
+	u8 are_lfs_attached;	/* Whether CPT LFs are attached */
+	u8 lfs_num;		/* Number of CPT LFs */
+	u8 kcrypto_eng_grp_num;	/* Kernel crypto engine group number */
+	u8 kvf_limits;          /* Kernel crypto limits */
+	atomic_t state;         /* LF's state. started/reset */
+};
+
+static inline void otx2_cpt_free_instruction_queues(
+					struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_cpt_inst_queue *iq;
+	int i;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		iq = &lfs->lf[i].iqueue;
+		if (iq->real_vaddr)
+			dma_free_coherent(&lfs->pdev->dev,
+					  iq->size,
+					  iq->real_vaddr,
+					  iq->real_dma_addr);
+		iq->real_vaddr = NULL;
+		iq->vaddr = NULL;
+	}
+}
+
+static inline int otx2_cpt_alloc_instruction_queues(
+					struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_cpt_inst_queue *iq;
+	int ret = 0, i;
+
+	if (!lfs->lfs_num)
+		return -EINVAL;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		iq = &lfs->lf[i].iqueue;
+		iq->size = OTX2_CPT_INST_QLEN_BYTES +
+			   OTX2_CPT_Q_FC_LEN +
+			   OTX2_CPT_INST_GRP_QLEN_BYTES +
+			   OTX2_CPT_INST_Q_ALIGNMENT;
+		iq->real_vaddr = dma_alloc_coherent(&lfs->pdev->dev, iq->size,
+					&iq->real_dma_addr, GFP_KERNEL);
+		if (!iq->real_vaddr) {
+			ret = -ENOMEM;
+			goto error;
+		}
+		iq->vaddr = iq->real_vaddr + OTX2_CPT_INST_GRP_QLEN_BYTES;
+		iq->dma_addr = iq->real_dma_addr + OTX2_CPT_INST_GRP_QLEN_BYTES;
+
+		/* Align pointers */
+		iq->vaddr = PTR_ALIGN(iq->vaddr, OTX2_CPT_INST_Q_ALIGNMENT);
+		iq->dma_addr = PTR_ALIGN(iq->dma_addr,
+					 OTX2_CPT_INST_Q_ALIGNMENT);
+	}
+	return 0;
+
+error:
+	otx2_cpt_free_instruction_queues(lfs);
+	return ret;
+}
+
+static inline void otx2_cptlf_set_iqueues_base_addr(
+					struct otx2_cptlfs_info *lfs)
+{
+	union otx2_cptx_lf_q_base lf_q_base;
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		lf_q_base.u = lfs->lf[slot].iqueue.dma_addr;
+		otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot,
+				 OTX2_CPT_LF_Q_BASE, lf_q_base.u);
+	}
+}
+
+static inline void otx2_cptlf_do_set_iqueue_size(struct otx2_cptlf_info *lf)
+{
+	union otx2_cptx_lf_q_size lf_q_size = { .u = 0x0 };
+
+	lf_q_size.s.size_div40 = OTX2_CPT_SIZE_DIV40;
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_Q_SIZE, lf_q_size.u);
+}
+
+static inline void otx2_cptlf_set_iqueues_size(struct otx2_cptlfs_info *lfs)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cptlf_do_set_iqueue_size(&lfs->lf[slot]);
+}
+
+static inline void otx2_cptlf_do_disable_iqueue(struct otx2_cptlf_info *lf)
+{
+	union otx2_cptx_lf_ctl lf_ctl = { .u = 0x0 };
+	union otx2_cptx_lf_inprog lf_inprog;
+	int timeout = 20;
+
+	/* Disable instructions enqueuing */
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_CTL, lf_ctl.u);
+
+	/* Wait for instruction queue to become empty */
+	do {
+		lf_inprog.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0,
+					      lf->slot, OTX2_CPT_LF_INPROG);
+		if (!lf_inprog.s.inflight)
+			break;
+
+		usleep_range(10000, 20000);
+		if (timeout-- < 0) {
+			dev_err(&lf->lfs->pdev->dev,
+				"Error LF %d is still busy.\n", lf->slot);
+			break;
+		}
+
+	} while (1);
+
+	/*
+	 * Disable executions in the LF's queue,
+	 * the queue should be empty at this point
+	 */
+	lf_inprog.s.eena = 0x0;
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_INPROG, lf_inprog.u);
+}
+
+static inline void otx2_cptlf_disable_iqueues(struct otx2_cptlfs_info *lfs)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cptlf_do_disable_iqueue(&lfs->lf[slot]);
+}
+
+static inline void otx2_cptlf_set_iqueue_enq(struct otx2_cptlf_info *lf,
+					     bool enable)
+{
+	union otx2_cptx_lf_ctl lf_ctl;
+
+	lf_ctl.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				   OTX2_CPT_LF_CTL);
+
+	/* Set iqueue's enqueuing */
+	lf_ctl.s.ena = enable ? 0x1 : 0x0;
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_CTL, lf_ctl.u);
+}
+
+static inline void otx2_cptlf_enable_iqueue_enq(struct otx2_cptlf_info *lf)
+{
+	otx2_cptlf_set_iqueue_enq(lf, true);
+}
+
+static inline void otx2_cptlf_set_iqueue_exec(struct otx2_cptlf_info *lf,
+					      bool enable)
+{
+	union otx2_cptx_lf_inprog lf_inprog;
+
+	lf_inprog.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				      OTX2_CPT_LF_INPROG);
+
+	/* Set iqueue's execution */
+	lf_inprog.s.eena = enable ? 0x1 : 0x0;
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_INPROG, lf_inprog.u);
+}
+
+static inline void otx2_cptlf_enable_iqueue_exec(struct otx2_cptlf_info *lf)
+{
+	otx2_cptlf_set_iqueue_exec(lf, true);
+}
+
+static inline void otx2_cptlf_disable_iqueue_exec(struct otx2_cptlf_info *lf)
+{
+	otx2_cptlf_set_iqueue_exec(lf, false);
+}
+
+static inline void otx2_cptlf_enable_iqueues(struct otx2_cptlfs_info *lfs)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		otx2_cptlf_enable_iqueue_exec(&lfs->lf[slot]);
+		otx2_cptlf_enable_iqueue_enq(&lfs->lf[slot]);
+	}
+}
+
+static inline void otx2_cpt_fill_inst(union otx2_cpt_inst_s *cptinst,
+				      struct otx2_cpt_iq_command *iq_cmd,
+				      u64 comp_baddr)
+{
+	cptinst->u[0] = 0x0;
+	cptinst->s.doneint = true;
+	cptinst->s.res_addr = comp_baddr;
+	cptinst->u[2] = 0x0;
+	cptinst->u[3] = 0x0;
+	cptinst->s.ei0 = iq_cmd->cmd.u;
+	cptinst->s.ei1 = iq_cmd->dptr;
+	cptinst->s.ei2 = iq_cmd->rptr;
+	cptinst->s.ei3 = iq_cmd->cptr.u;
+}
+
+/*
+ * On OcteonTX2 platform the parameter insts_num is used as a count of
+ * instructions to be enqueued. The valid values for insts_num are:
+ * 1 - 1 CPT instruction will be enqueued during LMTST operation
+ * 2 - 2 CPT instructions will be enqueued during LMTST operation
+ */
+static inline void otx2_cpt_send_cmd(union otx2_cpt_inst_s *cptinst,
+				     u32 insts_num, struct otx2_cptlf_info *lf)
+{
+	void __iomem *lmtline = lf->lmtline;
+	long ret;
+
+	/*
+	 * Make sure memory areas pointed in CPT_INST_S
+	 * are flushed before the instruction is sent to CPT
+	 */
+	dma_wmb();
+
+	do {
+		/* Copy CPT command to LMTLINE */
+		memcpy_toio(lmtline, cptinst, insts_num * OTX2_CPT_INST_SIZE);
+
+		/*
+		 * LDEOR initiates atomic transfer to I/O device
+		 * The following will cause the LMTST to fail (the LDEOR
+		 * returns zero):
+		 * - No stores have been performed to the LMTLINE since it was
+		 * last invalidated.
+		 * - The bytes which have been stored to LMTLINE since it was
+		 * last invalidated form a pattern that is non-contiguous, does
+		 * not start at byte 0, or does not end on a 8-byte boundary.
+		 * (i.e.comprises a formation of other than 1–16 8-byte
+		 * words.)
+		 *
+		 * These rules are designed such that an operating system
+		 * context switch or hypervisor guest switch need have no
+		 * knowledge of the LMTST operations; the switch code does not
+		 * need to store to LMTCANCEL. Also note as LMTLINE data cannot
+		 * be read, there is no information leakage between processes.
+		 */
+		ret = otx2_lmt_flush(lf->ioreg);
+
+	} while (!ret);
+}
+
+static inline bool otx2_cptlf_started(struct otx2_cptlfs_info *lfs)
+{
+	return atomic_read(&lfs->state) == OTX2_CPTLF_STARTED;
+}
+
+int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_msk, int pri,
+		    int lfs_num);
+void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs);
+int otx2_cptlf_register_interrupts(struct otx2_cptlfs_info *lfs);
+void otx2_cptlf_unregister_interrupts(struct otx2_cptlfs_info *lfs);
+void otx2_cptlf_free_irqs_affinity(struct otx2_cptlfs_info *lfs);
+int otx2_cptlf_set_irqs_affinity(struct otx2_cptlfs_info *lfs);
+
+#endif /* __OTX2_CPTLF_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h
new file mode 100644
index 000000000000..8c899ad531a5
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPTPF_H
+#define __OTX2_CPTPF_H
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptpf_ucode.h"
+#include "otx2_cptlf.h"
+
+struct otx2_cptpf_dev;
+struct otx2_cptvf_info {
+	struct otx2_cptpf_dev *cptpf;	/* PF pointer this VF belongs to */
+	struct work_struct vfpf_mbox_work;
+	struct pci_dev *vf_dev;
+	int vf_id;
+	int intr_idx;
+};
+
+struct cptpf_flr_work {
+	struct work_struct work;
+	struct otx2_cptpf_dev *pf;
+};
+
+struct otx2_cptpf_dev {
+	void __iomem *reg_base;		/* CPT PF registers start address */
+	void __iomem *afpf_mbox_base;	/* PF-AF mbox start address */
+	void __iomem *vfpf_mbox_base;   /* VF-PF mbox start address */
+	struct pci_dev *pdev;		/* PCI device handle */
+	struct otx2_cptvf_info vf[OTX2_CPT_MAX_VFS_NUM];
+	struct otx2_cpt_eng_grps eng_grps;/* Engine groups information */
+	struct otx2_cptlfs_info lfs;      /* CPT LFs attached to this PF */
+	/* HW capabilities for each engine type */
+	union otx2_cpt_eng_caps eng_caps[OTX2_CPT_MAX_ENG_TYPES];
+	bool is_eng_caps_discovered;
+
+	/* AF <=> PF mbox */
+	struct otx2_mbox	afpf_mbox;
+	struct work_struct	afpf_mbox_work;
+	struct workqueue_struct *afpf_mbox_wq;
+
+	/* VF <=> PF mbox */
+	struct otx2_mbox	vfpf_mbox;
+	struct workqueue_struct *vfpf_mbox_wq;
+
+	struct workqueue_struct	*flr_wq;
+	struct cptpf_flr_work   *flr_work;
+
+	u8 pf_id;               /* RVU PF number */
+	u8 max_vfs;		/* Maximum number of VFs supported by CPT */
+	u8 enabled_vfs;		/* Number of enabled VFs */
+	u8 kvf_limits;		/* Kernel crypto limits */
+};
+
+irqreturn_t otx2_cptpf_afpf_mbox_intr(int irq, void *arg);
+void otx2_cptpf_afpf_mbox_handler(struct work_struct *work);
+irqreturn_t otx2_cptpf_vfpf_mbox_intr(int irq, void *arg);
+void otx2_cptpf_vfpf_mbox_handler(struct work_struct *work);
+
+#endif /* __OTX2_CPTPF_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c
new file mode 100644
index 000000000000..5277e04badd9
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c
@@ -0,0 +1,713 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include <linux/firmware.h>
+#include "otx2_cpt_hw_types.h"
+#include "otx2_cpt_common.h"
+#include "otx2_cptpf_ucode.h"
+#include "otx2_cptpf.h"
+#include "rvu_reg.h"
+
+#define OTX2_CPT_DRV_NAME    "octeontx2-cpt"
+#define OTX2_CPT_DRV_STRING  "Marvell OcteonTX2 CPT Physical Function Driver"
+
+static void cptpf_enable_vfpf_mbox_intr(struct otx2_cptpf_dev *cptpf,
+					int num_vfs)
+{
+	int ena_bits;
+
+	/* Clear any pending interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INTX(0), ~0x0ULL);
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INTX(1), ~0x0ULL);
+
+	/* Enable VF interrupts for VFs from 0 to 63 */
+	ena_bits = ((num_vfs - 1) % 64);
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INT_ENA_W1SX(0),
+			 GENMASK_ULL(ena_bits, 0));
+
+	if (num_vfs > 64) {
+		/* Enable VF interrupts for VFs from 64 to 127 */
+		ena_bits = num_vfs - 64 - 1;
+		otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+				RVU_PF_VFPF_MBOX_INT_ENA_W1SX(1),
+				GENMASK_ULL(ena_bits, 0));
+	}
+}
+
+static void cptpf_disable_vfpf_mbox_intr(struct otx2_cptpf_dev *cptpf,
+					 int num_vfs)
+{
+	int vector;
+
+	/* Disable VF-PF interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), ~0ULL);
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1), ~0ULL);
+	/* Clear any pending interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFPF_MBOX_INTX(0), ~0ULL);
+
+	vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFPF_MBOX0);
+	free_irq(vector, cptpf);
+
+	if (num_vfs > 64) {
+		otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+				 RVU_PF_VFPF_MBOX_INTX(1), ~0ULL);
+		vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFPF_MBOX1);
+		free_irq(vector, cptpf);
+	}
+}
+
+static void cptpf_enable_vf_flr_intrs(struct otx2_cptpf_dev *cptpf)
+{
+	/* Clear interrupt if any */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFFLR_INTX(0),
+			~0x0ULL);
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFFLR_INTX(1),
+			~0x0ULL);
+
+	/* Enable VF FLR interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFFLR_INT_ENA_W1SX(0), ~0x0ULL);
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFFLR_INT_ENA_W1SX(1), ~0x0ULL);
+}
+
+static void cptpf_disable_vf_flr_intrs(struct otx2_cptpf_dev *cptpf,
+				       int num_vfs)
+{
+	int vector;
+
+	/* Disable VF FLR interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFFLR_INT_ENA_W1CX(0), ~0x0ULL);
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFFLR_INT_ENA_W1CX(1), ~0x0ULL);
+
+	/* Clear interrupt if any */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFFLR_INTX(0),
+			 ~0x0ULL);
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_VFFLR_INTX(1),
+			 ~0x0ULL);
+
+	vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFFLR0);
+	free_irq(vector, cptpf);
+
+	if (num_vfs > 64) {
+		vector = pci_irq_vector(cptpf->pdev, RVU_PF_INT_VEC_VFFLR1);
+		free_irq(vector, cptpf);
+	}
+}
+
+static void cptpf_flr_wq_handler(struct work_struct *work)
+{
+	struct cptpf_flr_work *flr_work;
+	struct otx2_cptpf_dev *pf;
+	struct mbox_msghdr *req;
+	struct otx2_mbox *mbox;
+	int vf, reg = 0;
+
+	flr_work = container_of(work, struct cptpf_flr_work, work);
+	pf = flr_work->pf;
+	mbox = &pf->afpf_mbox;
+
+	vf = flr_work - pf->flr_work;
+
+	req = otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct msg_rsp));
+	if (!req)
+		return;
+
+	req->sig = OTX2_MBOX_REQ_SIG;
+	req->id = MBOX_MSG_VF_FLR;
+	req->pcifunc &= RVU_PFVF_FUNC_MASK;
+	req->pcifunc |= (vf + 1) & RVU_PFVF_FUNC_MASK;
+
+	otx2_cpt_send_mbox_msg(mbox, pf->pdev);
+
+	if (vf >= 64) {
+		reg = 1;
+		vf = vf - 64;
+	}
+	/* Clear transaction pending register */
+	otx2_cpt_write64(pf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFTRPENDX(reg), BIT_ULL(vf));
+	otx2_cpt_write64(pf->reg_base, BLKADDR_RVUM, 0,
+			 RVU_PF_VFFLR_INT_ENA_W1SX(reg), BIT_ULL(vf));
+}
+
+static irqreturn_t cptpf_vf_flr_intr(int __always_unused irq, void *arg)
+{
+	int reg, dev, vf, start_vf, num_reg = 1;
+	struct otx2_cptpf_dev *cptpf = arg;
+	u64 intr;
+
+	if (cptpf->max_vfs > 64)
+		num_reg = 2;
+
+	for (reg = 0; reg < num_reg; reg++) {
+		intr = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0,
+				       RVU_PF_VFFLR_INTX(reg));
+		if (!intr)
+			continue;
+		start_vf = 64 * reg;
+		for (vf = 0; vf < 64; vf++) {
+			if (!(intr & BIT_ULL(vf)))
+				continue;
+			dev = vf + start_vf;
+			queue_work(cptpf->flr_wq, &cptpf->flr_work[dev].work);
+			/* Clear interrupt */
+			otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+					 RVU_PF_VFFLR_INTX(reg), BIT_ULL(vf));
+			/* Disable the interrupt */
+			otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0,
+					 RVU_PF_VFFLR_INT_ENA_W1CX(reg),
+					 BIT_ULL(vf));
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static void cptpf_unregister_vfpf_intr(struct otx2_cptpf_dev *cptpf,
+				       int num_vfs)
+{
+	cptpf_disable_vfpf_mbox_intr(cptpf, num_vfs);
+	cptpf_disable_vf_flr_intrs(cptpf, num_vfs);
+}
+
+static int cptpf_register_vfpf_intr(struct otx2_cptpf_dev *cptpf, int num_vfs)
+{
+	struct pci_dev *pdev = cptpf->pdev;
+	struct device *dev = &pdev->dev;
+	int ret, vector;
+
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX0);
+	/* Register VF-PF mailbox interrupt handler */
+	ret = request_irq(vector, otx2_cptpf_vfpf_mbox_intr, 0, "CPTVFPF Mbox0",
+			  cptpf);
+	if (ret) {
+		dev_err(dev,
+			"IRQ registration failed for PFVF mbox0 irq\n");
+		return ret;
+	}
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFFLR0);
+	/* Register VF FLR interrupt handler */
+	ret = request_irq(vector, cptpf_vf_flr_intr, 0, "CPTPF FLR0", cptpf);
+	if (ret) {
+		dev_err(dev,
+			"IRQ registration failed for VFFLR0 irq\n");
+		goto free_mbox0_irq;
+	}
+	if (num_vfs > 64) {
+		vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX1);
+		ret = request_irq(vector, otx2_cptpf_vfpf_mbox_intr, 0,
+				  "CPTVFPF Mbox1", cptpf);
+		if (ret) {
+			dev_err(dev,
+				"IRQ registration failed for PFVF mbox1 irq\n");
+			goto free_flr0_irq;
+		}
+		vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFFLR1);
+		/* Register VF FLR interrupt handler */
+		ret = request_irq(vector, cptpf_vf_flr_intr, 0, "CPTPF FLR1",
+				  cptpf);
+		if (ret) {
+			dev_err(dev,
+				"IRQ registration failed for VFFLR1 irq\n");
+			goto free_mbox1_irq;
+		}
+	}
+	cptpf_enable_vfpf_mbox_intr(cptpf, num_vfs);
+	cptpf_enable_vf_flr_intrs(cptpf);
+
+	return 0;
+
+free_mbox1_irq:
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX1);
+	free_irq(vector, cptpf);
+free_flr0_irq:
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFFLR0);
+	free_irq(vector, cptpf);
+free_mbox0_irq:
+	vector = pci_irq_vector(pdev, RVU_PF_INT_VEC_VFPF_MBOX0);
+	free_irq(vector, cptpf);
+	return ret;
+}
+
+static void cptpf_flr_wq_destroy(struct otx2_cptpf_dev *pf)
+{
+	if (!pf->flr_wq)
+		return;
+	destroy_workqueue(pf->flr_wq);
+	pf->flr_wq = NULL;
+	kfree(pf->flr_work);
+}
+
+static int cptpf_flr_wq_init(struct otx2_cptpf_dev *cptpf, int num_vfs)
+{
+	int vf;
+
+	cptpf->flr_wq = alloc_ordered_workqueue("cptpf_flr_wq", 0);
+	if (!cptpf->flr_wq)
+		return -ENOMEM;
+
+	cptpf->flr_work = kcalloc(num_vfs, sizeof(struct cptpf_flr_work),
+				  GFP_KERNEL);
+	if (!cptpf->flr_work)
+		goto destroy_wq;
+
+	for (vf = 0; vf < num_vfs; vf++) {
+		cptpf->flr_work[vf].pf = cptpf;
+		INIT_WORK(&cptpf->flr_work[vf].work, cptpf_flr_wq_handler);
+	}
+	return 0;
+
+destroy_wq:
+	destroy_workqueue(cptpf->flr_wq);
+	return -ENOMEM;
+}
+
+static int cptpf_vfpf_mbox_init(struct otx2_cptpf_dev *cptpf, int num_vfs)
+{
+	struct device *dev = &cptpf->pdev->dev;
+	u64 vfpf_mbox_base;
+	int err, i;
+
+	cptpf->vfpf_mbox_wq = alloc_workqueue("cpt_vfpf_mailbox",
+					      WQ_UNBOUND | WQ_HIGHPRI |
+					      WQ_MEM_RECLAIM, 1);
+	if (!cptpf->vfpf_mbox_wq)
+		return -ENOMEM;
+
+	/* Map VF-PF mailbox memory */
+	vfpf_mbox_base = readq(cptpf->reg_base + RVU_PF_VF_BAR4_ADDR);
+	if (!vfpf_mbox_base) {
+		dev_err(dev, "VF-PF mailbox address not configured\n");
+		err = -ENOMEM;
+		goto free_wqe;
+	}
+	cptpf->vfpf_mbox_base = devm_ioremap_wc(dev, vfpf_mbox_base,
+						MBOX_SIZE * cptpf->max_vfs);
+	if (!cptpf->vfpf_mbox_base) {
+		dev_err(dev, "Mapping of VF-PF mailbox address failed\n");
+		err = -ENOMEM;
+		goto free_wqe;
+	}
+	err = otx2_mbox_init(&cptpf->vfpf_mbox, cptpf->vfpf_mbox_base,
+			     cptpf->pdev, cptpf->reg_base, MBOX_DIR_PFVF,
+			     num_vfs);
+	if (err)
+		goto free_wqe;
+
+	for (i = 0; i < num_vfs; i++) {
+		cptpf->vf[i].vf_id = i;
+		cptpf->vf[i].cptpf = cptpf;
+		cptpf->vf[i].intr_idx = i % 64;
+		INIT_WORK(&cptpf->vf[i].vfpf_mbox_work,
+			  otx2_cptpf_vfpf_mbox_handler);
+	}
+	return 0;
+
+free_wqe:
+	destroy_workqueue(cptpf->vfpf_mbox_wq);
+	return err;
+}
+
+static void cptpf_vfpf_mbox_destroy(struct otx2_cptpf_dev *cptpf)
+{
+	destroy_workqueue(cptpf->vfpf_mbox_wq);
+	otx2_mbox_destroy(&cptpf->vfpf_mbox);
+}
+
+static void cptpf_disable_afpf_mbox_intr(struct otx2_cptpf_dev *cptpf)
+{
+	/* Disable AF-PF interrupt */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT_ENA_W1C,
+			 0x1ULL);
+	/* Clear interrupt if any */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT, 0x1ULL);
+}
+
+static int cptpf_register_afpf_mbox_intr(struct otx2_cptpf_dev *cptpf)
+{
+	struct pci_dev *pdev = cptpf->pdev;
+	struct device *dev = &pdev->dev;
+	int ret, irq;
+
+	irq = pci_irq_vector(pdev, RVU_PF_INT_VEC_AFPF_MBOX);
+	/* Register AF-PF mailbox interrupt handler */
+	ret = devm_request_irq(dev, irq, otx2_cptpf_afpf_mbox_intr, 0,
+			       "CPTAFPF Mbox", cptpf);
+	if (ret) {
+		dev_err(dev,
+			"IRQ registration failed for PFAF mbox irq\n");
+		return ret;
+	}
+	/* Clear interrupt if any, to avoid spurious interrupts */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT, 0x1ULL);
+	/* Enable AF-PF interrupt */
+	otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT_ENA_W1S,
+			 0x1ULL);
+
+	ret = otx2_cpt_send_ready_msg(&cptpf->afpf_mbox, cptpf->pdev);
+	if (ret) {
+		dev_warn(dev,
+			 "AF not responding to mailbox, deferring probe\n");
+		cptpf_disable_afpf_mbox_intr(cptpf);
+		return -EPROBE_DEFER;
+	}
+	return 0;
+}
+
+static int cptpf_afpf_mbox_init(struct otx2_cptpf_dev *cptpf)
+{
+	int err;
+
+	cptpf->afpf_mbox_wq = alloc_workqueue("cpt_afpf_mailbox",
+					      WQ_UNBOUND | WQ_HIGHPRI |
+					      WQ_MEM_RECLAIM, 1);
+	if (!cptpf->afpf_mbox_wq)
+		return -ENOMEM;
+
+	err = otx2_mbox_init(&cptpf->afpf_mbox, cptpf->afpf_mbox_base,
+			     cptpf->pdev, cptpf->reg_base, MBOX_DIR_PFAF, 1);
+	if (err)
+		goto error;
+
+	INIT_WORK(&cptpf->afpf_mbox_work, otx2_cptpf_afpf_mbox_handler);
+	return 0;
+
+error:
+	destroy_workqueue(cptpf->afpf_mbox_wq);
+	return err;
+}
+
+static void cptpf_afpf_mbox_destroy(struct otx2_cptpf_dev *cptpf)
+{
+	destroy_workqueue(cptpf->afpf_mbox_wq);
+	otx2_mbox_destroy(&cptpf->afpf_mbox);
+}
+
+static ssize_t kvf_limits_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", cptpf->kvf_limits);
+}
+
+static ssize_t kvf_limits_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev);
+	int lfs_num;
+
+	if (kstrtoint(buf, 0, &lfs_num)) {
+		dev_err(dev, "lfs count %d must be in range [1 - %d]\n",
+			lfs_num, num_online_cpus());
+		return -EINVAL;
+	}
+	if (lfs_num < 1 || lfs_num > num_online_cpus()) {
+		dev_err(dev, "lfs count %d must be in range [1 - %d]\n",
+			lfs_num, num_online_cpus());
+		return -EINVAL;
+	}
+	cptpf->kvf_limits = lfs_num;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(kvf_limits);
+static struct attribute *cptpf_attrs[] = {
+	&dev_attr_kvf_limits.attr,
+	NULL
+};
+
+static const struct attribute_group cptpf_sysfs_group = {
+	.attrs = cptpf_attrs,
+};
+
+static int cpt_is_pf_usable(struct otx2_cptpf_dev *cptpf)
+{
+	u64 rev;
+
+	rev = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0,
+			      RVU_PF_BLOCK_ADDRX_DISC(BLKADDR_RVUM));
+	rev = (rev >> 12) & 0xFF;
+	/*
+	 * Check if AF has setup revision for RVUM block, otherwise
+	 * driver probe should be deferred until AF driver comes up
+	 */
+	if (!rev) {
+		dev_warn(&cptpf->pdev->dev,
+			 "AF is not initialized, deferring probe\n");
+		return -EPROBE_DEFER;
+	}
+	return 0;
+}
+
+static int cptpf_device_reset(struct otx2_cptpf_dev *cptpf)
+{
+	int timeout = 10, ret;
+	u64 reg = 0;
+
+	ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+				    CPT_AF_BLK_RST, 0x1);
+	if (ret)
+		return ret;
+
+	do {
+		ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+					   CPT_AF_BLK_RST, &reg);
+		if (ret)
+			return ret;
+
+		if (!((reg >> 63) & 0x1))
+			break;
+
+		usleep_range(10000, 20000);
+		if (timeout-- < 0)
+			return -EBUSY;
+	} while (1);
+
+	return ret;
+}
+
+static int cptpf_device_init(struct otx2_cptpf_dev *cptpf)
+{
+	union otx2_cptx_af_constants1 af_cnsts1 = {0};
+	int ret = 0;
+
+	/* Reset the CPT PF device */
+	ret = cptpf_device_reset(cptpf);
+	if (ret)
+		return ret;
+
+	/* Get number of SE, IE and AE engines */
+	ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+				   CPT_AF_CONSTANTS1, &af_cnsts1.u);
+	if (ret)
+		return ret;
+
+	cptpf->eng_grps.avail.max_se_cnt = af_cnsts1.s.se;
+	cptpf->eng_grps.avail.max_ie_cnt = af_cnsts1.s.ie;
+	cptpf->eng_grps.avail.max_ae_cnt = af_cnsts1.s.ae;
+
+	/* Disable all cores */
+	ret = otx2_cpt_disable_all_cores(cptpf);
+
+	return ret;
+}
+
+static int cptpf_sriov_disable(struct pci_dev *pdev)
+{
+	struct otx2_cptpf_dev *cptpf = pci_get_drvdata(pdev);
+	int num_vfs = pci_num_vf(pdev);
+
+	if (!num_vfs)
+		return 0;
+
+	pci_disable_sriov(pdev);
+	cptpf_unregister_vfpf_intr(cptpf, num_vfs);
+	cptpf_flr_wq_destroy(cptpf);
+	cptpf_vfpf_mbox_destroy(cptpf);
+	module_put(THIS_MODULE);
+	cptpf->enabled_vfs = 0;
+
+	return 0;
+}
+
+static int cptpf_sriov_enable(struct pci_dev *pdev, int num_vfs)
+{
+	struct otx2_cptpf_dev *cptpf = pci_get_drvdata(pdev);
+	int ret;
+
+	/* Initialize VF<=>PF mailbox */
+	ret = cptpf_vfpf_mbox_init(cptpf, num_vfs);
+	if (ret)
+		return ret;
+
+	ret = cptpf_flr_wq_init(cptpf, num_vfs);
+	if (ret)
+		goto destroy_mbox;
+	/* Register VF<=>PF mailbox interrupt */
+	ret = cptpf_register_vfpf_intr(cptpf, num_vfs);
+	if (ret)
+		goto destroy_flr;
+
+	/* Get CPT HW capabilities using LOAD_FVC operation. */
+	ret = otx2_cpt_discover_eng_capabilities(cptpf);
+	if (ret)
+		goto disable_intr;
+
+	ret = otx2_cpt_create_eng_grps(cptpf->pdev, &cptpf->eng_grps);
+	if (ret)
+		goto disable_intr;
+
+	cptpf->enabled_vfs = num_vfs;
+	ret = pci_enable_sriov(pdev, num_vfs);
+	if (ret)
+		goto disable_intr;
+
+	dev_notice(&cptpf->pdev->dev, "VFs enabled: %d\n", num_vfs);
+
+	try_module_get(THIS_MODULE);
+	return num_vfs;
+
+disable_intr:
+	cptpf_unregister_vfpf_intr(cptpf, num_vfs);
+	cptpf->enabled_vfs = 0;
+destroy_flr:
+	cptpf_flr_wq_destroy(cptpf);
+destroy_mbox:
+	cptpf_vfpf_mbox_destroy(cptpf);
+	return ret;
+}
+
+static int otx2_cptpf_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	if (num_vfs > 0) {
+		return cptpf_sriov_enable(pdev, num_vfs);
+	} else {
+		return cptpf_sriov_disable(pdev);
+	}
+}
+
+static int otx2_cptpf_probe(struct pci_dev *pdev,
+			    const struct pci_device_id *ent)
+{
+	struct device *dev = &pdev->dev;
+	resource_size_t offset, size;
+	struct otx2_cptpf_dev *cptpf;
+	int err;
+
+	cptpf = devm_kzalloc(dev, sizeof(*cptpf), GFP_KERNEL);
+	if (!cptpf)
+		return -ENOMEM;
+
+	err = pcim_enable_device(pdev);
+	if (err) {
+		dev_err(dev, "Failed to enable PCI device\n");
+		goto clear_drvdata;
+	}
+
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "Unable to get usable DMA configuration\n");
+		goto clear_drvdata;
+	}
+	/* Map PF's configuration registers */
+	err = pcim_iomap_regions_request_all(pdev, 1 << PCI_PF_REG_BAR_NUM,
+					     OTX2_CPT_DRV_NAME);
+	if (err) {
+		dev_err(dev, "Couldn't get PCI resources 0x%x\n", err);
+		goto clear_drvdata;
+	}
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, cptpf);
+	cptpf->pdev = pdev;
+
+	cptpf->reg_base = pcim_iomap_table(pdev)[PCI_PF_REG_BAR_NUM];
+
+	/* Check if AF driver is up, otherwise defer probe */
+	err = cpt_is_pf_usable(cptpf);
+	if (err)
+		goto clear_drvdata;
+
+	offset = pci_resource_start(pdev, PCI_MBOX_BAR_NUM);
+	size = pci_resource_len(pdev, PCI_MBOX_BAR_NUM);
+	/* Map AF-PF mailbox memory */
+	cptpf->afpf_mbox_base = devm_ioremap_wc(dev, offset, size);
+	if (!cptpf->afpf_mbox_base) {
+		dev_err(&pdev->dev, "Unable to map BAR4\n");
+		err = -ENODEV;
+		goto clear_drvdata;
+	}
+	err = pci_alloc_irq_vectors(pdev, RVU_PF_INT_VEC_CNT,
+				    RVU_PF_INT_VEC_CNT, PCI_IRQ_MSIX);
+	if (err < 0) {
+		dev_err(dev, "Request for %d msix vectors failed\n",
+			RVU_PF_INT_VEC_CNT);
+		goto clear_drvdata;
+	}
+	/* Initialize AF-PF mailbox */
+	err = cptpf_afpf_mbox_init(cptpf);
+	if (err)
+		goto clear_drvdata;
+	/* Register mailbox interrupt */
+	err = cptpf_register_afpf_mbox_intr(cptpf);
+	if (err)
+		goto destroy_afpf_mbox;
+
+	cptpf->max_vfs = pci_sriov_get_totalvfs(pdev);
+
+	/* Initialize CPT PF device */
+	err = cptpf_device_init(cptpf);
+	if (err)
+		goto unregister_intr;
+
+	/* Initialize engine groups */
+	err = otx2_cpt_init_eng_grps(pdev, &cptpf->eng_grps);
+	if (err)
+		goto unregister_intr;
+
+	err = sysfs_create_group(&dev->kobj, &cptpf_sysfs_group);
+	if (err)
+		goto cleanup_eng_grps;
+	return 0;
+
+cleanup_eng_grps:
+	otx2_cpt_cleanup_eng_grps(pdev, &cptpf->eng_grps);
+unregister_intr:
+	cptpf_disable_afpf_mbox_intr(cptpf);
+destroy_afpf_mbox:
+	cptpf_afpf_mbox_destroy(cptpf);
+clear_drvdata:
+	pci_set_drvdata(pdev, NULL);
+	return err;
+}
+
+static void otx2_cptpf_remove(struct pci_dev *pdev)
+{
+	struct otx2_cptpf_dev *cptpf = pci_get_drvdata(pdev);
+
+	if (!cptpf)
+		return;
+
+	cptpf_sriov_disable(pdev);
+	/* Delete sysfs entry created for kernel VF limits */
+	sysfs_remove_group(&pdev->dev.kobj, &cptpf_sysfs_group);
+	/* Cleanup engine groups */
+	otx2_cpt_cleanup_eng_grps(pdev, &cptpf->eng_grps);
+	/* Disable AF-PF mailbox interrupt */
+	cptpf_disable_afpf_mbox_intr(cptpf);
+	/* Destroy AF-PF mbox */
+	cptpf_afpf_mbox_destroy(cptpf);
+	pci_set_drvdata(pdev, NULL);
+}
+
+/* Supported devices */
+static const struct pci_device_id otx2_cpt_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OTX2_CPT_PCI_PF_DEVICE_ID) },
+	{ 0, }  /* end of table */
+};
+
+static struct pci_driver otx2_cpt_pci_driver = {
+	.name = OTX2_CPT_DRV_NAME,
+	.id_table = otx2_cpt_id_table,
+	.probe = otx2_cptpf_probe,
+	.remove = otx2_cptpf_remove,
+	.sriov_configure = otx2_cptpf_sriov_configure
+};
+
+module_pci_driver(otx2_cpt_pci_driver);
+
+MODULE_AUTHOR("Marvell");
+MODULE_DESCRIPTION(OTX2_CPT_DRV_STRING);
+MODULE_LICENSE("GPL v2");
+MODULE_DEVICE_TABLE(pci, otx2_cpt_id_table);
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c
new file mode 100644
index 000000000000..186f1c1190c1
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptpf.h"
+#include "rvu_reg.h"
+
+/*
+ * CPT PF driver version, It will be incremented by 1 for every feature
+ * addition in CPT mailbox messages.
+ */
+#define OTX2_CPT_PF_DRV_VERSION 0x1
+
+static int forward_to_af(struct otx2_cptpf_dev *cptpf,
+			 struct otx2_cptvf_info *vf,
+			 struct mbox_msghdr *req, int size)
+{
+	struct mbox_msghdr *msg;
+	int ret;
+
+	msg = otx2_mbox_alloc_msg(&cptpf->afpf_mbox, 0, size);
+	if (msg == NULL)
+		return -ENOMEM;
+
+	memcpy((uint8_t *)msg + sizeof(struct mbox_msghdr),
+	       (uint8_t *)req + sizeof(struct mbox_msghdr), size);
+	msg->id = req->id;
+	msg->pcifunc = req->pcifunc;
+	msg->sig = req->sig;
+	msg->ver = req->ver;
+
+	otx2_mbox_msg_send(&cptpf->afpf_mbox, 0);
+	ret = otx2_mbox_wait_for_rsp(&cptpf->afpf_mbox, 0);
+	if (ret == -EIO) {
+		dev_err(&cptpf->pdev->dev, "RVU MBOX timeout.\n");
+		return ret;
+	} else if (ret) {
+		dev_err(&cptpf->pdev->dev, "RVU MBOX error: %d.\n", ret);
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static int handle_msg_get_caps(struct otx2_cptpf_dev *cptpf,
+			       struct otx2_cptvf_info *vf,
+			       struct mbox_msghdr *req)
+{
+	struct otx2_cpt_caps_rsp *rsp;
+
+	rsp = (struct otx2_cpt_caps_rsp *)
+	      otx2_mbox_alloc_msg(&cptpf->vfpf_mbox, vf->vf_id,
+				  sizeof(*rsp));
+	if (!rsp)
+		return -ENOMEM;
+
+	rsp->hdr.id = MBOX_MSG_GET_CAPS;
+	rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
+	rsp->hdr.pcifunc = req->pcifunc;
+	rsp->cpt_pf_drv_version = OTX2_CPT_PF_DRV_VERSION;
+	rsp->cpt_revision = cptpf->pdev->revision;
+	memcpy(&rsp->eng_caps, &cptpf->eng_caps, sizeof(rsp->eng_caps));
+
+	return 0;
+}
+
+static int handle_msg_get_eng_grp_num(struct otx2_cptpf_dev *cptpf,
+				      struct otx2_cptvf_info *vf,
+				      struct mbox_msghdr *req)
+{
+	struct otx2_cpt_egrp_num_msg *grp_req;
+	struct otx2_cpt_egrp_num_rsp *rsp;
+
+	grp_req = (struct otx2_cpt_egrp_num_msg *)req;
+	rsp = (struct otx2_cpt_egrp_num_rsp *)
+	       otx2_mbox_alloc_msg(&cptpf->vfpf_mbox, vf->vf_id, sizeof(*rsp));
+	if (!rsp)
+		return -ENOMEM;
+
+	rsp->hdr.id = MBOX_MSG_GET_ENG_GRP_NUM;
+	rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
+	rsp->hdr.pcifunc = req->pcifunc;
+	rsp->eng_type = grp_req->eng_type;
+	rsp->eng_grp_num = otx2_cpt_get_eng_grp(&cptpf->eng_grps,
+						grp_req->eng_type);
+
+	return 0;
+}
+
+static int handle_msg_kvf_limits(struct otx2_cptpf_dev *cptpf,
+				 struct otx2_cptvf_info *vf,
+				 struct mbox_msghdr *req)
+{
+	struct otx2_cpt_kvf_limits_rsp *rsp;
+
+	rsp = (struct otx2_cpt_kvf_limits_rsp *)
+	      otx2_mbox_alloc_msg(&cptpf->vfpf_mbox, vf->vf_id, sizeof(*rsp));
+	if (!rsp)
+		return -ENOMEM;
+
+	rsp->hdr.id = MBOX_MSG_GET_KVF_LIMITS;
+	rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
+	rsp->hdr.pcifunc = req->pcifunc;
+	rsp->kvf_limits = cptpf->kvf_limits;
+
+	return 0;
+}
+
+static int cptpf_handle_vf_req(struct otx2_cptpf_dev *cptpf,
+			       struct otx2_cptvf_info *vf,
+			       struct mbox_msghdr *req, int size)
+{
+	int err = 0;
+
+	/* Check if msg is valid, if not reply with an invalid msg */
+	if (req->sig != OTX2_MBOX_REQ_SIG)
+		goto inval_msg;
+
+	switch (req->id) {
+	case MBOX_MSG_GET_ENG_GRP_NUM:
+		err = handle_msg_get_eng_grp_num(cptpf, vf, req);
+		break;
+	case MBOX_MSG_GET_CAPS:
+		err = handle_msg_get_caps(cptpf, vf, req);
+		break;
+	case MBOX_MSG_GET_KVF_LIMITS:
+		err = handle_msg_kvf_limits(cptpf, vf, req);
+		break;
+	default:
+		err = forward_to_af(cptpf, vf, req, size);
+		break;
+	}
+	return err;
+
+inval_msg:
+	otx2_reply_invalid_msg(&cptpf->vfpf_mbox, vf->vf_id, 0, req->id);
+	otx2_mbox_msg_send(&cptpf->vfpf_mbox, vf->vf_id);
+	return err;
+}
+
+irqreturn_t otx2_cptpf_vfpf_mbox_intr(int __always_unused irq, void *arg)
+{
+	struct otx2_cptpf_dev *cptpf = arg;
+	struct otx2_cptvf_info *vf;
+	int i, vf_idx;
+	u64 intr;
+
+	/*
+	 * Check which VF has raised an interrupt and schedule
+	 * corresponding work queue to process the messages
+	 */
+	for (i = 0; i < 2; i++) {
+		/* Read the interrupt bits */
+		intr = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0,
+				       RVU_PF_VFPF_MBOX_INTX(i));
+
+		for (vf_idx = i * 64; vf_idx < cptpf->enabled_vfs; vf_idx++) {
+			vf = &cptpf->vf[vf_idx];
+			if (intr & (1ULL << vf->intr_idx)) {
+				queue_work(cptpf->vfpf_mbox_wq,
+					   &vf->vfpf_mbox_work);
+				/* Clear the interrupt */
+				otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM,
+						 0, RVU_PF_VFPF_MBOX_INTX(i),
+						 BIT_ULL(vf->intr_idx));
+			}
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+void otx2_cptpf_vfpf_mbox_handler(struct work_struct *work)
+{
+	struct otx2_cptpf_dev *cptpf;
+	struct otx2_cptvf_info *vf;
+	struct otx2_mbox_dev *mdev;
+	struct mbox_hdr *req_hdr;
+	struct mbox_msghdr *msg;
+	struct otx2_mbox *mbox;
+	int offset, i, err;
+
+	vf = container_of(work, struct otx2_cptvf_info, vfpf_mbox_work);
+	cptpf = vf->cptpf;
+	mbox = &cptpf->vfpf_mbox;
+	/* sync with mbox memory region */
+	smp_rmb();
+	mdev = &mbox->dev[vf->vf_id];
+	/* Process received mbox messages */
+	req_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+	offset = mbox->rx_start + ALIGN(sizeof(*req_hdr), MBOX_MSG_ALIGN);
+
+	for (i = 0; i < req_hdr->num_msgs; i++) {
+		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
+
+		/* Set which VF sent this message based on mbox IRQ */
+		msg->pcifunc = ((u16)cptpf->pf_id << RVU_PFVF_PF_SHIFT) |
+				((vf->vf_id + 1) & RVU_PFVF_FUNC_MASK);
+
+		err = cptpf_handle_vf_req(cptpf, vf, msg,
+					  msg->next_msgoff - offset);
+		/*
+		 * Behave as the AF, drop the msg if there is
+		 * no memory, timeout handling also goes here
+		 */
+		if (err == -ENOMEM || err == -EIO)
+			break;
+		offset = msg->next_msgoff;
+	}
+	/* Send mbox responses to VF */
+	if (mdev->num_msgs)
+		otx2_mbox_msg_send(mbox, vf->vf_id);
+}
+
+irqreturn_t otx2_cptpf_afpf_mbox_intr(int __always_unused irq, void *arg)
+{
+	struct otx2_cptpf_dev *cptpf = arg;
+	u64 intr;
+
+	/* Read the interrupt bits */
+	intr = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT);
+
+	if (intr & 0x1ULL) {
+		/* Schedule work queue function to process the MBOX request */
+		queue_work(cptpf->afpf_mbox_wq, &cptpf->afpf_mbox_work);
+		/* Clear and ack the interrupt */
+		otx2_cpt_write64(cptpf->reg_base, BLKADDR_RVUM, 0, RVU_PF_INT,
+				 0x1ULL);
+	}
+	return IRQ_HANDLED;
+}
+
+static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf,
+				  struct mbox_msghdr *msg)
+{
+	struct device *dev = &cptpf->pdev->dev;
+	struct cpt_rd_wr_reg_msg *rsp_rd_wr;
+
+	if (msg->id >= MBOX_MSG_MAX) {
+		dev_err(dev, "MBOX msg with unknown ID %d\n", msg->id);
+		return;
+	}
+	if (msg->sig != OTX2_MBOX_RSP_SIG) {
+		dev_err(dev, "MBOX msg with wrong signature %x, ID %d\n",
+			msg->sig, msg->id);
+		return;
+	}
+
+	switch (msg->id) {
+	case MBOX_MSG_READY:
+		cptpf->pf_id = (msg->pcifunc >> RVU_PFVF_PF_SHIFT) &
+				RVU_PFVF_PF_MASK;
+		break;
+	case MBOX_MSG_CPT_RD_WR_REGISTER:
+		rsp_rd_wr = (struct cpt_rd_wr_reg_msg *)msg;
+		if (msg->rc) {
+			dev_err(dev, "Reg %llx rd/wr(%d) failed %d\n",
+				rsp_rd_wr->reg_offset, rsp_rd_wr->is_write,
+				msg->rc);
+			return;
+		}
+		if (!rsp_rd_wr->is_write)
+			*rsp_rd_wr->ret_val = rsp_rd_wr->val;
+		break;
+	case MBOX_MSG_ATTACH_RESOURCES:
+		if (!msg->rc)
+			cptpf->lfs.are_lfs_attached = 1;
+		break;
+	case MBOX_MSG_DETACH_RESOURCES:
+		if (!msg->rc)
+			cptpf->lfs.are_lfs_attached = 0;
+		break;
+
+	default:
+		dev_err(dev,
+			"Unsupported msg %d received.\n", msg->id);
+		break;
+	}
+}
+
+static void forward_to_vf(struct otx2_cptpf_dev *cptpf, struct mbox_msghdr *msg,
+			  int vf_id, int size)
+{
+	struct otx2_mbox *vfpf_mbox;
+	struct mbox_msghdr *fwd;
+
+	if (msg->id >= MBOX_MSG_MAX) {
+		dev_err(&cptpf->pdev->dev,
+			"MBOX msg with unknown ID %d\n", msg->id);
+		return;
+	}
+	if (msg->sig != OTX2_MBOX_RSP_SIG) {
+		dev_err(&cptpf->pdev->dev,
+			"MBOX msg with wrong signature %x, ID %d\n",
+			msg->sig, msg->id);
+		return;
+	}
+	vfpf_mbox = &cptpf->vfpf_mbox;
+	vf_id--;
+	if (vf_id >= cptpf->enabled_vfs) {
+		dev_err(&cptpf->pdev->dev,
+			"MBOX msg to unknown VF: %d >= %d\n",
+			vf_id, cptpf->enabled_vfs);
+		return;
+	}
+	if (msg->id == MBOX_MSG_VF_FLR)
+		return;
+
+	fwd = otx2_mbox_alloc_msg(vfpf_mbox, vf_id, size);
+	if (!fwd) {
+		dev_err(&cptpf->pdev->dev,
+			"Forwarding to VF%d failed.\n", vf_id);
+		return;
+	}
+	memcpy((uint8_t *)fwd + sizeof(struct mbox_msghdr),
+		(uint8_t *)msg + sizeof(struct mbox_msghdr), size);
+	fwd->id = msg->id;
+	fwd->pcifunc = msg->pcifunc;
+	fwd->sig = msg->sig;
+	fwd->ver = msg->ver;
+	fwd->rc = msg->rc;
+}
+
+/* Handle mailbox messages received from AF */
+void otx2_cptpf_afpf_mbox_handler(struct work_struct *work)
+{
+	struct otx2_cptpf_dev *cptpf;
+	struct otx2_mbox *afpf_mbox;
+	struct otx2_mbox_dev *mdev;
+	struct mbox_hdr *rsp_hdr;
+	struct mbox_msghdr *msg;
+	int offset, vf_id, i;
+
+	cptpf = container_of(work, struct otx2_cptpf_dev, afpf_mbox_work);
+	afpf_mbox = &cptpf->afpf_mbox;
+	mdev = &afpf_mbox->dev[0];
+	/* Sync mbox data into memory */
+	smp_wmb();
+
+	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + afpf_mbox->rx_start);
+	offset = ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
+
+	for (i = 0; i < rsp_hdr->num_msgs; i++) {
+		msg = (struct mbox_msghdr *)(mdev->mbase + afpf_mbox->rx_start +
+					     offset);
+		vf_id = (msg->pcifunc >> RVU_PFVF_FUNC_SHIFT) &
+			 RVU_PFVF_FUNC_MASK;
+		if (vf_id > 0)
+			forward_to_vf(cptpf, msg, vf_id,
+				      msg->next_msgoff - offset);
+		else
+			process_afpf_mbox_msg(cptpf, msg);
+
+		offset = msg->next_msgoff;
+		mdev->msgs_acked++;
+	}
+	otx2_mbox_reset(afpf_mbox, 0);
+}
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
new file mode 100644
index 000000000000..1dc3ba298139
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
@@ -0,0 +1,1415 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include <linux/ctype.h>
+#include <linux/firmware.h>
+#include "otx2_cptpf_ucode.h"
+#include "otx2_cpt_common.h"
+#include "otx2_cptpf.h"
+#include "otx2_cptlf.h"
+#include "otx2_cpt_reqmgr.h"
+#include "rvu_reg.h"
+
+#define CSR_DELAY 30
+
+#define LOADFVC_RLEN 8
+#define LOADFVC_MAJOR_OP 0x01
+#define LOADFVC_MINOR_OP 0x08
+
+struct fw_info_t {
+	struct list_head ucodes;
+};
+
+static struct otx2_cpt_bitmap get_cores_bmap(struct device *dev,
+					struct otx2_cpt_eng_grp_info *eng_grp)
+{
+	struct otx2_cpt_bitmap bmap = { {0} };
+	bool found = false;
+	int i;
+
+	if (eng_grp->g->engs_num > OTX2_CPT_MAX_ENGINES) {
+		dev_err(dev, "unsupported number of engines %d on octeontx2\n",
+			eng_grp->g->engs_num);
+		return bmap;
+	}
+
+	for (i = 0; i  < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) {
+		if (eng_grp->engs[i].type) {
+			bitmap_or(bmap.bits, bmap.bits,
+				  eng_grp->engs[i].bmap,
+				  eng_grp->g->engs_num);
+			bmap.size = eng_grp->g->engs_num;
+			found = true;
+		}
+	}
+
+	if (!found)
+		dev_err(dev, "No engines reserved for engine group %d\n",
+			eng_grp->idx);
+	return bmap;
+}
+
+static int is_eng_type(int val, int eng_type)
+{
+	return val & (1 << eng_type);
+}
+
+static int is_2nd_ucode_used(struct otx2_cpt_eng_grp_info *eng_grp)
+{
+	if (eng_grp->ucode[1].type)
+		return true;
+	else
+		return false;
+}
+
+static void set_ucode_filename(struct otx2_cpt_ucode *ucode,
+			       const char *filename)
+{
+	strlcpy(ucode->filename, filename, OTX2_CPT_NAME_LENGTH);
+}
+
+static char *get_eng_type_str(int eng_type)
+{
+	char *str = "unknown";
+
+	switch (eng_type) {
+	case OTX2_CPT_SE_TYPES:
+		str = "SE";
+		break;
+
+	case OTX2_CPT_IE_TYPES:
+		str = "IE";
+		break;
+
+	case OTX2_CPT_AE_TYPES:
+		str = "AE";
+		break;
+	}
+	return str;
+}
+
+static char *get_ucode_type_str(int ucode_type)
+{
+	char *str = "unknown";
+
+	switch (ucode_type) {
+	case (1 << OTX2_CPT_SE_TYPES):
+		str = "SE";
+		break;
+
+	case (1 << OTX2_CPT_IE_TYPES):
+		str = "IE";
+		break;
+
+	case (1 << OTX2_CPT_AE_TYPES):
+		str = "AE";
+		break;
+
+	case (1 << OTX2_CPT_SE_TYPES | 1 << OTX2_CPT_IE_TYPES):
+		str = "SE+IPSEC";
+		break;
+	}
+	return str;
+}
+
+static int get_ucode_type(struct device *dev,
+			  struct otx2_cpt_ucode_hdr *ucode_hdr,
+			  int *ucode_type)
+{
+	struct otx2_cptpf_dev *cptpf = dev_get_drvdata(dev);
+	char ver_str_prefix[OTX2_CPT_UCODE_VER_STR_SZ];
+	char tmp_ver_str[OTX2_CPT_UCODE_VER_STR_SZ];
+	struct pci_dev *pdev = cptpf->pdev;
+	int i, val = 0;
+	u8 nn;
+
+	strlcpy(tmp_ver_str, ucode_hdr->ver_str, OTX2_CPT_UCODE_VER_STR_SZ);
+	for (i = 0; i < strlen(tmp_ver_str); i++)
+		tmp_ver_str[i] = tolower(tmp_ver_str[i]);
+
+	sprintf(ver_str_prefix, "ocpt-%02d", pdev->revision);
+	if (!strnstr(tmp_ver_str, ver_str_prefix, OTX2_CPT_UCODE_VER_STR_SZ))
+		return -EINVAL;
+
+	nn = ucode_hdr->ver_num.nn;
+	if (strnstr(tmp_ver_str, "se-", OTX2_CPT_UCODE_VER_STR_SZ) &&
+	    (nn == OTX2_CPT_SE_UC_TYPE1 || nn == OTX2_CPT_SE_UC_TYPE2 ||
+	     nn == OTX2_CPT_SE_UC_TYPE3))
+		val |= 1 << OTX2_CPT_SE_TYPES;
+	if (strnstr(tmp_ver_str, "ie-", OTX2_CPT_UCODE_VER_STR_SZ) &&
+	    (nn == OTX2_CPT_IE_UC_TYPE1 || nn == OTX2_CPT_IE_UC_TYPE2 ||
+	     nn == OTX2_CPT_IE_UC_TYPE3))
+		val |= 1 << OTX2_CPT_IE_TYPES;
+	if (strnstr(tmp_ver_str, "ae", OTX2_CPT_UCODE_VER_STR_SZ) &&
+	    nn == OTX2_CPT_AE_UC_TYPE)
+		val |= 1 << OTX2_CPT_AE_TYPES;
+
+	*ucode_type = val;
+
+	if (!val)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __write_ucode_base(struct otx2_cptpf_dev *cptpf, int eng,
+			      dma_addr_t dma_addr)
+{
+	return otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+				     CPT_AF_EXEX_UCODE_BASE(eng),
+				     (u64)dma_addr);
+}
+
+static int cpt_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, void *obj)
+{
+	struct otx2_cptpf_dev *cptpf = obj;
+	struct otx2_cpt_engs_rsvd *engs;
+	dma_addr_t dma_addr;
+	int i, bit, ret;
+
+	/* Set PF number for microcode fetches */
+	ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+				    CPT_AF_PF_FUNC,
+				    cptpf->pf_id << RVU_PFVF_PF_SHIFT);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) {
+		engs = &eng_grp->engs[i];
+		if (!engs->type)
+			continue;
+
+		dma_addr = engs->ucode->dma;
+
+		/*
+		 * Set UCODE_BASE only for the cores which are not used,
+		 * other cores should have already valid UCODE_BASE set
+		 */
+		for_each_set_bit(bit, engs->bmap, eng_grp->g->engs_num)
+			if (!eng_grp->g->eng_ref_cnt[bit]) {
+				ret = __write_ucode_base(cptpf, bit, dma_addr);
+				if (ret)
+					return ret;
+			}
+	}
+	return 0;
+}
+
+static int cpt_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp,
+					void *obj)
+{
+	struct otx2_cptpf_dev *cptpf = obj;
+	struct otx2_cpt_bitmap bmap;
+	int i, timeout = 10;
+	int busy, ret;
+	u64 reg = 0;
+
+	bmap = get_cores_bmap(&cptpf->pdev->dev, eng_grp);
+	if (!bmap.size)
+		return -EINVAL;
+
+	/* Detach the cores from group */
+	for_each_set_bit(i, bmap.bits, bmap.size) {
+		ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+					   CPT_AF_EXEX_CTL2(i), &reg);
+		if (ret)
+			return ret;
+
+		if (reg & (1ull << eng_grp->idx)) {
+			eng_grp->g->eng_ref_cnt[i]--;
+			reg &= ~(1ull << eng_grp->idx);
+
+			ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox,
+						    cptpf->pdev,
+						    CPT_AF_EXEX_CTL2(i), reg);
+			if (ret)
+				return ret;
+		}
+	}
+
+	/* Wait for cores to become idle */
+	do {
+		busy = 0;
+		usleep_range(10000, 20000);
+		if (timeout-- < 0)
+			return -EBUSY;
+
+		for_each_set_bit(i, bmap.bits, bmap.size) {
+			ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox,
+						   cptpf->pdev,
+						   CPT_AF_EXEX_STS(i), &reg);
+			if (ret)
+				return ret;
+
+			if (reg & 0x1) {
+				busy = 1;
+				break;
+			}
+		}
+	} while (busy);
+
+	/* Disable the cores only if they are not used anymore */
+	for_each_set_bit(i, bmap.bits, bmap.size) {
+		if (!eng_grp->g->eng_ref_cnt[i]) {
+			ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox,
+						    cptpf->pdev,
+						    CPT_AF_EXEX_CTL(i), 0x0);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int cpt_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp,
+				       void *obj)
+{
+	struct otx2_cptpf_dev *cptpf = obj;
+	struct otx2_cpt_bitmap bmap;
+	u64 reg = 0;
+	int i, ret;
+
+	bmap = get_cores_bmap(&cptpf->pdev->dev, eng_grp);
+	if (!bmap.size)
+		return -EINVAL;
+
+	/* Attach the cores to the group */
+	for_each_set_bit(i, bmap.bits, bmap.size) {
+		ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+					   CPT_AF_EXEX_CTL2(i), &reg);
+		if (ret)
+			return ret;
+
+		if (!(reg & (1ull << eng_grp->idx))) {
+			eng_grp->g->eng_ref_cnt[i]++;
+			reg |= 1ull << eng_grp->idx;
+
+			ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox,
+						    cptpf->pdev,
+						    CPT_AF_EXEX_CTL2(i), reg);
+			if (ret)
+				return ret;
+		}
+	}
+
+	/* Enable the cores */
+	for_each_set_bit(i, bmap.bits, bmap.size) {
+		ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox,
+						cptpf->pdev,
+						CPT_AF_EXEX_CTL(i), 0x1);
+		if (ret)
+			return ret;
+	}
+	ret = otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev);
+
+	return ret;
+}
+
+static int load_fw(struct device *dev, struct fw_info_t *fw_info,
+		   char *filename)
+{
+	struct otx2_cpt_ucode_hdr *ucode_hdr;
+	struct otx2_cpt_uc_info_t *uc_info;
+	int ucode_type, ucode_size;
+	int ret;
+
+	uc_info = kzalloc(sizeof(*uc_info), GFP_KERNEL);
+	if (!uc_info)
+		return -ENOMEM;
+
+	ret = request_firmware(&uc_info->fw, filename, dev);
+	if (ret)
+		goto free_uc_info;
+
+	ucode_hdr = (struct otx2_cpt_ucode_hdr *)uc_info->fw->data;
+	ret = get_ucode_type(dev, ucode_hdr, &ucode_type);
+	if (ret)
+		goto release_fw;
+
+	ucode_size = ntohl(ucode_hdr->code_length) * 2;
+	if (!ucode_size) {
+		dev_err(dev, "Ucode %s invalid size\n", filename);
+		ret = -EINVAL;
+		goto release_fw;
+	}
+
+	set_ucode_filename(&uc_info->ucode, filename);
+	memcpy(uc_info->ucode.ver_str, ucode_hdr->ver_str,
+	       OTX2_CPT_UCODE_VER_STR_SZ);
+	uc_info->ucode.ver_num = ucode_hdr->ver_num;
+	uc_info->ucode.type = ucode_type;
+	uc_info->ucode.size = ucode_size;
+	list_add_tail(&uc_info->list, &fw_info->ucodes);
+
+	return 0;
+
+release_fw:
+	release_firmware(uc_info->fw);
+free_uc_info:
+	kfree(uc_info);
+	return ret;
+}
+
+static void cpt_ucode_release_fw(struct fw_info_t *fw_info)
+{
+	struct otx2_cpt_uc_info_t *curr, *temp;
+
+	if (!fw_info)
+		return;
+
+	list_for_each_entry_safe(curr, temp, &fw_info->ucodes, list) {
+		list_del(&curr->list);
+		release_firmware(curr->fw);
+		kfree(curr);
+	}
+}
+
+static struct otx2_cpt_uc_info_t *get_ucode(struct fw_info_t *fw_info,
+					    int ucode_type)
+{
+	struct otx2_cpt_uc_info_t *curr;
+
+	list_for_each_entry(curr, &fw_info->ucodes, list) {
+		if (!is_eng_type(curr->ucode.type, ucode_type))
+			continue;
+
+		return curr;
+	}
+	return NULL;
+}
+
+static void print_uc_info(struct fw_info_t *fw_info)
+{
+	struct otx2_cpt_uc_info_t *curr;
+
+	list_for_each_entry(curr, &fw_info->ucodes, list) {
+		pr_debug("Ucode filename %s\n", curr->ucode.filename);
+		pr_debug("Ucode version string %s\n", curr->ucode.ver_str);
+		pr_debug("Ucode version %d.%d.%d.%d\n",
+			 curr->ucode.ver_num.nn, curr->ucode.ver_num.xx,
+			 curr->ucode.ver_num.yy, curr->ucode.ver_num.zz);
+		pr_debug("Ucode type (%d) %s\n", curr->ucode.type,
+			 get_ucode_type_str(curr->ucode.type));
+		pr_debug("Ucode size %d\n", curr->ucode.size);
+		pr_debug("Ucode ptr %p\n", curr->fw->data);
+	}
+}
+
+static int cpt_ucode_load_fw(struct pci_dev *pdev, struct fw_info_t *fw_info)
+{
+	char filename[OTX2_CPT_NAME_LENGTH];
+	char eng_type[8] = {0};
+	int ret, e, i;
+
+	INIT_LIST_HEAD(&fw_info->ucodes);
+
+	for (e = 1; e < OTX2_CPT_MAX_ENG_TYPES; e++) {
+		strcpy(eng_type, get_eng_type_str(e));
+		for (i = 0; i < strlen(eng_type); i++)
+			eng_type[i] = tolower(eng_type[i]);
+
+		snprintf(filename, sizeof(filename), "mrvl/cpt%02d/%s.out",
+			 pdev->revision, eng_type);
+		/* Request firmware for each engine type */
+		ret = load_fw(&pdev->dev, fw_info, filename);
+		if (ret)
+			goto release_fw;
+	}
+	print_uc_info(fw_info);
+	return 0;
+
+release_fw:
+	cpt_ucode_release_fw(fw_info);
+	return ret;
+}
+
+static struct otx2_cpt_engs_rsvd *find_engines_by_type(
+					struct otx2_cpt_eng_grp_info *eng_grp,
+					int eng_type)
+{
+	int i;
+
+	for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) {
+		if (!eng_grp->engs[i].type)
+			continue;
+
+		if (eng_grp->engs[i].type == eng_type)
+			return &eng_grp->engs[i];
+	}
+	return NULL;
+}
+
+static int eng_grp_has_eng_type(struct otx2_cpt_eng_grp_info *eng_grp,
+				int eng_type)
+{
+	struct otx2_cpt_engs_rsvd *engs;
+
+	engs = find_engines_by_type(eng_grp, eng_type);
+
+	return (engs != NULL ? 1 : 0);
+}
+
+static int update_engines_avail_count(struct device *dev,
+				      struct otx2_cpt_engs_available *avail,
+				      struct otx2_cpt_engs_rsvd *engs, int val)
+{
+	switch (engs->type) {
+	case OTX2_CPT_SE_TYPES:
+		avail->se_cnt += val;
+		break;
+
+	case OTX2_CPT_IE_TYPES:
+		avail->ie_cnt += val;
+		break;
+
+	case OTX2_CPT_AE_TYPES:
+		avail->ae_cnt += val;
+		break;
+
+	default:
+		dev_err(dev, "Invalid engine type %d\n", engs->type);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int update_engines_offset(struct device *dev,
+				 struct otx2_cpt_engs_available *avail,
+				 struct otx2_cpt_engs_rsvd *engs)
+{
+	switch (engs->type) {
+	case OTX2_CPT_SE_TYPES:
+		engs->offset = 0;
+		break;
+
+	case OTX2_CPT_IE_TYPES:
+		engs->offset = avail->max_se_cnt;
+		break;
+
+	case OTX2_CPT_AE_TYPES:
+		engs->offset = avail->max_se_cnt + avail->max_ie_cnt;
+		break;
+
+	default:
+		dev_err(dev, "Invalid engine type %d\n", engs->type);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int release_engines(struct device *dev,
+			   struct otx2_cpt_eng_grp_info *grp)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) {
+		if (!grp->engs[i].type)
+			continue;
+
+		if (grp->engs[i].count > 0) {
+			ret = update_engines_avail_count(dev, &grp->g->avail,
+							 &grp->engs[i],
+							 grp->engs[i].count);
+			if (ret)
+				return ret;
+		}
+
+		grp->engs[i].type = 0;
+		grp->engs[i].count = 0;
+		grp->engs[i].offset = 0;
+		grp->engs[i].ucode = NULL;
+		bitmap_zero(grp->engs[i].bmap, grp->g->engs_num);
+	}
+	return 0;
+}
+
+static int do_reserve_engines(struct device *dev,
+			      struct otx2_cpt_eng_grp_info *grp,
+			      struct otx2_cpt_engines *req_engs)
+{
+	struct otx2_cpt_engs_rsvd *engs = NULL;
+	int i, ret;
+
+	for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) {
+		if (!grp->engs[i].type) {
+			engs = &grp->engs[i];
+			break;
+		}
+	}
+
+	if (!engs)
+		return -ENOMEM;
+
+	engs->type = req_engs->type;
+	engs->count = req_engs->count;
+
+	ret = update_engines_offset(dev, &grp->g->avail, engs);
+	if (ret)
+		return ret;
+
+	if (engs->count > 0) {
+		ret = update_engines_avail_count(dev, &grp->g->avail, engs,
+						 -engs->count);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int check_engines_availability(struct device *dev,
+				      struct otx2_cpt_eng_grp_info *grp,
+				      struct otx2_cpt_engines *req_eng)
+{
+	int avail_cnt = 0;
+
+	switch (req_eng->type) {
+	case OTX2_CPT_SE_TYPES:
+		avail_cnt = grp->g->avail.se_cnt;
+		break;
+
+	case OTX2_CPT_IE_TYPES:
+		avail_cnt = grp->g->avail.ie_cnt;
+		break;
+
+	case OTX2_CPT_AE_TYPES:
+		avail_cnt = grp->g->avail.ae_cnt;
+		break;
+
+	default:
+		dev_err(dev, "Invalid engine type %d\n", req_eng->type);
+		return -EINVAL;
+	}
+
+	if (avail_cnt < req_eng->count) {
+		dev_err(dev,
+			"Error available %s engines %d < than requested %d\n",
+			get_eng_type_str(req_eng->type),
+			avail_cnt, req_eng->count);
+		return -EBUSY;
+	}
+	return 0;
+}
+
+static int reserve_engines(struct device *dev,
+			   struct otx2_cpt_eng_grp_info *grp,
+			   struct otx2_cpt_engines *req_engs, int ucodes_cnt)
+{
+	int i, ret = 0;
+
+	/* Validate if a number of requested engines are available */
+	for (i = 0; i < ucodes_cnt; i++) {
+		ret = check_engines_availability(dev, grp, &req_engs[i]);
+		if (ret)
+			return ret;
+	}
+
+	/* Reserve requested engines for this engine group */
+	for (i = 0; i < ucodes_cnt; i++) {
+		ret = do_reserve_engines(dev, grp, &req_engs[i]);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static void ucode_unload(struct device *dev, struct otx2_cpt_ucode *ucode)
+{
+	if (ucode->va) {
+		dma_free_coherent(dev, ucode->size, ucode->va, ucode->dma);
+		ucode->va = NULL;
+		ucode->dma = 0;
+		ucode->size = 0;
+	}
+
+	memset(&ucode->ver_str, 0, OTX2_CPT_UCODE_VER_STR_SZ);
+	memset(&ucode->ver_num, 0, sizeof(struct otx2_cpt_ucode_ver_num));
+	set_ucode_filename(ucode, "");
+	ucode->type = 0;
+}
+
+static int copy_ucode_to_dma_mem(struct device *dev,
+				 struct otx2_cpt_ucode *ucode,
+				 const u8 *ucode_data)
+{
+	u32 i;
+
+	/*  Allocate DMAable space */
+	ucode->va = dma_alloc_coherent(dev, ucode->size, &ucode->dma,
+				       GFP_KERNEL);
+	if (!ucode->va)
+		return -ENOMEM;
+
+	memcpy(ucode->va, ucode_data + sizeof(struct otx2_cpt_ucode_hdr),
+	       ucode->size);
+
+	/* Byte swap 64-bit */
+	for (i = 0; i < (ucode->size / 8); i++)
+		cpu_to_be64s(&((u64 *)ucode->va)[i]);
+	/*  Ucode needs 16-bit swap */
+	for (i = 0; i < (ucode->size / 2); i++)
+		cpu_to_be16s(&((u16 *)ucode->va)[i]);
+	return 0;
+}
+
+static int enable_eng_grp(struct otx2_cpt_eng_grp_info *eng_grp,
+			  void *obj)
+{
+	int ret;
+
+	/* Point microcode to each core of the group */
+	ret = cpt_set_ucode_base(eng_grp, obj);
+	if (ret)
+		return ret;
+
+	/* Attach the cores to the group and enable them */
+	ret = cpt_attach_and_enable_cores(eng_grp, obj);
+
+	return ret;
+}
+
+static int disable_eng_grp(struct device *dev,
+			   struct otx2_cpt_eng_grp_info *eng_grp,
+			   void *obj)
+{
+	int i, ret;
+
+	/* Disable all engines used by this group */
+	ret = cpt_detach_and_disable_cores(eng_grp, obj);
+	if (ret)
+		return ret;
+
+	/* Unload ucode used by this engine group */
+	ucode_unload(dev, &eng_grp->ucode[0]);
+	ucode_unload(dev, &eng_grp->ucode[1]);
+
+	for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) {
+		if (!eng_grp->engs[i].type)
+			continue;
+
+		eng_grp->engs[i].ucode = &eng_grp->ucode[0];
+	}
+
+	/* Clear UCODE_BASE register for each engine used by this group */
+	ret = cpt_set_ucode_base(eng_grp, obj);
+
+	return ret;
+}
+
+static void setup_eng_grp_mirroring(struct otx2_cpt_eng_grp_info *dst_grp,
+				    struct otx2_cpt_eng_grp_info *src_grp)
+{
+	/* Setup fields for engine group which is mirrored */
+	src_grp->mirror.is_ena = false;
+	src_grp->mirror.idx = 0;
+	src_grp->mirror.ref_count++;
+
+	/* Setup fields for mirroring engine group */
+	dst_grp->mirror.is_ena = true;
+	dst_grp->mirror.idx = src_grp->idx;
+	dst_grp->mirror.ref_count = 0;
+}
+
+static void remove_eng_grp_mirroring(struct otx2_cpt_eng_grp_info *dst_grp)
+{
+	struct otx2_cpt_eng_grp_info *src_grp;
+
+	if (!dst_grp->mirror.is_ena)
+		return;
+
+	src_grp = &dst_grp->g->grp[dst_grp->mirror.idx];
+
+	src_grp->mirror.ref_count--;
+	dst_grp->mirror.is_ena = false;
+	dst_grp->mirror.idx = 0;
+	dst_grp->mirror.ref_count = 0;
+}
+
+static void update_requested_engs(struct otx2_cpt_eng_grp_info *mirror_eng_grp,
+				  struct otx2_cpt_engines *engs, int engs_cnt)
+{
+	struct otx2_cpt_engs_rsvd *mirrored_engs;
+	int i;
+
+	for (i = 0; i < engs_cnt; i++) {
+		mirrored_engs = find_engines_by_type(mirror_eng_grp,
+						     engs[i].type);
+		if (!mirrored_engs)
+			continue;
+
+		/*
+		 * If mirrored group has this type of engines attached then
+		 * there are 3 scenarios possible:
+		 * 1) mirrored_engs.count == engs[i].count then all engines
+		 * from mirrored engine group will be shared with this engine
+		 * group
+		 * 2) mirrored_engs.count > engs[i].count then only a subset of
+		 * engines from mirrored engine group will be shared with this
+		 * engine group
+		 * 3) mirrored_engs.count < engs[i].count then all engines
+		 * from mirrored engine group will be shared with this group
+		 * and additional engines will be reserved for exclusively use
+		 * by this engine group
+		 */
+		engs[i].count -= mirrored_engs->count;
+	}
+}
+
+static struct otx2_cpt_eng_grp_info *find_mirrored_eng_grp(
+					struct otx2_cpt_eng_grp_info *grp)
+{
+	struct otx2_cpt_eng_grps *eng_grps = grp->g;
+	int i;
+
+	for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) {
+		if (!eng_grps->grp[i].is_enabled)
+			continue;
+		if (eng_grps->grp[i].ucode[0].type &&
+		    eng_grps->grp[i].ucode[1].type)
+			continue;
+		if (grp->idx == i)
+			continue;
+		if (!strncasecmp(eng_grps->grp[i].ucode[0].ver_str,
+				 grp->ucode[0].ver_str,
+				 OTX2_CPT_UCODE_VER_STR_SZ))
+			return &eng_grps->grp[i];
+	}
+
+	return NULL;
+}
+
+static struct otx2_cpt_eng_grp_info *find_unused_eng_grp(
+					struct otx2_cpt_eng_grps *eng_grps)
+{
+	int i;
+
+	for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) {
+		if (!eng_grps->grp[i].is_enabled)
+			return &eng_grps->grp[i];
+	}
+	return NULL;
+}
+
+static int eng_grp_update_masks(struct device *dev,
+				struct otx2_cpt_eng_grp_info *eng_grp)
+{
+	struct otx2_cpt_engs_rsvd *engs, *mirrored_engs;
+	struct otx2_cpt_bitmap tmp_bmap = { {0} };
+	int i, j, cnt, max_cnt;
+	int bit;
+
+	for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) {
+		engs = &eng_grp->engs[i];
+		if (!engs->type)
+			continue;
+		if (engs->count <= 0)
+			continue;
+
+		switch (engs->type) {
+		case OTX2_CPT_SE_TYPES:
+			max_cnt = eng_grp->g->avail.max_se_cnt;
+			break;
+
+		case OTX2_CPT_IE_TYPES:
+			max_cnt = eng_grp->g->avail.max_ie_cnt;
+			break;
+
+		case OTX2_CPT_AE_TYPES:
+			max_cnt = eng_grp->g->avail.max_ae_cnt;
+			break;
+
+		default:
+			dev_err(dev, "Invalid engine type %d\n", engs->type);
+			return -EINVAL;
+		}
+
+		cnt = engs->count;
+		WARN_ON(engs->offset + max_cnt > OTX2_CPT_MAX_ENGINES);
+		bitmap_zero(tmp_bmap.bits, eng_grp->g->engs_num);
+		for (j = engs->offset; j < engs->offset + max_cnt; j++) {
+			if (!eng_grp->g->eng_ref_cnt[j]) {
+				bitmap_set(tmp_bmap.bits, j, 1);
+				cnt--;
+				if (!cnt)
+					break;
+			}
+		}
+
+		if (cnt)
+			return -ENOSPC;
+
+		bitmap_copy(engs->bmap, tmp_bmap.bits, eng_grp->g->engs_num);
+	}
+
+	if (!eng_grp->mirror.is_ena)
+		return 0;
+
+	for (i = 0; i < OTX2_CPT_MAX_ETYPES_PER_GRP; i++) {
+		engs = &eng_grp->engs[i];
+		if (!engs->type)
+			continue;
+
+		mirrored_engs = find_engines_by_type(
+					&eng_grp->g->grp[eng_grp->mirror.idx],
+					engs->type);
+		WARN_ON(!mirrored_engs && engs->count <= 0);
+		if (!mirrored_engs)
+			continue;
+
+		bitmap_copy(tmp_bmap.bits, mirrored_engs->bmap,
+			    eng_grp->g->engs_num);
+		if (engs->count < 0) {
+			bit = find_first_bit(mirrored_engs->bmap,
+					     eng_grp->g->engs_num);
+			bitmap_clear(tmp_bmap.bits, bit, -engs->count);
+		}
+		bitmap_or(engs->bmap, engs->bmap, tmp_bmap.bits,
+			  eng_grp->g->engs_num);
+	}
+	return 0;
+}
+
+static int delete_engine_group(struct device *dev,
+			       struct otx2_cpt_eng_grp_info *eng_grp)
+{
+	int ret;
+
+	if (!eng_grp->is_enabled)
+		return 0;
+
+	if (eng_grp->mirror.ref_count)
+		return -EINVAL;
+
+	/* Removing engine group mirroring if enabled */
+	remove_eng_grp_mirroring(eng_grp);
+
+	/* Disable engine group */
+	ret = disable_eng_grp(dev, eng_grp, eng_grp->g->obj);
+	if (ret)
+		return ret;
+
+	/* Release all engines held by this engine group */
+	ret = release_engines(dev, eng_grp);
+	if (ret)
+		return ret;
+
+	eng_grp->is_enabled = false;
+
+	return 0;
+}
+
+static void update_ucode_ptrs(struct otx2_cpt_eng_grp_info *eng_grp)
+{
+	struct otx2_cpt_ucode *ucode;
+
+	if (eng_grp->mirror.is_ena)
+		ucode = &eng_grp->g->grp[eng_grp->mirror.idx].ucode[0];
+	else
+		ucode = &eng_grp->ucode[0];
+	WARN_ON(!eng_grp->engs[0].type);
+	eng_grp->engs[0].ucode = ucode;
+
+	if (eng_grp->engs[1].type) {
+		if (is_2nd_ucode_used(eng_grp))
+			eng_grp->engs[1].ucode = &eng_grp->ucode[1];
+		else
+			eng_grp->engs[1].ucode = ucode;
+	}
+}
+
+static int create_engine_group(struct device *dev,
+			       struct otx2_cpt_eng_grps *eng_grps,
+			       struct otx2_cpt_engines *engs, int ucodes_cnt,
+			       void *ucode_data[], int is_print)
+{
+	struct otx2_cpt_eng_grp_info *mirrored_eng_grp;
+	struct otx2_cpt_eng_grp_info *eng_grp;
+	struct otx2_cpt_uc_info_t *uc_info;
+	int i, ret = 0;
+
+	/* Find engine group which is not used */
+	eng_grp = find_unused_eng_grp(eng_grps);
+	if (!eng_grp) {
+		dev_err(dev, "Error all engine groups are being used\n");
+		return -ENOSPC;
+	}
+	/* Load ucode */
+	for (i = 0; i < ucodes_cnt; i++) {
+		uc_info = (struct otx2_cpt_uc_info_t *) ucode_data[i];
+		eng_grp->ucode[i] = uc_info->ucode;
+		ret = copy_ucode_to_dma_mem(dev, &eng_grp->ucode[i],
+					    uc_info->fw->data);
+		if (ret)
+			goto unload_ucode;
+	}
+
+	/* Check if this group mirrors another existing engine group */
+	mirrored_eng_grp = find_mirrored_eng_grp(eng_grp);
+	if (mirrored_eng_grp) {
+		/* Setup mirroring */
+		setup_eng_grp_mirroring(eng_grp, mirrored_eng_grp);
+
+		/*
+		 * Update count of requested engines because some
+		 * of them might be shared with mirrored group
+		 */
+		update_requested_engs(mirrored_eng_grp, engs, ucodes_cnt);
+	}
+	ret = reserve_engines(dev, eng_grp, engs, ucodes_cnt);
+	if (ret)
+		goto unload_ucode;
+
+	/* Update ucode pointers used by engines */
+	update_ucode_ptrs(eng_grp);
+
+	/* Update engine masks used by this group */
+	ret = eng_grp_update_masks(dev, eng_grp);
+	if (ret)
+		goto release_engs;
+
+	/* Enable engine group */
+	ret = enable_eng_grp(eng_grp, eng_grps->obj);
+	if (ret)
+		goto release_engs;
+
+	/*
+	 * If this engine group mirrors another engine group
+	 * then we need to unload ucode as we will use ucode
+	 * from mirrored engine group
+	 */
+	if (eng_grp->mirror.is_ena)
+		ucode_unload(dev, &eng_grp->ucode[0]);
+
+	eng_grp->is_enabled = true;
+
+	if (!is_print)
+		return 0;
+
+	if (mirrored_eng_grp)
+		dev_info(dev,
+			 "Engine_group%d: reuse microcode %s from group %d\n",
+			 eng_grp->idx, mirrored_eng_grp->ucode[0].ver_str,
+			 mirrored_eng_grp->idx);
+	else
+		dev_info(dev, "Engine_group%d: microcode loaded %s\n",
+			 eng_grp->idx, eng_grp->ucode[0].ver_str);
+	if (is_2nd_ucode_used(eng_grp))
+		dev_info(dev, "Engine_group%d: microcode loaded %s\n",
+			 eng_grp->idx, eng_grp->ucode[1].ver_str);
+
+	return 0;
+
+release_engs:
+	release_engines(dev, eng_grp);
+unload_ucode:
+	ucode_unload(dev, &eng_grp->ucode[0]);
+	ucode_unload(dev, &eng_grp->ucode[1]);
+	return ret;
+}
+
+static void delete_engine_grps(struct pci_dev *pdev,
+			       struct otx2_cpt_eng_grps *eng_grps)
+{
+	int i;
+
+	/* First delete all mirroring engine groups */
+	for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++)
+		if (eng_grps->grp[i].mirror.is_ena)
+			delete_engine_group(&pdev->dev, &eng_grps->grp[i]);
+
+	/* Delete remaining engine groups */
+	for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++)
+		delete_engine_group(&pdev->dev, &eng_grps->grp[i]);
+}
+
+int otx2_cpt_get_eng_grp(struct otx2_cpt_eng_grps *eng_grps, int eng_type)
+{
+
+	int eng_grp_num = OTX2_CPT_INVALID_CRYPTO_ENG_GRP;
+	struct otx2_cpt_eng_grp_info *grp;
+	int i;
+
+	for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) {
+		grp = &eng_grps->grp[i];
+		if (!grp->is_enabled)
+			continue;
+
+		if (eng_type == OTX2_CPT_SE_TYPES) {
+			if (eng_grp_has_eng_type(grp, eng_type) &&
+			    !eng_grp_has_eng_type(grp, OTX2_CPT_IE_TYPES)) {
+				eng_grp_num = i;
+				break;
+			}
+		} else {
+			if (eng_grp_has_eng_type(grp, eng_type)) {
+				eng_grp_num = i;
+				break;
+			}
+		}
+	}
+	return eng_grp_num;
+}
+
+int otx2_cpt_create_eng_grps(struct pci_dev *pdev,
+			     struct otx2_cpt_eng_grps *eng_grps)
+{
+	struct otx2_cpt_uc_info_t *uc_info[OTX2_CPT_MAX_ETYPES_PER_GRP] = {  };
+	struct otx2_cpt_engines engs[OTX2_CPT_MAX_ETYPES_PER_GRP] = { {0} };
+	struct fw_info_t fw_info;
+	int ret;
+
+	/*
+	 * We don't create engine groups if it was already
+	 * made (when user enabled VFs for the first time)
+	 */
+	if (eng_grps->is_grps_created)
+		return 0;
+
+	ret = cpt_ucode_load_fw(pdev, &fw_info);
+	if (ret)
+		return ret;
+
+	/*
+	 * Create engine group with SE engines for kernel
+	 * crypto functionality (symmetric crypto)
+	 */
+	uc_info[0] = get_ucode(&fw_info, OTX2_CPT_SE_TYPES);
+	if (uc_info[0] == NULL) {
+		dev_err(&pdev->dev, "Unable to find firmware for SE\n");
+		ret = -EINVAL;
+		goto release_fw;
+	}
+	engs[0].type = OTX2_CPT_SE_TYPES;
+	engs[0].count = eng_grps->avail.max_se_cnt;
+
+	ret = create_engine_group(&pdev->dev, eng_grps, engs, 1,
+				  (void **) uc_info, 1);
+	if (ret)
+		goto release_fw;
+
+	/*
+	 * Create engine group with SE+IE engines for IPSec.
+	 * All SE engines will be shared with engine group 0.
+	 */
+	uc_info[0] = get_ucode(&fw_info, OTX2_CPT_SE_TYPES);
+	uc_info[1] = get_ucode(&fw_info, OTX2_CPT_IE_TYPES);
+
+	if (uc_info[1] == NULL) {
+		dev_err(&pdev->dev, "Unable to find firmware for IE");
+		ret = -EINVAL;
+		goto delete_eng_grp;
+	}
+	engs[0].type = OTX2_CPT_SE_TYPES;
+	engs[0].count = eng_grps->avail.max_se_cnt;
+	engs[1].type = OTX2_CPT_IE_TYPES;
+	engs[1].count = eng_grps->avail.max_ie_cnt;
+
+	ret = create_engine_group(&pdev->dev, eng_grps, engs, 2,
+				  (void **) uc_info, 1);
+	if (ret)
+		goto delete_eng_grp;
+
+	/*
+	 * Create engine group with AE engines for asymmetric
+	 * crypto functionality.
+	 */
+	uc_info[0] = get_ucode(&fw_info, OTX2_CPT_AE_TYPES);
+	if (uc_info[0] == NULL) {
+		dev_err(&pdev->dev, "Unable to find firmware for AE");
+		ret = -EINVAL;
+		goto delete_eng_grp;
+	}
+	engs[0].type = OTX2_CPT_AE_TYPES;
+	engs[0].count = eng_grps->avail.max_ae_cnt;
+
+	ret = create_engine_group(&pdev->dev, eng_grps, engs, 1,
+				  (void **) uc_info, 1);
+	if (ret)
+		goto delete_eng_grp;
+
+	eng_grps->is_grps_created = true;
+
+	cpt_ucode_release_fw(&fw_info);
+	return 0;
+
+delete_eng_grp:
+	delete_engine_grps(pdev, eng_grps);
+release_fw:
+	cpt_ucode_release_fw(&fw_info);
+	return ret;
+}
+
+int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf)
+{
+	int i, ret, busy, total_cores;
+	int timeout = 10;
+	u64 reg = 0;
+
+	total_cores = cptpf->eng_grps.avail.max_se_cnt +
+		      cptpf->eng_grps.avail.max_ie_cnt +
+		      cptpf->eng_grps.avail.max_ae_cnt;
+
+	/* Disengage the cores from groups */
+	for (i = 0; i < total_cores; i++) {
+		ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+						CPT_AF_EXEX_CTL2(i), 0x0);
+		if (ret)
+			return ret;
+
+		cptpf->eng_grps.eng_ref_cnt[i] = 0;
+	}
+	ret = otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev);
+	if (ret)
+		return ret;
+
+	/* Wait for cores to become idle */
+	do {
+		busy = 0;
+		usleep_range(10000, 20000);
+		if (timeout-- < 0)
+			return -EBUSY;
+
+		for (i = 0; i < total_cores; i++) {
+			ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox,
+						   cptpf->pdev,
+						   CPT_AF_EXEX_STS(i), &reg);
+			if (ret)
+				return ret;
+
+			if (reg & 0x1) {
+				busy = 1;
+				break;
+			}
+		}
+	} while (busy);
+
+	/* Disable the cores */
+	for (i = 0; i < total_cores; i++) {
+		ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+						CPT_AF_EXEX_CTL(i), 0x0);
+		if (ret)
+			return ret;
+	}
+	return otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev);
+}
+
+void otx2_cpt_cleanup_eng_grps(struct pci_dev *pdev,
+			       struct otx2_cpt_eng_grps *eng_grps)
+{
+	struct otx2_cpt_eng_grp_info *grp;
+	int i, j;
+
+	delete_engine_grps(pdev, eng_grps);
+	/* Release memory */
+	for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) {
+		grp = &eng_grps->grp[i];
+		for (j = 0; j < OTX2_CPT_MAX_ETYPES_PER_GRP; j++) {
+			kfree(grp->engs[j].bmap);
+			grp->engs[j].bmap = NULL;
+		}
+	}
+}
+
+int otx2_cpt_init_eng_grps(struct pci_dev *pdev,
+			   struct otx2_cpt_eng_grps *eng_grps)
+{
+	struct otx2_cpt_eng_grp_info *grp;
+	int i, j, ret;
+
+	eng_grps->obj = pci_get_drvdata(pdev);
+	eng_grps->avail.se_cnt = eng_grps->avail.max_se_cnt;
+	eng_grps->avail.ie_cnt = eng_grps->avail.max_ie_cnt;
+	eng_grps->avail.ae_cnt = eng_grps->avail.max_ae_cnt;
+
+	eng_grps->engs_num = eng_grps->avail.max_se_cnt +
+			     eng_grps->avail.max_ie_cnt +
+			     eng_grps->avail.max_ae_cnt;
+	if (eng_grps->engs_num > OTX2_CPT_MAX_ENGINES) {
+		dev_err(&pdev->dev,
+			"Number of engines %d > than max supported %d\n",
+			eng_grps->engs_num, OTX2_CPT_MAX_ENGINES);
+		ret = -EINVAL;
+		goto cleanup_eng_grps;
+	}
+
+	for (i = 0; i < OTX2_CPT_MAX_ENGINE_GROUPS; i++) {
+		grp = &eng_grps->grp[i];
+		grp->g = eng_grps;
+		grp->idx = i;
+
+		for (j = 0; j < OTX2_CPT_MAX_ETYPES_PER_GRP; j++) {
+			grp->engs[j].bmap =
+				kcalloc(BITS_TO_LONGS(eng_grps->engs_num),
+					sizeof(long), GFP_KERNEL);
+			if (!grp->engs[j].bmap) {
+				ret = -ENOMEM;
+				goto cleanup_eng_grps;
+			}
+		}
+	}
+	return 0;
+
+cleanup_eng_grps:
+	otx2_cpt_cleanup_eng_grps(pdev, eng_grps);
+	return ret;
+}
+
+static int create_eng_caps_discovery_grps(struct pci_dev *pdev,
+					  struct otx2_cpt_eng_grps *eng_grps)
+{
+	struct otx2_cpt_uc_info_t *uc_info[OTX2_CPT_MAX_ETYPES_PER_GRP] = {  };
+	struct otx2_cpt_engines engs[OTX2_CPT_MAX_ETYPES_PER_GRP] = { {0} };
+	struct fw_info_t fw_info;
+	int ret;
+
+	ret = cpt_ucode_load_fw(pdev, &fw_info);
+	if (ret)
+		return ret;
+
+	uc_info[0] = get_ucode(&fw_info, OTX2_CPT_SE_TYPES);
+	if (uc_info[0] == NULL) {
+		dev_err(&pdev->dev, "Unable to find firmware for AE\n");
+		ret = -EINVAL;
+		goto release_fw;
+	}
+	engs[0].type = OTX2_CPT_AE_TYPES;
+	engs[0].count = 2;
+
+	ret = create_engine_group(&pdev->dev, eng_grps, engs, 1,
+				  (void **) uc_info, 0);
+	if (ret)
+		goto release_fw;
+
+	uc_info[0] = get_ucode(&fw_info, OTX2_CPT_SE_TYPES);
+	if (uc_info[0] == NULL) {
+		dev_err(&pdev->dev, "Unable to find firmware for SE\n");
+		ret = -EINVAL;
+		goto delete_eng_grp;
+	}
+	engs[0].type = OTX2_CPT_SE_TYPES;
+	engs[0].count = 2;
+
+	ret = create_engine_group(&pdev->dev, eng_grps, engs, 1,
+				  (void **) uc_info, 0);
+	if (ret)
+		goto delete_eng_grp;
+
+	uc_info[0] = get_ucode(&fw_info, OTX2_CPT_IE_TYPES);
+	if (uc_info[0] == NULL) {
+		dev_err(&pdev->dev, "Unable to find firmware for IE\n");
+		ret = -EINVAL;
+		goto delete_eng_grp;
+	}
+	engs[0].type = OTX2_CPT_IE_TYPES;
+	engs[0].count = 2;
+
+	ret = create_engine_group(&pdev->dev, eng_grps, engs, 1,
+				  (void **) uc_info, 0);
+	if (ret)
+		goto delete_eng_grp;
+
+	cpt_ucode_release_fw(&fw_info);
+	return 0;
+
+delete_eng_grp:
+	delete_engine_grps(pdev, eng_grps);
+release_fw:
+	cpt_ucode_release_fw(&fw_info);
+	return ret;
+}
+
+/*
+ * Get CPT HW capabilities using LOAD_FVC operation.
+ */
+int otx2_cpt_discover_eng_capabilities(struct otx2_cptpf_dev *cptpf)
+{
+	struct otx2_cptlfs_info *lfs = &cptpf->lfs;
+	struct otx2_cpt_iq_command iq_cmd;
+	union otx2_cpt_opcode opcode;
+	union otx2_cpt_res_s *result;
+	union otx2_cpt_inst_s inst;
+	dma_addr_t rptr_baddr;
+	struct pci_dev *pdev;
+	u32 len, compl_rlen;
+	int ret, etype;
+	void *rptr;
+
+	/*
+	 * We don't get capabilities if it was already done
+	 * (when user enabled VFs for the first time)
+	 */
+	if (cptpf->is_eng_caps_discovered)
+		return 0;
+
+	pdev = cptpf->pdev;
+	/*
+	 * Create engine groups for each type to submit LOAD_FVC op and
+	 * get engine's capabilities.
+	 */
+	ret = create_eng_caps_discovery_grps(pdev, &cptpf->eng_grps);
+	if (ret)
+		goto delete_grps;
+
+	lfs->pdev = pdev;
+	lfs->reg_base = cptpf->reg_base;
+	lfs->mbox = &cptpf->afpf_mbox;
+	ret = otx2_cptlf_init(&cptpf->lfs, OTX2_CPT_ALL_ENG_GRPS_MASK,
+			      OTX2_CPT_QUEUE_HI_PRIO, 1);
+	if (ret)
+		goto delete_grps;
+
+	compl_rlen = ALIGN(sizeof(union otx2_cpt_res_s), OTX2_CPT_DMA_MINALIGN);
+	len = compl_rlen + LOADFVC_RLEN;
+
+	result = kzalloc(len, GFP_KERNEL);
+	if (!result) {
+		ret = -ENOMEM;
+		goto lf_cleanup;
+	}
+	rptr_baddr = dma_map_single(&pdev->dev, (void *)result, len,
+				    DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(&pdev->dev, rptr_baddr)) {
+		dev_err(&pdev->dev, "DMA mapping failed\n");
+		ret = -EFAULT;
+		goto free_result;
+	}
+	rptr = (u8 *)result + compl_rlen;
+
+	/* Fill in the command */
+	opcode.s.major = LOADFVC_MAJOR_OP;
+	opcode.s.minor = LOADFVC_MINOR_OP;
+
+	iq_cmd.cmd.u = 0;
+	iq_cmd.cmd.s.opcode = cpu_to_be16(opcode.flags);
+
+	/* 64-bit swap for microcode data reads, not needed for addresses */
+	cpu_to_be64s(&iq_cmd.cmd.u);
+	iq_cmd.dptr = 0;
+	iq_cmd.rptr = rptr_baddr + compl_rlen;
+	iq_cmd.cptr.u = 0;
+
+	for (etype = 1; etype < OTX2_CPT_MAX_ENG_TYPES; etype++) {
+		result->s.compcode = OTX2_CPT_COMPLETION_CODE_INIT;
+		iq_cmd.cptr.s.grp = otx2_cpt_get_eng_grp(&cptpf->eng_grps,
+							 etype);
+		otx2_cpt_fill_inst(&inst, &iq_cmd, rptr_baddr);
+		otx2_cpt_send_cmd(&inst, 1, &cptpf->lfs.lf[0]);
+
+		while (result->s.compcode == OTX2_CPT_COMPLETION_CODE_INIT)
+			cpu_relax();
+
+		cptpf->eng_caps[etype].u = be64_to_cpup(rptr);
+	}
+	dma_unmap_single(&pdev->dev, rptr_baddr, len, DMA_BIDIRECTIONAL);
+	cptpf->is_eng_caps_discovered = true;
+
+free_result:
+	kfree(result);
+lf_cleanup:
+	otx2_cptlf_shutdown(&cptpf->lfs);
+delete_grps:
+	delete_engine_grps(pdev, &cptpf->eng_grps);
+
+	return ret;
+}
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h
new file mode 100644
index 000000000000..6b0d432de0af
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.h
@@ -0,0 +1,162 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPTPF_UCODE_H
+#define __OTX2_CPTPF_UCODE_H
+
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include "otx2_cpt_hw_types.h"
+#include "otx2_cpt_common.h"
+
+/*
+ * On OcteonTX2 platform IPSec ucode can use both IE and SE engines therefore
+ * IE and SE engines can be attached to the same engine group.
+ */
+#define OTX2_CPT_MAX_ETYPES_PER_GRP 2
+
+/* CPT ucode signature size */
+#define OTX2_CPT_UCODE_SIGN_LEN     256
+
+/* Microcode version string length */
+#define OTX2_CPT_UCODE_VER_STR_SZ   44
+
+/* Maximum number of supported engines/cores on OcteonTX2 platform */
+#define OTX2_CPT_MAX_ENGINES        128
+
+#define OTX2_CPT_ENGS_BITMASK_LEN   BITS_TO_LONGS(OTX2_CPT_MAX_ENGINES)
+
+/* Microcode types */
+enum otx2_cpt_ucode_type {
+	OTX2_CPT_AE_UC_TYPE = 1,  /* AE-MAIN */
+	OTX2_CPT_SE_UC_TYPE1 = 20,/* SE-MAIN - combination of 21 and 22 */
+	OTX2_CPT_SE_UC_TYPE2 = 21,/* Fast Path IPSec + AirCrypto */
+	OTX2_CPT_SE_UC_TYPE3 = 22,/*
+				   * Hash + HMAC + FlexiCrypto + RNG +
+				   * Full Feature IPSec + AirCrypto + Kasumi
+				   */
+	OTX2_CPT_IE_UC_TYPE1 = 30, /* IE-MAIN - combination of 31 and 32 */
+	OTX2_CPT_IE_UC_TYPE2 = 31, /* Fast Path IPSec */
+	OTX2_CPT_IE_UC_TYPE3 = 32, /*
+				    * Hash + HMAC + FlexiCrypto + RNG +
+				    * Full Future IPSec
+				    */
+};
+
+struct otx2_cpt_bitmap {
+	unsigned long bits[OTX2_CPT_ENGS_BITMASK_LEN];
+	int size;
+};
+
+struct otx2_cpt_engines {
+	int type;
+	int count;
+};
+
+/* Microcode version number */
+struct otx2_cpt_ucode_ver_num {
+	u8 nn;
+	u8 xx;
+	u8 yy;
+	u8 zz;
+};
+
+struct otx2_cpt_ucode_hdr {
+	struct otx2_cpt_ucode_ver_num ver_num;
+	u8 ver_str[OTX2_CPT_UCODE_VER_STR_SZ];
+	__be32 code_length;
+	u32 padding[3];
+};
+
+struct otx2_cpt_ucode {
+	u8 ver_str[OTX2_CPT_UCODE_VER_STR_SZ];/*
+					       * ucode version in readable
+					       * format
+					       */
+	struct otx2_cpt_ucode_ver_num ver_num;/* ucode version number */
+	char filename[OTX2_CPT_NAME_LENGTH];/* ucode filename */
+	dma_addr_t dma;		/* phys address of ucode image */
+	void *va;		/* virt address of ucode image */
+	u32 size;		/* ucode image size */
+	int type;		/* ucode image type SE, IE, AE or SE+IE */
+};
+
+struct otx2_cpt_uc_info_t {
+	struct list_head list;
+	struct otx2_cpt_ucode ucode;/* microcode information */
+	const struct firmware *fw;
+};
+
+/* Maximum and current number of engines available for all engine groups */
+struct otx2_cpt_engs_available {
+	int max_se_cnt;
+	int max_ie_cnt;
+	int max_ae_cnt;
+	int se_cnt;
+	int ie_cnt;
+	int ae_cnt;
+};
+
+/* Engines reserved to an engine group */
+struct otx2_cpt_engs_rsvd {
+	int type;	/* engine type */
+	int count;	/* number of engines attached */
+	int offset;     /* constant offset of engine type in the bitmap */
+	unsigned long *bmap;		/* attached engines bitmap */
+	struct otx2_cpt_ucode *ucode;	/* ucode used by these engines */
+};
+
+struct otx2_cpt_mirror_info {
+	int is_ena;	/*
+			 * is mirroring enabled, it is set only for engine
+			 * group which mirrors another engine group
+			 */
+	int idx;	/*
+			 * index of engine group which is mirrored by this
+			 * group, set only for engine group which mirrors
+			 * another group
+			 */
+	int ref_count;	/*
+			 * number of times this engine group is mirrored by
+			 * other groups, this is set only for engine group
+			 * which is mirrored by other group(s)
+			 */
+};
+
+struct otx2_cpt_eng_grp_info {
+	struct otx2_cpt_eng_grps *g; /* pointer to engine_groups structure */
+	/* engines attached */
+	struct otx2_cpt_engs_rsvd engs[OTX2_CPT_MAX_ETYPES_PER_GRP];
+	/* ucodes information */
+	struct otx2_cpt_ucode ucode[OTX2_CPT_MAX_ETYPES_PER_GRP];
+	/* engine group mirroring information */
+	struct otx2_cpt_mirror_info mirror;
+	int idx;	 /* engine group index */
+	bool is_enabled; /*
+			  * is engine group enabled, engine group is enabled
+			  * when it has engines attached and ucode loaded
+			  */
+};
+
+struct otx2_cpt_eng_grps {
+	struct otx2_cpt_eng_grp_info grp[OTX2_CPT_MAX_ENGINE_GROUPS];
+	struct otx2_cpt_engs_available avail;
+	void *obj;			/* device specific data */
+	int engs_num;			/* total number of engines supported */
+	u8 eng_ref_cnt[OTX2_CPT_MAX_ENGINES];/* engines reference count */
+	bool is_grps_created; /* Is the engine groups are already created */
+};
+struct otx2_cptpf_dev;
+int otx2_cpt_init_eng_grps(struct pci_dev *pdev,
+			   struct otx2_cpt_eng_grps *eng_grps);
+void otx2_cpt_cleanup_eng_grps(struct pci_dev *pdev,
+			       struct otx2_cpt_eng_grps *eng_grps);
+int otx2_cpt_create_eng_grps(struct pci_dev *pdev,
+			     struct otx2_cpt_eng_grps *eng_grps);
+int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf);
+int otx2_cpt_get_eng_grp(struct otx2_cpt_eng_grps *eng_grps, int eng_type);
+int otx2_cpt_discover_eng_capabilities(struct otx2_cptpf_dev *cptpf);
+
+#endif /* __OTX2_CPTPF_UCODE_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf.h b/drivers/crypto/marvell/octeontx2/otx2_cptvf.h
new file mode 100644
index 000000000000..4f0a169fddbd
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPTVF_H
+#define __OTX2_CPTVF_H
+
+#include "mbox.h"
+#include "otx2_cptlf.h"
+
+struct otx2_cptvf_dev {
+	void __iomem *reg_base;		/* Register start address */
+	void __iomem *pfvf_mbox_base;	/* PF-VF mbox start address */
+	struct pci_dev *pdev;		/* PCI device handle */
+	struct otx2_cptlfs_info lfs;	/* CPT LFs attached to this VF */
+	u8 vf_id;			/* Virtual function index */
+
+	/* PF <=> VF mbox */
+	struct otx2_mbox	pfvf_mbox;
+	struct work_struct	pfvf_mbox_work;
+	struct workqueue_struct *pfvf_mbox_wq;
+};
+
+irqreturn_t otx2_cptvf_pfvf_mbox_intr(int irq, void *arg);
+void otx2_cptvf_pfvf_mbox_handler(struct work_struct *work);
+int otx2_cptvf_send_eng_grp_num_msg(struct otx2_cptvf_dev *cptvf, int eng_type);
+int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf);
+
+#endif /* __OTX2_CPTVF_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c
new file mode 100644
index 000000000000..a72723455df7
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.c
@@ -0,0 +1,1758 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include <crypto/aes.h>
+#include <crypto/authenc.h>
+#include <crypto/cryptd.h>
+#include <crypto/des.h>
+#include <crypto/internal/aead.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
+#include <crypto/xts.h>
+#include <crypto/gcm.h>
+#include <crypto/scatterwalk.h>
+#include <linux/rtnetlink.h>
+#include <linux/sort.h>
+#include <linux/module.h>
+#include "otx2_cptvf.h"
+#include "otx2_cptvf_algs.h"
+#include "otx2_cpt_reqmgr.h"
+
+/* Size of salt in AES GCM mode */
+#define AES_GCM_SALT_SIZE 4
+/* Size of IV in AES GCM mode */
+#define AES_GCM_IV_SIZE 8
+/* Size of ICV (Integrity Check Value) in AES GCM mode */
+#define AES_GCM_ICV_SIZE 16
+/* Offset of IV in AES GCM mode */
+#define AES_GCM_IV_OFFSET 8
+#define CONTROL_WORD_LEN 8
+#define KEY2_OFFSET 48
+#define DMA_MODE_FLAG(dma_mode) \
+	(((dma_mode) == OTX2_CPT_DMA_MODE_SG) ? (1 << 7) : 0)
+
+/* Truncated SHA digest size */
+#define SHA1_TRUNC_DIGEST_SIZE 12
+#define SHA256_TRUNC_DIGEST_SIZE 16
+#define SHA384_TRUNC_DIGEST_SIZE 24
+#define SHA512_TRUNC_DIGEST_SIZE 32
+
+static DEFINE_MUTEX(mutex);
+static int is_crypto_registered;
+
+struct cpt_device_desc {
+	struct pci_dev *dev;
+	int num_queues;
+};
+
+struct cpt_device_table {
+	atomic_t count;
+	struct cpt_device_desc desc[OTX2_CPT_MAX_LFS_NUM];
+};
+
+static struct cpt_device_table se_devices = {
+	.count = ATOMIC_INIT(0)
+};
+
+static inline int get_se_device(struct pci_dev **pdev, int *cpu_num)
+{
+	int count;
+
+	count = atomic_read(&se_devices.count);
+	if (count < 1)
+		return -ENODEV;
+
+	*cpu_num = get_cpu();
+	/*
+	 * On OcteonTX2 platform CPT instruction queue is bound to each
+	 * local function LF, in turn LFs can be attached to PF
+	 * or VF therefore we always use first device. We get maximum
+	 * performance if one CPT queue is available for each cpu
+	 * otherwise CPT queues need to be shared between cpus.
+	 */
+	if (*cpu_num >= se_devices.desc[0].num_queues)
+		*cpu_num %= se_devices.desc[0].num_queues;
+	*pdev = se_devices.desc[0].dev;
+
+	put_cpu();
+
+	return 0;
+}
+
+static inline int validate_hmac_cipher_null(struct otx2_cpt_req_info *cpt_req)
+{
+	struct otx2_cpt_req_ctx *rctx;
+	struct aead_request *req;
+	struct crypto_aead *tfm;
+
+	req = container_of(cpt_req->areq, struct aead_request, base);
+	tfm = crypto_aead_reqtfm(req);
+	rctx = aead_request_ctx(req);
+	if (memcmp(rctx->fctx.hmac.s.hmac_calc,
+		   rctx->fctx.hmac.s.hmac_recv,
+		   crypto_aead_authsize(tfm)) != 0)
+		return -EBADMSG;
+
+	return 0;
+}
+
+static void otx2_cpt_aead_callback(int status, void *arg1, void *arg2)
+{
+	struct otx2_cpt_inst_info *inst_info = arg2;
+	struct crypto_async_request *areq = arg1;
+	struct otx2_cpt_req_info *cpt_req;
+	struct pci_dev *pdev;
+
+	if (inst_info) {
+		cpt_req = inst_info->req;
+		if (!status) {
+			/*
+			 * When selected cipher is NULL we need to manually
+			 * verify whether calculated hmac value matches
+			 * received hmac value
+			 */
+			if (cpt_req->req_type ==
+			    OTX2_CPT_AEAD_ENC_DEC_NULL_REQ &&
+			    !cpt_req->is_enc)
+				status = validate_hmac_cipher_null(cpt_req);
+		}
+		pdev = inst_info->pdev;
+		otx2_cpt_info_destroy(pdev, inst_info);
+	}
+	if (areq)
+		areq->complete(areq, status);
+}
+
+static void output_iv_copyback(struct crypto_async_request *areq)
+{
+	struct otx2_cpt_req_info *req_info;
+	struct otx2_cpt_req_ctx *rctx;
+	struct skcipher_request *sreq;
+	struct crypto_skcipher *stfm;
+	struct otx2_cpt_enc_ctx *ctx;
+	u32 start, ivsize;
+
+	sreq = container_of(areq, struct skcipher_request, base);
+	stfm = crypto_skcipher_reqtfm(sreq);
+	ctx = crypto_skcipher_ctx(stfm);
+	if (ctx->cipher_type == OTX2_CPT_AES_CBC ||
+	    ctx->cipher_type == OTX2_CPT_DES3_CBC) {
+		rctx = skcipher_request_ctx(sreq);
+		req_info = &rctx->cpt_req;
+		ivsize = crypto_skcipher_ivsize(stfm);
+		start = sreq->cryptlen - ivsize;
+
+		if (req_info->is_enc) {
+			scatterwalk_map_and_copy(sreq->iv, sreq->dst, start,
+						 ivsize, 0);
+		} else {
+			if (sreq->src != sreq->dst) {
+				scatterwalk_map_and_copy(sreq->iv, sreq->src,
+							 start, ivsize, 0);
+			} else {
+				memcpy(sreq->iv, req_info->iv_out, ivsize);
+				kfree(req_info->iv_out);
+			}
+		}
+	}
+}
+
+static void otx2_cpt_skcipher_callback(int status, void *arg1, void *arg2)
+{
+	struct otx2_cpt_inst_info *inst_info = arg2;
+	struct crypto_async_request *areq = arg1;
+	struct pci_dev *pdev;
+
+	if (areq) {
+		if (!status)
+			output_iv_copyback(areq);
+		if (inst_info) {
+			pdev = inst_info->pdev;
+			otx2_cpt_info_destroy(pdev, inst_info);
+		}
+		areq->complete(areq, status);
+	}
+}
+
+static inline void update_input_data(struct otx2_cpt_req_info *req_info,
+				     struct scatterlist *inp_sg,
+				     u32 nbytes, u32 *argcnt)
+{
+	req_info->req.dlen += nbytes;
+
+	while (nbytes) {
+		u32 len = (nbytes < inp_sg->length) ? nbytes : inp_sg->length;
+		u8 *ptr = sg_virt(inp_sg);
+
+		req_info->in[*argcnt].vptr = (void *)ptr;
+		req_info->in[*argcnt].size = len;
+		nbytes -= len;
+		++(*argcnt);
+		inp_sg = sg_next(inp_sg);
+	}
+}
+
+static inline void update_output_data(struct otx2_cpt_req_info *req_info,
+				      struct scatterlist *outp_sg,
+				      u32 offset, u32 nbytes, u32 *argcnt)
+{
+	u32 len, sg_len;
+	u8 *ptr;
+
+	req_info->rlen += nbytes;
+
+	while (nbytes) {
+		sg_len = outp_sg->length - offset;
+		len = (nbytes < sg_len) ? nbytes : sg_len;
+		ptr = sg_virt(outp_sg);
+
+		req_info->out[*argcnt].vptr = (void *) (ptr + offset);
+		req_info->out[*argcnt].size = len;
+		nbytes -= len;
+		++(*argcnt);
+		offset = 0;
+		outp_sg = sg_next(outp_sg);
+	}
+}
+
+static inline int create_ctx_hdr(struct skcipher_request *req, u32 enc,
+				 u32 *argcnt)
+{
+	struct crypto_skcipher *stfm = crypto_skcipher_reqtfm(req);
+	struct otx2_cpt_req_ctx *rctx = skcipher_request_ctx(req);
+	struct otx2_cpt_enc_ctx *ctx = crypto_skcipher_ctx(stfm);
+	struct otx2_cpt_req_info *req_info = &rctx->cpt_req;
+	struct otx2_cpt_fc_ctx *fctx = &rctx->fctx;
+	int ivsize = crypto_skcipher_ivsize(stfm);
+	u32 start = req->cryptlen - ivsize;
+	gfp_t flags;
+
+	flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+			GFP_KERNEL : GFP_ATOMIC;
+	req_info->ctrl.s.dma_mode = OTX2_CPT_DMA_MODE_SG;
+	req_info->ctrl.s.se_req = 1;
+
+	req_info->req.opcode.s.major = OTX2_CPT_MAJOR_OP_FC |
+				DMA_MODE_FLAG(OTX2_CPT_DMA_MODE_SG);
+	if (enc) {
+		req_info->req.opcode.s.minor = 2;
+	} else {
+		req_info->req.opcode.s.minor = 3;
+		if ((ctx->cipher_type == OTX2_CPT_AES_CBC ||
+		    ctx->cipher_type == OTX2_CPT_DES3_CBC) &&
+		    req->src == req->dst) {
+			req_info->iv_out = kmalloc(ivsize, flags);
+			if (!req_info->iv_out)
+				return -ENOMEM;
+
+			scatterwalk_map_and_copy(req_info->iv_out, req->src,
+						 start, ivsize, 0);
+		}
+	}
+	/* Encryption data length */
+	req_info->req.param1 = req->cryptlen;
+	/* Authentication data length */
+	req_info->req.param2 = 0;
+
+	fctx->enc.enc_ctrl.e.enc_cipher = ctx->cipher_type;
+	fctx->enc.enc_ctrl.e.aes_key = ctx->key_type;
+	fctx->enc.enc_ctrl.e.iv_source = OTX2_CPT_FROM_CPTR;
+
+	if (ctx->cipher_type == OTX2_CPT_AES_XTS)
+		memcpy(fctx->enc.encr_key, ctx->enc_key, ctx->key_len * 2);
+	else
+		memcpy(fctx->enc.encr_key, ctx->enc_key, ctx->key_len);
+
+	memcpy(fctx->enc.encr_iv, req->iv, crypto_skcipher_ivsize(stfm));
+
+	cpu_to_be64s(&fctx->enc.enc_ctrl.u);
+
+	/*
+	 * Storing  Packet Data Information in offset
+	 * Control Word First 8 bytes
+	 */
+	req_info->in[*argcnt].vptr = (u8 *)&rctx->ctrl_word;
+	req_info->in[*argcnt].size = CONTROL_WORD_LEN;
+	req_info->req.dlen += CONTROL_WORD_LEN;
+	++(*argcnt);
+
+	req_info->in[*argcnt].vptr = (u8 *)fctx;
+	req_info->in[*argcnt].size = sizeof(struct otx2_cpt_fc_ctx);
+	req_info->req.dlen += sizeof(struct otx2_cpt_fc_ctx);
+
+	++(*argcnt);
+
+	return 0;
+}
+
+static inline int create_input_list(struct skcipher_request *req, u32 enc,
+				    u32 enc_iv_len)
+{
+	struct otx2_cpt_req_ctx *rctx = skcipher_request_ctx(req);
+	struct otx2_cpt_req_info *req_info = &rctx->cpt_req;
+	u32 argcnt =  0;
+	int ret;
+
+	ret = create_ctx_hdr(req, enc, &argcnt);
+	if (ret)
+		return ret;
+
+	update_input_data(req_info, req->src, req->cryptlen, &argcnt);
+	req_info->in_cnt = argcnt;
+
+	return 0;
+}
+
+static inline void create_output_list(struct skcipher_request *req,
+				      u32 enc_iv_len)
+{
+	struct otx2_cpt_req_ctx *rctx = skcipher_request_ctx(req);
+	struct otx2_cpt_req_info *req_info = &rctx->cpt_req;
+	u32 argcnt = 0;
+
+	/*
+	 * OUTPUT Buffer Processing
+	 * AES encryption/decryption output would be
+	 * received in the following format
+	 *
+	 * ------IV--------|------ENCRYPTED/DECRYPTED DATA-----|
+	 * [ 16 Bytes/     [   Request Enc/Dec/ DATA Len AES CBC ]
+	 */
+	update_output_data(req_info, req->dst, 0, req->cryptlen, &argcnt);
+	req_info->out_cnt = argcnt;
+}
+
+static int skcipher_do_fallback(struct skcipher_request *req, bool is_enc)
+{
+	struct crypto_skcipher *stfm = crypto_skcipher_reqtfm(req);
+	struct otx2_cpt_req_ctx *rctx = skcipher_request_ctx(req);
+	struct otx2_cpt_enc_ctx *ctx = crypto_skcipher_ctx(stfm);
+	int ret;
+
+	if (ctx->fbk_cipher) {
+		skcipher_request_set_tfm(&rctx->sk_fbk_req, ctx->fbk_cipher);
+		skcipher_request_set_callback(&rctx->sk_fbk_req,
+					      req->base.flags,
+					      req->base.complete,
+					      req->base.data);
+		skcipher_request_set_crypt(&rctx->sk_fbk_req, req->src,
+					   req->dst, req->cryptlen, req->iv);
+		ret = is_enc ? crypto_skcipher_encrypt(&rctx->sk_fbk_req) :
+			       crypto_skcipher_decrypt(&rctx->sk_fbk_req);
+	} else {
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static inline int cpt_enc_dec(struct skcipher_request *req, u32 enc)
+{
+	struct crypto_skcipher *stfm = crypto_skcipher_reqtfm(req);
+	struct otx2_cpt_req_ctx *rctx = skcipher_request_ctx(req);
+	struct otx2_cpt_enc_ctx *ctx = crypto_skcipher_ctx(stfm);
+	struct otx2_cpt_req_info *req_info = &rctx->cpt_req;
+	u32 enc_iv_len = crypto_skcipher_ivsize(stfm);
+	struct pci_dev *pdev;
+	int status, cpu_num;
+
+	if (req->cryptlen == 0)
+		return 0;
+
+	if (!IS_ALIGNED(req->cryptlen, ctx->enc_align_len))
+		return -EINVAL;
+
+	if (req->cryptlen > OTX2_CPT_MAX_REQ_SIZE)
+		return skcipher_do_fallback(req, enc);
+
+	/* Clear control words */
+	rctx->ctrl_word.flags = 0;
+	rctx->fctx.enc.enc_ctrl.u = 0;
+
+	status = create_input_list(req, enc, enc_iv_len);
+	if (status)
+		return status;
+	create_output_list(req, enc_iv_len);
+
+	status = get_se_device(&pdev, &cpu_num);
+	if (status)
+		return status;
+
+	req_info->callback = otx2_cpt_skcipher_callback;
+	req_info->areq = &req->base;
+	req_info->req_type = OTX2_CPT_ENC_DEC_REQ;
+	req_info->is_enc = enc;
+	req_info->is_trunc_hmac = false;
+	req_info->ctrl.s.grp = otx2_cpt_get_kcrypto_eng_grp_num(pdev);
+
+	/*
+	 * We perform an asynchronous send and once
+	 * the request is completed the driver would
+	 * intimate through registered call back functions
+	 */
+	status = otx2_cpt_do_request(pdev, req_info, cpu_num);
+
+	return status;
+}
+
+static int otx2_cpt_skcipher_encrypt(struct skcipher_request *req)
+{
+	return cpt_enc_dec(req, true);
+}
+
+static int otx2_cpt_skcipher_decrypt(struct skcipher_request *req)
+{
+	return cpt_enc_dec(req, false);
+}
+
+static int otx2_cpt_skcipher_xts_setkey(struct crypto_skcipher *tfm,
+				       const u8 *key, u32 keylen)
+{
+	struct otx2_cpt_enc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	const u8 *key2 = key + (keylen / 2);
+	const u8 *key1 = key;
+	int ret;
+
+	ret = xts_check_key(crypto_skcipher_tfm(tfm), key, keylen);
+	if (ret)
+		return ret;
+	ctx->key_len = keylen;
+	ctx->enc_align_len = 1;
+	memcpy(ctx->enc_key, key1, keylen / 2);
+	memcpy(ctx->enc_key + KEY2_OFFSET, key2, keylen / 2);
+	ctx->cipher_type = OTX2_CPT_AES_XTS;
+	switch (ctx->key_len) {
+	case 2 * AES_KEYSIZE_128:
+		ctx->key_type = OTX2_CPT_AES_128_BIT;
+		break;
+	case 2 * AES_KEYSIZE_192:
+		ctx->key_type = OTX2_CPT_AES_192_BIT;
+		break;
+	case 2 * AES_KEYSIZE_256:
+		ctx->key_type = OTX2_CPT_AES_256_BIT;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return crypto_skcipher_setkey(ctx->fbk_cipher, key, keylen);
+}
+
+static int cpt_des_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			  u32 keylen, u8 cipher_type)
+{
+	struct otx2_cpt_enc_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	if (keylen != DES3_EDE_KEY_SIZE)
+		return -EINVAL;
+
+	ctx->key_len = keylen;
+	ctx->cipher_type = cipher_type;
+	ctx->enc_align_len = 8;
+
+	memcpy(ctx->enc_key, key, keylen);
+
+	return crypto_skcipher_setkey(ctx->fbk_cipher, key, keylen);
+}
+
+static int cpt_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			  u32 keylen, u8 cipher_type)
+{
+	struct otx2_cpt_enc_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		ctx->key_type = OTX2_CPT_AES_128_BIT;
+		break;
+	case AES_KEYSIZE_192:
+		ctx->key_type = OTX2_CPT_AES_192_BIT;
+		break;
+	case AES_KEYSIZE_256:
+		ctx->key_type = OTX2_CPT_AES_256_BIT;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (cipher_type == OTX2_CPT_AES_CBC || cipher_type == OTX2_CPT_AES_ECB)
+		ctx->enc_align_len = 16;
+	else
+		ctx->enc_align_len = 1;
+
+	ctx->key_len = keylen;
+	ctx->cipher_type = cipher_type;
+
+	memcpy(ctx->enc_key, key, keylen);
+
+	return crypto_skcipher_setkey(ctx->fbk_cipher, key, keylen);
+}
+
+static int otx2_cpt_skcipher_cbc_aes_setkey(struct crypto_skcipher *tfm,
+					    const u8 *key, u32 keylen)
+{
+	return cpt_aes_setkey(tfm, key, keylen, OTX2_CPT_AES_CBC);
+}
+
+static int otx2_cpt_skcipher_ecb_aes_setkey(struct crypto_skcipher *tfm,
+					    const u8 *key, u32 keylen)
+{
+	return cpt_aes_setkey(tfm, key, keylen, OTX2_CPT_AES_ECB);
+}
+
+static int otx2_cpt_skcipher_cbc_des3_setkey(struct crypto_skcipher *tfm,
+					     const u8 *key, u32 keylen)
+{
+	return cpt_des_setkey(tfm, key, keylen, OTX2_CPT_DES3_CBC);
+}
+
+static int otx2_cpt_skcipher_ecb_des3_setkey(struct crypto_skcipher *tfm,
+					     const u8 *key, u32 keylen)
+{
+	return cpt_des_setkey(tfm, key, keylen, OTX2_CPT_DES3_ECB);
+}
+
+static int cpt_skcipher_fallback_init(struct otx2_cpt_enc_ctx *ctx,
+				      struct crypto_alg *alg)
+{
+	if (alg->cra_flags & CRYPTO_ALG_NEED_FALLBACK) {
+		ctx->fbk_cipher =
+				crypto_alloc_skcipher(alg->cra_name, 0,
+						      CRYPTO_ALG_ASYNC |
+						      CRYPTO_ALG_NEED_FALLBACK);
+		if (IS_ERR(ctx->fbk_cipher)) {
+			pr_err("%s() failed to allocate fallback for %s\n",
+				__func__, alg->cra_name);
+			return PTR_ERR(ctx->fbk_cipher);
+		}
+	}
+	return 0;
+}
+
+static int otx2_cpt_enc_dec_init(struct crypto_skcipher *stfm)
+{
+	struct otx2_cpt_enc_ctx *ctx = crypto_skcipher_ctx(stfm);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(stfm);
+	struct crypto_alg *alg = tfm->__crt_alg;
+
+	memset(ctx, 0, sizeof(*ctx));
+	/*
+	 * Additional memory for skcipher_request is
+	 * allocated since the cryptd daemon uses
+	 * this memory for request_ctx information
+	 */
+	crypto_skcipher_set_reqsize(stfm, sizeof(struct otx2_cpt_req_ctx) +
+					sizeof(struct skcipher_request));
+
+	return cpt_skcipher_fallback_init(ctx, alg);
+}
+
+static void otx2_cpt_skcipher_exit(struct crypto_skcipher *tfm)
+{
+	struct otx2_cpt_enc_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	if (ctx->fbk_cipher) {
+		crypto_free_skcipher(ctx->fbk_cipher);
+		ctx->fbk_cipher = NULL;
+	}
+}
+
+static int cpt_aead_fallback_init(struct otx2_cpt_aead_ctx *ctx,
+				  struct crypto_alg *alg)
+{
+	if (alg->cra_flags & CRYPTO_ALG_NEED_FALLBACK) {
+		ctx->fbk_cipher =
+			    crypto_alloc_aead(alg->cra_name, 0,
+					      CRYPTO_ALG_ASYNC |
+					      CRYPTO_ALG_NEED_FALLBACK);
+		if (IS_ERR(ctx->fbk_cipher)) {
+			pr_err("%s() failed to allocate fallback for %s\n",
+				__func__, alg->cra_name);
+			return PTR_ERR(ctx->fbk_cipher);
+		}
+	}
+	return 0;
+}
+
+static int cpt_aead_init(struct crypto_aead *atfm, u8 cipher_type, u8 mac_type)
+{
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(atfm);
+	struct crypto_tfm *tfm = crypto_aead_tfm(atfm);
+	struct crypto_alg *alg = tfm->__crt_alg;
+
+	ctx->cipher_type = cipher_type;
+	ctx->mac_type = mac_type;
+
+	/*
+	 * When selected cipher is NULL we use HMAC opcode instead of
+	 * FLEXICRYPTO opcode therefore we don't need to use HASH algorithms
+	 * for calculating ipad and opad
+	 */
+	if (ctx->cipher_type != OTX2_CPT_CIPHER_NULL) {
+		switch (ctx->mac_type) {
+		case OTX2_CPT_SHA1:
+			ctx->hashalg = crypto_alloc_shash("sha1", 0,
+							  CRYPTO_ALG_ASYNC);
+			if (IS_ERR(ctx->hashalg))
+				return PTR_ERR(ctx->hashalg);
+			break;
+
+		case OTX2_CPT_SHA256:
+			ctx->hashalg = crypto_alloc_shash("sha256", 0,
+							  CRYPTO_ALG_ASYNC);
+			if (IS_ERR(ctx->hashalg))
+				return PTR_ERR(ctx->hashalg);
+			break;
+
+		case OTX2_CPT_SHA384:
+			ctx->hashalg = crypto_alloc_shash("sha384", 0,
+							  CRYPTO_ALG_ASYNC);
+			if (IS_ERR(ctx->hashalg))
+				return PTR_ERR(ctx->hashalg);
+			break;
+
+		case OTX2_CPT_SHA512:
+			ctx->hashalg = crypto_alloc_shash("sha512", 0,
+							  CRYPTO_ALG_ASYNC);
+			if (IS_ERR(ctx->hashalg))
+				return PTR_ERR(ctx->hashalg);
+			break;
+		}
+	}
+	switch (ctx->cipher_type) {
+	case OTX2_CPT_AES_CBC:
+	case OTX2_CPT_AES_ECB:
+		ctx->enc_align_len = 16;
+		break;
+	case OTX2_CPT_DES3_CBC:
+	case OTX2_CPT_DES3_ECB:
+		ctx->enc_align_len = 8;
+		break;
+	case OTX2_CPT_AES_GCM:
+	case OTX2_CPT_CIPHER_NULL:
+		ctx->enc_align_len = 1;
+		break;
+	}
+	crypto_aead_set_reqsize(atfm, sizeof(struct otx2_cpt_req_ctx));
+
+	return cpt_aead_fallback_init(ctx, alg);
+}
+
+static int otx2_cpt_aead_cbc_aes_sha1_init(struct crypto_aead *tfm)
+{
+	return cpt_aead_init(tfm, OTX2_CPT_AES_CBC, OTX2_CPT_SHA1);
+}
+
+static int otx2_cpt_aead_cbc_aes_sha256_init(struct crypto_aead *tfm)
+{
+	return cpt_aead_init(tfm, OTX2_CPT_AES_CBC, OTX2_CPT_SHA256);
+}
+
+static int otx2_cpt_aead_cbc_aes_sha384_init(struct crypto_aead *tfm)
+{
+	return cpt_aead_init(tfm, OTX2_CPT_AES_CBC, OTX2_CPT_SHA384);
+}
+
+static int otx2_cpt_aead_cbc_aes_sha512_init(struct crypto_aead *tfm)
+{
+	return cpt_aead_init(tfm, OTX2_CPT_AES_CBC, OTX2_CPT_SHA512);
+}
+
+static int otx2_cpt_aead_ecb_null_sha1_init(struct crypto_aead *tfm)
+{
+	return cpt_aead_init(tfm, OTX2_CPT_CIPHER_NULL, OTX2_CPT_SHA1);
+}
+
+static int otx2_cpt_aead_ecb_null_sha256_init(struct crypto_aead *tfm)
+{
+	return cpt_aead_init(tfm, OTX2_CPT_CIPHER_NULL, OTX2_CPT_SHA256);
+}
+
+static int otx2_cpt_aead_ecb_null_sha384_init(struct crypto_aead *tfm)
+{
+	return cpt_aead_init(tfm, OTX2_CPT_CIPHER_NULL, OTX2_CPT_SHA384);
+}
+
+static int otx2_cpt_aead_ecb_null_sha512_init(struct crypto_aead *tfm)
+{
+	return cpt_aead_init(tfm, OTX2_CPT_CIPHER_NULL, OTX2_CPT_SHA512);
+}
+
+static int otx2_cpt_aead_gcm_aes_init(struct crypto_aead *tfm)
+{
+	return cpt_aead_init(tfm, OTX2_CPT_AES_GCM, OTX2_CPT_MAC_NULL);
+}
+
+static void otx2_cpt_aead_exit(struct crypto_aead *tfm)
+{
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(tfm);
+
+	kfree(ctx->ipad);
+	kfree(ctx->opad);
+	if (ctx->hashalg)
+		crypto_free_shash(ctx->hashalg);
+	kfree(ctx->sdesc);
+
+	if (ctx->fbk_cipher) {
+		crypto_free_aead(ctx->fbk_cipher);
+		ctx->fbk_cipher = NULL;
+	}
+}
+
+static int otx2_cpt_aead_gcm_set_authsize(struct crypto_aead *tfm,
+					  unsigned int authsize)
+{
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(tfm);
+
+	if (crypto_rfc4106_check_authsize(authsize))
+		return -EINVAL;
+
+	tfm->authsize = authsize;
+	/* Set authsize for fallback case */
+	if (ctx->fbk_cipher)
+		ctx->fbk_cipher->authsize = authsize;
+
+	return 0;
+}
+
+static int otx2_cpt_aead_set_authsize(struct crypto_aead *tfm,
+				      unsigned int authsize)
+{
+	tfm->authsize = authsize;
+
+	return 0;
+}
+
+static int otx2_cpt_aead_null_set_authsize(struct crypto_aead *tfm,
+					   unsigned int authsize)
+{
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(tfm);
+
+	ctx->is_trunc_hmac = true;
+	tfm->authsize = authsize;
+
+	return 0;
+}
+
+static struct otx2_cpt_sdesc *alloc_sdesc(struct crypto_shash *alg)
+{
+	struct otx2_cpt_sdesc *sdesc;
+	int size;
+
+	size = sizeof(struct shash_desc) + crypto_shash_descsize(alg);
+	sdesc = kmalloc(size, GFP_KERNEL);
+	if (!sdesc)
+		return NULL;
+
+	sdesc->shash.tfm = alg;
+
+	return sdesc;
+}
+
+static inline void swap_data32(void *buf, u32 len)
+{
+	cpu_to_be32_array(buf, buf, len / 4);
+}
+
+static inline void swap_data64(void *buf, u32 len)
+{
+	u64 *src = buf;
+	int i = 0;
+
+	for (i = 0 ; i < len / 8; i++, src++)
+		cpu_to_be64s(src);
+}
+
+static int copy_pad(u8 mac_type, u8 *out_pad, u8 *in_pad)
+{
+	struct sha512_state *sha512;
+	struct sha256_state *sha256;
+	struct sha1_state *sha1;
+
+	switch (mac_type) {
+	case OTX2_CPT_SHA1:
+		sha1 = (struct sha1_state *) in_pad;
+		swap_data32(sha1->state, SHA1_DIGEST_SIZE);
+		memcpy(out_pad, &sha1->state, SHA1_DIGEST_SIZE);
+		break;
+
+	case OTX2_CPT_SHA256:
+		sha256 = (struct sha256_state *) in_pad;
+		swap_data32(sha256->state, SHA256_DIGEST_SIZE);
+		memcpy(out_pad, &sha256->state, SHA256_DIGEST_SIZE);
+		break;
+
+	case OTX2_CPT_SHA384:
+	case OTX2_CPT_SHA512:
+		sha512 = (struct sha512_state *) in_pad;
+		swap_data64(sha512->state, SHA512_DIGEST_SIZE);
+		memcpy(out_pad, &sha512->state, SHA512_DIGEST_SIZE);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int aead_hmac_init(struct crypto_aead *cipher)
+{
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(cipher);
+	int state_size = crypto_shash_statesize(ctx->hashalg);
+	int ds = crypto_shash_digestsize(ctx->hashalg);
+	int bs = crypto_shash_blocksize(ctx->hashalg);
+	int authkeylen = ctx->auth_key_len;
+	u8 *ipad = NULL, *opad = NULL;
+	int ret = 0, icount = 0;
+
+	ctx->sdesc = alloc_sdesc(ctx->hashalg);
+	if (!ctx->sdesc)
+		return -ENOMEM;
+
+	ctx->ipad = kzalloc(bs, GFP_KERNEL);
+	if (!ctx->ipad) {
+		ret = -ENOMEM;
+		goto calc_fail;
+	}
+
+	ctx->opad = kzalloc(bs, GFP_KERNEL);
+	if (!ctx->opad) {
+		ret = -ENOMEM;
+		goto calc_fail;
+	}
+
+	ipad = kzalloc(state_size, GFP_KERNEL);
+	if (!ipad) {
+		ret = -ENOMEM;
+		goto calc_fail;
+	}
+
+	opad = kzalloc(state_size, GFP_KERNEL);
+	if (!opad) {
+		ret = -ENOMEM;
+		goto calc_fail;
+	}
+
+	if (authkeylen > bs) {
+		ret = crypto_shash_digest(&ctx->sdesc->shash, ctx->key,
+					  authkeylen, ipad);
+		if (ret)
+			goto calc_fail;
+
+		authkeylen = ds;
+	} else {
+		memcpy(ipad, ctx->key, authkeylen);
+	}
+
+	memset(ipad + authkeylen, 0, bs - authkeylen);
+	memcpy(opad, ipad, bs);
+
+	for (icount = 0; icount < bs; icount++) {
+		ipad[icount] ^= 0x36;
+		opad[icount] ^= 0x5c;
+	}
+
+	/*
+	 * Partial Hash calculated from the software
+	 * algorithm is retrieved for IPAD & OPAD
+	 */
+
+	/* IPAD Calculation */
+	crypto_shash_init(&ctx->sdesc->shash);
+	crypto_shash_update(&ctx->sdesc->shash, ipad, bs);
+	crypto_shash_export(&ctx->sdesc->shash, ipad);
+	ret = copy_pad(ctx->mac_type, ctx->ipad, ipad);
+	if (ret)
+		goto calc_fail;
+
+	/* OPAD Calculation */
+	crypto_shash_init(&ctx->sdesc->shash);
+	crypto_shash_update(&ctx->sdesc->shash, opad, bs);
+	crypto_shash_export(&ctx->sdesc->shash, opad);
+	ret = copy_pad(ctx->mac_type, ctx->opad, opad);
+	if (ret)
+		goto calc_fail;
+
+	kfree(ipad);
+	kfree(opad);
+
+	return 0;
+
+calc_fail:
+	kfree(ctx->ipad);
+	ctx->ipad = NULL;
+	kfree(ctx->opad);
+	ctx->opad = NULL;
+	kfree(ipad);
+	kfree(opad);
+	kfree(ctx->sdesc);
+	ctx->sdesc = NULL;
+
+	return ret;
+}
+
+static int otx2_cpt_aead_cbc_aes_sha_setkey(struct crypto_aead *cipher,
+					    const unsigned char *key,
+					    unsigned int keylen)
+{
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(cipher);
+	struct crypto_authenc_key_param *param;
+	int enckeylen = 0, authkeylen = 0;
+	struct rtattr *rta = (void *)key;
+	int status;
+
+	if (!RTA_OK(rta, keylen))
+		return -EINVAL;
+
+	if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM)
+		return -EINVAL;
+
+	if (RTA_PAYLOAD(rta) < sizeof(*param))
+		return -EINVAL;
+
+	param = RTA_DATA(rta);
+	enckeylen = be32_to_cpu(param->enckeylen);
+	key += RTA_ALIGN(rta->rta_len);
+	keylen -= RTA_ALIGN(rta->rta_len);
+	if (keylen < enckeylen)
+		return -EINVAL;
+
+	if (keylen > OTX2_CPT_MAX_KEY_SIZE)
+		return -EINVAL;
+
+	authkeylen = keylen - enckeylen;
+	memcpy(ctx->key, key, keylen);
+
+	switch (enckeylen) {
+	case AES_KEYSIZE_128:
+		ctx->key_type = OTX2_CPT_AES_128_BIT;
+		break;
+	case AES_KEYSIZE_192:
+		ctx->key_type = OTX2_CPT_AES_192_BIT;
+		break;
+	case AES_KEYSIZE_256:
+		ctx->key_type = OTX2_CPT_AES_256_BIT;
+		break;
+	default:
+		/* Invalid key length */
+		return -EINVAL;
+	}
+
+	ctx->enc_key_len = enckeylen;
+	ctx->auth_key_len = authkeylen;
+
+	status = aead_hmac_init(cipher);
+	if (status)
+		return status;
+
+	return 0;
+}
+
+static int otx2_cpt_aead_ecb_null_sha_setkey(struct crypto_aead *cipher,
+					     const unsigned char *key,
+					     unsigned int keylen)
+{
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(cipher);
+	struct crypto_authenc_key_param *param;
+	struct rtattr *rta = (void *)key;
+	int enckeylen = 0;
+
+	if (!RTA_OK(rta, keylen))
+		return -EINVAL;
+
+	if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM)
+		return -EINVAL;
+
+	if (RTA_PAYLOAD(rta) < sizeof(*param))
+		return -EINVAL;
+
+	param = RTA_DATA(rta);
+	enckeylen = be32_to_cpu(param->enckeylen);
+	key += RTA_ALIGN(rta->rta_len);
+	keylen -= RTA_ALIGN(rta->rta_len);
+	if (enckeylen != 0)
+		return -EINVAL;
+
+	if (keylen > OTX2_CPT_MAX_KEY_SIZE)
+		return -EINVAL;
+
+	memcpy(ctx->key, key, keylen);
+	ctx->enc_key_len = enckeylen;
+	ctx->auth_key_len = keylen;
+
+	return 0;
+}
+
+static int otx2_cpt_aead_gcm_aes_setkey(struct crypto_aead *cipher,
+					const unsigned char *key,
+					unsigned int keylen)
+{
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(cipher);
+
+	/*
+	 * For aes gcm we expect to get encryption key (16, 24, 32 bytes)
+	 * and salt (4 bytes)
+	 */
+	switch (keylen) {
+	case AES_KEYSIZE_128 + AES_GCM_SALT_SIZE:
+		ctx->key_type = OTX2_CPT_AES_128_BIT;
+		ctx->enc_key_len = AES_KEYSIZE_128;
+		break;
+	case AES_KEYSIZE_192 + AES_GCM_SALT_SIZE:
+		ctx->key_type = OTX2_CPT_AES_192_BIT;
+		ctx->enc_key_len = AES_KEYSIZE_192;
+		break;
+	case AES_KEYSIZE_256 + AES_GCM_SALT_SIZE:
+		ctx->key_type = OTX2_CPT_AES_256_BIT;
+		ctx->enc_key_len = AES_KEYSIZE_256;
+		break;
+	default:
+		/* Invalid key and salt length */
+		return -EINVAL;
+	}
+
+	/* Store encryption key and salt */
+	memcpy(ctx->key, key, keylen);
+
+	return crypto_aead_setkey(ctx->fbk_cipher, key, keylen);
+}
+
+static inline int create_aead_ctx_hdr(struct aead_request *req, u32 enc,
+				      u32 *argcnt)
+{
+	struct otx2_cpt_req_ctx *rctx = aead_request_ctx(req);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct otx2_cpt_req_info *req_info = &rctx->cpt_req;
+	struct otx2_cpt_fc_ctx *fctx = &rctx->fctx;
+	int mac_len = crypto_aead_authsize(tfm);
+	int ds;
+
+	rctx->ctrl_word.e.enc_data_offset = req->assoclen;
+
+	switch (ctx->cipher_type) {
+	case OTX2_CPT_AES_CBC:
+		if (req->assoclen > 248 || !IS_ALIGNED(req->assoclen, 8))
+			return -EINVAL;
+
+		fctx->enc.enc_ctrl.e.iv_source = OTX2_CPT_FROM_CPTR;
+		/* Copy encryption key to context */
+		memcpy(fctx->enc.encr_key, ctx->key + ctx->auth_key_len,
+		       ctx->enc_key_len);
+		/* Copy IV to context */
+		memcpy(fctx->enc.encr_iv, req->iv, crypto_aead_ivsize(tfm));
+
+		ds = crypto_shash_digestsize(ctx->hashalg);
+		if (ctx->mac_type == OTX2_CPT_SHA384)
+			ds = SHA512_DIGEST_SIZE;
+		if (ctx->ipad)
+			memcpy(fctx->hmac.e.ipad, ctx->ipad, ds);
+		if (ctx->opad)
+			memcpy(fctx->hmac.e.opad, ctx->opad, ds);
+		break;
+
+	case OTX2_CPT_AES_GCM:
+		if (crypto_ipsec_check_assoclen(req->assoclen))
+			return -EINVAL;
+
+		fctx->enc.enc_ctrl.e.iv_source = OTX2_CPT_FROM_DPTR;
+		/* Copy encryption key to context */
+		memcpy(fctx->enc.encr_key, ctx->key, ctx->enc_key_len);
+		/* Copy salt to context */
+		memcpy(fctx->enc.encr_iv, ctx->key + ctx->enc_key_len,
+		       AES_GCM_SALT_SIZE);
+
+		rctx->ctrl_word.e.iv_offset = req->assoclen - AES_GCM_IV_OFFSET;
+		break;
+
+	default:
+		/* Unknown cipher type */
+		return -EINVAL;
+	}
+	cpu_to_be64s(&rctx->ctrl_word.flags);
+
+	req_info->ctrl.s.dma_mode = OTX2_CPT_DMA_MODE_SG;
+	req_info->ctrl.s.se_req = 1;
+	req_info->req.opcode.s.major = OTX2_CPT_MAJOR_OP_FC |
+				 DMA_MODE_FLAG(OTX2_CPT_DMA_MODE_SG);
+	if (enc) {
+		req_info->req.opcode.s.minor = 2;
+		req_info->req.param1 = req->cryptlen;
+		req_info->req.param2 = req->cryptlen + req->assoclen;
+	} else {
+		req_info->req.opcode.s.minor = 3;
+		req_info->req.param1 = req->cryptlen - mac_len;
+		req_info->req.param2 = req->cryptlen + req->assoclen - mac_len;
+	}
+
+	fctx->enc.enc_ctrl.e.enc_cipher = ctx->cipher_type;
+	fctx->enc.enc_ctrl.e.aes_key = ctx->key_type;
+	fctx->enc.enc_ctrl.e.mac_type = ctx->mac_type;
+	fctx->enc.enc_ctrl.e.mac_len = mac_len;
+	cpu_to_be64s(&fctx->enc.enc_ctrl.u);
+
+	/*
+	 * Storing Packet Data Information in offset
+	 * Control Word First 8 bytes
+	 */
+	req_info->in[*argcnt].vptr = (u8 *)&rctx->ctrl_word;
+	req_info->in[*argcnt].size = CONTROL_WORD_LEN;
+	req_info->req.dlen += CONTROL_WORD_LEN;
+	++(*argcnt);
+
+	req_info->in[*argcnt].vptr = (u8 *)fctx;
+	req_info->in[*argcnt].size = sizeof(struct otx2_cpt_fc_ctx);
+	req_info->req.dlen += sizeof(struct otx2_cpt_fc_ctx);
+	++(*argcnt);
+
+	return 0;
+}
+
+static inline void create_hmac_ctx_hdr(struct aead_request *req, u32 *argcnt,
+				      u32 enc)
+{
+	struct otx2_cpt_req_ctx *rctx = aead_request_ctx(req);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct otx2_cpt_req_info *req_info = &rctx->cpt_req;
+
+	req_info->ctrl.s.dma_mode = OTX2_CPT_DMA_MODE_SG;
+	req_info->ctrl.s.se_req = 1;
+	req_info->req.opcode.s.major = OTX2_CPT_MAJOR_OP_HMAC |
+				 DMA_MODE_FLAG(OTX2_CPT_DMA_MODE_SG);
+	req_info->is_trunc_hmac = ctx->is_trunc_hmac;
+
+	req_info->req.opcode.s.minor = 0;
+	req_info->req.param1 = ctx->auth_key_len;
+	req_info->req.param2 = ctx->mac_type << 8;
+
+	/* Add authentication key */
+	req_info->in[*argcnt].vptr = ctx->key;
+	req_info->in[*argcnt].size = round_up(ctx->auth_key_len, 8);
+	req_info->req.dlen += round_up(ctx->auth_key_len, 8);
+	++(*argcnt);
+}
+
+static inline int create_aead_input_list(struct aead_request *req, u32 enc)
+{
+	struct otx2_cpt_req_ctx *rctx = aead_request_ctx(req);
+	struct otx2_cpt_req_info *req_info = &rctx->cpt_req;
+	u32 inputlen =  req->cryptlen + req->assoclen;
+	u32 status, argcnt = 0;
+
+	status = create_aead_ctx_hdr(req, enc, &argcnt);
+	if (status)
+		return status;
+	update_input_data(req_info, req->src, inputlen, &argcnt);
+	req_info->in_cnt = argcnt;
+
+	return 0;
+}
+
+static inline void create_aead_output_list(struct aead_request *req, u32 enc,
+					   u32 mac_len)
+{
+	struct otx2_cpt_req_ctx *rctx = aead_request_ctx(req);
+	struct otx2_cpt_req_info *req_info =  &rctx->cpt_req;
+	u32 argcnt = 0, outputlen = 0;
+
+	if (enc)
+		outputlen = req->cryptlen +  req->assoclen + mac_len;
+	else
+		outputlen = req->cryptlen + req->assoclen - mac_len;
+
+	update_output_data(req_info, req->dst, 0, outputlen, &argcnt);
+	req_info->out_cnt = argcnt;
+}
+
+static inline void create_aead_null_input_list(struct aead_request *req,
+					       u32 enc, u32 mac_len)
+{
+	struct otx2_cpt_req_ctx *rctx = aead_request_ctx(req);
+	struct otx2_cpt_req_info *req_info = &rctx->cpt_req;
+	u32 inputlen, argcnt = 0;
+
+	if (enc)
+		inputlen =  req->cryptlen + req->assoclen;
+	else
+		inputlen =  req->cryptlen + req->assoclen - mac_len;
+
+	create_hmac_ctx_hdr(req, &argcnt, enc);
+	update_input_data(req_info, req->src, inputlen, &argcnt);
+	req_info->in_cnt = argcnt;
+}
+
+static inline int create_aead_null_output_list(struct aead_request *req,
+					       u32 enc, u32 mac_len)
+{
+	struct otx2_cpt_req_ctx *rctx = aead_request_ctx(req);
+	struct otx2_cpt_req_info *req_info =  &rctx->cpt_req;
+	struct scatterlist *dst;
+	u8 *ptr = NULL;
+	int argcnt = 0, status, offset;
+	u32 inputlen;
+
+	if (enc)
+		inputlen =  req->cryptlen + req->assoclen;
+	else
+		inputlen =  req->cryptlen + req->assoclen - mac_len;
+
+	/*
+	 * If source and destination are different
+	 * then copy payload to destination
+	 */
+	if (req->src != req->dst) {
+
+		ptr = kmalloc(inputlen, (req_info->areq->flags &
+					 CRYPTO_TFM_REQ_MAY_SLEEP) ?
+					 GFP_KERNEL : GFP_ATOMIC);
+		if (!ptr)
+			return -ENOMEM;
+
+		status = sg_copy_to_buffer(req->src, sg_nents(req->src), ptr,
+					   inputlen);
+		if (status != inputlen) {
+			status = -EINVAL;
+			goto error_free;
+		}
+		status = sg_copy_from_buffer(req->dst, sg_nents(req->dst), ptr,
+					     inputlen);
+		if (status != inputlen) {
+			status = -EINVAL;
+			goto error_free;
+		}
+		kfree(ptr);
+	}
+
+	if (enc) {
+		/*
+		 * In an encryption scenario hmac needs
+		 * to be appended after payload
+		 */
+		dst = req->dst;
+		offset = inputlen;
+		while (offset >= dst->length) {
+			offset -= dst->length;
+			dst = sg_next(dst);
+			if (!dst)
+				return -ENOENT;
+		}
+
+		update_output_data(req_info, dst, offset, mac_len, &argcnt);
+	} else {
+		/*
+		 * In a decryption scenario calculated hmac for received
+		 * payload needs to be compare with hmac received
+		 */
+		status = sg_copy_buffer(req->src, sg_nents(req->src),
+					rctx->fctx.hmac.s.hmac_recv, mac_len,
+					inputlen, true);
+		if (status != mac_len)
+			return -EINVAL;
+
+		req_info->out[argcnt].vptr = rctx->fctx.hmac.s.hmac_calc;
+		req_info->out[argcnt].size = mac_len;
+		argcnt++;
+	}
+
+	req_info->out_cnt = argcnt;
+	return 0;
+
+error_free:
+	kfree(ptr);
+	return status;
+}
+
+static int aead_do_fallback(struct aead_request *req, bool is_enc)
+{
+	struct otx2_cpt_req_ctx *rctx = aead_request_ctx(req);
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(aead);
+	int ret;
+
+	if (ctx->fbk_cipher) {
+		/* Store the cipher tfm and then use the fallback tfm */
+		aead_request_set_tfm(&rctx->fbk_req, ctx->fbk_cipher);
+		aead_request_set_callback(&rctx->fbk_req, req->base.flags,
+					  req->base.complete, req->base.data);
+		aead_request_set_crypt(&rctx->fbk_req, req->src,
+				       req->dst, req->cryptlen, req->iv);
+		ret = is_enc ? crypto_aead_encrypt(&rctx->fbk_req) :
+			       crypto_aead_decrypt(&rctx->fbk_req);
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int cpt_aead_enc_dec(struct aead_request *req, u8 reg_type, u8 enc)
+{
+	struct otx2_cpt_req_ctx *rctx = aead_request_ctx(req);
+	struct otx2_cpt_req_info *req_info = &rctx->cpt_req;
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct otx2_cpt_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct pci_dev *pdev;
+	int status, cpu_num;
+
+	/* Clear control words */
+	rctx->ctrl_word.flags = 0;
+	rctx->fctx.enc.enc_ctrl.u = 0;
+
+	req_info->callback = otx2_cpt_aead_callback;
+	req_info->areq = &req->base;
+	req_info->req_type = reg_type;
+	req_info->is_enc = enc;
+	req_info->is_trunc_hmac = false;
+
+	switch (reg_type) {
+	case OTX2_CPT_AEAD_ENC_DEC_REQ:
+		status = create_aead_input_list(req, enc);
+		if (status)
+			return status;
+		create_aead_output_list(req, enc, crypto_aead_authsize(tfm));
+		break;
+
+	case OTX2_CPT_AEAD_ENC_DEC_NULL_REQ:
+		create_aead_null_input_list(req, enc,
+					    crypto_aead_authsize(tfm));
+		status = create_aead_null_output_list(req, enc,
+						crypto_aead_authsize(tfm));
+		if (status)
+			return status;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+	if (!IS_ALIGNED(req_info->req.param1, ctx->enc_align_len))
+		return -EINVAL;
+
+	if (!req_info->req.param2 ||
+	    (req_info->req.param1 > OTX2_CPT_MAX_REQ_SIZE) ||
+	    (req_info->req.param2 > OTX2_CPT_MAX_REQ_SIZE))
+		return aead_do_fallback(req, enc);
+
+	status = get_se_device(&pdev, &cpu_num);
+	if (status)
+		return status;
+
+	req_info->ctrl.s.grp = otx2_cpt_get_kcrypto_eng_grp_num(pdev);
+
+	/*
+	 * We perform an asynchronous send and once
+	 * the request is completed the driver would
+	 * intimate through registered call back functions
+	 */
+	return otx2_cpt_do_request(pdev, req_info, cpu_num);
+}
+
+static int otx2_cpt_aead_encrypt(struct aead_request *req)
+{
+	return cpt_aead_enc_dec(req, OTX2_CPT_AEAD_ENC_DEC_REQ, true);
+}
+
+static int otx2_cpt_aead_decrypt(struct aead_request *req)
+{
+	return cpt_aead_enc_dec(req, OTX2_CPT_AEAD_ENC_DEC_REQ, false);
+}
+
+static int otx2_cpt_aead_null_encrypt(struct aead_request *req)
+{
+	return cpt_aead_enc_dec(req, OTX2_CPT_AEAD_ENC_DEC_NULL_REQ, true);
+}
+
+static int otx2_cpt_aead_null_decrypt(struct aead_request *req)
+{
+	return cpt_aead_enc_dec(req, OTX2_CPT_AEAD_ENC_DEC_NULL_REQ, false);
+}
+
+static struct skcipher_alg otx2_cpt_skciphers[] = { {
+	.base.cra_name = "xts(aes)",
+	.base.cra_driver_name = "cpt_xts_aes",
+	.base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize = AES_BLOCK_SIZE,
+	.base.cra_ctxsize = sizeof(struct otx2_cpt_enc_ctx),
+	.base.cra_alignmask = 7,
+	.base.cra_priority = 4001,
+	.base.cra_module = THIS_MODULE,
+
+	.init = otx2_cpt_enc_dec_init,
+	.exit = otx2_cpt_skcipher_exit,
+	.ivsize = AES_BLOCK_SIZE,
+	.min_keysize = 2 * AES_MIN_KEY_SIZE,
+	.max_keysize = 2 * AES_MAX_KEY_SIZE,
+	.setkey = otx2_cpt_skcipher_xts_setkey,
+	.encrypt = otx2_cpt_skcipher_encrypt,
+	.decrypt = otx2_cpt_skcipher_decrypt,
+}, {
+	.base.cra_name = "cbc(aes)",
+	.base.cra_driver_name = "cpt_cbc_aes",
+	.base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize = AES_BLOCK_SIZE,
+	.base.cra_ctxsize = sizeof(struct otx2_cpt_enc_ctx),
+	.base.cra_alignmask = 7,
+	.base.cra_priority = 4001,
+	.base.cra_module = THIS_MODULE,
+
+	.init = otx2_cpt_enc_dec_init,
+	.exit = otx2_cpt_skcipher_exit,
+	.ivsize = AES_BLOCK_SIZE,
+	.min_keysize = AES_MIN_KEY_SIZE,
+	.max_keysize = AES_MAX_KEY_SIZE,
+	.setkey = otx2_cpt_skcipher_cbc_aes_setkey,
+	.encrypt = otx2_cpt_skcipher_encrypt,
+	.decrypt = otx2_cpt_skcipher_decrypt,
+}, {
+	.base.cra_name = "ecb(aes)",
+	.base.cra_driver_name = "cpt_ecb_aes",
+	.base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize = AES_BLOCK_SIZE,
+	.base.cra_ctxsize = sizeof(struct otx2_cpt_enc_ctx),
+	.base.cra_alignmask = 7,
+	.base.cra_priority = 4001,
+	.base.cra_module = THIS_MODULE,
+
+	.init = otx2_cpt_enc_dec_init,
+	.exit = otx2_cpt_skcipher_exit,
+	.ivsize = 0,
+	.min_keysize = AES_MIN_KEY_SIZE,
+	.max_keysize = AES_MAX_KEY_SIZE,
+	.setkey = otx2_cpt_skcipher_ecb_aes_setkey,
+	.encrypt = otx2_cpt_skcipher_encrypt,
+	.decrypt = otx2_cpt_skcipher_decrypt,
+}, {
+	.base.cra_name = "cbc(des3_ede)",
+	.base.cra_driver_name = "cpt_cbc_des3_ede",
+	.base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+	.base.cra_ctxsize = sizeof(struct otx2_cpt_enc_ctx),
+	.base.cra_alignmask = 7,
+	.base.cra_priority = 4001,
+	.base.cra_module = THIS_MODULE,
+
+	.init = otx2_cpt_enc_dec_init,
+	.exit = otx2_cpt_skcipher_exit,
+	.min_keysize = DES3_EDE_KEY_SIZE,
+	.max_keysize = DES3_EDE_KEY_SIZE,
+	.ivsize = DES_BLOCK_SIZE,
+	.setkey = otx2_cpt_skcipher_cbc_des3_setkey,
+	.encrypt = otx2_cpt_skcipher_encrypt,
+	.decrypt = otx2_cpt_skcipher_decrypt,
+}, {
+	.base.cra_name = "ecb(des3_ede)",
+	.base.cra_driver_name = "cpt_ecb_des3_ede",
+	.base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+	.base.cra_ctxsize = sizeof(struct otx2_cpt_enc_ctx),
+	.base.cra_alignmask = 7,
+	.base.cra_priority = 4001,
+	.base.cra_module = THIS_MODULE,
+
+	.init = otx2_cpt_enc_dec_init,
+	.exit = otx2_cpt_skcipher_exit,
+	.min_keysize = DES3_EDE_KEY_SIZE,
+	.max_keysize = DES3_EDE_KEY_SIZE,
+	.ivsize = 0,
+	.setkey = otx2_cpt_skcipher_ecb_des3_setkey,
+	.encrypt = otx2_cpt_skcipher_encrypt,
+	.decrypt = otx2_cpt_skcipher_decrypt,
+} };
+
+static struct aead_alg otx2_cpt_aeads[] = { {
+	.base = {
+		.cra_name = "authenc(hmac(sha1),cbc(aes))",
+		.cra_driver_name = "cpt_hmac_sha1_cbc_aes",
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+		.cra_ctxsize = sizeof(struct otx2_cpt_aead_ctx),
+		.cra_priority = 4001,
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.init = otx2_cpt_aead_cbc_aes_sha1_init,
+	.exit = otx2_cpt_aead_exit,
+	.setkey = otx2_cpt_aead_cbc_aes_sha_setkey,
+	.setauthsize = otx2_cpt_aead_set_authsize,
+	.encrypt = otx2_cpt_aead_encrypt,
+	.decrypt = otx2_cpt_aead_decrypt,
+	.ivsize = AES_BLOCK_SIZE,
+	.maxauthsize = SHA1_DIGEST_SIZE,
+}, {
+	.base = {
+		.cra_name = "authenc(hmac(sha256),cbc(aes))",
+		.cra_driver_name = "cpt_hmac_sha256_cbc_aes",
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+		.cra_ctxsize = sizeof(struct otx2_cpt_aead_ctx),
+		.cra_priority = 4001,
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.init = otx2_cpt_aead_cbc_aes_sha256_init,
+	.exit = otx2_cpt_aead_exit,
+	.setkey = otx2_cpt_aead_cbc_aes_sha_setkey,
+	.setauthsize = otx2_cpt_aead_set_authsize,
+	.encrypt = otx2_cpt_aead_encrypt,
+	.decrypt = otx2_cpt_aead_decrypt,
+	.ivsize = AES_BLOCK_SIZE,
+	.maxauthsize = SHA256_DIGEST_SIZE,
+}, {
+	.base = {
+		.cra_name = "authenc(hmac(sha384),cbc(aes))",
+		.cra_driver_name = "cpt_hmac_sha384_cbc_aes",
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+		.cra_ctxsize = sizeof(struct otx2_cpt_aead_ctx),
+		.cra_priority = 4001,
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.init = otx2_cpt_aead_cbc_aes_sha384_init,
+	.exit = otx2_cpt_aead_exit,
+	.setkey = otx2_cpt_aead_cbc_aes_sha_setkey,
+	.setauthsize = otx2_cpt_aead_set_authsize,
+	.encrypt = otx2_cpt_aead_encrypt,
+	.decrypt = otx2_cpt_aead_decrypt,
+	.ivsize = AES_BLOCK_SIZE,
+	.maxauthsize = SHA384_DIGEST_SIZE,
+}, {
+	.base = {
+		.cra_name = "authenc(hmac(sha512),cbc(aes))",
+		.cra_driver_name = "cpt_hmac_sha512_cbc_aes",
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+		.cra_ctxsize = sizeof(struct otx2_cpt_aead_ctx),
+		.cra_priority = 4001,
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.init = otx2_cpt_aead_cbc_aes_sha512_init,
+	.exit = otx2_cpt_aead_exit,
+	.setkey = otx2_cpt_aead_cbc_aes_sha_setkey,
+	.setauthsize = otx2_cpt_aead_set_authsize,
+	.encrypt = otx2_cpt_aead_encrypt,
+	.decrypt = otx2_cpt_aead_decrypt,
+	.ivsize = AES_BLOCK_SIZE,
+	.maxauthsize = SHA512_DIGEST_SIZE,
+}, {
+	.base = {
+		.cra_name = "authenc(hmac(sha1),ecb(cipher_null))",
+		.cra_driver_name = "cpt_hmac_sha1_ecb_null",
+		.cra_blocksize = 1,
+		.cra_flags = CRYPTO_ALG_ASYNC,
+		.cra_ctxsize = sizeof(struct otx2_cpt_aead_ctx),
+		.cra_priority = 4001,
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.init = otx2_cpt_aead_ecb_null_sha1_init,
+	.exit = otx2_cpt_aead_exit,
+	.setkey = otx2_cpt_aead_ecb_null_sha_setkey,
+	.setauthsize = otx2_cpt_aead_null_set_authsize,
+	.encrypt = otx2_cpt_aead_null_encrypt,
+	.decrypt = otx2_cpt_aead_null_decrypt,
+	.ivsize = 0,
+	.maxauthsize = SHA1_DIGEST_SIZE,
+}, {
+	.base = {
+		.cra_name = "authenc(hmac(sha256),ecb(cipher_null))",
+		.cra_driver_name = "cpt_hmac_sha256_ecb_null",
+		.cra_blocksize = 1,
+		.cra_flags = CRYPTO_ALG_ASYNC,
+		.cra_ctxsize = sizeof(struct otx2_cpt_aead_ctx),
+		.cra_priority = 4001,
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.init = otx2_cpt_aead_ecb_null_sha256_init,
+	.exit = otx2_cpt_aead_exit,
+	.setkey = otx2_cpt_aead_ecb_null_sha_setkey,
+	.setauthsize = otx2_cpt_aead_null_set_authsize,
+	.encrypt = otx2_cpt_aead_null_encrypt,
+	.decrypt = otx2_cpt_aead_null_decrypt,
+	.ivsize = 0,
+	.maxauthsize = SHA256_DIGEST_SIZE,
+}, {
+	.base = {
+		.cra_name = "authenc(hmac(sha384),ecb(cipher_null))",
+		.cra_driver_name = "cpt_hmac_sha384_ecb_null",
+		.cra_blocksize = 1,
+		.cra_flags = CRYPTO_ALG_ASYNC,
+		.cra_ctxsize = sizeof(struct otx2_cpt_aead_ctx),
+		.cra_priority = 4001,
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.init = otx2_cpt_aead_ecb_null_sha384_init,
+	.exit = otx2_cpt_aead_exit,
+	.setkey = otx2_cpt_aead_ecb_null_sha_setkey,
+	.setauthsize = otx2_cpt_aead_null_set_authsize,
+	.encrypt = otx2_cpt_aead_null_encrypt,
+	.decrypt = otx2_cpt_aead_null_decrypt,
+	.ivsize = 0,
+	.maxauthsize = SHA384_DIGEST_SIZE,
+}, {
+	.base = {
+		.cra_name = "authenc(hmac(sha512),ecb(cipher_null))",
+		.cra_driver_name = "cpt_hmac_sha512_ecb_null",
+		.cra_blocksize = 1,
+		.cra_flags = CRYPTO_ALG_ASYNC,
+		.cra_ctxsize = sizeof(struct otx2_cpt_aead_ctx),
+		.cra_priority = 4001,
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.init = otx2_cpt_aead_ecb_null_sha512_init,
+	.exit = otx2_cpt_aead_exit,
+	.setkey = otx2_cpt_aead_ecb_null_sha_setkey,
+	.setauthsize = otx2_cpt_aead_null_set_authsize,
+	.encrypt = otx2_cpt_aead_null_encrypt,
+	.decrypt = otx2_cpt_aead_null_decrypt,
+	.ivsize = 0,
+	.maxauthsize = SHA512_DIGEST_SIZE,
+}, {
+	.base = {
+		.cra_name = "rfc4106(gcm(aes))",
+		.cra_driver_name = "cpt_rfc4106_gcm_aes",
+		.cra_blocksize = 1,
+		.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK,
+		.cra_ctxsize = sizeof(struct otx2_cpt_aead_ctx),
+		.cra_priority = 4001,
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.init = otx2_cpt_aead_gcm_aes_init,
+	.exit = otx2_cpt_aead_exit,
+	.setkey = otx2_cpt_aead_gcm_aes_setkey,
+	.setauthsize = otx2_cpt_aead_gcm_set_authsize,
+	.encrypt = otx2_cpt_aead_encrypt,
+	.decrypt = otx2_cpt_aead_decrypt,
+	.ivsize = AES_GCM_IV_SIZE,
+	.maxauthsize = AES_GCM_ICV_SIZE,
+} };
+
+static inline int cpt_register_algs(void)
+{
+	int i, err = 0;
+
+	if (!IS_ENABLED(CONFIG_DM_CRYPT)) {
+		for (i = 0; i < ARRAY_SIZE(otx2_cpt_skciphers); i++)
+			otx2_cpt_skciphers[i].base.cra_flags &=
+							~CRYPTO_ALG_DEAD;
+
+		err = crypto_register_skciphers(otx2_cpt_skciphers,
+						ARRAY_SIZE(otx2_cpt_skciphers));
+		if (err)
+			return err;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(otx2_cpt_aeads); i++)
+		otx2_cpt_aeads[i].base.cra_flags &= ~CRYPTO_ALG_DEAD;
+
+	err = crypto_register_aeads(otx2_cpt_aeads,
+				    ARRAY_SIZE(otx2_cpt_aeads));
+	if (err) {
+		crypto_unregister_skciphers(otx2_cpt_skciphers,
+					    ARRAY_SIZE(otx2_cpt_skciphers));
+		return err;
+	}
+
+	return 0;
+}
+
+static inline void cpt_unregister_algs(void)
+{
+	crypto_unregister_skciphers(otx2_cpt_skciphers,
+				    ARRAY_SIZE(otx2_cpt_skciphers));
+	crypto_unregister_aeads(otx2_cpt_aeads, ARRAY_SIZE(otx2_cpt_aeads));
+}
+
+static int compare_func(const void *lptr, const void *rptr)
+{
+	const struct cpt_device_desc *ldesc = (struct cpt_device_desc *) lptr;
+	const struct cpt_device_desc *rdesc = (struct cpt_device_desc *) rptr;
+
+	if (ldesc->dev->devfn < rdesc->dev->devfn)
+		return -1;
+	if (ldesc->dev->devfn > rdesc->dev->devfn)
+		return 1;
+	return 0;
+}
+
+static void swap_func(void *lptr, void *rptr, int size)
+{
+	struct cpt_device_desc *ldesc = lptr;
+	struct cpt_device_desc *rdesc = rptr;
+	struct cpt_device_desc desc;
+
+	desc = *ldesc;
+	*ldesc = *rdesc;
+	*rdesc = desc;
+}
+
+int otx2_cpt_crypto_init(struct pci_dev *pdev, struct module *mod,
+			 int num_queues, int num_devices)
+{
+	int ret = 0;
+	int count;
+
+	mutex_lock(&mutex);
+	count = atomic_read(&se_devices.count);
+	if (count >= OTX2_CPT_MAX_LFS_NUM) {
+		dev_err(&pdev->dev, "No space to add a new device\n");
+		ret = -ENOSPC;
+		goto unlock;
+	}
+	se_devices.desc[count].num_queues = num_queues;
+	se_devices.desc[count++].dev = pdev;
+	atomic_inc(&se_devices.count);
+
+	if (atomic_read(&se_devices.count) == num_devices &&
+	    is_crypto_registered == false) {
+		if (cpt_register_algs()) {
+			dev_err(&pdev->dev,
+				"Error in registering crypto algorithms\n");
+			ret =  -EINVAL;
+			goto unlock;
+		}
+		try_module_get(mod);
+		is_crypto_registered = true;
+	}
+	sort(se_devices.desc, count, sizeof(struct cpt_device_desc),
+	     compare_func, swap_func);
+
+unlock:
+	mutex_unlock(&mutex);
+	return ret;
+}
+
+void otx2_cpt_crypto_exit(struct pci_dev *pdev, struct module *mod)
+{
+	struct cpt_device_table *dev_tbl;
+	bool dev_found = false;
+	int i, j, count;
+
+	mutex_lock(&mutex);
+
+	dev_tbl = &se_devices;
+	count = atomic_read(&dev_tbl->count);
+	for (i = 0; i < count; i++) {
+		if (pdev == dev_tbl->desc[i].dev) {
+			for (j = i; j < count-1; j++)
+				dev_tbl->desc[j] = dev_tbl->desc[j+1];
+			dev_found = true;
+			break;
+		}
+	}
+
+	if (!dev_found) {
+		dev_err(&pdev->dev, "%s device not found\n", __func__);
+		goto unlock;
+	}
+	if (atomic_dec_and_test(&se_devices.count)) {
+		cpt_unregister_algs();
+		module_put(mod);
+		is_crypto_registered = false;
+	}
+
+unlock:
+	mutex_unlock(&mutex);
+}
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.h b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.h
new file mode 100644
index 000000000000..f04184bd1744
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_algs.h
@@ -0,0 +1,178 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __OTX2_CPT_ALGS_H
+#define __OTX2_CPT_ALGS_H
+
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
+#include <crypto/aead.h>
+#include "otx2_cpt_common.h"
+
+#define OTX2_CPT_MAX_ENC_KEY_SIZE    32
+#define OTX2_CPT_MAX_HASH_KEY_SIZE   64
+#define OTX2_CPT_MAX_KEY_SIZE (OTX2_CPT_MAX_ENC_KEY_SIZE + \
+			       OTX2_CPT_MAX_HASH_KEY_SIZE)
+enum otx2_cpt_request_type {
+	OTX2_CPT_ENC_DEC_REQ            = 0x1,
+	OTX2_CPT_AEAD_ENC_DEC_REQ       = 0x2,
+	OTX2_CPT_AEAD_ENC_DEC_NULL_REQ  = 0x3,
+	OTX2_CPT_PASSTHROUGH_REQ	= 0x4
+};
+
+enum otx2_cpt_major_opcodes {
+	OTX2_CPT_MAJOR_OP_MISC = 0x01,
+	OTX2_CPT_MAJOR_OP_FC   = 0x33,
+	OTX2_CPT_MAJOR_OP_HMAC = 0x35,
+};
+
+enum otx2_cpt_cipher_type {
+	OTX2_CPT_CIPHER_NULL = 0x0,
+	OTX2_CPT_DES3_CBC = 0x1,
+	OTX2_CPT_DES3_ECB = 0x2,
+	OTX2_CPT_AES_CBC  = 0x3,
+	OTX2_CPT_AES_ECB  = 0x4,
+	OTX2_CPT_AES_CFB  = 0x5,
+	OTX2_CPT_AES_CTR  = 0x6,
+	OTX2_CPT_AES_GCM  = 0x7,
+	OTX2_CPT_AES_XTS  = 0x8
+};
+
+enum otx2_cpt_mac_type {
+	OTX2_CPT_MAC_NULL = 0x0,
+	OTX2_CPT_MD5      = 0x1,
+	OTX2_CPT_SHA1     = 0x2,
+	OTX2_CPT_SHA224   = 0x3,
+	OTX2_CPT_SHA256   = 0x4,
+	OTX2_CPT_SHA384   = 0x5,
+	OTX2_CPT_SHA512   = 0x6,
+	OTX2_CPT_GMAC     = 0x7
+};
+
+enum otx2_cpt_aes_key_len {
+	OTX2_CPT_AES_128_BIT = 0x1,
+	OTX2_CPT_AES_192_BIT = 0x2,
+	OTX2_CPT_AES_256_BIT = 0x3
+};
+
+union otx2_cpt_encr_ctrl {
+	u64 u;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 enc_cipher:4;
+		u64 reserved_59:1;
+		u64 aes_key:2;
+		u64 iv_source:1;
+		u64 mac_type:4;
+		u64 reserved_49_51:3;
+		u64 auth_input_type:1;
+		u64 mac_len:8;
+		u64 reserved_32_39:8;
+		u64 encr_offset:16;
+		u64 iv_offset:8;
+		u64 auth_offset:8;
+#else
+		u64 auth_offset:8;
+		u64 iv_offset:8;
+		u64 encr_offset:16;
+		u64 reserved_32_39:8;
+		u64 mac_len:8;
+		u64 auth_input_type:1;
+		u64 reserved_49_51:3;
+		u64 mac_type:4;
+		u64 iv_source:1;
+		u64 aes_key:2;
+		u64 reserved_59:1;
+		u64 enc_cipher:4;
+#endif
+	} e;
+};
+
+struct otx2_cpt_cipher {
+	const char *name;
+	u8 value;
+};
+
+struct otx2_cpt_fc_enc_ctx {
+	union otx2_cpt_encr_ctrl enc_ctrl;
+	u8 encr_key[32];
+	u8 encr_iv[16];
+};
+
+union otx2_cpt_fc_hmac_ctx {
+	struct {
+		u8 ipad[64];
+		u8 opad[64];
+	} e;
+	struct {
+		u8 hmac_calc[64]; /* HMAC calculated */
+		u8 hmac_recv[64]; /* HMAC received */
+	} s;
+};
+
+struct otx2_cpt_fc_ctx {
+	struct otx2_cpt_fc_enc_ctx enc;
+	union otx2_cpt_fc_hmac_ctx hmac;
+};
+
+struct otx2_cpt_enc_ctx {
+	u32 key_len;
+	u8 enc_key[OTX2_CPT_MAX_KEY_SIZE];
+	u8 cipher_type;
+	u8 key_type;
+	u8 enc_align_len;
+	struct crypto_skcipher *fbk_cipher;
+};
+
+union otx2_cpt_offset_ctrl {
+	u64 flags;
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+		u64 reserved:32;
+		u64 enc_data_offset:16;
+		u64 iv_offset:8;
+		u64 auth_offset:8;
+#else
+		u64 auth_offset:8;
+		u64 iv_offset:8;
+		u64 enc_data_offset:16;
+		u64 reserved:32;
+#endif
+	} e;
+};
+
+struct otx2_cpt_req_ctx {
+	struct otx2_cpt_req_info cpt_req;
+	union otx2_cpt_offset_ctrl ctrl_word;
+	struct otx2_cpt_fc_ctx fctx;
+	union {
+		struct skcipher_request sk_fbk_req;
+		struct aead_request fbk_req;
+	};
+};
+
+struct otx2_cpt_sdesc {
+	struct shash_desc shash;
+};
+
+struct otx2_cpt_aead_ctx {
+	u8 key[OTX2_CPT_MAX_KEY_SIZE];
+	struct crypto_shash *hashalg;
+	struct otx2_cpt_sdesc *sdesc;
+	struct crypto_aead *fbk_cipher;
+	u8 *ipad;
+	u8 *opad;
+	u32 enc_key_len;
+	u32 auth_key_len;
+	u8 cipher_type;
+	u8 mac_type;
+	u8 key_type;
+	u8 is_trunc_hmac;
+	u8 enc_align_len;
+};
+int otx2_cpt_crypto_init(struct pci_dev *pdev, struct module *mod,
+			 int num_queues, int num_devices);
+void otx2_cpt_crypto_exit(struct pci_dev *pdev, struct module *mod);
+
+#endif /* __OTX2_CPT_ALGS_H */
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c
new file mode 100644
index 000000000000..47f378731024
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_main.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptvf.h"
+#include "otx2_cptlf.h"
+#include "otx2_cptvf_algs.h"
+#include <rvu_reg.h>
+
+#define OTX2_CPTVF_DRV_NAME "octeontx2-cptvf"
+
+static void cptvf_enable_pfvf_mbox_intrs(struct otx2_cptvf_dev *cptvf)
+{
+	/* Clear interrupt if any */
+	otx2_cpt_write64(cptvf->reg_base, BLKADDR_RVUM, 0, OTX2_RVU_VF_INT,
+			 0x1ULL);
+
+	/* Enable PF-VF interrupt */
+	otx2_cpt_write64(cptvf->reg_base, BLKADDR_RVUM, 0,
+			 OTX2_RVU_VF_INT_ENA_W1S, 0x1ULL);
+}
+
+static void cptvf_disable_pfvf_mbox_intrs(struct otx2_cptvf_dev *cptvf)
+{
+	/* Disable PF-VF interrupt */
+	otx2_cpt_write64(cptvf->reg_base, BLKADDR_RVUM, 0,
+			 OTX2_RVU_VF_INT_ENA_W1C, 0x1ULL);
+
+	/* Clear interrupt if any */
+	otx2_cpt_write64(cptvf->reg_base, BLKADDR_RVUM, 0, OTX2_RVU_VF_INT,
+			 0x1ULL);
+}
+
+static int cptvf_register_interrupts(struct otx2_cptvf_dev *cptvf)
+{
+	int ret, irq;
+	int num_vec;
+
+	num_vec = pci_msix_vec_count(cptvf->pdev);
+	if (num_vec <= 0)
+		return -EINVAL;
+
+	/* Enable MSI-X */
+	ret = pci_alloc_irq_vectors(cptvf->pdev, num_vec, num_vec,
+				    PCI_IRQ_MSIX);
+	if (ret < 0) {
+		dev_err(&cptvf->pdev->dev,
+			"Request for %d msix vectors failed\n", num_vec);
+		return ret;
+	}
+	irq = pci_irq_vector(cptvf->pdev, OTX2_CPT_VF_INT_VEC_E_MBOX);
+	/* Register VF<=>PF mailbox interrupt handler */
+	ret = devm_request_irq(&cptvf->pdev->dev, irq,
+			       otx2_cptvf_pfvf_mbox_intr, 0,
+			       "CPTPFVF Mbox", cptvf);
+	if (ret)
+		return ret;
+	/* Enable PF-VF mailbox interrupts */
+	cptvf_enable_pfvf_mbox_intrs(cptvf);
+
+	ret = otx2_cpt_send_ready_msg(&cptvf->pfvf_mbox, cptvf->pdev);
+	if (ret) {
+		dev_warn(&cptvf->pdev->dev,
+			 "PF not responding to mailbox, deferring probe\n");
+		cptvf_disable_pfvf_mbox_intrs(cptvf);
+		return -EPROBE_DEFER;
+	}
+	return 0;
+}
+
+static int cptvf_pfvf_mbox_init(struct otx2_cptvf_dev *cptvf)
+{
+	int ret;
+
+	cptvf->pfvf_mbox_wq = alloc_workqueue("cpt_pfvf_mailbox",
+					      WQ_UNBOUND | WQ_HIGHPRI |
+					      WQ_MEM_RECLAIM, 1);
+	if (!cptvf->pfvf_mbox_wq)
+		return -ENOMEM;
+
+	ret = otx2_mbox_init(&cptvf->pfvf_mbox, cptvf->pfvf_mbox_base,
+			     cptvf->pdev, cptvf->reg_base, MBOX_DIR_VFPF, 1);
+	if (ret)
+		goto free_wqe;
+
+	INIT_WORK(&cptvf->pfvf_mbox_work, otx2_cptvf_pfvf_mbox_handler);
+	return 0;
+
+free_wqe:
+	destroy_workqueue(cptvf->pfvf_mbox_wq);
+	return ret;
+}
+
+static void cptvf_pfvf_mbox_destroy(struct otx2_cptvf_dev *cptvf)
+{
+	destroy_workqueue(cptvf->pfvf_mbox_wq);
+	otx2_mbox_destroy(&cptvf->pfvf_mbox);
+}
+
+static void cptlf_work_handler(unsigned long data)
+{
+	otx2_cpt_post_process((struct otx2_cptlf_wqe *) data);
+}
+
+static void cleanup_tasklet_work(struct otx2_cptlfs_info *lfs)
+{
+	int i;
+
+	for (i = 0; i <  lfs->lfs_num; i++) {
+		if (!lfs->lf[i].wqe)
+			continue;
+
+		tasklet_kill(&lfs->lf[i].wqe->work);
+		kfree(lfs->lf[i].wqe);
+		lfs->lf[i].wqe = NULL;
+	}
+}
+
+static int init_tasklet_work(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_cptlf_wqe *wqe;
+	int i, ret = 0;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		wqe = kzalloc(sizeof(struct otx2_cptlf_wqe), GFP_KERNEL);
+		if (!wqe) {
+			ret = -ENOMEM;
+			goto cleanup_tasklet;
+		}
+
+		tasklet_init(&wqe->work, cptlf_work_handler, (u64) wqe);
+		wqe->lfs = lfs;
+		wqe->lf_num = i;
+		lfs->lf[i].wqe = wqe;
+	}
+	return 0;
+
+cleanup_tasklet:
+	cleanup_tasklet_work(lfs);
+	return ret;
+}
+
+static void free_pending_queues(struct otx2_cptlfs_info *lfs)
+{
+	int i;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		kfree(lfs->lf[i].pqueue.head);
+		lfs->lf[i].pqueue.head = NULL;
+	}
+}
+
+static int alloc_pending_queues(struct otx2_cptlfs_info *lfs)
+{
+	int size, ret, i;
+
+	if (!lfs->lfs_num)
+		return -EINVAL;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		lfs->lf[i].pqueue.qlen = OTX2_CPT_INST_QLEN_MSGS;
+		size = lfs->lf[i].pqueue.qlen *
+		       sizeof(struct otx2_cpt_pending_entry);
+
+		lfs->lf[i].pqueue.head = kzalloc(size, GFP_KERNEL);
+		if (!lfs->lf[i].pqueue.head) {
+			ret = -ENOMEM;
+			goto error;
+		}
+
+		/* Initialize spin lock */
+		spin_lock_init(&lfs->lf[i].pqueue.lock);
+	}
+	return 0;
+
+error:
+	free_pending_queues(lfs);
+	return ret;
+}
+
+static void lf_sw_cleanup(struct otx2_cptlfs_info *lfs)
+{
+	cleanup_tasklet_work(lfs);
+	free_pending_queues(lfs);
+}
+
+static int lf_sw_init(struct otx2_cptlfs_info *lfs)
+{
+	int ret;
+
+	ret = alloc_pending_queues(lfs);
+	if (ret) {
+		dev_err(&lfs->pdev->dev,
+			"Allocating pending queues failed\n");
+		return ret;
+	}
+	ret = init_tasklet_work(lfs);
+	if (ret) {
+		dev_err(&lfs->pdev->dev,
+			"Tasklet work init failed\n");
+		goto pending_queues_free;
+	}
+	return 0;
+
+pending_queues_free:
+	free_pending_queues(lfs);
+	return ret;
+}
+
+static void cptvf_lf_shutdown(struct otx2_cptlfs_info *lfs)
+{
+	atomic_set(&lfs->state, OTX2_CPTLF_IN_RESET);
+
+	/* Remove interrupts affinity */
+	otx2_cptlf_free_irqs_affinity(lfs);
+	/* Disable instruction queue */
+	otx2_cptlf_disable_iqueues(lfs);
+	/* Unregister crypto algorithms */
+	otx2_cpt_crypto_exit(lfs->pdev, THIS_MODULE);
+	/* Unregister LFs interrupts */
+	otx2_cptlf_unregister_interrupts(lfs);
+	/* Cleanup LFs software side */
+	lf_sw_cleanup(lfs);
+	/* Send request to detach LFs */
+	otx2_cpt_detach_rsrcs_msg(lfs);
+}
+
+static int cptvf_lf_init(struct otx2_cptvf_dev *cptvf)
+{
+	struct otx2_cptlfs_info *lfs = &cptvf->lfs;
+	struct device *dev = &cptvf->pdev->dev;
+	int ret, lfs_num;
+	u8 eng_grp_msk;
+
+	/* Get engine group number for symmetric crypto */
+	cptvf->lfs.kcrypto_eng_grp_num = OTX2_CPT_INVALID_CRYPTO_ENG_GRP;
+	ret = otx2_cptvf_send_eng_grp_num_msg(cptvf, OTX2_CPT_SE_TYPES);
+	if (ret)
+		return ret;
+
+	if (cptvf->lfs.kcrypto_eng_grp_num == OTX2_CPT_INVALID_CRYPTO_ENG_GRP) {
+		dev_err(dev, "Engine group for kernel crypto not available\n");
+		ret = -ENOENT;
+		return ret;
+	}
+	eng_grp_msk = 1 << cptvf->lfs.kcrypto_eng_grp_num;
+
+	ret = otx2_cptvf_send_kvf_limits_msg(cptvf);
+	if (ret)
+		return ret;
+
+	lfs->reg_base = cptvf->reg_base;
+	lfs->pdev = cptvf->pdev;
+	lfs->mbox = &cptvf->pfvf_mbox;
+
+	lfs_num = cptvf->lfs.kvf_limits ? cptvf->lfs.kvf_limits :
+		  num_online_cpus();
+	ret = otx2_cptlf_init(lfs, eng_grp_msk, OTX2_CPT_QUEUE_HI_PRIO,
+			      lfs_num);
+	if (ret)
+		return ret;
+
+	/* Get msix offsets for attached LFs */
+	ret = otx2_cpt_msix_offset_msg(lfs);
+	if (ret)
+		goto cleanup_lf;
+
+	/* Initialize LFs software side */
+	ret = lf_sw_init(lfs);
+	if (ret)
+		goto cleanup_lf;
+
+	/* Register LFs interrupts */
+	ret = otx2_cptlf_register_interrupts(lfs);
+	if (ret)
+		goto cleanup_lf_sw;
+
+	/* Set interrupts affinity */
+	ret = otx2_cptlf_set_irqs_affinity(lfs);
+	if (ret)
+		goto unregister_intr;
+
+	atomic_set(&lfs->state, OTX2_CPTLF_STARTED);
+	/* Register crypto algorithms */
+	ret = otx2_cpt_crypto_init(lfs->pdev, THIS_MODULE, lfs_num, 1);
+	if (ret) {
+		dev_err(&lfs->pdev->dev, "algorithms registration failed\n");
+		goto disable_irqs;
+	}
+	return 0;
+
+disable_irqs:
+	otx2_cptlf_free_irqs_affinity(lfs);
+unregister_intr:
+	otx2_cptlf_unregister_interrupts(lfs);
+cleanup_lf_sw:
+	lf_sw_cleanup(lfs);
+cleanup_lf:
+	otx2_cptlf_shutdown(lfs);
+
+	return ret;
+}
+
+static int otx2_cptvf_probe(struct pci_dev *pdev,
+			    const struct pci_device_id *ent)
+{
+	struct device *dev = &pdev->dev;
+	resource_size_t offset, size;
+	struct otx2_cptvf_dev *cptvf;
+	int ret;
+
+	cptvf = devm_kzalloc(dev, sizeof(*cptvf), GFP_KERNEL);
+	if (!cptvf)
+		return -ENOMEM;
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		dev_err(dev, "Failed to enable PCI device\n");
+		goto clear_drvdata;
+	}
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+	if (ret) {
+		dev_err(dev, "Unable to get usable DMA configuration\n");
+		goto clear_drvdata;
+	}
+	/* Map VF's configuration registers */
+	ret = pcim_iomap_regions_request_all(pdev, 1 << PCI_PF_REG_BAR_NUM,
+					     OTX2_CPTVF_DRV_NAME);
+	if (ret) {
+		dev_err(dev, "Couldn't get PCI resources 0x%x\n", ret);
+		goto clear_drvdata;
+	}
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, cptvf);
+	cptvf->pdev = pdev;
+
+	cptvf->reg_base = pcim_iomap_table(pdev)[PCI_PF_REG_BAR_NUM];
+
+	offset = pci_resource_start(pdev, PCI_MBOX_BAR_NUM);
+	size = pci_resource_len(pdev, PCI_MBOX_BAR_NUM);
+	/* Map PF-VF mailbox memory */
+	cptvf->pfvf_mbox_base = devm_ioremap_wc(dev, offset, size);
+	if (!cptvf->pfvf_mbox_base) {
+		dev_err(&pdev->dev, "Unable to map BAR4\n");
+		ret = -ENODEV;
+		goto clear_drvdata;
+	}
+	/* Initialize PF<=>VF mailbox */
+	ret = cptvf_pfvf_mbox_init(cptvf);
+	if (ret)
+		goto clear_drvdata;
+
+	/* Register interrupts */
+	ret = cptvf_register_interrupts(cptvf);
+	if (ret)
+		goto destroy_pfvf_mbox;
+
+	/* Initialize CPT LFs */
+	ret = cptvf_lf_init(cptvf);
+	if (ret)
+		goto unregister_interrupts;
+
+	return 0;
+
+unregister_interrupts:
+	cptvf_disable_pfvf_mbox_intrs(cptvf);
+destroy_pfvf_mbox:
+	cptvf_pfvf_mbox_destroy(cptvf);
+clear_drvdata:
+	pci_set_drvdata(pdev, NULL);
+
+	return ret;
+}
+
+static void otx2_cptvf_remove(struct pci_dev *pdev)
+{
+	struct otx2_cptvf_dev *cptvf = pci_get_drvdata(pdev);
+
+	if (!cptvf) {
+		dev_err(&pdev->dev, "Invalid CPT VF device.\n");
+		return;
+	}
+	cptvf_lf_shutdown(&cptvf->lfs);
+	/* Disable PF-VF mailbox interrupt */
+	cptvf_disable_pfvf_mbox_intrs(cptvf);
+	/* Destroy PF-VF mbox */
+	cptvf_pfvf_mbox_destroy(cptvf);
+	pci_set_drvdata(pdev, NULL);
+}
+
+/* Supported devices */
+static const struct pci_device_id otx2_cptvf_id_table[] = {
+	{PCI_VDEVICE(CAVIUM, OTX2_CPT_PCI_VF_DEVICE_ID), 0},
+	{ 0, }  /* end of table */
+};
+
+static struct pci_driver otx2_cptvf_pci_driver = {
+	.name = OTX2_CPTVF_DRV_NAME,
+	.id_table = otx2_cptvf_id_table,
+	.probe = otx2_cptvf_probe,
+	.remove = otx2_cptvf_remove,
+};
+
+module_pci_driver(otx2_cptvf_pci_driver);
+
+MODULE_AUTHOR("Marvell");
+MODULE_DESCRIPTION("Marvell OcteonTX2 CPT Virtual Function Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_DEVICE_TABLE(pci, otx2_cptvf_id_table);
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c
new file mode 100644
index 000000000000..5d73b711cba6
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptvf.h"
+#include <rvu_reg.h>
+
+irqreturn_t otx2_cptvf_pfvf_mbox_intr(int __always_unused irq, void *arg)
+{
+	struct otx2_cptvf_dev *cptvf = arg;
+	u64 intr;
+
+	/* Read the interrupt bits */
+	intr = otx2_cpt_read64(cptvf->reg_base, BLKADDR_RVUM, 0,
+			       OTX2_RVU_VF_INT);
+
+	if (intr & 0x1ULL) {
+		/* Schedule work queue function to process the MBOX request */
+		queue_work(cptvf->pfvf_mbox_wq, &cptvf->pfvf_mbox_work);
+		/* Clear and ack the interrupt */
+		otx2_cpt_write64(cptvf->reg_base, BLKADDR_RVUM, 0,
+				 OTX2_RVU_VF_INT, 0x1ULL);
+	}
+	return IRQ_HANDLED;
+}
+
+static void process_pfvf_mbox_mbox_msg(struct otx2_cptvf_dev *cptvf,
+				       struct mbox_msghdr *msg)
+{
+	struct otx2_cptlfs_info *lfs = &cptvf->lfs;
+	struct otx2_cpt_kvf_limits_rsp *rsp_limits;
+	struct otx2_cpt_egrp_num_rsp *rsp_grp;
+	struct cpt_rd_wr_reg_msg *rsp_reg;
+	struct msix_offset_rsp *rsp_msix;
+	int i;
+
+	if (msg->id >= MBOX_MSG_MAX) {
+		dev_err(&cptvf->pdev->dev,
+			"MBOX msg with unknown ID %d\n", msg->id);
+		return;
+	}
+	if (msg->sig != OTX2_MBOX_RSP_SIG) {
+		dev_err(&cptvf->pdev->dev,
+			"MBOX msg with wrong signature %x, ID %d\n",
+			msg->sig, msg->id);
+		return;
+	}
+	switch (msg->id) {
+	case MBOX_MSG_READY:
+		cptvf->vf_id = ((msg->pcifunc >> RVU_PFVF_FUNC_SHIFT)
+				& RVU_PFVF_FUNC_MASK) - 1;
+		break;
+	case MBOX_MSG_ATTACH_RESOURCES:
+		/* Check if resources were successfully attached */
+		if (!msg->rc)
+			lfs->are_lfs_attached = 1;
+		break;
+	case MBOX_MSG_DETACH_RESOURCES:
+		/* Check if resources were successfully detached */
+		if (!msg->rc)
+			lfs->are_lfs_attached = 0;
+		break;
+	case MBOX_MSG_MSIX_OFFSET:
+		rsp_msix = (struct msix_offset_rsp *) msg;
+		for (i = 0; i < rsp_msix->cptlfs; i++)
+			lfs->lf[i].msix_offset = rsp_msix->cptlf_msixoff[i];
+		break;
+	case MBOX_MSG_CPT_RD_WR_REGISTER:
+		rsp_reg = (struct cpt_rd_wr_reg_msg *) msg;
+		if (msg->rc) {
+			dev_err(&cptvf->pdev->dev,
+				"Reg %llx rd/wr(%d) failed %d\n",
+				rsp_reg->reg_offset, rsp_reg->is_write,
+				msg->rc);
+			return;
+		}
+		if (!rsp_reg->is_write)
+			*rsp_reg->ret_val = rsp_reg->val;
+		break;
+	case MBOX_MSG_GET_ENG_GRP_NUM:
+		rsp_grp = (struct otx2_cpt_egrp_num_rsp *) msg;
+		cptvf->lfs.kcrypto_eng_grp_num = rsp_grp->eng_grp_num;
+		break;
+	case MBOX_MSG_GET_KVF_LIMITS:
+		rsp_limits = (struct otx2_cpt_kvf_limits_rsp *) msg;
+		cptvf->lfs.kvf_limits = rsp_limits->kvf_limits;
+		break;
+	default:
+		dev_err(&cptvf->pdev->dev, "Unsupported msg %d received.\n",
+			msg->id);
+		break;
+	}
+}
+
+void otx2_cptvf_pfvf_mbox_handler(struct work_struct *work)
+{
+	struct otx2_cptvf_dev *cptvf;
+	struct otx2_mbox *pfvf_mbox;
+	struct otx2_mbox_dev *mdev;
+	struct mbox_hdr *rsp_hdr;
+	struct mbox_msghdr *msg;
+	int offset, i;
+
+	/* sync with mbox memory region */
+	smp_rmb();
+
+	cptvf = container_of(work, struct otx2_cptvf_dev, pfvf_mbox_work);
+	pfvf_mbox = &cptvf->pfvf_mbox;
+	mdev = &pfvf_mbox->dev[0];
+	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + pfvf_mbox->rx_start);
+	if (rsp_hdr->num_msgs == 0)
+		return;
+	offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
+
+	for (i = 0; i < rsp_hdr->num_msgs; i++) {
+		msg = (struct mbox_msghdr *)(mdev->mbase + pfvf_mbox->rx_start +
+					     offset);
+		process_pfvf_mbox_mbox_msg(cptvf, msg);
+		offset = msg->next_msgoff;
+		mdev->msgs_acked++;
+	}
+	otx2_mbox_reset(pfvf_mbox, 0);
+}
+
+int otx2_cptvf_send_eng_grp_num_msg(struct otx2_cptvf_dev *cptvf, int eng_type)
+{
+	struct otx2_mbox *mbox = &cptvf->pfvf_mbox;
+	struct pci_dev *pdev = cptvf->pdev;
+	struct otx2_cpt_egrp_num_msg *req;
+
+	req = (struct otx2_cpt_egrp_num_msg *)
+	      otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct otx2_cpt_egrp_num_rsp));
+	if (req == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+	req->hdr.id = MBOX_MSG_GET_ENG_GRP_NUM;
+	req->hdr.sig = OTX2_MBOX_REQ_SIG;
+	req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0);
+	req->eng_type = eng_type;
+
+	return otx2_cpt_send_mbox_msg(mbox, pdev);
+}
+
+int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf)
+{
+	struct otx2_mbox *mbox = &cptvf->pfvf_mbox;
+	struct pci_dev *pdev = cptvf->pdev;
+	struct mbox_msghdr *req;
+	int ret;
+
+	req = (struct mbox_msghdr *)
+	      otx2_mbox_alloc_msg_rsp(mbox, 0, sizeof(*req),
+				      sizeof(struct otx2_cpt_kvf_limits_rsp));
+	if (req == NULL) {
+		dev_err(&pdev->dev, "RVU MBOX failed to get message.\n");
+		return -EFAULT;
+	}
+	req->id = MBOX_MSG_GET_KVF_LIMITS;
+	req->sig = OTX2_MBOX_REQ_SIG;
+	req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0);
+
+	ret = otx2_cpt_send_mbox_msg(mbox, pdev);
+
+	return ret;
+}
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c
new file mode 100644
index 000000000000..d5c1c1b7c7e4
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_reqmgr.c
@@ -0,0 +1,541 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cptvf.h"
+#include "otx2_cpt_common.h"
+
+/* SG list header size in bytes */
+#define SG_LIST_HDR_SIZE	8
+
+/* Default timeout when waiting for free pending entry in us */
+#define CPT_PENTRY_TIMEOUT	1000
+#define CPT_PENTRY_STEP		50
+
+/* Default threshold for stopping and resuming sender requests */
+#define CPT_IQ_STOP_MARGIN	128
+#define CPT_IQ_RESUME_MARGIN	512
+
+/* Default command timeout in seconds */
+#define CPT_COMMAND_TIMEOUT	4
+#define CPT_TIME_IN_RESET_COUNT 5
+
+static void otx2_cpt_dump_sg_list(struct pci_dev *pdev,
+				  struct otx2_cpt_req_info *req)
+{
+	int i;
+
+	pr_debug("Gather list size %d\n", req->in_cnt);
+	for (i = 0; i < req->in_cnt; i++) {
+		pr_debug("Buffer %d size %d, vptr 0x%p, dmaptr 0x%p\n", i,
+			 req->in[i].size, req->in[i].vptr,
+			 (void *) req->in[i].dma_addr);
+		pr_debug("Buffer hexdump (%d bytes)\n",
+			 req->in[i].size);
+		print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1,
+				     req->in[i].vptr, req->in[i].size, false);
+	}
+	pr_debug("Scatter list size %d\n", req->out_cnt);
+	for (i = 0; i < req->out_cnt; i++) {
+		pr_debug("Buffer %d size %d, vptr 0x%p, dmaptr 0x%p\n", i,
+			 req->out[i].size, req->out[i].vptr,
+			 (void *) req->out[i].dma_addr);
+		pr_debug("Buffer hexdump (%d bytes)\n", req->out[i].size);
+		print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1,
+				     req->out[i].vptr, req->out[i].size, false);
+	}
+}
+
+static inline struct otx2_cpt_pending_entry *get_free_pending_entry(
+					struct otx2_cpt_pending_queue *q,
+					int qlen)
+{
+	struct otx2_cpt_pending_entry *ent = NULL;
+
+	ent = &q->head[q->rear];
+	if (unlikely(ent->busy))
+		return NULL;
+
+	q->rear++;
+	if (unlikely(q->rear == qlen))
+		q->rear = 0;
+
+	return ent;
+}
+
+static inline u32 modulo_inc(u32 index, u32 length, u32 inc)
+{
+	if (WARN_ON(inc > length))
+		inc = length;
+
+	index += inc;
+	if (unlikely(index >= length))
+		index -= length;
+
+	return index;
+}
+
+static inline void free_pentry(struct otx2_cpt_pending_entry *pentry)
+{
+	pentry->completion_addr = NULL;
+	pentry->info = NULL;
+	pentry->callback = NULL;
+	pentry->areq = NULL;
+	pentry->resume_sender = false;
+	pentry->busy = false;
+}
+
+static inline int setup_sgio_components(struct pci_dev *pdev,
+					struct otx2_cpt_buf_ptr *list,
+					int buf_count, u8 *buffer)
+{
+	struct otx2_cpt_sglist_component *sg_ptr = NULL;
+	int ret = 0, i, j;
+	int components;
+
+	if (unlikely(!list)) {
+		dev_err(&pdev->dev, "Input list pointer is NULL\n");
+		return -EFAULT;
+	}
+
+	for (i = 0; i < buf_count; i++) {
+		if (unlikely(!list[i].vptr))
+			continue;
+		list[i].dma_addr = dma_map_single(&pdev->dev, list[i].vptr,
+						  list[i].size,
+						  DMA_BIDIRECTIONAL);
+		if (unlikely(dma_mapping_error(&pdev->dev, list[i].dma_addr))) {
+			dev_err(&pdev->dev, "Dma mapping failed\n");
+			ret = -EIO;
+			goto sg_cleanup;
+		}
+	}
+	components = buf_count / 4;
+	sg_ptr = (struct otx2_cpt_sglist_component *)buffer;
+	for (i = 0; i < components; i++) {
+		sg_ptr->len0 = cpu_to_be16(list[i * 4 + 0].size);
+		sg_ptr->len1 = cpu_to_be16(list[i * 4 + 1].size);
+		sg_ptr->len2 = cpu_to_be16(list[i * 4 + 2].size);
+		sg_ptr->len3 = cpu_to_be16(list[i * 4 + 3].size);
+		sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr);
+		sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr);
+		sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr);
+		sg_ptr->ptr3 = cpu_to_be64(list[i * 4 + 3].dma_addr);
+		sg_ptr++;
+	}
+	components = buf_count % 4;
+
+	switch (components) {
+	case 3:
+		sg_ptr->len2 = cpu_to_be16(list[i * 4 + 2].size);
+		sg_ptr->ptr2 = cpu_to_be64(list[i * 4 + 2].dma_addr);
+		fallthrough;
+	case 2:
+		sg_ptr->len1 = cpu_to_be16(list[i * 4 + 1].size);
+		sg_ptr->ptr1 = cpu_to_be64(list[i * 4 + 1].dma_addr);
+		fallthrough;
+	case 1:
+		sg_ptr->len0 = cpu_to_be16(list[i * 4 + 0].size);
+		sg_ptr->ptr0 = cpu_to_be64(list[i * 4 + 0].dma_addr);
+		break;
+	default:
+		break;
+	}
+	return ret;
+
+sg_cleanup:
+	for (j = 0; j < i; j++) {
+		if (list[j].dma_addr) {
+			dma_unmap_single(&pdev->dev, list[j].dma_addr,
+					 list[j].size, DMA_BIDIRECTIONAL);
+		}
+
+		list[j].dma_addr = 0;
+	}
+	return ret;
+}
+
+static inline struct otx2_cpt_inst_info *info_create(struct pci_dev *pdev,
+					      struct otx2_cpt_req_info *req,
+					      gfp_t gfp)
+{
+	int align = OTX2_CPT_DMA_MINALIGN;
+	struct otx2_cpt_inst_info *info;
+	u32 dlen, align_dlen, info_len;
+	u16 g_sz_bytes, s_sz_bytes;
+	u32 total_mem_len;
+
+	if (unlikely(req->in_cnt > OTX2_CPT_MAX_SG_IN_CNT ||
+		     req->out_cnt > OTX2_CPT_MAX_SG_OUT_CNT)) {
+		dev_err(&pdev->dev, "Error too many sg components\n");
+		return NULL;
+	}
+
+	g_sz_bytes = ((req->in_cnt + 3) / 4) *
+		      sizeof(struct otx2_cpt_sglist_component);
+	s_sz_bytes = ((req->out_cnt + 3) / 4) *
+		      sizeof(struct otx2_cpt_sglist_component);
+
+	dlen = g_sz_bytes + s_sz_bytes + SG_LIST_HDR_SIZE;
+	align_dlen = ALIGN(dlen, align);
+	info_len = ALIGN(sizeof(*info), align);
+	total_mem_len = align_dlen + info_len + sizeof(union otx2_cpt_res_s);
+
+	info = kzalloc(total_mem_len, gfp);
+	if (unlikely(!info))
+		return NULL;
+
+	info->dlen = dlen;
+	info->in_buffer = (u8 *)info + info_len;
+
+	((u16 *)info->in_buffer)[0] = req->out_cnt;
+	((u16 *)info->in_buffer)[1] = req->in_cnt;
+	((u16 *)info->in_buffer)[2] = 0;
+	((u16 *)info->in_buffer)[3] = 0;
+	cpu_to_be64s((u64 *)info->in_buffer);
+
+	/* Setup gather (input) components */
+	if (setup_sgio_components(pdev, req->in, req->in_cnt,
+				  &info->in_buffer[8])) {
+		dev_err(&pdev->dev, "Failed to setup gather list\n");
+		goto destroy_info;
+	}
+
+	if (setup_sgio_components(pdev, req->out, req->out_cnt,
+				  &info->in_buffer[8 + g_sz_bytes])) {
+		dev_err(&pdev->dev, "Failed to setup scatter list\n");
+		goto destroy_info;
+	}
+
+	info->dma_len = total_mem_len - info_len;
+	info->dptr_baddr = dma_map_single(&pdev->dev, info->in_buffer,
+					  info->dma_len, DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(&pdev->dev, info->dptr_baddr))) {
+		dev_err(&pdev->dev, "DMA Mapping failed for cpt req\n");
+		goto destroy_info;
+	}
+	/*
+	 * Get buffer for union otx2_cpt_res_s response
+	 * structure and its physical address
+	 */
+	info->completion_addr = info->in_buffer + align_dlen;
+	info->comp_baddr = info->dptr_baddr + align_dlen;
+
+	return info;
+
+destroy_info:
+	otx2_cpt_info_destroy(pdev, info);
+	return NULL;
+}
+
+static int process_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+			   struct otx2_cpt_pending_queue *pqueue,
+			   struct otx2_cptlf_info *lf)
+{
+	struct otx2_cptvf_request *cpt_req = &req->req;
+	struct otx2_cpt_pending_entry *pentry = NULL;
+	union otx2_cpt_ctrl_info *ctrl = &req->ctrl;
+	struct otx2_cpt_inst_info *info = NULL;
+	union otx2_cpt_res_s *result = NULL;
+	struct otx2_cpt_iq_command iq_cmd;
+	union otx2_cpt_inst_s cptinst;
+	int retry, ret = 0;
+	u8 resume_sender;
+	gfp_t gfp;
+
+	gfp = (req->areq->flags & CRYPTO_TFM_REQ_MAY_SLEEP) ? GFP_KERNEL :
+							      GFP_ATOMIC;
+	if (unlikely(!otx2_cptlf_started(lf->lfs)))
+		return -ENODEV;
+
+	info = info_create(pdev, req, gfp);
+	if (unlikely(!info)) {
+		dev_err(&pdev->dev, "Setting up cpt inst info failed");
+		return -ENOMEM;
+	}
+	cpt_req->dlen = info->dlen;
+
+	result = info->completion_addr;
+	result->s.compcode = OTX2_CPT_COMPLETION_CODE_INIT;
+
+	spin_lock_bh(&pqueue->lock);
+	pentry = get_free_pending_entry(pqueue, pqueue->qlen);
+	retry = CPT_PENTRY_TIMEOUT / CPT_PENTRY_STEP;
+	while (unlikely(!pentry) && retry--) {
+		spin_unlock_bh(&pqueue->lock);
+		udelay(CPT_PENTRY_STEP);
+		spin_lock_bh(&pqueue->lock);
+		pentry = get_free_pending_entry(pqueue, pqueue->qlen);
+	}
+
+	if (unlikely(!pentry)) {
+		ret = -ENOSPC;
+		goto destroy_info;
+	}
+
+	/*
+	 * Check if we are close to filling in entire pending queue,
+	 * if so then tell the sender to stop/sleep by returning -EBUSY
+	 * We do it only for context which can sleep (GFP_KERNEL)
+	 */
+	if (gfp == GFP_KERNEL &&
+	    pqueue->pending_count > (pqueue->qlen - CPT_IQ_STOP_MARGIN)) {
+		pentry->resume_sender = true;
+	} else
+		pentry->resume_sender = false;
+	resume_sender = pentry->resume_sender;
+	pqueue->pending_count++;
+
+	pentry->completion_addr = info->completion_addr;
+	pentry->info = info;
+	pentry->callback = req->callback;
+	pentry->areq = req->areq;
+	pentry->busy = true;
+	info->pentry = pentry;
+	info->time_in = jiffies;
+	info->req = req;
+
+	/* Fill in the command */
+	iq_cmd.cmd.u = 0;
+	iq_cmd.cmd.s.opcode = cpu_to_be16(cpt_req->opcode.flags);
+	iq_cmd.cmd.s.param1 = cpu_to_be16(cpt_req->param1);
+	iq_cmd.cmd.s.param2 = cpu_to_be16(cpt_req->param2);
+	iq_cmd.cmd.s.dlen   = cpu_to_be16(cpt_req->dlen);
+
+	/* 64-bit swap for microcode data reads, not needed for addresses*/
+	cpu_to_be64s(&iq_cmd.cmd.u);
+	iq_cmd.dptr = info->dptr_baddr;
+	iq_cmd.rptr = 0;
+	iq_cmd.cptr.u = 0;
+	iq_cmd.cptr.s.grp = ctrl->s.grp;
+
+	/* Fill in the CPT_INST_S type command for HW interpretation */
+	otx2_cpt_fill_inst(&cptinst, &iq_cmd, info->comp_baddr);
+
+	/* Print debug info if enabled */
+	otx2_cpt_dump_sg_list(pdev, req);
+	pr_debug("Cpt_inst_s hexdump (%d bytes)\n", OTX2_CPT_INST_SIZE);
+	print_hex_dump_debug("", 0, 16, 1, &cptinst, OTX2_CPT_INST_SIZE, false);
+	pr_debug("Dptr hexdump (%d bytes)\n", cpt_req->dlen);
+	print_hex_dump_debug("", 0, 16, 1, info->in_buffer,
+			     cpt_req->dlen, false);
+
+	/* Send CPT command */
+	otx2_cpt_send_cmd(&cptinst, 1, lf);
+
+	/*
+	 * We allocate and prepare pending queue entry in critical section
+	 * together with submitting CPT instruction to CPT instruction queue
+	 * to make sure that order of CPT requests is the same in both
+	 * pending and instruction queues
+	 */
+	spin_unlock_bh(&pqueue->lock);
+
+	ret = resume_sender ? -EBUSY : -EINPROGRESS;
+	return ret;
+
+destroy_info:
+	spin_unlock_bh(&pqueue->lock);
+	otx2_cpt_info_destroy(pdev, info);
+	return ret;
+}
+
+int otx2_cpt_do_request(struct pci_dev *pdev, struct otx2_cpt_req_info *req,
+			int cpu_num)
+{
+	struct otx2_cptvf_dev *cptvf = pci_get_drvdata(pdev);
+	struct otx2_cptlfs_info *lfs = &cptvf->lfs;
+
+	return process_request(lfs->pdev, req, &lfs->lf[cpu_num].pqueue,
+			       &lfs->lf[cpu_num]);
+}
+
+static int cpt_process_ccode(struct pci_dev *pdev,
+			     union otx2_cpt_res_s *cpt_status,
+			     struct otx2_cpt_inst_info *info,
+			     u32 *res_code)
+{
+	u8 uc_ccode = cpt_status->s.uc_compcode;
+	u8 ccode = cpt_status->s.compcode;
+
+	switch (ccode) {
+	case OTX2_CPT_COMP_E_FAULT:
+		dev_err(&pdev->dev,
+			"Request failed with DMA fault\n");
+		otx2_cpt_dump_sg_list(pdev, info->req);
+		break;
+
+	case OTX2_CPT_COMP_E_HWERR:
+		dev_err(&pdev->dev,
+			"Request failed with hardware error\n");
+		otx2_cpt_dump_sg_list(pdev, info->req);
+		break;
+
+	case OTX2_CPT_COMP_E_INSTERR:
+		dev_err(&pdev->dev,
+			"Request failed with instruction error\n");
+		otx2_cpt_dump_sg_list(pdev, info->req);
+		break;
+
+	case OTX2_CPT_COMP_E_NOTDONE:
+		/* check for timeout */
+		if (time_after_eq(jiffies, info->time_in +
+				  CPT_COMMAND_TIMEOUT * HZ))
+			dev_warn(&pdev->dev,
+				 "Request timed out 0x%p", info->req);
+		else if (info->extra_time < CPT_TIME_IN_RESET_COUNT) {
+			info->time_in = jiffies;
+			info->extra_time++;
+		}
+		return 1;
+
+	case OTX2_CPT_COMP_E_GOOD:
+		/*
+		 * Check microcode completion code, it is only valid
+		 * when completion code is CPT_COMP_E::GOOD
+		 */
+		if (uc_ccode != OTX2_CPT_UCC_SUCCESS) {
+			/*
+			 * If requested hmac is truncated and ucode returns
+			 * s/g write length error then we report success
+			 * because ucode writes as many bytes of calculated
+			 * hmac as available in gather buffer and reports
+			 * s/g write length error if number of bytes in gather
+			 * buffer is less than full hmac size.
+			 */
+			if (info->req->is_trunc_hmac &&
+			    uc_ccode == OTX2_CPT_UCC_SG_WRITE_LENGTH) {
+				*res_code = 0;
+				break;
+			}
+
+			dev_err(&pdev->dev,
+				"Request failed with software error code 0x%x\n",
+				cpt_status->s.uc_compcode);
+			otx2_cpt_dump_sg_list(pdev, info->req);
+			break;
+		}
+		/* Request has been processed with success */
+		*res_code = 0;
+		break;
+
+	default:
+		dev_err(&pdev->dev,
+			"Request returned invalid status %d\n", ccode);
+		break;
+	}
+	return 0;
+}
+
+static inline void process_pending_queue(struct pci_dev *pdev,
+					 struct otx2_cpt_pending_queue *pqueue)
+{
+	struct otx2_cpt_pending_entry *resume_pentry = NULL;
+	void (*callback)(int status, void *arg, void *req);
+	struct otx2_cpt_pending_entry *pentry = NULL;
+	union otx2_cpt_res_s *cpt_status = NULL;
+	struct otx2_cpt_inst_info *info = NULL;
+	struct otx2_cpt_req_info *req = NULL;
+	struct crypto_async_request *areq;
+	u32 res_code, resume_index;
+
+	while (1) {
+		spin_lock_bh(&pqueue->lock);
+		pentry = &pqueue->head[pqueue->front];
+
+		if (WARN_ON(!pentry)) {
+			spin_unlock_bh(&pqueue->lock);
+			break;
+		}
+
+		res_code = -EINVAL;
+		if (unlikely(!pentry->busy)) {
+			spin_unlock_bh(&pqueue->lock);
+			break;
+		}
+
+		if (unlikely(!pentry->callback)) {
+			dev_err(&pdev->dev, "Callback NULL\n");
+			goto process_pentry;
+		}
+
+		info = pentry->info;
+		if (unlikely(!info)) {
+			dev_err(&pdev->dev, "Pending entry post arg NULL\n");
+			goto process_pentry;
+		}
+
+		req = info->req;
+		if (unlikely(!req)) {
+			dev_err(&pdev->dev, "Request NULL\n");
+			goto process_pentry;
+		}
+
+		cpt_status = pentry->completion_addr;
+		if (unlikely(!cpt_status)) {
+			dev_err(&pdev->dev, "Completion address NULL\n");
+			goto process_pentry;
+		}
+
+		if (cpt_process_ccode(pdev, cpt_status, info, &res_code)) {
+			spin_unlock_bh(&pqueue->lock);
+			return;
+		}
+		info->pdev = pdev;
+
+process_pentry:
+		/*
+		 * Check if we should inform sending side to resume
+		 * We do it CPT_IQ_RESUME_MARGIN elements in advance before
+		 * pending queue becomes empty
+		 */
+		resume_index = modulo_inc(pqueue->front, pqueue->qlen,
+					  CPT_IQ_RESUME_MARGIN);
+		resume_pentry = &pqueue->head[resume_index];
+		if (resume_pentry &&
+		    resume_pentry->resume_sender) {
+			resume_pentry->resume_sender = false;
+			callback = resume_pentry->callback;
+			areq = resume_pentry->areq;
+
+			if (callback) {
+				spin_unlock_bh(&pqueue->lock);
+
+				/*
+				 * EINPROGRESS is an indication for sending
+				 * side that it can resume sending requests
+				 */
+				callback(-EINPROGRESS, areq, info);
+				spin_lock_bh(&pqueue->lock);
+			}
+		}
+
+		callback = pentry->callback;
+		areq = pentry->areq;
+		free_pentry(pentry);
+
+		pqueue->pending_count--;
+		pqueue->front = modulo_inc(pqueue->front, pqueue->qlen, 1);
+		spin_unlock_bh(&pqueue->lock);
+
+		/*
+		 * Call callback after current pending entry has been
+		 * processed, we don't do it if the callback pointer is
+		 * invalid.
+		 */
+		if (callback)
+			callback(res_code, areq, info);
+	}
+}
+
+void otx2_cpt_post_process(struct otx2_cptlf_wqe *wqe)
+{
+	process_pending_queue(wqe->lfs->pdev,
+			      &wqe->lfs->lf[wqe->lf_num].pqueue);
+}
+
+int otx2_cpt_get_kcrypto_eng_grp_num(struct pci_dev *pdev)
+{
+	struct otx2_cptvf_dev *cptvf = pci_get_drvdata(pdev);
+
+	return cptvf->lfs.kcrypto_eng_grp_num;
+}
diff --git a/drivers/crypto/mediatek/Makefile b/drivers/crypto/mediatek/Makefile
deleted file mode 100644
index 196a4653974e..000000000000
--- a/drivers/crypto/mediatek/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_CRYPTO_DEV_MEDIATEK) += mtk-crypto.o
-mtk-crypto-objs:= mtk-platform.o mtk-aes.o mtk-sha.o
diff --git a/drivers/crypto/mediatek/mtk-aes.c b/drivers/crypto/mediatek/mtk-aes.c
deleted file mode 100644
index 7323066724c3..000000000000
--- a/drivers/crypto/mediatek/mtk-aes.c
+++ /dev/null
@@ -1,1271 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Cryptographic API.
- *
- * Driver for EIP97 AES acceleration.
- *
- * Copyright (c) 2016 Ryder Lee <ryder.lee@mediatek.com>
- *
- * Some ideas are from atmel-aes.c drivers.
- */
-
-#include <crypto/aes.h>
-#include <crypto/gcm.h>
-#include <crypto/internal/skcipher.h>
-#include "mtk-platform.h"
-
-#define AES_QUEUE_SIZE		512
-#define AES_BUF_ORDER		2
-#define AES_BUF_SIZE		((PAGE_SIZE << AES_BUF_ORDER) \
-				& ~(AES_BLOCK_SIZE - 1))
-#define AES_MAX_STATE_BUF_SIZE	SIZE_IN_WORDS(AES_KEYSIZE_256 + \
-				AES_BLOCK_SIZE * 2)
-#define AES_MAX_CT_SIZE		6
-
-#define AES_CT_CTRL_HDR		cpu_to_le32(0x00220000)
-
-/* AES-CBC/ECB/CTR/OFB/CFB command token */
-#define AES_CMD0		cpu_to_le32(0x05000000)
-#define AES_CMD1		cpu_to_le32(0x2d060000)
-#define AES_CMD2		cpu_to_le32(0xe4a63806)
-/* AES-GCM command token */
-#define AES_GCM_CMD0		cpu_to_le32(0x0b000000)
-#define AES_GCM_CMD1		cpu_to_le32(0xa0800000)
-#define AES_GCM_CMD2		cpu_to_le32(0x25000010)
-#define AES_GCM_CMD3		cpu_to_le32(0x0f020000)
-#define AES_GCM_CMD4		cpu_to_le32(0x21e60000)
-#define AES_GCM_CMD5		cpu_to_le32(0x40e60000)
-#define AES_GCM_CMD6		cpu_to_le32(0xd0070000)
-
-/* AES transform information word 0 fields */
-#define AES_TFM_BASIC_OUT	cpu_to_le32(0x4 << 0)
-#define AES_TFM_BASIC_IN	cpu_to_le32(0x5 << 0)
-#define AES_TFM_GCM_OUT		cpu_to_le32(0x6 << 0)
-#define AES_TFM_GCM_IN		cpu_to_le32(0xf << 0)
-#define AES_TFM_SIZE(x)		cpu_to_le32((x) << 8)
-#define AES_TFM_128BITS		cpu_to_le32(0xb << 16)
-#define AES_TFM_192BITS		cpu_to_le32(0xd << 16)
-#define AES_TFM_256BITS		cpu_to_le32(0xf << 16)
-#define AES_TFM_GHASH_DIGEST	cpu_to_le32(0x2 << 21)
-#define AES_TFM_GHASH		cpu_to_le32(0x4 << 23)
-/* AES transform information word 1 fields */
-#define AES_TFM_ECB		cpu_to_le32(0x0 << 0)
-#define AES_TFM_CBC		cpu_to_le32(0x1 << 0)
-#define AES_TFM_OFB		cpu_to_le32(0x4 << 0)
-#define AES_TFM_CFB128		cpu_to_le32(0x5 << 0)
-#define AES_TFM_CTR_INIT	cpu_to_le32(0x2 << 0)	/* init counter to 1 */
-#define AES_TFM_CTR_LOAD	cpu_to_le32(0x6 << 0)	/* load/reuse counter */
-#define AES_TFM_3IV		cpu_to_le32(0x7 << 5)	/* using IV 0-2 */
-#define AES_TFM_FULL_IV		cpu_to_le32(0xf << 5)	/* using IV 0-3 */
-#define AES_TFM_IV_CTR_MODE	cpu_to_le32(0x1 << 10)
-#define AES_TFM_ENC_HASH	cpu_to_le32(0x1 << 17)
-
-/* AES flags */
-#define AES_FLAGS_CIPHER_MSK	GENMASK(4, 0)
-#define AES_FLAGS_ECB		BIT(0)
-#define AES_FLAGS_CBC		BIT(1)
-#define AES_FLAGS_CTR		BIT(2)
-#define AES_FLAGS_OFB		BIT(3)
-#define AES_FLAGS_CFB128	BIT(4)
-#define AES_FLAGS_GCM		BIT(5)
-#define AES_FLAGS_ENCRYPT	BIT(6)
-#define AES_FLAGS_BUSY		BIT(7)
-
-#define AES_AUTH_TAG_ERR	cpu_to_le32(BIT(26))
-
-/**
- * mtk_aes_info - hardware information of AES
- * @cmd:	command token, hardware instruction
- * @tfm:	transform state of cipher algorithm.
- * @state:	contains keys and initial vectors.
- *
- * Memory layout of GCM buffer:
- * /-----------\
- * |  AES KEY  | 128/196/256 bits
- * |-----------|
- * |  HASH KEY | a string 128 zero bits encrypted using the block cipher
- * |-----------|
- * |    IVs    | 4 * 4 bytes
- * \-----------/
- *
- * The engine requires all these info to do:
- * - Commands decoding and control of the engine's data path.
- * - Coordinating hardware data fetch and store operations.
- * - Result token construction and output.
- */
-struct mtk_aes_info {
-	__le32 cmd[AES_MAX_CT_SIZE];
-	__le32 tfm[2];
-	__le32 state[AES_MAX_STATE_BUF_SIZE];
-};
-
-struct mtk_aes_reqctx {
-	u64 mode;
-};
-
-struct mtk_aes_base_ctx {
-	struct mtk_cryp *cryp;
-	u32 keylen;
-	__le32 key[12];
-	__le32 keymode;
-
-	mtk_aes_fn start;
-
-	struct mtk_aes_info info;
-	dma_addr_t ct_dma;
-	dma_addr_t tfm_dma;
-
-	__le32 ct_hdr;
-	u32 ct_size;
-};
-
-struct mtk_aes_ctx {
-	struct mtk_aes_base_ctx	base;
-};
-
-struct mtk_aes_ctr_ctx {
-	struct mtk_aes_base_ctx base;
-
-	__be32	iv[AES_BLOCK_SIZE / sizeof(u32)];
-	size_t offset;
-	struct scatterlist src[2];
-	struct scatterlist dst[2];
-};
-
-struct mtk_aes_gcm_ctx {
-	struct mtk_aes_base_ctx base;
-
-	u32 authsize;
-	size_t textlen;
-};
-
-struct mtk_aes_drv {
-	struct list_head dev_list;
-	/* Device list lock */
-	spinlock_t lock;
-};
-
-static struct mtk_aes_drv mtk_aes = {
-	.dev_list = LIST_HEAD_INIT(mtk_aes.dev_list),
-	.lock = __SPIN_LOCK_UNLOCKED(mtk_aes.lock),
-};
-
-static inline u32 mtk_aes_read(struct mtk_cryp *cryp, u32 offset)
-{
-	return readl_relaxed(cryp->base + offset);
-}
-
-static inline void mtk_aes_write(struct mtk_cryp *cryp,
-				 u32 offset, u32 value)
-{
-	writel_relaxed(value, cryp->base + offset);
-}
-
-static struct mtk_cryp *mtk_aes_find_dev(struct mtk_aes_base_ctx *ctx)
-{
-	struct mtk_cryp *cryp = NULL;
-	struct mtk_cryp *tmp;
-
-	spin_lock_bh(&mtk_aes.lock);
-	if (!ctx->cryp) {
-		list_for_each_entry(tmp, &mtk_aes.dev_list, aes_list) {
-			cryp = tmp;
-			break;
-		}
-		ctx->cryp = cryp;
-	} else {
-		cryp = ctx->cryp;
-	}
-	spin_unlock_bh(&mtk_aes.lock);
-
-	return cryp;
-}
-
-static inline size_t mtk_aes_padlen(size_t len)
-{
-	len &= AES_BLOCK_SIZE - 1;
-	return len ? AES_BLOCK_SIZE - len : 0;
-}
-
-static bool mtk_aes_check_aligned(struct scatterlist *sg, size_t len,
-				  struct mtk_aes_dma *dma)
-{
-	int nents;
-
-	if (!IS_ALIGNED(len, AES_BLOCK_SIZE))
-		return false;
-
-	for (nents = 0; sg; sg = sg_next(sg), ++nents) {
-		if (!IS_ALIGNED(sg->offset, sizeof(u32)))
-			return false;
-
-		if (len <= sg->length) {
-			if (!IS_ALIGNED(len, AES_BLOCK_SIZE))
-				return false;
-
-			dma->nents = nents + 1;
-			dma->remainder = sg->length - len;
-			sg->length = len;
-			return true;
-		}
-
-		if (!IS_ALIGNED(sg->length, AES_BLOCK_SIZE))
-			return false;
-
-		len -= sg->length;
-	}
-
-	return false;
-}
-
-static inline void mtk_aes_set_mode(struct mtk_aes_rec *aes,
-				    const struct mtk_aes_reqctx *rctx)
-{
-	/* Clear all but persistent flags and set request flags. */
-	aes->flags = (aes->flags & AES_FLAGS_BUSY) | rctx->mode;
-}
-
-static inline void mtk_aes_restore_sg(const struct mtk_aes_dma *dma)
-{
-	struct scatterlist *sg = dma->sg;
-	int nents = dma->nents;
-
-	if (!dma->remainder)
-		return;
-
-	while (--nents > 0 && sg)
-		sg = sg_next(sg);
-
-	if (!sg)
-		return;
-
-	sg->length += dma->remainder;
-}
-
-static inline int mtk_aes_complete(struct mtk_cryp *cryp,
-				   struct mtk_aes_rec *aes,
-				   int err)
-{
-	aes->flags &= ~AES_FLAGS_BUSY;
-	aes->areq->complete(aes->areq, err);
-	/* Handle new request */
-	tasklet_schedule(&aes->queue_task);
-	return err;
-}
-
-/*
- * Write descriptors for processing. This will configure the engine, load
- * the transform information and then start the packet processing.
- */
-static int mtk_aes_xmit(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
-{
-	struct mtk_ring *ring = cryp->ring[aes->id];
-	struct mtk_desc *cmd = NULL, *res = NULL;
-	struct scatterlist *ssg = aes->src.sg, *dsg = aes->dst.sg;
-	u32 slen = aes->src.sg_len, dlen = aes->dst.sg_len;
-	int nents;
-
-	/* Write command descriptors */
-	for (nents = 0; nents < slen; ++nents, ssg = sg_next(ssg)) {
-		cmd = ring->cmd_next;
-		cmd->hdr = MTK_DESC_BUF_LEN(ssg->length);
-		cmd->buf = cpu_to_le32(sg_dma_address(ssg));
-
-		if (nents == 0) {
-			cmd->hdr |= MTK_DESC_FIRST |
-				    MTK_DESC_CT_LEN(aes->ctx->ct_size);
-			cmd->ct = cpu_to_le32(aes->ctx->ct_dma);
-			cmd->ct_hdr = aes->ctx->ct_hdr;
-			cmd->tfm = cpu_to_le32(aes->ctx->tfm_dma);
-		}
-
-		/* Shift ring buffer and check boundary */
-		if (++ring->cmd_next == ring->cmd_base + MTK_DESC_NUM)
-			ring->cmd_next = ring->cmd_base;
-	}
-	cmd->hdr |= MTK_DESC_LAST;
-
-	/* Prepare result descriptors */
-	for (nents = 0; nents < dlen; ++nents, dsg = sg_next(dsg)) {
-		res = ring->res_next;
-		res->hdr = MTK_DESC_BUF_LEN(dsg->length);
-		res->buf = cpu_to_le32(sg_dma_address(dsg));
-
-		if (nents == 0)
-			res->hdr |= MTK_DESC_FIRST;
-
-		/* Shift ring buffer and check boundary */
-		if (++ring->res_next == ring->res_base + MTK_DESC_NUM)
-			ring->res_next = ring->res_base;
-	}
-	res->hdr |= MTK_DESC_LAST;
-
-	/* Pointer to current result descriptor */
-	ring->res_prev = res;
-
-	/* Prepare enough space for authenticated tag */
-	if (aes->flags & AES_FLAGS_GCM)
-		le32_add_cpu(&res->hdr, AES_BLOCK_SIZE);
-
-	/*
-	 * Make sure that all changes to the DMA ring are done before we
-	 * start engine.
-	 */
-	wmb();
-	/* Start DMA transfer */
-	mtk_aes_write(cryp, RDR_PREP_COUNT(aes->id), MTK_DESC_CNT(dlen));
-	mtk_aes_write(cryp, CDR_PREP_COUNT(aes->id), MTK_DESC_CNT(slen));
-
-	return -EINPROGRESS;
-}
-
-static void mtk_aes_unmap(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
-{
-	struct mtk_aes_base_ctx *ctx = aes->ctx;
-
-	dma_unmap_single(cryp->dev, ctx->ct_dma, sizeof(ctx->info),
-			 DMA_TO_DEVICE);
-
-	if (aes->src.sg == aes->dst.sg) {
-		dma_unmap_sg(cryp->dev, aes->src.sg, aes->src.nents,
-			     DMA_BIDIRECTIONAL);
-
-		if (aes->src.sg != &aes->aligned_sg)
-			mtk_aes_restore_sg(&aes->src);
-	} else {
-		dma_unmap_sg(cryp->dev, aes->dst.sg, aes->dst.nents,
-			     DMA_FROM_DEVICE);
-
-		if (aes->dst.sg != &aes->aligned_sg)
-			mtk_aes_restore_sg(&aes->dst);
-
-		dma_unmap_sg(cryp->dev, aes->src.sg, aes->src.nents,
-			     DMA_TO_DEVICE);
-
-		if (aes->src.sg != &aes->aligned_sg)
-			mtk_aes_restore_sg(&aes->src);
-	}
-
-	if (aes->dst.sg == &aes->aligned_sg)
-		sg_copy_from_buffer(aes->real_dst, sg_nents(aes->real_dst),
-				    aes->buf, aes->total);
-}
-
-static int mtk_aes_map(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
-{
-	struct mtk_aes_base_ctx *ctx = aes->ctx;
-	struct mtk_aes_info *info = &ctx->info;
-
-	ctx->ct_dma = dma_map_single(cryp->dev, info, sizeof(*info),
-				     DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(cryp->dev, ctx->ct_dma)))
-		goto exit;
-
-	ctx->tfm_dma = ctx->ct_dma + sizeof(info->cmd);
-
-	if (aes->src.sg == aes->dst.sg) {
-		aes->src.sg_len = dma_map_sg(cryp->dev, aes->src.sg,
-					     aes->src.nents,
-					     DMA_BIDIRECTIONAL);
-		aes->dst.sg_len = aes->src.sg_len;
-		if (unlikely(!aes->src.sg_len))
-			goto sg_map_err;
-	} else {
-		aes->src.sg_len = dma_map_sg(cryp->dev, aes->src.sg,
-					     aes->src.nents, DMA_TO_DEVICE);
-		if (unlikely(!aes->src.sg_len))
-			goto sg_map_err;
-
-		aes->dst.sg_len = dma_map_sg(cryp->dev, aes->dst.sg,
-					     aes->dst.nents, DMA_FROM_DEVICE);
-		if (unlikely(!aes->dst.sg_len)) {
-			dma_unmap_sg(cryp->dev, aes->src.sg, aes->src.nents,
-				     DMA_TO_DEVICE);
-			goto sg_map_err;
-		}
-	}
-
-	return mtk_aes_xmit(cryp, aes);
-
-sg_map_err:
-	dma_unmap_single(cryp->dev, ctx->ct_dma, sizeof(*info), DMA_TO_DEVICE);
-exit:
-	return mtk_aes_complete(cryp, aes, -EINVAL);
-}
-
-/* Initialize transform information of CBC/ECB/CTR/OFB/CFB mode */
-static void mtk_aes_info_init(struct mtk_cryp *cryp, struct mtk_aes_rec *aes,
-			      size_t len)
-{
-	struct skcipher_request *req = skcipher_request_cast(aes->areq);
-	struct mtk_aes_base_ctx *ctx = aes->ctx;
-	struct mtk_aes_info *info = &ctx->info;
-	u32 cnt = 0;
-
-	ctx->ct_hdr = AES_CT_CTRL_HDR | cpu_to_le32(len);
-	info->cmd[cnt++] = AES_CMD0 | cpu_to_le32(len);
-	info->cmd[cnt++] = AES_CMD1;
-
-	info->tfm[0] = AES_TFM_SIZE(ctx->keylen) | ctx->keymode;
-	if (aes->flags & AES_FLAGS_ENCRYPT)
-		info->tfm[0] |= AES_TFM_BASIC_OUT;
-	else
-		info->tfm[0] |= AES_TFM_BASIC_IN;
-
-	switch (aes->flags & AES_FLAGS_CIPHER_MSK) {
-	case AES_FLAGS_CBC:
-		info->tfm[1] = AES_TFM_CBC;
-		break;
-	case AES_FLAGS_ECB:
-		info->tfm[1] = AES_TFM_ECB;
-		goto ecb;
-	case AES_FLAGS_CTR:
-		info->tfm[1] = AES_TFM_CTR_LOAD;
-		goto ctr;
-	case AES_FLAGS_OFB:
-		info->tfm[1] = AES_TFM_OFB;
-		break;
-	case AES_FLAGS_CFB128:
-		info->tfm[1] = AES_TFM_CFB128;
-		break;
-	default:
-		/* Should not happen... */
-		return;
-	}
-
-	memcpy(info->state + ctx->keylen, req->iv, AES_BLOCK_SIZE);
-ctr:
-	le32_add_cpu(&info->tfm[0],
-		     le32_to_cpu(AES_TFM_SIZE(SIZE_IN_WORDS(AES_BLOCK_SIZE))));
-	info->tfm[1] |= AES_TFM_FULL_IV;
-	info->cmd[cnt++] = AES_CMD2;
-ecb:
-	ctx->ct_size = cnt;
-}
-
-static int mtk_aes_dma(struct mtk_cryp *cryp, struct mtk_aes_rec *aes,
-		       struct scatterlist *src, struct scatterlist *dst,
-		       size_t len)
-{
-	size_t padlen = 0;
-	bool src_aligned, dst_aligned;
-
-	aes->total = len;
-	aes->src.sg = src;
-	aes->dst.sg = dst;
-	aes->real_dst = dst;
-
-	src_aligned = mtk_aes_check_aligned(src, len, &aes->src);
-	if (src == dst)
-		dst_aligned = src_aligned;
-	else
-		dst_aligned = mtk_aes_check_aligned(dst, len, &aes->dst);
-
-	if (!src_aligned || !dst_aligned) {
-		padlen = mtk_aes_padlen(len);
-
-		if (len + padlen > AES_BUF_SIZE)
-			return mtk_aes_complete(cryp, aes, -ENOMEM);
-
-		if (!src_aligned) {
-			sg_copy_to_buffer(src, sg_nents(src), aes->buf, len);
-			aes->src.sg = &aes->aligned_sg;
-			aes->src.nents = 1;
-			aes->src.remainder = 0;
-		}
-
-		if (!dst_aligned) {
-			aes->dst.sg = &aes->aligned_sg;
-			aes->dst.nents = 1;
-			aes->dst.remainder = 0;
-		}
-
-		sg_init_table(&aes->aligned_sg, 1);
-		sg_set_buf(&aes->aligned_sg, aes->buf, len + padlen);
-	}
-
-	mtk_aes_info_init(cryp, aes, len + padlen);
-
-	return mtk_aes_map(cryp, aes);
-}
-
-static int mtk_aes_handle_queue(struct mtk_cryp *cryp, u8 id,
-				struct crypto_async_request *new_areq)
-{
-	struct mtk_aes_rec *aes = cryp->aes[id];
-	struct crypto_async_request *areq, *backlog;
-	struct mtk_aes_base_ctx *ctx;
-	unsigned long flags;
-	int ret = 0;
-
-	spin_lock_irqsave(&aes->lock, flags);
-	if (new_areq)
-		ret = crypto_enqueue_request(&aes->queue, new_areq);
-	if (aes->flags & AES_FLAGS_BUSY) {
-		spin_unlock_irqrestore(&aes->lock, flags);
-		return ret;
-	}
-	backlog = crypto_get_backlog(&aes->queue);
-	areq = crypto_dequeue_request(&aes->queue);
-	if (areq)
-		aes->flags |= AES_FLAGS_BUSY;
-	spin_unlock_irqrestore(&aes->lock, flags);
-
-	if (!areq)
-		return ret;
-
-	if (backlog)
-		backlog->complete(backlog, -EINPROGRESS);
-
-	ctx = crypto_tfm_ctx(areq->tfm);
-	/* Write key into state buffer */
-	memcpy(ctx->info.state, ctx->key, sizeof(ctx->key));
-
-	aes->areq = areq;
-	aes->ctx = ctx;
-
-	return ctx->start(cryp, aes);
-}
-
-static int mtk_aes_transfer_complete(struct mtk_cryp *cryp,
-				     struct mtk_aes_rec *aes)
-{
-	return mtk_aes_complete(cryp, aes, 0);
-}
-
-static int mtk_aes_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
-{
-	struct skcipher_request *req = skcipher_request_cast(aes->areq);
-	struct mtk_aes_reqctx *rctx = skcipher_request_ctx(req);
-
-	mtk_aes_set_mode(aes, rctx);
-	aes->resume = mtk_aes_transfer_complete;
-
-	return mtk_aes_dma(cryp, aes, req->src, req->dst, req->cryptlen);
-}
-
-static inline struct mtk_aes_ctr_ctx *
-mtk_aes_ctr_ctx_cast(struct mtk_aes_base_ctx *ctx)
-{
-	return container_of(ctx, struct mtk_aes_ctr_ctx, base);
-}
-
-static int mtk_aes_ctr_transfer(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
-{
-	struct mtk_aes_base_ctx *ctx = aes->ctx;
-	struct mtk_aes_ctr_ctx *cctx = mtk_aes_ctr_ctx_cast(ctx);
-	struct skcipher_request *req = skcipher_request_cast(aes->areq);
-	struct scatterlist *src, *dst;
-	u32 start, end, ctr, blocks;
-	size_t datalen;
-	bool fragmented = false;
-
-	/* Check for transfer completion. */
-	cctx->offset += aes->total;
-	if (cctx->offset >= req->cryptlen)
-		return mtk_aes_transfer_complete(cryp, aes);
-
-	/* Compute data length. */
-	datalen = req->cryptlen - cctx->offset;
-	blocks = DIV_ROUND_UP(datalen, AES_BLOCK_SIZE);
-	ctr = be32_to_cpu(cctx->iv[3]);
-
-	/* Check 32bit counter overflow. */
-	start = ctr;
-	end = start + blocks - 1;
-	if (end < start) {
-		ctr = 0xffffffff;
-		datalen = AES_BLOCK_SIZE * -start;
-		fragmented = true;
-	}
-
-	/* Jump to offset. */
-	src = scatterwalk_ffwd(cctx->src, req->src, cctx->offset);
-	dst = ((req->src == req->dst) ? src :
-	       scatterwalk_ffwd(cctx->dst, req->dst, cctx->offset));
-
-	/* Write IVs into transform state buffer. */
-	memcpy(ctx->info.state + ctx->keylen, cctx->iv, AES_BLOCK_SIZE);
-
-	if (unlikely(fragmented)) {
-	/*
-	 * Increment the counter manually to cope with the hardware
-	 * counter overflow.
-	 */
-		cctx->iv[3] = cpu_to_be32(ctr);
-		crypto_inc((u8 *)cctx->iv, AES_BLOCK_SIZE);
-	}
-
-	return mtk_aes_dma(cryp, aes, src, dst, datalen);
-}
-
-static int mtk_aes_ctr_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
-{
-	struct mtk_aes_ctr_ctx *cctx = mtk_aes_ctr_ctx_cast(aes->ctx);
-	struct skcipher_request *req = skcipher_request_cast(aes->areq);
-	struct mtk_aes_reqctx *rctx = skcipher_request_ctx(req);
-
-	mtk_aes_set_mode(aes, rctx);
-
-	memcpy(cctx->iv, req->iv, AES_BLOCK_SIZE);
-	cctx->offset = 0;
-	aes->total = 0;
-	aes->resume = mtk_aes_ctr_transfer;
-
-	return mtk_aes_ctr_transfer(cryp, aes);
-}
-
-/* Check and set the AES key to transform state buffer */
-static int mtk_aes_setkey(struct crypto_skcipher *tfm,
-			  const u8 *key, u32 keylen)
-{
-	struct mtk_aes_base_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	switch (keylen) {
-	case AES_KEYSIZE_128:
-		ctx->keymode = AES_TFM_128BITS;
-		break;
-	case AES_KEYSIZE_192:
-		ctx->keymode = AES_TFM_192BITS;
-		break;
-	case AES_KEYSIZE_256:
-		ctx->keymode = AES_TFM_256BITS;
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	ctx->keylen = SIZE_IN_WORDS(keylen);
-	memcpy(ctx->key, key, keylen);
-
-	return 0;
-}
-
-static int mtk_aes_crypt(struct skcipher_request *req, u64 mode)
-{
-	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
-	struct mtk_aes_base_ctx *ctx = crypto_skcipher_ctx(skcipher);
-	struct mtk_aes_reqctx *rctx;
-	struct mtk_cryp *cryp;
-
-	cryp = mtk_aes_find_dev(ctx);
-	if (!cryp)
-		return -ENODEV;
-
-	rctx = skcipher_request_ctx(req);
-	rctx->mode = mode;
-
-	return mtk_aes_handle_queue(cryp, !(mode & AES_FLAGS_ENCRYPT),
-				    &req->base);
-}
-
-static int mtk_aes_ecb_encrypt(struct skcipher_request *req)
-{
-	return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_ECB);
-}
-
-static int mtk_aes_ecb_decrypt(struct skcipher_request *req)
-{
-	return mtk_aes_crypt(req, AES_FLAGS_ECB);
-}
-
-static int mtk_aes_cbc_encrypt(struct skcipher_request *req)
-{
-	return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_CBC);
-}
-
-static int mtk_aes_cbc_decrypt(struct skcipher_request *req)
-{
-	return mtk_aes_crypt(req, AES_FLAGS_CBC);
-}
-
-static int mtk_aes_ctr_encrypt(struct skcipher_request *req)
-{
-	return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_CTR);
-}
-
-static int mtk_aes_ctr_decrypt(struct skcipher_request *req)
-{
-	return mtk_aes_crypt(req, AES_FLAGS_CTR);
-}
-
-static int mtk_aes_ofb_encrypt(struct skcipher_request *req)
-{
-	return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_OFB);
-}
-
-static int mtk_aes_ofb_decrypt(struct skcipher_request *req)
-{
-	return mtk_aes_crypt(req, AES_FLAGS_OFB);
-}
-
-static int mtk_aes_cfb_encrypt(struct skcipher_request *req)
-{
-	return mtk_aes_crypt(req, AES_FLAGS_ENCRYPT | AES_FLAGS_CFB128);
-}
-
-static int mtk_aes_cfb_decrypt(struct skcipher_request *req)
-{
-	return mtk_aes_crypt(req, AES_FLAGS_CFB128);
-}
-
-static int mtk_aes_init_tfm(struct crypto_skcipher *tfm)
-{
-	struct mtk_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	crypto_skcipher_set_reqsize(tfm, sizeof(struct mtk_aes_reqctx));
-	ctx->base.start = mtk_aes_start;
-	return 0;
-}
-
-static int mtk_aes_ctr_init_tfm(struct crypto_skcipher *tfm)
-{
-	struct mtk_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	crypto_skcipher_set_reqsize(tfm, sizeof(struct mtk_aes_reqctx));
-	ctx->base.start = mtk_aes_ctr_start;
-	return 0;
-}
-
-static struct skcipher_alg aes_algs[] = {
-{
-	.base.cra_name		= "cbc(aes)",
-	.base.cra_driver_name	= "cbc-aes-mtk",
-	.base.cra_priority	= 400,
-	.base.cra_flags		= CRYPTO_ALG_ASYNC,
-	.base.cra_blocksize	= AES_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct mtk_aes_ctx),
-	.base.cra_alignmask	= 0xf,
-	.base.cra_module	= THIS_MODULE,
-
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.setkey			= mtk_aes_setkey,
-	.encrypt		= mtk_aes_cbc_encrypt,
-	.decrypt		= mtk_aes_cbc_decrypt,
-	.ivsize			= AES_BLOCK_SIZE,
-	.init			= mtk_aes_init_tfm,
-},
-{
-	.base.cra_name		= "ecb(aes)",
-	.base.cra_driver_name	= "ecb-aes-mtk",
-	.base.cra_priority	= 400,
-	.base.cra_flags		= CRYPTO_ALG_ASYNC,
-	.base.cra_blocksize	= AES_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct mtk_aes_ctx),
-	.base.cra_alignmask	= 0xf,
-	.base.cra_module	= THIS_MODULE,
-
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.setkey			= mtk_aes_setkey,
-	.encrypt		= mtk_aes_ecb_encrypt,
-	.decrypt		= mtk_aes_ecb_decrypt,
-	.init			= mtk_aes_init_tfm,
-},
-{
-	.base.cra_name		= "ctr(aes)",
-	.base.cra_driver_name	= "ctr-aes-mtk",
-	.base.cra_priority	= 400,
-	.base.cra_flags		= CRYPTO_ALG_ASYNC,
-	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct mtk_aes_ctx),
-	.base.cra_alignmask	= 0xf,
-	.base.cra_module	= THIS_MODULE,
-
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.ivsize			= AES_BLOCK_SIZE,
-	.setkey			= mtk_aes_setkey,
-	.encrypt		= mtk_aes_ctr_encrypt,
-	.decrypt		= mtk_aes_ctr_decrypt,
-	.init			= mtk_aes_ctr_init_tfm,
-},
-{
-	.base.cra_name		= "ofb(aes)",
-	.base.cra_driver_name	= "ofb-aes-mtk",
-	.base.cra_priority	= 400,
-	.base.cra_flags		= CRYPTO_ALG_ASYNC,
-	.base.cra_blocksize	= AES_BLOCK_SIZE,
-	.base.cra_ctxsize	= sizeof(struct mtk_aes_ctx),
-	.base.cra_alignmask	= 0xf,
-	.base.cra_module	= THIS_MODULE,
-
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.ivsize			= AES_BLOCK_SIZE,
-	.setkey			= mtk_aes_setkey,
-	.encrypt		= mtk_aes_ofb_encrypt,
-	.decrypt		= mtk_aes_ofb_decrypt,
-},
-{
-	.base.cra_name		= "cfb(aes)",
-	.base.cra_driver_name	= "cfb-aes-mtk",
-	.base.cra_priority	= 400,
-	.base.cra_flags		= CRYPTO_ALG_ASYNC,
-	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct mtk_aes_ctx),
-	.base.cra_alignmask	= 0xf,
-	.base.cra_module	= THIS_MODULE,
-
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.ivsize			= AES_BLOCK_SIZE,
-	.setkey			= mtk_aes_setkey,
-	.encrypt		= mtk_aes_cfb_encrypt,
-	.decrypt		= mtk_aes_cfb_decrypt,
-},
-};
-
-static inline struct mtk_aes_gcm_ctx *
-mtk_aes_gcm_ctx_cast(struct mtk_aes_base_ctx *ctx)
-{
-	return container_of(ctx, struct mtk_aes_gcm_ctx, base);
-}
-
-/*
- * Engine will verify and compare tag automatically, so we just need
- * to check returned status which stored in the result descriptor.
- */
-static int mtk_aes_gcm_tag_verify(struct mtk_cryp *cryp,
-				  struct mtk_aes_rec *aes)
-{
-	__le32 status = cryp->ring[aes->id]->res_prev->ct;
-
-	return mtk_aes_complete(cryp, aes, (status & AES_AUTH_TAG_ERR) ?
-				-EBADMSG : 0);
-}
-
-/* Initialize transform information of GCM mode */
-static void mtk_aes_gcm_info_init(struct mtk_cryp *cryp,
-				  struct mtk_aes_rec *aes,
-				  size_t len)
-{
-	struct aead_request *req = aead_request_cast(aes->areq);
-	struct mtk_aes_base_ctx *ctx = aes->ctx;
-	struct mtk_aes_gcm_ctx *gctx = mtk_aes_gcm_ctx_cast(ctx);
-	struct mtk_aes_info *info = &ctx->info;
-	u32 ivsize = crypto_aead_ivsize(crypto_aead_reqtfm(req));
-	u32 cnt = 0;
-
-	ctx->ct_hdr = AES_CT_CTRL_HDR | cpu_to_le32(len);
-
-	info->cmd[cnt++] = AES_GCM_CMD0 | cpu_to_le32(req->assoclen);
-	info->cmd[cnt++] = AES_GCM_CMD1 | cpu_to_le32(req->assoclen);
-	info->cmd[cnt++] = AES_GCM_CMD2;
-	info->cmd[cnt++] = AES_GCM_CMD3 | cpu_to_le32(gctx->textlen);
-
-	if (aes->flags & AES_FLAGS_ENCRYPT) {
-		info->cmd[cnt++] = AES_GCM_CMD4 | cpu_to_le32(gctx->authsize);
-		info->tfm[0] = AES_TFM_GCM_OUT;
-	} else {
-		info->cmd[cnt++] = AES_GCM_CMD5 | cpu_to_le32(gctx->authsize);
-		info->cmd[cnt++] = AES_GCM_CMD6 | cpu_to_le32(gctx->authsize);
-		info->tfm[0] = AES_TFM_GCM_IN;
-	}
-	ctx->ct_size = cnt;
-
-	info->tfm[0] |= AES_TFM_GHASH_DIGEST | AES_TFM_GHASH | AES_TFM_SIZE(
-			ctx->keylen + SIZE_IN_WORDS(AES_BLOCK_SIZE + ivsize)) |
-			ctx->keymode;
-	info->tfm[1] = AES_TFM_CTR_INIT | AES_TFM_IV_CTR_MODE | AES_TFM_3IV |
-		       AES_TFM_ENC_HASH;
-
-	memcpy(info->state + ctx->keylen + SIZE_IN_WORDS(AES_BLOCK_SIZE),
-	       req->iv, ivsize);
-}
-
-static int mtk_aes_gcm_dma(struct mtk_cryp *cryp, struct mtk_aes_rec *aes,
-			   struct scatterlist *src, struct scatterlist *dst,
-			   size_t len)
-{
-	bool src_aligned, dst_aligned;
-
-	aes->src.sg = src;
-	aes->dst.sg = dst;
-	aes->real_dst = dst;
-
-	src_aligned = mtk_aes_check_aligned(src, len, &aes->src);
-	if (src == dst)
-		dst_aligned = src_aligned;
-	else
-		dst_aligned = mtk_aes_check_aligned(dst, len, &aes->dst);
-
-	if (!src_aligned || !dst_aligned) {
-		if (aes->total > AES_BUF_SIZE)
-			return mtk_aes_complete(cryp, aes, -ENOMEM);
-
-		if (!src_aligned) {
-			sg_copy_to_buffer(src, sg_nents(src), aes->buf, len);
-			aes->src.sg = &aes->aligned_sg;
-			aes->src.nents = 1;
-			aes->src.remainder = 0;
-		}
-
-		if (!dst_aligned) {
-			aes->dst.sg = &aes->aligned_sg;
-			aes->dst.nents = 1;
-			aes->dst.remainder = 0;
-		}
-
-		sg_init_table(&aes->aligned_sg, 1);
-		sg_set_buf(&aes->aligned_sg, aes->buf, aes->total);
-	}
-
-	mtk_aes_gcm_info_init(cryp, aes, len);
-
-	return mtk_aes_map(cryp, aes);
-}
-
-/* Todo: GMAC */
-static int mtk_aes_gcm_start(struct mtk_cryp *cryp, struct mtk_aes_rec *aes)
-{
-	struct mtk_aes_gcm_ctx *gctx = mtk_aes_gcm_ctx_cast(aes->ctx);
-	struct aead_request *req = aead_request_cast(aes->areq);
-	struct mtk_aes_reqctx *rctx = aead_request_ctx(req);
-	u32 len = req->assoclen + req->cryptlen;
-
-	mtk_aes_set_mode(aes, rctx);
-
-	if (aes->flags & AES_FLAGS_ENCRYPT) {
-		u32 tag[4];
-
-		aes->resume = mtk_aes_transfer_complete;
-		/* Compute total process length. */
-		aes->total = len + gctx->authsize;
-		/* Hardware will append authenticated tag to output buffer */
-		scatterwalk_map_and_copy(tag, req->dst, len, gctx->authsize, 1);
-	} else {
-		aes->resume = mtk_aes_gcm_tag_verify;
-		aes->total = len;
-	}
-
-	return mtk_aes_gcm_dma(cryp, aes, req->src, req->dst, len);
-}
-
-static int mtk_aes_gcm_crypt(struct aead_request *req, u64 mode)
-{
-	struct mtk_aes_base_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
-	struct mtk_aes_gcm_ctx *gctx = mtk_aes_gcm_ctx_cast(ctx);
-	struct mtk_aes_reqctx *rctx = aead_request_ctx(req);
-	struct mtk_cryp *cryp;
-	bool enc = !!(mode & AES_FLAGS_ENCRYPT);
-
-	cryp = mtk_aes_find_dev(ctx);
-	if (!cryp)
-		return -ENODEV;
-
-	/* Compute text length. */
-	gctx->textlen = req->cryptlen - (enc ? 0 : gctx->authsize);
-
-	/* Empty messages are not supported yet */
-	if (!gctx->textlen && !req->assoclen)
-		return -EINVAL;
-
-	rctx->mode = AES_FLAGS_GCM | mode;
-
-	return mtk_aes_handle_queue(cryp, enc, &req->base);
-}
-
-/*
- * Because of the hardware limitation, we need to pre-calculate key(H)
- * for the GHASH operation. The result of the encryption operation
- * need to be stored in the transform state buffer.
- */
-static int mtk_aes_gcm_setkey(struct crypto_aead *aead, const u8 *key,
-			      u32 keylen)
-{
-	struct mtk_aes_base_ctx *ctx = crypto_aead_ctx(aead);
-	union {
-		u32 x32[SIZE_IN_WORDS(AES_BLOCK_SIZE)];
-		u8 x8[AES_BLOCK_SIZE];
-	} hash = {};
-	struct crypto_aes_ctx aes_ctx;
-	int err;
-	int i;
-
-	switch (keylen) {
-	case AES_KEYSIZE_128:
-		ctx->keymode = AES_TFM_128BITS;
-		break;
-	case AES_KEYSIZE_192:
-		ctx->keymode = AES_TFM_192BITS;
-		break;
-	case AES_KEYSIZE_256:
-		ctx->keymode = AES_TFM_256BITS;
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	ctx->keylen = SIZE_IN_WORDS(keylen);
-
-	err = aes_expandkey(&aes_ctx, key, keylen);
-	if (err)
-		return err;
-
-	aes_encrypt(&aes_ctx, hash.x8, hash.x8);
-	memzero_explicit(&aes_ctx, sizeof(aes_ctx));
-
-	memcpy(ctx->key, key, keylen);
-
-	/* Why do we need to do this? */
-	for (i = 0; i < SIZE_IN_WORDS(AES_BLOCK_SIZE); i++)
-		hash.x32[i] = swab32(hash.x32[i]);
-
-	memcpy(ctx->key + ctx->keylen, &hash, AES_BLOCK_SIZE);
-
-	return 0;
-}
-
-static int mtk_aes_gcm_setauthsize(struct crypto_aead *aead,
-				   u32 authsize)
-{
-	struct mtk_aes_base_ctx *ctx = crypto_aead_ctx(aead);
-	struct mtk_aes_gcm_ctx *gctx = mtk_aes_gcm_ctx_cast(ctx);
-
-	/* Same as crypto_gcm_authsize() from crypto/gcm.c */
-	switch (authsize) {
-	case 8:
-	case 12:
-	case 16:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	gctx->authsize = authsize;
-	return 0;
-}
-
-static int mtk_aes_gcm_encrypt(struct aead_request *req)
-{
-	return mtk_aes_gcm_crypt(req, AES_FLAGS_ENCRYPT);
-}
-
-static int mtk_aes_gcm_decrypt(struct aead_request *req)
-{
-	return mtk_aes_gcm_crypt(req, 0);
-}
-
-static int mtk_aes_gcm_init(struct crypto_aead *aead)
-{
-	struct mtk_aes_gcm_ctx *ctx = crypto_aead_ctx(aead);
-
-	crypto_aead_set_reqsize(aead, sizeof(struct mtk_aes_reqctx));
-	ctx->base.start = mtk_aes_gcm_start;
-	return 0;
-}
-
-static struct aead_alg aes_gcm_alg = {
-	.setkey		= mtk_aes_gcm_setkey,
-	.setauthsize	= mtk_aes_gcm_setauthsize,
-	.encrypt	= mtk_aes_gcm_encrypt,
-	.decrypt	= mtk_aes_gcm_decrypt,
-	.init		= mtk_aes_gcm_init,
-	.ivsize		= GCM_AES_IV_SIZE,
-	.maxauthsize	= AES_BLOCK_SIZE,
-
-	.base = {
-		.cra_name		= "gcm(aes)",
-		.cra_driver_name	= "gcm-aes-mtk",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= 1,
-		.cra_ctxsize		= sizeof(struct mtk_aes_gcm_ctx),
-		.cra_alignmask		= 0xf,
-		.cra_module		= THIS_MODULE,
-	},
-};
-
-static void mtk_aes_queue_task(unsigned long data)
-{
-	struct mtk_aes_rec *aes = (struct mtk_aes_rec *)data;
-
-	mtk_aes_handle_queue(aes->cryp, aes->id, NULL);
-}
-
-static void mtk_aes_done_task(unsigned long data)
-{
-	struct mtk_aes_rec *aes = (struct mtk_aes_rec *)data;
-	struct mtk_cryp *cryp = aes->cryp;
-
-	mtk_aes_unmap(cryp, aes);
-	aes->resume(cryp, aes);
-}
-
-static irqreturn_t mtk_aes_irq(int irq, void *dev_id)
-{
-	struct mtk_aes_rec *aes  = (struct mtk_aes_rec *)dev_id;
-	struct mtk_cryp *cryp = aes->cryp;
-	u32 val = mtk_aes_read(cryp, RDR_STAT(aes->id));
-
-	mtk_aes_write(cryp, RDR_STAT(aes->id), val);
-
-	if (likely(AES_FLAGS_BUSY & aes->flags)) {
-		mtk_aes_write(cryp, RDR_PROC_COUNT(aes->id), MTK_CNT_RST);
-		mtk_aes_write(cryp, RDR_THRESH(aes->id),
-			      MTK_RDR_PROC_THRESH | MTK_RDR_PROC_MODE);
-
-		tasklet_schedule(&aes->done_task);
-	} else {
-		dev_warn(cryp->dev, "AES interrupt when no active requests.\n");
-	}
-	return IRQ_HANDLED;
-}
-
-/*
- * The purpose of creating encryption and decryption records is
- * to process outbound/inbound data in parallel, it can improve
- * performance in most use cases, such as IPSec VPN, especially
- * under heavy network traffic.
- */
-static int mtk_aes_record_init(struct mtk_cryp *cryp)
-{
-	struct mtk_aes_rec **aes = cryp->aes;
-	int i, err = -ENOMEM;
-
-	for (i = 0; i < MTK_REC_NUM; i++) {
-		aes[i] = kzalloc(sizeof(**aes), GFP_KERNEL);
-		if (!aes[i])
-			goto err_cleanup;
-
-		aes[i]->buf = (void *)__get_free_pages(GFP_KERNEL,
-						AES_BUF_ORDER);
-		if (!aes[i]->buf)
-			goto err_cleanup;
-
-		aes[i]->cryp = cryp;
-
-		spin_lock_init(&aes[i]->lock);
-		crypto_init_queue(&aes[i]->queue, AES_QUEUE_SIZE);
-
-		tasklet_init(&aes[i]->queue_task, mtk_aes_queue_task,
-			     (unsigned long)aes[i]);
-		tasklet_init(&aes[i]->done_task, mtk_aes_done_task,
-			     (unsigned long)aes[i]);
-	}
-
-	/* Link to ring0 and ring1 respectively */
-	aes[0]->id = MTK_RING0;
-	aes[1]->id = MTK_RING1;
-
-	return 0;
-
-err_cleanup:
-	for (; i--; ) {
-		free_page((unsigned long)aes[i]->buf);
-		kfree(aes[i]);
-	}
-
-	return err;
-}
-
-static void mtk_aes_record_free(struct mtk_cryp *cryp)
-{
-	int i;
-
-	for (i = 0; i < MTK_REC_NUM; i++) {
-		tasklet_kill(&cryp->aes[i]->done_task);
-		tasklet_kill(&cryp->aes[i]->queue_task);
-
-		free_page((unsigned long)cryp->aes[i]->buf);
-		kfree(cryp->aes[i]);
-	}
-}
-
-static void mtk_aes_unregister_algs(void)
-{
-	int i;
-
-	crypto_unregister_aead(&aes_gcm_alg);
-
-	for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
-		crypto_unregister_skcipher(&aes_algs[i]);
-}
-
-static int mtk_aes_register_algs(void)
-{
-	int err, i;
-
-	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
-		err = crypto_register_skcipher(&aes_algs[i]);
-		if (err)
-			goto err_aes_algs;
-	}
-
-	err = crypto_register_aead(&aes_gcm_alg);
-	if (err)
-		goto err_aes_algs;
-
-	return 0;
-
-err_aes_algs:
-	for (; i--; )
-		crypto_unregister_skcipher(&aes_algs[i]);
-
-	return err;
-}
-
-int mtk_cipher_alg_register(struct mtk_cryp *cryp)
-{
-	int ret;
-
-	INIT_LIST_HEAD(&cryp->aes_list);
-
-	/* Initialize two cipher records */
-	ret = mtk_aes_record_init(cryp);
-	if (ret)
-		goto err_record;
-
-	ret = devm_request_irq(cryp->dev, cryp->irq[MTK_RING0], mtk_aes_irq,
-			       0, "mtk-aes", cryp->aes[0]);
-	if (ret) {
-		dev_err(cryp->dev, "unable to request AES irq.\n");
-		goto err_res;
-	}
-
-	ret = devm_request_irq(cryp->dev, cryp->irq[MTK_RING1], mtk_aes_irq,
-			       0, "mtk-aes", cryp->aes[1]);
-	if (ret) {
-		dev_err(cryp->dev, "unable to request AES irq.\n");
-		goto err_res;
-	}
-
-	/* Enable ring0 and ring1 interrupt */
-	mtk_aes_write(cryp, AIC_ENABLE_SET(MTK_RING0), MTK_IRQ_RDR0);
-	mtk_aes_write(cryp, AIC_ENABLE_SET(MTK_RING1), MTK_IRQ_RDR1);
-
-	spin_lock(&mtk_aes.lock);
-	list_add_tail(&cryp->aes_list, &mtk_aes.dev_list);
-	spin_unlock(&mtk_aes.lock);
-
-	ret = mtk_aes_register_algs();
-	if (ret)
-		goto err_algs;
-
-	return 0;
-
-err_algs:
-	spin_lock(&mtk_aes.lock);
-	list_del(&cryp->aes_list);
-	spin_unlock(&mtk_aes.lock);
-err_res:
-	mtk_aes_record_free(cryp);
-err_record:
-
-	dev_err(cryp->dev, "mtk-aes initialization failed.\n");
-	return ret;
-}
-
-void mtk_cipher_alg_release(struct mtk_cryp *cryp)
-{
-	spin_lock(&mtk_aes.lock);
-	list_del(&cryp->aes_list);
-	spin_unlock(&mtk_aes.lock);
-
-	mtk_aes_unregister_algs();
-	mtk_aes_record_free(cryp);
-}
diff --git a/drivers/crypto/mediatek/mtk-platform.c b/drivers/crypto/mediatek/mtk-platform.c
deleted file mode 100644
index 9d878620e5c9..000000000000
--- a/drivers/crypto/mediatek/mtk-platform.c
+++ /dev/null
@@ -1,586 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Driver for EIP97 cryptographic accelerator.
- *
- * Copyright (c) 2016 Ryder Lee <ryder.lee@mediatek.com>
- */
-
-#include <linux/clk.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mod_devicetable.h>
-#include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
-#include "mtk-platform.h"
-
-#define MTK_BURST_SIZE_MSK		GENMASK(7, 4)
-#define MTK_BURST_SIZE(x)		((x) << 4)
-#define MTK_DESC_SIZE(x)		((x) << 0)
-#define MTK_DESC_OFFSET(x)		((x) << 16)
-#define MTK_DESC_FETCH_SIZE(x)		((x) << 0)
-#define MTK_DESC_FETCH_THRESH(x)	((x) << 16)
-#define MTK_DESC_OVL_IRQ_EN		BIT(25)
-#define MTK_DESC_ATP_PRESENT		BIT(30)
-
-#define MTK_DFSE_IDLE			GENMASK(3, 0)
-#define MTK_DFSE_THR_CTRL_EN		BIT(30)
-#define MTK_DFSE_THR_CTRL_RESET		BIT(31)
-#define MTK_DFSE_RING_ID(x)		(((x) >> 12) & GENMASK(3, 0))
-#define MTK_DFSE_MIN_DATA(x)		((x) << 0)
-#define MTK_DFSE_MAX_DATA(x)		((x) << 8)
-#define MTK_DFE_MIN_CTRL(x)		((x) << 16)
-#define MTK_DFE_MAX_CTRL(x)		((x) << 24)
-
-#define MTK_IN_BUF_MIN_THRESH(x)	((x) << 8)
-#define MTK_IN_BUF_MAX_THRESH(x)	((x) << 12)
-#define MTK_OUT_BUF_MIN_THRESH(x)	((x) << 0)
-#define MTK_OUT_BUF_MAX_THRESH(x)	((x) << 4)
-#define MTK_IN_TBUF_SIZE(x)		(((x) >> 4) & GENMASK(3, 0))
-#define MTK_IN_DBUF_SIZE(x)		(((x) >> 8) & GENMASK(3, 0))
-#define MTK_OUT_DBUF_SIZE(x)		(((x) >> 16) & GENMASK(3, 0))
-#define MTK_CMD_FIFO_SIZE(x)		(((x) >> 8) & GENMASK(3, 0))
-#define MTK_RES_FIFO_SIZE(x)		(((x) >> 12) & GENMASK(3, 0))
-
-#define MTK_PE_TK_LOC_AVL		BIT(2)
-#define MTK_PE_PROC_HELD		BIT(14)
-#define MTK_PE_TK_TIMEOUT_EN		BIT(22)
-#define MTK_PE_INPUT_DMA_ERR		BIT(0)
-#define MTK_PE_OUTPUT_DMA_ERR		BIT(1)
-#define MTK_PE_PKT_PORC_ERR		BIT(2)
-#define MTK_PE_PKT_TIMEOUT		BIT(3)
-#define MTK_PE_FATAL_ERR		BIT(14)
-#define MTK_PE_INPUT_DMA_ERR_EN		BIT(16)
-#define MTK_PE_OUTPUT_DMA_ERR_EN	BIT(17)
-#define MTK_PE_PKT_PORC_ERR_EN		BIT(18)
-#define MTK_PE_PKT_TIMEOUT_EN		BIT(19)
-#define MTK_PE_FATAL_ERR_EN		BIT(30)
-#define MTK_PE_INT_OUT_EN		BIT(31)
-
-#define MTK_HIA_SIGNATURE		((u16)0x35ca)
-#define MTK_HIA_DATA_WIDTH(x)		(((x) >> 25) & GENMASK(1, 0))
-#define MTK_HIA_DMA_LENGTH(x)		(((x) >> 20) & GENMASK(4, 0))
-#define MTK_CDR_STAT_CLR		GENMASK(4, 0)
-#define MTK_RDR_STAT_CLR		GENMASK(7, 0)
-
-#define MTK_AIC_INT_MSK			GENMASK(5, 0)
-#define MTK_AIC_VER_MSK			(GENMASK(15, 0) | GENMASK(27, 20))
-#define MTK_AIC_VER11			0x011036c9
-#define MTK_AIC_VER12			0x012036c9
-#define MTK_AIC_G_CLR			GENMASK(30, 20)
-
-/**
- * EIP97 is an integrated security subsystem to accelerate cryptographic
- * functions and protocols to offload the host processor.
- * Some important hardware modules are briefly introduced below:
- *
- * Host Interface Adapter(HIA) - the main interface between the host
- * system and the hardware subsystem. It is responsible for attaching
- * processing engine to the specific host bus interface and provides a
- * standardized software view for off loading tasks to the engine.
- *
- * Command Descriptor Ring Manager(CDR Manager) - keeps track of how many
- * CD the host has prepared in the CDR. It monitors the fill level of its
- * CD-FIFO and if there's sufficient space for the next block of descriptors,
- * then it fires off a DMA request to fetch a block of CDs.
- *
- * Data fetch engine(DFE) - It is responsible for parsing the CD and
- * setting up the required control and packet data DMA transfers from
- * system memory to the processing engine.
- *
- * Result Descriptor Ring Manager(RDR Manager) - same as CDR Manager,
- * but target is result descriptors, Moreover, it also handles the RD
- * updates under control of the DSE. For each packet data segment
- * processed, the DSE triggers the RDR Manager to write the updated RD.
- * If triggered to update, the RDR Manager sets up a DMA operation to
- * copy the RD from the DSE to the correct location in the RDR.
- *
- * Data Store Engine(DSE) - It is responsible for parsing the prepared RD
- * and setting up the required control and packet data DMA transfers from
- * the processing engine to system memory.
- *
- * Advanced Interrupt Controllers(AICs) - receive interrupt request signals
- * from various sources and combine them into one interrupt output.
- * The AICs are used by:
- * - One for the HIA global and processing engine interrupts.
- * - The others for the descriptor ring interrupts.
- */
-
-/* Cryptographic engine capabilities */
-struct mtk_sys_cap {
-	/* host interface adapter */
-	u32 hia_ver;
-	u32 hia_opt;
-	/* packet engine */
-	u32 pkt_eng_opt;
-	/* global hardware */
-	u32 hw_opt;
-};
-
-static void mtk_desc_ring_link(struct mtk_cryp *cryp, u32 mask)
-{
-	/* Assign rings to DFE/DSE thread and enable it */
-	writel(MTK_DFSE_THR_CTRL_EN | mask, cryp->base + DFE_THR_CTRL);
-	writel(MTK_DFSE_THR_CTRL_EN | mask, cryp->base + DSE_THR_CTRL);
-}
-
-static void mtk_dfe_dse_buf_setup(struct mtk_cryp *cryp,
-				  struct mtk_sys_cap *cap)
-{
-	u32 width = MTK_HIA_DATA_WIDTH(cap->hia_opt) + 2;
-	u32 len = MTK_HIA_DMA_LENGTH(cap->hia_opt) - 1;
-	u32 ipbuf = min((u32)MTK_IN_DBUF_SIZE(cap->hw_opt) + width, len);
-	u32 opbuf = min((u32)MTK_OUT_DBUF_SIZE(cap->hw_opt) + width, len);
-	u32 itbuf = min((u32)MTK_IN_TBUF_SIZE(cap->hw_opt) + width, len);
-
-	writel(MTK_DFSE_MIN_DATA(ipbuf - 1) |
-	       MTK_DFSE_MAX_DATA(ipbuf) |
-	       MTK_DFE_MIN_CTRL(itbuf - 1) |
-	       MTK_DFE_MAX_CTRL(itbuf),
-	       cryp->base + DFE_CFG);
-
-	writel(MTK_DFSE_MIN_DATA(opbuf - 1) |
-	       MTK_DFSE_MAX_DATA(opbuf),
-	       cryp->base + DSE_CFG);
-
-	writel(MTK_IN_BUF_MIN_THRESH(ipbuf - 1) |
-	       MTK_IN_BUF_MAX_THRESH(ipbuf),
-	       cryp->base + PE_IN_DBUF_THRESH);
-
-	writel(MTK_IN_BUF_MIN_THRESH(itbuf - 1) |
-	       MTK_IN_BUF_MAX_THRESH(itbuf),
-	       cryp->base + PE_IN_TBUF_THRESH);
-
-	writel(MTK_OUT_BUF_MIN_THRESH(opbuf - 1) |
-	       MTK_OUT_BUF_MAX_THRESH(opbuf),
-	       cryp->base + PE_OUT_DBUF_THRESH);
-
-	writel(0, cryp->base + PE_OUT_TBUF_THRESH);
-	writel(0, cryp->base + PE_OUT_BUF_CTRL);
-}
-
-static int mtk_dfe_dse_state_check(struct mtk_cryp *cryp)
-{
-	int ret = -EINVAL;
-	u32 val;
-
-	/* Check for completion of all DMA transfers */
-	val = readl(cryp->base + DFE_THR_STAT);
-	if (MTK_DFSE_RING_ID(val) == MTK_DFSE_IDLE) {
-		val = readl(cryp->base + DSE_THR_STAT);
-		if (MTK_DFSE_RING_ID(val) == MTK_DFSE_IDLE)
-			ret = 0;
-	}
-
-	if (!ret) {
-		/* Take DFE/DSE thread out of reset */
-		writel(0, cryp->base + DFE_THR_CTRL);
-		writel(0, cryp->base + DSE_THR_CTRL);
-	} else {
-		return -EBUSY;
-	}
-
-	return 0;
-}
-
-static int mtk_dfe_dse_reset(struct mtk_cryp *cryp)
-{
-	/* Reset DSE/DFE and correct system priorities for all rings. */
-	writel(MTK_DFSE_THR_CTRL_RESET, cryp->base + DFE_THR_CTRL);
-	writel(0, cryp->base + DFE_PRIO_0);
-	writel(0, cryp->base + DFE_PRIO_1);
-	writel(0, cryp->base + DFE_PRIO_2);
-	writel(0, cryp->base + DFE_PRIO_3);
-
-	writel(MTK_DFSE_THR_CTRL_RESET, cryp->base + DSE_THR_CTRL);
-	writel(0, cryp->base + DSE_PRIO_0);
-	writel(0, cryp->base + DSE_PRIO_1);
-	writel(0, cryp->base + DSE_PRIO_2);
-	writel(0, cryp->base + DSE_PRIO_3);
-
-	return mtk_dfe_dse_state_check(cryp);
-}
-
-static void mtk_cmd_desc_ring_setup(struct mtk_cryp *cryp,
-				    int i, struct mtk_sys_cap *cap)
-{
-	/* Full descriptor that fits FIFO minus one */
-	u32 count =
-		((1 << MTK_CMD_FIFO_SIZE(cap->hia_opt)) / MTK_DESC_SZ) - 1;
-
-	/* Temporarily disable external triggering */
-	writel(0, cryp->base + CDR_CFG(i));
-
-	/* Clear CDR count */
-	writel(MTK_CNT_RST, cryp->base + CDR_PREP_COUNT(i));
-	writel(MTK_CNT_RST, cryp->base + CDR_PROC_COUNT(i));
-
-	writel(0, cryp->base + CDR_PREP_PNTR(i));
-	writel(0, cryp->base + CDR_PROC_PNTR(i));
-	writel(0, cryp->base + CDR_DMA_CFG(i));
-
-	/* Configure CDR host address space */
-	writel(0, cryp->base + CDR_BASE_ADDR_HI(i));
-	writel(cryp->ring[i]->cmd_dma, cryp->base + CDR_BASE_ADDR_LO(i));
-
-	writel(MTK_DESC_RING_SZ, cryp->base + CDR_RING_SIZE(i));
-
-	/* Clear and disable all CDR interrupts */
-	writel(MTK_CDR_STAT_CLR, cryp->base + CDR_STAT(i));
-
-	/*
-	 * Set command descriptor offset and enable additional
-	 * token present in descriptor.
-	 */
-	writel(MTK_DESC_SIZE(MTK_DESC_SZ) |
-		   MTK_DESC_OFFSET(MTK_DESC_OFF) |
-	       MTK_DESC_ATP_PRESENT,
-	       cryp->base + CDR_DESC_SIZE(i));
-
-	writel(MTK_DESC_FETCH_SIZE(count * MTK_DESC_OFF) |
-		   MTK_DESC_FETCH_THRESH(count * MTK_DESC_SZ),
-		   cryp->base + CDR_CFG(i));
-}
-
-static void mtk_res_desc_ring_setup(struct mtk_cryp *cryp,
-				    int i, struct mtk_sys_cap *cap)
-{
-	u32 rndup = 2;
-	u32 count = ((1 << MTK_RES_FIFO_SIZE(cap->hia_opt)) / rndup) - 1;
-
-	/* Temporarily disable external triggering */
-	writel(0, cryp->base + RDR_CFG(i));
-
-	/* Clear RDR count */
-	writel(MTK_CNT_RST, cryp->base + RDR_PREP_COUNT(i));
-	writel(MTK_CNT_RST, cryp->base + RDR_PROC_COUNT(i));
-
-	writel(0, cryp->base + RDR_PREP_PNTR(i));
-	writel(0, cryp->base + RDR_PROC_PNTR(i));
-	writel(0, cryp->base + RDR_DMA_CFG(i));
-
-	/* Configure RDR host address space */
-	writel(0, cryp->base + RDR_BASE_ADDR_HI(i));
-	writel(cryp->ring[i]->res_dma, cryp->base + RDR_BASE_ADDR_LO(i));
-
-	writel(MTK_DESC_RING_SZ, cryp->base + RDR_RING_SIZE(i));
-	writel(MTK_RDR_STAT_CLR, cryp->base + RDR_STAT(i));
-
-	/*
-	 * RDR manager generates update interrupts on a per-completed-packet,
-	 * and the rd_proc_thresh_irq interrupt is fired when proc_pkt_count
-	 * for the RDR exceeds the number of packets.
-	 */
-	writel(MTK_RDR_PROC_THRESH | MTK_RDR_PROC_MODE,
-	       cryp->base + RDR_THRESH(i));
-
-	/*
-	 * Configure a threshold and time-out value for the processed
-	 * result descriptors (or complete packets) that are written to
-	 * the RDR.
-	 */
-	writel(MTK_DESC_SIZE(MTK_DESC_SZ) | MTK_DESC_OFFSET(MTK_DESC_OFF),
-	       cryp->base + RDR_DESC_SIZE(i));
-
-	/*
-	 * Configure HIA fetch size and fetch threshold that are used to
-	 * fetch blocks of multiple descriptors.
-	 */
-	writel(MTK_DESC_FETCH_SIZE(count * MTK_DESC_OFF) |
-	       MTK_DESC_FETCH_THRESH(count * rndup) |
-	       MTK_DESC_OVL_IRQ_EN,
-		   cryp->base + RDR_CFG(i));
-}
-
-static int mtk_packet_engine_setup(struct mtk_cryp *cryp)
-{
-	struct mtk_sys_cap cap;
-	int i, err;
-	u32 val;
-
-	cap.hia_ver = readl(cryp->base + HIA_VERSION);
-	cap.hia_opt = readl(cryp->base + HIA_OPTIONS);
-	cap.hw_opt = readl(cryp->base + EIP97_OPTIONS);
-
-	if (!(((u16)cap.hia_ver) == MTK_HIA_SIGNATURE))
-		return -EINVAL;
-
-	/* Configure endianness conversion method for master (DMA) interface */
-	writel(0, cryp->base + EIP97_MST_CTRL);
-
-	/* Set HIA burst size */
-	val = readl(cryp->base + HIA_MST_CTRL);
-	val &= ~MTK_BURST_SIZE_MSK;
-	val |= MTK_BURST_SIZE(5);
-	writel(val, cryp->base + HIA_MST_CTRL);
-
-	err = mtk_dfe_dse_reset(cryp);
-	if (err) {
-		dev_err(cryp->dev, "Failed to reset DFE and DSE.\n");
-		return err;
-	}
-
-	mtk_dfe_dse_buf_setup(cryp, &cap);
-
-	/* Enable the 4 rings for the packet engines. */
-	mtk_desc_ring_link(cryp, 0xf);
-
-	for (i = 0; i < MTK_RING_MAX; i++) {
-		mtk_cmd_desc_ring_setup(cryp, i, &cap);
-		mtk_res_desc_ring_setup(cryp, i, &cap);
-	}
-
-	writel(MTK_PE_TK_LOC_AVL | MTK_PE_PROC_HELD | MTK_PE_TK_TIMEOUT_EN,
-	       cryp->base + PE_TOKEN_CTRL_STAT);
-
-	/* Clear all pending interrupts */
-	writel(MTK_AIC_G_CLR, cryp->base + AIC_G_ACK);
-	writel(MTK_PE_INPUT_DMA_ERR | MTK_PE_OUTPUT_DMA_ERR |
-	       MTK_PE_PKT_PORC_ERR | MTK_PE_PKT_TIMEOUT |
-	       MTK_PE_FATAL_ERR | MTK_PE_INPUT_DMA_ERR_EN |
-	       MTK_PE_OUTPUT_DMA_ERR_EN | MTK_PE_PKT_PORC_ERR_EN |
-	       MTK_PE_PKT_TIMEOUT_EN | MTK_PE_FATAL_ERR_EN |
-	       MTK_PE_INT_OUT_EN,
-	       cryp->base + PE_INTERRUPT_CTRL_STAT);
-
-	return 0;
-}
-
-static int mtk_aic_cap_check(struct mtk_cryp *cryp, int hw)
-{
-	u32 val;
-
-	if (hw == MTK_RING_MAX)
-		val = readl(cryp->base + AIC_G_VERSION);
-	else
-		val = readl(cryp->base + AIC_VERSION(hw));
-
-	val &= MTK_AIC_VER_MSK;
-	if (val != MTK_AIC_VER11 && val != MTK_AIC_VER12)
-		return -ENXIO;
-
-	if (hw == MTK_RING_MAX)
-		val = readl(cryp->base + AIC_G_OPTIONS);
-	else
-		val = readl(cryp->base + AIC_OPTIONS(hw));
-
-	val &= MTK_AIC_INT_MSK;
-	if (!val || val > 32)
-		return -ENXIO;
-
-	return 0;
-}
-
-static int mtk_aic_init(struct mtk_cryp *cryp, int hw)
-{
-	int err;
-
-	err = mtk_aic_cap_check(cryp, hw);
-	if (err)
-		return err;
-
-	/* Disable all interrupts and set initial configuration */
-	if (hw == MTK_RING_MAX) {
-		writel(0, cryp->base + AIC_G_ENABLE_CTRL);
-		writel(0, cryp->base + AIC_G_POL_CTRL);
-		writel(0, cryp->base + AIC_G_TYPE_CTRL);
-		writel(0, cryp->base + AIC_G_ENABLE_SET);
-	} else {
-		writel(0, cryp->base + AIC_ENABLE_CTRL(hw));
-		writel(0, cryp->base + AIC_POL_CTRL(hw));
-		writel(0, cryp->base + AIC_TYPE_CTRL(hw));
-		writel(0, cryp->base + AIC_ENABLE_SET(hw));
-	}
-
-	return 0;
-}
-
-static int mtk_accelerator_init(struct mtk_cryp *cryp)
-{
-	int i, err;
-
-	/* Initialize advanced interrupt controller(AIC) */
-	for (i = 0; i < MTK_IRQ_NUM; i++) {
-		err = mtk_aic_init(cryp, i);
-		if (err) {
-			dev_err(cryp->dev, "Failed to initialize AIC.\n");
-			return err;
-		}
-	}
-
-	/* Initialize packet engine */
-	err = mtk_packet_engine_setup(cryp);
-	if (err) {
-		dev_err(cryp->dev, "Failed to configure packet engine.\n");
-		return err;
-	}
-
-	return 0;
-}
-
-static void mtk_desc_dma_free(struct mtk_cryp *cryp)
-{
-	int i;
-
-	for (i = 0; i < MTK_RING_MAX; i++) {
-		dma_free_coherent(cryp->dev, MTK_DESC_RING_SZ,
-				  cryp->ring[i]->res_base,
-				  cryp->ring[i]->res_dma);
-		dma_free_coherent(cryp->dev, MTK_DESC_RING_SZ,
-				  cryp->ring[i]->cmd_base,
-				  cryp->ring[i]->cmd_dma);
-		kfree(cryp->ring[i]);
-	}
-}
-
-static int mtk_desc_ring_alloc(struct mtk_cryp *cryp)
-{
-	struct mtk_ring **ring = cryp->ring;
-	int i;
-
-	for (i = 0; i < MTK_RING_MAX; i++) {
-		ring[i] = kzalloc(sizeof(**ring), GFP_KERNEL);
-		if (!ring[i])
-			goto err_cleanup;
-
-		ring[i]->cmd_base = dma_alloc_coherent(cryp->dev,
-						       MTK_DESC_RING_SZ,
-						       &ring[i]->cmd_dma,
-						       GFP_KERNEL);
-		if (!ring[i]->cmd_base)
-			goto err_cleanup;
-
-		ring[i]->res_base = dma_alloc_coherent(cryp->dev,
-						       MTK_DESC_RING_SZ,
-						       &ring[i]->res_dma,
-						       GFP_KERNEL);
-		if (!ring[i]->res_base)
-			goto err_cleanup;
-
-		ring[i]->cmd_next = ring[i]->cmd_base;
-		ring[i]->res_next = ring[i]->res_base;
-	}
-	return 0;
-
-err_cleanup:
-	do {
-		dma_free_coherent(cryp->dev, MTK_DESC_RING_SZ,
-				  ring[i]->res_base, ring[i]->res_dma);
-		dma_free_coherent(cryp->dev, MTK_DESC_RING_SZ,
-				  ring[i]->cmd_base, ring[i]->cmd_dma);
-		kfree(ring[i]);
-	} while (i--);
-	return -ENOMEM;
-}
-
-static int mtk_crypto_probe(struct platform_device *pdev)
-{
-	struct mtk_cryp *cryp;
-	int i, err;
-
-	cryp = devm_kzalloc(&pdev->dev, sizeof(*cryp), GFP_KERNEL);
-	if (!cryp)
-		return -ENOMEM;
-
-	cryp->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(cryp->base))
-		return PTR_ERR(cryp->base);
-
-	for (i = 0; i < MTK_IRQ_NUM; i++) {
-		cryp->irq[i] = platform_get_irq(pdev, i);
-		if (cryp->irq[i] < 0)
-			return cryp->irq[i];
-	}
-
-	cryp->clk_cryp = devm_clk_get(&pdev->dev, "cryp");
-	if (IS_ERR(cryp->clk_cryp))
-		return -EPROBE_DEFER;
-
-	cryp->dev = &pdev->dev;
-	pm_runtime_enable(cryp->dev);
-	pm_runtime_get_sync(cryp->dev);
-
-	err = clk_prepare_enable(cryp->clk_cryp);
-	if (err)
-		goto err_clk_cryp;
-
-	/* Allocate four command/result descriptor rings */
-	err = mtk_desc_ring_alloc(cryp);
-	if (err) {
-		dev_err(cryp->dev, "Unable to allocate descriptor rings.\n");
-		goto err_resource;
-	}
-
-	/* Initialize hardware modules */
-	err = mtk_accelerator_init(cryp);
-	if (err) {
-		dev_err(cryp->dev, "Failed to initialize cryptographic engine.\n");
-		goto err_engine;
-	}
-
-	err = mtk_cipher_alg_register(cryp);
-	if (err) {
-		dev_err(cryp->dev, "Unable to register cipher algorithm.\n");
-		goto err_cipher;
-	}
-
-	err = mtk_hash_alg_register(cryp);
-	if (err) {
-		dev_err(cryp->dev, "Unable to register hash algorithm.\n");
-		goto err_hash;
-	}
-
-	platform_set_drvdata(pdev, cryp);
-	return 0;
-
-err_hash:
-	mtk_cipher_alg_release(cryp);
-err_cipher:
-	mtk_dfe_dse_reset(cryp);
-err_engine:
-	mtk_desc_dma_free(cryp);
-err_resource:
-	clk_disable_unprepare(cryp->clk_cryp);
-err_clk_cryp:
-	pm_runtime_put_sync(cryp->dev);
-	pm_runtime_disable(cryp->dev);
-
-	return err;
-}
-
-static int mtk_crypto_remove(struct platform_device *pdev)
-{
-	struct mtk_cryp *cryp = platform_get_drvdata(pdev);
-
-	mtk_hash_alg_release(cryp);
-	mtk_cipher_alg_release(cryp);
-	mtk_desc_dma_free(cryp);
-
-	clk_disable_unprepare(cryp->clk_cryp);
-
-	pm_runtime_put_sync(cryp->dev);
-	pm_runtime_disable(cryp->dev);
-	platform_set_drvdata(pdev, NULL);
-
-	return 0;
-}
-
-static const struct of_device_id of_crypto_id[] = {
-	{ .compatible = "mediatek,eip97-crypto" },
-	{},
-};
-MODULE_DEVICE_TABLE(of, of_crypto_id);
-
-static struct platform_driver mtk_crypto_driver = {
-	.probe = mtk_crypto_probe,
-	.remove = mtk_crypto_remove,
-	.driver = {
-		   .name = "mtk-crypto",
-		   .of_match_table = of_crypto_id,
-	},
-};
-module_platform_driver(mtk_crypto_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Ryder Lee <ryder.lee@mediatek.com>");
-MODULE_DESCRIPTION("Cryptographic accelerator driver for EIP97");
diff --git a/drivers/crypto/mediatek/mtk-platform.h b/drivers/crypto/mediatek/mtk-platform.h
deleted file mode 100644
index 47920c51abac..000000000000
--- a/drivers/crypto/mediatek/mtk-platform.h
+++ /dev/null
@@ -1,231 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Driver for EIP97 cryptographic accelerator.
- *
- * Copyright (c) 2016 Ryder Lee <ryder.lee@mediatek.com>
- */
-
-#ifndef __MTK_PLATFORM_H_
-#define __MTK_PLATFORM_H_
-
-#include <crypto/algapi.h>
-#include <crypto/internal/aead.h>
-#include <crypto/internal/hash.h>
-#include <crypto/scatterwalk.h>
-#include <crypto/skcipher.h>
-#include <linux/crypto.h>
-#include <linux/dma-mapping.h>
-#include <linux/interrupt.h>
-#include <linux/scatterlist.h>
-#include "mtk-regs.h"
-
-#define MTK_RDR_PROC_THRESH	BIT(0)
-#define MTK_RDR_PROC_MODE	BIT(23)
-#define MTK_CNT_RST		BIT(31)
-#define MTK_IRQ_RDR0		BIT(1)
-#define MTK_IRQ_RDR1		BIT(3)
-#define MTK_IRQ_RDR2		BIT(5)
-#define MTK_IRQ_RDR3		BIT(7)
-
-#define SIZE_IN_WORDS(x)	((x) >> 2)
-
-/**
- * Ring 0/1 are used by AES encrypt and decrypt.
- * Ring 2/3 are used by SHA.
- */
-enum {
-	MTK_RING0,
-	MTK_RING1,
-	MTK_RING2,
-	MTK_RING3,
-	MTK_RING_MAX
-};
-
-#define MTK_REC_NUM		(MTK_RING_MAX / 2)
-#define MTK_IRQ_NUM		5
-
-/**
- * struct mtk_desc - DMA descriptor
- * @hdr:	the descriptor control header
- * @buf:	DMA address of input buffer segment
- * @ct:		DMA address of command token that control operation flow
- * @ct_hdr:	the command token control header
- * @tag:	the user-defined field
- * @tfm:	DMA address of transform state
- * @bound:	align descriptors offset boundary
- *
- * Structure passed to the crypto engine to describe where source
- * data needs to be fetched and how it needs to be processed.
- */
-struct mtk_desc {
-	__le32 hdr;
-	__le32 buf;
-	__le32 ct;
-	__le32 ct_hdr;
-	__le32 tag;
-	__le32 tfm;
-	__le32 bound[2];
-};
-
-#define MTK_DESC_NUM		512
-#define MTK_DESC_OFF		SIZE_IN_WORDS(sizeof(struct mtk_desc))
-#define MTK_DESC_SZ		(MTK_DESC_OFF - 2)
-#define MTK_DESC_RING_SZ	((sizeof(struct mtk_desc) * MTK_DESC_NUM))
-#define MTK_DESC_CNT(x)		((MTK_DESC_OFF * (x)) << 2)
-#define MTK_DESC_LAST		cpu_to_le32(BIT(22))
-#define MTK_DESC_FIRST		cpu_to_le32(BIT(23))
-#define MTK_DESC_BUF_LEN(x)	cpu_to_le32(x)
-#define MTK_DESC_CT_LEN(x)	cpu_to_le32((x) << 24)
-
-/**
- * struct mtk_ring - Descriptor ring
- * @cmd_base:	pointer to command descriptor ring base
- * @cmd_next:	pointer to the next command descriptor
- * @cmd_dma:	DMA address of command descriptor ring
- * @res_base:	pointer to result descriptor ring base
- * @res_next:	pointer to the next result descriptor
- * @res_prev:	pointer to the previous result descriptor
- * @res_dma:	DMA address of result descriptor ring
- *
- * A descriptor ring is a circular buffer that is used to manage
- * one or more descriptors. There are two type of descriptor rings;
- * the command descriptor ring and result descriptor ring.
- */
-struct mtk_ring {
-	struct mtk_desc *cmd_base;
-	struct mtk_desc *cmd_next;
-	dma_addr_t cmd_dma;
-	struct mtk_desc *res_base;
-	struct mtk_desc *res_next;
-	struct mtk_desc *res_prev;
-	dma_addr_t res_dma;
-};
-
-/**
- * struct mtk_aes_dma - Structure that holds sg list info
- * @sg:		pointer to scatter-gather list
- * @nents:	number of entries in the sg list
- * @remainder:	remainder of sg list
- * @sg_len:	number of entries in the sg mapped list
- */
-struct mtk_aes_dma {
-	struct scatterlist *sg;
-	int nents;
-	u32 remainder;
-	u32 sg_len;
-};
-
-struct mtk_aes_base_ctx;
-struct mtk_aes_rec;
-struct mtk_cryp;
-
-typedef int (*mtk_aes_fn)(struct mtk_cryp *cryp, struct mtk_aes_rec *aes);
-
-/**
- * struct mtk_aes_rec - AES operation record
- * @cryp:	pointer to Cryptographic device
- * @queue:	crypto request queue
- * @areq:	pointer to async request
- * @done_task:	the tasklet is use in AES interrupt
- * @queue_task:	the tasklet is used to dequeue request
- * @ctx:	pointer to current context
- * @src:	the structure that holds source sg list info
- * @dst:	the structure that holds destination sg list info
- * @aligned_sg:	the scatter list is use to alignment
- * @real_dst:	pointer to the destination sg list
- * @resume:	pointer to resume function
- * @total:	request buffer length
- * @buf:	pointer to page buffer
- * @id:		the current use of ring
- * @flags:	it's describing AES operation state
- * @lock:	the async queue lock
- *
- * Structure used to record AES execution state.
- */
-struct mtk_aes_rec {
-	struct mtk_cryp *cryp;
-	struct crypto_queue queue;
-	struct crypto_async_request *areq;
-	struct tasklet_struct done_task;
-	struct tasklet_struct queue_task;
-	struct mtk_aes_base_ctx *ctx;
-	struct mtk_aes_dma src;
-	struct mtk_aes_dma dst;
-
-	struct scatterlist aligned_sg;
-	struct scatterlist *real_dst;
-
-	mtk_aes_fn resume;
-
-	size_t total;
-	void *buf;
-
-	u8 id;
-	unsigned long flags;
-	/* queue lock */
-	spinlock_t lock;
-};
-
-/**
- * struct mtk_sha_rec - SHA operation record
- * @cryp:	pointer to Cryptographic device
- * @queue:	crypto request queue
- * @req:	pointer to ahash request
- * @done_task:	the tasklet is use in SHA interrupt
- * @queue_task:	the tasklet is used to dequeue request
- * @id:		the current use of ring
- * @flags:	it's describing SHA operation state
- * @lock:	the async queue lock
- *
- * Structure used to record SHA execution state.
- */
-struct mtk_sha_rec {
-	struct mtk_cryp *cryp;
-	struct crypto_queue queue;
-	struct ahash_request *req;
-	struct tasklet_struct done_task;
-	struct tasklet_struct queue_task;
-
-	u8 id;
-	unsigned long flags;
-	/* queue lock */
-	spinlock_t lock;
-};
-
-/**
- * struct mtk_cryp - Cryptographic device
- * @base:	pointer to mapped register I/O base
- * @dev:	pointer to device
- * @clk_cryp:	pointer to crypto clock
- * @irq:	global system and rings IRQ
- * @ring:	pointer to descriptor rings
- * @aes:	pointer to operation record of AES
- * @sha:	pointer to operation record of SHA
- * @aes_list:	device list of AES
- * @sha_list:	device list of SHA
- * @rec:	it's used to select SHA record for tfm
- *
- * Structure storing cryptographic device information.
- */
-struct mtk_cryp {
-	void __iomem *base;
-	struct device *dev;
-	struct clk *clk_cryp;
-	int irq[MTK_IRQ_NUM];
-
-	struct mtk_ring *ring[MTK_RING_MAX];
-	struct mtk_aes_rec *aes[MTK_REC_NUM];
-	struct mtk_sha_rec *sha[MTK_REC_NUM];
-
-	struct list_head aes_list;
-	struct list_head sha_list;
-
-	bool rec;
-};
-
-int mtk_cipher_alg_register(struct mtk_cryp *cryp);
-void mtk_cipher_alg_release(struct mtk_cryp *cryp);
-int mtk_hash_alg_register(struct mtk_cryp *cryp);
-void mtk_hash_alg_release(struct mtk_cryp *cryp);
-
-#endif /* __MTK_PLATFORM_H_ */
diff --git a/drivers/crypto/mediatek/mtk-regs.h b/drivers/crypto/mediatek/mtk-regs.h
deleted file mode 100644
index d3defda7a750..000000000000
--- a/drivers/crypto/mediatek/mtk-regs.h
+++ /dev/null
@@ -1,190 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Support for MediaTek cryptographic accelerator.
- *
- * Copyright (c) 2016 MediaTek Inc.
- * Author: Ryder Lee <ryder.lee@mediatek.com>
- */
-
-#ifndef __MTK_REGS_H__
-#define __MTK_REGS_H__
-
-/* HIA, Command Descriptor Ring Manager */
-#define CDR_BASE_ADDR_LO(x)		(0x0 + ((x) << 12))
-#define CDR_BASE_ADDR_HI(x)		(0x4 + ((x) << 12))
-#define CDR_DATA_BASE_ADDR_LO(x)	(0x8 + ((x) << 12))
-#define CDR_DATA_BASE_ADDR_HI(x)	(0xC + ((x) << 12))
-#define CDR_ACD_BASE_ADDR_LO(x)		(0x10 + ((x) << 12))
-#define CDR_ACD_BASE_ADDR_HI(x)		(0x14 + ((x) << 12))
-#define CDR_RING_SIZE(x)		(0x18 + ((x) << 12))
-#define CDR_DESC_SIZE(x)		(0x1C + ((x) << 12))
-#define CDR_CFG(x)			(0x20 + ((x) << 12))
-#define CDR_DMA_CFG(x)			(0x24 + ((x) << 12))
-#define CDR_THRESH(x)			(0x28 + ((x) << 12))
-#define CDR_PREP_COUNT(x)		(0x2C + ((x) << 12))
-#define CDR_PROC_COUNT(x)		(0x30 + ((x) << 12))
-#define CDR_PREP_PNTR(x)		(0x34 + ((x) << 12))
-#define CDR_PROC_PNTR(x)		(0x38 + ((x) << 12))
-#define CDR_STAT(x)			(0x3C + ((x) << 12))
-
-/* HIA, Result Descriptor Ring Manager */
-#define RDR_BASE_ADDR_LO(x)		(0x800 + ((x) << 12))
-#define RDR_BASE_ADDR_HI(x)		(0x804 + ((x) << 12))
-#define RDR_DATA_BASE_ADDR_LO(x)	(0x808 + ((x) << 12))
-#define RDR_DATA_BASE_ADDR_HI(x)	(0x80C + ((x) << 12))
-#define RDR_ACD_BASE_ADDR_LO(x)		(0x810 + ((x) << 12))
-#define RDR_ACD_BASE_ADDR_HI(x)		(0x814 + ((x) << 12))
-#define RDR_RING_SIZE(x)		(0x818 + ((x) << 12))
-#define RDR_DESC_SIZE(x)		(0x81C + ((x) << 12))
-#define RDR_CFG(x)			(0x820 + ((x) << 12))
-#define RDR_DMA_CFG(x)			(0x824 + ((x) << 12))
-#define RDR_THRESH(x)			(0x828 + ((x) << 12))
-#define RDR_PREP_COUNT(x)		(0x82C + ((x) << 12))
-#define RDR_PROC_COUNT(x)		(0x830 + ((x) << 12))
-#define RDR_PREP_PNTR(x)		(0x834 + ((x) << 12))
-#define RDR_PROC_PNTR(x)		(0x838 + ((x) << 12))
-#define RDR_STAT(x)			(0x83C + ((x) << 12))
-
-/* HIA, Ring AIC */
-#define AIC_POL_CTRL(x)			(0xE000 - ((x) << 12))
-#define	AIC_TYPE_CTRL(x)		(0xE004 - ((x) << 12))
-#define	AIC_ENABLE_CTRL(x)		(0xE008 - ((x) << 12))
-#define	AIC_RAW_STAL(x)			(0xE00C - ((x) << 12))
-#define	AIC_ENABLE_SET(x)		(0xE00C - ((x) << 12))
-#define	AIC_ENABLED_STAT(x)		(0xE010 - ((x) << 12))
-#define	AIC_ACK(x)			(0xE010 - ((x) << 12))
-#define	AIC_ENABLE_CLR(x)		(0xE014 - ((x) << 12))
-#define	AIC_OPTIONS(x)			(0xE018 - ((x) << 12))
-#define	AIC_VERSION(x)			(0xE01C - ((x) << 12))
-
-/* HIA, Global AIC */
-#define AIC_G_POL_CTRL			0xF800
-#define AIC_G_TYPE_CTRL			0xF804
-#define AIC_G_ENABLE_CTRL		0xF808
-#define AIC_G_RAW_STAT			0xF80C
-#define AIC_G_ENABLE_SET		0xF80C
-#define AIC_G_ENABLED_STAT		0xF810
-#define AIC_G_ACK			0xF810
-#define AIC_G_ENABLE_CLR		0xF814
-#define AIC_G_OPTIONS			0xF818
-#define AIC_G_VERSION			0xF81C
-
-/* HIA, Data Fetch Engine */
-#define DFE_CFG				0xF000
-#define DFE_PRIO_0			0xF010
-#define DFE_PRIO_1			0xF014
-#define DFE_PRIO_2			0xF018
-#define DFE_PRIO_3			0xF01C
-
-/* HIA, Data Fetch Engine access monitoring for CDR */
-#define DFE_RING_REGION_LO(x)		(0xF080 + ((x) << 3))
-#define DFE_RING_REGION_HI(x)		(0xF084 + ((x) << 3))
-
-/* HIA, Data Fetch Engine thread control and status for thread */
-#define DFE_THR_CTRL			0xF200
-#define DFE_THR_STAT			0xF204
-#define DFE_THR_DESC_CTRL		0xF208
-#define DFE_THR_DESC_DPTR_LO		0xF210
-#define DFE_THR_DESC_DPTR_HI		0xF214
-#define DFE_THR_DESC_ACDPTR_LO		0xF218
-#define DFE_THR_DESC_ACDPTR_HI		0xF21C
-
-/* HIA, Data Store Engine */
-#define DSE_CFG				0xF400
-#define DSE_PRIO_0			0xF410
-#define DSE_PRIO_1			0xF414
-#define DSE_PRIO_2			0xF418
-#define DSE_PRIO_3			0xF41C
-
-/* HIA, Data Store Engine access monitoring for RDR */
-#define DSE_RING_REGION_LO(x)		(0xF480 + ((x) << 3))
-#define DSE_RING_REGION_HI(x)		(0xF484 + ((x) << 3))
-
-/* HIA, Data Store Engine thread control and status for thread */
-#define DSE_THR_CTRL			0xF600
-#define DSE_THR_STAT			0xF604
-#define DSE_THR_DESC_CTRL		0xF608
-#define DSE_THR_DESC_DPTR_LO		0xF610
-#define DSE_THR_DESC_DPTR_HI		0xF614
-#define DSE_THR_DESC_S_DPTR_LO		0xF618
-#define DSE_THR_DESC_S_DPTR_HI		0xF61C
-#define DSE_THR_ERROR_STAT		0xF620
-
-/* HIA Global */
-#define HIA_MST_CTRL			0xFFF4
-#define HIA_OPTIONS			0xFFF8
-#define HIA_VERSION			0xFFFC
-
-/* Processing Engine Input Side, Processing Engine */
-#define PE_IN_DBUF_THRESH		0x10000
-#define PE_IN_TBUF_THRESH		0x10100
-
-/* Packet Engine Configuration / Status Registers */
-#define PE_TOKEN_CTRL_STAT		0x11000
-#define PE_FUNCTION_EN			0x11004
-#define PE_CONTEXT_CTRL			0x11008
-#define PE_INTERRUPT_CTRL_STAT		0x11010
-#define PE_CONTEXT_STAT			0x1100C
-#define PE_OUT_TRANS_CTRL_STAT		0x11018
-#define PE_OUT_BUF_CTRL			0x1101C
-
-/* Packet Engine PRNG Registers */
-#define PE_PRNG_STAT			0x11040
-#define PE_PRNG_CTRL			0x11044
-#define PE_PRNG_SEED_L			0x11048
-#define PE_PRNG_SEED_H			0x1104C
-#define PE_PRNG_KEY_0_L			0x11050
-#define PE_PRNG_KEY_0_H			0x11054
-#define PE_PRNG_KEY_1_L			0x11058
-#define PE_PRNG_KEY_1_H			0x1105C
-#define PE_PRNG_RES_0			0x11060
-#define PE_PRNG_RES_1			0x11064
-#define PE_PRNG_RES_2			0x11068
-#define PE_PRNG_RES_3			0x1106C
-#define PE_PRNG_LFSR_L			0x11070
-#define PE_PRNG_LFSR_H			0x11074
-
-/* Packet Engine AIC */
-#define PE_EIP96_AIC_POL_CTRL		0x113C0
-#define PE_EIP96_AIC_TYPE_CTRL		0x113C4
-#define PE_EIP96_AIC_ENABLE_CTRL	0x113C8
-#define PE_EIP96_AIC_RAW_STAT		0x113CC
-#define PE_EIP96_AIC_ENABLE_SET		0x113CC
-#define PE_EIP96_AIC_ENABLED_STAT	0x113D0
-#define PE_EIP96_AIC_ACK		0x113D0
-#define PE_EIP96_AIC_ENABLE_CLR		0x113D4
-#define PE_EIP96_AIC_OPTIONS		0x113D8
-#define PE_EIP96_AIC_VERSION		0x113DC
-
-/* Packet Engine Options & Version Registers */
-#define PE_EIP96_OPTIONS		0x113F8
-#define PE_EIP96_VERSION		0x113FC
-
-/* Processing Engine Output Side */
-#define PE_OUT_DBUF_THRESH		0x11C00
-#define PE_OUT_TBUF_THRESH		0x11D00
-
-/* Processing Engine Local AIC */
-#define PE_AIC_POL_CTRL			0x11F00
-#define PE_AIC_TYPE_CTRL		0x11F04
-#define PE_AIC_ENABLE_CTRL		0x11F08
-#define PE_AIC_RAW_STAT			0x11F0C
-#define PE_AIC_ENABLE_SET		0x11F0C
-#define PE_AIC_ENABLED_STAT		0x11F10
-#define PE_AIC_ENABLE_CLR		0x11F14
-#define PE_AIC_OPTIONS			0x11F18
-#define PE_AIC_VERSION			0x11F1C
-
-/* Processing Engine General Configuration and Version */
-#define PE_IN_FLIGHT			0x11FF0
-#define PE_OPTIONS			0x11FF8
-#define PE_VERSION			0x11FFC
-
-/* EIP-97 - Global */
-#define EIP97_CLOCK_STATE		0x1FFE4
-#define EIP97_FORCE_CLOCK_ON		0x1FFE8
-#define EIP97_FORCE_CLOCK_OFF		0x1FFEC
-#define EIP97_MST_CTRL			0x1FFF4
-#define EIP97_OPTIONS			0x1FFF8
-#define EIP97_VERSION			0x1FFFC
-#endif /* __MTK_REGS_H__ */
diff --git a/drivers/crypto/mediatek/mtk-sha.c b/drivers/crypto/mediatek/mtk-sha.c
deleted file mode 100644
index f55aacdafbef..000000000000
--- a/drivers/crypto/mediatek/mtk-sha.c
+++ /dev/null
@@ -1,1353 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Cryptographic API.
- *
- * Driver for EIP97 SHA1/SHA2(HMAC) acceleration.
- *
- * Copyright (c) 2016 Ryder Lee <ryder.lee@mediatek.com>
- *
- * Some ideas are from atmel-sha.c and omap-sham.c drivers.
- */
-
-#include <crypto/hmac.h>
-#include <crypto/sha1.h>
-#include <crypto/sha2.h>
-#include "mtk-platform.h"
-
-#define SHA_ALIGN_MSK		(sizeof(u32) - 1)
-#define SHA_QUEUE_SIZE		512
-#define SHA_BUF_SIZE		((u32)PAGE_SIZE)
-
-#define SHA_OP_UPDATE		1
-#define SHA_OP_FINAL		2
-
-#define SHA_DATA_LEN_MSK	cpu_to_le32(GENMASK(16, 0))
-#define SHA_MAX_DIGEST_BUF_SIZE	32
-
-/* SHA command token */
-#define SHA_CT_SIZE		5
-#define SHA_CT_CTRL_HDR		cpu_to_le32(0x02220000)
-#define SHA_CMD0		cpu_to_le32(0x03020000)
-#define SHA_CMD1		cpu_to_le32(0x21060000)
-#define SHA_CMD2		cpu_to_le32(0xe0e63802)
-
-/* SHA transform information */
-#define SHA_TFM_HASH		cpu_to_le32(0x2 << 0)
-#define SHA_TFM_SIZE(x)		cpu_to_le32((x) << 8)
-#define SHA_TFM_START		cpu_to_le32(0x1 << 4)
-#define SHA_TFM_CONTINUE	cpu_to_le32(0x1 << 5)
-#define SHA_TFM_HASH_STORE	cpu_to_le32(0x1 << 19)
-#define SHA_TFM_SHA1		cpu_to_le32(0x2 << 23)
-#define SHA_TFM_SHA256		cpu_to_le32(0x3 << 23)
-#define SHA_TFM_SHA224		cpu_to_le32(0x4 << 23)
-#define SHA_TFM_SHA512		cpu_to_le32(0x5 << 23)
-#define SHA_TFM_SHA384		cpu_to_le32(0x6 << 23)
-#define SHA_TFM_DIGEST(x)	cpu_to_le32(((x) & GENMASK(3, 0)) << 24)
-
-/* SHA flags */
-#define SHA_FLAGS_BUSY		BIT(0)
-#define	SHA_FLAGS_FINAL		BIT(1)
-#define SHA_FLAGS_FINUP		BIT(2)
-#define SHA_FLAGS_SG		BIT(3)
-#define SHA_FLAGS_ALGO_MSK	GENMASK(8, 4)
-#define SHA_FLAGS_SHA1		BIT(4)
-#define SHA_FLAGS_SHA224	BIT(5)
-#define SHA_FLAGS_SHA256	BIT(6)
-#define SHA_FLAGS_SHA384	BIT(7)
-#define SHA_FLAGS_SHA512	BIT(8)
-#define SHA_FLAGS_HMAC		BIT(9)
-#define SHA_FLAGS_PAD		BIT(10)
-
-/**
- * mtk_sha_info - hardware information of AES
- * @cmd:	command token, hardware instruction
- * @tfm:	transform state of cipher algorithm.
- * @state:	contains keys and initial vectors.
- *
- */
-struct mtk_sha_info {
-	__le32 ctrl[2];
-	__le32 cmd[3];
-	__le32 tfm[2];
-	__le32 digest[SHA_MAX_DIGEST_BUF_SIZE];
-};
-
-struct mtk_sha_reqctx {
-	struct mtk_sha_info info;
-	unsigned long flags;
-	unsigned long op;
-
-	u64 digcnt;
-	size_t bufcnt;
-	dma_addr_t dma_addr;
-
-	__le32 ct_hdr;
-	u32 ct_size;
-	dma_addr_t ct_dma;
-	dma_addr_t tfm_dma;
-
-	/* Walk state */
-	struct scatterlist *sg;
-	u32 offset;	/* Offset in current sg */
-	u32 total;	/* Total request */
-	size_t ds;
-	size_t bs;
-
-	u8 *buffer;
-};
-
-struct mtk_sha_hmac_ctx {
-	struct crypto_shash	*shash;
-	u8 ipad[SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
-	u8 opad[SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
-};
-
-struct mtk_sha_ctx {
-	struct mtk_cryp *cryp;
-	unsigned long flags;
-	u8 id;
-	u8 buf[SHA_BUF_SIZE] __aligned(sizeof(u32));
-
-	struct mtk_sha_hmac_ctx	base[];
-};
-
-struct mtk_sha_drv {
-	struct list_head dev_list;
-	/* Device list lock */
-	spinlock_t lock;
-};
-
-static struct mtk_sha_drv mtk_sha = {
-	.dev_list = LIST_HEAD_INIT(mtk_sha.dev_list),
-	.lock = __SPIN_LOCK_UNLOCKED(mtk_sha.lock),
-};
-
-static int mtk_sha_handle_queue(struct mtk_cryp *cryp, u8 id,
-				struct ahash_request *req);
-
-static inline u32 mtk_sha_read(struct mtk_cryp *cryp, u32 offset)
-{
-	return readl_relaxed(cryp->base + offset);
-}
-
-static inline void mtk_sha_write(struct mtk_cryp *cryp,
-				 u32 offset, u32 value)
-{
-	writel_relaxed(value, cryp->base + offset);
-}
-
-static inline void mtk_sha_ring_shift(struct mtk_ring *ring,
-				      struct mtk_desc **cmd_curr,
-				      struct mtk_desc **res_curr,
-				      int *count)
-{
-	*cmd_curr = ring->cmd_next++;
-	*res_curr = ring->res_next++;
-	(*count)++;
-
-	if (ring->cmd_next == ring->cmd_base + MTK_DESC_NUM) {
-		ring->cmd_next = ring->cmd_base;
-		ring->res_next = ring->res_base;
-	}
-}
-
-static struct mtk_cryp *mtk_sha_find_dev(struct mtk_sha_ctx *tctx)
-{
-	struct mtk_cryp *cryp = NULL;
-	struct mtk_cryp *tmp;
-
-	spin_lock_bh(&mtk_sha.lock);
-	if (!tctx->cryp) {
-		list_for_each_entry(tmp, &mtk_sha.dev_list, sha_list) {
-			cryp = tmp;
-			break;
-		}
-		tctx->cryp = cryp;
-	} else {
-		cryp = tctx->cryp;
-	}
-
-	/*
-	 * Assign record id to tfm in round-robin fashion, and this
-	 * will help tfm to bind  to corresponding descriptor rings.
-	 */
-	tctx->id = cryp->rec;
-	cryp->rec = !cryp->rec;
-
-	spin_unlock_bh(&mtk_sha.lock);
-
-	return cryp;
-}
-
-static int mtk_sha_append_sg(struct mtk_sha_reqctx *ctx)
-{
-	size_t count;
-
-	while ((ctx->bufcnt < SHA_BUF_SIZE) && ctx->total) {
-		count = min(ctx->sg->length - ctx->offset, ctx->total);
-		count = min(count, SHA_BUF_SIZE - ctx->bufcnt);
-
-		if (count <= 0) {
-			/*
-			 * Check if count <= 0 because the buffer is full or
-			 * because the sg length is 0. In the latest case,
-			 * check if there is another sg in the list, a 0 length
-			 * sg doesn't necessarily mean the end of the sg list.
-			 */
-			if ((ctx->sg->length == 0) && !sg_is_last(ctx->sg)) {
-				ctx->sg = sg_next(ctx->sg);
-				continue;
-			} else {
-				break;
-			}
-		}
-
-		scatterwalk_map_and_copy(ctx->buffer + ctx->bufcnt, ctx->sg,
-					 ctx->offset, count, 0);
-
-		ctx->bufcnt += count;
-		ctx->offset += count;
-		ctx->total -= count;
-
-		if (ctx->offset == ctx->sg->length) {
-			ctx->sg = sg_next(ctx->sg);
-			if (ctx->sg)
-				ctx->offset = 0;
-			else
-				ctx->total = 0;
-		}
-	}
-
-	return 0;
-}
-
-/*
- * The purpose of this padding is to ensure that the padded message is a
- * multiple of 512 bits (SHA1/SHA224/SHA256) or 1024 bits (SHA384/SHA512).
- * The bit "1" is appended at the end of the message followed by
- * "padlen-1" zero bits. Then a 64 bits block (SHA1/SHA224/SHA256) or
- * 128 bits block (SHA384/SHA512) equals to the message length in bits
- * is appended.
- *
- * For SHA1/SHA224/SHA256, padlen is calculated as followed:
- *  - if message length < 56 bytes then padlen = 56 - message length
- *  - else padlen = 64 + 56 - message length
- *
- * For SHA384/SHA512, padlen is calculated as followed:
- *  - if message length < 112 bytes then padlen = 112 - message length
- *  - else padlen = 128 + 112 - message length
- */
-static void mtk_sha_fill_padding(struct mtk_sha_reqctx *ctx, u32 len)
-{
-	u32 index, padlen;
-	__be64 bits[2];
-	u64 size = ctx->digcnt;
-
-	size += ctx->bufcnt;
-	size += len;
-
-	bits[1] = cpu_to_be64(size << 3);
-	bits[0] = cpu_to_be64(size >> 61);
-
-	switch (ctx->flags & SHA_FLAGS_ALGO_MSK) {
-	case SHA_FLAGS_SHA384:
-	case SHA_FLAGS_SHA512:
-		index = ctx->bufcnt & 0x7f;
-		padlen = (index < 112) ? (112 - index) : ((128 + 112) - index);
-		*(ctx->buffer + ctx->bufcnt) = 0x80;
-		memset(ctx->buffer + ctx->bufcnt + 1, 0, padlen - 1);
-		memcpy(ctx->buffer + ctx->bufcnt + padlen, bits, 16);
-		ctx->bufcnt += padlen + 16;
-		ctx->flags |= SHA_FLAGS_PAD;
-		break;
-
-	default:
-		index = ctx->bufcnt & 0x3f;
-		padlen = (index < 56) ? (56 - index) : ((64 + 56) - index);
-		*(ctx->buffer + ctx->bufcnt) = 0x80;
-		memset(ctx->buffer + ctx->bufcnt + 1, 0, padlen - 1);
-		memcpy(ctx->buffer + ctx->bufcnt + padlen, &bits[1], 8);
-		ctx->bufcnt += padlen + 8;
-		ctx->flags |= SHA_FLAGS_PAD;
-		break;
-	}
-}
-
-/* Initialize basic transform information of SHA */
-static void mtk_sha_info_init(struct mtk_sha_reqctx *ctx)
-{
-	struct mtk_sha_info *info = &ctx->info;
-
-	ctx->ct_hdr = SHA_CT_CTRL_HDR;
-	ctx->ct_size = SHA_CT_SIZE;
-
-	info->tfm[0] = SHA_TFM_HASH | SHA_TFM_SIZE(SIZE_IN_WORDS(ctx->ds));
-
-	switch (ctx->flags & SHA_FLAGS_ALGO_MSK) {
-	case SHA_FLAGS_SHA1:
-		info->tfm[0] |= SHA_TFM_SHA1;
-		break;
-	case SHA_FLAGS_SHA224:
-		info->tfm[0] |= SHA_TFM_SHA224;
-		break;
-	case SHA_FLAGS_SHA256:
-		info->tfm[0] |= SHA_TFM_SHA256;
-		break;
-	case SHA_FLAGS_SHA384:
-		info->tfm[0] |= SHA_TFM_SHA384;
-		break;
-	case SHA_FLAGS_SHA512:
-		info->tfm[0] |= SHA_TFM_SHA512;
-		break;
-
-	default:
-		/* Should not happen... */
-		return;
-	}
-
-	info->tfm[1] = SHA_TFM_HASH_STORE;
-	info->ctrl[0] = info->tfm[0] | SHA_TFM_CONTINUE | SHA_TFM_START;
-	info->ctrl[1] = info->tfm[1];
-
-	info->cmd[0] = SHA_CMD0;
-	info->cmd[1] = SHA_CMD1;
-	info->cmd[2] = SHA_CMD2 | SHA_TFM_DIGEST(SIZE_IN_WORDS(ctx->ds));
-}
-
-/*
- * Update input data length field of transform information and
- * map it to DMA region.
- */
-static int mtk_sha_info_update(struct mtk_cryp *cryp,
-			       struct mtk_sha_rec *sha,
-			       size_t len1, size_t len2)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
-	struct mtk_sha_info *info = &ctx->info;
-
-	ctx->ct_hdr &= ~SHA_DATA_LEN_MSK;
-	ctx->ct_hdr |= cpu_to_le32(len1 + len2);
-	info->cmd[0] &= ~SHA_DATA_LEN_MSK;
-	info->cmd[0] |= cpu_to_le32(len1 + len2);
-
-	/* Setting SHA_TFM_START only for the first iteration */
-	if (ctx->digcnt)
-		info->ctrl[0] &= ~SHA_TFM_START;
-
-	ctx->digcnt += len1;
-
-	ctx->ct_dma = dma_map_single(cryp->dev, info, sizeof(*info),
-				     DMA_BIDIRECTIONAL);
-	if (unlikely(dma_mapping_error(cryp->dev, ctx->ct_dma))) {
-		dev_err(cryp->dev, "dma %zu bytes error\n", sizeof(*info));
-		return -EINVAL;
-	}
-
-	ctx->tfm_dma = ctx->ct_dma + sizeof(info->ctrl) + sizeof(info->cmd);
-
-	return 0;
-}
-
-/*
- * Because of hardware limitation, we must pre-calculate the inner
- * and outer digest that need to be processed firstly by engine, then
- * apply the result digest to the input message. These complex hashing
- * procedures limits HMAC performance, so we use fallback SW encoding.
- */
-static int mtk_sha_finish_hmac(struct ahash_request *req)
-{
-	struct mtk_sha_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
-	struct mtk_sha_hmac_ctx *bctx = tctx->base;
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
-
-	SHASH_DESC_ON_STACK(shash, bctx->shash);
-
-	shash->tfm = bctx->shash;
-
-	return crypto_shash_init(shash) ?:
-	       crypto_shash_update(shash, bctx->opad, ctx->bs) ?:
-	       crypto_shash_finup(shash, req->result, ctx->ds, req->result);
-}
-
-/* Initialize request context */
-static int mtk_sha_init(struct ahash_request *req)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct mtk_sha_ctx *tctx = crypto_ahash_ctx(tfm);
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
-
-	ctx->flags = 0;
-	ctx->ds = crypto_ahash_digestsize(tfm);
-
-	switch (ctx->ds) {
-	case SHA1_DIGEST_SIZE:
-		ctx->flags |= SHA_FLAGS_SHA1;
-		ctx->bs = SHA1_BLOCK_SIZE;
-		break;
-	case SHA224_DIGEST_SIZE:
-		ctx->flags |= SHA_FLAGS_SHA224;
-		ctx->bs = SHA224_BLOCK_SIZE;
-		break;
-	case SHA256_DIGEST_SIZE:
-		ctx->flags |= SHA_FLAGS_SHA256;
-		ctx->bs = SHA256_BLOCK_SIZE;
-		break;
-	case SHA384_DIGEST_SIZE:
-		ctx->flags |= SHA_FLAGS_SHA384;
-		ctx->bs = SHA384_BLOCK_SIZE;
-		break;
-	case SHA512_DIGEST_SIZE:
-		ctx->flags |= SHA_FLAGS_SHA512;
-		ctx->bs = SHA512_BLOCK_SIZE;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	ctx->bufcnt = 0;
-	ctx->digcnt = 0;
-	ctx->buffer = tctx->buf;
-
-	if (tctx->flags & SHA_FLAGS_HMAC) {
-		struct mtk_sha_hmac_ctx *bctx = tctx->base;
-
-		memcpy(ctx->buffer, bctx->ipad, ctx->bs);
-		ctx->bufcnt = ctx->bs;
-		ctx->flags |= SHA_FLAGS_HMAC;
-	}
-
-	return 0;
-}
-
-static int mtk_sha_xmit(struct mtk_cryp *cryp, struct mtk_sha_rec *sha,
-			dma_addr_t addr1, size_t len1,
-			dma_addr_t addr2, size_t len2)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
-	struct mtk_ring *ring = cryp->ring[sha->id];
-	struct mtk_desc *cmd, *res;
-	int err, count = 0;
-
-	err = mtk_sha_info_update(cryp, sha, len1, len2);
-	if (err)
-		return err;
-
-	/* Fill in the command/result descriptors */
-	mtk_sha_ring_shift(ring, &cmd, &res, &count);
-
-	res->hdr = MTK_DESC_FIRST | MTK_DESC_BUF_LEN(len1);
-	cmd->hdr = MTK_DESC_FIRST | MTK_DESC_BUF_LEN(len1) |
-		   MTK_DESC_CT_LEN(ctx->ct_size);
-	cmd->buf = cpu_to_le32(addr1);
-	cmd->ct = cpu_to_le32(ctx->ct_dma);
-	cmd->ct_hdr = ctx->ct_hdr;
-	cmd->tfm = cpu_to_le32(ctx->tfm_dma);
-
-	if (len2) {
-		mtk_sha_ring_shift(ring, &cmd, &res, &count);
-
-		res->hdr = MTK_DESC_BUF_LEN(len2);
-		cmd->hdr = MTK_DESC_BUF_LEN(len2);
-		cmd->buf = cpu_to_le32(addr2);
-	}
-
-	cmd->hdr |= MTK_DESC_LAST;
-	res->hdr |= MTK_DESC_LAST;
-
-	/*
-	 * Make sure that all changes to the DMA ring are done before we
-	 * start engine.
-	 */
-	wmb();
-	/* Start DMA transfer */
-	mtk_sha_write(cryp, RDR_PREP_COUNT(sha->id), MTK_DESC_CNT(count));
-	mtk_sha_write(cryp, CDR_PREP_COUNT(sha->id), MTK_DESC_CNT(count));
-
-	return -EINPROGRESS;
-}
-
-static int mtk_sha_dma_map(struct mtk_cryp *cryp,
-			   struct mtk_sha_rec *sha,
-			   struct mtk_sha_reqctx *ctx,
-			   size_t count)
-{
-	ctx->dma_addr = dma_map_single(cryp->dev, ctx->buffer,
-				       SHA_BUF_SIZE, DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(cryp->dev, ctx->dma_addr))) {
-		dev_err(cryp->dev, "dma map error\n");
-		return -EINVAL;
-	}
-
-	ctx->flags &= ~SHA_FLAGS_SG;
-
-	return mtk_sha_xmit(cryp, sha, ctx->dma_addr, count, 0, 0);
-}
-
-static int mtk_sha_update_slow(struct mtk_cryp *cryp,
-			       struct mtk_sha_rec *sha)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
-	size_t count;
-	u32 final;
-
-	mtk_sha_append_sg(ctx);
-
-	final = (ctx->flags & SHA_FLAGS_FINUP) && !ctx->total;
-
-	dev_dbg(cryp->dev, "slow: bufcnt: %zu\n", ctx->bufcnt);
-
-	if (final) {
-		sha->flags |= SHA_FLAGS_FINAL;
-		mtk_sha_fill_padding(ctx, 0);
-	}
-
-	if (final || (ctx->bufcnt == SHA_BUF_SIZE && ctx->total)) {
-		count = ctx->bufcnt;
-		ctx->bufcnt = 0;
-
-		return mtk_sha_dma_map(cryp, sha, ctx, count);
-	}
-	return 0;
-}
-
-static int mtk_sha_update_start(struct mtk_cryp *cryp,
-				struct mtk_sha_rec *sha)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
-	u32 len, final, tail;
-	struct scatterlist *sg;
-
-	if (!ctx->total)
-		return 0;
-
-	if (ctx->bufcnt || ctx->offset)
-		return mtk_sha_update_slow(cryp, sha);
-
-	sg = ctx->sg;
-
-	if (!IS_ALIGNED(sg->offset, sizeof(u32)))
-		return mtk_sha_update_slow(cryp, sha);
-
-	if (!sg_is_last(sg) && !IS_ALIGNED(sg->length, ctx->bs))
-		/* size is not ctx->bs aligned */
-		return mtk_sha_update_slow(cryp, sha);
-
-	len = min(ctx->total, sg->length);
-
-	if (sg_is_last(sg)) {
-		if (!(ctx->flags & SHA_FLAGS_FINUP)) {
-			/* not last sg must be ctx->bs aligned */
-			tail = len & (ctx->bs - 1);
-			len -= tail;
-		}
-	}
-
-	ctx->total -= len;
-	ctx->offset = len; /* offset where to start slow */
-
-	final = (ctx->flags & SHA_FLAGS_FINUP) && !ctx->total;
-
-	/* Add padding */
-	if (final) {
-		size_t count;
-
-		tail = len & (ctx->bs - 1);
-		len -= tail;
-		ctx->total += tail;
-		ctx->offset = len; /* offset where to start slow */
-
-		sg = ctx->sg;
-		mtk_sha_append_sg(ctx);
-		mtk_sha_fill_padding(ctx, len);
-
-		ctx->dma_addr = dma_map_single(cryp->dev, ctx->buffer,
-					       SHA_BUF_SIZE, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(cryp->dev, ctx->dma_addr))) {
-			dev_err(cryp->dev, "dma map bytes error\n");
-			return -EINVAL;
-		}
-
-		sha->flags |= SHA_FLAGS_FINAL;
-		count = ctx->bufcnt;
-		ctx->bufcnt = 0;
-
-		if (len == 0) {
-			ctx->flags &= ~SHA_FLAGS_SG;
-			return mtk_sha_xmit(cryp, sha, ctx->dma_addr,
-					    count, 0, 0);
-
-		} else {
-			ctx->sg = sg;
-			if (!dma_map_sg(cryp->dev, ctx->sg, 1, DMA_TO_DEVICE)) {
-				dev_err(cryp->dev, "dma_map_sg error\n");
-				return -EINVAL;
-			}
-
-			ctx->flags |= SHA_FLAGS_SG;
-			return mtk_sha_xmit(cryp, sha, sg_dma_address(ctx->sg),
-					    len, ctx->dma_addr, count);
-		}
-	}
-
-	if (!dma_map_sg(cryp->dev, ctx->sg, 1, DMA_TO_DEVICE)) {
-		dev_err(cryp->dev, "dma_map_sg  error\n");
-		return -EINVAL;
-	}
-
-	ctx->flags |= SHA_FLAGS_SG;
-
-	return mtk_sha_xmit(cryp, sha, sg_dma_address(ctx->sg),
-			    len, 0, 0);
-}
-
-static int mtk_sha_final_req(struct mtk_cryp *cryp,
-			     struct mtk_sha_rec *sha)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
-	size_t count;
-
-	mtk_sha_fill_padding(ctx, 0);
-
-	sha->flags |= SHA_FLAGS_FINAL;
-	count = ctx->bufcnt;
-	ctx->bufcnt = 0;
-
-	return mtk_sha_dma_map(cryp, sha, ctx, count);
-}
-
-/* Copy ready hash (+ finalize hmac) */
-static int mtk_sha_finish(struct ahash_request *req)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
-	__le32 *digest = ctx->info.digest;
-	u32 *result = (u32 *)req->result;
-	int i;
-
-	/* Get the hash from the digest buffer */
-	for (i = 0; i < SIZE_IN_WORDS(ctx->ds); i++)
-		result[i] = le32_to_cpu(digest[i]);
-
-	if (ctx->flags & SHA_FLAGS_HMAC)
-		return mtk_sha_finish_hmac(req);
-
-	return 0;
-}
-
-static void mtk_sha_finish_req(struct mtk_cryp *cryp,
-			       struct mtk_sha_rec *sha,
-			       int err)
-{
-	if (likely(!err && (SHA_FLAGS_FINAL & sha->flags)))
-		err = mtk_sha_finish(sha->req);
-
-	sha->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL);
-
-	sha->req->base.complete(&sha->req->base, err);
-
-	/* Handle new request */
-	tasklet_schedule(&sha->queue_task);
-}
-
-static int mtk_sha_handle_queue(struct mtk_cryp *cryp, u8 id,
-				struct ahash_request *req)
-{
-	struct mtk_sha_rec *sha = cryp->sha[id];
-	struct crypto_async_request *async_req, *backlog;
-	struct mtk_sha_reqctx *ctx;
-	unsigned long flags;
-	int err = 0, ret = 0;
-
-	spin_lock_irqsave(&sha->lock, flags);
-	if (req)
-		ret = ahash_enqueue_request(&sha->queue, req);
-
-	if (SHA_FLAGS_BUSY & sha->flags) {
-		spin_unlock_irqrestore(&sha->lock, flags);
-		return ret;
-	}
-
-	backlog = crypto_get_backlog(&sha->queue);
-	async_req = crypto_dequeue_request(&sha->queue);
-	if (async_req)
-		sha->flags |= SHA_FLAGS_BUSY;
-	spin_unlock_irqrestore(&sha->lock, flags);
-
-	if (!async_req)
-		return ret;
-
-	if (backlog)
-		backlog->complete(backlog, -EINPROGRESS);
-
-	req = ahash_request_cast(async_req);
-	ctx = ahash_request_ctx(req);
-
-	sha->req = req;
-
-	mtk_sha_info_init(ctx);
-
-	if (ctx->op == SHA_OP_UPDATE) {
-		err = mtk_sha_update_start(cryp, sha);
-		if (err != -EINPROGRESS && (ctx->flags & SHA_FLAGS_FINUP))
-			/* No final() after finup() */
-			err = mtk_sha_final_req(cryp, sha);
-	} else if (ctx->op == SHA_OP_FINAL) {
-		err = mtk_sha_final_req(cryp, sha);
-	}
-
-	if (unlikely(err != -EINPROGRESS))
-		/* Task will not finish it, so do it here */
-		mtk_sha_finish_req(cryp, sha, err);
-
-	return ret;
-}
-
-static int mtk_sha_enqueue(struct ahash_request *req, u32 op)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
-	struct mtk_sha_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
-
-	ctx->op = op;
-
-	return mtk_sha_handle_queue(tctx->cryp, tctx->id, req);
-}
-
-static void mtk_sha_unmap(struct mtk_cryp *cryp, struct mtk_sha_rec *sha)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(sha->req);
-
-	dma_unmap_single(cryp->dev, ctx->ct_dma, sizeof(ctx->info),
-			 DMA_BIDIRECTIONAL);
-
-	if (ctx->flags & SHA_FLAGS_SG) {
-		dma_unmap_sg(cryp->dev, ctx->sg, 1, DMA_TO_DEVICE);
-		if (ctx->sg->length == ctx->offset) {
-			ctx->sg = sg_next(ctx->sg);
-			if (ctx->sg)
-				ctx->offset = 0;
-		}
-		if (ctx->flags & SHA_FLAGS_PAD) {
-			dma_unmap_single(cryp->dev, ctx->dma_addr,
-					 SHA_BUF_SIZE, DMA_TO_DEVICE);
-		}
-	} else
-		dma_unmap_single(cryp->dev, ctx->dma_addr,
-				 SHA_BUF_SIZE, DMA_TO_DEVICE);
-}
-
-static void mtk_sha_complete(struct mtk_cryp *cryp,
-			     struct mtk_sha_rec *sha)
-{
-	int err = 0;
-
-	err = mtk_sha_update_start(cryp, sha);
-	if (err != -EINPROGRESS)
-		mtk_sha_finish_req(cryp, sha, err);
-}
-
-static int mtk_sha_update(struct ahash_request *req)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
-
-	ctx->total = req->nbytes;
-	ctx->sg = req->src;
-	ctx->offset = 0;
-
-	if ((ctx->bufcnt + ctx->total < SHA_BUF_SIZE) &&
-	    !(ctx->flags & SHA_FLAGS_FINUP))
-		return mtk_sha_append_sg(ctx);
-
-	return mtk_sha_enqueue(req, SHA_OP_UPDATE);
-}
-
-static int mtk_sha_final(struct ahash_request *req)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
-
-	ctx->flags |= SHA_FLAGS_FINUP;
-
-	if (ctx->flags & SHA_FLAGS_PAD)
-		return mtk_sha_finish(req);
-
-	return mtk_sha_enqueue(req, SHA_OP_FINAL);
-}
-
-static int mtk_sha_finup(struct ahash_request *req)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
-	int err1, err2;
-
-	ctx->flags |= SHA_FLAGS_FINUP;
-
-	err1 = mtk_sha_update(req);
-	if (err1 == -EINPROGRESS ||
-	    (err1 == -EBUSY && (ahash_request_flags(req) &
-				CRYPTO_TFM_REQ_MAY_BACKLOG)))
-		return err1;
-	/*
-	 * final() has to be always called to cleanup resources
-	 * even if update() failed
-	 */
-	err2 = mtk_sha_final(req);
-
-	return err1 ?: err2;
-}
-
-static int mtk_sha_digest(struct ahash_request *req)
-{
-	return mtk_sha_init(req) ?: mtk_sha_finup(req);
-}
-
-static int mtk_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
-			  u32 keylen)
-{
-	struct mtk_sha_ctx *tctx = crypto_ahash_ctx(tfm);
-	struct mtk_sha_hmac_ctx *bctx = tctx->base;
-	size_t bs = crypto_shash_blocksize(bctx->shash);
-	size_t ds = crypto_shash_digestsize(bctx->shash);
-	int err, i;
-
-	if (keylen > bs) {
-		err = crypto_shash_tfm_digest(bctx->shash, key, keylen,
-					      bctx->ipad);
-		if (err)
-			return err;
-		keylen = ds;
-	} else {
-		memcpy(bctx->ipad, key, keylen);
-	}
-
-	memset(bctx->ipad + keylen, 0, bs - keylen);
-	memcpy(bctx->opad, bctx->ipad, bs);
-
-	for (i = 0; i < bs; i++) {
-		bctx->ipad[i] ^= HMAC_IPAD_VALUE;
-		bctx->opad[i] ^= HMAC_OPAD_VALUE;
-	}
-
-	return 0;
-}
-
-static int mtk_sha_export(struct ahash_request *req, void *out)
-{
-	const struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
-
-	memcpy(out, ctx, sizeof(*ctx));
-	return 0;
-}
-
-static int mtk_sha_import(struct ahash_request *req, const void *in)
-{
-	struct mtk_sha_reqctx *ctx = ahash_request_ctx(req);
-
-	memcpy(ctx, in, sizeof(*ctx));
-	return 0;
-}
-
-static int mtk_sha_cra_init_alg(struct crypto_tfm *tfm,
-				const char *alg_base)
-{
-	struct mtk_sha_ctx *tctx = crypto_tfm_ctx(tfm);
-	struct mtk_cryp *cryp = NULL;
-
-	cryp = mtk_sha_find_dev(tctx);
-	if (!cryp)
-		return -ENODEV;
-
-	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-				 sizeof(struct mtk_sha_reqctx));
-
-	if (alg_base) {
-		struct mtk_sha_hmac_ctx *bctx = tctx->base;
-
-		tctx->flags |= SHA_FLAGS_HMAC;
-		bctx->shash = crypto_alloc_shash(alg_base, 0,
-					CRYPTO_ALG_NEED_FALLBACK);
-		if (IS_ERR(bctx->shash)) {
-			pr_err("base driver %s could not be loaded.\n",
-			       alg_base);
-
-			return PTR_ERR(bctx->shash);
-		}
-	}
-	return 0;
-}
-
-static int mtk_sha_cra_init(struct crypto_tfm *tfm)
-{
-	return mtk_sha_cra_init_alg(tfm, NULL);
-}
-
-static int mtk_sha_cra_sha1_init(struct crypto_tfm *tfm)
-{
-	return mtk_sha_cra_init_alg(tfm, "sha1");
-}
-
-static int mtk_sha_cra_sha224_init(struct crypto_tfm *tfm)
-{
-	return mtk_sha_cra_init_alg(tfm, "sha224");
-}
-
-static int mtk_sha_cra_sha256_init(struct crypto_tfm *tfm)
-{
-	return mtk_sha_cra_init_alg(tfm, "sha256");
-}
-
-static int mtk_sha_cra_sha384_init(struct crypto_tfm *tfm)
-{
-	return mtk_sha_cra_init_alg(tfm, "sha384");
-}
-
-static int mtk_sha_cra_sha512_init(struct crypto_tfm *tfm)
-{
-	return mtk_sha_cra_init_alg(tfm, "sha512");
-}
-
-static void mtk_sha_cra_exit(struct crypto_tfm *tfm)
-{
-	struct mtk_sha_ctx *tctx = crypto_tfm_ctx(tfm);
-
-	if (tctx->flags & SHA_FLAGS_HMAC) {
-		struct mtk_sha_hmac_ctx *bctx = tctx->base;
-
-		crypto_free_shash(bctx->shash);
-	}
-}
-
-static struct ahash_alg algs_sha1_sha224_sha256[] = {
-{
-	.init		= mtk_sha_init,
-	.update		= mtk_sha_update,
-	.final		= mtk_sha_final,
-	.finup		= mtk_sha_finup,
-	.digest		= mtk_sha_digest,
-	.export		= mtk_sha_export,
-	.import		= mtk_sha_import,
-	.halg.digestsize	= SHA1_DIGEST_SIZE,
-	.halg.statesize = sizeof(struct mtk_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "sha1",
-		.cra_driver_name	= "mtk-sha1",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= SHA1_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct mtk_sha_ctx),
-		.cra_alignmask		= SHA_ALIGN_MSK,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= mtk_sha_cra_init,
-		.cra_exit		= mtk_sha_cra_exit,
-	}
-},
-{
-	.init		= mtk_sha_init,
-	.update		= mtk_sha_update,
-	.final		= mtk_sha_final,
-	.finup		= mtk_sha_finup,
-	.digest		= mtk_sha_digest,
-	.export		= mtk_sha_export,
-	.import		= mtk_sha_import,
-	.halg.digestsize	= SHA224_DIGEST_SIZE,
-	.halg.statesize = sizeof(struct mtk_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "sha224",
-		.cra_driver_name	= "mtk-sha224",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= SHA224_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct mtk_sha_ctx),
-		.cra_alignmask		= SHA_ALIGN_MSK,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= mtk_sha_cra_init,
-		.cra_exit		= mtk_sha_cra_exit,
-	}
-},
-{
-	.init		= mtk_sha_init,
-	.update		= mtk_sha_update,
-	.final		= mtk_sha_final,
-	.finup		= mtk_sha_finup,
-	.digest		= mtk_sha_digest,
-	.export		= mtk_sha_export,
-	.import		= mtk_sha_import,
-	.halg.digestsize	= SHA256_DIGEST_SIZE,
-	.halg.statesize = sizeof(struct mtk_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "sha256",
-		.cra_driver_name	= "mtk-sha256",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= SHA256_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct mtk_sha_ctx),
-		.cra_alignmask		= SHA_ALIGN_MSK,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= mtk_sha_cra_init,
-		.cra_exit		= mtk_sha_cra_exit,
-	}
-},
-{
-	.init		= mtk_sha_init,
-	.update		= mtk_sha_update,
-	.final		= mtk_sha_final,
-	.finup		= mtk_sha_finup,
-	.digest		= mtk_sha_digest,
-	.export		= mtk_sha_export,
-	.import		= mtk_sha_import,
-	.setkey		= mtk_sha_setkey,
-	.halg.digestsize	= SHA1_DIGEST_SIZE,
-	.halg.statesize = sizeof(struct mtk_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "hmac(sha1)",
-		.cra_driver_name	= "mtk-hmac-sha1",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC |
-					  CRYPTO_ALG_NEED_FALLBACK,
-		.cra_blocksize		= SHA1_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct mtk_sha_ctx) +
-					sizeof(struct mtk_sha_hmac_ctx),
-		.cra_alignmask		= SHA_ALIGN_MSK,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= mtk_sha_cra_sha1_init,
-		.cra_exit		= mtk_sha_cra_exit,
-	}
-},
-{
-	.init		= mtk_sha_init,
-	.update		= mtk_sha_update,
-	.final		= mtk_sha_final,
-	.finup		= mtk_sha_finup,
-	.digest		= mtk_sha_digest,
-	.export		= mtk_sha_export,
-	.import		= mtk_sha_import,
-	.setkey		= mtk_sha_setkey,
-	.halg.digestsize	= SHA224_DIGEST_SIZE,
-	.halg.statesize = sizeof(struct mtk_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "hmac(sha224)",
-		.cra_driver_name	= "mtk-hmac-sha224",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC |
-					  CRYPTO_ALG_NEED_FALLBACK,
-		.cra_blocksize		= SHA224_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct mtk_sha_ctx) +
-					sizeof(struct mtk_sha_hmac_ctx),
-		.cra_alignmask		= SHA_ALIGN_MSK,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= mtk_sha_cra_sha224_init,
-		.cra_exit		= mtk_sha_cra_exit,
-	}
-},
-{
-	.init		= mtk_sha_init,
-	.update		= mtk_sha_update,
-	.final		= mtk_sha_final,
-	.finup		= mtk_sha_finup,
-	.digest		= mtk_sha_digest,
-	.export		= mtk_sha_export,
-	.import		= mtk_sha_import,
-	.setkey		= mtk_sha_setkey,
-	.halg.digestsize	= SHA256_DIGEST_SIZE,
-	.halg.statesize = sizeof(struct mtk_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "hmac(sha256)",
-		.cra_driver_name	= "mtk-hmac-sha256",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC |
-					  CRYPTO_ALG_NEED_FALLBACK,
-		.cra_blocksize		= SHA256_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct mtk_sha_ctx) +
-					sizeof(struct mtk_sha_hmac_ctx),
-		.cra_alignmask		= SHA_ALIGN_MSK,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= mtk_sha_cra_sha256_init,
-		.cra_exit		= mtk_sha_cra_exit,
-	}
-},
-};
-
-static struct ahash_alg algs_sha384_sha512[] = {
-{
-	.init		= mtk_sha_init,
-	.update		= mtk_sha_update,
-	.final		= mtk_sha_final,
-	.finup		= mtk_sha_finup,
-	.digest		= mtk_sha_digest,
-	.export		= mtk_sha_export,
-	.import		= mtk_sha_import,
-	.halg.digestsize	= SHA384_DIGEST_SIZE,
-	.halg.statesize = sizeof(struct mtk_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "sha384",
-		.cra_driver_name	= "mtk-sha384",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= SHA384_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct mtk_sha_ctx),
-		.cra_alignmask		= SHA_ALIGN_MSK,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= mtk_sha_cra_init,
-		.cra_exit		= mtk_sha_cra_exit,
-	}
-},
-{
-	.init		= mtk_sha_init,
-	.update		= mtk_sha_update,
-	.final		= mtk_sha_final,
-	.finup		= mtk_sha_finup,
-	.digest		= mtk_sha_digest,
-	.export		= mtk_sha_export,
-	.import		= mtk_sha_import,
-	.halg.digestsize	= SHA512_DIGEST_SIZE,
-	.halg.statesize = sizeof(struct mtk_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "sha512",
-		.cra_driver_name	= "mtk-sha512",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= SHA512_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct mtk_sha_ctx),
-		.cra_alignmask		= SHA_ALIGN_MSK,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= mtk_sha_cra_init,
-		.cra_exit		= mtk_sha_cra_exit,
-	}
-},
-{
-	.init		= mtk_sha_init,
-	.update		= mtk_sha_update,
-	.final		= mtk_sha_final,
-	.finup		= mtk_sha_finup,
-	.digest		= mtk_sha_digest,
-	.export		= mtk_sha_export,
-	.import		= mtk_sha_import,
-	.setkey		= mtk_sha_setkey,
-	.halg.digestsize	= SHA384_DIGEST_SIZE,
-	.halg.statesize = sizeof(struct mtk_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "hmac(sha384)",
-		.cra_driver_name	= "mtk-hmac-sha384",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC |
-					  CRYPTO_ALG_NEED_FALLBACK,
-		.cra_blocksize		= SHA384_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct mtk_sha_ctx) +
-					sizeof(struct mtk_sha_hmac_ctx),
-		.cra_alignmask		= SHA_ALIGN_MSK,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= mtk_sha_cra_sha384_init,
-		.cra_exit		= mtk_sha_cra_exit,
-	}
-},
-{
-	.init		= mtk_sha_init,
-	.update		= mtk_sha_update,
-	.final		= mtk_sha_final,
-	.finup		= mtk_sha_finup,
-	.digest		= mtk_sha_digest,
-	.export		= mtk_sha_export,
-	.import		= mtk_sha_import,
-	.setkey		= mtk_sha_setkey,
-	.halg.digestsize	= SHA512_DIGEST_SIZE,
-	.halg.statesize = sizeof(struct mtk_sha_reqctx),
-	.halg.base	= {
-		.cra_name		= "hmac(sha512)",
-		.cra_driver_name	= "mtk-hmac-sha512",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC |
-					  CRYPTO_ALG_NEED_FALLBACK,
-		.cra_blocksize		= SHA512_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct mtk_sha_ctx) +
-					sizeof(struct mtk_sha_hmac_ctx),
-		.cra_alignmask		= SHA_ALIGN_MSK,
-		.cra_module		= THIS_MODULE,
-		.cra_init		= mtk_sha_cra_sha512_init,
-		.cra_exit		= mtk_sha_cra_exit,
-	}
-},
-};
-
-static void mtk_sha_queue_task(unsigned long data)
-{
-	struct mtk_sha_rec *sha = (struct mtk_sha_rec *)data;
-
-	mtk_sha_handle_queue(sha->cryp, sha->id - MTK_RING2, NULL);
-}
-
-static void mtk_sha_done_task(unsigned long data)
-{
-	struct mtk_sha_rec *sha = (struct mtk_sha_rec *)data;
-	struct mtk_cryp *cryp = sha->cryp;
-
-	mtk_sha_unmap(cryp, sha);
-	mtk_sha_complete(cryp, sha);
-}
-
-static irqreturn_t mtk_sha_irq(int irq, void *dev_id)
-{
-	struct mtk_sha_rec *sha = (struct mtk_sha_rec *)dev_id;
-	struct mtk_cryp *cryp = sha->cryp;
-	u32 val = mtk_sha_read(cryp, RDR_STAT(sha->id));
-
-	mtk_sha_write(cryp, RDR_STAT(sha->id), val);
-
-	if (likely((SHA_FLAGS_BUSY & sha->flags))) {
-		mtk_sha_write(cryp, RDR_PROC_COUNT(sha->id), MTK_CNT_RST);
-		mtk_sha_write(cryp, RDR_THRESH(sha->id),
-			      MTK_RDR_PROC_THRESH | MTK_RDR_PROC_MODE);
-
-		tasklet_schedule(&sha->done_task);
-	} else {
-		dev_warn(cryp->dev, "SHA interrupt when no active requests.\n");
-	}
-	return IRQ_HANDLED;
-}
-
-/*
- * The purpose of two SHA records is used to get extra performance.
- * It is similar to mtk_aes_record_init().
- */
-static int mtk_sha_record_init(struct mtk_cryp *cryp)
-{
-	struct mtk_sha_rec **sha = cryp->sha;
-	int i, err = -ENOMEM;
-
-	for (i = 0; i < MTK_REC_NUM; i++) {
-		sha[i] = kzalloc(sizeof(**sha), GFP_KERNEL);
-		if (!sha[i])
-			goto err_cleanup;
-
-		sha[i]->cryp = cryp;
-
-		spin_lock_init(&sha[i]->lock);
-		crypto_init_queue(&sha[i]->queue, SHA_QUEUE_SIZE);
-
-		tasklet_init(&sha[i]->queue_task, mtk_sha_queue_task,
-			     (unsigned long)sha[i]);
-		tasklet_init(&sha[i]->done_task, mtk_sha_done_task,
-			     (unsigned long)sha[i]);
-	}
-
-	/* Link to ring2 and ring3 respectively */
-	sha[0]->id = MTK_RING2;
-	sha[1]->id = MTK_RING3;
-
-	cryp->rec = 1;
-
-	return 0;
-
-err_cleanup:
-	for (; i--; )
-		kfree(sha[i]);
-	return err;
-}
-
-static void mtk_sha_record_free(struct mtk_cryp *cryp)
-{
-	int i;
-
-	for (i = 0; i < MTK_REC_NUM; i++) {
-		tasklet_kill(&cryp->sha[i]->done_task);
-		tasklet_kill(&cryp->sha[i]->queue_task);
-
-		kfree(cryp->sha[i]);
-	}
-}
-
-static void mtk_sha_unregister_algs(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(algs_sha1_sha224_sha256); i++)
-		crypto_unregister_ahash(&algs_sha1_sha224_sha256[i]);
-
-	for (i = 0; i < ARRAY_SIZE(algs_sha384_sha512); i++)
-		crypto_unregister_ahash(&algs_sha384_sha512[i]);
-}
-
-static int mtk_sha_register_algs(void)
-{
-	int err, i;
-
-	for (i = 0; i < ARRAY_SIZE(algs_sha1_sha224_sha256); i++) {
-		err = crypto_register_ahash(&algs_sha1_sha224_sha256[i]);
-		if (err)
-			goto err_sha_224_256_algs;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(algs_sha384_sha512); i++) {
-		err = crypto_register_ahash(&algs_sha384_sha512[i]);
-		if (err)
-			goto err_sha_384_512_algs;
-	}
-
-	return 0;
-
-err_sha_384_512_algs:
-	for (; i--; )
-		crypto_unregister_ahash(&algs_sha384_sha512[i]);
-	i = ARRAY_SIZE(algs_sha1_sha224_sha256);
-err_sha_224_256_algs:
-	for (; i--; )
-		crypto_unregister_ahash(&algs_sha1_sha224_sha256[i]);
-
-	return err;
-}
-
-int mtk_hash_alg_register(struct mtk_cryp *cryp)
-{
-	int err;
-
-	INIT_LIST_HEAD(&cryp->sha_list);
-
-	/* Initialize two hash records */
-	err = mtk_sha_record_init(cryp);
-	if (err)
-		goto err_record;
-
-	err = devm_request_irq(cryp->dev, cryp->irq[MTK_RING2], mtk_sha_irq,
-			       0, "mtk-sha", cryp->sha[0]);
-	if (err) {
-		dev_err(cryp->dev, "unable to request sha irq0.\n");
-		goto err_res;
-	}
-
-	err = devm_request_irq(cryp->dev, cryp->irq[MTK_RING3], mtk_sha_irq,
-			       0, "mtk-sha", cryp->sha[1]);
-	if (err) {
-		dev_err(cryp->dev, "unable to request sha irq1.\n");
-		goto err_res;
-	}
-
-	/* Enable ring2 and ring3 interrupt for hash */
-	mtk_sha_write(cryp, AIC_ENABLE_SET(MTK_RING2), MTK_IRQ_RDR2);
-	mtk_sha_write(cryp, AIC_ENABLE_SET(MTK_RING3), MTK_IRQ_RDR3);
-
-	spin_lock(&mtk_sha.lock);
-	list_add_tail(&cryp->sha_list, &mtk_sha.dev_list);
-	spin_unlock(&mtk_sha.lock);
-
-	err = mtk_sha_register_algs();
-	if (err)
-		goto err_algs;
-
-	return 0;
-
-err_algs:
-	spin_lock(&mtk_sha.lock);
-	list_del(&cryp->sha_list);
-	spin_unlock(&mtk_sha.lock);
-err_res:
-	mtk_sha_record_free(cryp);
-err_record:
-
-	dev_err(cryp->dev, "mtk-sha initialization failed.\n");
-	return err;
-}
-
-void mtk_hash_alg_release(struct mtk_cryp *cryp)
-{
-	spin_lock(&mtk_sha.lock);
-	list_del(&cryp->sha_list);
-	spin_unlock(&mtk_sha.lock);
-
-	mtk_sha_unregister_algs();
-	mtk_sha_record_free(cryp);
-}
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
deleted file mode 100644
index 84f9c16d984c..000000000000
--- a/drivers/crypto/picoxcell_crypto.c
+++ /dev/null
@@ -1,1807 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (c) 2010-2011 Picochip Ltd., Jamie Iles
- */
-#include <crypto/internal/aead.h>
-#include <crypto/aes.h>
-#include <crypto/algapi.h>
-#include <crypto/authenc.h>
-#include <crypto/internal/des.h>
-#include <crypto/md5.h>
-#include <crypto/sha1.h>
-#include <crypto/sha2.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/clk.h>
-#include <linux/crypto.h>
-#include <linux/delay.h>
-#include <linux/dma-mapping.h>
-#include <linux/dmapool.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/list.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/pm.h>
-#include <linux/rtnetlink.h>
-#include <linux/scatterlist.h>
-#include <linux/sched.h>
-#include <linux/sizes.h>
-#include <linux/slab.h>
-#include <linux/timer.h>
-
-#include "picoxcell_crypto_regs.h"
-
-/*
- * The threshold for the number of entries in the CMD FIFO available before
- * the CMD0_CNT interrupt is raised. Increasing this value will reduce the
- * number of interrupts raised to the CPU.
- */
-#define CMD0_IRQ_THRESHOLD   1
-
-/*
- * The timeout period (in jiffies) for a PDU. When the the number of PDUs in
- * flight is greater than the STAT_IRQ_THRESHOLD or 0 the timer is disabled.
- * When there are packets in flight but lower than the threshold, we enable
- * the timer and at expiry, attempt to remove any processed packets from the
- * queue and if there are still packets left, schedule the timer again.
- */
-#define PACKET_TIMEOUT	    1
-
-/* The priority to register each algorithm with. */
-#define SPACC_CRYPTO_ALG_PRIORITY	10000
-
-#define SPACC_CRYPTO_KASUMI_F8_KEY_LEN	16
-#define SPACC_CRYPTO_IPSEC_CIPHER_PG_SZ 64
-#define SPACC_CRYPTO_IPSEC_HASH_PG_SZ	64
-#define SPACC_CRYPTO_IPSEC_MAX_CTXS	32
-#define SPACC_CRYPTO_IPSEC_FIFO_SZ	32
-#define SPACC_CRYPTO_L2_CIPHER_PG_SZ	64
-#define SPACC_CRYPTO_L2_HASH_PG_SZ	64
-#define SPACC_CRYPTO_L2_MAX_CTXS	128
-#define SPACC_CRYPTO_L2_FIFO_SZ		128
-
-#define MAX_DDT_LEN			16
-
-/* DDT format. This must match the hardware DDT format exactly. */
-struct spacc_ddt {
-	dma_addr_t	p;
-	u32		len;
-};
-
-/*
- * Asynchronous crypto request structure.
- *
- * This structure defines a request that is either queued for processing or
- * being processed.
- */
-struct spacc_req {
-	struct list_head		list;
-	struct spacc_engine		*engine;
-	struct crypto_async_request	*req;
-	int				result;
-	bool				is_encrypt;
-	unsigned			ctx_id;
-	dma_addr_t			src_addr, dst_addr;
-	struct spacc_ddt		*src_ddt, *dst_ddt;
-	void				(*complete)(struct spacc_req *req);
-	struct skcipher_request		fallback_req;	// keep at the end
-};
-
-struct spacc_aead {
-	unsigned long			ctrl_default;
-	unsigned long			type;
-	struct aead_alg			alg;
-	struct spacc_engine		*engine;
-	struct list_head		entry;
-	int				key_offs;
-	int				iv_offs;
-};
-
-struct spacc_engine {
-	void __iomem			*regs;
-	struct list_head		pending;
-	int				next_ctx;
-	spinlock_t			hw_lock;
-	int				in_flight;
-	struct list_head		completed;
-	struct list_head		in_progress;
-	struct tasklet_struct		complete;
-	unsigned long			fifo_sz;
-	void __iomem			*cipher_ctx_base;
-	void __iomem			*hash_key_base;
-	struct spacc_alg		*algs;
-	unsigned			num_algs;
-	struct list_head		registered_algs;
-	struct spacc_aead		*aeads;
-	unsigned			num_aeads;
-	struct list_head		registered_aeads;
-	size_t				cipher_pg_sz;
-	size_t				hash_pg_sz;
-	const char			*name;
-	struct clk			*clk;
-	struct device			*dev;
-	unsigned			max_ctxs;
-	struct timer_list		packet_timeout;
-	unsigned			stat_irq_thresh;
-	struct dma_pool			*req_pool;
-};
-
-/* Algorithm type mask. */
-#define SPACC_CRYPTO_ALG_MASK		0x7
-
-/* SPACC definition of a crypto algorithm. */
-struct spacc_alg {
-	unsigned long			ctrl_default;
-	unsigned long			type;
-	struct skcipher_alg		alg;
-	struct spacc_engine		*engine;
-	struct list_head		entry;
-	int				key_offs;
-	int				iv_offs;
-};
-
-/* Generic context structure for any algorithm type. */
-struct spacc_generic_ctx {
-	struct spacc_engine		*engine;
-	int				flags;
-	int				key_offs;
-	int				iv_offs;
-};
-
-/* Block cipher context. */
-struct spacc_ablk_ctx {
-	struct spacc_generic_ctx	generic;
-	u8				key[AES_MAX_KEY_SIZE];
-	u8				key_len;
-	/*
-	 * The fallback cipher. If the operation can't be done in hardware,
-	 * fallback to a software version.
-	 */
-	struct crypto_skcipher		*sw_cipher;
-};
-
-/* AEAD cipher context. */
-struct spacc_aead_ctx {
-	struct spacc_generic_ctx	generic;
-	u8				cipher_key[AES_MAX_KEY_SIZE];
-	u8				hash_ctx[SPACC_CRYPTO_IPSEC_HASH_PG_SZ];
-	u8				cipher_key_len;
-	u8				hash_key_len;
-	struct crypto_aead		*sw_cipher;
-};
-
-static int spacc_ablk_submit(struct spacc_req *req);
-
-static inline struct spacc_alg *to_spacc_skcipher(struct skcipher_alg *alg)
-{
-	return alg ? container_of(alg, struct spacc_alg, alg) : NULL;
-}
-
-static inline struct spacc_aead *to_spacc_aead(struct aead_alg *alg)
-{
-	return container_of(alg, struct spacc_aead, alg);
-}
-
-static inline int spacc_fifo_cmd_full(struct spacc_engine *engine)
-{
-	u32 fifo_stat = readl(engine->regs + SPA_FIFO_STAT_REG_OFFSET);
-
-	return fifo_stat & SPA_FIFO_CMD_FULL;
-}
-
-/*
- * Given a cipher context, and a context number, get the base address of the
- * context page.
- *
- * Returns the address of the context page where the key/context may
- * be written.
- */
-static inline void __iomem *spacc_ctx_page_addr(struct spacc_generic_ctx *ctx,
-						unsigned indx,
-						bool is_cipher_ctx)
-{
-	return is_cipher_ctx ? ctx->engine->cipher_ctx_base +
-			(indx * ctx->engine->cipher_pg_sz) :
-		ctx->engine->hash_key_base + (indx * ctx->engine->hash_pg_sz);
-}
-
-/* The context pages can only be written with 32-bit accesses. */
-static inline void memcpy_toio32(u32 __iomem *dst, const void *src,
-				 unsigned count)
-{
-	const u32 *src32 = (const u32 *) src;
-
-	while (count--)
-		writel(*src32++, dst++);
-}
-
-static void spacc_cipher_write_ctx(struct spacc_generic_ctx *ctx,
-				   void __iomem *page_addr, const u8 *key,
-				   size_t key_len, const u8 *iv, size_t iv_len)
-{
-	void __iomem *key_ptr = page_addr + ctx->key_offs;
-	void __iomem *iv_ptr = page_addr + ctx->iv_offs;
-
-	memcpy_toio32(key_ptr, key, key_len / 4);
-	memcpy_toio32(iv_ptr, iv, iv_len / 4);
-}
-
-/*
- * Load a context into the engines context memory.
- *
- * Returns the index of the context page where the context was loaded.
- */
-static unsigned spacc_load_ctx(struct spacc_generic_ctx *ctx,
-			       const u8 *ciph_key, size_t ciph_len,
-			       const u8 *iv, size_t ivlen, const u8 *hash_key,
-			       size_t hash_len)
-{
-	unsigned indx = ctx->engine->next_ctx++;
-	void __iomem *ciph_page_addr, *hash_page_addr;
-
-	ciph_page_addr = spacc_ctx_page_addr(ctx, indx, 1);
-	hash_page_addr = spacc_ctx_page_addr(ctx, indx, 0);
-
-	ctx->engine->next_ctx &= ctx->engine->fifo_sz - 1;
-	spacc_cipher_write_ctx(ctx, ciph_page_addr, ciph_key, ciph_len, iv,
-			       ivlen);
-	writel(ciph_len | (indx << SPA_KEY_SZ_CTX_INDEX_OFFSET) |
-	       (1 << SPA_KEY_SZ_CIPHER_OFFSET),
-	       ctx->engine->regs + SPA_KEY_SZ_REG_OFFSET);
-
-	if (hash_key) {
-		memcpy_toio32(hash_page_addr, hash_key, hash_len / 4);
-		writel(hash_len | (indx << SPA_KEY_SZ_CTX_INDEX_OFFSET),
-		       ctx->engine->regs + SPA_KEY_SZ_REG_OFFSET);
-	}
-
-	return indx;
-}
-
-static inline void ddt_set(struct spacc_ddt *ddt, dma_addr_t phys, size_t len)
-{
-	ddt->p = phys;
-	ddt->len = len;
-}
-
-/*
- * Take a crypto request and scatterlists for the data and turn them into DDTs
- * for passing to the crypto engines. This also DMA maps the data so that the
- * crypto engines can DMA to/from them.
- */
-static struct spacc_ddt *spacc_sg_to_ddt(struct spacc_engine *engine,
-					 struct scatterlist *payload,
-					 unsigned nbytes,
-					 enum dma_data_direction dir,
-					 dma_addr_t *ddt_phys)
-{
-	unsigned mapped_ents;
-	struct scatterlist *cur;
-	struct spacc_ddt *ddt;
-	int i;
-	int nents;
-
-	nents = sg_nents_for_len(payload, nbytes);
-	if (nents < 0) {
-		dev_err(engine->dev, "Invalid numbers of SG.\n");
-		return NULL;
-	}
-	mapped_ents = dma_map_sg(engine->dev, payload, nents, dir);
-
-	if (mapped_ents + 1 > MAX_DDT_LEN)
-		goto out;
-
-	ddt = dma_pool_alloc(engine->req_pool, GFP_ATOMIC, ddt_phys);
-	if (!ddt)
-		goto out;
-
-	for_each_sg(payload, cur, mapped_ents, i)
-		ddt_set(&ddt[i], sg_dma_address(cur), sg_dma_len(cur));
-	ddt_set(&ddt[mapped_ents], 0, 0);
-
-	return ddt;
-
-out:
-	dma_unmap_sg(engine->dev, payload, nents, dir);
-	return NULL;
-}
-
-static int spacc_aead_make_ddts(struct aead_request *areq)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
-	struct spacc_req *req = aead_request_ctx(areq);
-	struct spacc_engine *engine = req->engine;
-	struct spacc_ddt *src_ddt, *dst_ddt;
-	unsigned total;
-	int src_nents, dst_nents;
-	struct scatterlist *cur;
-	int i, dst_ents, src_ents;
-
-	total = areq->assoclen + areq->cryptlen;
-	if (req->is_encrypt)
-		total += crypto_aead_authsize(aead);
-
-	src_nents = sg_nents_for_len(areq->src, total);
-	if (src_nents < 0) {
-		dev_err(engine->dev, "Invalid numbers of src SG.\n");
-		return src_nents;
-	}
-	if (src_nents + 1 > MAX_DDT_LEN)
-		return -E2BIG;
-
-	dst_nents = 0;
-	if (areq->src != areq->dst) {
-		dst_nents = sg_nents_for_len(areq->dst, total);
-		if (dst_nents < 0) {
-			dev_err(engine->dev, "Invalid numbers of dst SG.\n");
-			return dst_nents;
-		}
-		if (src_nents + 1 > MAX_DDT_LEN)
-			return -E2BIG;
-	}
-
-	src_ddt = dma_pool_alloc(engine->req_pool, GFP_ATOMIC, &req->src_addr);
-	if (!src_ddt)
-		goto err;
-
-	dst_ddt = dma_pool_alloc(engine->req_pool, GFP_ATOMIC, &req->dst_addr);
-	if (!dst_ddt)
-		goto err_free_src;
-
-	req->src_ddt = src_ddt;
-	req->dst_ddt = dst_ddt;
-
-	if (dst_nents) {
-		src_ents = dma_map_sg(engine->dev, areq->src, src_nents,
-				      DMA_TO_DEVICE);
-		if (!src_ents)
-			goto err_free_dst;
-
-		dst_ents = dma_map_sg(engine->dev, areq->dst, dst_nents,
-				      DMA_FROM_DEVICE);
-
-		if (!dst_ents) {
-			dma_unmap_sg(engine->dev, areq->src, src_nents,
-				     DMA_TO_DEVICE);
-			goto err_free_dst;
-		}
-	} else {
-		src_ents = dma_map_sg(engine->dev, areq->src, src_nents,
-				      DMA_BIDIRECTIONAL);
-		if (!src_ents)
-			goto err_free_dst;
-		dst_ents = src_ents;
-	}
-
-	/*
-	 * Now map in the payload for the source and destination and terminate
-	 * with the NULL pointers.
-	 */
-	for_each_sg(areq->src, cur, src_ents, i)
-		ddt_set(src_ddt++, sg_dma_address(cur), sg_dma_len(cur));
-
-	/* For decryption we need to skip the associated data. */
-	total = req->is_encrypt ? 0 : areq->assoclen;
-	for_each_sg(areq->dst, cur, dst_ents, i) {
-		unsigned len = sg_dma_len(cur);
-
-		if (len <= total) {
-			total -= len;
-			continue;
-		}
-
-		ddt_set(dst_ddt++, sg_dma_address(cur) + total, len - total);
-	}
-
-	ddt_set(src_ddt, 0, 0);
-	ddt_set(dst_ddt, 0, 0);
-
-	return 0;
-
-err_free_dst:
-	dma_pool_free(engine->req_pool, dst_ddt, req->dst_addr);
-err_free_src:
-	dma_pool_free(engine->req_pool, src_ddt, req->src_addr);
-err:
-	return -ENOMEM;
-}
-
-static void spacc_aead_free_ddts(struct spacc_req *req)
-{
-	struct aead_request *areq = container_of(req->req, struct aead_request,
-						 base);
-	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
-	unsigned total = areq->assoclen + areq->cryptlen +
-			 (req->is_encrypt ? crypto_aead_authsize(aead) : 0);
-	struct spacc_aead_ctx *aead_ctx = crypto_aead_ctx(aead);
-	struct spacc_engine *engine = aead_ctx->generic.engine;
-	int nents = sg_nents_for_len(areq->src, total);
-
-	/* sg_nents_for_len should not fail since it works when mapping sg */
-	if (unlikely(nents < 0)) {
-		dev_err(engine->dev, "Invalid numbers of src SG.\n");
-		return;
-	}
-
-	if (areq->src != areq->dst) {
-		dma_unmap_sg(engine->dev, areq->src, nents, DMA_TO_DEVICE);
-		nents = sg_nents_for_len(areq->dst, total);
-		if (unlikely(nents < 0)) {
-			dev_err(engine->dev, "Invalid numbers of dst SG.\n");
-			return;
-		}
-		dma_unmap_sg(engine->dev, areq->dst, nents, DMA_FROM_DEVICE);
-	} else
-		dma_unmap_sg(engine->dev, areq->src, nents, DMA_BIDIRECTIONAL);
-
-	dma_pool_free(engine->req_pool, req->src_ddt, req->src_addr);
-	dma_pool_free(engine->req_pool, req->dst_ddt, req->dst_addr);
-}
-
-static void spacc_free_ddt(struct spacc_req *req, struct spacc_ddt *ddt,
-			   dma_addr_t ddt_addr, struct scatterlist *payload,
-			   unsigned nbytes, enum dma_data_direction dir)
-{
-	int nents = sg_nents_for_len(payload, nbytes);
-
-	if (nents < 0) {
-		dev_err(req->engine->dev, "Invalid numbers of SG.\n");
-		return;
-	}
-
-	dma_unmap_sg(req->engine->dev, payload, nents, dir);
-	dma_pool_free(req->engine->req_pool, ddt, ddt_addr);
-}
-
-static int spacc_aead_setkey(struct crypto_aead *tfm, const u8 *key,
-			     unsigned int keylen)
-{
-	struct spacc_aead_ctx *ctx = crypto_aead_ctx(tfm);
-	struct crypto_authenc_keys keys;
-	int err;
-
-	crypto_aead_clear_flags(ctx->sw_cipher, CRYPTO_TFM_REQ_MASK);
-	crypto_aead_set_flags(ctx->sw_cipher, crypto_aead_get_flags(tfm) &
-					      CRYPTO_TFM_REQ_MASK);
-	err = crypto_aead_setkey(ctx->sw_cipher, key, keylen);
-	if (err)
-		return err;
-
-	if (crypto_authenc_extractkeys(&keys, key, keylen) != 0)
-		goto badkey;
-
-	if (keys.enckeylen > AES_MAX_KEY_SIZE)
-		goto badkey;
-
-	if (keys.authkeylen > sizeof(ctx->hash_ctx))
-		goto badkey;
-
-	memcpy(ctx->cipher_key, keys.enckey, keys.enckeylen);
-	ctx->cipher_key_len = keys.enckeylen;
-
-	memcpy(ctx->hash_ctx, keys.authkey, keys.authkeylen);
-	ctx->hash_key_len = keys.authkeylen;
-
-	memzero_explicit(&keys, sizeof(keys));
-	return 0;
-
-badkey:
-	memzero_explicit(&keys, sizeof(keys));
-	return -EINVAL;
-}
-
-static int spacc_aead_setauthsize(struct crypto_aead *tfm,
-				  unsigned int authsize)
-{
-	struct spacc_aead_ctx *ctx = crypto_tfm_ctx(crypto_aead_tfm(tfm));
-
-	return crypto_aead_setauthsize(ctx->sw_cipher, authsize);
-}
-
-/*
- * Check if an AEAD request requires a fallback operation. Some requests can't
- * be completed in hardware because the hardware may not support certain key
- * sizes. In these cases we need to complete the request in software.
- */
-static int spacc_aead_need_fallback(struct aead_request *aead_req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(aead_req);
-	struct aead_alg *alg = crypto_aead_alg(aead);
-	struct spacc_aead *spacc_alg = to_spacc_aead(alg);
-	struct spacc_aead_ctx *ctx = crypto_aead_ctx(aead);
-
-	/*
-	 * If we have a non-supported key-length, then we need to do a
-	 * software fallback.
-	 */
-	if ((spacc_alg->ctrl_default & SPACC_CRYPTO_ALG_MASK) ==
-	    SPA_CTRL_CIPH_ALG_AES &&
-	    ctx->cipher_key_len != AES_KEYSIZE_128 &&
-	    ctx->cipher_key_len != AES_KEYSIZE_256)
-		return 1;
-
-	return 0;
-}
-
-static int spacc_aead_do_fallback(struct aead_request *req, unsigned alg_type,
-				  bool is_encrypt)
-{
-	struct crypto_tfm *old_tfm = crypto_aead_tfm(crypto_aead_reqtfm(req));
-	struct spacc_aead_ctx *ctx = crypto_tfm_ctx(old_tfm);
-	struct aead_request *subreq = aead_request_ctx(req);
-
-	aead_request_set_tfm(subreq, ctx->sw_cipher);
-	aead_request_set_callback(subreq, req->base.flags,
-				  req->base.complete, req->base.data);
-	aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
-			       req->iv);
-	aead_request_set_ad(subreq, req->assoclen);
-
-	return is_encrypt ? crypto_aead_encrypt(subreq) :
-			    crypto_aead_decrypt(subreq);
-}
-
-static void spacc_aead_complete(struct spacc_req *req)
-{
-	spacc_aead_free_ddts(req);
-	req->req->complete(req->req, req->result);
-}
-
-static int spacc_aead_submit(struct spacc_req *req)
-{
-	struct aead_request *aead_req =
-		container_of(req->req, struct aead_request, base);
-	struct crypto_aead *aead = crypto_aead_reqtfm(aead_req);
-	unsigned int authsize = crypto_aead_authsize(aead);
-	struct spacc_aead_ctx *ctx = crypto_aead_ctx(aead);
-	struct aead_alg *alg = crypto_aead_alg(aead);
-	struct spacc_aead *spacc_alg = to_spacc_aead(alg);
-	struct spacc_engine *engine = ctx->generic.engine;
-	u32 ctrl, proc_len, assoc_len;
-
-	req->result = -EINPROGRESS;
-	req->ctx_id = spacc_load_ctx(&ctx->generic, ctx->cipher_key,
-		ctx->cipher_key_len, aead_req->iv, crypto_aead_ivsize(aead),
-		ctx->hash_ctx, ctx->hash_key_len);
-
-	/* Set the source and destination DDT pointers. */
-	writel(req->src_addr, engine->regs + SPA_SRC_PTR_REG_OFFSET);
-	writel(req->dst_addr, engine->regs + SPA_DST_PTR_REG_OFFSET);
-	writel(0, engine->regs + SPA_OFFSET_REG_OFFSET);
-
-	assoc_len = aead_req->assoclen;
-	proc_len = aead_req->cryptlen + assoc_len;
-
-	/*
-	 * If we are decrypting, we need to take the length of the ICV out of
-	 * the processing length.
-	 */
-	if (!req->is_encrypt)
-		proc_len -= authsize;
-
-	writel(proc_len, engine->regs + SPA_PROC_LEN_REG_OFFSET);
-	writel(assoc_len, engine->regs + SPA_AAD_LEN_REG_OFFSET);
-	writel(authsize, engine->regs + SPA_ICV_LEN_REG_OFFSET);
-	writel(0, engine->regs + SPA_ICV_OFFSET_REG_OFFSET);
-	writel(0, engine->regs + SPA_AUX_INFO_REG_OFFSET);
-
-	ctrl = spacc_alg->ctrl_default | (req->ctx_id << SPA_CTRL_CTX_IDX) |
-		(1 << SPA_CTRL_ICV_APPEND);
-	if (req->is_encrypt)
-		ctrl |= (1 << SPA_CTRL_ENCRYPT_IDX) | (1 << SPA_CTRL_AAD_COPY);
-	else
-		ctrl |= (1 << SPA_CTRL_KEY_EXP);
-
-	mod_timer(&engine->packet_timeout, jiffies + PACKET_TIMEOUT);
-
-	writel(ctrl, engine->regs + SPA_CTRL_REG_OFFSET);
-
-	return -EINPROGRESS;
-}
-
-static int spacc_req_submit(struct spacc_req *req);
-
-static void spacc_push(struct spacc_engine *engine)
-{
-	struct spacc_req *req;
-
-	while (!list_empty(&engine->pending) &&
-	       engine->in_flight + 1 <= engine->fifo_sz) {
-
-		++engine->in_flight;
-		req = list_first_entry(&engine->pending, struct spacc_req,
-				       list);
-		list_move_tail(&req->list, &engine->in_progress);
-
-		req->result = spacc_req_submit(req);
-	}
-}
-
-/*
- * Setup an AEAD request for processing. This will configure the engine, load
- * the context and then start the packet processing.
- */
-static int spacc_aead_setup(struct aead_request *req,
-			    unsigned alg_type, bool is_encrypt)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct aead_alg *alg = crypto_aead_alg(aead);
-	struct spacc_engine *engine = to_spacc_aead(alg)->engine;
-	struct spacc_req *dev_req = aead_request_ctx(req);
-	int err;
-	unsigned long flags;
-
-	dev_req->req		= &req->base;
-	dev_req->is_encrypt	= is_encrypt;
-	dev_req->result		= -EBUSY;
-	dev_req->engine		= engine;
-	dev_req->complete	= spacc_aead_complete;
-
-	if (unlikely(spacc_aead_need_fallback(req) ||
-		     ((err = spacc_aead_make_ddts(req)) == -E2BIG)))
-		return spacc_aead_do_fallback(req, alg_type, is_encrypt);
-
-	if (err)
-		goto out;
-
-	err = -EINPROGRESS;
-	spin_lock_irqsave(&engine->hw_lock, flags);
-	if (unlikely(spacc_fifo_cmd_full(engine)) ||
-	    engine->in_flight + 1 > engine->fifo_sz) {
-		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) {
-			err = -EBUSY;
-			spin_unlock_irqrestore(&engine->hw_lock, flags);
-			goto out_free_ddts;
-		}
-		list_add_tail(&dev_req->list, &engine->pending);
-	} else {
-		list_add_tail(&dev_req->list, &engine->pending);
-		spacc_push(engine);
-	}
-	spin_unlock_irqrestore(&engine->hw_lock, flags);
-
-	goto out;
-
-out_free_ddts:
-	spacc_aead_free_ddts(dev_req);
-out:
-	return err;
-}
-
-static int spacc_aead_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct spacc_aead *alg = to_spacc_aead(crypto_aead_alg(aead));
-
-	return spacc_aead_setup(req, alg->type, 1);
-}
-
-static int spacc_aead_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct spacc_aead  *alg = to_spacc_aead(crypto_aead_alg(aead));
-
-	return spacc_aead_setup(req, alg->type, 0);
-}
-
-/*
- * Initialise a new AEAD context. This is responsible for allocating the
- * fallback cipher and initialising the context.
- */
-static int spacc_aead_cra_init(struct crypto_aead *tfm)
-{
-	struct spacc_aead_ctx *ctx = crypto_aead_ctx(tfm);
-	struct aead_alg *alg = crypto_aead_alg(tfm);
-	struct spacc_aead *spacc_alg = to_spacc_aead(alg);
-	struct spacc_engine *engine = spacc_alg->engine;
-
-	ctx->generic.flags = spacc_alg->type;
-	ctx->generic.engine = engine;
-	ctx->sw_cipher = crypto_alloc_aead(alg->base.cra_name, 0,
-					   CRYPTO_ALG_NEED_FALLBACK);
-	if (IS_ERR(ctx->sw_cipher))
-		return PTR_ERR(ctx->sw_cipher);
-	ctx->generic.key_offs = spacc_alg->key_offs;
-	ctx->generic.iv_offs = spacc_alg->iv_offs;
-
-	crypto_aead_set_reqsize(
-		tfm,
-		max(sizeof(struct spacc_req),
-		    sizeof(struct aead_request) +
-		    crypto_aead_reqsize(ctx->sw_cipher)));
-
-	return 0;
-}
-
-/*
- * Destructor for an AEAD context. This is called when the transform is freed
- * and must free the fallback cipher.
- */
-static void spacc_aead_cra_exit(struct crypto_aead *tfm)
-{
-	struct spacc_aead_ctx *ctx = crypto_aead_ctx(tfm);
-
-	crypto_free_aead(ctx->sw_cipher);
-}
-
-/*
- * Set the DES key for a block cipher transform. This also performs weak key
- * checking if the transform has requested it.
- */
-static int spacc_des_setkey(struct crypto_skcipher *cipher, const u8 *key,
-			    unsigned int len)
-{
-	struct spacc_ablk_ctx *ctx = crypto_skcipher_ctx(cipher);
-	int err;
-
-	err = verify_skcipher_des_key(cipher, key);
-	if (err)
-		return err;
-
-	memcpy(ctx->key, key, len);
-	ctx->key_len = len;
-
-	return 0;
-}
-
-/*
- * Set the 3DES key for a block cipher transform. This also performs weak key
- * checking if the transform has requested it.
- */
-static int spacc_des3_setkey(struct crypto_skcipher *cipher, const u8 *key,
-			     unsigned int len)
-{
-	struct spacc_ablk_ctx *ctx = crypto_skcipher_ctx(cipher);
-	int err;
-
-	err = verify_skcipher_des3_key(cipher, key);
-	if (err)
-		return err;
-
-	memcpy(ctx->key, key, len);
-	ctx->key_len = len;
-
-	return 0;
-}
-
-/*
- * Set the key for an AES block cipher. Some key lengths are not supported in
- * hardware so this must also check whether a fallback is needed.
- */
-static int spacc_aes_setkey(struct crypto_skcipher *cipher, const u8 *key,
-			    unsigned int len)
-{
-	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
-	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err = 0;
-
-	if (len > AES_MAX_KEY_SIZE)
-		return -EINVAL;
-
-	/*
-	 * IPSec engine only supports 128 and 256 bit AES keys. If we get a
-	 * request for any other size (192 bits) then we need to do a software
-	 * fallback.
-	 */
-	if (len != AES_KEYSIZE_128 && len != AES_KEYSIZE_256) {
-		if (!ctx->sw_cipher)
-			return -EINVAL;
-
-		/*
-		 * Set the fallback transform to use the same request flags as
-		 * the hardware transform.
-		 */
-		crypto_skcipher_clear_flags(ctx->sw_cipher,
-					    CRYPTO_TFM_REQ_MASK);
-		crypto_skcipher_set_flags(ctx->sw_cipher,
-					  cipher->base.crt_flags &
-					  CRYPTO_TFM_REQ_MASK);
-
-		err = crypto_skcipher_setkey(ctx->sw_cipher, key, len);
-		if (err)
-			goto sw_setkey_failed;
-	}
-
-	memcpy(ctx->key, key, len);
-	ctx->key_len = len;
-
-sw_setkey_failed:
-	return err;
-}
-
-static int spacc_kasumi_f8_setkey(struct crypto_skcipher *cipher,
-				  const u8 *key, unsigned int len)
-{
-	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
-	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err = 0;
-
-	if (len > AES_MAX_KEY_SIZE) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	memcpy(ctx->key, key, len);
-	ctx->key_len = len;
-
-out:
-	return err;
-}
-
-static int spacc_ablk_need_fallback(struct spacc_req *req)
-{
-	struct skcipher_request *ablk_req = skcipher_request_cast(req->req);
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(ablk_req);
-	struct spacc_alg *spacc_alg = to_spacc_skcipher(crypto_skcipher_alg(tfm));
-	struct spacc_ablk_ctx *ctx;
-
-	ctx = crypto_skcipher_ctx(tfm);
-
-	return (spacc_alg->ctrl_default & SPACC_CRYPTO_ALG_MASK) ==
-			SPA_CTRL_CIPH_ALG_AES &&
-			ctx->key_len != AES_KEYSIZE_128 &&
-			ctx->key_len != AES_KEYSIZE_256;
-}
-
-static void spacc_ablk_complete(struct spacc_req *req)
-{
-	struct skcipher_request *ablk_req = skcipher_request_cast(req->req);
-
-	if (ablk_req->src != ablk_req->dst) {
-		spacc_free_ddt(req, req->src_ddt, req->src_addr, ablk_req->src,
-			       ablk_req->cryptlen, DMA_TO_DEVICE);
-		spacc_free_ddt(req, req->dst_ddt, req->dst_addr, ablk_req->dst,
-			       ablk_req->cryptlen, DMA_FROM_DEVICE);
-	} else
-		spacc_free_ddt(req, req->dst_ddt, req->dst_addr, ablk_req->dst,
-			       ablk_req->cryptlen, DMA_BIDIRECTIONAL);
-
-	req->req->complete(req->req, req->result);
-}
-
-static int spacc_ablk_submit(struct spacc_req *req)
-{
-	struct skcipher_request *ablk_req = skcipher_request_cast(req->req);
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(ablk_req);
-	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
-	struct spacc_alg *spacc_alg = to_spacc_skcipher(alg);
-	struct spacc_ablk_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct spacc_engine *engine = ctx->generic.engine;
-	u32 ctrl;
-
-	req->ctx_id = spacc_load_ctx(&ctx->generic, ctx->key,
-		ctx->key_len, ablk_req->iv, alg->ivsize,
-		NULL, 0);
-
-	writel(req->src_addr, engine->regs + SPA_SRC_PTR_REG_OFFSET);
-	writel(req->dst_addr, engine->regs + SPA_DST_PTR_REG_OFFSET);
-	writel(0, engine->regs + SPA_OFFSET_REG_OFFSET);
-
-	writel(ablk_req->cryptlen, engine->regs + SPA_PROC_LEN_REG_OFFSET);
-	writel(0, engine->regs + SPA_ICV_OFFSET_REG_OFFSET);
-	writel(0, engine->regs + SPA_AUX_INFO_REG_OFFSET);
-	writel(0, engine->regs + SPA_AAD_LEN_REG_OFFSET);
-
-	ctrl = spacc_alg->ctrl_default | (req->ctx_id << SPA_CTRL_CTX_IDX) |
-		(req->is_encrypt ? (1 << SPA_CTRL_ENCRYPT_IDX) :
-		 (1 << SPA_CTRL_KEY_EXP));
-
-	mod_timer(&engine->packet_timeout, jiffies + PACKET_TIMEOUT);
-
-	writel(ctrl, engine->regs + SPA_CTRL_REG_OFFSET);
-
-	return -EINPROGRESS;
-}
-
-static int spacc_ablk_do_fallback(struct skcipher_request *req,
-				  unsigned alg_type, bool is_encrypt)
-{
-	struct crypto_tfm *old_tfm =
-	    crypto_skcipher_tfm(crypto_skcipher_reqtfm(req));
-	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(old_tfm);
-	struct spacc_req *dev_req = skcipher_request_ctx(req);
-	int err;
-
-	/*
-	 * Change the request to use the software fallback transform, and once
-	 * the ciphering has completed, put the old transform back into the
-	 * request.
-	 */
-	skcipher_request_set_tfm(&dev_req->fallback_req, ctx->sw_cipher);
-	skcipher_request_set_callback(&dev_req->fallback_req, req->base.flags,
-				      req->base.complete, req->base.data);
-	skcipher_request_set_crypt(&dev_req->fallback_req, req->src, req->dst,
-				   req->cryptlen, req->iv);
-	err = is_encrypt ? crypto_skcipher_encrypt(&dev_req->fallback_req) :
-			   crypto_skcipher_decrypt(&dev_req->fallback_req);
-
-	return err;
-}
-
-static int spacc_ablk_setup(struct skcipher_request *req, unsigned alg_type,
-			    bool is_encrypt)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
-	struct spacc_engine *engine = to_spacc_skcipher(alg)->engine;
-	struct spacc_req *dev_req = skcipher_request_ctx(req);
-	unsigned long flags;
-	int err = -ENOMEM;
-
-	dev_req->req		= &req->base;
-	dev_req->is_encrypt	= is_encrypt;
-	dev_req->engine		= engine;
-	dev_req->complete	= spacc_ablk_complete;
-	dev_req->result		= -EINPROGRESS;
-
-	if (unlikely(spacc_ablk_need_fallback(dev_req)))
-		return spacc_ablk_do_fallback(req, alg_type, is_encrypt);
-
-	/*
-	 * Create the DDT's for the engine. If we share the same source and
-	 * destination then we can optimize by reusing the DDT's.
-	 */
-	if (req->src != req->dst) {
-		dev_req->src_ddt = spacc_sg_to_ddt(engine, req->src,
-			req->cryptlen, DMA_TO_DEVICE, &dev_req->src_addr);
-		if (!dev_req->src_ddt)
-			goto out;
-
-		dev_req->dst_ddt = spacc_sg_to_ddt(engine, req->dst,
-			req->cryptlen, DMA_FROM_DEVICE, &dev_req->dst_addr);
-		if (!dev_req->dst_ddt)
-			goto out_free_src;
-	} else {
-		dev_req->dst_ddt = spacc_sg_to_ddt(engine, req->dst,
-			req->cryptlen, DMA_BIDIRECTIONAL, &dev_req->dst_addr);
-		if (!dev_req->dst_ddt)
-			goto out;
-
-		dev_req->src_ddt = NULL;
-		dev_req->src_addr = dev_req->dst_addr;
-	}
-
-	err = -EINPROGRESS;
-	spin_lock_irqsave(&engine->hw_lock, flags);
-	/*
-	 * Check if the engine will accept the operation now. If it won't then
-	 * we either stick it on the end of a pending list if we can backlog,
-	 * or bailout with an error if not.
-	 */
-	if (unlikely(spacc_fifo_cmd_full(engine)) ||
-	    engine->in_flight + 1 > engine->fifo_sz) {
-		if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) {
-			err = -EBUSY;
-			spin_unlock_irqrestore(&engine->hw_lock, flags);
-			goto out_free_ddts;
-		}
-		list_add_tail(&dev_req->list, &engine->pending);
-	} else {
-		list_add_tail(&dev_req->list, &engine->pending);
-		spacc_push(engine);
-	}
-	spin_unlock_irqrestore(&engine->hw_lock, flags);
-
-	goto out;
-
-out_free_ddts:
-	spacc_free_ddt(dev_req, dev_req->dst_ddt, dev_req->dst_addr, req->dst,
-		       req->cryptlen, req->src == req->dst ?
-		       DMA_BIDIRECTIONAL : DMA_FROM_DEVICE);
-out_free_src:
-	if (req->src != req->dst)
-		spacc_free_ddt(dev_req, dev_req->src_ddt, dev_req->src_addr,
-			       req->src, req->cryptlen, DMA_TO_DEVICE);
-out:
-	return err;
-}
-
-static int spacc_ablk_init_tfm(struct crypto_skcipher *tfm)
-{
-	struct spacc_ablk_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
-	struct spacc_alg *spacc_alg = to_spacc_skcipher(alg);
-	struct spacc_engine *engine = spacc_alg->engine;
-
-	ctx->generic.flags = spacc_alg->type;
-	ctx->generic.engine = engine;
-	if (alg->base.cra_flags & CRYPTO_ALG_NEED_FALLBACK) {
-		ctx->sw_cipher = crypto_alloc_skcipher(alg->base.cra_name, 0,
-						       CRYPTO_ALG_NEED_FALLBACK);
-		if (IS_ERR(ctx->sw_cipher)) {
-			dev_warn(engine->dev, "failed to allocate fallback for %s\n",
-				 alg->base.cra_name);
-			return PTR_ERR(ctx->sw_cipher);
-		}
-		crypto_skcipher_set_reqsize(tfm, sizeof(struct spacc_req) +
-						 crypto_skcipher_reqsize(ctx->sw_cipher));
-	} else {
-		/* take the size without the fallback skcipher_request at the end */
-		crypto_skcipher_set_reqsize(tfm, offsetof(struct spacc_req,
-							  fallback_req));
-	}
-
-	ctx->generic.key_offs = spacc_alg->key_offs;
-	ctx->generic.iv_offs = spacc_alg->iv_offs;
-
-	return 0;
-}
-
-static void spacc_ablk_exit_tfm(struct crypto_skcipher *tfm)
-{
-	struct spacc_ablk_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	crypto_free_skcipher(ctx->sw_cipher);
-}
-
-static int spacc_ablk_encrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req);
-	struct skcipher_alg *alg = crypto_skcipher_alg(cipher);
-	struct spacc_alg *spacc_alg = to_spacc_skcipher(alg);
-
-	return spacc_ablk_setup(req, spacc_alg->type, 1);
-}
-
-static int spacc_ablk_decrypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req);
-	struct skcipher_alg *alg = crypto_skcipher_alg(cipher);
-	struct spacc_alg *spacc_alg = to_spacc_skcipher(alg);
-
-	return spacc_ablk_setup(req, spacc_alg->type, 0);
-}
-
-static inline int spacc_fifo_stat_empty(struct spacc_engine *engine)
-{
-	return readl(engine->regs + SPA_FIFO_STAT_REG_OFFSET) &
-		SPA_FIFO_STAT_EMPTY;
-}
-
-static void spacc_process_done(struct spacc_engine *engine)
-{
-	struct spacc_req *req;
-	unsigned long flags;
-
-	spin_lock_irqsave(&engine->hw_lock, flags);
-
-	while (!spacc_fifo_stat_empty(engine)) {
-		req = list_first_entry(&engine->in_progress, struct spacc_req,
-				       list);
-		list_move_tail(&req->list, &engine->completed);
-		--engine->in_flight;
-
-		/* POP the status register. */
-		writel(~0, engine->regs + SPA_STAT_POP_REG_OFFSET);
-		req->result = (readl(engine->regs + SPA_STATUS_REG_OFFSET) &
-		     SPA_STATUS_RES_CODE_MASK) >> SPA_STATUS_RES_CODE_OFFSET;
-
-		/*
-		 * Convert the SPAcc error status into the standard POSIX error
-		 * codes.
-		 */
-		if (unlikely(req->result)) {
-			switch (req->result) {
-			case SPA_STATUS_ICV_FAIL:
-				req->result = -EBADMSG;
-				break;
-
-			case SPA_STATUS_MEMORY_ERROR:
-				dev_warn(engine->dev,
-					 "memory error triggered\n");
-				req->result = -EFAULT;
-				break;
-
-			case SPA_STATUS_BLOCK_ERROR:
-				dev_warn(engine->dev,
-					 "block error triggered\n");
-				req->result = -EIO;
-				break;
-			}
-		}
-	}
-
-	tasklet_schedule(&engine->complete);
-
-	spin_unlock_irqrestore(&engine->hw_lock, flags);
-}
-
-static irqreturn_t spacc_spacc_irq(int irq, void *dev)
-{
-	struct spacc_engine *engine = (struct spacc_engine *)dev;
-	u32 spacc_irq_stat = readl(engine->regs + SPA_IRQ_STAT_REG_OFFSET);
-
-	writel(spacc_irq_stat, engine->regs + SPA_IRQ_STAT_REG_OFFSET);
-	spacc_process_done(engine);
-
-	return IRQ_HANDLED;
-}
-
-static void spacc_packet_timeout(struct timer_list *t)
-{
-	struct spacc_engine *engine = from_timer(engine, t, packet_timeout);
-
-	spacc_process_done(engine);
-}
-
-static int spacc_req_submit(struct spacc_req *req)
-{
-	struct crypto_alg *alg = req->req->tfm->__crt_alg;
-
-	if (CRYPTO_ALG_TYPE_AEAD == (CRYPTO_ALG_TYPE_MASK & alg->cra_flags))
-		return spacc_aead_submit(req);
-	else
-		return spacc_ablk_submit(req);
-}
-
-static void spacc_spacc_complete(unsigned long data)
-{
-	struct spacc_engine *engine = (struct spacc_engine *)data;
-	struct spacc_req *req, *tmp;
-	unsigned long flags;
-	LIST_HEAD(completed);
-
-	spin_lock_irqsave(&engine->hw_lock, flags);
-
-	list_splice_init(&engine->completed, &completed);
-	spacc_push(engine);
-	if (engine->in_flight)
-		mod_timer(&engine->packet_timeout, jiffies + PACKET_TIMEOUT);
-
-	spin_unlock_irqrestore(&engine->hw_lock, flags);
-
-	list_for_each_entry_safe(req, tmp, &completed, list) {
-		list_del(&req->list);
-		req->complete(req);
-	}
-}
-
-#ifdef CONFIG_PM
-static int spacc_suspend(struct device *dev)
-{
-	struct spacc_engine *engine = dev_get_drvdata(dev);
-
-	/*
-	 * We only support standby mode. All we have to do is gate the clock to
-	 * the spacc. The hardware will preserve state until we turn it back
-	 * on again.
-	 */
-	clk_disable(engine->clk);
-
-	return 0;
-}
-
-static int spacc_resume(struct device *dev)
-{
-	struct spacc_engine *engine = dev_get_drvdata(dev);
-
-	return clk_enable(engine->clk);
-}
-
-static const struct dev_pm_ops spacc_pm_ops = {
-	.suspend	= spacc_suspend,
-	.resume		= spacc_resume,
-};
-#endif /* CONFIG_PM */
-
-static inline struct spacc_engine *spacc_dev_to_engine(struct device *dev)
-{
-	return dev ? dev_get_drvdata(dev) : NULL;
-}
-
-static ssize_t spacc_stat_irq_thresh_show(struct device *dev,
-					  struct device_attribute *attr,
-					  char *buf)
-{
-	struct spacc_engine *engine = spacc_dev_to_engine(dev);
-
-	return snprintf(buf, PAGE_SIZE, "%u\n", engine->stat_irq_thresh);
-}
-
-static ssize_t spacc_stat_irq_thresh_store(struct device *dev,
-					   struct device_attribute *attr,
-					   const char *buf, size_t len)
-{
-	struct spacc_engine *engine = spacc_dev_to_engine(dev);
-	unsigned long thresh;
-
-	if (kstrtoul(buf, 0, &thresh))
-		return -EINVAL;
-
-	thresh = clamp(thresh, 1UL, engine->fifo_sz - 1);
-
-	engine->stat_irq_thresh = thresh;
-	writel(engine->stat_irq_thresh << SPA_IRQ_CTRL_STAT_CNT_OFFSET,
-	       engine->regs + SPA_IRQ_CTRL_REG_OFFSET);
-
-	return len;
-}
-static DEVICE_ATTR(stat_irq_thresh, 0644, spacc_stat_irq_thresh_show,
-		   spacc_stat_irq_thresh_store);
-
-static struct spacc_alg ipsec_engine_algs[] = {
-	{
-		.ctrl_default = SPA_CTRL_CIPH_ALG_AES | SPA_CTRL_CIPH_MODE_CBC,
-		.key_offs = 0,
-		.iv_offs = AES_MAX_KEY_SIZE,
-		.alg = {
-			.base.cra_name		= "cbc(aes)",
-			.base.cra_driver_name	= "cbc-aes-picoxcell",
-			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
-			.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
-						  CRYPTO_ALG_ASYNC |
-						  CRYPTO_ALG_ALLOCATES_MEMORY |
-						  CRYPTO_ALG_NEED_FALLBACK,
-			.base.cra_blocksize	= AES_BLOCK_SIZE,
-			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
-			.base.cra_module	= THIS_MODULE,
-
-			.setkey			= spacc_aes_setkey,
-			.encrypt 		= spacc_ablk_encrypt,
-			.decrypt 		= spacc_ablk_decrypt,
-			.min_keysize 		= AES_MIN_KEY_SIZE,
-			.max_keysize 		= AES_MAX_KEY_SIZE,
-			.ivsize			= AES_BLOCK_SIZE,
-			.init			= spacc_ablk_init_tfm,
-			.exit			= spacc_ablk_exit_tfm,
-		},
-	},
-	{
-		.key_offs = 0,
-		.iv_offs = AES_MAX_KEY_SIZE,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_AES | SPA_CTRL_CIPH_MODE_ECB,
-		.alg = {
-			.base.cra_name		= "ecb(aes)",
-			.base.cra_driver_name	= "ecb-aes-picoxcell",
-			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
-			.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
-						  CRYPTO_ALG_ASYNC |
-						  CRYPTO_ALG_ALLOCATES_MEMORY |
-						  CRYPTO_ALG_NEED_FALLBACK,
-			.base.cra_blocksize	= AES_BLOCK_SIZE,
-			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
-			.base.cra_module	= THIS_MODULE,
-
-			.setkey			= spacc_aes_setkey,
-			.encrypt 		= spacc_ablk_encrypt,
-			.decrypt 		= spacc_ablk_decrypt,
-			.min_keysize 		= AES_MIN_KEY_SIZE,
-			.max_keysize 		= AES_MAX_KEY_SIZE,
-			.init			= spacc_ablk_init_tfm,
-			.exit			= spacc_ablk_exit_tfm,
-		},
-	},
-	{
-		.key_offs = DES_BLOCK_SIZE,
-		.iv_offs = 0,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_DES | SPA_CTRL_CIPH_MODE_CBC,
-		.alg = {
-			.base.cra_name		= "cbc(des)",
-			.base.cra_driver_name	= "cbc-des-picoxcell",
-			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
-			.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
-						  CRYPTO_ALG_ASYNC |
-						  CRYPTO_ALG_ALLOCATES_MEMORY,
-			.base.cra_blocksize	= DES_BLOCK_SIZE,
-			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
-			.base.cra_module	= THIS_MODULE,
-
-			.setkey			= spacc_des_setkey,
-			.encrypt		= spacc_ablk_encrypt,
-			.decrypt		= spacc_ablk_decrypt,
-			.min_keysize		= DES_KEY_SIZE,
-			.max_keysize		= DES_KEY_SIZE,
-			.ivsize			= DES_BLOCK_SIZE,
-			.init			= spacc_ablk_init_tfm,
-			.exit			= spacc_ablk_exit_tfm,
-		},
-	},
-	{
-		.key_offs = DES_BLOCK_SIZE,
-		.iv_offs = 0,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_DES | SPA_CTRL_CIPH_MODE_ECB,
-		.alg = {
-			.base.cra_name		= "ecb(des)",
-			.base.cra_driver_name	= "ecb-des-picoxcell",
-			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
-			.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
-						  CRYPTO_ALG_ASYNC |
-						  CRYPTO_ALG_ALLOCATES_MEMORY,
-			.base.cra_blocksize	= DES_BLOCK_SIZE,
-			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
-			.base.cra_module	= THIS_MODULE,
-
-			.setkey			= spacc_des_setkey,
-			.encrypt		= spacc_ablk_encrypt,
-			.decrypt		= spacc_ablk_decrypt,
-			.min_keysize		= DES_KEY_SIZE,
-			.max_keysize		= DES_KEY_SIZE,
-			.init			= spacc_ablk_init_tfm,
-			.exit			= spacc_ablk_exit_tfm,
-		},
-	},
-	{
-		.key_offs = DES_BLOCK_SIZE,
-		.iv_offs = 0,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_DES | SPA_CTRL_CIPH_MODE_CBC,
-		.alg = {
-			.base.cra_name		= "cbc(des3_ede)",
-			.base.cra_driver_name	= "cbc-des3-ede-picoxcell",
-			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
-			.base.cra_flags		= CRYPTO_ALG_ASYNC |
-						  CRYPTO_ALG_ALLOCATES_MEMORY |
-						  CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
-			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
-			.base.cra_module	= THIS_MODULE,
-
-			.setkey			= spacc_des3_setkey,
-			.encrypt		= spacc_ablk_encrypt,
-			.decrypt		= spacc_ablk_decrypt,
-			.min_keysize		= DES3_EDE_KEY_SIZE,
-			.max_keysize		= DES3_EDE_KEY_SIZE,
-			.ivsize			= DES3_EDE_BLOCK_SIZE,
-			.init			= spacc_ablk_init_tfm,
-			.exit			= spacc_ablk_exit_tfm,
-		},
-	},
-	{
-		.key_offs = DES_BLOCK_SIZE,
-		.iv_offs = 0,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_DES | SPA_CTRL_CIPH_MODE_ECB,
-		.alg = {
-			.base.cra_name		= "ecb(des3_ede)",
-			.base.cra_driver_name	= "ecb-des3-ede-picoxcell",
-			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
-			.base.cra_flags		= CRYPTO_ALG_ASYNC |
-						  CRYPTO_ALG_ALLOCATES_MEMORY |
-						  CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.base.cra_blocksize	= DES3_EDE_BLOCK_SIZE,
-			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
-			.base.cra_module	= THIS_MODULE,
-
-			.setkey			= spacc_des3_setkey,
-			.encrypt		= spacc_ablk_encrypt,
-			.decrypt		= spacc_ablk_decrypt,
-			.min_keysize		= DES3_EDE_KEY_SIZE,
-			.max_keysize		= DES3_EDE_KEY_SIZE,
-			.init			= spacc_ablk_init_tfm,
-			.exit			= spacc_ablk_exit_tfm,
-		},
-	},
-};
-
-static struct spacc_aead ipsec_engine_aeads[] = {
-	{
-		.ctrl_default = SPA_CTRL_CIPH_ALG_AES |
-				SPA_CTRL_CIPH_MODE_CBC |
-				SPA_CTRL_HASH_ALG_SHA |
-				SPA_CTRL_HASH_MODE_HMAC,
-		.key_offs = 0,
-		.iv_offs = AES_MAX_KEY_SIZE,
-		.alg = {
-			.base = {
-				.cra_name = "authenc(hmac(sha1),cbc(aes))",
-				.cra_driver_name = "authenc-hmac-sha1-"
-						   "cbc-aes-picoxcell",
-				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-				.cra_flags = CRYPTO_ALG_ASYNC |
-					     CRYPTO_ALG_ALLOCATES_MEMORY |
-					     CRYPTO_ALG_NEED_FALLBACK |
-					     CRYPTO_ALG_KERN_DRIVER_ONLY,
-				.cra_blocksize = AES_BLOCK_SIZE,
-				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-				.cra_module = THIS_MODULE,
-			},
-			.setkey = spacc_aead_setkey,
-			.setauthsize = spacc_aead_setauthsize,
-			.encrypt = spacc_aead_encrypt,
-			.decrypt = spacc_aead_decrypt,
-			.ivsize = AES_BLOCK_SIZE,
-			.maxauthsize = SHA1_DIGEST_SIZE,
-			.init = spacc_aead_cra_init,
-			.exit = spacc_aead_cra_exit,
-		},
-	},
-	{
-		.ctrl_default = SPA_CTRL_CIPH_ALG_AES |
-				SPA_CTRL_CIPH_MODE_CBC |
-				SPA_CTRL_HASH_ALG_SHA256 |
-				SPA_CTRL_HASH_MODE_HMAC,
-		.key_offs = 0,
-		.iv_offs = AES_MAX_KEY_SIZE,
-		.alg = {
-			.base = {
-				.cra_name = "authenc(hmac(sha256),cbc(aes))",
-				.cra_driver_name = "authenc-hmac-sha256-"
-						   "cbc-aes-picoxcell",
-				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-				.cra_flags = CRYPTO_ALG_ASYNC |
-					     CRYPTO_ALG_ALLOCATES_MEMORY |
-					     CRYPTO_ALG_NEED_FALLBACK |
-					     CRYPTO_ALG_KERN_DRIVER_ONLY,
-				.cra_blocksize = AES_BLOCK_SIZE,
-				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-				.cra_module = THIS_MODULE,
-			},
-			.setkey = spacc_aead_setkey,
-			.setauthsize = spacc_aead_setauthsize,
-			.encrypt = spacc_aead_encrypt,
-			.decrypt = spacc_aead_decrypt,
-			.ivsize = AES_BLOCK_SIZE,
-			.maxauthsize = SHA256_DIGEST_SIZE,
-			.init = spacc_aead_cra_init,
-			.exit = spacc_aead_cra_exit,
-		},
-	},
-	{
-		.key_offs = 0,
-		.iv_offs = AES_MAX_KEY_SIZE,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_AES |
-				SPA_CTRL_CIPH_MODE_CBC |
-				SPA_CTRL_HASH_ALG_MD5 |
-				SPA_CTRL_HASH_MODE_HMAC,
-		.alg = {
-			.base = {
-				.cra_name = "authenc(hmac(md5),cbc(aes))",
-				.cra_driver_name = "authenc-hmac-md5-"
-						   "cbc-aes-picoxcell",
-				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-				.cra_flags = CRYPTO_ALG_ASYNC |
-					     CRYPTO_ALG_ALLOCATES_MEMORY |
-					     CRYPTO_ALG_NEED_FALLBACK |
-					     CRYPTO_ALG_KERN_DRIVER_ONLY,
-				.cra_blocksize = AES_BLOCK_SIZE,
-				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-				.cra_module = THIS_MODULE,
-			},
-			.setkey = spacc_aead_setkey,
-			.setauthsize = spacc_aead_setauthsize,
-			.encrypt = spacc_aead_encrypt,
-			.decrypt = spacc_aead_decrypt,
-			.ivsize = AES_BLOCK_SIZE,
-			.maxauthsize = MD5_DIGEST_SIZE,
-			.init = spacc_aead_cra_init,
-			.exit = spacc_aead_cra_exit,
-		},
-	},
-	{
-		.key_offs = DES_BLOCK_SIZE,
-		.iv_offs = 0,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_DES |
-				SPA_CTRL_CIPH_MODE_CBC |
-				SPA_CTRL_HASH_ALG_SHA |
-				SPA_CTRL_HASH_MODE_HMAC,
-		.alg = {
-			.base = {
-				.cra_name = "authenc(hmac(sha1),cbc(des3_ede))",
-				.cra_driver_name = "authenc-hmac-sha1-"
-						   "cbc-3des-picoxcell",
-				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-				.cra_flags = CRYPTO_ALG_ASYNC |
-					     CRYPTO_ALG_ALLOCATES_MEMORY |
-					     CRYPTO_ALG_NEED_FALLBACK |
-					     CRYPTO_ALG_KERN_DRIVER_ONLY,
-				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-				.cra_module = THIS_MODULE,
-			},
-			.setkey = spacc_aead_setkey,
-			.setauthsize = spacc_aead_setauthsize,
-			.encrypt = spacc_aead_encrypt,
-			.decrypt = spacc_aead_decrypt,
-			.ivsize = DES3_EDE_BLOCK_SIZE,
-			.maxauthsize = SHA1_DIGEST_SIZE,
-			.init = spacc_aead_cra_init,
-			.exit = spacc_aead_cra_exit,
-		},
-	},
-	{
-		.key_offs = DES_BLOCK_SIZE,
-		.iv_offs = 0,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_AES |
-				SPA_CTRL_CIPH_MODE_CBC |
-				SPA_CTRL_HASH_ALG_SHA256 |
-				SPA_CTRL_HASH_MODE_HMAC,
-		.alg = {
-			.base = {
-				.cra_name = "authenc(hmac(sha256),"
-					    "cbc(des3_ede))",
-				.cra_driver_name = "authenc-hmac-sha256-"
-						   "cbc-3des-picoxcell",
-				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-				.cra_flags = CRYPTO_ALG_ASYNC |
-					     CRYPTO_ALG_ALLOCATES_MEMORY |
-					     CRYPTO_ALG_NEED_FALLBACK |
-					     CRYPTO_ALG_KERN_DRIVER_ONLY,
-				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-				.cra_module = THIS_MODULE,
-			},
-			.setkey = spacc_aead_setkey,
-			.setauthsize = spacc_aead_setauthsize,
-			.encrypt = spacc_aead_encrypt,
-			.decrypt = spacc_aead_decrypt,
-			.ivsize = DES3_EDE_BLOCK_SIZE,
-			.maxauthsize = SHA256_DIGEST_SIZE,
-			.init = spacc_aead_cra_init,
-			.exit = spacc_aead_cra_exit,
-		},
-	},
-	{
-		.key_offs = DES_BLOCK_SIZE,
-		.iv_offs = 0,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_DES |
-				SPA_CTRL_CIPH_MODE_CBC |
-				SPA_CTRL_HASH_ALG_MD5 |
-				SPA_CTRL_HASH_MODE_HMAC,
-		.alg = {
-			.base = {
-				.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
-				.cra_driver_name = "authenc-hmac-md5-"
-						   "cbc-3des-picoxcell",
-				.cra_priority = SPACC_CRYPTO_ALG_PRIORITY,
-				.cra_flags = CRYPTO_ALG_ASYNC |
-					     CRYPTO_ALG_ALLOCATES_MEMORY |
-					     CRYPTO_ALG_NEED_FALLBACK |
-					     CRYPTO_ALG_KERN_DRIVER_ONLY,
-				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-				.cra_ctxsize = sizeof(struct spacc_aead_ctx),
-				.cra_module = THIS_MODULE,
-			},
-			.setkey = spacc_aead_setkey,
-			.setauthsize = spacc_aead_setauthsize,
-			.encrypt = spacc_aead_encrypt,
-			.decrypt = spacc_aead_decrypt,
-			.ivsize = DES3_EDE_BLOCK_SIZE,
-			.maxauthsize = MD5_DIGEST_SIZE,
-			.init = spacc_aead_cra_init,
-			.exit = spacc_aead_cra_exit,
-		},
-	},
-};
-
-static struct spacc_alg l2_engine_algs[] = {
-	{
-		.key_offs = 0,
-		.iv_offs = SPACC_CRYPTO_KASUMI_F8_KEY_LEN,
-		.ctrl_default = SPA_CTRL_CIPH_ALG_KASUMI |
-				SPA_CTRL_CIPH_MODE_F8,
-		.alg = {
-			.base.cra_name		= "f8(kasumi)",
-			.base.cra_driver_name	= "f8-kasumi-picoxcell",
-			.base.cra_priority	= SPACC_CRYPTO_ALG_PRIORITY,
-			.base.cra_flags		= CRYPTO_ALG_ASYNC |
-						  CRYPTO_ALG_ALLOCATES_MEMORY |
-						  CRYPTO_ALG_KERN_DRIVER_ONLY,
-			.base.cra_blocksize	= 8,
-			.base.cra_ctxsize	= sizeof(struct spacc_ablk_ctx),
-			.base.cra_module	= THIS_MODULE,
-
-			.setkey			= spacc_kasumi_f8_setkey,
-			.encrypt		= spacc_ablk_encrypt,
-			.decrypt		= spacc_ablk_decrypt,
-			.min_keysize		= 16,
-			.max_keysize		= 16,
-			.ivsize			= 8,
-			.init			= spacc_ablk_init_tfm,
-			.exit			= spacc_ablk_exit_tfm,
-		},
-	},
-};
-
-#ifdef CONFIG_OF
-static const struct of_device_id spacc_of_id_table[] = {
-	{ .compatible = "picochip,spacc-ipsec" },
-	{ .compatible = "picochip,spacc-l2" },
-	{}
-};
-MODULE_DEVICE_TABLE(of, spacc_of_id_table);
-#endif /* CONFIG_OF */
-
-static void spacc_tasklet_kill(void *data)
-{
-	tasklet_kill(data);
-}
-
-static int spacc_probe(struct platform_device *pdev)
-{
-	int i, err, ret;
-	struct resource *irq;
-	struct device_node *np = pdev->dev.of_node;
-	struct spacc_engine *engine = devm_kzalloc(&pdev->dev, sizeof(*engine),
-						   GFP_KERNEL);
-	if (!engine)
-		return -ENOMEM;
-
-	if (of_device_is_compatible(np, "picochip,spacc-ipsec")) {
-		engine->max_ctxs	= SPACC_CRYPTO_IPSEC_MAX_CTXS;
-		engine->cipher_pg_sz	= SPACC_CRYPTO_IPSEC_CIPHER_PG_SZ;
-		engine->hash_pg_sz	= SPACC_CRYPTO_IPSEC_HASH_PG_SZ;
-		engine->fifo_sz		= SPACC_CRYPTO_IPSEC_FIFO_SZ;
-		engine->algs		= ipsec_engine_algs;
-		engine->num_algs	= ARRAY_SIZE(ipsec_engine_algs);
-		engine->aeads		= ipsec_engine_aeads;
-		engine->num_aeads	= ARRAY_SIZE(ipsec_engine_aeads);
-	} else if (of_device_is_compatible(np, "picochip,spacc-l2")) {
-		engine->max_ctxs	= SPACC_CRYPTO_L2_MAX_CTXS;
-		engine->cipher_pg_sz	= SPACC_CRYPTO_L2_CIPHER_PG_SZ;
-		engine->hash_pg_sz	= SPACC_CRYPTO_L2_HASH_PG_SZ;
-		engine->fifo_sz		= SPACC_CRYPTO_L2_FIFO_SZ;
-		engine->algs		= l2_engine_algs;
-		engine->num_algs	= ARRAY_SIZE(l2_engine_algs);
-	} else {
-		return -EINVAL;
-	}
-
-	engine->name = dev_name(&pdev->dev);
-
-	engine->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(engine->regs))
-		return PTR_ERR(engine->regs);
-
-	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!irq) {
-		dev_err(&pdev->dev, "no memory/irq resource for engine\n");
-		return -ENXIO;
-	}
-
-	tasklet_init(&engine->complete, spacc_spacc_complete,
-		     (unsigned long)engine);
-
-	ret = devm_add_action(&pdev->dev, spacc_tasklet_kill,
-			      &engine->complete);
-	if (ret)
-		return ret;
-
-	if (devm_request_irq(&pdev->dev, irq->start, spacc_spacc_irq, 0,
-			     engine->name, engine)) {
-		dev_err(engine->dev, "failed to request IRQ\n");
-		return -EBUSY;
-	}
-
-	engine->dev		= &pdev->dev;
-	engine->cipher_ctx_base = engine->regs + SPA_CIPH_KEY_BASE_REG_OFFSET;
-	engine->hash_key_base	= engine->regs + SPA_HASH_KEY_BASE_REG_OFFSET;
-
-	engine->req_pool = dmam_pool_create(engine->name, engine->dev,
-		MAX_DDT_LEN * sizeof(struct spacc_ddt), 8, SZ_64K);
-	if (!engine->req_pool)
-		return -ENOMEM;
-
-	spin_lock_init(&engine->hw_lock);
-
-	engine->clk = clk_get(&pdev->dev, "ref");
-	if (IS_ERR(engine->clk)) {
-		dev_info(&pdev->dev, "clk unavailable\n");
-		return PTR_ERR(engine->clk);
-	}
-
-	if (clk_prepare_enable(engine->clk)) {
-		dev_info(&pdev->dev, "unable to prepare/enable clk\n");
-		ret = -EIO;
-		goto err_clk_put;
-	}
-
-	/*
-	 * Use an IRQ threshold of 50% as a default. This seems to be a
-	 * reasonable trade off of latency against throughput but can be
-	 * changed at runtime.
-	 */
-	engine->stat_irq_thresh = (engine->fifo_sz / 2);
-
-	ret = device_create_file(&pdev->dev, &dev_attr_stat_irq_thresh);
-	if (ret)
-		goto err_clk_disable;
-
-	/*
-	 * Configure the interrupts. We only use the STAT_CNT interrupt as we
-	 * only submit a new packet for processing when we complete another in
-	 * the queue. This minimizes time spent in the interrupt handler.
-	 */
-	writel(engine->stat_irq_thresh << SPA_IRQ_CTRL_STAT_CNT_OFFSET,
-	       engine->regs + SPA_IRQ_CTRL_REG_OFFSET);
-	writel(SPA_IRQ_EN_STAT_EN | SPA_IRQ_EN_GLBL_EN,
-	       engine->regs + SPA_IRQ_EN_REG_OFFSET);
-
-	timer_setup(&engine->packet_timeout, spacc_packet_timeout, 0);
-
-	INIT_LIST_HEAD(&engine->pending);
-	INIT_LIST_HEAD(&engine->completed);
-	INIT_LIST_HEAD(&engine->in_progress);
-	engine->in_flight = 0;
-
-	platform_set_drvdata(pdev, engine);
-
-	ret = -EINVAL;
-	INIT_LIST_HEAD(&engine->registered_algs);
-	for (i = 0; i < engine->num_algs; ++i) {
-		engine->algs[i].engine = engine;
-		err = crypto_register_skcipher(&engine->algs[i].alg);
-		if (!err) {
-			list_add_tail(&engine->algs[i].entry,
-				      &engine->registered_algs);
-			ret = 0;
-		}
-		if (err)
-			dev_err(engine->dev, "failed to register alg \"%s\"\n",
-				engine->algs[i].alg.base.cra_name);
-		else
-			dev_dbg(engine->dev, "registered alg \"%s\"\n",
-				engine->algs[i].alg.base.cra_name);
-	}
-
-	INIT_LIST_HEAD(&engine->registered_aeads);
-	for (i = 0; i < engine->num_aeads; ++i) {
-		engine->aeads[i].engine = engine;
-		err = crypto_register_aead(&engine->aeads[i].alg);
-		if (!err) {
-			list_add_tail(&engine->aeads[i].entry,
-				      &engine->registered_aeads);
-			ret = 0;
-		}
-		if (err)
-			dev_err(engine->dev, "failed to register alg \"%s\"\n",
-				engine->aeads[i].alg.base.cra_name);
-		else
-			dev_dbg(engine->dev, "registered alg \"%s\"\n",
-				engine->aeads[i].alg.base.cra_name);
-	}
-
-	if (!ret)
-		return 0;
-
-	del_timer_sync(&engine->packet_timeout);
-	device_remove_file(&pdev->dev, &dev_attr_stat_irq_thresh);
-err_clk_disable:
-	clk_disable_unprepare(engine->clk);
-err_clk_put:
-	clk_put(engine->clk);
-
-	return ret;
-}
-
-static int spacc_remove(struct platform_device *pdev)
-{
-	struct spacc_aead *aead, *an;
-	struct spacc_alg *alg, *next;
-	struct spacc_engine *engine = platform_get_drvdata(pdev);
-
-	del_timer_sync(&engine->packet_timeout);
-	device_remove_file(&pdev->dev, &dev_attr_stat_irq_thresh);
-
-	list_for_each_entry_safe(aead, an, &engine->registered_aeads, entry) {
-		list_del(&aead->entry);
-		crypto_unregister_aead(&aead->alg);
-	}
-
-	list_for_each_entry_safe(alg, next, &engine->registered_algs, entry) {
-		list_del(&alg->entry);
-		crypto_unregister_skcipher(&alg->alg);
-	}
-
-	clk_disable_unprepare(engine->clk);
-	clk_put(engine->clk);
-
-	return 0;
-}
-
-static struct platform_driver spacc_driver = {
-	.probe		= spacc_probe,
-	.remove		= spacc_remove,
-	.driver		= {
-		.name	= "picochip,spacc",
-#ifdef CONFIG_PM
-		.pm	= &spacc_pm_ops,
-#endif /* CONFIG_PM */
-		.of_match_table	= of_match_ptr(spacc_of_id_table),
-	},
-};
-
-module_platform_driver(spacc_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Jamie Iles");
diff --git a/drivers/crypto/picoxcell_crypto_regs.h b/drivers/crypto/picoxcell_crypto_regs.h
deleted file mode 100644
index b870a50238ba..000000000000
--- a/drivers/crypto/picoxcell_crypto_regs.h
+++ /dev/null
@@ -1,115 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (c) 2010 Picochip Ltd., Jamie Iles
- */
-#ifndef __PICOXCELL_CRYPTO_REGS_H__
-#define __PICOXCELL_CRYPTO_REGS_H__
-
-#define SPA_STATUS_OK			0
-#define SPA_STATUS_ICV_FAIL		1
-#define SPA_STATUS_MEMORY_ERROR		2
-#define SPA_STATUS_BLOCK_ERROR		3
-
-#define SPA_IRQ_CTRL_STAT_CNT_OFFSET	16
-#define SPA_IRQ_STAT_STAT_MASK		(1 << 4)
-#define SPA_FIFO_STAT_STAT_OFFSET	16
-#define SPA_FIFO_STAT_STAT_CNT_MASK	(0x3F << SPA_FIFO_STAT_STAT_OFFSET)
-#define SPA_STATUS_RES_CODE_OFFSET	24
-#define SPA_STATUS_RES_CODE_MASK	(0x3 << SPA_STATUS_RES_CODE_OFFSET)
-#define SPA_KEY_SZ_CTX_INDEX_OFFSET	8
-#define SPA_KEY_SZ_CIPHER_OFFSET	31
-
-#define SPA_IRQ_EN_REG_OFFSET		0x00000000
-#define SPA_IRQ_STAT_REG_OFFSET		0x00000004
-#define SPA_IRQ_CTRL_REG_OFFSET		0x00000008
-#define SPA_FIFO_STAT_REG_OFFSET	0x0000000C
-#define SPA_SDMA_BRST_SZ_REG_OFFSET	0x00000010
-#define SPA_SRC_PTR_REG_OFFSET		0x00000020
-#define SPA_DST_PTR_REG_OFFSET		0x00000024
-#define SPA_OFFSET_REG_OFFSET		0x00000028
-#define SPA_AAD_LEN_REG_OFFSET		0x0000002C
-#define SPA_PROC_LEN_REG_OFFSET		0x00000030
-#define SPA_ICV_LEN_REG_OFFSET		0x00000034
-#define SPA_ICV_OFFSET_REG_OFFSET	0x00000038
-#define SPA_SW_CTRL_REG_OFFSET		0x0000003C
-#define SPA_CTRL_REG_OFFSET		0x00000040
-#define SPA_AUX_INFO_REG_OFFSET		0x0000004C
-#define SPA_STAT_POP_REG_OFFSET		0x00000050
-#define SPA_STATUS_REG_OFFSET		0x00000054
-#define SPA_KEY_SZ_REG_OFFSET		0x00000100
-#define SPA_CIPH_KEY_BASE_REG_OFFSET	0x00004000
-#define SPA_HASH_KEY_BASE_REG_OFFSET	0x00008000
-#define SPA_RC4_CTX_BASE_REG_OFFSET	0x00020000
-
-#define SPA_IRQ_EN_REG_RESET		0x00000000
-#define SPA_IRQ_CTRL_REG_RESET		0x00000000
-#define SPA_FIFO_STAT_REG_RESET		0x00000000
-#define SPA_SDMA_BRST_SZ_REG_RESET	0x00000000
-#define SPA_SRC_PTR_REG_RESET		0x00000000
-#define SPA_DST_PTR_REG_RESET		0x00000000
-#define SPA_OFFSET_REG_RESET		0x00000000
-#define SPA_AAD_LEN_REG_RESET		0x00000000
-#define SPA_PROC_LEN_REG_RESET		0x00000000
-#define SPA_ICV_LEN_REG_RESET		0x00000000
-#define SPA_ICV_OFFSET_REG_RESET	0x00000000
-#define SPA_SW_CTRL_REG_RESET		0x00000000
-#define SPA_CTRL_REG_RESET		0x00000000
-#define SPA_AUX_INFO_REG_RESET		0x00000000
-#define SPA_STAT_POP_REG_RESET		0x00000000
-#define SPA_STATUS_REG_RESET		0x00000000
-#define SPA_KEY_SZ_REG_RESET		0x00000000
-
-#define SPA_CTRL_HASH_ALG_IDX		4
-#define SPA_CTRL_CIPH_MODE_IDX		8
-#define SPA_CTRL_HASH_MODE_IDX		12
-#define SPA_CTRL_CTX_IDX		16
-#define SPA_CTRL_ENCRYPT_IDX		24
-#define SPA_CTRL_AAD_COPY		25
-#define SPA_CTRL_ICV_PT			26
-#define SPA_CTRL_ICV_ENC		27
-#define SPA_CTRL_ICV_APPEND		28
-#define SPA_CTRL_KEY_EXP		29
-
-#define SPA_KEY_SZ_CXT_IDX		8
-#define SPA_KEY_SZ_CIPHER_IDX		31
-
-#define SPA_IRQ_EN_CMD0_EN		(1 << 0)
-#define SPA_IRQ_EN_STAT_EN		(1 << 4)
-#define SPA_IRQ_EN_GLBL_EN		(1 << 31)
-
-#define SPA_CTRL_CIPH_ALG_NULL		0x00
-#define SPA_CTRL_CIPH_ALG_DES		0x01
-#define SPA_CTRL_CIPH_ALG_AES		0x02
-#define SPA_CTRL_CIPH_ALG_RC4		0x03
-#define SPA_CTRL_CIPH_ALG_MULTI2	0x04
-#define SPA_CTRL_CIPH_ALG_KASUMI	0x05
-
-#define SPA_CTRL_HASH_ALG_NULL		(0x00 << SPA_CTRL_HASH_ALG_IDX)
-#define SPA_CTRL_HASH_ALG_MD5		(0x01 << SPA_CTRL_HASH_ALG_IDX)
-#define SPA_CTRL_HASH_ALG_SHA		(0x02 << SPA_CTRL_HASH_ALG_IDX)
-#define SPA_CTRL_HASH_ALG_SHA224	(0x03 << SPA_CTRL_HASH_ALG_IDX)
-#define SPA_CTRL_HASH_ALG_SHA256	(0x04 << SPA_CTRL_HASH_ALG_IDX)
-#define SPA_CTRL_HASH_ALG_SHA384	(0x05 << SPA_CTRL_HASH_ALG_IDX)
-#define SPA_CTRL_HASH_ALG_SHA512	(0x06 << SPA_CTRL_HASH_ALG_IDX)
-#define SPA_CTRL_HASH_ALG_AESMAC	(0x07 << SPA_CTRL_HASH_ALG_IDX)
-#define SPA_CTRL_HASH_ALG_AESCMAC	(0x08 << SPA_CTRL_HASH_ALG_IDX)
-#define SPA_CTRL_HASH_ALG_KASF9		(0x09 << SPA_CTRL_HASH_ALG_IDX)
-
-#define SPA_CTRL_CIPH_MODE_NULL		(0x00 << SPA_CTRL_CIPH_MODE_IDX)
-#define SPA_CTRL_CIPH_MODE_ECB		(0x00 << SPA_CTRL_CIPH_MODE_IDX)
-#define SPA_CTRL_CIPH_MODE_CBC		(0x01 << SPA_CTRL_CIPH_MODE_IDX)
-#define SPA_CTRL_CIPH_MODE_CTR		(0x02 << SPA_CTRL_CIPH_MODE_IDX)
-#define SPA_CTRL_CIPH_MODE_CCM		(0x03 << SPA_CTRL_CIPH_MODE_IDX)
-#define SPA_CTRL_CIPH_MODE_GCM		(0x05 << SPA_CTRL_CIPH_MODE_IDX)
-#define SPA_CTRL_CIPH_MODE_OFB		(0x07 << SPA_CTRL_CIPH_MODE_IDX)
-#define SPA_CTRL_CIPH_MODE_CFB		(0x08 << SPA_CTRL_CIPH_MODE_IDX)
-#define SPA_CTRL_CIPH_MODE_F8		(0x09 << SPA_CTRL_CIPH_MODE_IDX)
-
-#define SPA_CTRL_HASH_MODE_RAW		(0x00 << SPA_CTRL_HASH_MODE_IDX)
-#define SPA_CTRL_HASH_MODE_SSLMAC	(0x01 << SPA_CTRL_HASH_MODE_IDX)
-#define SPA_CTRL_HASH_MODE_HMAC		(0x02 << SPA_CTRL_HASH_MODE_IDX)
-
-#define SPA_FIFO_STAT_EMPTY		(1 << 31)
-#define SPA_FIFO_CMD_FULL		(1 << 7)
-
-#endif /* __PICOXCELL_CRYPTO_REGS_H__ */
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig
index 846a3d90b41a..77783feb62b2 100644
--- a/drivers/crypto/qat/Kconfig
+++ b/drivers/crypto/qat/Kconfig
@@ -11,7 +11,7 @@ config CRYPTO_DEV_QAT
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
-	select CRYPTO_AES
+	select CRYPTO_LIB_AES
 	select FW_LOADER
 
 config CRYPTO_DEV_QAT_DH895xCC
diff --git a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c
index 344bfae45bff..6a9be01fdf33 100644
--- a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c
+++ b/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c
@@ -19,7 +19,7 @@ static struct adf_fw_config adf_4xxx_fw_config[] = {
 };
 
 /* Worker thread to service arbiter mappings */
-static u32 thrd_to_arb_map[] = {
+static const u32 thrd_to_arb_map[ADF_4XXX_MAX_ACCELENGINES] = {
 	0x5555555, 0x5555555, 0x5555555, 0x5555555,
 	0xAAAAAAA, 0xAAAAAAA, 0xAAAAAAA, 0xAAAAAAA,
 	0x0
@@ -119,17 +119,9 @@ static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
 	return DEV_SKU_1;
 }
 
-static void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
-				    u32 const **arb_map_config)
+static const u32 *adf_get_arbiter_mapping(void)
 {
-	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
-	unsigned long ae_mask = hw_device->ae_mask;
-	int i;
-
-	for_each_clear_bit(i, &ae_mask, ADF_4XXX_MAX_ACCELENGINES)
-		thrd_to_arb_map[i] = 0;
-
-	*arb_map_config = thrd_to_arb_map;
+	return thrd_to_arb_map;
 }
 
 static void get_arb_info(struct arb_info *arb_info)
diff --git a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
index eb45f1b1ae3e..f5990d042c9a 100644
--- a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
+++ b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
@@ -7,8 +7,8 @@
 #include "adf_c3xxx_hw_data.h"
 #include "icp_qat_hw.h"
 
-/* Worker thread to service arbiter mappings based on dev SKUs */
-static const u32 thrd_to_arb_map_6_me_sku[] = {
+/* Worker thread to service arbiter mappings */
+static const u32 thrd_to_arb_map[ADF_C3XXX_MAX_ACCELENGINES] = {
 	0x12222AAA, 0x11222AAA, 0x12222AAA,
 	0x11222AAA, 0x12222AAA, 0x11222AAA
 };
@@ -101,18 +101,9 @@ static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
 	return DEV_SKU_UNKNOWN;
 }
 
-static void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
-				    u32 const **arb_map_config)
+static const u32 *adf_get_arbiter_mapping(void)
 {
-	switch (accel_dev->accel_pci_dev.sku) {
-	case DEV_SKU_4:
-		*arb_map_config = thrd_to_arb_map_6_me_sku;
-		break;
-	default:
-		dev_err(&GET_DEV(accel_dev),
-			"The configuration doesn't match any SKU");
-		*arb_map_config = NULL;
-	}
+	return thrd_to_arb_map;
 }
 
 static u32 get_pf2vf_offset(u32 i)
diff --git a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
index babdffbcb846..cadcf12884c8 100644
--- a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
+++ b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
@@ -7,13 +7,8 @@
 #include "adf_c62x_hw_data.h"
 #include "icp_qat_hw.h"
 
-/* Worker thread to service arbiter mappings based on dev SKUs */
-static const u32 thrd_to_arb_map_8_me_sku[] = {
-	0x12222AAA, 0x11222AAA, 0x12222AAA, 0x11222AAA, 0x12222AAA,
-	0x11222AAA, 0x12222AAA, 0x11222AAA, 0, 0
-};
-
-static const u32 thrd_to_arb_map_10_me_sku[] = {
+/* Worker thread to service arbiter mappings */
+static const u32 thrd_to_arb_map[ADF_C62X_MAX_ACCELENGINES] = {
 	0x12222AAA, 0x11222AAA, 0x12222AAA, 0x11222AAA, 0x12222AAA,
 	0x11222AAA, 0x12222AAA, 0x11222AAA, 0x12222AAA, 0x11222AAA
 };
@@ -108,21 +103,9 @@ static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
 	return DEV_SKU_UNKNOWN;
 }
 
-static void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
-				    u32 const **arb_map_config)
-{
-	switch (accel_dev->accel_pci_dev.sku) {
-	case DEV_SKU_2:
-		*arb_map_config = thrd_to_arb_map_8_me_sku;
-		break;
-	case DEV_SKU_4:
-		*arb_map_config = thrd_to_arb_map_10_me_sku;
-		break;
-	default:
-		dev_err(&GET_DEV(accel_dev),
-			"The configuration doesn't match any SKU");
-		*arb_map_config = NULL;
-	}
+static const u32 *adf_get_arbiter_mapping(void)
+{
+	return thrd_to_arb_map;
 }
 
 static u32 get_pf2vf_offset(u32 i)
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index c46a5805b294..5527344546e5 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -168,8 +168,7 @@ struct adf_hw_device_data {
 	int (*send_admin_init)(struct adf_accel_dev *accel_dev);
 	int (*init_arb)(struct adf_accel_dev *accel_dev);
 	void (*exit_arb)(struct adf_accel_dev *accel_dev);
-	void (*get_arb_mapping)(struct adf_accel_dev *accel_dev,
-				const u32 **cfg);
+	const u32 *(*get_arb_mapping)(void);
 	void (*disable_iov)(struct adf_accel_dev *accel_dev);
 	void (*configure_iov_threads)(struct adf_accel_dev *accel_dev,
 				      bool enable);
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
index eb9b3be9d8eb..96b437bfe3de 100644
--- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -464,3 +464,4 @@ MODULE_AUTHOR("Intel");
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
 MODULE_ALIAS_CRYPTO("intel_qat");
 MODULE_VERSION(ADF_DRV_VERSION);
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/drivers/crypto/qat/qat_common/adf_hw_arbiter.c b/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
index 9f5240d9488b..64e4596a24f4 100644
--- a/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
+++ b/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
@@ -19,6 +19,7 @@ int adf_init_arb(struct adf_accel_dev *accel_dev)
 {
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
 	void __iomem *csr = accel_dev->transport->banks[0].csr_addr;
+	unsigned long ae_mask = hw_data->ae_mask;
 	u32 arb_off, wt_off, arb_cfg;
 	const u32 *thd_2_arb_cfg;
 	struct arb_info info;
@@ -35,12 +36,9 @@ int adf_init_arb(struct adf_accel_dev *accel_dev)
 		WRITE_CSR_ARB_SARCONFIG(csr, arb_off, arb, arb_cfg);
 
 	/* Map worker threads to service arbiters */
-	hw_data->get_arb_mapping(accel_dev, &thd_2_arb_cfg);
+	thd_2_arb_cfg = hw_data->get_arb_mapping();
 
-	if (!thd_2_arb_cfg)
-		return -EFAULT;
-
-	for (i = 0; i < hw_data->num_engines; i++)
+	for_each_set_bit(i, &ae_mask, hw_data->num_engines)
 		WRITE_CSR_ARB_WT2SAM(csr, arb_off, wt_off, i, thd_2_arb_cfg[i]);
 
 	return 0;
diff --git a/drivers/crypto/qat/qat_common/adf_transport.c b/drivers/crypto/qat/qat_common/adf_transport.c
index 5a7030acdc33..888c1e047295 100644
--- a/drivers/crypto/qat/qat_common/adf_transport.c
+++ b/drivers/crypto/qat/qat_common/adf_transport.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only)
 /* Copyright(c) 2014 - 2020 Intel Corporation */
 #include <linux/delay.h>
+#include <linux/nospec.h>
 #include "adf_accel_devices.h"
 #include "adf_transport_internal.h"
 #include "adf_transport_access_macros.h"
@@ -246,6 +247,7 @@ int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section,
 		return -EFAULT;
 	}
 
+	ring_num = array_index_nospec(ring_num, num_rings_per_bank);
 	bank = &transport_data->banks[bank_num];
 	if (adf_reserve_ring(bank, ring_num)) {
 		dev_err(&GET_DEV(accel_dev), "Ring %d, %s already exists.\n",
diff --git a/drivers/crypto/qat/qat_common/adf_transport_debug.c b/drivers/crypto/qat/qat_common/adf_transport_debug.c
index 1205186ad51e..e69e5907f595 100644
--- a/drivers/crypto/qat/qat_common/adf_transport_debug.c
+++ b/drivers/crypto/qat/qat_common/adf_transport_debug.c
@@ -62,8 +62,8 @@ static int adf_ring_show(struct seq_file *sfile, void *v)
 		seq_printf(sfile, "head %x, tail %x, empty: %d\n",
 			   head, tail, (empty & 1 << ring->ring_number)
 			   >> ring->ring_number);
-		seq_printf(sfile, "ring size %d, msg size %d\n",
-			   ADF_SIZE_TO_RING_SIZE_IN_BYTES(ring->ring_size),
+		seq_printf(sfile, "ring size %lld, msg size %d\n",
+			   (long long)ADF_SIZE_TO_RING_SIZE_IN_BYTES(ring->ring_size),
 			   ADF_MSG_SIZE_TO_BYTES(ring->msg_size));
 		seq_puts(sfile, "----------- Ring data ------------\n");
 		return 0;
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 31c7a206a629..ff78c73c47e3 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -4,6 +4,7 @@
 #include <linux/slab.h>
 #include <linux/crypto.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/aes.h>
 #include <crypto/sha1.h>
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c
index 2c863d25327a..b0b78445418b 100644
--- a/drivers/crypto/qat/qat_common/qat_asym_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c
@@ -321,13 +321,13 @@ static int qat_dh_compute_value(struct kpp_request *req)
 	qat_req->out.dh.out_tab[1] = 0;
 	/* Mapping in.in.b or in.in_g2.xa is the same */
 	qat_req->phy_in = dma_map_single(dev, &qat_req->in.dh.in.b,
-					 sizeof(struct qat_dh_input_params),
+					 sizeof(qat_req->in.dh.in.b),
 					 DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_in)))
 		goto unmap_dst;
 
 	qat_req->phy_out = dma_map_single(dev, &qat_req->out.dh.r,
-					  sizeof(struct qat_dh_output_params),
+					  sizeof(qat_req->out.dh.r),
 					  DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_out)))
 		goto unmap_in_params;
@@ -716,13 +716,13 @@ static int qat_rsa_enc(struct akcipher_request *req)
 	qat_req->in.rsa.in_tab[3] = 0;
 	qat_req->out.rsa.out_tab[1] = 0;
 	qat_req->phy_in = dma_map_single(dev, &qat_req->in.rsa.enc.m,
-					 sizeof(struct qat_rsa_input_params),
+					 sizeof(qat_req->in.rsa.enc.m),
 					 DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_in)))
 		goto unmap_dst;
 
 	qat_req->phy_out = dma_map_single(dev, &qat_req->out.rsa.enc.c,
-					  sizeof(struct qat_rsa_output_params),
+					  sizeof(qat_req->out.rsa.enc.c),
 					  DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_out)))
 		goto unmap_in_params;
@@ -864,13 +864,13 @@ static int qat_rsa_dec(struct akcipher_request *req)
 		qat_req->in.rsa.in_tab[3] = 0;
 	qat_req->out.rsa.out_tab[1] = 0;
 	qat_req->phy_in = dma_map_single(dev, &qat_req->in.rsa.dec.c,
-					 sizeof(struct qat_rsa_input_params),
+					 sizeof(qat_req->in.rsa.dec.c),
 					 DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_in)))
 		goto unmap_dst;
 
 	qat_req->phy_out = dma_map_single(dev, &qat_req->out.rsa.dec.m,
-					  sizeof(struct qat_rsa_output_params),
+					  sizeof(qat_req->out.rsa.dec.m),
 					  DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_out)))
 		goto unmap_in_params;
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
index 1e83d9397b11..7dd7cd6c3ef8 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
@@ -7,14 +7,8 @@
 #include "adf_dh895xcc_hw_data.h"
 #include "icp_qat_hw.h"
 
-/* Worker thread to service arbiter mappings based on dev SKUs */
-static const u32 thrd_to_arb_map_sku4[] = {
-	0x12222AAA, 0x11666666, 0x12222AAA, 0x11666666,
-	0x12222AAA, 0x11222222, 0x12222AAA, 0x11222222,
-	0x00000000, 0x00000000, 0x00000000, 0x00000000
-};
-
-static const u32 thrd_to_arb_map_sku6[] = {
+/* Worker thread to service arbiter mappings */
+static const u32 thrd_to_arb_map[ADF_DH895XCC_MAX_ACCELENGINES] = {
 	0x12222AAA, 0x11666666, 0x12222AAA, 0x11666666,
 	0x12222AAA, 0x11222222, 0x12222AAA, 0x11222222,
 	0x12222AAA, 0x11222222, 0x12222AAA, 0x11222222
@@ -127,23 +121,9 @@ static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
 	return DEV_SKU_UNKNOWN;
 }
 
-static void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
-				    u32 const **arb_map_config)
+static const u32 *adf_get_arbiter_mapping(void)
 {
-	switch (accel_dev->accel_pci_dev.sku) {
-	case DEV_SKU_1:
-		*arb_map_config = thrd_to_arb_map_sku4;
-		break;
-
-	case DEV_SKU_2:
-	case DEV_SKU_4:
-		*arb_map_config = thrd_to_arb_map_sku6;
-		break;
-	default:
-		dev_err(&GET_DEV(accel_dev),
-			"The configuration doesn't match any SKU");
-		*arb_map_config = NULL;
-	}
+	return thrd_to_arb_map;
 }
 
 static u32 get_pf2vf_offset(u32 i)
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 8b5be29cb4dc..457084b344c1 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -1350,12 +1350,6 @@ static void sahara_unregister_algs(struct sahara_dev *dev)
 			crypto_unregister_ahash(&sha_v4_algs[i]);
 }
 
-static const struct platform_device_id sahara_platform_ids[] = {
-	{ .name = "sahara-imx27" },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(platform, sahara_platform_ids);
-
 static const struct of_device_id sahara_dt_ids[] = {
 	{ .compatible = "fsl,imx53-sahara" },
 	{ .compatible = "fsl,imx27-sahara" },
@@ -1540,7 +1534,6 @@ static struct platform_driver sahara_driver = {
 		.name	= SAHARA_NAME,
 		.of_match_table = sahara_dt_ids,
 	},
-	.id_table = sahara_platform_ids,
 };
 
 module_platform_driver(sahara_driver);
diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c
index 2670c30332fa..2a4793176c71 100644
--- a/drivers/crypto/stm32/stm32-cryp.c
+++ b/drivers/crypto/stm32/stm32-cryp.c
@@ -1229,7 +1229,7 @@ static void stm32_cryp_check_ctr_counter(struct stm32_cryp *cryp)
 		cr = stm32_cryp_read(cryp, CRYP_CR);
 		stm32_cryp_write(cryp, CRYP_CR, cr & ~CR_CRYPEN);
 
-		stm32_cryp_hw_write_iv(cryp, (u32 *)cryp->last_ctr);
+		stm32_cryp_hw_write_iv(cryp, (__be32 *)cryp->last_ctr);
 
 		stm32_cryp_write(cryp, CRYP_CR, cr);
 	}
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 4fd85f31630a..25c9f825b8b5 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -1093,11 +1093,12 @@ static void ipsec_esp_decrypt_hwauth_done(struct device *dev,
  */
 static int sg_to_link_tbl_offset(struct scatterlist *sg, int sg_count,
 				 unsigned int offset, int datalen, int elen,
-				 struct talitos_ptr *link_tbl_ptr)
+				 struct talitos_ptr *link_tbl_ptr, int align)
 {
 	int n_sg = elen ? sg_count + 1 : sg_count;
 	int count = 0;
 	int cryptlen = datalen + elen;
+	int padding = ALIGN(cryptlen, align) - cryptlen;
 
 	while (cryptlen && sg && n_sg--) {
 		unsigned int len = sg_dma_len(sg);
@@ -1121,7 +1122,7 @@ static int sg_to_link_tbl_offset(struct scatterlist *sg, int sg_count,
 			offset += datalen;
 		}
 		to_talitos_ptr(link_tbl_ptr + count,
-			       sg_dma_address(sg) + offset, len, 0);
+			       sg_dma_address(sg) + offset, sg_next(sg) ? len : len + padding, 0);
 		to_talitos_ptr_ext_set(link_tbl_ptr + count, 0, 0);
 		count++;
 		cryptlen -= len;
@@ -1144,10 +1145,11 @@ 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,
-			      bool force)
+			      bool force, int align)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
+	int aligned_len = ALIGN(len, align);
 
 	if (!src) {
 		to_talitos_ptr(ptr, 0, 0, is_sec1);
@@ -1155,22 +1157,22 @@ static int talitos_sg_map_ext(struct device *dev, struct scatterlist *src,
 	}
 	to_talitos_ptr_ext_set(ptr, elen, is_sec1);
 	if (sg_count == 1 && !force) {
-		to_talitos_ptr(ptr, sg_dma_address(src) + offset, len, is_sec1);
+		to_talitos_ptr(ptr, sg_dma_address(src) + offset, aligned_len, is_sec1);
 		return sg_count;
 	}
 	if (is_sec1) {
-		to_talitos_ptr(ptr, edesc->dma_link_tbl + offset, len, is_sec1);
+		to_talitos_ptr(ptr, edesc->dma_link_tbl + offset, aligned_len, is_sec1);
 		return sg_count;
 	}
 	sg_count = sg_to_link_tbl_offset(src, sg_count, offset, len, elen,
-					 &edesc->link_tbl[tbl_off]);
+					 &edesc->link_tbl[tbl_off], align);
 	if (sg_count == 1 && !force) {
 		/* Only one segment now, so no link tbl needed*/
 		copy_talitos_ptr(ptr, &edesc->link_tbl[tbl_off], is_sec1);
 		return sg_count;
 	}
 	to_talitos_ptr(ptr, edesc->dma_link_tbl +
-			    tbl_off * sizeof(struct talitos_ptr), len, is_sec1);
+			    tbl_off * sizeof(struct talitos_ptr), aligned_len, is_sec1);
 	to_talitos_ptr_ext_or(ptr, DESC_PTR_LNKTBL_JUMP, is_sec1);
 
 	return sg_count;
@@ -1182,7 +1184,7 @@ static int talitos_sg_map(struct device *dev, struct scatterlist *src,
 			  unsigned int offset, int tbl_off)
 {
 	return talitos_sg_map_ext(dev, src, len, edesc, ptr, sg_count, offset,
-				  tbl_off, 0, false);
+				  tbl_off, 0, false, 1);
 }
 
 /*
@@ -1251,7 +1253,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 
 	ret = talitos_sg_map_ext(dev, areq->src, cryptlen, edesc, &desc->ptr[4],
 				 sg_count, areq->assoclen, tbl_off, elen,
-				 false);
+				 false, 1);
 
 	if (ret > 1) {
 		tbl_off += ret;
@@ -1271,7 +1273,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 		elen = 0;
 	ret = talitos_sg_map_ext(dev, areq->dst, cryptlen, edesc, &desc->ptr[5],
 				 sg_count, areq->assoclen, tbl_off, elen,
-				 is_ipsec_esp && !encrypt);
+				 is_ipsec_esp && !encrypt, 1);
 	tbl_off += ret;
 
 	if (!encrypt && is_ipsec_esp) {
@@ -1577,6 +1579,8 @@ static int common_nonsnoop(struct talitos_edesc *edesc,
 	bool sync_needed = false;
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
+	bool is_ctr = (desc->hdr & DESC_HDR_SEL0_MASK) == DESC_HDR_SEL0_AESU &&
+		      (desc->hdr & DESC_HDR_MODE0_AESU_MASK) == DESC_HDR_MODE0_AESU_CTR;
 
 	/* first DWORD empty */
 
@@ -1597,8 +1601,8 @@ static int common_nonsnoop(struct talitos_edesc *edesc,
 	/*
 	 * cipher in
 	 */
-	sg_count = talitos_sg_map(dev, areq->src, cryptlen, edesc,
-				  &desc->ptr[3], sg_count, 0, 0);
+	sg_count = talitos_sg_map_ext(dev, areq->src, cryptlen, edesc, &desc->ptr[3],
+				      sg_count, 0, 0, 0, false, is_ctr ? 16 : 1);
 	if (sg_count > 1)
 		sync_needed = true;
 
@@ -2763,6 +2767,22 @@ static struct talitos_alg_template driver_algs[] = {
 	},
 	{	.type = CRYPTO_ALG_TYPE_SKCIPHER,
 		.alg.skcipher = {
+			.base.cra_name = "ctr(aes)",
+			.base.cra_driver_name = "ctr-aes-talitos",
+			.base.cra_blocksize = 1,
+			.base.cra_flags = CRYPTO_ALG_ASYNC |
+					  CRYPTO_ALG_ALLOCATES_MEMORY,
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			.setkey = skcipher_aes_setkey,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CTR,
+	},
+	{	.type = CRYPTO_ALG_TYPE_SKCIPHER,
+		.alg.skcipher = {
 			.base.cra_name = "ecb(des)",
 			.base.cra_driver_name = "ecb-des-talitos",
 			.base.cra_blocksize = DES_BLOCK_SIZE,
@@ -3178,6 +3198,12 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 			t_alg->algt.alg.skcipher.setkey ?: skcipher_setkey;
 		t_alg->algt.alg.skcipher.encrypt = skcipher_encrypt;
 		t_alg->algt.alg.skcipher.decrypt = skcipher_decrypt;
+		if (!strcmp(alg->cra_name, "ctr(aes)") && !has_ftr_sec1(priv) &&
+		    DESC_TYPE(t_alg->algt.desc_hdr_template) !=
+		    DESC_TYPE(DESC_HDR_TYPE_AESU_CTR_NONSNOOP)) {
+			devm_kfree(dev, t_alg);
+			return ERR_PTR(-ENOTSUPP);
+		}
 		break;
 	case CRYPTO_ALG_TYPE_AEAD:
 		alg = &t_alg->algt.alg.aead.base;
diff --git a/drivers/crypto/talitos.h b/drivers/crypto/talitos.h
index 1469b956948a..32825119e880 100644
--- a/drivers/crypto/talitos.h
+++ b/drivers/crypto/talitos.h
@@ -344,6 +344,7 @@ static inline bool has_ftr_sec1(struct talitos_private *priv)
 
 /* primary execution unit mode (MODE0) and derivatives */
 #define	DESC_HDR_MODE0_ENCRYPT		cpu_to_be32(0x00100000)
+#define	DESC_HDR_MODE0_AESU_MASK	cpu_to_be32(0x00600000)
 #define	DESC_HDR_MODE0_AESU_CBC		cpu_to_be32(0x00200000)
 #define	DESC_HDR_MODE0_AESU_CTR		cpu_to_be32(0x00600000)
 #define	DESC_HDR_MODE0_DEU_CBC		cpu_to_be32(0x00400000)
diff --git a/drivers/crypto/vmx/aes.c b/drivers/crypto/vmx/aes.c
index 2bc5d4e1adf4..d05c02baebcf 100644
--- a/drivers/crypto/vmx/aes.c
+++ b/drivers/crypto/vmx/aes.c
@@ -14,6 +14,7 @@
 #include <asm/simd.h>
 #include <asm/switch_to.h>
 #include <crypto/aes.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/internal/simd.h>
 
 #include "aesp8-ppc.h"
diff --git a/drivers/crypto/vmx/aesp8-ppc.h b/drivers/crypto/vmx/aesp8-ppc.h
index 01774a4d26a2..5764d4438388 100644
--- a/drivers/crypto/vmx/aesp8-ppc.h
+++ b/drivers/crypto/vmx/aesp8-ppc.h
@@ -7,6 +7,12 @@ struct aes_key {
 	int rounds;
 };
 
+extern struct shash_alg p8_ghash_alg;
+extern struct crypto_alg p8_aes_alg;
+extern struct skcipher_alg p8_aes_cbc_alg;
+extern struct skcipher_alg p8_aes_ctr_alg;
+extern struct skcipher_alg p8_aes_xts_alg;
+
 int aes_p8_set_encrypt_key(const u8 *userKey, const int bits,
 			   struct aes_key *key);
 int aes_p8_set_decrypt_key(const u8 *userKey, const int bits,
diff --git a/drivers/crypto/vmx/vmx.c b/drivers/crypto/vmx/vmx.c
index 3e0335fb406c..a40d08e75fc0 100644
--- a/drivers/crypto/vmx/vmx.c
+++ b/drivers/crypto/vmx/vmx.c
@@ -17,11 +17,7 @@
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 
-extern struct shash_alg p8_ghash_alg;
-extern struct crypto_alg p8_aes_alg;
-extern struct skcipher_alg p8_aes_cbc_alg;
-extern struct skcipher_alg p8_aes_ctr_alg;
-extern struct skcipher_alg p8_aes_xts_alg;
+#include "aesp8-ppc.h"
 
 static int __init p8_init(void)
 {
@@ -78,3 +74,4 @@ MODULE_DESCRIPTION("IBM VMX cryptographic acceleration instructions "
 		   "support on Power 8");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0.0");
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 1ebb4b943876..45d12b0e9a2f 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -91,6 +91,7 @@ config WIREGUARD
 	select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON
 	select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON
 	select CRYPTO_POLY1305_ARM if ARM
+	select CRYPTO_BLAKE2S_ARM if ARM
 	select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON
 	select CRYPTO_CHACHA_MIPS if CPU_MIPS32_R2
 	select CRYPTO_POLY1305_MIPS if CPU_MIPS32 || (CPU_MIPS64 && 64BIT)
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/Kconfig b/drivers/net/ethernet/chelsio/inline_crypto/Kconfig
index bc06e83fd3c6..521955e1f894 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/Kconfig
+++ b/drivers/net/ethernet/chelsio/inline_crypto/Kconfig
@@ -42,6 +42,7 @@ config CHELSIO_TLS_DEVICE
         depends on CHELSIO_T4
         depends on TLS
         depends on TLS_DEVICE
+	select CRYPTO_LIB_AES
         help
           This flag enables support for kernel tls offload over Chelsio T6
           crypto accelerator. CONFIG_CHELSIO_TLS_DEVICE flag can be enabled
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index 1b7e8c91b541..46a809f2aeca 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -9,6 +9,7 @@
 #include <linux/ip.h>
 #include <net/ipv6.h>
 #include <linux/netdevice.h>
+#include <crypto/aes.h>
 #include "chcr_ktls.h"
 
 static LIST_HEAD(uld_ctx_list);
@@ -74,7 +75,7 @@ static int chcr_ktls_save_keys(struct chcr_ktls_info *tx_info,
 	unsigned char ghash_h[TLS_CIPHER_AES_GCM_256_TAG_SIZE];
 	struct tls12_crypto_info_aes_gcm_128 *info_128_gcm;
 	struct ktls_key_ctx *kctx = &tx_info->key_ctx;
-	struct crypto_cipher *cipher;
+	struct crypto_aes_ctx aes_ctx;
 	unsigned char *key, *salt;
 
 	switch (crypto_info->cipher_type) {
@@ -135,18 +136,14 @@ static int chcr_ktls_save_keys(struct chcr_ktls_info *tx_info,
 	/* Calculate the H = CIPH(K, 0 repeated 16 times).
 	 * It will go in key context
 	 */
-	cipher = crypto_alloc_cipher("aes", 0, 0);
-	if (IS_ERR(cipher)) {
-		ret = -ENOMEM;
-		goto out;
-	}
 
-	ret = crypto_cipher_setkey(cipher, key, keylen);
+	ret = aes_expandkey(&aes_ctx, key, keylen);
 	if (ret)
-		goto out1;
+		goto out;
 
 	memset(ghash_h, 0, ghash_size);
-	crypto_cipher_encrypt_one(cipher, ghash_h, ghash_h);
+	aes_encrypt(&aes_ctx, ghash_h, ghash_h);
+	memzero_explicit(&aes_ctx, sizeof(aes_ctx));
 
 	/* fill the Key context */
 	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
@@ -155,7 +152,7 @@ static int chcr_ktls_save_keys(struct chcr_ktls_info *tx_info,
 						 key_ctx_size >> 4);
 	} else {
 		ret = -EINVAL;
-		goto out1;
+		goto out;
 	}
 
 	memcpy(kctx->salt, salt, tx_info->salt_size);
@@ -163,8 +160,6 @@ static int chcr_ktls_save_keys(struct chcr_ktls_info *tx_info,
 	memcpy(kctx->key + keylen, ghash_h, ghash_size);
 	tx_info->key_ctx_len = key_ctx_size;
 
-out1:
-	crypto_free_cipher(cipher);
 out:
 	return ret;
 }
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 18dd7a4aaf7d..86f0748009af 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -189,45 +189,6 @@ static inline void *crypto_instance_ctx(struct crypto_instance *inst)
 	return inst->__ctx;
 }
 
-struct crypto_cipher_spawn {
-	struct crypto_spawn base;
-};
-
-static inline int crypto_grab_cipher(struct crypto_cipher_spawn *spawn,
-				     struct crypto_instance *inst,
-				     const char *name, u32 type, u32 mask)
-{
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_CIPHER;
-	mask |= CRYPTO_ALG_TYPE_MASK;
-	return crypto_grab_spawn(&spawn->base, inst, name, type, mask);
-}
-
-static inline void crypto_drop_cipher(struct crypto_cipher_spawn *spawn)
-{
-	crypto_drop_spawn(&spawn->base);
-}
-
-static inline struct crypto_alg *crypto_spawn_cipher_alg(
-	struct crypto_cipher_spawn *spawn)
-{
-	return spawn->base.alg;
-}
-
-static inline struct crypto_cipher *crypto_spawn_cipher(
-	struct crypto_cipher_spawn *spawn)
-{
-	u32 type = CRYPTO_ALG_TYPE_CIPHER;
-	u32 mask = CRYPTO_ALG_TYPE_MASK;
-
-	return __crypto_cipher_cast(crypto_spawn_tfm(&spawn->base, type, mask));
-}
-
-static inline struct cipher_alg *crypto_cipher_alg(struct crypto_cipher *tfm)
-{
-	return &crypto_cipher_tfm(tfm)->__crt_alg->cra_cipher;
-}
-
 static inline struct crypto_async_request *crypto_get_backlog(
 	struct crypto_queue *queue)
 {
diff --git a/include/crypto/blake2b.h b/include/crypto/blake2b.h
new file mode 100644
index 000000000000..18875f16f8ca
--- /dev/null
+++ b/include/crypto/blake2b.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+
+#ifndef _CRYPTO_BLAKE2B_H
+#define _CRYPTO_BLAKE2B_H
+
+#include <linux/bug.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+enum blake2b_lengths {
+	BLAKE2B_BLOCK_SIZE = 128,
+	BLAKE2B_HASH_SIZE = 64,
+	BLAKE2B_KEY_SIZE = 64,
+
+	BLAKE2B_160_HASH_SIZE = 20,
+	BLAKE2B_256_HASH_SIZE = 32,
+	BLAKE2B_384_HASH_SIZE = 48,
+	BLAKE2B_512_HASH_SIZE = 64,
+};
+
+struct blake2b_state {
+	/* 'h', 't', and 'f' are used in assembly code, so keep them as-is. */
+	u64 h[8];
+	u64 t[2];
+	u64 f[2];
+	u8 buf[BLAKE2B_BLOCK_SIZE];
+	unsigned int buflen;
+	unsigned int outlen;
+};
+
+enum blake2b_iv {
+	BLAKE2B_IV0 = 0x6A09E667F3BCC908ULL,
+	BLAKE2B_IV1 = 0xBB67AE8584CAA73BULL,
+	BLAKE2B_IV2 = 0x3C6EF372FE94F82BULL,
+	BLAKE2B_IV3 = 0xA54FF53A5F1D36F1ULL,
+	BLAKE2B_IV4 = 0x510E527FADE682D1ULL,
+	BLAKE2B_IV5 = 0x9B05688C2B3E6C1FULL,
+	BLAKE2B_IV6 = 0x1F83D9ABFB41BD6BULL,
+	BLAKE2B_IV7 = 0x5BE0CD19137E2179ULL,
+};
+
+static inline void __blake2b_init(struct blake2b_state *state, size_t outlen,
+				  const void *key, size_t keylen)
+{
+	state->h[0] = BLAKE2B_IV0 ^ (0x01010000 | keylen << 8 | outlen);
+	state->h[1] = BLAKE2B_IV1;
+	state->h[2] = BLAKE2B_IV2;
+	state->h[3] = BLAKE2B_IV3;
+	state->h[4] = BLAKE2B_IV4;
+	state->h[5] = BLAKE2B_IV5;
+	state->h[6] = BLAKE2B_IV6;
+	state->h[7] = BLAKE2B_IV7;
+	state->t[0] = 0;
+	state->t[1] = 0;
+	state->f[0] = 0;
+	state->f[1] = 0;
+	state->buflen = 0;
+	state->outlen = outlen;
+	if (keylen) {
+		memcpy(state->buf, key, keylen);
+		memset(&state->buf[keylen], 0, BLAKE2B_BLOCK_SIZE - keylen);
+		state->buflen = BLAKE2B_BLOCK_SIZE;
+	}
+}
+
+#endif /* _CRYPTO_BLAKE2B_H */
diff --git a/include/crypto/blake2s.h b/include/crypto/blake2s.h
index b471deac28ff..bc3fb59442ce 100644
--- a/include/crypto/blake2s.h
+++ b/include/crypto/blake2s.h
@@ -3,15 +3,14 @@
  * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  */
 
-#ifndef BLAKE2S_H
-#define BLAKE2S_H
+#ifndef _CRYPTO_BLAKE2S_H
+#define _CRYPTO_BLAKE2S_H
 
+#include <linux/bug.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 
-#include <asm/bug.h>
-
 enum blake2s_lengths {
 	BLAKE2S_BLOCK_SIZE = 64,
 	BLAKE2S_HASH_SIZE = 32,
@@ -24,6 +23,7 @@ enum blake2s_lengths {
 };
 
 struct blake2s_state {
+	/* 'h', 't', and 'f' are used in assembly code, so keep them as-is. */
 	u32 h[8];
 	u32 t[2];
 	u32 f[2];
@@ -43,29 +43,34 @@ enum blake2s_iv {
 	BLAKE2S_IV7 = 0x5BE0CD19UL,
 };
 
-void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen);
-void blake2s_final(struct blake2s_state *state, u8 *out);
-
-static inline void blake2s_init_param(struct blake2s_state *state,
-				      const u32 param)
+static inline void __blake2s_init(struct blake2s_state *state, size_t outlen,
+				  const void *key, size_t keylen)
 {
-	*state = (struct blake2s_state){{
-		BLAKE2S_IV0 ^ param,
-		BLAKE2S_IV1,
-		BLAKE2S_IV2,
-		BLAKE2S_IV3,
-		BLAKE2S_IV4,
-		BLAKE2S_IV5,
-		BLAKE2S_IV6,
-		BLAKE2S_IV7,
-	}};
+	state->h[0] = BLAKE2S_IV0 ^ (0x01010000 | keylen << 8 | outlen);
+	state->h[1] = BLAKE2S_IV1;
+	state->h[2] = BLAKE2S_IV2;
+	state->h[3] = BLAKE2S_IV3;
+	state->h[4] = BLAKE2S_IV4;
+	state->h[5] = BLAKE2S_IV5;
+	state->h[6] = BLAKE2S_IV6;
+	state->h[7] = BLAKE2S_IV7;
+	state->t[0] = 0;
+	state->t[1] = 0;
+	state->f[0] = 0;
+	state->f[1] = 0;
+	state->buflen = 0;
+	state->outlen = outlen;
+	if (keylen) {
+		memcpy(state->buf, key, keylen);
+		memset(&state->buf[keylen], 0, BLAKE2S_BLOCK_SIZE - keylen);
+		state->buflen = BLAKE2S_BLOCK_SIZE;
+	}
 }
 
 static inline void blake2s_init(struct blake2s_state *state,
 				const size_t outlen)
 {
-	blake2s_init_param(state, 0x01010000 | outlen);
-	state->outlen = outlen;
+	__blake2s_init(state, outlen, NULL, 0);
 }
 
 static inline void blake2s_init_key(struct blake2s_state *state,
@@ -75,12 +80,12 @@ static inline void blake2s_init_key(struct blake2s_state *state,
 	WARN_ON(IS_ENABLED(DEBUG) && (!outlen || outlen > BLAKE2S_HASH_SIZE ||
 		!key || !keylen || keylen > BLAKE2S_KEY_SIZE));
 
-	blake2s_init_param(state, 0x01010000 | keylen << 8 | outlen);
-	memcpy(state->buf, key, keylen);
-	state->buflen = BLAKE2S_BLOCK_SIZE;
-	state->outlen = outlen;
+	__blake2s_init(state, outlen, key, keylen);
 }
 
+void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen);
+void blake2s_final(struct blake2s_state *state, u8 *out);
+
 static inline void blake2s(u8 *out, const u8 *in, const u8 *key,
 			   const size_t outlen, const size_t inlen,
 			   const size_t keylen)
@@ -91,11 +96,7 @@ static inline void blake2s(u8 *out, const u8 *in, const u8 *key,
 		outlen > BLAKE2S_HASH_SIZE || keylen > BLAKE2S_KEY_SIZE ||
 		(!key && keylen)));
 
-	if (keylen)
-		blake2s_init_key(&state, outlen, key, keylen);
-	else
-		blake2s_init(&state, outlen);
-
+	__blake2s_init(&state, outlen, key, keylen);
 	blake2s_update(&state, in, inlen);
 	blake2s_final(&state, out);
 }
@@ -103,4 +104,4 @@ static inline void blake2s(u8 *out, const u8 *in, const u8 *key,
 void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen,
 		     const size_t keylen);
 
-#endif /* BLAKE2S_H */
+#endif /* _CRYPTO_BLAKE2S_H */
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index af2ff31ff619..13f8a6a54ca8 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -149,7 +149,7 @@ struct ahash_alg {
 
 struct shash_desc {
 	struct crypto_shash *tfm;
-	void *__ctx[] CRYPTO_MINALIGN_ATTR;
+	void *__ctx[] __aligned(ARCH_SLAB_MINALIGN);
 };
 
 #define HASH_MAX_DIGESTSIZE	 64
@@ -162,9 +162,9 @@ struct shash_desc {
 
 #define HASH_MAX_STATESIZE	512
 
-#define SHASH_DESC_ON_STACK(shash, ctx)				  \
-	char __##shash##_desc[sizeof(struct shash_desc) +	  \
-		HASH_MAX_DESCSIZE] CRYPTO_MINALIGN_ATTR; \
+#define SHASH_DESC_ON_STACK(shash, ctx)					     \
+	char __##shash##_desc[sizeof(struct shash_desc) + HASH_MAX_DESCSIZE] \
+		__aligned(__alignof__(struct shash_desc));		     \
 	struct shash_desc *shash = (struct shash_desc *)__##shash##_desc
 
 /**
diff --git a/include/crypto/internal/blake2b.h b/include/crypto/internal/blake2b.h
new file mode 100644
index 000000000000..982fe5e8471c
--- /dev/null
+++ b/include/crypto/internal/blake2b.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Helper functions for BLAKE2b implementations.
+ * Keep this in sync with the corresponding BLAKE2s header.
+ */
+
+#ifndef _CRYPTO_INTERNAL_BLAKE2B_H
+#define _CRYPTO_INTERNAL_BLAKE2B_H
+
+#include <crypto/blake2b.h>
+#include <crypto/internal/hash.h>
+#include <linux/string.h>
+
+void blake2b_compress_generic(struct blake2b_state *state,
+			      const u8 *block, size_t nblocks, u32 inc);
+
+static inline void blake2b_set_lastblock(struct blake2b_state *state)
+{
+	state->f[0] = -1;
+}
+
+typedef void (*blake2b_compress_t)(struct blake2b_state *state,
+				   const u8 *block, size_t nblocks, u32 inc);
+
+static inline void __blake2b_update(struct blake2b_state *state,
+				    const u8 *in, size_t inlen,
+				    blake2b_compress_t compress)
+{
+	const size_t fill = BLAKE2B_BLOCK_SIZE - state->buflen;
+
+	if (unlikely(!inlen))
+		return;
+	if (inlen > fill) {
+		memcpy(state->buf + state->buflen, in, fill);
+		(*compress)(state, state->buf, 1, BLAKE2B_BLOCK_SIZE);
+		state->buflen = 0;
+		in += fill;
+		inlen -= fill;
+	}
+	if (inlen > BLAKE2B_BLOCK_SIZE) {
+		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2B_BLOCK_SIZE);
+		/* Hash one less (full) block than strictly possible */
+		(*compress)(state, in, nblocks - 1, BLAKE2B_BLOCK_SIZE);
+		in += BLAKE2B_BLOCK_SIZE * (nblocks - 1);
+		inlen -= BLAKE2B_BLOCK_SIZE * (nblocks - 1);
+	}
+	memcpy(state->buf + state->buflen, in, inlen);
+	state->buflen += inlen;
+}
+
+static inline void __blake2b_final(struct blake2b_state *state, u8 *out,
+				   blake2b_compress_t compress)
+{
+	int i;
+
+	blake2b_set_lastblock(state);
+	memset(state->buf + state->buflen, 0,
+	       BLAKE2B_BLOCK_SIZE - state->buflen); /* Padding */
+	(*compress)(state, state->buf, 1, state->buflen);
+	for (i = 0; i < ARRAY_SIZE(state->h); i++)
+		__cpu_to_le64s(&state->h[i]);
+	memcpy(out, state->h, state->outlen);
+}
+
+/* Helper functions for shash implementations of BLAKE2b */
+
+struct blake2b_tfm_ctx {
+	u8 key[BLAKE2B_KEY_SIZE];
+	unsigned int keylen;
+};
+
+static inline int crypto_blake2b_setkey(struct crypto_shash *tfm,
+					const u8 *key, unsigned int keylen)
+{
+	struct blake2b_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+
+	if (keylen == 0 || keylen > BLAKE2B_KEY_SIZE)
+		return -EINVAL;
+
+	memcpy(tctx->key, key, keylen);
+	tctx->keylen = keylen;
+
+	return 0;
+}
+
+static inline int crypto_blake2b_init(struct shash_desc *desc)
+{
+	const struct blake2b_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct blake2b_state *state = shash_desc_ctx(desc);
+	unsigned int outlen = crypto_shash_digestsize(desc->tfm);
+
+	__blake2b_init(state, outlen, tctx->key, tctx->keylen);
+	return 0;
+}
+
+static inline int crypto_blake2b_update(struct shash_desc *desc,
+					const u8 *in, unsigned int inlen,
+					blake2b_compress_t compress)
+{
+	struct blake2b_state *state = shash_desc_ctx(desc);
+
+	__blake2b_update(state, in, inlen, compress);
+	return 0;
+}
+
+static inline int crypto_blake2b_final(struct shash_desc *desc, u8 *out,
+				       blake2b_compress_t compress)
+{
+	struct blake2b_state *state = shash_desc_ctx(desc);
+
+	__blake2b_final(state, out, compress);
+	return 0;
+}
+
+#endif /* _CRYPTO_INTERNAL_BLAKE2B_H */
diff --git a/include/crypto/internal/blake2s.h b/include/crypto/internal/blake2s.h
index 6e376ae6b6b5..8e50d487500f 100644
--- a/include/crypto/internal/blake2s.h
+++ b/include/crypto/internal/blake2s.h
@@ -1,14 +1,15 @@
 /* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Helper functions for BLAKE2s implementations.
+ * Keep this in sync with the corresponding BLAKE2b header.
+ */
 
-#ifndef BLAKE2S_INTERNAL_H
-#define BLAKE2S_INTERNAL_H
+#ifndef _CRYPTO_INTERNAL_BLAKE2S_H
+#define _CRYPTO_INTERNAL_BLAKE2S_H
 
 #include <crypto/blake2s.h>
-
-struct blake2s_tfm_ctx {
-	u8 key[BLAKE2S_KEY_SIZE];
-	unsigned int keylen;
-};
+#include <crypto/internal/hash.h>
+#include <linux/string.h>
 
 void blake2s_compress_generic(struct blake2s_state *state,const u8 *block,
 			      size_t nblocks, const u32 inc);
@@ -23,4 +24,96 @@ static inline void blake2s_set_lastblock(struct blake2s_state *state)
 	state->f[0] = -1;
 }
 
-#endif /* BLAKE2S_INTERNAL_H */
+typedef void (*blake2s_compress_t)(struct blake2s_state *state,
+				   const u8 *block, size_t nblocks, u32 inc);
+
+/* Helper functions for BLAKE2s shared by the library and shash APIs */
+
+static inline void __blake2s_update(struct blake2s_state *state,
+				    const u8 *in, size_t inlen,
+				    blake2s_compress_t compress)
+{
+	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
+
+	if (unlikely(!inlen))
+		return;
+	if (inlen > fill) {
+		memcpy(state->buf + state->buflen, in, fill);
+		(*compress)(state, state->buf, 1, BLAKE2S_BLOCK_SIZE);
+		state->buflen = 0;
+		in += fill;
+		inlen -= fill;
+	}
+	if (inlen > BLAKE2S_BLOCK_SIZE) {
+		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
+		/* Hash one less (full) block than strictly possible */
+		(*compress)(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE);
+		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+	}
+	memcpy(state->buf + state->buflen, in, inlen);
+	state->buflen += inlen;
+}
+
+static inline void __blake2s_final(struct blake2s_state *state, u8 *out,
+				   blake2s_compress_t compress)
+{
+	blake2s_set_lastblock(state);
+	memset(state->buf + state->buflen, 0,
+	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
+	(*compress)(state, state->buf, 1, state->buflen);
+	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
+	memcpy(out, state->h, state->outlen);
+}
+
+/* Helper functions for shash implementations of BLAKE2s */
+
+struct blake2s_tfm_ctx {
+	u8 key[BLAKE2S_KEY_SIZE];
+	unsigned int keylen;
+};
+
+static inline int crypto_blake2s_setkey(struct crypto_shash *tfm,
+					const u8 *key, unsigned int keylen)
+{
+	struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+
+	if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE)
+		return -EINVAL;
+
+	memcpy(tctx->key, key, keylen);
+	tctx->keylen = keylen;
+
+	return 0;
+}
+
+static inline int crypto_blake2s_init(struct shash_desc *desc)
+{
+	const struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct blake2s_state *state = shash_desc_ctx(desc);
+	unsigned int outlen = crypto_shash_digestsize(desc->tfm);
+
+	__blake2s_init(state, outlen, tctx->key, tctx->keylen);
+	return 0;
+}
+
+static inline int crypto_blake2s_update(struct shash_desc *desc,
+					const u8 *in, unsigned int inlen,
+					blake2s_compress_t compress)
+{
+	struct blake2s_state *state = shash_desc_ctx(desc);
+
+	__blake2s_update(state, in, inlen, compress);
+	return 0;
+}
+
+static inline int crypto_blake2s_final(struct shash_desc *desc, u8 *out,
+				       blake2s_compress_t compress)
+{
+	struct blake2s_state *state = shash_desc_ctx(desc);
+
+	__blake2s_final(state, out, compress);
+	return 0;
+}
+
+#endif /* _CRYPTO_INTERNAL_BLAKE2S_H */
diff --git a/include/crypto/internal/cipher.h b/include/crypto/internal/cipher.h
new file mode 100644
index 000000000000..a9174ba90250
--- /dev/null
+++ b/include/crypto/internal/cipher.h
@@ -0,0 +1,218 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
+ * Copyright (c) 2002 David S. Miller (davem@redhat.com)
+ * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * Portions derived from Cryptoapi, by Alexander Kjeldaas <astor@fast.no>
+ * and Nettle, by Niels Möller.
+ */
+
+#ifndef _CRYPTO_INTERNAL_CIPHER_H
+#define _CRYPTO_INTERNAL_CIPHER_H
+
+#include <crypto/algapi.h>
+
+struct crypto_cipher {
+	struct crypto_tfm base;
+};
+
+/**
+ * DOC: Single Block Cipher API
+ *
+ * The single block cipher API is used with the ciphers of type
+ * CRYPTO_ALG_TYPE_CIPHER (listed as type "cipher" in /proc/crypto).
+ *
+ * Using the single block cipher API calls, operations with the basic cipher
+ * primitive can be implemented. These cipher primitives exclude any block
+ * chaining operations including IV handling.
+ *
+ * The purpose of this single block cipher API is to support the implementation
+ * of templates or other concepts that only need to perform the cipher operation
+ * on one block at a time. Templates invoke the underlying cipher primitive
+ * block-wise and process either the input or the output data of these cipher
+ * operations.
+ */
+
+static inline struct crypto_cipher *__crypto_cipher_cast(struct crypto_tfm *tfm)
+{
+	return (struct crypto_cipher *)tfm;
+}
+
+/**
+ * crypto_alloc_cipher() - allocate single block cipher handle
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	     single block cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Allocate a cipher handle for a single block cipher. The returned struct
+ * crypto_cipher is the cipher handle that is required for any subsequent API
+ * invocation for that single block cipher.
+ *
+ * Return: allocated cipher handle in case of success; IS_ERR() is true in case
+ *	   of an error, PTR_ERR() returns the error code.
+ */
+static inline struct crypto_cipher *crypto_alloc_cipher(const char *alg_name,
+							u32 type, u32 mask)
+{
+	type &= ~CRYPTO_ALG_TYPE_MASK;
+	type |= CRYPTO_ALG_TYPE_CIPHER;
+	mask |= CRYPTO_ALG_TYPE_MASK;
+
+	return __crypto_cipher_cast(crypto_alloc_base(alg_name, type, mask));
+}
+
+static inline struct crypto_tfm *crypto_cipher_tfm(struct crypto_cipher *tfm)
+{
+	return &tfm->base;
+}
+
+/**
+ * crypto_free_cipher() - zeroize and free the single block cipher handle
+ * @tfm: cipher handle to be freed
+ */
+static inline void crypto_free_cipher(struct crypto_cipher *tfm)
+{
+	crypto_free_tfm(crypto_cipher_tfm(tfm));
+}
+
+/**
+ * crypto_has_cipher() - Search for the availability of a single block cipher
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	     single block cipher
+ * @type: specifies the type of the cipher
+ * @mask: specifies the mask for the cipher
+ *
+ * Return: true when the single block cipher is known to the kernel crypto API;
+ *	   false otherwise
+ */
+static inline int crypto_has_cipher(const char *alg_name, u32 type, u32 mask)
+{
+	type &= ~CRYPTO_ALG_TYPE_MASK;
+	type |= CRYPTO_ALG_TYPE_CIPHER;
+	mask |= CRYPTO_ALG_TYPE_MASK;
+
+	return crypto_has_alg(alg_name, type, mask);
+}
+
+/**
+ * crypto_cipher_blocksize() - obtain block size for cipher
+ * @tfm: cipher handle
+ *
+ * The block size for the single block cipher referenced with the cipher handle
+ * tfm is returned. The caller may use that information to allocate appropriate
+ * memory for the data returned by the encryption or decryption operation
+ *
+ * Return: block size of cipher
+ */
+static inline unsigned int crypto_cipher_blocksize(struct crypto_cipher *tfm)
+{
+	return crypto_tfm_alg_blocksize(crypto_cipher_tfm(tfm));
+}
+
+static inline unsigned int crypto_cipher_alignmask(struct crypto_cipher *tfm)
+{
+	return crypto_tfm_alg_alignmask(crypto_cipher_tfm(tfm));
+}
+
+static inline u32 crypto_cipher_get_flags(struct crypto_cipher *tfm)
+{
+	return crypto_tfm_get_flags(crypto_cipher_tfm(tfm));
+}
+
+static inline void crypto_cipher_set_flags(struct crypto_cipher *tfm,
+					   u32 flags)
+{
+	crypto_tfm_set_flags(crypto_cipher_tfm(tfm), flags);
+}
+
+static inline void crypto_cipher_clear_flags(struct crypto_cipher *tfm,
+					     u32 flags)
+{
+	crypto_tfm_clear_flags(crypto_cipher_tfm(tfm), flags);
+}
+
+/**
+ * crypto_cipher_setkey() - set key for cipher
+ * @tfm: cipher handle
+ * @key: buffer holding the key
+ * @keylen: length of the key in bytes
+ *
+ * The caller provided key is set for the single block cipher referenced by the
+ * cipher handle.
+ *
+ * Note, the key length determines the cipher type. Many block ciphers implement
+ * different cipher modes depending on the key size, such as AES-128 vs AES-192
+ * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128
+ * is performed.
+ *
+ * Return: 0 if the setting of the key was successful; < 0 if an error occurred
+ */
+int crypto_cipher_setkey(struct crypto_cipher *tfm,
+			 const u8 *key, unsigned int keylen);
+
+/**
+ * crypto_cipher_encrypt_one() - encrypt one block of plaintext
+ * @tfm: cipher handle
+ * @dst: points to the buffer that will be filled with the ciphertext
+ * @src: buffer holding the plaintext to be encrypted
+ *
+ * Invoke the encryption operation of one block. The caller must ensure that
+ * the plaintext and ciphertext buffers are at least one block in size.
+ */
+void crypto_cipher_encrypt_one(struct crypto_cipher *tfm,
+			       u8 *dst, const u8 *src);
+
+/**
+ * crypto_cipher_decrypt_one() - decrypt one block of ciphertext
+ * @tfm: cipher handle
+ * @dst: points to the buffer that will be filled with the plaintext
+ * @src: buffer holding the ciphertext to be decrypted
+ *
+ * Invoke the decryption operation of one block. The caller must ensure that
+ * the plaintext and ciphertext buffers are at least one block in size.
+ */
+void crypto_cipher_decrypt_one(struct crypto_cipher *tfm,
+			       u8 *dst, const u8 *src);
+
+struct crypto_cipher_spawn {
+	struct crypto_spawn base;
+};
+
+static inline int crypto_grab_cipher(struct crypto_cipher_spawn *spawn,
+				     struct crypto_instance *inst,
+				     const char *name, u32 type, u32 mask)
+{
+	type &= ~CRYPTO_ALG_TYPE_MASK;
+	type |= CRYPTO_ALG_TYPE_CIPHER;
+	mask |= CRYPTO_ALG_TYPE_MASK;
+	return crypto_grab_spawn(&spawn->base, inst, name, type, mask);
+}
+
+static inline void crypto_drop_cipher(struct crypto_cipher_spawn *spawn)
+{
+	crypto_drop_spawn(&spawn->base);
+}
+
+static inline struct crypto_alg *crypto_spawn_cipher_alg(
+       struct crypto_cipher_spawn *spawn)
+{
+	return spawn->base.alg;
+}
+
+static inline struct crypto_cipher *crypto_spawn_cipher(
+	struct crypto_cipher_spawn *spawn)
+{
+	u32 type = CRYPTO_ALG_TYPE_CIPHER;
+	u32 mask = CRYPTO_ALG_TYPE_MASK;
+
+	return __crypto_cipher_cast(crypto_spawn_tfm(&spawn->base, type, mask));
+}
+
+static inline struct cipher_alg *crypto_cipher_alg(struct crypto_cipher *tfm)
+{
+	return &crypto_cipher_tfm(tfm)->__crt_alg->cra_cipher;
+}
+
+#endif
diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h
index 10226c12c5df..a2339f80a615 100644
--- a/include/crypto/internal/skcipher.h
+++ b/include/crypto/internal/skcipher.h
@@ -9,6 +9,7 @@
 #define _CRYPTO_INTERNAL_SKCIPHER_H
 
 #include <crypto/algapi.h>
+#include <crypto/internal/cipher.h>
 #include <crypto/skcipher.h>
 #include <linux/list.h>
 #include <linux/types.h>
@@ -132,7 +133,6 @@ int skcipher_walk_done(struct skcipher_walk *walk, int err);
 int skcipher_walk_virt(struct skcipher_walk *walk,
 		       struct skcipher_request *req,
 		       bool atomic);
-void skcipher_walk_atomise(struct skcipher_walk *walk);
 int skcipher_walk_async(struct skcipher_walk *walk,
 			struct skcipher_request *req);
 int skcipher_walk_aead_encrypt(struct skcipher_walk *walk,
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index ef90e07c9635..da5e0d74bb2f 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -151,9 +151,12 @@
  * The macro CRYPTO_MINALIGN_ATTR (along with the void * type in the actual
  * declaration) is used to ensure that the crypto_tfm context structure is
  * aligned correctly for the given architecture so that there are no alignment
- * faults for C data types.  In particular, this is required on platforms such
- * as arm where pointers are 32-bit aligned but there are data types such as
- * u64 which require 64-bit alignment.
+ * faults for C data types.  On architectures that support non-cache coherent
+ * DMA, such as ARM or arm64, it also takes into account the minimal alignment
+ * that is required to ensure that the context struct member does not share any
+ * cachelines with the rest of the struct. This is needed to ensure that cache
+ * maintenance for non-coherent DMA (cache invalidation in particular) does not
+ * affect data that may be accessed by the CPU concurrently.
  */
 #define CRYPTO_MINALIGN ARCH_KMALLOC_MINALIGN
 
@@ -636,10 +639,6 @@ struct crypto_tfm {
 	void *__crt_ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
-struct crypto_cipher {
-	struct crypto_tfm base;
-};
-
 struct crypto_comp {
 	struct crypto_tfm base;
 };
@@ -743,165 +742,6 @@ static inline unsigned int crypto_tfm_ctx_alignment(void)
 	return __alignof__(tfm->__crt_ctx);
 }
 
-/**
- * DOC: Single Block Cipher API
- *
- * The single block cipher API is used with the ciphers of type
- * CRYPTO_ALG_TYPE_CIPHER (listed as type "cipher" in /proc/crypto).
- *
- * Using the single block cipher API calls, operations with the basic cipher
- * primitive can be implemented. These cipher primitives exclude any block
- * chaining operations including IV handling.
- *
- * The purpose of this single block cipher API is to support the implementation
- * of templates or other concepts that only need to perform the cipher operation
- * on one block at a time. Templates invoke the underlying cipher primitive
- * block-wise and process either the input or the output data of these cipher
- * operations.
- */
-
-static inline struct crypto_cipher *__crypto_cipher_cast(struct crypto_tfm *tfm)
-{
-	return (struct crypto_cipher *)tfm;
-}
-
-/**
- * crypto_alloc_cipher() - allocate single block cipher handle
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	     single block cipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Allocate a cipher handle for a single block cipher. The returned struct
- * crypto_cipher is the cipher handle that is required for any subsequent API
- * invocation for that single block cipher.
- *
- * Return: allocated cipher handle in case of success; IS_ERR() is true in case
- *	   of an error, PTR_ERR() returns the error code.
- */
-static inline struct crypto_cipher *crypto_alloc_cipher(const char *alg_name,
-							u32 type, u32 mask)
-{
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_CIPHER;
-	mask |= CRYPTO_ALG_TYPE_MASK;
-
-	return __crypto_cipher_cast(crypto_alloc_base(alg_name, type, mask));
-}
-
-static inline struct crypto_tfm *crypto_cipher_tfm(struct crypto_cipher *tfm)
-{
-	return &tfm->base;
-}
-
-/**
- * crypto_free_cipher() - zeroize and free the single block cipher handle
- * @tfm: cipher handle to be freed
- */
-static inline void crypto_free_cipher(struct crypto_cipher *tfm)
-{
-	crypto_free_tfm(crypto_cipher_tfm(tfm));
-}
-
-/**
- * crypto_has_cipher() - Search for the availability of a single block cipher
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	     single block cipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Return: true when the single block cipher is known to the kernel crypto API;
- *	   false otherwise
- */
-static inline int crypto_has_cipher(const char *alg_name, u32 type, u32 mask)
-{
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_CIPHER;
-	mask |= CRYPTO_ALG_TYPE_MASK;
-
-	return crypto_has_alg(alg_name, type, mask);
-}
-
-/**
- * crypto_cipher_blocksize() - obtain block size for cipher
- * @tfm: cipher handle
- *
- * The block size for the single block cipher referenced with the cipher handle
- * tfm is returned. The caller may use that information to allocate appropriate
- * memory for the data returned by the encryption or decryption operation
- *
- * Return: block size of cipher
- */
-static inline unsigned int crypto_cipher_blocksize(struct crypto_cipher *tfm)
-{
-	return crypto_tfm_alg_blocksize(crypto_cipher_tfm(tfm));
-}
-
-static inline unsigned int crypto_cipher_alignmask(struct crypto_cipher *tfm)
-{
-	return crypto_tfm_alg_alignmask(crypto_cipher_tfm(tfm));
-}
-
-static inline u32 crypto_cipher_get_flags(struct crypto_cipher *tfm)
-{
-	return crypto_tfm_get_flags(crypto_cipher_tfm(tfm));
-}
-
-static inline void crypto_cipher_set_flags(struct crypto_cipher *tfm,
-					   u32 flags)
-{
-	crypto_tfm_set_flags(crypto_cipher_tfm(tfm), flags);
-}
-
-static inline void crypto_cipher_clear_flags(struct crypto_cipher *tfm,
-					     u32 flags)
-{
-	crypto_tfm_clear_flags(crypto_cipher_tfm(tfm), flags);
-}
-
-/**
- * crypto_cipher_setkey() - set key for cipher
- * @tfm: cipher handle
- * @key: buffer holding the key
- * @keylen: length of the key in bytes
- *
- * The caller provided key is set for the single block cipher referenced by the
- * cipher handle.
- *
- * Note, the key length determines the cipher type. Many block ciphers implement
- * different cipher modes depending on the key size, such as AES-128 vs AES-192
- * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128
- * is performed.
- *
- * Return: 0 if the setting of the key was successful; < 0 if an error occurred
- */
-int crypto_cipher_setkey(struct crypto_cipher *tfm,
-			 const u8 *key, unsigned int keylen);
-
-/**
- * crypto_cipher_encrypt_one() - encrypt one block of plaintext
- * @tfm: cipher handle
- * @dst: points to the buffer that will be filled with the ciphertext
- * @src: buffer holding the plaintext to be encrypted
- *
- * Invoke the encryption operation of one block. The caller must ensure that
- * the plaintext and ciphertext buffers are at least one block in size.
- */
-void crypto_cipher_encrypt_one(struct crypto_cipher *tfm,
-			       u8 *dst, const u8 *src);
-
-/**
- * crypto_cipher_decrypt_one() - decrypt one block of ciphertext
- * @tfm: cipher handle
- * @dst: points to the buffer that will be filled with the plaintext
- * @src: buffer holding the ciphertext to be decrypted
- *
- * Invoke the decryption operation of one block. The caller must ensure that
- * the plaintext and ciphertext buffers are at least one block in size.
- */
-void crypto_cipher_decrypt_one(struct crypto_cipher *tfm,
-			       u8 *dst, const u8 *src);
-
 static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm)
 {
 	return (struct crypto_comp *)tfm;
diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c
index 6a4b6b78d630..c64ac8bfb6a9 100644
--- a/lib/crypto/blake2s.c
+++ b/lib/crypto/blake2s.c
@@ -15,55 +15,23 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/bug.h>
-#include <asm/unaligned.h>
+
+#if IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S)
+#  define blake2s_compress blake2s_compress_arch
+#else
+#  define blake2s_compress blake2s_compress_generic
+#endif
 
 void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen)
 {
-	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
-
-	if (unlikely(!inlen))
-		return;
-	if (inlen > fill) {
-		memcpy(state->buf + state->buflen, in, fill);
-		if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S))
-			blake2s_compress_arch(state, state->buf, 1,
-					      BLAKE2S_BLOCK_SIZE);
-		else
-			blake2s_compress_generic(state, state->buf, 1,
-						 BLAKE2S_BLOCK_SIZE);
-		state->buflen = 0;
-		in += fill;
-		inlen -= fill;
-	}
-	if (inlen > BLAKE2S_BLOCK_SIZE) {
-		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
-		/* Hash one less (full) block than strictly possible */
-		if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S))
-			blake2s_compress_arch(state, in, nblocks - 1,
-					      BLAKE2S_BLOCK_SIZE);
-		else
-			blake2s_compress_generic(state, in, nblocks - 1,
-						 BLAKE2S_BLOCK_SIZE);
-		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
-		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
-	}
-	memcpy(state->buf + state->buflen, in, inlen);
-	state->buflen += inlen;
+	__blake2s_update(state, in, inlen, blake2s_compress);
 }
 EXPORT_SYMBOL(blake2s_update);
 
 void blake2s_final(struct blake2s_state *state, u8 *out)
 {
 	WARN_ON(IS_ENABLED(DEBUG) && !out);
-	blake2s_set_lastblock(state);
-	memset(state->buf + state->buflen, 0,
-	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
-	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S))
-		blake2s_compress_arch(state, state->buf, 1, state->buflen);
-	else
-		blake2s_compress_generic(state, state->buf, 1, state->buflen);
-	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
-	memcpy(out, state->h, state->outlen);
+	__blake2s_final(state, out, blake2s_compress);
 	memzero_explicit(state, sizeof(*state));
 }
 EXPORT_SYMBOL(blake2s_final);
diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c
index 5850f3b87359..c2fcdb98cc02 100644
--- a/lib/crypto/chacha20poly1305.c
+++ b/lib/crypto/chacha20poly1305.c
@@ -362,7 +362,12 @@ static int __init mod_init(void)
 	return 0;
 }
 
+static void __exit mod_exit(void)
+{
+}
+
 module_init(mod_init);
+module_exit(mod_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("ChaCha20Poly1305 AEAD construction");
 MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
author	Linus Torvalds <torvalds@linux-foundation.org>	2021-02-22 04:23:56 +0300
committer	Linus Torvalds <torvalds@linux-foundation.org>	2021-02-22 04:23:56 +0300
commit	31caf8b2a847214be856f843e251fc2ed2cd1075 (patch)
tree	245257387cfcae352fae27b1ca824daab55472ba
parent	a2b095e0efa7229a1a88602283ba1a8a32004851 (diff)
parent	0de9dc80625b0ca1cb9730c5ed1c5a8cab538369 (diff)
download	linux-31caf8b2a847214be856f843e251fc2ed2cd1075.tar.xz